diff options
Diffstat (limited to 'tools')
220 files changed, 5993 insertions, 1308 deletions
diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 60a89dba01b6..60a89dba01b6 100644 --- a/tools/arch/x86/include/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index 4205ed4158bf..cb52a3a8b8fc 100644 --- a/tools/arch/x86/include/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -1,7 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NR_userfaultfd -#define __NR_userfaultfd 282 -#endif #ifndef __NR_perf_event_open # define __NR_perf_event_open 298 #endif diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index c41f95815480..797699462cd8 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -37,10 +37,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 7f36385aa9e2..ade44577688e 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ switch (id) { case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: case BPF_FUNC_probe_write_user: if (!full_mode) continue; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index e3ec47a6a612..cc835859465b 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -803,7 +803,10 @@ static int do_skeleton(int argc, char **argv) } \n\ \n\ err = %1$s__create_skeleton(obj); \n\ - err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ if (err) \n\ goto err_out; \n\ \n\ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e9785f1064a..6fc59d61937a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid @@ -4898,6 +4899,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5088,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index b0bf56c5f120..5a5bd74f55bd 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -742,7 +742,7 @@ class DebugfsProvider(Provider): The fields are all available KVM debugfs files """ - exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns'] + exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns', 'halt_wait_ns'] fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2] if field not in exempt_list] diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index b9987c3efa3c..963b1060d944 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -14,14 +14,6 @@ #define __type(name, val) typeof(val) *name #define __array(name, val) typeof(val) *name[] -/* Helper macro to print out debug messages */ -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names @@ -224,4 +216,47 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + +#define __bpf_printk(fmt, ...) \ +({ \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + #endif diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 8df718a6b142..80087b13877f 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -5,6 +5,7 @@ #include <string.h> #include <errno.h> #include <linux/filter.h> +#include <sys/param.h> #include "btf.h" #include "bpf.h" #include "libbpf.h" @@ -135,13 +136,17 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) static int add_data(struct bpf_gen *gen, const void *data, __u32 size) { + __u32 size8 = roundup(size, 8); + __u64 zero = 0; void *prev; - if (realloc_data_buf(gen, size)) + if (realloc_data_buf(gen, size8)) return 0; prev = gen->data_cur; memcpy(gen->data_cur, data, size); gen->data_cur += size; + memcpy(gen->data_cur, &zero, size8 - size); + gen->data_cur += size8 - size; return prev - gen->data_start; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index da65a1666a5e..8892f2f1bbcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -220,17 +220,40 @@ struct reloc_desc { struct bpf_sec_def; -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog); +typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); +typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie); +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); + +/* stored as sec_def->cookie for all libbpf-supported SEC()s */ +enum sec_def_flags { + SEC_NONE = 0, + /* expected_attach_type is optional, if kernel doesn't support that */ + SEC_EXP_ATTACH_OPT = 1, + /* legacy, only used by libbpf_get_type_names() and + * libbpf_attach_type_by_name(), not used by libbpf itself at all. + * This used to be associated with cgroup (and few other) BPF programs + * that were attachable through BPF_PROG_ATTACH command. Pretty + * meaningless nowadays, though. + */ + SEC_ATTACHABLE = 2, + SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT, + /* attachment target is specified through BTF ID in either kernel or + * other BPF program's BTF object */ + SEC_ATTACH_BTF = 4, + /* BPF program type allows sleeping/blocking in kernel */ + SEC_SLEEPABLE = 8, + /* allow non-strict prefix matching */ + SEC_SLOPPY_PFX = 16, +}; struct bpf_sec_def { const char *sec; - size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - bool is_exp_attach_type_optional; - bool is_attachable; - bool is_attach_btf; - bool is_sleepable; + long cookie; + + init_fn_t init_fn; + preload_fn_t preload_fn; attach_fn_t attach_fn; }; @@ -1665,7 +1688,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, void *ext_val; __u64 num; - if (strncmp(buf, "CONFIG_", 7)) + if (!str_has_pfx(buf, "CONFIG_")) return 0; sep = strchr(buf, '='); @@ -1845,6 +1868,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; nr_maps++; } /* Assume equally sized map definitions */ @@ -1869,6 +1894,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -1881,8 +1908,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } - if (GELF_ST_TYPE(sym.st_info) == STT_SECTION - || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + if (GELF_ST_BIND(sym.st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; } @@ -2913,7 +2939,7 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) static bool is_sec_name_dwarf(const char *name) { /* approximation, but the actual list is too long */ - return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; + return str_has_pfx(name, ".debug_"); } static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) @@ -2935,7 +2961,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) if (is_sec_name_dwarf(name)) return true; - if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + if (str_has_pfx(name, ".rel")) { name += sizeof(".rel") - 1; /* DWARF section relocations */ if (is_sec_name_dwarf(name)) @@ -4643,6 +4669,30 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.inner_map_fd = map->inner_map_fd; } + switch (def->type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + default: + break; + } + if (obj->gen_loader) { bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. @@ -6094,6 +6144,48 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program return 0; } +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id); + +/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ +static int libbpf_preload_prog(struct bpf_program *prog, + struct bpf_prog_load_params *attr, long cookie) +{ + enum sec_def_flags def = cookie; + + /* old kernels might not support specifying expected_attach_type */ + if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + attr->expected_attach_type = 0; + + if (def & SEC_SLEEPABLE) + attr->prog_flags |= BPF_F_SLEEPABLE; + + if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { + int btf_obj_fd = 0, btf_type_id = 0, err; + const char *attach_name; + + attach_name = strchr(prog->sec_name, '/') + 1; + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + /* cache resolved BTF FD and BTF type ID in the prog */ + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; + + /* but by now libbpf common logic is not utilizing + * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because + * this callback is called after attrs were populated by + * libbpf, so this callback has to update attr explicitly here + */ + attr->attach_btf_obj_fd = btf_obj_fd; + attr->attach_btf_id = btf_type_id; + } + return 0; +} + static int load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *license, __u32 kern_version, int *pfd) @@ -6102,7 +6194,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL; - int btf_fd, ret; + int btf_fd, ret, err; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6118,22 +6210,15 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, return -EINVAL; load_attr.prog_type = prog->type; - /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && - prog->sec_def->is_exp_attach_type_optional) - load_attr.expected_attach_type = 0; - else - load_attr.expected_attach_type = prog->expected_attach_type; + load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(prog->obj, FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insn_cnt = insns_cnt; load_attr.license = license; load_attr.attach_btf_id = prog->attach_btf_id; - if (prog->attach_prog_fd) - load_attr.attach_prog_fd = prog->attach_prog_fd; - else - load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; @@ -6152,6 +6237,16 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; + /* adjust load_attr if sec_def provides custom preload callback */ + if (prog->sec_def && prog->sec_def->preload_fn) { + err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to prepare load attributes: %d\n", + prog->name, err); + return err; + } + } + if (prog->obj->gen_loader) { bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, prog - prog->obj->programs); @@ -6267,8 +6362,6 @@ static int bpf_program__record_externs(struct bpf_program *prog) return 0; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); - int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { int err = 0, fd, i; @@ -6278,19 +6371,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) return libbpf_err(-EINVAL); } - if ((prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { - int btf_obj_fd = 0, btf_type_id = 0; - - err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); - if (err) - return libbpf_err(err); - - prog->attach_btf_obj_fd = btf_obj_fd; - prog->attach_btf_id = btf_type_id; - } - if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { pr_warn("Internal error: can't load program '%s'\n", @@ -6400,6 +6480,7 @@ static const struct bpf_sec_def *find_sec_def(const char *sec_name); static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) { struct bpf_program *prog; + int err; bpf_object__for_each_program(prog, obj) { prog->sec_def = find_sec_def(prog->sec_name); @@ -6410,8 +6491,6 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object continue; } - if (prog->sec_def->is_sleepable) - prog->prog_flags |= BPF_F_SLEEPABLE; bpf_program__set_type(prog, prog->sec_def->prog_type); bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); @@ -6421,6 +6500,18 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); #pragma GCC diagnostic pop + + /* sec_def can have custom callback which should be called + * after bpf_program is initialized to adjust its properties + */ + if (prog->sec_def->init_fn) { + err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to initialize: %d\n", + prog->name, err); + return err; + } + } } return 0; @@ -6847,8 +6938,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, if (err) return err; pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); - } else if (ext->type == EXT_KCFG && - strncmp(ext->name, "CONFIG_", 7) == 0) { + } else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) { need_config = true; } else if (ext->type == EXT_KSYM) { if (ext->ksym.type_id) @@ -6934,7 +7024,8 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) if (obj->gen_loader) { /* reset FDs */ - btf__set_fd(obj->btf, -1); + if (obj->btf) + btf__set_fd(obj->btf, -1); for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) @@ -7908,217 +7999,143 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ - attachable, attach_btf) \ - { \ - .sec = string, \ - .len = sizeof(string) - 1, \ - .prog_type = ptype, \ - .expected_attach_type = eatype, \ - .is_exp_attach_type_optional = eatype_optional, \ - .is_attachable = attachable, \ - .is_attach_btf = attach_btf, \ - } - -/* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) - -/* Programs that can be attached. */ -#define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) - -/* Programs that must specify expected attach type at load time. */ -#define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) - -/* Programs that use BTF to identify attach point */ -#define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) - -/* Programs that can be attached but attach type can't be identified by section - * name. Kept for backward compatibility. - */ -#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) - -#define SEC_DEF(sec_pfx, ptype, ...) { \ +#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = sec_pfx, \ - .len = sizeof(sec_pfx) - 1, \ .prog_type = BPF_PROG_TYPE_##ptype, \ + .expected_attach_type = atype, \ + .cookie = (long)(flags), \ + .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog); -static struct bpf_link *attach_tp(const struct bpf_program *prog); -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog); -static struct bpf_link *attach_trace(const struct bpf_program *prog); -static struct bpf_link *attach_lsm(const struct bpf_program *prog); -static struct bpf_link *attach_iter(const struct bpf_program *prog); +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); static const struct bpf_sec_def section_defs[] = { - BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), - BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT), - SEC_DEF("kprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - SEC_DEF("kretprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), - BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - SEC_DEF("tracepoint/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("tp/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("raw_tp/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("tp_btf/", TRACING, - .expected_attach_type = BPF_TRACE_RAW_TP, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fexit/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry.s/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret.s/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fexit.s/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("freplace/", EXT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("lsm/", LSM, - .is_attach_btf = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("lsm.s/", LSM, - .is_attach_btf = true, - .is_sleepable = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("iter/", TRACING, - .expected_attach_type = BPF_TRACE_ITER, - .is_attach_btf = true, - .attach_fn = attach_iter), - SEC_DEF("syscall", SYSCALL, - .is_sleepable = true), - BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, - BPF_XDP_DEVMAP), - BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, - BPF_XDP_CPUMAP), - BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, - BPF_XDP), - BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), - BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), - BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), - BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), - BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), - BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_INGRESS), - BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_EGRESS), - BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), - BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_RELEASE), - BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET4_POST_BIND), - BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET6_POST_BIND), - BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, - BPF_CGROUP_DEVICE), - BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, - BPF_CGROUP_SOCK_OPS), - BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_PARSER), - BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_VERDICT), - BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), - BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, - BPF_SK_MSG_VERDICT), - BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, - BPF_LIRC_MODE2), - BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, - BPF_FLOW_DISSECTOR), - BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_BIND), - BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_BIND), - BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_CONNECT), - BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_CONNECT), - BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_SENDMSG), - BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_SENDMSG), - BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_RECVMSG), - BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_RECVMSG), - BPF_EAPROG_SEC("cgroup/getpeername4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getpeername6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getsockname4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/getsockname6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, - BPF_CGROUP_SYSCTL), - BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_GETSOCKOPT), - BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_SETSOCKOPT), - BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), - BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, - BPF_SK_LOOKUP), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace/", EXT, 0, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), + SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), + SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#undef BPF_PROG_SEC_IMPL -#undef BPF_PROG_SEC -#undef BPF_APROG_SEC -#undef BPF_EAPROG_SEC -#undef BPF_APROG_COMPAT -#undef SEC_DEF - #define MAX_TYPE_NAME_SIZE 32 static const struct bpf_sec_def *find_sec_def(const char *sec_name) { - int i, n = ARRAY_SIZE(section_defs); + const struct bpf_sec_def *sec_def; + enum sec_def_flags sec_flags; + int i, n = ARRAY_SIZE(section_defs), len; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; for (i = 0; i < n; i++) { - if (strncmp(sec_name, - section_defs[i].sec, section_defs[i].len)) + sec_def = §ion_defs[i]; + sec_flags = sec_def->cookie; + len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; + continue; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + continue; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return sec_def; + continue; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; continue; - return §ion_defs[i]; + } + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + if (strcmp(sec_name, sec_def->sec) == 0) + return sec_def; } return NULL; } @@ -8135,8 +8152,15 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (attach_type && !section_defs[i].is_attachable) - continue; + const struct bpf_sec_def *sec_def = §ion_defs[i]; + + if (attach_type) { + if (sec_def->preload_fn != libbpf_preload_prog) + continue; + + if (!(sec_def->cookie & SEC_ATTACHABLE)) + continue; + } if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); @@ -8460,20 +8484,13 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, return -ESRCH; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id) +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id) { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *attach_name; int err = 0; - if (!prog->sec_def || !prog->sec_def->is_attach_btf) { - pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", - prog->sec_name); - return -ESRCH; - } - attach_name = prog->sec_name + prog->sec_def->len; - /* BPF program's BTF ID */ if (attach_prog_fd) { err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); @@ -8523,7 +8540,9 @@ int libbpf_attach_type_by_name(const char *name, return libbpf_err(-EINVAL); } - if (!sec_def->is_attachable) + if (sec_def->preload_fn != libbpf_preload_prog) + return libbpf_err(-EINVAL); + if (!(sec_def->cookie & SEC_ATTACHABLE)) return libbpf_err(-EINVAL); *attach_type = sec_def->expected_attach_type; @@ -9011,59 +9030,18 @@ int bpf_link__unpin(struct bpf_link *link) return 0; } -static int poke_kprobe_events(bool add, const char *name, bool retprobe, uint64_t offset) -{ - int fd, ret = 0; - pid_t p = getpid(); - char cmd[260], probename[128], probefunc[128]; - const char *file = "/sys/kernel/debug/tracing/kprobe_events"; - - if (retprobe) - snprintf(probename, sizeof(probename), "kretprobes/%s_libbpf_%u", name, p); - else - snprintf(probename, sizeof(probename), "kprobes/%s_libbpf_%u", name, p); - - if (offset) - snprintf(probefunc, sizeof(probefunc), "%s+%zu", name, (size_t)offset); - - if (add) { - snprintf(cmd, sizeof(cmd), "%c:%s %s", - retprobe ? 'r' : 'p', - probename, - offset ? probefunc : name); - } else { - snprintf(cmd, sizeof(cmd), "-:%s", probename); - } - - fd = open(file, O_WRONLY | O_APPEND, 0); - if (!fd) - return -errno; - ret = write(fd, cmd, strlen(cmd)); - if (ret < 0) - ret = -errno; - close(fd); - - return ret; -} - -static inline int add_kprobe_event_legacy(const char *name, bool retprobe, uint64_t offset) -{ - return poke_kprobe_events(true, name, retprobe, offset); -} - -static inline int remove_kprobe_event_legacy(const char *name, bool retprobe) -{ - return poke_kprobe_events(false, name, retprobe, 0); -} - struct bpf_link_perf { struct bpf_link link; int perf_event_fd; /* legacy kprobe support: keep track of probe identifier and type */ char *legacy_probe_name; + bool legacy_is_kprobe; bool legacy_is_retprobe; }; +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); +static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe); + static int bpf_link_perf_detach(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9076,10 +9054,16 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(perf_link->perf_event_fd); close(link->fd); - /* legacy kprobe needs to be removed after perf event fd closure */ - if (perf_link->legacy_probe_name) - err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, - perf_link->legacy_is_retprobe); + /* legacy uprobe/kprobe needs to be removed after perf event fd closure */ + if (perf_link->legacy_probe_name) { + if (perf_link->legacy_is_kprobe) { + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } else { + err = remove_uprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } + } return err; } @@ -9202,18 +9186,6 @@ static int parse_uint_from_file(const char *file, const char *fmt) return ret; } -static int determine_kprobe_perf_type_legacy(const char *func_name, bool is_retprobe) -{ - char file[192]; - - snprintf(file, sizeof(file), - "/sys/kernel/debug/tracing/events/%s/%s_libbpf_%d/id", - is_retprobe ? "kretprobes" : "kprobes", - func_name, getpid()); - - return parse_uint_from_file(file, "%d\n"); -} - static int determine_kprobe_perf_type(void) { const char *file = "/sys/bus/event_source/devices/kprobe/type"; @@ -9296,21 +9268,79 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, return pfd; } -static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64_t offset, int pid) +static int append_to_file(const char *file, const char *fmt, ...) +{ + int fd, n, err = 0; + va_list ap; + + fd = open(file, O_WRONLY | O_APPEND, 0); + if (fd < 0) + return -errno; + + va_start(ap, fmt); + n = vdprintf(fd, fmt, ap); + va_end(ap); + + if (n < 0) + err = -errno; + + close(fd); + return err; +} + +static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *kfunc_name, size_t offset) +{ + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset); +} + +static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "%c:%s/%s %s+0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "kretprobes" : "kprobes", + probe_name, kfunc_name, offset); +} + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name); +} + +static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[256]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "kretprobes" : "kprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset, int pid) { struct perf_event_attr attr = {}; char errmsg[STRERR_BUFSIZE]; int type, pfd, err; - err = add_kprobe_event_legacy(name, retprobe, offset); + err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); if (err < 0) { - pr_warn("failed to add legacy kprobe event: %s\n", + pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", + kfunc_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); return err; } - type = determine_kprobe_perf_type_legacy(name, retprobe); + type = determine_kprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { - pr_warn("failed to determine legacy kprobe event id: %s\n", + pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", + kfunc_name, offset, libbpf_strerror_r(type, errmsg, sizeof(errmsg))); return type; } @@ -9340,7 +9370,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, char errmsg[STRERR_BUFSIZE]; char *legacy_probe = NULL; struct bpf_link *link; - unsigned long offset; + size_t offset; bool retprobe, legacy; int pfd, err; @@ -9357,36 +9387,48 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, func_name, offset, -1 /* pid */, 0 /* ref_ctr_off */); } else { + char probe_name[256]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); + legacy_probe = strdup(func_name); if (!legacy_probe) return libbpf_err_ptr(-ENOMEM); - pfd = perf_event_kprobe_open_legacy(retprobe, func_name, + pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name, offset, -1 /* pid */); } if (pfd < 0) { - pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + err = -errno; + pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { close(pfd); - pr_warn("prog '%s': failed to attach to %s '%s': %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, + pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; } if (legacy) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = true; perf_link->legacy_is_retprobe = retprobe; } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); } struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, @@ -9400,7 +9442,7 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog) +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; @@ -9409,8 +9451,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog) char *func; int n, err; - func_name = prog->sec_name + prog->sec_def->len; - opts.retprobe = strcmp(prog->sec_def->sec, "kretprobe/") == 0; + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); + if (opts.retprobe) + func_name = prog->sec_name + sizeof("kretprobe/") - 1; + else + func_name = prog->sec_name + sizeof("kprobe/") - 1; n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { @@ -9431,17 +9476,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog) return link; } +static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *binary_path, uint64_t offset) +{ + int i; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } +} + +static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "%c:%s/%s %s:0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "uretprobes" : "uprobes", + probe_name, binary_path, offset); +} + +static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name); +} + +static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[512]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "uretprobes" : "uprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset, int pid) +{ + struct perf_event_attr attr; + int type, pfd, err; + + err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); + if (err < 0) { + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", + binary_path, (size_t)offset, err); + return err; + } + type = determine_uprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", + binary_path, offset, err); + return type; + } + + memset(&attr, 0, sizeof(attr)); + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + return err; + } + return pfd; +} + LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; + char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; - bool retprobe; + bool retprobe, legacy; if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); @@ -9450,15 +9574,35 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, - func_offset, pid, ref_ctr_off); + legacy = determine_uprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, + func_offset, pid, ref_ctr_off); + } else { + char probe_name[512]; + + if (ref_ctr_off) + return libbpf_err_ptr(-EINVAL); + + gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), + binary_path, func_offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe, + binary_path, func_offset, pid); + } if (pfd < 0) { + err = -errno; pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { @@ -9467,9 +9611,20 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = false; + perf_link->legacy_is_retprobe = retprobe; } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); + } struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, @@ -9573,7 +9728,7 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_program *prog) +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) { char *sec_name, *tp_cat, *tp_name; struct bpf_link *link; @@ -9582,8 +9737,11 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog) if (!sec_name) return libbpf_err_ptr(-ENOMEM); - /* extract "tp/<category>/<name>" */ - tp_cat = sec_name + prog->sec_def->len; + /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ + if (str_has_pfx(prog->sec_name, "tp/")) + tp_cat = sec_name + sizeof("tp/") - 1; + else + tp_cat = sec_name + sizeof("tracepoint/") - 1; tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); @@ -9627,9 +9785,14 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog) +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) { - const char *tp_name = prog->sec_name + prog->sec_def->len; + const char *tp_name; + + if (str_has_pfx(prog->sec_name, "raw_tp/")) + tp_name = prog->sec_name + sizeof("raw_tp/") - 1; + else + tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1; return bpf_program__attach_raw_tracepoint(prog, tp_name); } @@ -9674,12 +9837,12 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_program *prog) +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) { return bpf_program__attach_trace(prog); } -static struct bpf_link *attach_lsm(const struct bpf_program *prog) +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) { return bpf_program__attach_lsm(prog); } @@ -9810,7 +9973,7 @@ bpf_program__attach_iter(const struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_program *prog) +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) { return bpf_program__attach_iter(prog, NULL); } @@ -9820,7 +9983,7 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) if (!prog->sec_def || !prog->sec_def->attach_fn) return libbpf_err_ptr(-ESRCH); - return prog->sec_def->attach_fn(prog); + return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); } static int bpf_link__detach_struct_ops(struct bpf_link *link) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c90e3d79e72c..e35490c54eb3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -269,7 +269,7 @@ struct bpf_kprobe_opts { /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; /* function's offset to install kprobe to */ - unsigned long offset; + size_t offset; /* kprobe is return probe */ bool retprobe; size_t :0; @@ -481,9 +481,13 @@ struct bpf_map_def { unsigned int map_flags; }; -/* - * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, - * so no need to worry about a name clash. +/** + * @brief **bpf_object__find_map_by_name()** returns BPF map of + * the given name, if it exists within the passed BPF object + * @param obj BPF object + * @param name name of the BPF map + * @return BPF map instance, if such map exists within the BPF object; + * or NULL otherwise. */ LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -509,7 +513,12 @@ bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -/* get/set map FD */ +/** + * @brief **bpf_map__fd()** gets the file descriptor of the passed + * BPF map + * @param map the BPF map instance + * @return the file descriptor; or -EINVAL in case of an error + */ LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ @@ -550,6 +559,14 @@ LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_internal()** tells the caller whether or not the + * passed map is a special map created by libbpf automatically for things like + * global variables, __ksym externs, Kconfig values, etc + * @param map the bpf_map + * @return true, if the map is an internal map; false, otherwise + */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); @@ -561,6 +578,38 @@ 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); LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Many libbpf API functions which return pointers have logic to encode error + * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** + * should be used on the return value from these functions immediately after + * calling the API function, with no intervening calls that could clobber the + * `errno` variable. Consult the individual functions documentation to verify + * if this logic applies should be used. + * + * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` + * is enabled, NULL is returned on error instead. + * + * If ptr is NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. + * + * Example usage: + * + * struct perf_buffer *pb; + * + * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); + * err = libbpf_get_error(pb); + * if (err) { + * pb = NULL; + * fprintf(stderr, "failed to open perf buffer: %d\n", err); + * goto cleanup; + * } + */ LIBBPF_API long libbpf_get_error(const void *ptr); struct bpf_prog_load_attr { @@ -825,9 +874,10 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); -/* - * A helper function to get the number of possible CPUs before looking up - * per-CPU maps. Negative errno is returned on failure. +/** + * @brief **libbpf_num_possible_cpus()** is a helper function to get the + * number of possible CPUs that the host kernel supports and expects. + * @return number of possible CPUs; or error code on failure * * Example usage: * @@ -837,7 +887,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); * } * long values[ncpus]; * bpf_map_lookup_elem(per_cpu_map_fd, key, values); - * */ LIBBPF_API int libbpf_num_possible_cpus(void); diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ceb0c98979bc..ec79400517d4 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -89,6 +89,13 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is + * a string literal known at compilation time or char * pointer known only at + * runtime. + */ +#define str_has_pfx(str, pfx) \ + (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) + /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index df0d03dcffab..74e6f860f703 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -46,6 +46,15 @@ enum libbpf_strict_mode { */ LIBBPF_STRICT_DIRECT_ERRS = 0x02, + /* + * Enforce strict BPF program section (SEC()) names. + * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were + * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become + * unrecognized by libbpf and would have to be just SEC("xdp") and + * SEC("xdp") and SEC("perf_event"). + */ + LIBBPF_STRICT_SEC_NAME = 0x04, + __LIBBPF_STRICT_LAST, }; diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 10911a8cad0f..2df880cefdae 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1649,11 +1649,17 @@ static bool btf_is_non_static(const struct btf_type *t) static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name, int *out_btf_sec_id, int *out_btf_id) { - int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0; + int i, j, n, m, btf_id = 0; const struct btf_type *t; const struct btf_var_secinfo *vi; const char *name; + if (!obj->btf) { + pr_warn("failed to find BTF info for object '%s'\n", obj->filename); + return -EINVAL; + } + + n = btf__get_nr_types(obj->btf); for (i = 1; i <= n; i++) { t = btf__type_by_id(obj->btf, i); diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index b22b50c1b173..9cf66702fa8d 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -105,10 +105,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; - if (err < 0) + if (err < 0) { err = -errno; - else + } else { err = (int)attr.test.retval; + errno = -err; + } goto out; } err = 0; diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c index 1fb8b49de1d6..ea655318153f 100644 --- a/tools/lib/bpf/strset.c +++ b/tools/lib/bpf/strset.c @@ -88,6 +88,7 @@ void strset__free(struct strset *set) hashmap__free(set->strs_hash); free(set->strs_data); + free(set); } size_t strset__data_size(const struct strset *set) diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index d8886720e83d..8441e3e1aaac 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -43,7 +43,7 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y)) +#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y)) #define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL) int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -54,7 +54,10 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { - FD(evsel, cpu, thread) = -1; + int *fd = FD(evsel, cpu, thread); + + if (fd) + *fd = -1; } } } @@ -80,7 +83,7 @@ sys_perf_event_open(struct perf_event_attr *attr, static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd) { struct perf_evsel *leader = evsel->leader; - int fd; + int *fd; if (evsel == leader) { *group_fd = -1; @@ -95,10 +98,10 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou return -ENOTCONN; fd = FD(leader, cpu, thread); - if (fd == -1) + if (fd == NULL || *fd == -1) return -EBADF; - *group_fd = fd; + *group_fd = *fd; return 0; } @@ -138,7 +141,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { - int fd, group_fd; + int fd, group_fd, *evsel_fd; + + evsel_fd = FD(evsel, cpu, thread); + if (evsel_fd == NULL) + return -EINVAL; err = get_group_fd(evsel, cpu, thread, &group_fd); if (err < 0) @@ -151,7 +158,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, if (fd < 0) return -errno; - FD(evsel, cpu, thread) = fd; + *evsel_fd = fd; } } @@ -163,9 +170,12 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; + int *fd = FD(evsel, cpu, thread); + + if (fd && *fd >= 0) { + close(*fd); + *fd = -1; + } } } @@ -209,13 +219,12 @@ void perf_evsel__munmap(struct perf_evsel *evsel) for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread); - struct perf_mmap *map = MMAP(evsel, cpu, thread); + int *fd = FD(evsel, cpu, thread); - if (fd < 0) + if (fd == NULL || *fd < 0) continue; - perf_mmap__munmap(map); + perf_mmap__munmap(MMAP(evsel, cpu, thread)); } } @@ -239,15 +248,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread); - struct perf_mmap *map = MMAP(evsel, cpu, thread); + int *fd = FD(evsel, cpu, thread); + struct perf_mmap *map; - if (fd < 0) + if (fd == NULL || *fd < 0) continue; + map = MMAP(evsel, cpu, thread); perf_mmap__init(map, NULL, false, NULL); - ret = perf_mmap__mmap(map, &mp, fd, cpu); + ret = perf_mmap__mmap(map, &mp, *fd, cpu); if (ret) { perf_evsel__munmap(evsel); return ret; @@ -260,7 +270,9 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread) { - if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL) + int *fd = FD(evsel, cpu, thread); + + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL) return NULL; return MMAP(evsel, cpu, thread)->base; @@ -295,17 +307,18 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu, thread); memset(count, 0, sizeof(*count)); - if (FD(evsel, cpu, thread) < 0) + if (fd == NULL || *fd < 0) return -EINVAL; if (MMAP(evsel, cpu, thread) && !perf_mmap__read_self(MMAP(evsel, cpu, thread), count)) return 0; - if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) + if (readn(*fd, count->values, size) <= 0) return -errno; return 0; @@ -318,8 +331,13 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread), - err = ioctl(fd, ioc, arg); + int err; + int *fd = FD(evsel, cpu, thread); + + if (fd == NULL || *fd < 0) + return -1; + + err = ioctl(*fd, ioc, arg); if (err) return err; diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index c67c83399170..ce91a582f0e4 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -40,7 +40,7 @@ static int test_stat_cpu(void) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK, }; - int err, cpu, tmp; + int err, idx; cpus = perf_cpu_map__new(NULL); __T("failed to create cpus", cpus); @@ -70,10 +70,10 @@ static int test_stat_cpu(void) perf_evlist__for_each_evsel(evlist, evsel) { cpus = perf_evsel__cpus(evsel); - perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { struct perf_counts_values counts = { .val = 0 }; - perf_evsel__read(evsel, cpu, 0, &counts); + perf_evsel__read(evsel, idx, 0, &counts); __T("failed to read value for evsel", counts.val != 0); } } diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index a184e4861627..33ae9334861a 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -22,7 +22,7 @@ static int test_stat_cpu(void) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; - int err, cpu, tmp; + int err, idx; cpus = perf_cpu_map__new(NULL); __T("failed to create cpus", cpus); @@ -33,10 +33,10 @@ static int test_stat_cpu(void) err = perf_evsel__open(evsel, cpus, NULL); __T("failed to open evsel", err == 0); - perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { struct perf_counts_values counts = { .val = 0 }; - perf_evsel__read(evsel, cpu, 0, &counts); + perf_evsel__read(evsel, idx, 0, &counts); __T("failed to read value for evsel", counts.val != 0); } @@ -148,6 +148,7 @@ static int test_stat_user_read(int event) __T("failed to mmap evsel", err == 0); pc = perf_evsel__mmap_base(evsel, 0, 0); + __T("failed to get mmapped address", pc); #if defined(__i386__) || defined(__x86_64__) __T("userspace counter access not supported", pc->cap_user_rdpmc); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index bc821056aba9..0893436cc09f 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -684,7 +684,7 @@ static int elf_add_alternative(struct elf *elf, sec = find_section_by_name(elf, ".altinstructions"); if (!sec) { sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, size, 0); + SHF_ALLOC, 0, 0); if (!sec) { WARN_ELF("elf_create_section"); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e5947fbb9e7a..06b5c164ae93 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -292,7 +292,7 @@ static int decode_instructions(struct objtool_file *file) !strcmp(sec->name, ".entry.text")) sec->noinstr = true; - for (offset = 0; offset < sec->len; offset += insn->len) { + for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { insn = malloc(sizeof(*insn)); if (!insn) { WARN("malloc failed"); @@ -307,7 +307,7 @@ static int decode_instructions(struct objtool_file *file) insn->offset = offset; ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, + sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, &insn->stack_ops); @@ -349,9 +349,9 @@ static struct instruction *find_last_insn(struct objtool_file *file, { struct instruction *insn = NULL; unsigned int offset; - unsigned int end = (sec->len > 10) ? sec->len - 10 : 0; + unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0; - for (offset = sec->len - 1; offset >= end && !insn; offset--) + for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--) insn = find_insn(file, sec, offset); return insn; @@ -389,7 +389,7 @@ static int add_dead_ends(struct objtool_file *file) insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", @@ -424,7 +424,7 @@ reachable: insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", @@ -1561,14 +1561,14 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - if (sec->len % sizeof(struct unwind_hint)) { + if (sec->sh.sh_size % sizeof(struct unwind_hint)) { WARN("struct unwind_hint size mismatch"); return -1; } file->hints = true; - for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { + for (i = 0; i < sec->sh.sh_size / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 8676c7598728..fee03b744a6e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -286,10 +286,9 @@ static int read_sections(struct elf *elf) return -1; } } - sec->len = sec->sh.sh_size; if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->len; + elf->text_size += sec->sh.sh_size; list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); @@ -509,6 +508,7 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, list_add_tail(&reloc->list, &sec->reloc->reloc_list); elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + sec->reloc->sh.sh_size += sec->reloc->sh.sh_entsize; sec->reloc->changed = true; return 0; @@ -734,8 +734,8 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) data->d_size = strlen(str) + 1; data->d_align = 1; - len = strtab->len; - strtab->len += data->d_size; + len = strtab->sh.sh_size; + strtab->sh.sh_size += data->d_size; strtab->changed = true; return len; @@ -790,9 +790,9 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 1; data->d_type = ELF_T_SYM; - sym->idx = symtab->len / sizeof(sym->sym); + sym->idx = symtab->sh.sh_size / sizeof(sym->sym); - symtab->len += data->d_size; + symtab->sh.sh_size += data->d_size; symtab->changed = true; symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); @@ -814,7 +814,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 4; data->d_type = ELF_T_WORD; - symtab_shndx->len += 4; + symtab_shndx->sh.sh_size += 4; symtab_shndx->changed = true; } @@ -855,7 +855,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->len = size; sec->changed = true; sec->data = elf_newdata(s); @@ -979,63 +978,63 @@ static struct section *elf_create_reloc_section(struct elf *elf, } } -static int elf_rebuild_rel_reloc_section(struct section *sec, int nr) +static int elf_rebuild_rel_reloc_section(struct section *sec) { struct reloc *reloc; - int idx = 0, size; + int idx = 0; void *buf; /* Allocate a buffer for relocations */ - size = nr * sizeof(GElf_Rel); - buf = malloc(size); + buf = malloc(sec->sh.sh_size); if (!buf) { perror("malloc"); return -1; } sec->data->d_buf = buf; - sec->data->d_size = size; + sec->data->d_size = sec->sh.sh_size; sec->data->d_type = ELF_T_REL; - sec->sh.sh_size = size; - idx = 0; list_for_each_entry(reloc, &sec->reloc_list, list) { reloc->rel.r_offset = reloc->offset; reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - gelf_update_rel(sec->data, idx, &reloc->rel); + if (!gelf_update_rel(sec->data, idx, &reloc->rel)) { + WARN_ELF("gelf_update_rel"); + return -1; + } idx++; } return 0; } -static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) +static int elf_rebuild_rela_reloc_section(struct section *sec) { struct reloc *reloc; - int idx = 0, size; + int idx = 0; void *buf; /* Allocate a buffer for relocations with addends */ - size = nr * sizeof(GElf_Rela); - buf = malloc(size); + buf = malloc(sec->sh.sh_size); if (!buf) { perror("malloc"); return -1; } sec->data->d_buf = buf; - sec->data->d_size = size; + sec->data->d_size = sec->sh.sh_size; sec->data->d_type = ELF_T_RELA; - sec->sh.sh_size = size; - idx = 0; list_for_each_entry(reloc, &sec->reloc_list, list) { reloc->rela.r_offset = reloc->offset; reloc->rela.r_addend = reloc->addend; reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - gelf_update_rela(sec->data, idx, &reloc->rela); + if (!gelf_update_rela(sec->data, idx, &reloc->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } idx++; } @@ -1044,16 +1043,9 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) static int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) { - struct reloc *reloc; - int nr; - - nr = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) - nr++; - switch (sec->sh.sh_type) { - case SHT_REL: return elf_rebuild_rel_reloc_section(sec, nr); - case SHT_RELA: return elf_rebuild_rela_reloc_section(sec, nr); + case SHT_REL: return elf_rebuild_rel_reloc_section(sec); + case SHT_RELA: return elf_rebuild_rela_reloc_section(sec); default: return -1; } } @@ -1113,12 +1105,6 @@ int elf_write(struct elf *elf) /* Update changed relocation sections and section headers: */ list_for_each_entry(sec, &elf->sections, list) { if (sec->changed) { - if (sec->base && - elf_rebuild_reloc_section(elf, sec)) { - WARN("elf_rebuild_reloc_section"); - return -1; - } - s = elf_getscn(elf->elf, sec->idx); if (!s) { WARN_ELF("elf_getscn"); @@ -1129,6 +1115,12 @@ int elf_write(struct elf *elf) return -1; } + if (sec->base && + elf_rebuild_reloc_section(elf, sec)) { + WARN("elf_rebuild_reloc_section"); + return -1; + } + sec->changed = false; elf->changed = true; } diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e34395047530..075d8291b854 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -38,7 +38,6 @@ struct section { Elf_Data *data; char *name; int idx; - unsigned int len; bool changed, text, rodata, noinstr; }; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index dc9b7dd314b0..b5865e2450cb 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -204,7 +204,7 @@ int orc_create(struct objtool_file *file) /* Add a section terminator */ if (!empty) { - orc_list_add(&orc_list, &null, sec, sec->len); + orc_list_add(&orc_list, &null, sec, sec->sh.sh_size); nr++; } } diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bc925cf19e2d..06c3eacab3d5 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,6 +58,13 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } +static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, + unsigned long *off) +{ + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; +} + static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) @@ -91,14 +98,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_reloc->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section reloc symbol %s", - sec, offset + entry->orig, orig_reloc->sym->name); - return -1; - } - alt->orig_sec = orig_reloc->sym->sec; - alt->orig_off = orig_reloc->addend; + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); @@ -116,8 +117,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1; - alt->new_sec = new_reloc->sym->sec; - alt->new_off = (unsigned int)new_reloc->addend; + reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) @@ -159,13 +159,13 @@ int special_get_alts(struct elf *elf, struct list_head *alts) if (!sec) continue; - if (sec->len % entry->size != 0) { + if (sec->sh.sh_size % entry->size != 0) { WARN("%s size not a multiple of %d", sec->name, entry->size); return -1; } - nr_entries = sec->len / entry->size; + nr_entries = sec->sh.sh_size / entry->size; for (idx = 0; idx < nr_entries; idx++) { alt = malloc(sizeof(*alt)); diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt index 52152d156ad9..79936355d819 100644 --- a/tools/perf/Documentation/jitdump-specification.txt +++ b/tools/perf/Documentation/jitdump-specification.txt @@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html -The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html +The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index de6beedb7283..3b6a2c84ea02 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -261,7 +261,7 @@ COALESCE User can specify how to sort offsets for cacheline. Following fields are available and governs the final -output fields set for caheline offsets output: +output fields set for cacheline offsets output: tid - coalesced by process TIDs pid - coalesced by process PIDs diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 184ba62420f0..db465fa7ee91 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns. "Transactions" events correspond to the start or end of transactions. The 'flags' field can be used in perf script to determine whether the event is a -tranasaction start, commit or abort. +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 diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 74d774592196..1b4d452923d7 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -44,7 +44,7 @@ COMMON OPTIONS -f:: --force:: - Don't complan, do it. + Don't complain, do it. REPORT OPTIONS -------------- diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5a1f68122f50..fa4f39d305a7 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -54,7 +54,7 @@ all sched_wakeup events in the system: 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_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 0250dc61cf98..cf4b7f4b625a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -448,7 +448,7 @@ all sched_wakeup events in the system: 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_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4c9310be6acc..7e6fb7cbc0f4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements. Print metrics or metricgroups specified in a comma separated list. For a group all metrics from the group are added. The events from the metrics are automatically measured. -See perf list output for the possble metrics and metricgroups. +See perf list output for the possible metrics and metricgroups. -A:: --no-aggr:: diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt index c6302df4cf29..a15b93fdcf50 100644 --- a/tools/perf/Documentation/topdown.txt +++ b/tools/perf/Documentation/topdown.txt @@ -2,7 +2,7 @@ Using TopDown metrics in user space ----------------------------------- Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown -methology to break down CPU pipeline execution into 4 bottlenecks: +methodology to break down CPU pipeline execution into 4 bottlenecks: frontend bound, backend bound, bad speculation, retiring. For more details on Topdown see [1][5] diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..14e3e8d702a0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -143,7 +143,7 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd +OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..5cd702062a04 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -802,7 +802,7 @@ endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(filter-out -static,$(LDFLAGS))' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index c7c7ec0812d5..5fc6a2a3dbc5 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -8,10 +8,10 @@ #include <linux/coresight-pmu.h> #include <linux/zalloc.h> -#include "../../util/auxtrace.h" -#include "../../util/debug.h" -#include "../../util/evlist.h" -#include "../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/debug.h" +#include "../../../util/evlist.h" +#include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 515aae470e23..293a23bf8be3 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,19 +16,19 @@ #include <linux/zalloc.h> #include "cs-etm.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/auxtrace.h" -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/perf_api_probe.h" -#include "../../util/evsel_config.h" -#include "../../util/pmu.h" -#include "../../util/cs-etm.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/perf_api_probe.h" +#include "../../../util/evsel_config.h" +#include "../../../util/pmu.h" +#include "../../../util/cs-etm.h" #include <internal/lib.h> // page_size -#include "../../util/session.h" +#include "../../../util/session.h" #include <errno.h> #include <stdlib.h> diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index bbc297a7e2e3..b8b23b9dc598 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,7 @@ #include <linux/string.h> #include "arm-spe.h" -#include "../../util/pmu.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 36ba4c69c3c5..b7692cb0c733 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 3a550225dfaf..438906bf0014 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,8 +3,8 @@ #include <errno.h> #include <libunwind.h> #include "perf_regs.h" -#include "../../util/unwind.h" -#include "../../util/debug.h" +#include "../../../util/unwind.h" +#include "../../../util/debug.h" int libunwind__arch_reg_id(int regnum) { diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index eeafe97b8105..792cd75ade33 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, u8 die = ((struct iio_root_port *)evsel->priv)->die; struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); - if (count->run && count->ena) { + if (count && count->run && count->ena) { if (evsel->prev_raw_counts && !out->force_header) { struct perf_counts_values *prev_count = perf_counts(evsel->prev_raw_counts, die, 0); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0e824f7d8b19..6211d0b84b7a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -368,16 +368,6 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } -static inline unsigned int attr_type(unsigned int type) -{ - switch (type) { - case OUTPUT_TYPE_SYNTH: - return PERF_TYPE_SYNTH; - default: - return type; - } -} - static bool output_set_by_user(void) { int j; @@ -556,6 +546,18 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } +static struct evsel *find_first_output_type(struct evlist *evlist, + unsigned int type) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (output_type(evsel->core.attr.type) == (int)type) + return evsel; + } + return NULL; +} + /* * verify all user requested events exist and the samples * have the expected data @@ -567,7 +569,7 @@ static int perf_session__check_output_opt(struct perf_session *session) struct evsel *evsel; for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, attr_type(j)); + evsel = find_first_output_type(session->evlist, j); /* * even if fields is set to 0 (ie., show nothing) event must diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f6e87b7be5fa..f0ecfda34ece 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv) goto out; } else if (verbose) iostat_list(evsel_list, &stat_config); + if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target)) + target.system_wide = true; } if (add_default_attributes()) diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 84a0cedf1fd9..f1f2965f6775 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -1046,7 +1046,7 @@ { "EventCode": "0x4e010", "EventName": "PM_GCT_NOSLOT_IC_L3MISS", - "BriefDescription": "Gct empty for this thread due to icach l3 miss", + "BriefDescription": "Gct empty for this thread due to icache l3 miss", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..7c887d37b893 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1285,6 +1285,7 @@ int main(int argc, char *argv[]) } free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return 0; @@ -1306,6 +1307,7 @@ err_close_eventsfp: create_empty_mapping(output_file); err_out: free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return ret; } diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d9e99b3f77e6..d8ea6a88163f 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -68,3 +68,100 @@ fd=10 type=0 config=5 optional=1 + +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index 8b04a055d154..b656ab93c5bf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 4fca9f1bfbf8..97625090a1c4 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index 4bb58e1c82a6..d555042e3fbf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 @@ -174,8 +271,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event21:base-stat] -fd=21 +[event30:base-stat] +fd=30 type=3 config=512 optional=1 @@ -184,8 +281,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event22:base-stat] -fd=22 +[event31:base-stat] +fd=31 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..9b4a765e4b73 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, struct thread *thread, struct state *state) { struct addr_location al; - unsigned char buf1[BUFSZ]; - unsigned char buf2[BUFSZ]; + unsigned char buf1[BUFSZ] = {0}; + unsigned char buf2[BUFSZ] = {0}; size_t ret_len; u64 objdump_addr; const char *objdump_name; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index a288035eb362..c756284b3b13 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -20,6 +20,23 @@ /* For bsearch. We try to unwind functions in shared object. */ #include <stdlib.h> +/* + * The test will assert frames are on the stack but tail call optimizations lose + * the frame of the caller. Clang can disable this optimization on a called + * function but GCC currently (11/2020) lacks this attribute. The barrier is + * used to inhibit tail calls in these cases. + */ +#ifdef __has_attribute +#if __has_attribute(disable_tail_calls) +#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls)) +#define NO_TAIL_CALL_BARRIER +#endif +#endif +#ifndef NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory"); +#endif + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -noinline int test_dwarf_unwind__thread(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -noinline int test_dwarf_unwind__compare(void *p1, void *p2) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -noinline int test_dwarf_unwind__krava_3(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -noinline int test_dwarf_unwind__krava_2(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread) { - return test_dwarf_unwind__krava_3(thread); + int ret; + + ret = test_dwarf_unwind__krava_3(thread); + NO_TAIL_CALL_BARRIER; + return ret; } -noinline int test_dwarf_unwind__krava_1(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread) { - return test_dwarf_unwind__krava_2(thread); + int ret; + + ret = test_dwarf_unwind__krava_2(thread); + NO_TAIL_CALL_BARRIER; + return ret; } int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 781afe42e90e..fa5bd5c20e96 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -757,25 +757,40 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, } void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down) + unsigned int row, int diff, bool arrow_down) { - unsigned int end_row; + int end_row; - if (row >= browser->top_idx) - end_row = row - browser->top_idx; - else + if (diff <= 0) return; SLsmg_set_char_set(1); if (arrow_down) { + if (row + diff <= browser->top_idx) + return; + + end_row = row + diff - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); - SLsmg_write_char(SLSMG_ULCORN_CHAR); - ui_browser__gotorc(browser, end_row, column); - SLsmg_draw_hline(2); - ui_browser__gotorc(browser, end_row + 1, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); + + while (--end_row >= 0 && end_row > (int)(row - browser->top_idx)) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_draw_vline(1); + } + + end_row = (int)(row - browser->top_idx); + if (end_row >= 0) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_hline(2); + } } else { + if (row < browser->top_idx) + return; + + end_row = row - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); ui_browser__gotorc(browser, end_row, column); diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 3678eb88f119..510ce4554050 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -51,7 +51,7 @@ void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, u64 start, u64 end); void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down); + unsigned int row, int diff, bool arrow_down); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *browser, const char *title, diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ef4da4295bf7..e81c2493efdf 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -125,13 +125,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ab->selection = al; } -static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) +static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor) { struct disasm_line *pos = list_prev_entry(cursor, al.node); const char *name; + int diff = 1; + + while (pos && pos->al.offset == -1) { + pos = list_prev_entry(pos, al.node); + if (!ab->opts->hide_src_code) + diff++; + } if (!pos) - return false; + return 0; if (ins__is_lock(&pos->ins)) name = pos->ops.locked.ins.name; @@ -139,9 +146,11 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) name = pos->ins.name; if (!name || !cursor->ins.name) - return false; + return 0; - return ins__is_fused(ab->arch, name, cursor->ins.name); + if (ins__is_fused(ab->arch, name, cursor->ins.name)) + return diff; + return 0; } static void annotate_browser__draw_current_jump(struct ui_browser *browser) @@ -155,6 +164,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) struct annotation *notes = symbol__annotation(sym); u8 pcnt_width = annotation__pcnt_width(notes); int width; + int diff = 0; /* PLT symbols contain external offsets */ if (strstr(sym->name, "@plt")) @@ -205,11 +215,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) pcnt_width + 2 + notes->widths.addr + width, from, to); - if (is_fused(ab, cursor)) { + diff = is_fused(ab, cursor); + if (diff > 0) { ui_browser__mark_fused(browser, pcnt_width + 3 + notes->widths.addr + width, - from - 1, - to > from); + from - diff, diff, to > from); } } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 683f6d63560e..1a7112a87736 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -24,7 +24,10 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" int err = btf__get_from_id(id, &btf); +#pragma GCC diagnostic pop return err ? ERR_PTR(err) : btf; } diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4fb5e90d7a57..60ce5908c664 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set, section->name, item->name); ret = fn(key, value, data); if (ret < 0) { - pr_err("Error: wrong config key-value pair %s=%s\n", + pr_err("Error in the given config file: wrong config key-value pair %s=%s\n", key, value); /* * Can't be just a 'break', as perf_config_set__for_each_entry() diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index da19be7da284..44e40bad0e33 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2149,6 +2149,7 @@ static int add_callchain_ip(struct thread *thread, al.filtered = 0; al.sym = NULL; + al.srcline = NULL; if (!cpumode) { thread__find_cpumode_addr_location(thread, ip, &al); } else { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 069c2cfdd3be..352f16076e01 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2116,7 +2116,7 @@ fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) static int __perf_session__process_decomp_events(struct perf_session *session) { s64 skip; - u64 size, file_pos = 0; + u64 size; struct decomp *decomp = session->decomp_last; if (!decomp) @@ -2132,7 +2132,7 @@ static int __perf_session__process_decomp_events(struct perf_session *session) size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, file_pos)) < 0) { + (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", decomp->file_pos + decomp->head, event->header.size, event->header.type); return -EINVAL; diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 5a931456e718..ac35c61f65f5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -16,7 +16,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from collections import namedtuple from enum import Enum, auto -from typing import Iterable +from typing import Iterable, Sequence import kunit_config import kunit_json @@ -186,6 +186,26 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, exec_result.elapsed_time)) return parse_result +# Problem: +# $ kunit.py run --json +# works as one would expect and prints the parsed test results as JSON. +# $ kunit.py run --json suite_name +# would *not* pass suite_name as the filter_glob and print as json. +# argparse will consider it to be another way of writing +# $ kunit.py run --json=suite_name +# i.e. it would run all tests, and dump the json to a `suite_name` file. +# So we hackily automatically rewrite --json => --json=stdout +pseudo_bool_flag_defaults = { + '--json': 'stdout', + '--raw_output': 'kunit', +} +def massage_argv(argv: Sequence[str]) -> Sequence[str]: + def massage_arg(arg: str) -> str: + if arg not in pseudo_bool_flag_defaults: + return arg + return f'{arg}={pseudo_bool_flag_defaults[arg]}' + return list(map(massage_arg, argv)) + def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' @@ -303,7 +323,7 @@ def main(argv, linux=None): help='Specifies the file to read results from.', type=str, nargs='?', metavar='input_file') - cli_args = parser.parse_args(argv) + cli_args = parser.parse_args(massage_argv(argv)) if get_kernel_root_path(): os.chdir(get_kernel_root_path()) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 619c4554cbff..1edcc8373b4e 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -408,6 +408,14 @@ class KUnitMainTest(unittest.TestCase): self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + def test_run_raw_output_does_not_take_positional_args(self): + # --raw_output is a string flag, but we don't want it to consume + # any positional arguments, only ones after an '=' + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + kunit.main(['run', '--raw_output', 'filter_glob'], self.linux_source_mock) + self.linux_source_mock.run_kernel.assert_called_once_with( + args=None, build_dir='.kunit', filter_glob='filter_glob', timeout=300) + def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 6836510a522f..22722abc9dfa 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -266,16 +266,19 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; - if (feats_ok(td)) + if (feats_ok(td)) { fprintf(stderr, "Required Features: [%s] supported\n", feats_to_string(td->feats_required & td->feats_supported)); - else + } else { fprintf(stderr, "Required Features: [%s] NOT supported\n", feats_to_string(td->feats_required & ~td->feats_supported)); + td->result = KSFT_SKIP; + return 0; + } } /* Perform test specific additional initialization */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1a4d30ff3275..aa94739a1835 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -315,7 +315,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c + test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \ + trace_vprintk.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o @@ -375,7 +376,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ $$(INCLUDE_DIR)/vmlinux.h \ - $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT) + $(wildcard $(BPFDIR)/bpf_*.h) \ + | $(TRUNNER_OUTPUT) $$(BPFOBJ) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS)) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 8200c0da2769..554553acc6d9 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -242,3 +242,16 @@ To fix this issue, user newer libbpf. .. Links .. _clang reloc patch: https://reviews.llvm.org/D102712 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst + +Clang dependencies for the u32 spill test (xdpwall) +=================================================== +The xdpwall selftest requires a change in `Clang 14`__. + +Without it, the xdpwall selftest will fail and the error message +from running test_progs will look like: + +.. code-block:: console + + test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007 + +__ https://reviews.llvm.org/D109073 diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index bf307bb9e446..6c511dcd1465 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -14,6 +14,20 @@ void test_attach_probe(void) struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr, ref_ctr_offset; + bool legacy; + + /* Check if new-style kprobe/uprobe API is supported. + * Kernels that support new FD-based kprobe and uprobe BPF attachment + * through perf_event_open() syscall expose + * /sys/bus/event_source/devices/kprobe/type and + * /sys/bus/event_source/devices/uprobe/type files, respectively. They + * contain magic numbers that are passed as "type" field of + * perf_event_attr. Lack of such file in the system indicates legacy + * kernel with old-style kprobe/uprobe attach interface through + * creating per-probe event through tracefs. For such cases + * ref_ctr_offset feature is not supported, so we don't test it. + */ + legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; base_addr = get_base_addr(); if (CHECK(base_addr < 0, "get_base_addr", @@ -45,10 +59,11 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_kretprobe = kretprobe_link; - ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); + if (!legacy) + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); uprobe_opts.retprobe = false; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, 0 /* self pid */, "/proc/self/exe", @@ -58,11 +73,12 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_uprobe = uprobe_link; - ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); + if (!legacy) + ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); /* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */ uprobe_opts.retprobe = true; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, -1 /* any pid */, "/proc/self/exe", diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 52ccf0cf35e1..87f9df653e4e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -358,12 +358,27 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, TEST_BTF_DUMP_DATA_OVER(btf, d, NULL, str, int, sizeof(int)-1, "", 1); #ifdef __SIZEOF_INT128__ - TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128, BTF_F_COMPACT, - "(__int128)0xffffffffffffffff", - 0xffffffffffffffff); - ASSERT_OK(btf_dump_data(btf, d, "__int128", NULL, 0, &i, 16, str, - "(__int128)0xfffffffffffffffffffffffffffffffe"), - "dump __int128"); + /* gcc encode unsigned __int128 type with name "__int128 unsigned" in dwarf, + * and clang encode it with name "unsigned __int128" in dwarf. + * Do an availability test for either variant before doing actual test. + */ + if (btf__find_by_name(btf, "unsigned __int128") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, unsigned __int128, BTF_F_COMPACT, + "(unsigned __int128)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "unsigned __int128", NULL, 0, &i, 16, str, + "(unsigned __int128)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else if (btf__find_by_name(btf, "__int128 unsigned") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128 unsigned, BTF_F_COMPACT, + "(__int128 unsigned)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "__int128 unsigned", NULL, 0, &i, 16, str, + "(__int128 unsigned)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else { + ASSERT_TRUE(false, "unsigned_int128_not_found"); + } #endif } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 225714f71ac6..ac54e3f91d42 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -458,9 +458,9 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return -1; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i); + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (!prog) return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c index f81db9135ae4..67e86f8d8677 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c +++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c @@ -38,10 +38,9 @@ static int create_perf_events(void) static void close_perf_events(void) { - int cpu = 0; - int fd; + int cpu, fd; - while (cpu++ < cpu_cnt) { + for (cpu = 0; cpu < cpu_cnt; cpu++) { fd = pfd_array[cpu]; if (fd < 0) break; diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 95bd12097358..52fe157e2a90 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,7 +3,7 @@ void test_probe_user(void) { - const char *prog_name = "kprobe/__sys_connect"; + const char *prog_name = "handle_sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -18,7 +18,7 @@ void test_probe_user(void) if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; - kprobe_prog = bpf_object__find_program_by_title(obj, prog_name); + kprobe_prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!kprobe_prog, "find_probe", "prog '%s' not found\n", prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 4e91f4d6466c..873323fb18ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,6 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +static void toggle_object_autoload_progs(const struct bpf_object *obj, + const char *name_load) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *name = bpf_program__name(prog); + + if (!strcmp(name_load, name)) + bpf_program__set_autoload(prog, true); + else + bpf_program__set_autoload(prog, false); + } +} + void test_reference_tracking(void) { const char *file = "test_sk_lookup_kern.o"; @@ -9,44 +24,49 @@ void test_reference_tracking(void) .object_name = obj_name, .relaxed_maps = true, ); - struct bpf_object *obj; + struct bpf_object *obj_iter, *obj = NULL; struct bpf_program *prog; __u32 duration = 0; int err = 0; - obj = bpf_object__open_file(file, &open_opts); - if (!ASSERT_OK_PTR(obj, "obj_open_file")) + obj_iter = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj_iter, "obj_iter_open_file")) return; - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", + if (CHECK(strcmp(bpf_object__name(obj_iter), obj_name), "obj_name", "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + bpf_object__name(obj_iter), obj_name)) goto cleanup; - bpf_object__for_each_program(prog, obj) { - const char *title; + bpf_object__for_each_program(prog, obj_iter) { + const char *name; - /* Ignore .text sections */ - title = bpf_program__section_name(prog); - if (strstr(title, ".text") != NULL) + name = bpf_program__name(prog); + if (!test__start_subtest(name)) continue; - if (!test__start_subtest(title)) - continue; + obj = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj, "obj_open_file")) + goto cleanup; + toggle_object_autoload_progs(obj, name); /* Expect verifier failure if test name has 'err' */ - if (strstr(title, "err_") != NULL) { + if (strncmp(name, "err_", sizeof("err_") - 1) == 0) { libbpf_print_fn_t old_print_fn; old_print_fn = libbpf_set_print(NULL); - err = !bpf_program__load(prog, "GPL", 0); + err = !bpf_object__load(obj); libbpf_set_print(old_print_fn); } else { - err = bpf_program__load(prog, "GPL", 0); + err = bpf_object__load(obj); } - CHECK(err, title, "\n"); + ASSERT_OK(err, name); + + bpf_object__close(obj); + obj = NULL; } cleanup: bpf_object__close(obj); + bpf_object__close(obj_iter); } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3a469099f30d..1d272e05188e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -48,7 +48,7 @@ configure_stack(void) return false; sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", "direct-action object-file ./test_sk_assign.o", - "section classifier/sk_assign_test", + "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", "run with -vv for more info\n")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 51fac975b316..bc34f7773444 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,7 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -15,23 +15,23 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) return -1; } - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) { - log_err("Failed to find %s BPF program", title); + log_err("Failed to find %s BPF program", name); return -1; } err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, attach_type, BPF_F_ALLOW_MULTI); if (err) { - log_err("Failed to attach %s BPF program", title); + log_err("Failed to attach %s BPF program", name); return -1; } return 0; } -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -42,7 +42,7 @@ static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) if (err) return -1; - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) return -1; @@ -89,7 +89,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) goto detach; @@ -113,7 +113,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent"); + err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); if (err) goto detach; @@ -157,7 +157,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) { log_err("Failed to detach child program"); goto detach; @@ -198,8 +198,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt/child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt/parent"); + prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); + prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); return err; } @@ -236,7 +236,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt"); + err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -263,7 +263,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt"); + err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -289,8 +289,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt"); + prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); + prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 7bf3a7a97d7b..9825f1f7bfcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -21,7 +21,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -38,9 +38,9 @@ static void test_tailcall_1(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -70,9 +70,9 @@ static void test_tailcall_1(void) err, errno, retval); for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -92,9 +92,9 @@ static void test_tailcall_1(void) for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { j = bpf_map__def(prog_array)->max_entries - 1 - i; - snprintf(prog_name, sizeof(prog_name), "classifier/%i", j); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -159,7 +159,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -176,9 +176,9 @@ static void test_tailcall_2(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -233,7 +233,7 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -249,7 +249,7 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -329,7 +329,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -354,9 +354,9 @@ static void test_tailcall_4(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -417,7 +417,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -442,9 +442,9 @@ static void test_tailcall_5(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -503,7 +503,7 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -521,9 +521,9 @@ static void test_tailcall_bpf2bpf_1(void) /* nop -> jmp */ for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -587,7 +587,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -603,7 +603,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -665,7 +665,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -682,9 +682,9 @@ static void test_tailcall_bpf2bpf_3(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -762,7 +762,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -779,9 +779,9 @@ static void test_tailcall_bpf2bpf_4(bool noise) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index d39bc00feb45..e47835f0a674 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -10,7 +10,7 @@ void test_trace_printk(void) { - int err, iter = 0, duration = 0, found = 0; + int err = 0, iter = 0, found = 0; struct trace_printk__bss *bss; struct trace_printk *skel; char *buf = NULL; @@ -18,25 +18,24 @@ void test_trace_printk(void) size_t buflen; skel = trace_printk__open(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "trace_printk__open")) return; - ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]"); skel->rodata->fmt[0] = 't'; err = trace_printk__load(skel); - if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__load")) goto cleanup; bss = skel->bss; err = trace_printk__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__attach")) goto cleanup; fp = fopen(TRACEBUF, "r"); - if (CHECK(fp == NULL, "could not open trace buffer", - "error %d opening %s", errno, TRACEBUF)) + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) goto cleanup; /* We do not want to wait forever if this test fails... */ @@ -46,14 +45,10 @@ void test_trace_printk(void) usleep(1); trace_printk__detach(skel); - if (CHECK(bss->trace_printk_ran == 0, - "bpf_trace_printk never ran", - "ran == %d", bss->trace_printk_ran)) + if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran")) goto cleanup; - if (CHECK(bss->trace_printk_ret <= 0, - "bpf_trace_printk returned <= 0 value", - "got %d", bss->trace_printk_ret)) + if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret")) goto cleanup; /* verify our search string is in the trace buffer */ @@ -66,8 +61,7 @@ void test_trace_printk(void) break; } - if (CHECK(!found, "message from bpf_trace_printk not found", - "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + if (!ASSERT_EQ(found, bss->trace_printk_ran, "found")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c new file mode 100644 index 000000000000..61a24e62e1a0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <test_progs.h> + +#include "trace_vprintk.lskel.h" + +#define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" +#define SEARCHMSG "1,2,3,4,5,6,7,8,9,10" + +void test_trace_vprintk(void) +{ + int err = 0, iter = 0, found = 0; + struct trace_vprintk__bss *bss; + struct trace_vprintk *skel; + char *buf = NULL; + FILE *fp = NULL; + size_t buflen; + + skel = trace_vprintk__open_and_load(); + if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load")) + goto cleanup; + + bss = skel->bss; + + err = trace_vprintk__attach(skel); + if (!ASSERT_OK(err, "trace_vprintk__attach")) + goto cleanup; + + fp = fopen(TRACEBUF, "r"); + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) + goto cleanup; + + /* We do not want to wait forever if this test fails... */ + fcntl(fileno(fp), F_SETFL, O_NONBLOCK); + + /* wait for tracepoint to trigger */ + usleep(1); + trace_vprintk__detach(skel); + + if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran")) + goto cleanup; + + if (!ASSERT_GT(bss->trace_vprintk_ret, 0, "bss->trace_vprintk_ret")) + goto cleanup; + + /* verify our search string is in the trace buffer */ + while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) { + if (strstr(buf, SEARCHMSG) != NULL) + found++; + if (found == bss->trace_vprintk_ran) + break; + if (++iter > 1000) + break; + } + + if (!ASSERT_EQ(found, bss->trace_vprintk_ran, "found")) + goto cleanup; + + if (!ASSERT_LT(bss->null_data_vprintk_ret, 0, "bss->null_data_vprintk_ret")) + goto cleanup; + +cleanup: + trace_vprintk__destroy(skel); + free(buf); + if (fp) + fclose(fp); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c new file mode 100644 index 000000000000..f3927829a55a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "test_progs.h" +#include "xdpwall.skel.h" + +void test_xdpwall(void) +{ + struct xdpwall *skel; + + skel = xdpwall__open_and_load(); + ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?"); + + xdpwall__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 95a5a0778ed7..f266c757b3df 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -19,9 +19,8 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -int _version SEC("version") = 1; #define PROG(F) PROG_(F, _##F) -#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME +#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c index a25373002055..3f81ff92184c 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c index a149f33bc533..d662db27fe4a 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c index 75e8e1069fe7..df918b2469da 100644 --- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -47,7 +47,7 @@ check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, u32 arraymap_output = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c index 913dd91aafff..276994d5c0c7 100644 --- a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c @@ -78,7 +78,7 @@ int hashmap_output = 0; int hashmap_elems = 0; int percpu_map_elems = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 55e283050cab..7236da72ce80 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -9,8 +9,8 @@ char _license[] SEC("license") = "GPL"; struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); #define _(P) (__builtin_preserve_access_index(P)) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 470f8723e463..8a8cf59017aa 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -8,7 +8,7 @@ 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; -SEC("classifier") +SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; @@ -23,7 +23,7 @@ int kfunc_call_test2(struct __sk_buff *skb) return bpf_kfunc_call_test2((struct sock *)sk, 1, 2); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 5fbd9e232d44..c1fdecabeabf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -33,7 +33,7 @@ int __noinline f1(struct __sk_buff *skb) return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { return f1(skb); diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c index 25467d13c356..b3fcb5274ee0 100644 --- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -11,8 +11,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c index 7f2eaa2f89f8..992b7861003a 100644 --- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -25,7 +25,7 @@ out: return ip; } -SEC("classifier/cls") +SEC("tc") int main_prog(struct __sk_buff *skb) { struct iphdr *ip = NULL; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 4797dc985064..73872c535cbb 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -7,22 +7,22 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_rx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_tx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_msg SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 9d8c212dde9f..177a59069dae 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -4,9 +4,8 @@ #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; -SEC("cgroup/getsockopt/child") +SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; @@ -29,7 +28,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) return 1; } -SEC("cgroup/getsockopt/parent") +SEC("cgroup/getsockopt") int _getsockopt_parent(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 7115bcefbe8a..8159a0b4a69a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -11,8 +11,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -20,7 +20,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { /* Multiple locations to make sure we patch @@ -45,4 +45,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 0431e4fe7efd..a5ff53e61702 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -10,41 +10,41 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); return 0; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 2); return 1; } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { return 2; } -SEC("classifier/3") -int bpf_func_3(struct __sk_buff *skb) +SEC("tc") +int classifier_3(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 4); return 3; } -SEC("classifier/4") -int bpf_func_4(struct __sk_buff *skb) +SEC("tc") +int classifier_4(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 3); return 4; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -56,4 +56,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 910858fe078a..f60bcd7b8d4b 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -12,15 +12,15 @@ struct { int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; bpf_tail_call_static(skb, &jmp_table, 0); return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -28,4 +28,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index bd4be135c39d..a56bbc2313ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call(skb, &jmp_table, selector); @@ -30,4 +30,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index adf30a33064e..8d03496eb6ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { int idx = 0; @@ -37,4 +37,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c index 0f4a811cc028..d77b8abd62f3 100644 --- a/tools/testing/selftests/bpf/progs/tailcall6.c +++ b/tools/testing/selftests/bpf/progs/tailcall6.c @@ -12,8 +12,8 @@ struct { int count, which; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; if (__builtin_constant_p(which)) @@ -22,7 +22,7 @@ int bpf_func_0(struct __sk_buff *skb) return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { if (__builtin_constant_p(which)) diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c index 0103f3dd9f02..8c91428deb90 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c @@ -10,8 +10,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -26,7 +26,7 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); @@ -35,4 +35,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 3cc4c12817b5..ce97d141daee 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -22,14 +22,14 @@ int subprog_tail(struct __sk_buff *skb) int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; return subprog_tail(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -38,4 +38,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c index 0d5482bea6c9..7fab39a3bb12 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c @@ -33,23 +33,23 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { volatile char arr[128] = {}; return subprog_tail2(skb); } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { volatile char arr[128] = {}; return skb->len * 3; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { volatile char arr[128] = {}; @@ -58,4 +58,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index e89368a50b97..b67e8022d500 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -50,30 +50,29 @@ int subprog_tail(struct __sk_buff *skb) return skb->len; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { return subprog_tail_2(skb); } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { count++; return subprog_tail_2(skb); } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { return subprog_tail_1(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { return subprog_tail(skb); } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c index c1e0c8c7c55f..c218cf8989a9 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -21,8 +21,8 @@ struct inner_map_sz2 { struct outer_arr { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); /* it's possible to use anonymous struct as inner map definition here */ __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -61,8 +61,8 @@ struct inner_map_sz4 { struct outer_arr_dyn { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(map_flags, BPF_F_INNER_MAP); @@ -81,7 +81,7 @@ struct outer_arr_dyn { struct outer_hash { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 5); - __uint(key_size, sizeof(int)); + __type(key, int); /* Here everything works flawlessly due to reuse of struct inner_map * and compiler will complain at the attempt to use non-inner_map * references below. This is great experience. @@ -111,8 +111,8 @@ struct sockarr_sz2 { struct outer_sockarr_sz1 { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct sockarr_sz1); } outer_sockarr SEC(".maps") = { .values = { (void *)&sockarr_sz1 }, diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index 9a6b85dd52d2..e2bea4da194b 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -145,7 +145,7 @@ release: return TC_ACT_OK; } -SEC("classifier/ingress") +SEC("tc") int cls_ingress(struct __sk_buff *skb) { struct ipv6hdr *ip6h; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c index 77e47b9e4446..4faba88e45a5 100644 --- a/tools/testing/selftests/bpf/progs/test_cgroup_link.c +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -6,14 +6,14 @@ int calls = 0; int alt_calls = 0; -SEC("cgroup_skb/egress1") +SEC("cgroup_skb/egress") int egress(struct __sk_buff *skb) { __sync_fetch_and_add(&calls, 1); return 1; } -SEC("cgroup_skb/egress2") +SEC("cgroup_skb/egress") int egress_alt(struct __sk_buff *skb) { __sync_fetch_and_add(&alt_calls, 1); diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 71184af57749..2ec1de11a3ae 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -153,7 +153,7 @@ int xdp_input_len_exceed(struct xdp_md *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_use_helper(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -172,7 +172,7 @@ out: return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu(struct __sk_buff *ctx) { __u32 ifindex = GLOBAL_USER_IFINDEX; @@ -196,7 +196,7 @@ int tc_exceed_mtu(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu_da(struct __sk_buff *ctx) { /* SKB Direct-Access variant */ @@ -223,7 +223,7 @@ int tc_exceed_mtu_da(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_minus_delta(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -245,7 +245,7 @@ int tc_minus_delta(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -265,7 +265,7 @@ int tc_input_len(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len_exceed(struct __sk_buff *ctx) { int retval = BPF_DROP; /* Fail */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index e2a5acc4785c..2833ad722cb7 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -928,7 +928,7 @@ static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) } } -SEC("classifier/cls_redirect") +SEC("tc") int cls_redirect(struct __sk_buff *skb) { metrics_t *metrics = get_global_metrics(); diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 1319be1c54ba..719e314ef3e4 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -68,7 +68,7 @@ static struct foo struct3 = { bpf_map_update_elem(&result_##map, &key, var, 0); \ } while (0) -SEC("classifier/static_data_load") +SEC("tc") int load_static_data(struct __sk_buff *skb) { static const __u64 bar = ~0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index 880260f6d536..7b42dad187b8 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -38,7 +38,7 @@ int f3(int val, struct __sk_buff *skb, int var) return skb->ifindex * val * var; } -SEC("classifier/test") +SEC("tc") int test_cls(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 86f0ecb304fc..01bf8275dfd6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func3.c +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -54,7 +54,7 @@ int f8(struct __sk_buff *skb) } #endif -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { #ifndef NO_FN8 diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index 260c25b827ef..9248d03e0d06 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(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 69e19c64e10b..af8c78bdfb25 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func6.c +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(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 309b3f6136bd..6cb8e2f5254c 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func7.c +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -10,7 +10,7 @@ void foo(struct __sk_buff *skb) skb->tc_index = 0; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { foo(skb); diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 1cfeb940cf9f..a6d91932dcd5 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -9,21 +9,19 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(__u32)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } mim_array SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(int)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } mim_hash SEC(".maps"); -SEC("xdp_mimtest") +SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { int value = 123; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c index 703c08e06442..9c7d75cf0bd6 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c @@ -13,7 +13,7 @@ struct inner { struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 0); /* This will make map creation to fail */ - __uint(key_size, sizeof(__u32)); + __type(key, __u32); __array(values, struct inner); } mim SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index 6077a025092c..2c121c5d66a7 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -293,7 +293,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) return check_active_hdr_in(skops); } -SEC("sockops/misc_estab") +SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c index fb22de7c365d..1249a945699f 100644 --- a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c +++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c @@ -7,15 +7,15 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } array_1 SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __uint(map_flags, BPF_F_PRESERVE_ELEMS); } array_2 SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index 8207a2dc2f9d..d37ce29fd393 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -8,8 +8,8 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); SEC("tp/raw_syscalls/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 852051064507..3cfd88141ddc 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -97,7 +97,7 @@ int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) return 0; } -SEC("classifier/test_pkt_access") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 610c74ea9f64..d1839366f3e1 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -7,8 +7,6 @@ #include <linux/pkt_cls.h> #include <bpf/bpf_helpers.h> -int _version SEC("version") = 1; - #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define TEST_FIELD(TYPE, FIELD, MASK) \ { \ @@ -27,7 +25,7 @@ int _version SEC("version") = 1; } #endif -SEC("classifier/test_pkt_md_access") +SEC("tc") int test_pkt_md_access(struct __sk_buff *skb) { TEST_FIELD(__u8, len, 0xFF); diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 89b3532ccc75..8812a90da4eb 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -8,13 +8,37 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "" +#endif + static struct sockaddr_in old; -SEC("kprobe/__sys_connect") +SEC("kprobe/" SYS_PREFIX "sys_connect") int BPF_KPROBE(handle_sys_connect) { - void *ptr = (void *)PT_REGS_PARM2(ctx); +#if SYSCALL_WRAPPER == 1 + struct pt_regs *real_regs; +#endif struct sockaddr_in new; + void *ptr; + +#if SYSCALL_WRAPPER == 0 + ptr = (void *)PT_REGS_PARM2(ctx); +#else + real_regs = (struct pt_regs *)PT_REGS_PARM1(ctx); + bpf_probe_read_kernel(&ptr, sizeof(ptr), &PT_REGS_PARM2(real_regs)); +#endif bpf_probe_read_user(&old, sizeof(old), ptr); __builtin_memset(&new, 0xab, sizeof(new)); diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 26e77dcc7e91..0f9bc258225e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -24,8 +24,8 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } outer_map SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 1ecd987005d2..02f79356d5eb 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -36,7 +36,6 @@ struct { .pinning = PIN_GLOBAL_NS, }; -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -159,7 +158,7 @@ assign: return ret; } -SEC("classifier/sk_assign_test") +SEC("tc") int bpf_sk_assign_test(struct __sk_buff *skb) { struct bpf_sock_tuple *tuple, ln = {0}; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index ac6f7f205e25..48534d810391 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -72,32 +72,32 @@ static const __u16 DST_PORT = 7007; /* Host byte order */ static const __u32 DST_IP4 = IP4(127, 0, 0, 1); static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); -SEC("sk_lookup/lookup_pass") +SEC("sk_lookup") int lookup_pass(struct bpf_sk_lookup *ctx) { return SK_PASS; } -SEC("sk_lookup/lookup_drop") +SEC("sk_lookup") int lookup_drop(struct bpf_sk_lookup *ctx) { return SK_DROP; } -SEC("sk_reuseport/reuse_pass") +SEC("sk_reuseport") int reuseport_pass(struct sk_reuseport_md *ctx) { return SK_PASS; } -SEC("sk_reuseport/reuse_drop") +SEC("sk_reuseport") int reuseport_drop(struct sk_reuseport_md *ctx) { return SK_DROP; } /* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ -SEC("sk_lookup/redir_port") +SEC("sk_lookup") int redir_port(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -116,7 +116,7 @@ int redir_port(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip4") +SEC("sk_lookup") int redir_ip4(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -139,7 +139,7 @@ int redir_ip4(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip6") +SEC("sk_lookup") int redir_ip6(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -164,7 +164,7 @@ int redir_ip6(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a") +SEC("sk_lookup") int select_sock_a(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -179,7 +179,7 @@ int select_sock_a(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a_no_reuseport") +SEC("sk_lookup") int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -194,7 +194,7 @@ int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_reuseport/select_sock_b") +SEC("sk_reuseport") int select_sock_b(struct sk_reuseport_md *ctx) { __u32 key = KEY_SERVER_B; @@ -205,7 +205,7 @@ int select_sock_b(struct sk_reuseport_md *ctx) } /* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ -SEC("sk_lookup/sk_assign_eexist") +SEC("sk_lookup") int sk_assign_eexist(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -238,7 +238,7 @@ out: } /* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ -SEC("sk_lookup/sk_assign_replace_flag") +SEC("sk_lookup") int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -270,7 +270,7 @@ out: } /* Check that bpf_sk_assign(sk=NULL) is accepted. */ -SEC("sk_lookup/sk_assign_null") +SEC("sk_lookup") int sk_assign_null(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk = NULL; @@ -313,7 +313,7 @@ out: } /* Check that selected sk is accessible through context. */ -SEC("sk_lookup/access_ctx_sk") +SEC("sk_lookup") int access_ctx_sk(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk1 = NULL, *sk2 = NULL; @@ -379,7 +379,7 @@ out: * are not covered because they give bogus results, that is the * verifier ignores the offset. */ -SEC("sk_lookup/ctx_narrow_access") +SEC("sk_lookup") int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -553,7 +553,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) } /* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ -SEC("sk_lookup/sk_assign_esocknosupport") +SEC("sk_lookup") int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -578,28 +578,28 @@ out: return ret; } -SEC("sk_lookup/multi_prog_pass1") +SEC("sk_lookup") int multi_prog_pass1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_pass2") +SEC("sk_lookup") int multi_prog_pass2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_drop1") +SEC("sk_lookup") int multi_prog_drop1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_DROP; } -SEC("sk_lookup/multi_prog_drop2") +SEC("sk_lookup") int multi_prog_drop2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); @@ -623,7 +623,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir1") +SEC("sk_lookup") int multi_prog_redir1(struct bpf_sk_lookup *ctx) { int ret; @@ -633,7 +633,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir2") +SEC("sk_lookup") int multi_prog_redir2(struct bpf_sk_lookup *ctx) { int ret; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index 8249075f088f..40f161480a2f 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -15,7 +15,6 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -53,8 +52,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, return result; } -SEC("classifier/sk_lookup_success") -int bpf_sk_lookup_test0(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; void *data = (void *)(long)skb->data; @@ -79,8 +78,8 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb) return sk ? TC_ACT_OK : TC_ACT_UNSPEC; } -SEC("classifier/sk_lookup_success_simple") -int bpf_sk_lookup_test1(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success_simple(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -91,8 +90,8 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb) return 0; } -SEC("classifier/err_use_after_free") -int bpf_sk_lookup_uaf(struct __sk_buff *skb) +SEC("tc") +int err_use_after_free(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -106,8 +105,8 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb) return family; } -SEC("classifier/err_modify_sk_pointer") -int bpf_sk_lookup_modptr(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -121,8 +120,8 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb) return 0; } -SEC("classifier/err_modify_sk_or_null_pointer") -int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_or_null_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -135,8 +134,8 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) return 0; } -SEC("classifier/err_no_release") -int bpf_sk_lookup_test2(struct __sk_buff *skb) +SEC("tc") +int err_no_release(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; @@ -144,8 +143,8 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_twice") -int bpf_sk_lookup_test3(struct __sk_buff *skb) +SEC("tc") +int err_release_twice(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -156,8 +155,8 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_unchecked") -int bpf_sk_lookup_test4(struct __sk_buff *skb) +SEC("tc") +int err_release_unchecked(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -173,8 +172,8 @@ void lookup_no_release(struct __sk_buff *skb) bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); } -SEC("classifier/err_no_release_subcall") -int bpf_sk_lookup_test5(struct __sk_buff *skb) +SEC("tc") +int err_no_release_subcall(struct __sk_buff *skb) { lookup_no_release(skb); return 0; diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c index bb3fbf1a29e3..507215791c5b 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -14,7 +14,7 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("classifier/test_skb_helpers") +SEC("tc") int test_skb_helpers(struct __sk_buff *skb) { struct task_struct *task; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a1cc58b10c7c..00f1456aaeda 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -56,7 +56,7 @@ int prog_stream_verdict(struct __sk_buff *skb) return verdict; } -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { unsigned int *count; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c index 2d31f66e4f23..3c69aa971738 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c @@ -9,7 +9,7 @@ struct { __type(value, __u64); } sock_map SEC(".maps"); -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { return SK_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c index 9d0c9f28cab2..6d64ea536e3d 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_update.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -24,7 +24,7 @@ struct { __type(value, __u64); } dst_sock_hash SEC(".maps"); -SEC("classifier/copy_sock_map") +SEC("tc") int copy_sock_map(void *ctx) { struct bpf_sock *sk; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index 0cf0134631b4..7449fdb1763b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -28,8 +28,8 @@ struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 128); __uint(map_flags, BPF_F_STACK_BUILD_ID); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 00ed48672620..a8233e7f173b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -27,8 +27,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index 18a3a7ed924a..d28ca8d1f3d0 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -5,7 +5,7 @@ /* Dummy prog to test TC-BPF API */ -SEC("classifier") +SEC("tc") int cls(struct __sk_buff *skb) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index 0c93d326a663..3e32ea375ab4 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -70,7 +70,7 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -83,7 +83,7 @@ int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; @@ -108,7 +108,7 @@ int tc_dst(struct __sk_buff *skb) return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index f7ab69cf018e..ec4cce19362d 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,7 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -143,13 +143,13 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return tc_redir(skb); diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fe818cd5f010..365eacb5dc34 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -16,31 +16,31 @@ volatile const __u32 IFINDEX_DST; static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { return TC_ACT_SHOT; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("classifier/dst_ingress_l3") +SEC("tc") int tc_dst_l3(struct __sk_buff *skb) { return bpf_redirect(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress_l3") +SEC("tc") int tc_src_l3(struct __sk_buff *skb) { __u16 proto = skb->protocol; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 47cbe2eeae43..cd747cd93dbe 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -148,7 +148,7 @@ release: bpf_sk_release(sk); } -SEC("clsact/check_syncookie") +SEC("tc") int check_syncookie_clsact(struct __sk_buff *skb) { check_syncookie(skb, (void *)(long)skb->data, @@ -156,7 +156,7 @@ int check_syncookie_clsact(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("xdp/check_syncookie") +SEC("xdp") int check_syncookie_xdp(struct xdp_md *ctx) { check_syncookie(ctx, (void *)(long)ctx->data, diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c index 678bd0fad29e..5f4e87ee949a 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -594,7 +594,7 @@ static int handle_parse_hdr(struct bpf_sock_ops *skops) return CG_OK; } -SEC("sockops/estab") +SEC("sockops") int estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ac63410bb541..24e9344994ef 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -24,8 +24,8 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 2); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } perf_event_map SEC(".maps"); int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 31f9bce37491..e6aa2fc6ce6b 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -210,7 +210,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; 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 3d66599eee2e..199c61b7d062 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 @@ -2,7 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_adjust_tail_grow") +SEC("xdp") int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index 22065a9cfb25..b7448253d135 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -9,9 +9,7 @@ #include <linux/if_ether.h> #include <bpf/bpf_helpers.h> -int _version SEC("version") = 1; - -SEC("xdp_adjust_tail_shrink") +SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index a038e827f850..58cf4345f5cc 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -36,8 +36,8 @@ struct meta { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); __u64 test_result_fentry = 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c index b360ba2bd441..807bf895f42c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_dm_log") +SEC("xdp") int xdpdm_devlog(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c index eb93ea95d1d8..ee7d6ac0f615 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_link.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -5,7 +5,7 @@ char LICENSE[] SEC("license") = "GPL"; -SEC("xdp/handler") +SEC("xdp") int xdp_handler(struct xdp_md *xdp) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index fcabcda30ba3..27eb52dda92c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -206,7 +206,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 3a67921f62b5..596c4e71bf3a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -797,7 +797,7 @@ out: return XDP_DROP; } -SEC("xdp-test-v4") +SEC("xdp") int balancer_ingress_v4(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; @@ -816,7 +816,7 @@ int balancer_ingress_v4(struct xdp_md *ctx) return XDP_DROP; } -SEC("xdp-test-v6") +SEC("xdp") int balancer_ingress_v6(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 59ee4f182ff8..532025057711 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -12,13 +12,13 @@ struct { __uint(max_entries, 4); } cpu_map SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&cpu_map, 1, 0); } -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 0ac086497722..1e6b9c38ea6d 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -9,7 +9,7 @@ struct { __uint(max_entries, 4); } dm_ports SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&dm_ports, 1, 0); @@ -18,7 +18,7 @@ int xdp_redir_prog(struct xdp_md *ctx) /* invalid program on DEVMAP entry; * SEC name means expected attach type not set */ -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c new file mode 100644 index 000000000000..d327241ba047 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int null_data_vprintk_ret = 0; +int trace_vprintk_ret = 0; +int trace_vprintk_ran = 0; + +SEC("fentry/__x64_sys_nanosleep") +int sys_enter(void *ctx) +{ + static const char one[] = "1"; + static const char three[] = "3"; + static const char five[] = "5"; + static const char seven[] = "7"; + static const char nine[] = "9"; + static const char f[] = "%pS\n"; + + /* runner doesn't search for \t, just ensure it compiles */ + bpf_printk("\t"); + + trace_vprintk_ret = __bpf_vprintk("%s,%d,%s,%d,%s,%d,%s,%d,%s,%d %d\n", + one, 2, three, 4, five, 6, seven, 8, nine, 10, ++trace_vprintk_ran); + + /* non-NULL fmt w/ NULL data should result in error */ + null_data_vprintk_ret = bpf_trace_vprintk(f, sizeof(f), NULL, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index ea25e8881992..d988b2e0cee8 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -4,7 +4,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 880debcbcd65..8395782b6e0a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -34,7 +34,7 @@ struct { __uint(max_entries, 128); } mac_map SEC(".maps"); -SEC("xdp_redirect_map_multi") +SEC("xdp") int xdp_redirect_map_multi_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -63,7 +63,7 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx) } /* The following 2 progs are for 2nd devmap prog testing */ -SEC("xdp_redirect_map_ingress") +SEC("xdp") int xdp_redirect_map_all_prog(struct xdp_md *ctx) { return bpf_redirect_map(&map_egress, 0, diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 6b9ca40bd1f4..4ad73847b8a5 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -86,7 +86,7 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type) return XDP_TX; } -SEC("xdpclient") +SEC("xdp") int xdping_client(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -150,7 +150,7 @@ int xdping_client(struct xdp_md *ctx) return XDP_TX; } -SEC("xdpserver") +SEC("xdp") int xdping_server(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c new file mode 100644 index 000000000000..7a891a0c3a39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdpwall.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <stdbool.h> +#include <stdint.h> +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +enum pkt_parse_err { + NO_ERR, + BAD_IP6_HDR, + BAD_IP4GUE_HDR, + BAD_IP6GUE_HDR, +}; + +enum pkt_flag { + TUNNEL = 0x1, + TCP_SYN = 0x2, + QUIC_INITIAL_FLAG = 0x4, + TCP_ACK = 0x8, + TCP_RST = 0x10 +}; + +struct v4_lpm_key { + __u32 prefixlen; + __u32 src; +}; + +struct v4_lpm_val { + struct v4_lpm_key key; + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, struct in6_addr); + __type(value, bool); +} v6_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, __u32); + __type(value, bool); +} v4_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(max_entries, 16); + __uint(key_size, sizeof(struct v4_lpm_key)); + __uint(value_size, sizeof(struct v4_lpm_val)); + __uint(map_flags, BPF_F_NO_PREALLOC); +} v4_lpm_val_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u8); +} tcp_port_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u16); +} udp_port_map SEC(".maps"); + +enum ip_type { V4 = 1, V6 = 2 }; + +struct fw_match_info { + __u8 v4_src_ip_match; + __u8 v6_src_ip_match; + __u8 v4_src_prefix_match; + __u8 v4_dst_prefix_match; + __u8 tcp_dp_match; + __u16 udp_sp_match; + __u16 udp_dp_match; + bool is_tcp; + bool is_tcp_syn; +}; + +struct pkt_info { + enum ip_type type; + union { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } ip; + int sport; + int dport; + __u16 trans_hdr_offset; + __u8 proto; + __u8 flags; +}; + +static __always_inline struct ethhdr *parse_ethhdr(void *data, void *data_end) +{ + struct ethhdr *eth = data; + + if (eth + 1 > data_end) + return NULL; + + return eth; +} + +static __always_inline __u8 filter_ipv6_addr(const struct in6_addr *ipv6addr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v6_addr_map, ipv6addr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_addr(const __u32 ipaddr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v4_addr_map, &ipaddr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_lpm(const __u32 ipaddr) +{ + struct v4_lpm_key v4_key = {}; + struct v4_lpm_val *lpm_val; + + v4_key.src = ipaddr; + v4_key.prefixlen = 32; + + lpm_val = bpf_map_lookup_elem(&v4_lpm_val_map, &v4_key); + + return lpm_val ? lpm_val->val : 0; +} + + +static __always_inline void +filter_src_dst_ip(struct pkt_info* info, struct fw_match_info* match_info) +{ + if (info->type == V6) { + match_info->v6_src_ip_match = + filter_ipv6_addr(&info->ip.ipv6->saddr); + } else if (info->type == V4) { + match_info->v4_src_ip_match = + filter_ipv4_addr(info->ip.ipv4->saddr); + match_info->v4_src_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->saddr); + match_info->v4_dst_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->daddr); + } +} + +static __always_inline void * +get_transport_hdr(__u16 offset, void *data, void *data_end) +{ + if (offset > 255 || data + offset > data_end) + return NULL; + + return data + offset; +} + +static __always_inline bool tcphdr_only_contains_flag(struct tcphdr *tcp, + __u32 FLAG) +{ + return (tcp_flag_word(tcp) & + (TCP_FLAG_ACK | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)) == FLAG; +} + +static __always_inline void set_tcp_flags(struct pkt_info *info, + struct tcphdr *tcp) { + if (tcphdr_only_contains_flag(tcp, TCP_FLAG_SYN)) + info->flags |= TCP_SYN; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_ACK)) + info->flags |= TCP_ACK; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_RST)) + info->flags |= TCP_RST; +} + +static __always_inline bool +parse_tcp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct tcphdr *tcp = transport_hdr; + + if (tcp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(tcp->source); + info->dport = bpf_ntohs(tcp->dest); + set_tcp_flags(info, tcp); + + return true; +} + +static __always_inline bool +parse_udp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct udphdr *udp = transport_hdr; + + if (udp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(udp->source); + info->dport = bpf_ntohs(udp->dest); + + return true; +} + +static __always_inline __u8 filter_tcp_port(int port) +{ + __u8 *leaf = bpf_map_lookup_elem(&tcp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline __u16 filter_udp_port(int port) +{ + __u16 *leaf = bpf_map_lookup_elem(&udp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline bool +filter_transport_hdr(void *transport_hdr, void *data_end, + struct pkt_info *info, struct fw_match_info *match_info) +{ + if (info->proto == IPPROTO_TCP) { + if (!parse_tcp(info, transport_hdr, data_end)) + return false; + + match_info->is_tcp = true; + match_info->is_tcp_syn = (info->flags & TCP_SYN) > 0; + + match_info->tcp_dp_match = filter_tcp_port(info->dport); + } else if (info->proto == IPPROTO_UDP) { + if (!parse_udp(info, transport_hdr, data_end)) + return false; + + match_info->udp_dp_match = filter_udp_port(info->dport); + match_info->udp_sp_match = filter_udp_port(info->sport); + } + + return true; +} + +static __always_inline __u8 +parse_gue_v6(struct pkt_info *info, struct ipv6hdr *ip6h, void *data_end) +{ + struct udphdr *udp = (struct udphdr *)(ip6h + 1); + void *encap_data = udp + 1; + + if (udp + 1 > data_end) + return BAD_IP6_HDR; + + if (udp->dest != bpf_htons(6666)) + return NO_ERR; + + info->flags |= TUNNEL; + + if (encap_data + 1 > data_end) + return BAD_IP6GUE_HDR; + + if (*(__u8 *)encap_data & 0x30) { + struct ipv6hdr *inner_ip6h = encap_data; + + if (inner_ip6h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V6; + info->proto = inner_ip6h->nexthdr; + info->ip.ipv6 = inner_ip6h; + info->trans_hdr_offset += sizeof(struct ipv6hdr) + sizeof(struct udphdr); + } else { + struct iphdr *inner_ip4h = encap_data; + + if (inner_ip4h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V4; + info->proto = inner_ip4h->protocol; + info->ip.ipv4 = inner_ip4h; + info->trans_hdr_offset += sizeof(struct iphdr) + sizeof(struct udphdr); + } + + return NO_ERR; +} + +static __always_inline __u8 parse_ipv6_gue(struct pkt_info *info, + void *data, void *data_end) +{ + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + + if (ip6h + 1 > data_end) + return BAD_IP6_HDR; + + info->proto = ip6h->nexthdr; + info->ip.ipv6 = ip6h; + info->type = V6; + info->trans_hdr_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + + if (info->proto == IPPROTO_UDP) + return parse_gue_v6(info, ip6h, data_end); + + return NO_ERR; +} + +SEC("xdp") +int edgewall(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)(ctx->data_end); + void *data = (void *)(long)(ctx->data); + struct fw_match_info match_info = {}; + struct pkt_info info = {}; + __u8 parse_err = NO_ERR; + void *transport_hdr; + struct ethhdr *eth; + bool filter_res; + __u32 proto; + + eth = parse_ethhdr(data, data_end); + if (!eth) + return XDP_DROP; + + proto = eth->h_proto; + if (proto != bpf_htons(ETH_P_IPV6)) + return XDP_DROP; + + if (parse_ipv6_gue(&info, data, data_end)) + return XDP_DROP; + + if (info.proto == IPPROTO_ICMPV6) + return XDP_PASS; + + if (info.proto != IPPROTO_TCP && info.proto != IPPROTO_UDP) + return XDP_DROP; + + filter_src_dst_ip(&info, &match_info); + + transport_hdr = get_transport_hdr(info.trans_hdr_offset, data, + data_end); + if (!transport_hdr) + return XDP_DROP; + + filter_res = filter_transport_hdr(transport_hdr, data_end, + &info, &match_info); + if (!filter_res) + return XDP_DROP; + + if (match_info.is_tcp && !match_info.is_tcp_syn) + return XDP_PASS; + + return XDP_DROP; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py index 4fed2dc25c0a..1c2408ee1f5d 100644 --- a/tools/testing/selftests/bpf/test_bpftool.py +++ b/tools/testing/selftests/bpf/test_bpftool.py @@ -57,6 +57,11 @@ def default_iface(f): return f(*args, iface, **kwargs) return wrapper +DMESG_EMITTING_HELPERS = [ + "bpf_probe_write_user", + "bpf_trace_printk", + "bpf_trace_vprintk", + ] class TestBpftool(unittest.TestCase): @classmethod @@ -67,10 +72,7 @@ class TestBpftool(unittest.TestCase): @default_iface def test_feature_dev_json(self, iface): - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "program_types", @@ -94,10 +96,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe"]), bpftool_json(["feature"]), ] - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "system_config", @@ -121,10 +120,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe", "kernel", "full"]), bpftool_json(["feature", "probe", "full"]), ] - expected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + expected_helpers = DMESG_EMITTING_HELPERS for tc in test_cases: # Check if expected helpers are included at least once in any @@ -157,7 +153,7 @@ class TestBpftool(unittest.TestCase): not_full_set.add(helper) self.assertCountEqual(full_set - not_full_set, - {"bpf_probe_write_user", "bpf_trace_printk"}) + set(DMESG_EMITTING_HELPERS)) self.assertCountEqual(not_full_set - full_set, set()) def test_feature_macros(self): diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index 59ea56945e6c..b497bb85b667 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -112,6 +112,14 @@ setup() ip netns add "${NS2}" ip netns add "${NS3}" + # rp_filter gets confused by what these tests are doing, so disable it + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -236,11 +244,6 @@ setup() ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) sleep 1 # reduce flakiness diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 9b3617d770a5..6413c1472554 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -76,8 +76,8 @@ DIR=$(dirname $0) TEST_IF=lo MAX_PING_TRIES=5 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o" -CLSACT_SECTION="clsact/check_syncookie" -XDP_SECTION="xdp/check_syncookie" +CLSACT_SECTION="tc" +XDP_SECTION="xdp" BPF_PROG_ID=0 PROG="${DIR}/test_tcp_check_syncookie_user" diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 1ccbe804e8e1..ca1372924023 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -168,14 +168,15 @@ add_vxlan_tunnel() ip netns exec at_ns0 \ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 \ + ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF # root namespace ip link add dev $DEV type $TYPE external gbp dstport 4789 ip link set dev $DEV address 52:54:00:d9:02:00 up ip addr add dev $DEV 10.1.1.200/24 - arp -s 10.1.1.100 52:54:00:d9:01:00 + ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV } add_ip6vxlan_tunnel() diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 637fcf4fe4e3..d10cefd6eb09 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -1,5 +1,8 @@ #!/bin/sh +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + cleanup() { if [ "$?" = "0" ]; then @@ -17,7 +20,7 @@ cleanup() ip link set dev lo xdp off 2>/dev/null > /dev/null if [ $? -ne 0 ];then echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit 0 + exit $KSFT_SKIP fi set -e diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c033850886f4..57c8db9972a6 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -52,8 +52,8 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 1538373157e3..351955c2bdfd 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -88,7 +88,7 @@ setup_ns() # Add a neigh entry for IPv4 ping test ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 ip -n ns$i link set veth0 $mode obj \ - xdp_dummy.o sec xdp_dummy &> /dev/null || \ + xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}') diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index 995278e684b6..a3a1eaee26ea 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -107,9 +107,9 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index bb8b0da91686..0cbc7604a2f8 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer <hawk@kernel.org> +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then TESTNAME=xdp_vlan @@ -94,7 +97,7 @@ while true; do -h | --help ) usage; echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit 0 + exit $KSFT_SKIP ;; * ) shift @@ -117,7 +120,7 @@ fi ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit 0 + exit $KSFT_SKIP fi # Interactive mode likely require us to cleanup netns diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 0b943897aaf6..c9991c3f3bd2 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -104,3 +104,164 @@ .result = ACCEPT, .retval = POINTER_VALUE, }, +{ + "Spill and refill a u32 const scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const, refill from another half of the uninit u32 from the stack", + .insns = { + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -4+0 size 4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -6) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a u32 const scalar at non 8byte aligned stack addr. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* r4 = *(u32 *)(r10 -4), */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a umax=40 bounded scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = (*u32 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r2 += r4 R2=pkt R4=inv,umax=40 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), + /* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20), + /* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1), + /* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 842d9155d36c..79a3453dab25 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -178,9 +178,8 @@ int main(int argc, char **argv) return 1; } - main_prog = bpf_object__find_program_by_title(obj, - server ? "xdpserver" : - "xdpclient"); + main_prog = bpf_object__find_program_by_name(obj, + server ? "xdping_server" : "xdping_client"); if (main_prog) prog_fd = bpf_program__fd(main_prog); if (!main_prog || prog_fd < 0) { diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 127bcde06c86..6c7cf8aadc79 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -384,6 +384,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, ifobj->umem = &ifobj->umem_arr[0]; ifobj->xsk = &ifobj->xsk_arr[0]; ifobj->use_poll = false; + ifobj->pacing_on = true; ifobj->pkt_stream = test->pkt_stream_default; if (i == 0) { @@ -445,6 +446,12 @@ static void test_spec_set_name(struct test_spec *test, const char *name) strncpy(test->name, name, MAX_TEST_NAME_SIZE); } +static void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) + pkt_stream->rx_pkt_nb = 0; +} + static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) { if (pkt_nb >= pkt_stream->nb_pkts) @@ -507,8 +514,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb pkt_stream->nb_pkts = nb_pkts; for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + - DEFAULT_OFFSET; + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size; pkt_stream->pkts[i].len = pkt_len; pkt_stream->pkts[i].payload = i; @@ -536,14 +542,14 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) test->ifobj_rx->pkt_stream = pkt_stream; } -static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset) +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) { struct xsk_umem_info *umem = test->ifobj_tx->umem; struct pkt_stream *pkt_stream; u32 i; pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default); - for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) { + for (i = 1; i < test->pkt_stream_default->nb_pkts; i += 2) { pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset; pkt_stream->pkts[i].len = pkt_len; } @@ -635,6 +641,25 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "---------------------------------------\n"); } +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, + u64 pkt_stream_addr) +{ + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset = 0; + + if (!pkt_stream->use_addr_for_fill) + pkt_stream_addr = 0; + + expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_test_result_fail("ERROR: [%s] expected [%u], got [%u]\n", __func__, expected_offset, + offset); + return false; +} + static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); @@ -717,13 +742,15 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * struct pollfd *fds) { struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); + struct xsk_umem_info *umem = xsk->umem; u32 idx_rx = 0, idx_fq = 0, rcvd, i; + u32 total = 0; int ret; while (pkt) { rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); @@ -731,16 +758,16 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * continue; } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } for (i = 0; i < rcvd; i++) { @@ -757,15 +784,25 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len)) + + if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len)) + return; + if (!is_offset_correct(umem, pkt_stream, addr, pkt->addr)) return; - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; pkt = pkt_stream_get_next_rx_pkt(pkt_stream); } - xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_prod__submit(&umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= rcvd; + total += rcvd; + if (pkts_in_flight < umem->num_frames) + pthread_cond_signal(&pacing_cond); + pthread_mutex_unlock(&pacing_mutex); } } @@ -791,10 +828,19 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) valid_pkts++; } + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + if (ifobject->pacing_on && pkts_in_flight >= ifobject->umem->num_frames - BATCH_SIZE) { + kick_tx(xsk); + pthread_cond_wait(&pacing_cond, &pacing_mutex); + } + pthread_mutex_unlock(&pacing_mutex); + xsk_ring_prod__submit(&xsk->tx, i); xsk->outstanding_tx += valid_pkts; - complete_pkts(xsk, BATCH_SIZE); + complete_pkts(xsk, i); + usleep(10); return i; } @@ -813,8 +859,6 @@ static void send_pkts(struct ifobject *ifobject) fds.events = POLLOUT; while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - u32 sent; - if (ifobject->use_poll) { int ret; @@ -826,9 +870,7 @@ static void send_pkts(struct ifobject *ifobject) continue; } - sent = __send_pkts(ifobject, pkt_cnt); - pkt_cnt += sent; - usleep(10); + pkt_cnt += __send_pkts(ifobject, pkt_cnt); } wait_for_tx_completion(ifobject->xsk); @@ -913,18 +955,17 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; u32 ctr = 0; void *bufs; + int ret; bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); if (bufs == MAP_FAILED) exit_with_error(errno); - while (ctr++ < SOCK_RECONF_CTR) { - int ret; - - ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); - if (ret) - exit_with_error(-ret); + ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); + if (ret) + exit_with_error(-ret); + while (ctr++ < SOCK_RECONF_CTR) { ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], ifobject, i); if (!ret) @@ -971,13 +1012,18 @@ static void *worker_testapp_validate_tx(void *arg) static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) { - u32 idx = 0, i; + u32 idx = 0, i, buffers_to_fill; int ret; - ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) { + for (i = 0; i < buffers_to_fill; i++) { u64 addr; if (pkt_stream->use_addr_for_fill) { @@ -987,12 +1033,12 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream break; addr = pkt->addr; } else { - addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET; + addr = i * umem->frame_size; } *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + xsk_ring_prod__submit(&umem->fq, buffers_to_fill); } static void *worker_testapp_validate_rx(void *arg) @@ -1032,6 +1078,8 @@ static void testapp_validate_traffic(struct test_spec *test) exit_with_error(errno); test->current_step++; + pkt_stream_reset(ifobj_rx->pkt_stream); + pkts_in_flight = 0; /*Spawn RX thread */ pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); @@ -1108,6 +1156,13 @@ static void testapp_bpf_res(struct test_spec *test) testapp_validate_traffic(test); } +static void testapp_headroom(struct test_spec *test) +{ + test_spec_set_name(test, "UMEM_HEADROOM"); + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + testapp_validate_traffic(test); +} + static void testapp_stats(struct test_spec *test) { int i; @@ -1115,6 +1170,8 @@ static void testapp_stats(struct test_spec *test) for (i = 0; i < STAT_TEST_TYPE_MAX; i++) { test_spec_reset(test); stat_test_type = i; + /* No or few packets will be received so cannot pace packets */ + test->ifobj_tx->pacing_on = false; switch (stat_test_type) { case STAT_TEST_RX_DROPPED: @@ -1181,7 +1238,7 @@ static bool testapp_unaligned(struct test_spec *test) test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32); + pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); test->ifobj_rx->pkt_stream->use_addr_for_fill = true; testapp_validate_traffic(test); @@ -1189,6 +1246,15 @@ static bool testapp_unaligned(struct test_spec *test) return true; } +static void testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + + 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) { struct pkt pkts[] = { @@ -1270,6 +1336,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ test_spec_set_name(test, "RUN_TO_COMPLETION"); testapp_validate_traffic(test); break; + case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: + test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); + testapp_single_pkt(test); + break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; @@ -1305,6 +1375,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ if (!testapp_unaligned(test)) return; break; + case TEST_TYPE_HEADROOM: + testapp_headroom(test); + break; default: break; } diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 5ac4a5e64744..2f705f44b748 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -35,13 +35,13 @@ #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define BATCH_SIZE 8 +#define BATCH_SIZE 64 #define POLL_TMOUT 1000 #define DEFAULT_PKT_CNT (4 * 1024) #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) #define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE) #define RX_FULL_RXQSIZE 32 -#define DEFAULT_OFFSET 256 +#define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -55,11 +55,13 @@ enum test_mode { enum test_type { TEST_TYPE_RUN_TO_COMPLETION, TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME, + TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT, TEST_TYPE_POLL, TEST_TYPE_UNALIGNED, TEST_TYPE_ALIGNED_INV_DESC, TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME, TEST_TYPE_UNALIGNED_INV_DESC, + TEST_TYPE_HEADROOM, TEST_TYPE_TEARDOWN, TEST_TYPE_BIDI, TEST_TYPE_STATS, @@ -136,6 +138,7 @@ struct ifobject { bool tx_on; bool rx_on; bool use_poll; + bool pacing_on; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -151,5 +154,9 @@ struct test_spec { }; pthread_barrier_t barr; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; +pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; + +u32 pkts_in_flight; #endif /* XDPXCEIVER_H */ diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c index 4de902ea14d8..de1c4e6de0b2 100644 --- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c +++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <errno.h> -#include <linux/fcntl.h> +#include <fcntl.h> #include <malloc.h> #include <sys/ioctl.h> diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index 8817851da7a9..e9a82cae8c9a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -13,7 +13,7 @@ # | # +-------------------|-----+ # | SW1 | | -# | $swp1 + | +# | $swp1 + | # | 192.0.2.2/28 | # | | # | + g1a (gre) | @@ -27,8 +27,8 @@ # | # +--|----------------------+ # | | VRF2 | -# | + $rp2 | -# | 198.51.100.2/28 | +# | + $rp2 | +# | 198.51.100.2/28 | # +-------------------------+ lib_dir=$(dirname $0)/../../../net/forwarding @@ -116,12 +116,16 @@ cleanup() forwarding_restore } -ecn_payload_get() +ipip_payload_get() { + local flags=$1; shift + local key=$1; shift + p=$(: - )"0"$( : GRE flags + )"$flags"$( : GRE flags )"0:00:"$( : Reserved + version )"08:00:"$( : ETH protocol type + )"$key"$( : Key )"4"$( : IP version )"5:"$( : IHL )"00:"$( : IP TOS @@ -137,6 +141,11 @@ ecn_payload_get() echo $p } +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + ecn_decap_test() { local trap_name="decap_error" @@ -171,31 +180,6 @@ ecn_decap_test() tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } -ipip_payload_get() -{ - local flags=$1; shift - local key=$1; shift - - p=$(: - )"$flags"$( : GRE flags - )"0:00:"$( : Reserved + version - )"08:00:"$( : ETH protocol type - )"$key"$( : Key - )"4"$( : IP version - )"5:"$( : IHL - )"00:"$( : IP TOS - )"00:14:"$( : IP total length - )"00:00:"$( : IP identification - )"20:00:"$( : IP flags + frag off - )"30:"$( : IP TTL - )"01:"$( : IP proto - )"E7:E6:"$( : IP header csum - )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 - )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 - ) - echo $p -} - no_matching_tunnel_test() { local trap_name="decap_error" @@ -239,7 +223,8 @@ decap_error_test() no_matching_tunnel_test "Decap error: Source IP check failed" \ 192.0.2.68 "0" no_matching_tunnel_test \ - "Decap error: Key exists but was not expected" $sip "2" ":E9:" + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" # Destroy the tunnel and create new one with key __addr_add_del g1 del 192.0.2.65/32 @@ -251,7 +236,8 @@ decap_error_test() no_matching_tunnel_test \ "Decap error: Key does not exist but was expected" $sip "0" no_matching_tunnel_test \ - "Decap error: Packet has a wrong key field" $sip "2" "E8:" + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh new file mode 100755 index 000000000000..ade79ef08de3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh @@ -0,0 +1,276 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test qdisc offload indication + + +ALL_TESTS=" + test_root + test_etsprio +" +NUM_NETIFS=1 +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/lib.sh + +check_not_offloaded() +{ + local handle=$1; shift + local h + local offloaded + + h=$(qdisc_stats_get $h1 "$handle" .handle) + [[ $h == '"'$handle'"' ]] + check_err $? "Qdisc with handle $handle does not exist" + + offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_fail $? "Qdisc with handle $handle offloaded, but should not be" +} + +check_all_offloaded() +{ + local handle=$1; shift + + if [[ ! -z $handle ]]; then + local offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_err $? "Qdisc with handle $handle not offloaded" + fi + + local unoffloaded=$(tc q sh dev $h1 invisible | + grep -v offloaded | + sed s/root/parent\ root/ | + cut -d' ' -f 5) + [[ -z $unoffloaded ]] + check_err $? "Qdiscs with following parents not offloaded: $unoffloaded" + + pre_cleanup +} + +with_ets() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + ets bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_prio() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + prio bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_red() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + red limit 1000000 min 200000 max 300000 probability 0.5 avpkt 1500 + "$@" + tc qdisc del dev $h1 $locus +} + +with_tbf() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + tbf rate 400Mbit burst 128K limit 1M + "$@" + tc qdisc del dev $h1 $locus +} + +with_pfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle pfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_bfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle bfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_drr() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle drr + "$@" + tc qdisc del dev $h1 $locus +} + +with_qdiscs() +{ + local handle=$1; shift + local parent=$1; shift + local kind=$1; shift + local next_handle=$((handle * 2)) + local locus; + + if [[ $kind == "--" ]]; then + local cmd=$1; shift + $cmd $(printf %x: $parent) "$@" + else + if ((parent == 0)); then + locus=root + else + locus=$(printf "parent %x:1" $parent) + fi + + with_$kind $(printf %x: $handle) "$locus" \ + with_qdiscs $next_handle $handle "$@" + fi +} + +get_name() +{ + local parent=$1; shift + local name=$(echo "" "${@^^}" | tr ' ' -) + + if ((parent != 0)); then + kind=$(qdisc_stats_get $h1 $parent: .kind) + kind=${kind%\"} + kind=${kind#\"} + name="-${kind^^}$name" + fi + + echo root$name +} + +do_test_offloaded() +{ + local handle=$1; shift + local parent=$1; shift + + RET=0 + with_qdiscs $handle $parent "$@" -- check_all_offloaded + log_test $(get_name $parent "$@")" offloaded" +} + +do_test_nooffload() +{ + local handle=$1; shift + local parent=$1; shift + + local name=$(echo "${@^^}" | tr ' ' -) + local kind + + RET=0 + with_qdiscs $handle $parent "$@" -- check_not_offloaded + log_test $(get_name $parent "$@")" not offloaded" +} + +do_test_combinations() +{ + local handle=$1; shift + local parent=$1; shift + + local cont + local leaf + local fifo + + for cont in "" ets prio; do + for leaf in "" red tbf "red tbf" "tbf red"; do + for fifo in "" pfifo bfifo; do + if [[ -z "$cont$leaf$fifo" ]]; then + continue + fi + do_test_offloaded $handle $parent \ + $cont $leaf $fifo + done + done + done + + for cont in ets prio; do + for leaf in red tbf; do + do_test_nooffload $handle $parent $cont red tbf $leaf + do_test_nooffload $handle $parent $cont tbf red $leaf + done + for leaf in "red red" "tbf tbf"; do + do_test_nooffload $handle $parent $cont $leaf + done + done + + do_test_nooffload $handle $parent drr +} + +test_root() +{ + do_test_combinations 1 0 +} + +do_test_etsprio() +{ + local parent=$1; shift + local tbfpfx=$1; shift + local cont + + for cont in ets prio; do + RET=0 + with_$cont 8: "$parent" \ + with_red 11: "parent 8:1" \ + with_red 12: "parent 8:2" \ + with_tbf 13: "parent 8:3" \ + with_tbf 14: "parent 8:4" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED,TBF} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_tbf 84: "parent 8:4" \ + with_red 841: "parent 84:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF,TBF-RED} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_bfifo 8111: "parent 811:1" \ + with_tbf 82: "parent 8:2" \ + with_red 821: "parent 82:1" \ + with_bfifo 8211: "parent 821:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF-bFIFO,TBF-RED-bFIFO} offloaded" + done +} + +test_etsprio() +{ + do_test_etsprio root "" +} + +cleanup() +{ + tc qdisc del dev $h1 root &>/dev/null +} + +trap cleanup EXIT +h1=${NETIFS[p1]} +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 33ddd01689be..dd90cd87d4f9 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -331,6 +331,14 @@ get_nmarked() ethtool_stats_get $swp3 ecn_marked } +get_qdisc_nmarked() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked +} + get_qdisc_npackets() { local vlan=$1; shift @@ -384,14 +392,15 @@ build_backlog() check_marking() { + local get_nmarked=$1; shift local vlan=$1; shift local cond=$1; shift local npackets_0=$(get_qdisc_npackets $vlan) - local nmarked_0=$(get_nmarked $vlan) + local nmarked_0=$($get_nmarked $vlan) sleep 5 local npackets_1=$(get_qdisc_npackets $vlan) - local nmarked_1=$(get_nmarked $vlan) + local nmarked_1=$($get_nmarked $vlan) local nmarked_d=$((nmarked_1 - nmarked_0)) local npackets_d=$((npackets_1 - npackets_0)) @@ -404,6 +413,7 @@ check_marking() ecn_test_common() { local name=$1; shift + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift local backlog @@ -416,7 +426,7 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking "$get_nmarked" $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): $name backlog < limit" @@ -426,22 +436,23 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan ">= 95") + pct=$(check_marking "$get_nmarked" $vlan ">= 95") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." log_test "TC $((vlan - 10)): $name backlog > limit" } -do_ecn_test() +__do_ecn_test() { + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift - local name=ECN + local name=${1-ECN}; shift start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" "$get_nmarked" $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, it should all get dropped, and backlog @@ -455,6 +466,26 @@ do_ecn_test() sleep 1 } +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + + __do_ecn_test get_nmarked "$vlan" "$limit" +} + +do_ecn_test_perband() +{ + local vlan=$1; shift + local limit=$1; shift + + # Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2. + [[ "$DEVLINK_VIDDID" == "15b3:cb84" || + "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return + + __do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN" +} + do_ecn_nodrop_test() { local vlan=$1; shift @@ -465,7 +496,7 @@ do_ecn_nodrop_test() $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" get_nmarked $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, in nodrop mode, make sure it goes to @@ -495,7 +526,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): RED backlog < limit" @@ -503,7 +534,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_fail $? "Traffic went into backlog instead of being early-dropped" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." local diff=$((limit - backlog)) pct=$((100 * diff / limit)) @@ -544,6 +575,53 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } +do_mark_test() +{ + local vlan=$1; shift + local limit=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local should_fail=$1; shift + local base + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Create a bit of a backlog and observe no mirroring due to marks. + qevent_rule_install_$subtest + + build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null + + base=$($fetch_counter) + count=$(busywait 1100 until_counter_is ">= $((base + 1))" \ + $fetch_counter) + check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure" + + # Above limit, everything should be mirrored, we should see lots of + # packets. + build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null + busywait_for_counter 1100 +10000 \ + $fetch_counter > /dev/null + check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + busywait_for_counter 1100 +10 \ + $fetch_counter > /dev/null + check_fail $? "Spurious packets observed after uninstall" + + if ((should_fail)); then + log_test "TC $((vlan - 10)): marked packets not $subtest'd" + else + log_test "TC $((vlan - 10)): marked packets $subtest'd" + fi + + stop_traffic + sleep 1 +} + do_drop_test() { local vlan=$1; shift @@ -551,10 +629,8 @@ do_drop_test() local trigger=$1; shift local subtest=$1; shift local fetch_counter=$1; shift - local backlog local base local now - local pct RET=0 @@ -628,6 +704,22 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } +do_mark_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto tcp \ + action drop + + do_mark_test "$vlan" "$limit" mirror \ + qevent_counter_fetch_mirror \ + $(: should_fail=)0 + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + qevent_rule_install_trap() { tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ @@ -655,3 +747,14 @@ do_drop_trap_test() do_drop_test "$vlan" "$limit" "$trap_name" trap \ "qevent_counter_fetch_trap $trap_name" } + +qevent_rule_install_trap_fwd() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap_fwd hw_stats disabled +} + +qevent_rule_uninstall_trap_fwd() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index f3ef3274f9b3..1e5ad3209436 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -4,11 +4,13 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test red_mirror_test red_trap_test + ecn_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -21,28 +23,60 @@ source sch_red_core.sh BACKLOG1=200000 BACKLOG2=500000 -install_qdisc() +install_root_qdisc() { - local -a args=("$@") - tc qdisc add dev $swp3 root handle 10: $QDISC \ bands 8 priomap 7 6 5 4 3 2 1 0 +} + +install_qdisc_tc0() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ probability 1.0 avpkt 8000 burst 38 "${args[@]}" +} + +install_qdisc_tc1() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ probability 1.0 avpkt 8000 burst 63 "${args[@]}" +} + +install_qdisc() +{ + install_root_qdisc + install_qdisc_tc0 "$@" + install_qdisc_tc1 "$@" sleep 1 } -uninstall_qdisc() +uninstall_qdisc_tc0() { - tc qdisc del dev $swp3 parent 10:7 tc qdisc del dev $swp3 parent 10:8 +} + +uninstall_qdisc_tc1() +{ + tc qdisc del dev $swp3 parent 10:7 +} + +uninstall_root_qdisc() +{ tc qdisc del dev $swp3 root } +uninstall_qdisc() +{ + uninstall_qdisc_tc0 + uninstall_qdisc_tc1 + uninstall_root_qdisc +} + ecn_test() { install_qdisc ecn @@ -53,6 +87,16 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + + do_ecn_test_perband 10 $BACKLOG1 + do_ecn_test_perband 11 $BACKLOG2 + + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop @@ -112,6 +156,16 @@ red_trap_test() uninstall_qdisc } +ecn_mirror_test() +{ + install_qdisc ecn qevent mark block 10 + + do_mark_mirror_test 10 $BACKLOG1 + do_mark_mirror_test 11 $BACKLOG2 + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index ede9c38d3eff..d79a82f317d2 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -4,6 +4,7 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test @@ -35,6 +36,13 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + do_ecn_test_perband 10 $BACKLOG + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh new file mode 100755 index 000000000000..f62ce479c266 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh @@ -0,0 +1,250 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 2001:db8:1::1/64 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 2001:db8:1::2/64 | +# | | +# | + g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 2001:db8:10::1/64 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 2001:db8:10::2/64 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 2001:db8:1::1/64 +} + +vrf2_create() +{ + simple_if_init $rp2 2001:db8:10::2/64 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 2001:db8:10::2/64 +} + +switch_create() +{ + ip link set dev $swp1 up + __addr_add_del $swp1 add 2001:db8:1::2/64 + tc qdisc add dev $swp1 clsact + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit + ip link set dev g1 up + __addr_add_del g1 add 2001:db8:3::1/128 + + ip link set dev $rp1 up + __addr_add_del $rp1 add 2001:db8:10::1/64 +} + +switch_destroy() +{ + __addr_add_del $rp1 del 2001:db8:10::1/64 + ip link set dev $rp1 down + + __addr_add_del g1 del 2001:db8:3::1/128 + ip link set dev g1 down + tunnel_destroy g1 + + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 2001:db8:1::2/64 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ipip_payload_get() +{ + local saddr="20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:01" + local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01" + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"86:dd:"$( : ETH protocol type + )"$key"$( : Key + )"6"$( : IP version + )"0:0"$( : Traffic class + )"0:00:00:"$( : Flow label + )"00:00:"$( : Payload length + )"3a:"$( : Next header + )"04:"$( : Hop limit + )"$saddr:"$( : IP saddr + )"$daddr:"$( : IP daddr + ) + echo $p +} + +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 skip_sw \ + action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 2001:db8:3::2 -B 2001:db8:3::1 -t ip \ + tos=$outer_tos,next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 2001:db8:3::1 -t ip next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=2001:db8:3::2 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 2001:db8:4::2 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 2001:db8:3::1/128 + tunnel_destroy g1 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit key 233 + __addr_add_del g1 add 2001:db8:3::1/128 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..eaf8a04a7ca5 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Copyright 2020 NXP Semiconductors +# Copyright 2020 NXP WAIT_TIME=1 NUM_NETIFS=4 @@ -156,6 +156,11 @@ create_tcam_skeleton() setup_prepare() { + ip link set $eth0 up + ip link set $eth1 up + ip link set $eth2 up + ip link set $eth3 up + create_tcam_skeleton $eth0 ip link add br0 type bridge @@ -242,9 +247,9 @@ test_vlan_push() tcpdump_cleanup } -test_vlan_modify() +test_vlan_ingress_modify() { - printf "Testing VLAN modification.. " + printf "Testing ingress VLAN modification.. " ip link set br0 type bridge vlan_filtering 1 bridge vlan add dev $eth0 vid 200 @@ -280,6 +285,44 @@ test_vlan_modify() ip link set br0 type bridge vlan_filtering 0 } +test_vlan_egress_modify() +{ + printf "Testing egress VLAN modification.. " + + tc qdisc add dev $eth1 clsact + + ip link set br0 type bridge vlan_filtering 1 + bridge vlan add dev $eth0 vid 200 + bridge vlan add dev $eth1 vid 200 + + tc filter add dev $eth1 egress chain $(ES0) pref 3 \ + protocol 802.1Q flower skip_sw vlan_id 200 vlan_prio 0 \ + action vlan modify id 300 priority 7 + + tcpdump_start $eth2 + + $MZ $eth3.200 -q -c 1 -p 64 -a $eth3_mac -b $eth2_mac -t ip + + sleep 1 + + tcpdump_stop + + if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then + echo "OK" + else + echo "FAIL" + fi + + tcpdump_cleanup + + tc filter del dev $eth1 egress chain $(ES0) pref 3 + tc qdisc del dev $eth1 clsact + + bridge vlan del dev $eth0 vid 200 + bridge vlan del dev $eth1 vid 200 + ip link set br0 type bridge vlan_filtering 0 +} + test_skbedit_priority() { local num_pkts=100 @@ -304,7 +347,8 @@ trap cleanup EXIT ALL_TESTS=" test_vlan_pop test_vlan_push - test_vlan_modify + test_vlan_ingress_modify + test_vlan_egress_modify test_skbedit_priority " diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index 5f5b2ba3e557..60c02b482be8 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -11,8 +11,8 @@ SYSTEM="syscalls" EVENT="sys_enter_openat" FIELD="filename" EPROBE="eprobe_open" - -echo "e:$EPROBE $SYSTEM/$EVENT file=+0(\$filename):ustring" >> dynamic_events +OPTIONS="file=+0(\$filename):ustring" +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events grep -q "$EPROBE" dynamic_events test -d events/eprobes/$EPROBE @@ -37,4 +37,54 @@ echo "-:$EPROBE" >> dynamic_events ! grep -q "$EPROBE" dynamic_events ! test -d events/eprobes/$EPROBE +# test various ways to remove the probe (already tested with just event name) + +# With group name +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# Finally make sure what is in the dynamic_events file clears it too +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +LINE=`sed -e '/$EPROBE/s/^e/-/' < dynamic_events` +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + clear_trace diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 98053d3afbda..b8dbabe24ac2 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -24,6 +24,7 @@ /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test +/x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_msr_exit_test @@ -48,6 +49,7 @@ /kvm_page_table_test /memslot_modification_stress_test /memslot_perf_test +/rseq_test /set_memory_region_test /steal_time /kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 5d05801ab816..d1774f461393 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -56,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test @@ -80,6 +81,7 @@ TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += memslot_perf_test +TEST_GEN_PROGS_x86_64 += rseq_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test @@ -93,6 +95,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test +TEST_GEN_PROGS_aarch64 += rseq_test TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test @@ -104,6 +107,7 @@ TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS_s390x += kvm_page_table_test +TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 71e277c7c3f3..5d95113c7b7c 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -371,9 +371,7 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); exit(0); } @@ -381,7 +379,7 @@ static void help(char *name) int main(int argc, char *argv[]) { struct test_params params = { - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, .vcpus = 1, }; diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index e79c1b64977f..1510b21e6306 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -179,7 +179,7 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } - if (!pollfd[0].revents & POLLIN) + if (!(pollfd[0].revents & POLLIN)) continue; r = read(uffd, &msg, sizeof(msg)); @@ -416,7 +416,7 @@ static void help(char *name) { puts(""); printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" - " [-b memory] [-t type] [-v vcpus] [-o]\n", name); + " [-b memory] [-s type] [-v vcpus] [-o]\n", name); guest_modes_help(); printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); @@ -426,8 +426,7 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); - printf(" -t: The type of backing memory to use. Default: anonymous\n"); - backing_src_help(); + backing_src_help("-s"); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -439,14 +438,14 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -465,7 +464,7 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; - case 't': + case 's': p.src_type = parse_backing_src_type(optarg); break; case 'v': @@ -485,7 +484,7 @@ int main(int argc, char *argv[]) if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && !backing_src_is_shared(p.src_type)) { - TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s"); } for_each_guest_mode(run_test, &p); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 479868570d59..7ffab5bd5ce5 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -118,42 +118,64 @@ static inline void disable_dirty_logging(struct kvm_vm *vm, int slots) toggle_dirty_logging(vm, slots, false); } -static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_get_dirty_log(vm, slot, slot_bitmap); + kvm_vm_get_dirty_log(vm, slot, bitmaps[i]); } } -static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], + int slots, uint64_t pages_per_slot) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages); + kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot); } } +static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot) +{ + unsigned long **bitmaps; + int i; + + bitmaps = malloc(slots * sizeof(bitmaps[0])); + TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array."); + + for (i = 0; i < slots; i++) { + bitmaps[i] = bitmap_zalloc(pages_per_slot); + TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap."); + } + + return bitmaps; +} + +static void free_bitmaps(unsigned long *bitmaps[], int slots) +{ + int i; + + for (i = 0; i < slots; i++) + free(bitmaps[i]); + + free(bitmaps); +} + static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; pthread_t *vcpu_threads; struct kvm_vm *vm; - unsigned long *bmap; + unsigned long **bitmaps; uint64_t guest_num_pages; uint64_t host_num_pages; + uint64_t pages_per_slot; int vcpu_id; struct timespec start; struct timespec ts_diff; @@ -171,7 +193,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_num_pages = vm_num_host_pages(mode, guest_num_pages); - bmap = bitmap_zalloc(host_num_pages); + pages_per_slot = host_num_pages / p->slots; + + bitmaps = alloc_bitmaps(p->slots, pages_per_slot); if (dirty_log_manual_caps) { cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; @@ -239,7 +263,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) iteration, ts_diff.tv_sec, ts_diff.tv_nsec); clock_gettime(CLOCK_MONOTONIC, &start); - get_dirty_log(vm, p->slots, bmap, host_num_pages); + get_dirty_log(vm, bitmaps, p->slots); ts_diff = timespec_elapsed(start); get_dirty_log_total = timespec_add(get_dirty_log_total, ts_diff); @@ -248,7 +272,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (dirty_log_manual_caps) { clock_gettime(CLOCK_MONOTONIC, &start); - clear_dirty_log(vm, p->slots, bmap, host_num_pages); + clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot); ts_diff = timespec_elapsed(start); clear_dirty_log_total = timespec_add(clear_dirty_log_total, ts_diff); @@ -281,7 +305,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); } - free(bmap); + free_bitmaps(bitmaps, p->slots); free(vcpu_threads); perf_test_destroy_vm(vm); } @@ -308,11 +332,9 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); + backing_src_help("-s"); printf(" -x: Split the memory region into this number of memslots.\n" - " (default: 1)"); - backing_src_help(); + " (default: 1)\n"); puts(""); exit(0); } @@ -324,7 +346,7 @@ int main(int argc, char *argv[]) .iterations = TEST_HOST_LOOP_N, .wr_fract = 1, .partition_vcpu_memory_access = true, - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, }; int opt; diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d79be15dd3d2..f8fddc84c0d3 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -90,18 +90,23 @@ enum vm_mem_backing_src_type { NUM_SRC_TYPES, }; +#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS + struct vm_mem_backing_src_alias { const char *name; uint32_t flag; }; +#define MIN_RUN_DELAY_NS 200000UL + bool thp_configured(void); size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); -void backing_src_help(void); +void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +long get_run_delay(void); /* * Whether or not the given source type is shared memory (as opposed to diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 242ae8e09a65..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -312,37 +312,37 @@ static inline void set_xmm(int n, unsigned long val) } } -typedef unsigned long v1di __attribute__ ((vector_size (8))); +#define GET_XMM(__xmm) \ +({ \ + unsigned long __val; \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ + __val; \ +}) + static inline unsigned long get_xmm(int n) { assert(n >= 0 && n <= 7); - register v1di xmm0 __asm__("%xmm0"); - register v1di xmm1 __asm__("%xmm1"); - register v1di xmm2 __asm__("%xmm2"); - register v1di xmm3 __asm__("%xmm3"); - register v1di xmm4 __asm__("%xmm4"); - register v1di xmm5 __asm__("%xmm5"); - register v1di xmm6 __asm__("%xmm6"); - register v1di xmm7 __asm__("%xmm7"); switch (n) { case 0: - return (unsigned long)xmm0; + return GET_XMM(xmm0); case 1: - return (unsigned long)xmm1; + return GET_XMM(xmm1); case 2: - return (unsigned long)xmm2; + return GET_XMM(xmm2); case 3: - return (unsigned long)xmm3; + return GET_XMM(xmm3); case 4: - return (unsigned long)xmm4; + return GET_XMM(xmm4); case 5: - return (unsigned long)xmm5; + return GET_XMM(xmm5); case 6: - return (unsigned long)xmm6; + return GET_XMM(xmm6); case 7: - return (unsigned long)xmm7; + return GET_XMM(xmm7); } + + /* never reached */ return 0; } diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 0d04a7db7f24..36407cb0ec85 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -456,10 +456,7 @@ static void help(char *name) " (default: 1G)\n"); printf(" -v: specify the number of vCPUs to run\n" " (default: 1)\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n" - " (default: anonymous)\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); } @@ -468,7 +465,7 @@ int main(int argc, char *argv[]) int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { .test_mem_size = DEFAULT_TEST_MEM_SIZE, - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, }; int opt; diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index af1031fed97f..b72429108993 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -11,6 +11,7 @@ #include <stdlib.h> #include <time.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <linux/mman.h> #include "linux/kernel.h" @@ -129,13 +130,16 @@ size_t get_trans_hugepagesz(void) { size_t size; FILE *f; + int ret; TEST_ASSERT(thp_configured(), "THP is not configured in host kernel"); f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r"); TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size"); - fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size"); fclose(f); return size; @@ -279,13 +283,22 @@ size_t get_backing_src_pagesz(uint32_t i) } } -void backing_src_help(void) +static void print_available_backing_src_types(const char *prefix) { int i; - printf("Available backing src types:\n"); + printf("%sAvailable backing src types:\n", prefix); + for (i = 0; i < NUM_SRC_TYPES; i++) - printf("\t%s\n", vm_mem_backing_src_alias(i)->name); + printf("%s %s\n", prefix, vm_mem_backing_src_alias(i)->name); +} + +void backing_src_help(const char *flag) +{ + printf(" %s: specify the type of memory that should be used to\n" + " back the guest data region. (default: %s)\n", + flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name); + print_available_backing_src_types(" "); } enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) @@ -296,7 +309,23 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name)) return i; - backing_src_help(); + print_available_backing_src_types(""); TEST_FAIL("Unknown backing src type: %s", type_name); return -1; } + +long get_run_delay(void) +{ + char path[64]; + long val[2]; + FILE *fp; + + sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); + fp = fopen(path, "r"); + /* Return MIN_RUN_DELAY_NS upon failure just to be safe */ + if (fscanf(fp, "%ld %ld ", &val[0], &val[1]) < 2) + val[1] = MIN_RUN_DELAY_NS; + fclose(fp); + + return val[1]; +} diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c new file mode 100644 index 000000000000..4158da0da2bb --- /dev/null +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <errno.h> +#include <fcntl.h> +#include <pthread.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <syscall.h> +#include <sys/ioctl.h> +#include <sys/sysinfo.h> +#include <asm/barrier.h> +#include <linux/atomic.h> +#include <linux/rseq.h> +#include <linux/unistd.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID 0 + +static __thread volatile struct rseq __rseq = { + .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, +}; + +/* + * Use an arbitrary, bogus signature for configuring rseq, this test does not + * actually enter an rseq critical section. + */ +#define RSEQ_SIG 0xdeadbeef + +/* + * Any bug related to task migration is likely to be timing-dependent; perform + * a large number of migrations to reduce the odds of a false negative. + */ +#define NR_TASK_MIGRATIONS 100000 + +static pthread_t migration_thread; +static cpu_set_t possible_mask; +static int min_cpu, max_cpu; +static bool done; + +static atomic_t seq_cnt; + +static void guest_code(void) +{ + for (;;) + GUEST_SYNC(0); +} + +static void sys_rseq(int flags) +{ + int r; + + r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG); + TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); +} + +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + +static void *migration_worker(void *ign) +{ + cpu_set_t allowed_mask; + int r, i, cpu; + + CPU_ZERO(&allowed_mask); + + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { + CPU_SET(cpu, &allowed_mask); + + /* + * Bump the sequence count twice to allow the reader to detect + * that a migration may have occurred in between rseq and sched + * CPU ID reads. An odd sequence count indicates a migration + * is in-progress, while a completely different count indicates + * a migration occurred since the count was last read. + */ + atomic_inc(&seq_cnt); + + /* + * Ensure the odd count is visible while sched_getcpu() isn't + * stable, i.e. while changing affinity is in-progress. + */ + smp_wmb(); + r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + smp_wmb(); + atomic_inc(&seq_cnt); + + CPU_CLR(cpu, &allowed_mask); + + /* + * Wait 1-10us before proceeding to the next iteration and more + * specifically, before bumping seq_cnt again. A delay is + * needed on three fronts: + * + * 1. To allow sched_setaffinity() to prompt migration before + * ioctl(KVM_RUN) enters the guest so that TIF_NOTIFY_RESUME + * (or TIF_NEED_RESCHED, which indirectly leads to handling + * NOTIFY_RESUME) is handled in KVM context. + * + * If NOTIFY_RESUME/NEED_RESCHED is set after KVM enters + * the guest, the guest will trigger a IO/MMIO exit all the + * way to userspace and the TIF flags will be handled by + * the generic "exit to userspace" logic, not by KVM. The + * exit to userspace is necessary to give the test a chance + * to check the rseq CPU ID (see #2). + * + * Alternatively, guest_code() could include an instruction + * to trigger an exit that is handled by KVM, but any such + * exit requires architecture specific code. + * + * 2. To let ioctl(KVM_RUN) make its way back to the test + * before the next round of migration. The test's check on + * the rseq CPU ID must wait for migration to complete in + * order to avoid false positive, thus any kernel rseq bug + * will be missed if the next migration starts before the + * check completes. + * + * 3. To ensure the read-side makes efficient forward progress, + * e.g. if sched_getcpu() involves a syscall. Stalling the + * read-side means the test will spend more time waiting for + * sched_getcpu() to stabilize and less time trying to hit + * the timing-dependent bug. + * + * Because any bug in this area is likely to be timing-dependent, + * run with a range of delays at 1us intervals from 1us to 10us + * as a best effort to avoid tuning the test to the point where + * it can hit _only_ the original bug and not detect future + * regressions. + * + * The original bug can reproduce with a delay up to ~500us on + * x86-64, but starts to require more iterations to reproduce + * as the delay creeps above ~10us, and the average runtime of + * each iteration obviously increases as well. Cap the delay + * at 10us to keep test runtime reasonable while minimizing + * potential coverage loss. + * + * The lower bound for reproducing the bug is likely below 1us, + * e.g. failures occur on x86-64 with nanosleep(0), but at that + * point the overhead of the syscall likely dominates the delay. + * Use usleep() for simplicity and to avoid unnecessary kernel + * dependencies. + */ + usleep((i % 10) + 1); + } + done = true; + return NULL; +} + +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + +int main(int argc, char *argv[]) +{ + int r, i, snapshot; + struct kvm_vm *vm; + u32 cpu, rseq_cpu; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); + TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, + strerror(errno)); + + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); + exit(KSFT_SKIP); + } + + sys_rseq(0); + + /* + * Create and run a dummy VM that immediately exits to userspace via + * GUEST_SYNC, while concurrently migrating the process by setting its + * CPU affinity. + */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); + + pthread_create(&migration_thread, NULL, migration_worker, 0); + + for (i = 0; !done; i++) { + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + "Guest failed?"); + + /* + * Verify rseq's CPU matches sched's CPU. Ensure migration + * doesn't occur between sched_getcpu() and reading the rseq + * cpu_id by rereading both if the sequence count changes, or + * if the count is odd (migration in-progress). + */ + do { + /* + * Drop bit 0 to force a mismatch if the count is odd, + * i.e. if a migration is in-progress. + */ + snapshot = atomic_read(&seq_cnt) & ~1; + + /* + * Ensure reading sched_getcpu() and rseq.cpu_id + * complete in a single "no migration" window, i.e. are + * not reordered across the seq_cnt reads. + */ + smp_rmb(); + cpu = sched_getcpu(); + rseq_cpu = READ_ONCE(__rseq.cpu_id); + smp_rmb(); + } while (snapshot != atomic_read(&seq_cnt)); + + TEST_ASSERT(rseq_cpu == cpu, + "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu); + } + + /* + * Sanity check that the test was able to enter the guest a reasonable + * number of times, e.g. didn't get stalled too often/long waiting for + * sched_getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a + * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs + * than migrations given the 1us+ delay in the migration task. + */ + TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2), + "Only performed %d KVM_RUNs, task stalled too much?\n", i); + + pthread_join(migration_thread, NULL); + + kvm_vm_free(vm); + + sys_rseq(RSEQ_FLAG_UNREGISTER); + + return 0; +} diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index ecec30865a74..62f2eb9ee3d5 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -10,7 +10,6 @@ #include <sched.h> #include <pthread.h> #include <linux/kernel.h> -#include <sys/syscall.h> #include <asm/kvm.h> #include <asm/kvm_para.h> @@ -20,7 +19,6 @@ #define NR_VCPUS 4 #define ST_GPA_BASE (1 << 30) -#define MIN_RUN_DELAY_NS 200000UL static void *st_gva[NR_VCPUS]; static uint64_t guest_stolen_time[NR_VCPUS]; @@ -118,12 +116,12 @@ struct st_time { uint64_t st_time; }; -static int64_t smccc(uint32_t func, uint32_t arg) +static int64_t smccc(uint32_t func, uint64_t arg) { unsigned long ret; asm volatile( - "mov x0, %1\n" + "mov w0, %w1\n" "mov x1, %2\n" "hvc #0\n" "mov %0, x0\n" @@ -217,20 +215,6 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) #endif -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static void *do_steal_time(void *arg) { struct timespec ts, stop; 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 e6480fd5c4bd..8039e1eff938 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -82,7 +82,8 @@ int get_warnings_count(void) FILE *f; f = popen("dmesg | grep \"WARNING:\" | wc -l", "r"); - fscanf(f, "%d", &warnings); + if (fscanf(f, "%d", &warnings) < 1) + warnings = 0; fclose(f); return warnings; diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c new file mode 100644 index 000000000000..df04f56ce859 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "apic.h" + +#define VCPU_ID 0 + +static struct kvm_vm *vm; + +bool vintr_irq_called; +bool intr_irq_called; + +#define VINTR_IRQ_NUMBER 0x20 +#define INTR_IRQ_NUMBER 0x30 + +static void vintr_irq_handler(struct ex_regs *regs) +{ + vintr_irq_called = true; +} + +static void intr_irq_handler(struct ex_regs *regs) +{ + x2apic_write_reg(APIC_EOI, 0x00); + intr_irq_called = true; +} + +static void l2_guest_code(struct svm_test_data *svm) +{ + /* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC, + * and since L1 didn't enable virtual interrupt masking, + * L2 should receive it and not L1. + * + * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ + * so it should also receive it after the following 'sti'. + */ + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER); + + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + GUEST_ASSERT(vintr_irq_called); + GUEST_ASSERT(intr_irq_called); + + __asm__ __volatile__( + "vmcall\n" + ); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* No virtual interrupt masking */ + vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + /* No intercepts for real and virtual interrupts */ + vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + + /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ + vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); + vmcb->control.int_vector = VINTR_IRQ_NUMBER; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); + vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); + return 0; +} 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 117bf49a3d79..eda0d2a51224 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,7 +14,6 @@ #include <stdint.h> #include <time.h> #include <sched.h> -#include <sys/syscall.h> #define VCPU_ID 5 @@ -98,20 +97,6 @@ static void guest_code(void) GUEST_DONE(); } -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static int cmp_timespec(struct timespec *a, struct timespec *b) { if (a->tv_sec > b->tv_sec) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index fa2ac0e56b43..fe7ee2b0f29c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -48,6 +48,7 @@ ARCH ?= $(SUBARCH) # When local build is done, headers are installed in the default # INSTALL_HDR_PATH usr/include. .PHONY: khdr +.NOTPARALLEL: khdr: ifndef KSFT_KHDR_INSTALL_DONE ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index cfc7f4f97fd1..df341648f818 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,5 +1,2 @@ -##TEST_GEN_FILES := test_unix_oob -TEST_PROGS := test_unix_oob +TEST_GEN_PROGS := test_unix_oob include ../../lib.mk - -all: $(TEST_PROGS) diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index 0f3e3763f4f8..3dece8b29253 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -271,8 +271,9 @@ main(int argc, char **argv) read_oob(pfd, &oob); if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) { - fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", - "atmark %d\n", signal_recvd, len, oob, atmark); + fprintf(stderr, + "Test 3 failed, sigurg %d len %d OOB %c atmark %d\n", + signal_recvd, len, oob, atmark); die(1); } diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 21b646d10b88..86ab429fe7f3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y +CONFIG_CRYPTO_SM4=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 13350cd5c8ac..8e67a252b672 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -289,6 +289,12 @@ set_sysctl() run_cmd sysctl -q -w $* } +# get sysctl values in NS-A +get_sysctl() +{ + ${NSA_CMD} sysctl -n $* +} + ################################################################################ # Setup for tests @@ -1003,6 +1009,60 @@ ipv4_tcp_md5() run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + test_ipv4_md5_vrf__vrf_server__no_bind_ifindex + test_ipv4_md5_vrf__global_server__bind_ifindex0 +} + +test_ipv4_md5_vrf__vrf_server__no_bind_ifindex() +{ + log_start + show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection" + + log_start + show_hint "Binding both the socket and the key is not required but it works" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection" +} + +test_ipv4_md5_vrf__global_server__bind_ifindex0() +{ + # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections + local old_tcp_l3mdev_accept + old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept) + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection" + log_start + + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection" + + # restore value + set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } ipv4_tcp_novrf() diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0d293391e9a4..b5a69ad191b0 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2078,6 +2078,7 @@ basic_res() "id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1" log_test $? 0 "Dump all nexthop buckets in a group" + sleep 0.1 (( $($IP -j nexthop bucket list id 101 | jq '[.[] | select(.bucket.idle_time > 0 and .bucket.idle_time < 2)] | length') == 4 )) diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index d97bd6889446..72ee644d47bf 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ gre_multipath.sh \ + ip6_forward_instats_vrf.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b802c14d2950..bf17e485684f 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,9 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process +# filter by software/hardware +TC_FLAG=skip_hw +# IPv6 traceroute utility name. +TROUTE6=traceroute6 + diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh new file mode 100755 index 000000000000..9f5b3e2e5e95 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -0,0 +1,172 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test ipv6 stats on the incoming if when forwarding with VRF + +ALL_TESTS=" + ipv6_ping + ipv6_in_too_big_err + ipv6_in_hdr_err + ipv6_in_addr_err + ipv6_in_discard +" + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 2001:1:1::2/64 + ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1 + simple_if_fini $h1 2001:1:1::2/64 +} + +router_create() +{ + vrf_create router + __simple_if_init $rtr1 router 2001:1:1::1/64 + __simple_if_init $rtr2 router 2001:1:2::1/64 + mtu_set $rtr2 1280 +} + +router_destroy() +{ + mtu_restore $rtr2 + __simple_if_fini $rtr2 2001:1:2::1/64 + __simple_if_fini $rtr1 2001:1:1::1/64 + vrf_destroy router +} + +h2_create() +{ + simple_if_init $h2 2001:1:2::2/64 + ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + mtu_set $h2 1280 +} + +h2_destroy() +{ + mtu_restore $h2 + ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + simple_if_fini $h2 2001:1:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rtr1=${NETIFS[p2]} + + rtr2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + router_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + router_destroy + h1_destroy + vrf_cleanup +} + +ipv6_in_too_big_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + local vrf_name=$(master_name_get $h1) + + # Send too big packets + ip vrf exec $vrf_name \ + $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InTooBigErrors" +} + +ipv6_in_hdr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + local vrf_name=$(master_name_get $h1) + + # Send packets with hop limit 1, easiest with traceroute6 as some ping6 + # doesn't allow hop limit to be specified + ip vrf exec $vrf_name \ + $TROUTE6 2001:1:2::2 &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InHdrErrors" +} + +ipv6_in_addr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + local vrf_name=$(master_name_get $h1) + + # Disable forwarding temporary while sending the packet + sysctl -qw net.ipv6.conf.all.forwarding=0 + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + sysctl -qw net.ipv6.conf.all.forwarding=1 + + local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InAddrErrors" +} + +ipv6_in_discard() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards) + local vrf_name=$(master_name_get $h1) + + # Add a policy to discard + ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + ip xfrm policy del dst 2001:1:2::2/128 dir fwd + + local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InDiscards" +} +ipv6_ping() +{ + RET=0 + + ping6_test $h1 2001:1:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh new file mode 100755 index 000000000000..96c97064f2d3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel without key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 + sw2_flat_create $ol2 $ul2 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh new file mode 100755 index 000000000000..ff9fb0db9bd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 key 233 + sw2_flat_create $ol2 $ul2 key 233 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh new file mode 100755 index 000000000000..12c138785242 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with keys. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 ikey 111 okey 222 + sw2_flat_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh new file mode 100755 index 000000000000..83b55c30a5c3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 + sw2_hierarchical_create $ol2 $ul2 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh new file mode 100755 index 000000000000..256607916d92 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 key 22 + sw2_hierarchical_create $ol2 $ul2 key 22 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh new file mode 100755 index 000000000000..ad1bcd6334a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 ikey 111 okey 222 + sw2_hierarchical_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh new file mode 100644 index 000000000000..58a3597037b1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -0,0 +1,438 @@ +# SPDX-License-Identifier: GPL-2.0 +#!/bin/bash + +# Handles creation and destruction of IP-in-IP or GRE tunnels over the given +# topology. Supports both flat and hierarchical models. +# +# Flat Model: +# Overlay and underlay share the same VRF. +# SW1 uses default VRF so tunnel has no bound dev. +# SW2 uses non-default VRF tunnel has a bound dev. +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.2/24 | +# | 2001:db8:1::2/64 | +# | | +# | + g1a (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 --. | +# | tos=inherit | | +# | . | +# | .--------------------- | +# | | | +# | v | +# | + $ul1.111 (vlan) | +# | | 2001:db8:10::1/64 | +# | \ | +# | \____________ | +# | | | +# | VRF default + $ul1 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul2 + | +# | ___________| | +# | / | +# | / | +# | + $ul2.111 (vlan) | +# | ^ 2001:db8:10::2/64 | +# | | | +# | | | +# | '----------------------. | +# | + g2a (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 --' | +# | tos=inherit | +# | | +# | + $ol2 | +# | | 203.0.113.2/24 | +# | VRF v$ol2 | 2001:db8:2::2/64 | +# +---------------------|-----------------------+ +# +---------------------|----------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ +# +# Hierarchical model: +# The tunnel is bound to a device in a different VRF +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | +-----------------------|-----------------+ | +# | | $ol1 + | | +# | | 198.51.100.2/24 | | +# | | 2001:db8:1::2/64 | | +# | | | | +# | | + g1a (ip6gre) | | +# | | loc=2001:db8:3::1 | | +# | | rem=2001:db8:3::2 | | +# | | tos=inherit | | +# | | ^ | | +# | | VRF v$ol1 | | | +# | +--------------------|--------------------+ | +# | | | +# | +--------------------|--------------------+ | +# | | VRF v$ul1 | | | +# | | | | | +# | | v | | +# | | dummy1 + | | +# | | 2001:db8:3::1/64 | | +# | | .-----------' | | +# | | | | | +# | | v | | +# | | + $ul1.111 (vlan) | | +# | | | 2001:db8:10::1/64 | | +# | | \ | | +# | | \__________ | | +# | | | | | +# | | + $ul1 | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|---------------------+ +# | SW2 | | +# | +---------------------|-------------------+ | +# | | + $ul2 | | +# | | _____| | | +# | | / | | +# | | / | | +# | | | $ul2.111 (vlan) | | +# | | + 2001:db8:10::2/64 | | +# | | ^ | | +# | | | | | +# | | '------. | | +# | | dummy2 + | | +# | | 2001:db8:3::2/64 | | +# | | ^ | | +# | | | | | +# | | | | | +# | | VRF v$ul2 | | | +# | +---------------------|-------------------+ | +# | | | +# | +---------------------|-------------------+ | +# | | VRF v$ol2 | | | +# | | | | | +# | | v | | +# | | g2a (ip6gre) + | | +# | | loc=2001:db8:3::2 | | +# | | rem=2001:db8:3::1 | | +# | | tos=inherit | | +# | | | | +# | | $ol2 + | | +# | | 203.0.113.2/24 | | | +# | | 2001:db8:2::2/64 | | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|--------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ + +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.1/24 2001:db8:1::1/64 + ip route add vrf v$h1 203.0.113.0/24 via 198.51.100.2 + ip -6 route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 + ip route del vrf v$h1 203.0.113.0/24 via 198.51.100.2 + simple_if_fini $h1 198.51.100.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.1/24 2001:db8:2::1/64 + ip route add vrf v$h2 198.51.100.0/24 via 203.0.113.2 + ip -6 route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 + ip route del vrf v$h2 198.51.100.0/24 via 203.0.113.2 + simple_if_fini $h2 203.0.113.1/24 2001:db8:2::1/64 +} + +sw1_flat_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip link set dev $ol1 up + __addr_add_del $ol1 add 198.51.100.2/24 2001:db8:1::2/64 + + ip link set dev $ul1 up + vlan_create $ul1 111 "" 2001:db8:10::1/64 + + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit "$@" + ip link set dev g1a up + __addr_add_del g1a add "2001:db8:3::1/128" + + ip -6 route add 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add 203.0.113.0/24 dev g1a + ip -6 route add 2001:db8:2::/64 dev g1a +} + +sw1_flat_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del 2001:db8:2::/64 + ip route del 203.0.113.0/24 + ip -6 route del 2001:db8:3::2/128 via 2001:db8:10::2 + + __simple_if_fini g1a 2001:db8:3::1/128 + tunnel_destroy g1a + + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + __simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_flat_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 2001:db8:10::2/64 + + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev v$ol2 "$@" + __simple_if_init g2a v$ol2 2001:db8:3::2/128 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_flat_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + + __simple_if_fini g2a 2001:db8:3::2/128 + tunnel_destroy g2a + + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +sw1_hierarchical_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + simple_if_init $ol1 198.51.100.2/24 2001:db8:1::2/64 + simple_if_init $ul1 + ip link add name dummy1 type dummy + __simple_if_init dummy1 v$ul1 2001:db8:3::1/64 + + vlan_create $ul1 111 v$ul1 2001:db8:10::1/64 + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit dev dummy1 "$@" + ip link set dev g1a master v$ol1 + + ip -6 route add vrf v$ul1 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add vrf v$ol1 203.0.113.0/24 dev g1a + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1a +} + +sw1_hierarchical_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + ip -6 route del vrf v$ul1 2001:db8:3::2/128 + + tunnel_destroy g1a + vlan_destroy $ul1 111 + + __simple_if_fini dummy1 2001:db8:3::1/64 + ip link del dev dummy1 + + simple_if_fini $ul1 + simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_hierarchical_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + simple_if_init $ul2 + + ip link add name dummy2 type dummy + __simple_if_init dummy2 v$ul2 2001:db8:3::2/64 + + vlan_create $ul2 111 v$ul2 2001:db8:10::2/64 + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev dummy2 "$@" + ip link set dev g2a master v$ol2 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ul2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_hierarchical_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ul2 2001:db8:3::1/128 + + tunnel_destroy g2a + vlan_destroy $ul2 111 + + __simple_if_fini dummy2 2001:db8:3::2/64 + ip link del dev dummy2 + + simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +test_traffic_ip4ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv4 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 203.0.113.1 action pass + + $MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \ + -B 203.0.113.1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv4 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +test_traffic_ip6ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv6 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 2001:db8:2::1 action pass + + $MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \ + -B 2001:db8:2::1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv6 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +topo_mtu_change() +{ + local mtu=$1 + + ip link set mtu $mtu dev $h1 + ip link set mtu $mtu dev $ol1 + ip link set mtu $mtu dev g1a + ip link set mtu $mtu dev $ul1 + ip link set mtu $mtu dev $ul1.111 + ip link set mtu $mtu dev $h2 + ip link set mtu $mtu dev $ol2 + ip link set mtu $mtu dev g2a + ip link set mtu $mtu dev $ul2 + ip link set mtu $mtu dev $ul2.111 +} + +test_mtu_change() +{ + RET=0 + + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_fail $? "ping GRE IPv6 should not pass with packet size 1800" + + RET=0 + + topo_mtu_change 2000 + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_err $? + log_test "ping GRE IPv6, packet size 1800 after MTU change" +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e7fc5c35b569..92087d423bcf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -751,6 +751,14 @@ qdisc_parent_stats_get() | jq '.[] | select(.parent == "'"$parent"'") | '"$selector" } +ipv6_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2 +} + humanize() { local speed=$1; shift diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 0e18e8be6e2a..bce8bb8d2b6f 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -16,6 +16,16 @@ tc_check_packets() tc_rule_handle_stats_get "$id" "$handle" > /dev/null } +tc_check_at_least_x_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + + busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \ + tc_rule_handle_stats_get "$id" "$handle" > /dev/null +} + tc_check_packets_hitting() { local id=$1 diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 3caf72bb9c6a..a2b9fad5a9a6 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -6,7 +6,7 @@ # This script evaluates the IOAM insertion for IPv6 by checking the IOAM data # consistency directly inside packets on the receiver side. Tests are divided # into three categories: OUTPUT (evaluates the IOAM processing by the sender), -# INPUT (evaluates the IOAM processing by the receiver) and GLOBAL (evaluates +# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates # wider use cases that do not fall into the other two categories). Both OUTPUT # and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL # tests use the entire three-node topology (alpha, beta, gamma). Each test is @@ -200,7 +200,7 @@ check_kernel_compatibility() ip -netns ioam-tmp-node link set veth0 up ip -netns ioam-tmp-node link set veth1 up - ip -netns ioam-tmp-node ioam namespace add 0 &>/dev/null + ip -netns ioam-tmp-node ioam namespace add 0 ns_ad=$? ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0" @@ -214,11 +214,11 @@ check_kernel_compatibility() exit 1 fi - ip -netns ioam-tmp-node route add db02::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + ip -netns ioam-tmp-node route add db02::/64 encap ioam6 mode inline \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 tr_ad=$? - ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6 trace" + ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6" tr_sh=$? if [[ $tr_ad != 0 || $tr_sh != 0 ]] @@ -232,6 +232,30 @@ check_kernel_compatibility() ip link del veth0 2>/dev/null || true ip netns del ioam-tmp-node || true + + lsmod | grep -q "ip6_tunnel" + ip6tnl_loaded=$? + + if [ $ip6tnl_loaded = 0 ] + then + encap_tests=0 + else + modprobe ip6_tunnel &>/dev/null + lsmod | grep -q "ip6_tunnel" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + ip a | grep -q "ip6tnl0" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + echo "Note: ip6_tunnel not found neither as a module nor inside the" \ + "kernel, tests that require it (encap mode) will be omitted" + fi + fi + fi } cleanup() @@ -242,6 +266,11 @@ cleanup() ip netns del ioam-node-alpha || true ip netns del ioam-node-beta || true ip netns del ioam-node-gamma || true + + if [ $ip6tnl_loaded != 0 ] + then + modprobe -r ip6_tunnel 2>/dev/null || true + fi } setup() @@ -329,6 +358,12 @@ log_test_failed() printf "TEST: %-60s [FAIL]\n" "${desc}" } +log_results() +{ + echo "- Tests passed: ${npassed}" + echo "- Tests failed: ${nfailed}" +} + run_test() { local name=$1 @@ -349,17 +384,27 @@ run_test() ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null if [ $? != 0 ] then + nfailed=$((nfailed+1)) log_test_failed "${desc}" kill -2 $spid &>/dev/null else wait $spid - [ $? = 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" + if [ $? = 0 ] + then + npassed=$((npassed+1)) + log_test_passed "${desc}" + else + nfailed=$((nfailed+1)) + log_test_failed "${desc}" + fi fi } run() { echo + printf "%0.s-" {1..74} + echo echo "OUTPUT tests" printf "%0.s-" {1..74} echo @@ -369,7 +414,8 @@ run() for t in $TESTS_OUTPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean OUTPUT settings @@ -378,6 +424,8 @@ run() echo + printf "%0.s-" {1..74} + echo echo "INPUT tests" printf "%0.s-" {1..74} echo @@ -387,7 +435,8 @@ run() for t in $TESTS_INPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean INPUT settings @@ -396,7 +445,8 @@ run() ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]} ip -netns ioam-node-alpha route change db01::/64 dev veth0 - + echo + printf "%0.s-" {1..74} echo echo "GLOBAL tests" printf "%0.s-" {1..74} @@ -404,8 +454,12 @@ run() for t in $TESTS_GLOBAL do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done + + echo + log_results } bit2type=( @@ -431,11 +485,16 @@ out_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_no_room() @@ -446,11 +505,16 @@ out_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_bits() @@ -465,15 +529,36 @@ out_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + for i in {0..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 - - run_test "out_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 &>/dev/null + + local cmd_res=$? + local descr="${desc/<n>/$i}" + + if [[ $i -ge 12 && $i -le 21 ]] + then + if [ $cmd_res != 0 ] + then + npassed=$((npassed+1)) + log_test_passed "$descr" + else + nfailed=$((nfailed+1)) + log_test_failed "$descr" + fi + else + run_test "out_bit$i" "$descr ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + fi done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -485,11 +570,16 @@ out_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 100 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 100 dev veth0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -510,11 +600,16 @@ in_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_no_room() @@ -525,11 +620,16 @@ in_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_bits() @@ -544,15 +644,21 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) - for i in {0..22} + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + for i in {0..11} {22..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 - run_test "in_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -569,11 +675,16 @@ in_oflag() # back the IOAM namespace that was previously configured on the sender. ip -netns ioam-node-alpha ioam namespace add 123 - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down # And we clean the exception for this test to get things back to normal for # other INPUT tests @@ -588,11 +699,16 @@ in_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 80 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 80 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -611,11 +727,16 @@ fwd_full_supp_trace() ############################################################################## local desc="Forward - Full supported trace" - ip -netns ioam-node-alpha route change db02::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db02::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-gamma db01::2 \ - db02::2 veth0 0xfff002 123 + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-gamma \ + db01::2 db02::2 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 down } @@ -625,6 +746,9 @@ fwd_full_supp_trace() # # ################################################################################ +npassed=0 +nfailed=0 + if [ "$(id -u)" -ne 0 ] then echo "SKIP: Need root privileges" diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d376cb2c383c..8f6997d35816 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -94,16 +94,6 @@ enum { TEST_OUT_BIT9, TEST_OUT_BIT10, TEST_OUT_BIT11, - TEST_OUT_BIT12, - TEST_OUT_BIT13, - TEST_OUT_BIT14, - TEST_OUT_BIT15, - TEST_OUT_BIT16, - TEST_OUT_BIT17, - TEST_OUT_BIT18, - TEST_OUT_BIT19, - TEST_OUT_BIT20, - TEST_OUT_BIT21, TEST_OUT_BIT22, TEST_OUT_FULL_SUPP_TRACE, @@ -125,16 +115,6 @@ enum { TEST_IN_BIT9, TEST_IN_BIT10, TEST_IN_BIT11, - TEST_IN_BIT12, - TEST_IN_BIT13, - TEST_IN_BIT14, - TEST_IN_BIT15, - TEST_IN_BIT16, - TEST_IN_BIT17, - TEST_IN_BIT18, - TEST_IN_BIT19, - TEST_IN_BIT20, - TEST_IN_BIT21, TEST_IN_BIT22, TEST_IN_FULL_SUPP_TRACE, @@ -199,30 +179,6 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, ioam6h->nodelen != 2 || ioam6h->remlen; - case TEST_OUT_BIT12: - case TEST_IN_BIT12: - case TEST_OUT_BIT13: - case TEST_IN_BIT13: - case TEST_OUT_BIT14: - case TEST_IN_BIT14: - case TEST_OUT_BIT15: - case TEST_IN_BIT15: - case TEST_OUT_BIT16: - case TEST_IN_BIT16: - case TEST_OUT_BIT17: - case TEST_IN_BIT17: - case TEST_OUT_BIT18: - case TEST_IN_BIT18: - case TEST_OUT_BIT19: - case TEST_IN_BIT19: - case TEST_OUT_BIT20: - case TEST_IN_BIT20: - case TEST_OUT_BIT21: - case TEST_IN_BIT21: - return ioam6h->overflow || - ioam6h->nodelen || - ioam6h->remlen != 1; - case TEST_OUT_BIT22: case TEST_IN_BIT22: return ioam6h->overflow || @@ -326,6 +282,66 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } + if (ioam6h->type.bit12) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit13) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit14) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit15) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit16) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit17) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit18) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit19) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit20) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit21) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + if (ioam6h->type.bit22) { len = cnf.sc_data ? strlen(cnf.sc_data) : 0; aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; @@ -455,26 +471,6 @@ static int str2id(const char *tname) return TEST_OUT_BIT10; if (!strcmp("out_bit11", tname)) return TEST_OUT_BIT11; - if (!strcmp("out_bit12", tname)) - return TEST_OUT_BIT12; - if (!strcmp("out_bit13", tname)) - return TEST_OUT_BIT13; - if (!strcmp("out_bit14", tname)) - return TEST_OUT_BIT14; - if (!strcmp("out_bit15", tname)) - return TEST_OUT_BIT15; - if (!strcmp("out_bit16", tname)) - return TEST_OUT_BIT16; - if (!strcmp("out_bit17", tname)) - return TEST_OUT_BIT17; - if (!strcmp("out_bit18", tname)) - return TEST_OUT_BIT18; - if (!strcmp("out_bit19", tname)) - return TEST_OUT_BIT19; - if (!strcmp("out_bit20", tname)) - return TEST_OUT_BIT20; - if (!strcmp("out_bit21", tname)) - return TEST_OUT_BIT21; if (!strcmp("out_bit22", tname)) return TEST_OUT_BIT22; if (!strcmp("out_full_supp_trace", tname)) @@ -509,26 +505,6 @@ static int str2id(const char *tname) return TEST_IN_BIT10; if (!strcmp("in_bit11", tname)) return TEST_IN_BIT11; - if (!strcmp("in_bit12", tname)) - return TEST_IN_BIT12; - if (!strcmp("in_bit13", tname)) - return TEST_IN_BIT13; - if (!strcmp("in_bit14", tname)) - return TEST_IN_BIT14; - if (!strcmp("in_bit15", tname)) - return TEST_IN_BIT15; - if (!strcmp("in_bit16", tname)) - return TEST_IN_BIT16; - if (!strcmp("in_bit17", tname)) - return TEST_IN_BIT17; - if (!strcmp("in_bit18", tname)) - return TEST_IN_BIT18; - if (!strcmp("in_bit19", tname)) - return TEST_IN_BIT19; - if (!strcmp("in_bit20", tname)) - return TEST_IN_BIT20; - if (!strcmp("in_bit21", tname)) - return TEST_IN_BIT21; if (!strcmp("in_bit22", tname)) return TEST_IN_BIT22; if (!strcmp("in_full_supp_trace", tname)) @@ -606,16 +582,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_OUT_BIT9] = check_ioam_header_and_data, [TEST_OUT_BIT10] = check_ioam_header_and_data, [TEST_OUT_BIT11] = check_ioam_header_and_data, - [TEST_OUT_BIT12] = check_ioam_header, - [TEST_OUT_BIT13] = check_ioam_header, - [TEST_OUT_BIT14] = check_ioam_header, - [TEST_OUT_BIT15] = check_ioam_header, - [TEST_OUT_BIT16] = check_ioam_header, - [TEST_OUT_BIT17] = check_ioam_header, - [TEST_OUT_BIT18] = check_ioam_header, - [TEST_OUT_BIT19] = check_ioam_header, - [TEST_OUT_BIT20] = check_ioam_header, - [TEST_OUT_BIT21] = check_ioam_header, [TEST_OUT_BIT22] = check_ioam_header_and_data, [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_IN_UNDEF_NS] = check_ioam_header, @@ -633,16 +599,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_IN_BIT9] = check_ioam_header_and_data, [TEST_IN_BIT10] = check_ioam_header_and_data, [TEST_IN_BIT11] = check_ioam_header_and_data, - [TEST_IN_BIT12] = check_ioam_header, - [TEST_IN_BIT13] = check_ioam_header, - [TEST_IN_BIT14] = check_ioam_header, - [TEST_IN_BIT15] = check_ioam_header, - [TEST_IN_BIT16] = check_ioam_header, - [TEST_IN_BIT17] = check_ioam_header, - [TEST_IN_BIT18] = check_ioam_header, - [TEST_IN_BIT19] = check_ioam_header, - [TEST_IN_BIT20] = check_ioam_header, - [TEST_IN_BIT21] = check_ioam_header, [TEST_IN_BIT22] = check_ioam_header_and_data, [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 255793c5ac4f..293d349e21fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -945,12 +945,15 @@ subflows_tests() # subflow limited by client reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 + ip netns exec $ns2 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by client" 0 0 0 # subflow limited by server reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 @@ -973,7 +976,7 @@ subflows_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 - # multiple subflows limited by serverf + # multiple subflows limited by server reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl limits 0 2 diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 3c741abe034e..cbacf9f6538b 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -70,7 +70,7 @@ check() check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "defaults limits" +subflows 2" "defaults limits" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -118,11 +118,11 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "rcv addrs above hard limit" +subflows 2" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "subflows above hard limit" +subflows 2" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index bd6288302094..b599003eb5ba 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -28,6 +28,7 @@ #include <unistd.h> #include <time.h> #include <errno.h> +#include <getopt.h> #include <linux/xfrm.h> #include <linux/ipsec.h> @@ -101,6 +102,8 @@ struct sock_args { struct sockaddr_in6 v6; } md5_prefix; unsigned int prefix_len; + /* 0: default, -1: force off, +1: force on */ + int bind_key_ifindex; /* expected addresses and device index for connection */ const char *expected_dev; @@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args } memcpy(&md5sig.tcpm_addr, addr, alen); - if (args->ifindex) { + if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { opt = TCP_MD5SIG_EXT; md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; md5sig.tcpm_ifindex = args->ifindex; + log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex); + } else { + log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex); } rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); @@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) } #define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define OPT_FORCE_BIND_KEY_IFINDEX 1001 +#define OPT_NO_BIND_KEY_IFINDEX 1002 + +static struct option long_opts[] = { + {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, + {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {0, 0, 0, 0} +}; static void print_usage(char *prog) { @@ -1858,6 +1872,10 @@ static void print_usage(char *prog) " -M password use MD5 sum protection\n" " -X password MD5 password for client mode\n" " -m prefix/len prefix and length to use for MD5 key\n" + " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" + " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" + " (default: only if -I is passed)\n" + "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1893,7 +1911,7 @@ int main(int argc, char *argv[]) * process input args */ - while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) { switch (rc) { case 'B': both_mode = 1; @@ -1966,6 +1984,12 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case OPT_FORCE_BIND_KEY_IFINDEX: + args.bind_key_ifindex = 1; + break; + case OPT_NO_BIND_KEY_IFINDEX: + args.bind_key_ifindex = -1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 97fceb9be9ed..d3047e251fe9 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -29,6 +29,8 @@ struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; + struct tls12_crypto_info_sm4_gcm sm4gcm; + struct tls12_crypto_info_sm4_ccm sm4ccm; }; size_t len; }; @@ -49,6 +51,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aes128.info.version = tls_version; tls12->aes128.info.cipher_type = cipher_type; break; + case TLS_CIPHER_SM4_GCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_gcm); + tls12->sm4gcm.info.version = tls_version; + tls12->sm4gcm.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_SM4_CCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_ccm); + tls12->sm4ccm.info.version = tls_version; + tls12->sm4ccm.info.cipher_type = cipher_type; + break; default: break; } @@ -148,13 +160,13 @@ FIXTURE_VARIANT(tls) uint16_t cipher_type; }; -FIXTURE_VARIANT_ADD(tls, 12_gcm) +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, }; -FIXTURE_VARIANT_ADD(tls, 13_gcm) +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, @@ -172,6 +184,18 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha) .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, }; +FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_GCM, +}; + +FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_CCM, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 427d94816f2d..d4ffebb989f8 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -199,7 +199,6 @@ fi # test basic connectivity if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 - bash exit 1 fi diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index d7e07f4c3d7f..da1c1e4b6c86 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -741,6 +741,149 @@ EOF return $lret } +# test port shadowing. +# create two listening services, one on router (ns0), one +# on client (ns2), which is masqueraded from ns1 point of view. +# ns2 sends udp packet coming from service port to ns1, on a highport. +# Later, if n1 uses same highport to connect to ns0:service, packet +# might be port-forwarded to ns2 instead. + +# second argument tells if we expect the 'fake-entry' to take effect +# (CLIENT) or not (ROUTER). +test_port_shadow() +{ + local test=$1 + local expect=$2 + local daddrc="10.0.1.99" + local daddrs="10.0.1.1" + local result="" + local logmsg="" + + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_r=$! + + echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_c=$! + + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + + # ns1 tries to connect to ns0:1405. With default settings this should connect + # to client, it matches the conntrack entry created above. + + result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + + if [ "$result" = "$expect" ] ;then + echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" + else + echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended" + ret=1 + fi + + kill $nc_r $nc_c 2>/dev/null + + # flush udp entries for next test round, if any + ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 +} + +# This prevents port shadow of router service via packet filter, +# packets claiming to originate from service port from internal +# network are dropped. +test_port_shadow_filter() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family filter { + chain forward { + type filter hook forward priority 0; policy accept; + meta iif veth1 udp sport 1405 drop + } +} +EOF + test_port_shadow "port-filter" "ROUTER" + + ip netns exec "$ns0" nft delete table $family filter +} + +# This prevents port shadow of router service via notrack. +test_port_shadow_notrack() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family raw { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 udp dport 1405 notrack + udp dport 1405 notrack + } + chain output { + type filter hook output priority -300; policy accept; + udp sport 1405 notrack + } +} +EOF + test_port_shadow "port-notrack" "ROUTER" + + ip netns exec "$ns0" nft delete table $family raw +} + +# This prevents port shadow of router service via sport remap. +test_port_shadow_pat() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family pat { + chain postrouting { + type nat hook postrouting priority -1; policy accept; + meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random + } +} +EOF + test_port_shadow "pat" "ROUTER" + + ip netns exec "$ns0" nft delete table $family pat +} + +test_port_shadowing() +{ + local family="ip" + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" + + # test packet filter based mitigation: prevent forwarding of + # packets claiming to come from the service port. + test_port_shadow_filter "$family" + + # test conntrack based mitigation: connections going or coming + # from router:service bypass connection tracking. + test_port_shadow_notrack "$family" + + # test nat based mitigation: fowarded packets coming from service port + # are masqueraded with random highport. + test_port_shadow_pat "$family" + + ip netns exec "$ns0" nft delete table $family nat +} # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do @@ -861,6 +1004,8 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +test_port_shadowing + if [ $ret -ne 0 ];then echo -n "FAIL: " nft --version diff --git a/tools/testing/selftests/netfilter/nft_nat_zones.sh b/tools/testing/selftests/netfilter/nft_nat_zones.sh new file mode 100755 index 000000000000..b9ab37380f33 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat_zones.sh @@ -0,0 +1,309 @@ +#!/bin/bash +# +# Test connection tracking zone and NAT source port reallocation support. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Don't increase too much, 2000 clients should work +# just fine but script can then take several minutes with +# KASAN/debug builds. +maxclients=100 + +have_iperf=1 +ret=0 + +# client1---. +# veth1-. +# | +# NAT Gateway --veth0--> Server +# | | +# veth2-' | +# client2---' | +# .... | +# clientX----vethX---' + +# All clients share identical IP address. +# NAT Gateway uses policy routing and conntrack zones to isolate client +# namespaces. Each client connects to Server, each with colliding tuples: +# clientsaddr:10000 -> serveraddr:dport +# NAT Gateway is supposed to do port reallocation for each of the +# connections. + +sfx=$(mktemp -u "XXXXXXXX") +gw="ns-gw-$sfx" +cl1="ns-cl1-$sfx" +cl2="ns-cl2-$sfx" +srv="ns-srv-$sfx" + +v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null) +v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null) +v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null) +v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null) +v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null) +v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null) + +cleanup() +{ + ip netns del $gw + ip netns del $srv + for i in $(seq 1 $maxclients); do + ip netns del ns-cl$i-$sfx 2>/dev/null + done + + sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +conntrack -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without conntrack tool" + exit $ksft_skip +fi + +iperf3 -v >/dev/null 2>&1 +if [ $? -ne 0 ];then + have_iperf=0 +fi + +ip netns add "$gw" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi +ip -net "$gw" link set lo up + +trap cleanup EXIT + +ip netns add "$srv" +if [ $? -ne 0 ];then + echo "SKIP: Could not create server netns $srv" + exit $ksft_skip +fi + +ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv" +ip -net "$gw" link set veth0 up +ip -net "$srv" link set lo up +ip -net "$srv" link set eth0 up + +sysctl -q net.ipv6.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + + ip netns add "$cl" + if [ $? -ne 0 ];then + echo "SKIP: Could not create client netns $cl" + exit $ksft_skip + fi + ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip + fi +done + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + echo netns exec "$cl" ip link set lo up + echo netns exec "$cl" ip link set eth0 up + echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2 + echo netns exec "$gw" ip link set veth$i up + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2 + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0 + + # clients have same IP addresses. + echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0 + echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0 + echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0 + echo netns exec "$cl" ip route add default via dead:1::2 dev eth0 + + # NB: same addresses on client-facing interfaces. + echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i + echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i + + # gw: policy routing + echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i)) +done | ip -batch /dev/stdin + +ip -net "$gw" addr add 10.3.0.1/24 dev veth0 +ip -net "$gw" addr add dead:3::1/64 dev veth0 + +ip -net "$srv" addr add 10.3.0.99/24 dev eth0 +ip -net "$srv" addr add dead:3::99/64 dev eth0 + +ip netns exec $gw nft -f /dev/stdin<<EOF +table inet raw { + map iiftomark { + type ifname : mark + } + + map iiftozone { + typeof iifname : ct zone + } + + set inicmp { + flags dynamic + type ipv4_addr . ifname . ipv4_addr + } + set inflows { + flags dynamic + type ipv4_addr . inet_service . ifname . ipv4_addr . inet_service + } + + set inflows6 { + flags dynamic + type ipv6_addr . inet_service . ifname . ipv6_addr . inet_service + } + + chain prerouting { + type filter hook prerouting priority -64000; policy accept; + ct original zone set meta iifname map @iiftozone + meta mark set meta iifname map @iiftomark + + tcp flags & (syn|ack) == ack add @inflows { ip saddr . tcp sport . meta iifname . ip daddr . tcp dport counter } + add @inflows6 { ip6 saddr . tcp sport . meta iifname . ip6 daddr . tcp dport counter } + ip protocol icmp add @inicmp { ip saddr . meta iifname . ip daddr counter } + } + + chain nat_postrouting { + type nat hook postrouting priority 0; policy accept; + ct mark set meta mark meta oifname veth0 masquerade + } + + chain mangle_prerouting { + type filter hook prerouting priority -100; policy accept; + ct direction reply meta mark set ct mark + } +} +EOF + +( echo add element inet raw iiftomark \{ + for i in $(seq 1 $((maxclients-1))); do + echo \"veth$i\" : $i, + done + echo \"veth$maxclients\" : $maxclients \} + echo add element inet raw iiftozone \{ + for i in $(seq 1 $((maxclients-1))); do + echo \"veth$i\" : $i, + done + echo \"veth$maxclients\" : $maxclients \} +) | ip netns exec $gw nft -f /dev/stdin + +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null + +# useful for debugging: allows to use 'ping' from clients to gateway. +ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null + +for i in $(seq 1 $maxclients); do + cl="ns-cl$i-$sfx" + ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 & + if [ $? -ne 0 ]; then + echo FAIL: Ping failure from $cl 1>&2 + ret=1 + break + fi +done + +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }" + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth$i" 1>&2 + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2 + break + fi +done + +ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" + ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2 +fi + +if [ $ret -eq 0 ]; then + echo "PASS: ping test from all $maxclients namespaces" +fi + +if [ $have_iperf -eq 0 ];then + echo "SKIP: iperf3 not installed" + if [ $ret -ne 0 ];then + exit $ret + fi + exit $ksft_skip +fi + +ip netns exec $srv iperf3 -s > /dev/null 2>&1 & +iperfpid=$! +sleep 1 + +for i in $(seq 1 $maxclients); do + if [ $ret -ne 0 ]; then + break + fi + cl="ns-cl$i-$sfx" + ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null + if [ $? -ne 0 ]; then + echo FAIL: Failure to connect for $cl 1>&2 + ip netns exec $gw conntrack -S 1>&2 + ret=1 + fi +done +if [ $ret -eq 0 ];then + echo "PASS: iperf3 connections for all $maxclients net namespaces" +fi + +kill $iperfpid +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: can't find expected tcp entry for veth$i" 1>&2 + break + fi +done +if [ $ret -eq 0 ];then + echo "PASS: Found client connection for all $maxclients net namespaces" +fi + +ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: cannot find return entry on veth0" 1>&2 +fi + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh new file mode 100755 index 000000000000..ac646376eb01 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -0,0 +1,156 @@ +#!/bin/bash + +# Test insertion speed for packets with identical addresses/ports +# that are all placed in distinct conntrack zones. + +sfx=$(mktemp -u "XXXXXXXX") +ns="ns-$sfx" + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +zones=20000 +have_ct_tool=0 +ret=0 + +cleanup() +{ + ip netns del $ns +} + +ip netns add $ns +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi + +trap cleanup EXIT + +conntrack -V > /dev/null 2>&1 +if [ $? -eq 0 ];then + have_ct_tool=1 +fi + +ip -net "$ns" link set lo up + +test_zones() { + local max_zones=$1 + +ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600 +ip netns exec $ns nft -f /dev/stdin<<EOF +flush ruleset +table inet raw { + map rndzone { + typeof numgen inc mod $max_zones : ct zone + } + + chain output { + type filter hook output priority -64000; policy accept; + udp dport 12345 ct zone set numgen inc mod 65536 map @rndzone + } +} +EOF + ( + echo "add element inet raw rndzone {" + for i in $(seq 1 $max_zones);do + echo -n "$i : $i" + if [ $i -lt $max_zones ]; then + echo "," + else + echo "}" + fi + done + ) | ip netns exec $ns nft -f /dev/stdin + + local i=0 + local j=0 + local outerstart=$(date +%s%3N) + local stop=$outerstart + + while [ $i -lt $max_zones ]; do + local start=$(date +%s%3N) + i=$((i + 10000)) + j=$((j + 1)) + dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + if [ $? -ne 0 ] ;then + ret=1 + break + fi + + stop=$(date +%s%3N) + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + done + + if [ $have_ct_tool -eq 1 ]; then + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries from packet path in $duration ms total" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries" + ret=1 + fi + fi + + if [ $ret -ne 0 ];then + echo "FAIL: insert $max_zones entries from packet path" 1>&2 + fi +} + +test_conntrack_tool() { + local max_zones=$1 + + ip netns exec $ns conntrack -F >/dev/null 2>/dev/null + + local outerstart=$(date +%s%3N) + local start=$(date +%s%3N) + local stop=$start + local i=0 + while [ $i -lt $max_zones ]; do + i=$((i + 1)) + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1 + if [ $? -ne 0 ];then + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null + echo "FAIL: conntrack -I returned an error" + ret=1 + break + fi + + if [ $((i%10000)) -eq 0 ];then + stop=$(date +%s%3N) + + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total)" + start=$stop + fi + done + + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries via ctnetlink in $duration ms" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)" + ret=1 + fi +} + +test_zones $zones + +if [ $have_ct_tool -eq 1 ];then + test_conntrack_tool $zones +else + echo "SKIP: Could not run ctnetlink insertion test without conntrack tool" + if [ $ret -eq 0 ];then + exit $ksft_skip + fi +fi + +exit $ret diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S index bd1ca25febe4..aed632d29fff 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S +++ b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include <ppc-asm.h> +#include <basic_asm.h> #include <asm/unistd.h> .text @@ -26,3 +26,38 @@ FUNC_START(getppid_tm_suspended) 1: li r3, -1 blr + + +.macro scv level + .long (0x44000001 | (\level) << 5) +.endm + +FUNC_START(getppid_scv_tm_active) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + scv 0 + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr + +FUNC_START(getppid_scv_tm_suspended) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + tsuspend. + scv 0 + tresume. + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index 467a6b3134b2..b763354c2eb4 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -19,23 +19,36 @@ #include "utils.h" #include "tm.h" +#ifndef PPC_FEATURE2_SCV +#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */ +#endif + extern int getppid_tm_active(void); extern int getppid_tm_suspended(void); +extern int getppid_scv_tm_active(void); +extern int getppid_scv_tm_suspended(void); unsigned retries = 0; #define TEST_DURATION 10 /* seconds */ -pid_t getppid_tm(bool suspend) +pid_t getppid_tm(bool scv, bool suspend) { int i; pid_t pid; for (i = 0; i < TM_RETRIES; i++) { - if (suspend) - pid = getppid_tm_suspended(); - else - pid = getppid_tm_active(); + if (suspend) { + if (scv) + pid = getppid_scv_tm_suspended(); + else + pid = getppid_tm_suspended(); + } else { + if (scv) + pid = getppid_scv_tm_active(); + else + pid = getppid_tm_active(); + } if (pid >= 0) return pid; @@ -82,15 +95,24 @@ int tm_syscall(void) * Test a syscall within a suspended transaction and verify * that it succeeds. */ - FAIL_IF(getppid_tm(true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(false, true) == -1); /* Should succeed. */ /* * Test a syscall within an active transaction and verify that * it fails with the correct failure code. */ - FAIL_IF(getppid_tm(false) != -1); /* Should fail... */ + FAIL_IF(getppid_tm(false, false) != -1); /* Should fail... */ FAIL_IF(!failure_is_persistent()); /* ...persistently... */ FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + + /* Now do it all again with scv if it is available. */ + if (have_hwcap2(PPC_FEATURE2_SCV)) { + FAIL_IF(getppid_tm(true, true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(true, false) != -1); /* Should fail... */ + FAIL_IF(!failure_is_persistent()); /* ...persistently... */ + FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + } + gettimeofday(&now, 0); } diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 10ab56c2484a..60aa1a4fc69b 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -414,9 +414,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features) uffd_test_ops->allocate_area((void **)&area_src); uffd_test_ops->allocate_area((void **)&area_dst); - uffd_test_ops->release_pages(area_src); - uffd_test_ops->release_pages(area_dst); - userfaultfd_open(features); count_verify = malloc(nr_pages * sizeof(unsigned long long)); @@ -437,6 +434,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features) *(area_count(area_src, nr) + 1) = 1; } + /* + * After initialization of area_src, we must explicitly release pages + * for area_dst to make sure it's fully empty. Otherwise we could have + * some area_dst pages be errornously initialized with zero pages, + * hence we could hit memory corruption later in the test. + * + * One example is when THP is globally enabled, above allocate_area() + * calls could have the two areas merged into a single VMA (as they + * will have the same VMA flags so they're mergeable). When we + * initialize the area_src above, it's possible that some part of + * area_dst could have been faulted in via one huge THP that will be + * shared between area_src and area_dst. It could cause some of the + * area_dst won't be trapped by missing userfaults. + * + * This release_pages() will guarantee even if that happened, we'll + * proactively split the thp and drop any accidentally initialized + * pages within area_dst. + */ + uffd_test_ops->release_pages(area_dst); + pipefd = malloc(sizeof(int) * nr_cpus * 2); if (!pipefd) err("pipefd"); diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index cec6f5a738e1..fa927ad16f8a 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts) read_vsock_stat(&sockets); check_no_sockets(&sockets); - - free_sock_stat(&sockets); } static void test_listen_socket_server(const struct test_opts *opts) diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c index ee8208b2f946..69c3ead25313 100644 --- a/tools/usb/testusb.c +++ b/tools/usb/testusb.c @@ -265,12 +265,6 @@ nomem: } entry->ifnum = ifnum; - - /* FIXME update USBDEVFS_CONNECTINFO so it tells about high speed etc */ - - fprintf(stderr, "%s speed\t%s\t%u\n", - speed(entry->speed), entry->name, entry->ifnum); - entry->next = testdevs; testdevs = entry; return 0; @@ -299,6 +293,14 @@ static void *handle_testdev (void *arg) return 0; } + status = ioctl(fd, USBDEVFS_GET_SPEED, NULL); + if (status < 0) + fprintf(stderr, "USBDEVFS_GET_SPEED failed %d\n", status); + else + dev->speed = status; + fprintf(stderr, "%s speed\t%s\t%u\n", + speed(dev->speed), dev->name, dev->ifnum); + restart: for (i = 0; i < TEST_CASES; i++) { if (dev->test != -1 && dev->test != i) diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 0517c744b04e..f62f10c988db 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -1331,7 +1331,7 @@ int main(int argc, char *argv[]) if (opt_list && opt_list_mapcnt) kpagecount_fd = checked_open(PROC_KPAGECOUNT, O_RDONLY); - if (opt_mark_idle && opt_file) + if (opt_mark_idle) page_idle_fd = checked_open(SYS_KERNEL_MM_PAGE_IDLE, O_RDWR); if (opt_list && opt_pid) |