diff options
Diffstat (limited to 'tools')
128 files changed, 4536 insertions, 1102 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/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h index 7862f217d85d..f2e506f7d57f 100644 --- a/tools/bootconfig/include/linux/memblock.h +++ b/tools/bootconfig/include/linux/memblock.h @@ -4,9 +4,8 @@ #include <stdlib.h> -#define __pa(addr) (addr) #define SMP_CACHE_BYTES 0 #define memblock_alloc(size, align) malloc(size) -#define memblock_free(paddr, size) free(paddr) +#define memblock_free_ptr(paddr, size) free(paddr) #endif diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 95c072b70d0e..8816f06fc6c7 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,9 +16,9 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#if GCC_VERSION >= 40300 +#if __has_attribute(__error__) # define __compiletime_error(message) __attribute__((error(message))) -#endif /* GCC_VERSION >= 40300 */ +#endif /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) @@ -38,7 +38,3 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 8712ff70995f..dcb0c1bf6866 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -5,12 +5,9 @@ #include <linux/compiler.h> /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -36,8 +33,6 @@ #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) - -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -73,135 +68,6 @@ __builtin_mul_overflow(__a, __b, __d); \ }) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) - -#define check_sub_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) - -#define check_mul_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** * array_size() - Calculate size of 2-dimensional array. * diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..2fc09579e24a 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1210,14 +1210,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1241,7 +1243,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ @@ -1307,6 +1315,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) 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/libbpf.c b/tools/lib/bpf/libbpf.c index 88d8825fc6f6..e4f83c304ec9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6894,7 +6894,8 @@ 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) 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/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..4d6d7fc13255 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -20,6 +20,7 @@ #include <objtool/arch.h> #include <objtool/warn.h> #include <objtool/endianness.h> +#include <objtool/builtin.h> #include <arch/elf.h> static int is_x86_64(const struct elf *elf) @@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn) #define rm_is_mem(reg) (mod_is_mem() && !is_RIP() && rm_is(reg)) #define rm_is_reg(reg) (mod_is_reg() && modrm_rm == (reg)) -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, struct list_head *ops_list) { + const struct elf *elf = file->elf; struct insn insn; int x86_64, ret; unsigned char op1, op2, @@ -544,6 +546,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec, *type = INSN_RETURN; break; + case 0xc7: /* mov imm, r/m */ + if (!noinstr) + break; + + if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { + struct reloc *immr, *disp; + struct symbol *func; + int idx; + + immr = find_reloc_by_dest(elf, (void *)sec, offset+3); + disp = find_reloc_by_dest(elf, (void *)sec, offset+7); + + if (!immr || strcmp(immr->sym->name, "pv_ops")) + break; + + idx = (immr->addend + 8) / sizeof(void *); + + func = disp->sym; + if (disp->sym->type == STT_SECTION) + func = find_symbol_by_offset(disp->sym->sec, disp->addend); + if (!func) { + WARN("no func for pv_ops[]"); + return -1; + } + + objtool_pv_add(file, idx, func); + } + + break; + case 0xcf: /* iret */ /* * Handle sync_core(), which has an IRET to self. @@ -659,154 +691,52 @@ const char *arch_nop_insn(int len) return nops[len-1]; } -/* asm/alternative.h ? */ - -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) - -struct alt_instr { - s32 instr_offset; /* original instruction */ - s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ - u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ -} __packed; - -static int elf_add_alternative(struct elf *elf, - struct instruction *orig, struct symbol *sym, - int cpuid, u8 orig_len, u8 repl_len) -{ - const int size = sizeof(struct alt_instr); - struct alt_instr *alt; - struct section *sec; - Elf_Scn *s; - - sec = find_section_by_name(elf, ".altinstructions"); - if (!sec) { - sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, size, 0); - - if (!sec) { - WARN_ELF("elf_create_section"); - return -1; - } - } - - s = elf_getscn(elf->elf, sec->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return -1; - } - - sec->data = elf_newdata(s); - if (!sec->data) { - WARN_ELF("elf_newdata"); - return -1; - } - - sec->data->d_size = size; - sec->data->d_align = 1; - - alt = sec->data->d_buf = malloc(size); - if (!sec->data->d_buf) { - perror("malloc"); - return -1; - } - memset(sec->data->d_buf, 0, size); - - if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, - R_X86_64_PC32, orig->sec, orig->offset)) { - WARN("elf_create_reloc: alt_instr::instr_offset"); - return -1; - } - - if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, - R_X86_64_PC32, sym, 0)) { - WARN("elf_create_reloc: alt_instr::repl_offset"); - return -1; - } - - alt->cpuid = bswap_if_needed(cpuid); - alt->instrlen = orig_len; - alt->replacementlen = repl_len; - - sec->sh.sh_size += size; - sec->changed = true; - - return 0; -} - -#define X86_FEATURE_RETPOLINE ( 7*32+12) +#define BYTE_RET 0xC3 -int arch_rewrite_retpolines(struct objtool_file *file) +const char *arch_ret_insn(int len) { - struct instruction *insn; - struct reloc *reloc; - struct symbol *sym; - char name[32] = ""; - - list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - - if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) - continue; - - if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) - continue; - - reloc = insn->reloc; - - sprintf(name, "__x86_indirect_alt_%s_%s", - insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", - reloc->sym->name + 21); - - sym = find_symbol_by_name(file->elf, name); - if (!sym) { - sym = elf_create_undef_symbol(file->elf, name); - if (!sym) { - WARN("elf_create_undef_symbol"); - return -1; - } - } + static const char ret[5][5] = { + { BYTE_RET }, + { BYTE_RET, BYTES_NOP1 }, + { BYTE_RET, BYTES_NOP2 }, + { BYTE_RET, BYTES_NOP3 }, + { BYTE_RET, BYTES_NOP4 }, + }; - if (elf_add_alternative(file->elf, insn, sym, - ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { - WARN("elf_add_alternative"); - return -1; - } + if (len < 1 || len > 5) { + WARN("invalid RET size: %d\n", len); + return NULL; } - return 0; + return ret[len-1]; } -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) +int arch_decode_hint_reg(u8 sp_reg, int *base) { - struct cfi_reg *cfa = &insn->cfi.cfa; - switch (sp_reg) { case ORC_REG_UNDEFINED: - cfa->base = CFI_UNDEFINED; + *base = CFI_UNDEFINED; break; case ORC_REG_SP: - cfa->base = CFI_SP; + *base = CFI_SP; break; case ORC_REG_BP: - cfa->base = CFI_BP; + *base = CFI_BP; break; case ORC_REG_SP_INDIRECT: - cfa->base = CFI_SP_INDIRECT; + *base = CFI_SP_INDIRECT; break; case ORC_REG_R10: - cfa->base = CFI_R10; + *base = CFI_R10; break; case ORC_REG_R13: - cfa->base = CFI_R13; + *base = CFI_R13; break; case ORC_REG_DI: - cfa->base = CFI_DI; + *base = CFI_DI; break; case ORC_REG_DX: - cfa->base = CFI_DX; + *base = CFI_DX; break; default: return -1; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e5947fbb9e7a..fb3f251ea021 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@ #include <string.h> #include <stdlib.h> +#include <sys/mman.h> #include <arch/elf.h> #include <objtool/builtin.h> @@ -26,7 +27,11 @@ struct alternative { bool skip_orig; }; -struct cfi_init_state initial_func_cfi; +static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; + +static struct cfi_init_state initial_func_cfi; +static struct cfi_state init_cfi; +static struct cfi_state func_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -173,6 +178,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "rewind_stack_do_exit", "kunit_try_catch_throw", "xen_start_kernel", + "cpu_bringup_and_idle", }; if (!func) @@ -265,6 +271,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec) state->noinstr = sec->noinstr; } +static struct cfi_state *cfi_alloc(void) +{ + struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1); + if (!cfi) { + WARN("calloc failed"); + exit(1); + } + nr_cfi++; + return cfi; +} + +static int cfi_bits; +static struct hlist_head *cfi_hash; + +static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2) +{ + return memcmp((void *)cfi1 + sizeof(cfi1->hash), + (void *)cfi2 + sizeof(cfi2->hash), + sizeof(struct cfi_state) - sizeof(struct hlist_node)); +} + +static inline u32 cfi_key(struct cfi_state *cfi) +{ + return jhash((void *)cfi + sizeof(cfi->hash), + sizeof(*cfi) - sizeof(cfi->hash), 0); +} + +static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + struct cfi_state *obj; + + hlist_for_each_entry(obj, head, hash) { + if (!cficmp(cfi, obj)) { + nr_cfi_cache++; + return obj; + } + } + + obj = cfi_alloc(); + *obj = *cfi; + hlist_add_head(&obj->hash, head); + + return obj; +} + +static void cfi_hash_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + + hlist_add_head(&cfi->hash, head); +} + +static void *cfi_hash_alloc(unsigned long size) +{ + cfi_bits = max(10, ilog2(size)); + cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits, + PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (cfi_hash == (void *)-1L) { + WARN("mmap fail cfi_hash"); + cfi_hash = NULL; + } else if (stats) { + printf("cfi_bits: %d\n", cfi_bits); + } + + return cfi_hash; +} + +static unsigned long nr_insns; +static unsigned long nr_insns_visited; + /* * Call the arch-specific instruction decoder for all the instructions and add * them to the global instruction list. @@ -275,7 +353,6 @@ static int decode_instructions(struct objtool_file *file) struct symbol *func; unsigned long offset; struct instruction *insn; - unsigned long nr_insns = 0; int ret; for_each_sec(file, sec) { @@ -292,7 +369,7 @@ 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"); @@ -301,13 +378,12 @@ static int decode_instructions(struct objtool_file *file) memset(insn, 0, sizeof(*insn)); INIT_LIST_HEAD(&insn->alts); INIT_LIST_HEAD(&insn->stack_ops); - init_cfi_state(&insn->cfi); insn->sec = sec; insn->offset = offset; - ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, + ret = arch_decode_instruction(file, sec, offset, + sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, &insn->stack_ops); @@ -344,14 +420,90 @@ err: return ret; } +/* + * Read the pv_ops[] .data table to find the static initialized values. + */ +static int add_pv_ops(struct objtool_file *file, const char *symname) +{ + struct symbol *sym, *func; + unsigned long off, end; + struct reloc *rel; + int idx; + + sym = find_symbol_by_name(file->elf, symname); + if (!sym) + return 0; + + off = sym->offset; + end = off + sym->len; + for (;;) { + rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!rel) + break; + + func = rel->sym; + if (func->type == STT_SECTION) + func = find_symbol_by_offset(rel->sym->sec, rel->addend); + + idx = (rel->offset - sym->offset) / sizeof(unsigned long); + + objtool_pv_add(file, idx, func); + + off = rel->offset + 1; + if (off > end) + break; + } + + return 0; +} + +/* + * Allocate and initialize file->pv_ops[]. + */ +static int init_pv_ops(struct objtool_file *file) +{ + static const char *pv_ops_tables[] = { + "pv_ops", + "xen_cpu_ops", + "xen_irq_ops", + "xen_mmu_ops", + NULL, + }; + const char *pv_ops; + struct symbol *sym; + int idx, nr; + + if (!noinstr) + return 0; + + file->pv_ops = NULL; + + sym = find_symbol_by_name(file->elf, "pv_ops"); + if (!sym) + return 0; + + nr = sym->len / sizeof(unsigned long); + file->pv_ops = calloc(sizeof(struct pv_state), nr); + if (!file->pv_ops) + return -1; + + for (idx = 0; idx < nr; idx++) + INIT_LIST_HEAD(&file->pv_ops[idx].targets); + + for (idx = 0; (pv_ops = pv_ops_tables[idx]); idx++) + add_pv_ops(file, pv_ops); + + return 0; +} + static struct instruction *find_last_insn(struct objtool_file *file, struct section *sec) { 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 +541,7 @@ 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 +576,7 @@ 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", @@ -531,6 +683,52 @@ static int create_static_call_sections(struct objtool_file *file) return 0; } +static int create_retpoline_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".retpoline_sites"); + if (sec) { + WARN("file already has .retpoline_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".retpoline_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .retpoline_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .retpoline_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_mcount_loc_sections(struct objtool_file *file) { struct section *sec; @@ -549,7 +747,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return 0; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) + list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx); @@ -557,7 +755,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return -1; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) { + list_for_each_entry(insn, &file->mcount_loc_list, call_node) { loc = (unsigned long *)sec->data->d_buf + idx; memset(loc, 0, sizeof(unsigned long)); @@ -817,6 +1015,9 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return NULL; if (!insn->reloc) { + if (!file) + return NULL; + insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); if (!insn->reloc) { @@ -828,6 +1029,136 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return insn->reloc; } +static void remove_insn_ops(struct instruction *insn) +{ + struct stack_op *op, *tmp; + + list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { + list_del(&op->list); + free(op); + } +} + +static void annotate_call_site(struct objtool_file *file, + struct instruction *insn, bool sibling) +{ + struct reloc *reloc = insn_reloc(file, insn); + struct symbol *sym = insn->call_dest; + + if (!sym) + sym = reloc->sym; + + /* + * Alternative replacement code is just template code which is + * sometimes copied to the original instruction. For now, don't + * annotate it. (In the future we might consider annotating the + * original instruction if/when it ever makes sense to do so.) + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + return; + + if (sym->static_call_tramp) { + list_add_tail(&insn->call_node, &file->static_call_list); + return; + } + + if (sym->retpoline_thunk) { + list_add_tail(&insn->call_node, &file->retpoline_call_list); + return; + } + + /* + * Many compilers cannot disable KCOV with a function attribute + * so they need a little help, NOP out any KCOV calls from noinstr + * text. + */ + if (insn->sec->noinstr && sym->kcov) { + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + sibling ? arch_ret_insn(insn->len) + : arch_nop_insn(insn->len)); + + insn->type = sibling ? INSN_RETURN : INSN_NOP; + return; + } + + if (mcount && sym->fentry) { + if (sibling) + WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); + + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + arch_nop_insn(insn->len)); + + insn->type = INSN_NOP; + + list_add_tail(&insn->call_node, &file->mcount_loc_list); + return; + } +} + +static void add_call_dest(struct objtool_file *file, struct instruction *insn, + struct symbol *dest, bool sibling) +{ + insn->call_dest = dest; + if (!dest) + return; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, sibling); +} + +static void add_retpoline_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Retpoline calls/jumps are really dynamic calls/jumps in disguise, + * so convert them accordingly. + */ + switch (insn->type) { + case INSN_CALL: + insn->type = INSN_CALL_DYNAMIC; + break; + case INSN_JUMP_UNCONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC; + break; + case INSN_JUMP_CONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + break; + default: + return; + } + + insn->retpoline_safe = true; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, false); +} /* * Find the destination instructions for all jumps. */ @@ -849,28 +1180,12 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline jumps are really dynamic jumps in - * disguise, so convert them accordingly. - */ - if (insn->type == INSN_JUMP_UNCONDITIONAL) - insn->type = INSN_JUMP_DYNAMIC; - else - insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - insn->retpoline_safe = true; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ - insn->call_dest = reloc->sym; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { dest_sec = reloc->sym->sec; @@ -926,13 +1241,8 @@ static int add_jump_destinations(struct objtool_file *file) } else if (insn->jump_dest->func->pfunc != insn->func->pfunc && insn->jump_dest->offset == insn->jump_dest->func->offset) { - /* internal sibling call (without reloc) */ - insn->call_dest = insn->jump_dest->func; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, insn->jump_dest->func, true); } } } @@ -940,16 +1250,6 @@ static int add_jump_destinations(struct objtool_file *file) return 0; } -static void remove_insn_ops(struct instruction *insn) -{ - struct stack_op *op, *tmp; - - list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { - list_del(&op->list); - free(op); - } -} - static struct symbol *find_call_destination(struct section *sec, unsigned long offset) { struct symbol *call_dest; @@ -968,6 +1268,7 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; + struct symbol *dest; struct reloc *reloc; for_each_insn(file, insn) { @@ -977,7 +1278,9 @@ static int add_call_destinations(struct objtool_file *file) reloc = insn_reloc(file, insn); if (!reloc) { dest_off = arch_jump_destination(insn); - insn->call_dest = find_call_destination(insn->sec, dest_off); + dest = find_call_destination(insn->sec, dest_off); + + add_call_dest(file, insn, dest, false); if (insn->ignore) continue; @@ -995,9 +1298,8 @@ static int add_call_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_off = arch_dest_reloc_offset(reloc->addend); - insn->call_dest = find_call_destination(reloc->sym->sec, - dest_off); - if (!insn->call_dest) { + dest = find_call_destination(reloc->sym->sec, dest_off); + if (!dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, reloc->sym->sec->name, @@ -1005,70 +1307,13 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline calls are really dynamic calls in - * disguise, so convert them accordingly. - */ - insn->type = INSN_CALL_DYNAMIC; - insn->retpoline_safe = true; + add_call_dest(file, insn, dest, false); - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - remove_insn_ops(insn); - continue; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); } else - insn->call_dest = reloc->sym; - - if (insn->call_dest && insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } - - /* - * Many compilers cannot disable KCOV with a function attribute - * so they need a little help, NOP out any KCOV calls from noinstr - * text. - */ - if (insn->sec->noinstr && - !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - insn->type = INSN_NOP; - } - - if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - - insn->type = INSN_NOP; - - list_add_tail(&insn->mcount_loc_node, - &file->mcount_loc_list); - } - - /* - * Whatever stack impact regular CALLs have, should be undone - * by the RETURN of the called function. - * - * Annotated intra-function calls retain the stack_ops but - * are converted to JUMP, see read_intra_function_calls(). - */ - remove_insn_ops(insn); + add_call_dest(file, insn, reloc->sym, false); } return 0; @@ -1136,7 +1381,6 @@ static int handle_group_alt(struct objtool_file *file, memset(nop, 0, sizeof(*nop)); INIT_LIST_HEAD(&nop->alts); INIT_LIST_HEAD(&nop->stack_ops); - init_cfi_state(&nop->cfi); nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1545,10 +1789,11 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { + struct cfi_state cfi = init_cfi; struct section *sec, *relocsec; - struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; + struct reloc *reloc; int i; sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1561,14 +1806,14 @@ 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)); @@ -1586,19 +1831,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; if (hint->type == UNWIND_HINT_TYPE_FUNC) { - set_func_state(&insn->cfi); + insn->cfi = &func_cfi; continue; } - if (arch_decode_hint_reg(insn, hint->sp_reg)) { + if (insn->cfi) + cfi = *(insn->cfi); + + if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; } - insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset); - insn->cfi.type = hint->type; - insn->cfi.end = hint->end; + cfi.cfa.offset = bswap_if_needed(hint->sp_offset); + cfi.type = hint->type; + cfi.end = hint->end; + + insn->cfi = cfi_hash_find_or_add(&cfi); } return 0; @@ -1737,17 +1987,28 @@ static int read_intra_function_calls(struct objtool_file *file) return 0; } -static int read_static_call_tramps(struct objtool_file *file) +static int classify_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func; for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind == STB_GLOBAL && - !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + if (func->bind != STB_GLOBAL) + continue; + + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, strlen(STATIC_CALL_TRAMP_PREFIX_STR))) func->static_call_tramp = true; + + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; + + if (!strcmp(func->name, "__fentry__")) + func->fentry = true; + + if (!strncmp(func->name, "__sanitizer_cov_", 16)) + func->kcov = true; } } @@ -1780,17 +2041,16 @@ static void mark_rodata(struct objtool_file *file) file->rodata = found; } -__weak int arch_rewrite_retpolines(struct objtool_file *file) -{ - return 0; -} - static int decode_sections(struct objtool_file *file) { int ret; mark_rodata(file); + ret = init_pv_ops(file); + if (ret) + return ret; + ret = decode_instructions(file); if (ret) return ret; @@ -1809,7 +2069,7 @@ static int decode_sections(struct objtool_file *file) /* * Must be before add_{jump_call}_destination. */ - ret = read_static_call_tramps(file); + ret = classify_symbols(file); if (ret) return ret; @@ -1853,23 +2113,14 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - /* - * Must be after add_special_section_alts(), since this will emit - * alternatives. Must be after add_{jump,call}_destination(), since - * those create the call insn lists. - */ - ret = arch_rewrite_retpolines(file); - if (ret) - return ret; - return 0; } static bool is_fentry_call(struct instruction *insn) { - if (insn->type == INSN_CALL && insn->call_dest && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) + if (insn->type == INSN_CALL && + insn->call_dest && + insn->call_dest->fentry) return true; return false; @@ -2452,13 +2703,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn if (!insn->alt_group) return 0; + if (!insn->cfi) { + WARN("CFI missing"); + return -1; + } + alt_cfi = insn->alt_group->cfi; group_off = insn->offset - insn->alt_group->first_insn->offset; if (!alt_cfi[group_off]) { - alt_cfi[group_off] = &insn->cfi; + alt_cfi[group_off] = insn->cfi; } else { - if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + if (cficmp(alt_cfi[group_off], insn->cfi)) { WARN_FUNC("stack layout conflict in alternatives", insn->sec, insn->offset); return -1; @@ -2509,9 +2765,14 @@ static int handle_insn_ops(struct instruction *insn, static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) { - struct cfi_state *cfi1 = &insn->cfi; + struct cfi_state *cfi1 = insn->cfi; int i; + if (!cfi1) { + WARN("CFI missing"); + return false; + } + if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", @@ -2562,20 +2823,64 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { + static char pvname[16]; + struct reloc *rel; + int idx; + if (insn->call_dest) return insn->call_dest->name; + rel = insn_reloc(NULL, insn); + if (rel && !strcmp(rel->sym->name, "pv_ops")) { + idx = (rel->addend / sizeof(void *)); + snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); + return pvname; + } + return "{dynamic}"; } -static inline bool noinstr_call_dest(struct symbol *func) +static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) +{ + struct symbol *target; + struct reloc *rel; + int idx; + + rel = insn_reloc(file, insn); + if (!rel || strcmp(rel->sym->name, "pv_ops")) + return false; + + idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + + if (file->pv_ops[idx].clean) + return true; + + file->pv_ops[idx].clean = true; + + list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) { + if (!target->sec->noinstr) { + WARN("pv_ops[%d]: %s", idx, target->name); + file->pv_ops[idx].clean = false; + } + } + + return file->pv_ops[idx].clean; +} + +static inline bool noinstr_call_dest(struct objtool_file *file, + struct instruction *insn, + struct symbol *func) { /* * We can't deal with indirect function calls at present; * assume they're instrumented. */ - if (!func) + if (!func) { + if (file->pv_ops) + return pv_call_dest(file, insn); + return false; + } /* * If the symbol is from a noinstr section; we good. @@ -2594,10 +2899,12 @@ static inline bool noinstr_call_dest(struct symbol *func) return false; } -static int validate_call(struct instruction *insn, struct insn_state *state) +static int validate_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - !noinstr_call_dest(insn->call_dest)) { + !noinstr_call_dest(file, insn, insn->call_dest)) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -2618,7 +2925,9 @@ static int validate_call(struct instruction *insn, struct insn_state *state) return 0; } -static int validate_sibling_call(struct instruction *insn, struct insn_state *state) +static int validate_sibling_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (has_modified_stack_frame(insn, state)) { WARN_FUNC("sibling call from callable instruction with modified stack frame", @@ -2626,7 +2935,7 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st return 1; } - return validate_call(insn, state); + return validate_call(file, insn, state); } static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) @@ -2696,7 +3005,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state) { struct alternative *alt; - struct instruction *next_insn; + struct instruction *next_insn, *prev_insn = NULL; struct section *sec; u8 visited; int ret; @@ -2725,15 +3034,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (insn->visited & visited) return 0; + } else { + nr_insns_visited++; } if (state.noinstr) state.instr += insn->instr; - if (insn->hint) - state.cfi = insn->cfi; - else - insn->cfi = state.cfi; + if (insn->hint) { + state.cfi = *insn->cfi; + } else { + /* XXX track if we actually changed state.cfi */ + + if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) { + insn->cfi = prev_insn->cfi; + nr_cfi_reused++; + } else { + insn->cfi = cfi_hash_find_or_add(&state.cfi); + } + } insn->visited |= visited; @@ -2769,7 +3088,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CALL: case INSN_CALL_DYNAMIC: - ret = validate_call(insn, &state); + ret = validate_call(file, insn, &state); if (ret) return ret; @@ -2788,7 +3107,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; @@ -2810,7 +3129,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; } @@ -2883,6 +3202,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + prev_insn = insn; insn = next_insn; } @@ -3138,10 +3458,20 @@ int check(struct objtool_file *file) int ret, warnings = 0; arch_initial_func_cfi_state(&initial_func_cfi); + init_cfi_state(&init_cfi); + init_cfi_state(&func_cfi); + set_func_state(&func_cfi); + + if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) + goto out; + + cfi_hash_add(&init_cfi); + cfi_hash_add(&func_cfi); ret = decode_sections(file); if (ret < 0) goto out; + warnings += ret; if (list_empty(&file->insn_list)) @@ -3185,6 +3515,13 @@ int check(struct objtool_file *file) goto out; warnings += ret; + if (retpoline) { + ret = create_retpoline_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) @@ -3192,6 +3529,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (stats) { + printf("nr_insns_visited: %ld\n", nr_insns_visited); + printf("nr_cfi: %ld\n", nr_cfi); + printf("nr_cfi_reused: %ld\n", nr_cfi_reused); + printf("nr_cfi_cache: %ld\n", nr_cfi_cache); + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 8676c7598728..81a4c543ff7e 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; @@ -734,97 +734,13 @@ 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; } -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) -{ - struct section *symtab, *symtab_shndx; - struct symbol *sym; - Elf_Data *data; - Elf_Scn *s; - - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return NULL; - } - memset(sym, 0, sizeof(*sym)); - - sym->name = strdup(name); - - sym->sym.st_name = elf_add_string(elf, NULL, sym->name); - if (sym->sym.st_name == -1) - return NULL; - - sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); - // st_other 0 - // st_shndx 0 - // st_value 0 - // st_size 0 - - symtab = find_section_by_name(elf, ".symtab"); - if (!symtab) { - WARN("can't find .symtab"); - return NULL; - } - - s = elf_getscn(elf->elf, symtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym; - data->d_size = sizeof(sym->sym); - data->d_align = 1; - data->d_type = ELF_T_SYM; - - sym->idx = symtab->len / sizeof(sym->sym); - - symtab->len += data->d_size; - symtab->changed = true; - - symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); - if (symtab_shndx) { - s = elf_getscn(elf->elf, symtab_shndx->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym.st_size; /* conveniently 0 */ - data->d_size = sizeof(Elf32_Word); - data->d_align = 4; - data->d_type = ELF_T_WORD; - - symtab_shndx->len += 4; - symtab_shndx->changed = true; - } - - sym->sec = find_section_by_index(elf, 0); - - elf_add_symbol(elf, sym); - - return sym; -} - struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { @@ -855,7 +771,6 @@ 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 +894,63 @@ 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 +959,9 @@ 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 +1021,6 @@ 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 +1031,12 @@ 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/arch.h b/tools/objtool/include/objtool/arch.h index 062bb6e9b865..589ff58426ab 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -69,7 +69,7 @@ struct instruction; void arch_initial_func_cfi_state(struct cfi_init_state *state); -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, @@ -82,8 +82,9 @@ unsigned long arch_jump_destination(struct instruction *insn); unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); +const char *arch_ret_insn(int len); -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg); +int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index fd5cb0bed9bf..f11d1ac1dadf 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -7,6 +7,7 @@ #define _OBJTOOL_CFI_H #include <arch/cfi_regs.h> +#include <linux/list.h> #define CFI_UNDEFINED -1 #define CFI_CFA -2 @@ -24,6 +25,7 @@ struct cfi_init_state { }; struct cfi_state { + struct hlist_node hash; /* must be first, cficmp() */ struct cfi_reg regs[CFI_NUM_REGS]; struct cfi_reg vals[CFI_NUM_REGS]; struct cfi_reg cfa; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 56d50bc50c10..6cfff078897f 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -40,7 +40,6 @@ struct instruction { struct list_head list; struct hlist_node hash; struct list_head call_node; - struct list_head mcount_loc_node; struct section *sec; unsigned long offset; unsigned int len; @@ -60,7 +59,7 @@ struct instruction { struct list_head alts; struct symbol *func; struct list_head stack_ops; - struct cfi_state cfi; + struct cfi_state *cfi; }; static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e34395047530..cdc739fa9a6f 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; }; @@ -55,8 +54,12 @@ struct symbol { unsigned long offset; unsigned int len; struct symbol *pfunc, *cfunc, *alias; - bool uaccess_safe; - bool static_call_tramp; + u8 uaccess_safe : 1; + u8 static_call_tramp : 1; + u8 retpoline_thunk : 1; + u8 fentry : 1; + u8 kcov : 1; + struct list_head pv_target; }; struct reloc { @@ -141,7 +144,6 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 24fa83634de4..f99fbc6078d5 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -14,6 +14,11 @@ #define __weak __attribute__((weak)) +struct pv_state { + bool clean; + struct list_head targets; +}; + struct objtool_file { struct elf *elf; struct list_head insn_list; @@ -25,10 +30,14 @@ struct objtool_file { unsigned long jl_short, jl_long; unsigned long jl_nop_short, jl_nop_long; + + struct pv_state *pv_ops; }; struct objtool_file *objtool_open_read(const char *_objname); +void objtool_pv_add(struct objtool_file *file, int idx, struct symbol *func); + int check(struct objtool_file *file); int orc_dump(const char *objname); int orc_create(struct objtool_file *file); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index e21db8bce493..c90c7084e45a 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -135,6 +135,28 @@ struct objtool_file *objtool_open_read(const char *_objname) return &file; } +void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) +{ + if (!noinstr) + return; + + if (!f->pv_ops) { + WARN("paravirt confusion"); + return; + } + + /* + * These functions will be patched into native code, + * see paravirt_patch(). + */ + if (!strcmp(func->name, "_paravirt_nop") || + !strcmp(func->name, "_paravirt_ident_64")) + return; + + list_add(&func->pv_target, &f->pv_ops[idx].targets); + f->pv_ops[idx].clean = false; +} + static void cmd_usage(void) { unsigned int i, longest = 0; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index dc9b7dd314b0..dd3c64af9db2 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -13,13 +13,19 @@ #include <objtool/warn.h> #include <objtool/endianness.h> -static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, + struct instruction *insn) { - struct instruction *insn = container_of(cfi, struct instruction, cfi); struct cfi_reg *bp = &cfi->regs[CFI_BP]; memset(orc, 0, sizeof(*orc)); + if (!cfi) { + orc->end = 0; + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + } + orc->end = cfi->end; if (cfi->cfa.base == CFI_UNDEFINED) { @@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file) int i; if (!alt_group) { - if (init_orc_entry(&orc, &insn->cfi)) + if (init_orc_entry(&orc, insn->cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file) struct cfi_state *cfi = alt_group->cfi[i]; if (!cfi) continue; - if (init_orc_entry(&orc, cfi)) + /* errors are reported on the original insn */ + if (init_orc_entry(&orc, cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -204,7 +211,7 @@ 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..e2223dd91c37 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); @@ -108,16 +109,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; } - /* - * Skip retpoline .altinstr_replacement... we already rewrite the - * instructions for retpolines anyway, see arch_is_retpoline() - * usage in add_{call,jump}_destinations(). - */ - 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 +151,13 @@ 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..b856afa6eb52 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h $(Q)$(MKDIR) -p $(OUTPUT)dlfilters $(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $< +.SECONDARY: $(DLFILTERS:.so=.o) + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< @@ -802,7 +804,7 @@ 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/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; 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..c32c2eb16d7d 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; @@ -469,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) return -EINVAL; if (PRINT_FIELD(SYM) && @@ -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 @@ -4037,11 +4039,15 @@ script_found: goto out_delete; uname(&uts); - if (data.is_pipe || /* assume pipe_mode indicates native_arch */ - !strcmp(uts.machine, session->header.env.arch) || - (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386"))) + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; + } else if (session->header.env.arch) { + if (!strcmp(uts.machine, session->header.env.arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386")) + native_arch = true; + } script.session = session; script__setup_sample_type(&script); 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/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..3167b4628b6d 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -301,6 +301,16 @@ static const char * const mem_lvlnum[] = { [PERF_MEM_LVLNUM_NA] = "N/A", }; +static const char * const mem_hops[] = { + "N/A", + /* + * While printing, 'Remote' will be added to represent + * 'Remote core, same node' accesses as remote field need + * to be set with mem_hops field. + */ + "core, same node", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; @@ -320,12 +330,14 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; } + if (mem_info && mem_info->data_src.mem_hops) + l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); + printed = 0; for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { if (!(m & 0x1)) @@ -472,8 +484,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) /* * Skylake might report unknown remote level via this * bit, consider it when evaluating remote HITMs. + * + * Incase of power, remote field can also be used to denote cache + * accesses from the another core of same node. Hence, setting + * mrem only when HOPS is zero along with set remote field. */ - bool mrem = data_src->mem_remote; + bool mrem = (data_src->mem_remote && !data_src->mem_hops); int err = 0; #define HITM_INC(__f) \ 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 866531c08e4f..799b88152e9e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -375,7 +375,8 @@ $(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/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 033051717ba5..f3daa44a8266 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -12,27 +12,36 @@ #include <unistd.h> #include <ftw.h> - #include "cgroup_helpers.h" /* * To avoid relying on the system setup, when setup_cgroup_env is called - * we create a new mount namespace, and cgroup namespace. The cgroup2 - * root is mounted at CGROUP_MOUNT_PATH - * - * Unfortunately, most people don't have cgroupv2 enabled at this point in time. - * It's easier to create our own mount namespace and manage it ourselves. + * we create a new mount namespace, and cgroup namespace. The cgroupv2 + * root is mounted at CGROUP_MOUNT_PATH. Unfortunately, most people don't + * have cgroupv2 enabled at this point in time. It's easier to create our + * own mount namespace and manage it ourselves. We assume /mnt exists. * - * We assume /mnt exists. + * Related cgroupv1 helpers are named *classid*(), since we only use the + * net_cls controller for tagging net_cls.classid. We assume the default + * mount under /sys/fs/cgroup/net_cls, which should be the case for the + * vast majority of users. */ #define WALK_FD_LIMIT 16 + #define CGROUP_MOUNT_PATH "/mnt" +#define CGROUP_MOUNT_DFLT "/sys/fs/cgroup" +#define NETCLS_MOUNT_PATH CGROUP_MOUNT_DFLT "/net_cls" #define CGROUP_WORK_DIR "/cgroup-test-work-dir" + #define format_cgroup_path(buf, path) \ snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \ CGROUP_WORK_DIR, path) +#define format_classid_path(buf) \ + snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ + CGROUP_WORK_DIR) + /** * enable_all_controllers() - Enable all available cgroup v2 controllers * @@ -139,8 +148,7 @@ static int nftwfunc(const char *filename, const struct stat *statptr, return 0; } - -static int join_cgroup_from_top(char *cgroup_path) +static int join_cgroup_from_top(const char *cgroup_path) { char cgroup_procs_path[PATH_MAX + 1]; pid_t pid = getpid(); @@ -313,3 +321,114 @@ int cgroup_setup_and_join(const char *path) { } return cg_fd; } + +/** + * setup_classid_environment() - Setup the cgroupv1 net_cls environment + * + * After calling this function, cleanup_classid_environment should be called + * once testing is complete. + * + * This function will print an error to stderr and return 1 if it is unable + * to setup the cgroup environment. If setup is successful, 0 is returned. + */ +int setup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + + if (mount("tmpfs", CGROUP_MOUNT_DFLT, "tmpfs", 0, NULL) && + errno != EBUSY) { + log_err("mount cgroup base"); + return 1; + } + + if (mkdir(NETCLS_MOUNT_PATH, 0777) && errno != EEXIST) { + log_err("mkdir cgroup net_cls"); + return 1; + } + + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && + errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + cleanup_classid_environment(); + + if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) { + log_err("mkdir cgroup work dir"); + return 1; + } + + return 0; +} + +/** + * set_classid() - Set a cgroupv1 net_cls classid + * @id: the numeric classid + * + * Writes the passed classid into the cgroup work dir's net_cls.classid + * file in order to later on trigger socket tagging. + * + * On success, it returns 0, otherwise on failure it returns 1. If there + * is a failure, it prints the error to stderr. + */ +int set_classid(unsigned int id) +{ + char cgroup_workdir[PATH_MAX - 42]; + char cgroup_classid_path[PATH_MAX + 1]; + int fd, rc = 0; + + format_classid_path(cgroup_workdir); + snprintf(cgroup_classid_path, sizeof(cgroup_classid_path), + "%s/net_cls.classid", cgroup_workdir); + + fd = open(cgroup_classid_path, O_WRONLY); + if (fd < 0) { + log_err("Opening cgroup classid: %s", cgroup_classid_path); + return 1; + } + + if (dprintf(fd, "%u\n", id) < 0) { + log_err("Setting cgroup classid"); + rc = 1; + } + + close(fd); + return rc; +} + +/** + * join_classid() - Join a cgroupv1 net_cls classid + * + * This function expects the cgroup work dir to be already created, as we + * join it here. This causes the process sockets to be tagged with the given + * net_cls classid. + * + * On success, it returns 0, otherwise on failure it returns 1. + */ +int join_classid(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return join_cgroup_from_top(cgroup_workdir); +} + +/** + * cleanup_classid_environment() - Cleanup the cgroupv1 net_cls environment + * + * At call time, it moves the calling process to the root cgroup, and then + * runs the deletion process. + * + * On failure, it will print an error to stderr, and try to continue. + */ +void cleanup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + join_cgroup_from_top(NETCLS_MOUNT_PATH); + nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT); +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 5fe3d88e4f0d..629da3854b3e 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_HELPERS_H #define __CGROUP_HELPERS_H + #include <errno.h> #include <string.h> @@ -8,12 +9,21 @@ #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) - +/* cgroupv2 related */ int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); +unsigned long long get_cgroup_id(const char *path); + int join_cgroup(const char *path); + int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); -unsigned long long get_cgroup_id(const char *path); -#endif +/* cgroupv1 related */ +int set_classid(unsigned int id); +int join_classid(void); + +int setup_classid_environment(void); +void cleanup_classid_environment(void); + +#endif /* __CGROUP_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 7e9f6375757a..6db1af8fdee7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -208,11 +208,26 @@ error_close: static int connect_fd_to_addr(int fd, const struct sockaddr_storage *addr, - socklen_t addrlen) + socklen_t addrlen, const bool must_fail) { - if (connect(fd, (const struct sockaddr *)addr, addrlen)) { - log_err("Failed to connect to server"); - return -1; + int ret; + + errno = 0; + ret = connect(fd, (const struct sockaddr *)addr, addrlen); + if (must_fail) { + if (!ret) { + log_err("Unexpected success to connect to server"); + return -1; + } + if (errno != EPERM) { + log_err("Unexpected error from connect to server"); + return -1; + } + } else { + if (ret) { + log_err("Failed to connect to server"); + return -1; + } } return 0; @@ -257,7 +272,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) strlen(opts->cc) + 1)) goto error_close; - if (connect_fd_to_addr(fd, &addr, addrlen)) + if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) goto error_close; return fd; @@ -289,7 +304,7 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) return -1; } - if (connect_fd_to_addr(client_fd, &addr, len)) + if (connect_fd_to_addr(client_fd, &addr, len, false)) return -1; return 0; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index da7e132657d5..d198181a5648 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -20,6 +20,7 @@ typedef __u16 __sum16; struct network_helper_opts { const char *cc; int timeout_ms; + bool must_fail; }; /* ipv4 test vector */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c new file mode 100644 index 000000000000..ab3b9bc5e6d1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "connect4_dropper.skel.h" + +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int run_test(int cgroup_fd, int server_fd, bool classid) +{ + struct network_helper_opts opts = { + .must_fail = true, + }; + struct connect4_dropper *skel; + int fd, err = 0; + + skel = connect4_dropper__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return -1; + + skel->links.connect_v4_dropper = + bpf_program__attach_cgroup(skel->progs.connect_v4_dropper, + cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.connect_v4_dropper, "prog_attach")) { + err = -1; + goto out; + } + + if (classid && !ASSERT_OK(join_classid(), "join_classid")) { + err = -1; + goto out; + } + + fd = connect_to_fd_opts(server_fd, &opts); + if (fd < 0) + err = -1; + else + close(fd); +out: + connect4_dropper__destroy(skel); + return err; +} + +void test_cgroup_v1v2(void) +{ + struct network_helper_opts opts = {}; + int server_fd, client_fd, cgroup_fd; + static const int port = 60123; + + /* Step 1: Check base connectivity works without any BPF. */ + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) + return; + client_fd = connect_to_fd_opts(server_fd, &opts); + if (!ASSERT_GE(client_fd, 0, "client_fd")) { + close(server_fd); + return; + } + close(client_fd); + close(server_fd); + + /* Step 2: Check BPF policy prog attached to cgroups drops connectivity. */ + cgroup_fd = test__join_cgroup("/connect_dropper"); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + return; + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) { + close(cgroup_fd); + return; + } + ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only"); + setup_classid_environment(); + set_classid(42); + ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2"); + cleanup_classid_environment(); + close(server_fd); + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5c5979046523..d88bb65b74cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int err, n; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, goto close_peer1; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_peer1: xclose(p1); @@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); @@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; u32 key; char b; @@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 53f0e0fa1a53..37c20b5ffa70 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE #include <test_progs.h> -#include <linux/ptrace.h> #include "test_task_pt_regs.skel.h" void test_task_pt_regs(void) diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c new file mode 100644 index 000000000000..b565d997810a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define VERDICT_REJECT 0 +#define VERDICT_PROCEED 1 + +SEC("cgroup/connect4") +int connect_v4_dropper(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_STREAM) + return VERDICT_PROCEED; + if (ctx->user_port == bpf_htons(60123)) + return VERDICT_REJECT; + return VERDICT_PROCEED; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c index 6c059f1cfa1b..e6cb09259408 100644 --- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c +++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c @@ -1,12 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/ptrace.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct pt_regs current_regs = {}; -struct pt_regs ctx_regs = {}; +#define PT_REGS_SIZE sizeof(struct pt_regs) + +/* + * The kernel struct pt_regs isn't exported in its entirety to userspace. + * Pass it as an array to task_pt_regs.c + */ +char current_regs[PT_REGS_SIZE] = {}; +char ctx_regs[PT_REGS_SIZE] = {}; int uprobe_res = 0; SEC("uprobe/trigger_func") @@ -17,8 +22,10 @@ int handle_uprobe(struct pt_regs *ctx) current = bpf_get_current_task_btf(); regs = (struct pt_regs *) bpf_task_pt_regs(current); - __builtin_memcpy(¤t_regs, regs, sizeof(*regs)); - __builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx)); + if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs)) + return 0; + if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx)) + return 0; /* Prove that uprobe was run */ uprobe_res = 1; 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/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/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..f7d84549cc3e 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 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/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 0e78b49d0f2f..fbcbdb6963b3 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -8,3 +8,4 @@ futex_wait_uninitialized_heap futex_wait_wouldblock futex_wait futex_requeue +futex_waitv diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index bd1fec59e010..5cc38de9d8ea 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_FILES := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file \ futex_wait \ - futex_requeue + futex_requeue \ + futex_waitv TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 1f8f6daaf1e7..3651ce17beeb 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -17,6 +17,7 @@ #include <pthread.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-timeout" @@ -96,6 +97,12 @@ int main(int argc, char *argv[]) struct timespec to; pthread_t thread; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -118,7 +125,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(9); ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); @@ -175,6 +182,18 @@ int main(int argc, char *argv[]) res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME); test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS); + /* futex_waitv with CLOCK_MONOTONIC */ + if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT); + + /* futex_waitv with CLOCK_REALTIME */ + if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME); + test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT); + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 0ae390ff8164..7d7a6a06cdb7 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -22,6 +22,7 @@ #include <string.h> #include <time.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-wouldblock" @@ -42,6 +43,12 @@ int main(int argc, char *argv[]) futex_t f1 = FUTEX_INITIALIZER; int res, ret = RET_PASS; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1+1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -61,18 +68,44 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG); if (!res || errno != EWOULDBLOCK) { - fail("futex_wait returned: %d %s\n", - res ? errno : res, res ? strerror(errno) : ""); + ksft_test_result_fail("futex_wait returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wait\n"); } - print_result(TEST_NAME, ret); + if (clock_gettime(CLOCK_MONOTONIC, &to)) { + error("clock_gettime failed\n", errno); + return errno; + } + + to.tv_nsec += timeout_ns; + + if (to.tv_nsec >= 1000000000) { + to.tv_sec++; + to.tv_nsec -= 1000000000; + } + + info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + if (!res || errno != EWOULDBLOCK) { + ksft_test_result_pass("futex_waitv returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv\n"); + } + + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c new file mode 100644 index 000000000000..a94337f677e1 --- /dev/null +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * futex_waitv() test by André Almeida <andrealmeid@collabora.com> + * + * Copyright 2021 Collabora Ltd. + */ + +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <pthread.h> +#include <stdint.h> +#include <sys/shm.h> +#include "futextest.h" +#include "futex2test.h" +#include "logging.h" + +#define TEST_NAME "futex-wait" +#define WAKE_WAIT_US 10000 +#define NR_FUTEXES 30 +static struct futex_waitv waitv[NR_FUTEXES]; +u_int32_t futexes[NR_FUTEXES] = {0}; + +void usage(char *prog) +{ + printf("Usage: %s\n", prog); + printf(" -c Use color\n"); + printf(" -h Display this help message\n"); + printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", + VQUIET, VCRITICAL, VINFO); +} + +void *waiterfn(void *arg) +{ + struct timespec to; + int res; + + /* setting absolute timeout for futex2 */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res < 0) { + ksft_test_result_fail("futex_waitv returned: %d %s\n", + errno, strerror(errno)); + } else if (res != NR_FUTEXES - 1) { + ksft_test_result_fail("futex_waitv returned: %d, expecting %d\n", + res, NR_FUTEXES - 1); + } + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t waiter; + int res, ret = RET_PASS; + struct timespec to; + int c, i; + + while ((c = getopt(argc, argv, "cht:v:")) != -1) { + switch (c) { + case 'c': + log_color(1); + break; + case 'h': + usage(basename(argv[0])); + exit(0); + case 'v': + log_verbosity(atoi(optarg)); + break; + default: + usage(basename(argv[0])); + exit(1); + } + } + + ksft_print_header(); + ksft_set_plan(7); + ksft_print_msg("%s: Test FUTEX_WAITV\n", + basename(argv[0])); + + for (i = 0; i < NR_FUTEXES; i++) { + waitv[i].uaddr = (uintptr_t)&futexes[i]; + waitv[i].flags = FUTEX_32 | FUTEX_PRIVATE_FLAG; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + /* Private waitv */ + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, FUTEX_PRIVATE_FLAG); + if (res != 1) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv private\n"); + } + + /* Shared waitv */ + for (i = 0; i < NR_FUTEXES; i++) { + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); + + if (shm_id < 0) { + perror("shmget"); + exit(1); + } + + unsigned int *shared_data = shmat(shm_id, NULL, 0); + + *shared_data = 0; + waitv[i].uaddr = (uintptr_t)shared_data; + waitv[i].flags = FUTEX_32; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv shared\n"); + } + + for (i = 0; i < NR_FUTEXES; i++) + shmdt(u64_to_ptr(waitv[i].uaddr)); + + /* Testing a waiter without FUTEX_32 flag */ + waitv[0].flags = FUTEX_PRIVATE_FLAG; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv without FUTEX_32\n"); + } + + /* Testing a waiter with an unaligned address */ + waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32; + waitv[0].uaddr = 1; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv with an unaligned address\n"); + } + + /* Testing a NULL address for waiters.uaddr */ + waitv[0].uaddr = 0x00000000; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n"); + } + + /* Testing a NULL address for *waiters */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in *waiters\n"); + } + + /* Testing an invalid clockid */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_TAI); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv invalid clockid\n"); + } + + ksft_print_cnts(); + return ret; +} diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh index 11a9d62290f5..5ccd599da6c3 100755 --- a/tools/testing/selftests/futex/functional/run.sh +++ b/tools/testing/selftests/futex/functional/run.sh @@ -79,3 +79,6 @@ echo echo ./futex_requeue $COLOR + +echo +./futex_waitv $COLOR diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h new file mode 100644 index 000000000000..9d305520e849 --- /dev/null +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Futex2 library addons for futex tests + * + * Copyright 2021 Collabora Ltd. + */ +#include <stdint.h> + +#define u64_to_ptr(x) ((void *)(uintptr_t)(x)) + +/** + * futex_waitv - Wait at multiple futexes, wake on any + * @waiters: Array of waiters + * @nr_waiters: Length of waiters array + * @flags: Operation flags + * @timo: Optional timeout for operation + */ +static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, + unsigned long flags, struct timespec *timo, clockid_t clockid) +{ + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); +} 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/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c index e1bf55dabdf6..162c41e9bcae 100644 --- a/tools/testing/selftests/nci/nci_dev.c +++ b/tools/testing/selftests/nci/nci_dev.c @@ -746,7 +746,7 @@ int read_write_nci_cmd(int nfc_sock, int virtual_fd, const __u8 *cmd, __u32 cmd_ const __u8 *rsp, __u32 rsp_len) { char buf[256]; - unsigned int len; + int len; send(nfc_sock, &cmd[3], cmd_len - 3, 0); len = read(virtual_fd, buf, cmd_len); 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/altnames.sh b/tools/testing/selftests/net/altnames.sh index 4254ddc3f70b..1ef9e4159bba 100755 --- a/tools/testing/selftests/net/altnames.sh +++ b/tools/testing/selftests/net/altnames.sh @@ -45,7 +45,7 @@ altnames_test() check_err $? "Got unexpected long alternative name from link show JSON" ip link property del $DUMMY_DEV altname $SHORT_NAME - check_err $? "Failed to add short alternative name" + check_err $? "Failed to delete short alternative name" ip -j -p link show $SHORT_NAME &>/dev/null check_fail $? "Unexpected success while trying to do link show with deleted short alternative name" 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..3313566ce906 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 @@ -439,10 +445,13 @@ cleanup() ip -netns ${NSA} link set dev ${NSA_DEV} down ip -netns ${NSA} link del dev ${NSA_DEV} + ip netns pids ${NSA} | xargs kill 2>/dev/null ip netns del ${NSA} fi + ip netns pids ${NSB} | xargs kill 2>/dev/null ip netns del ${NSB} + ip netns pids ${NSC} | xargs kill 2>/dev/null ip netns del ${NSC} >/dev/null 2>&1 } @@ -1003,6 +1012,60 @@ 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/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..e5e2fbeca22e 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,5 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# 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 $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e7fc5c35b569..92087d423bcf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -751,6 +751,14 @@ qdisc_parent_stats_get() | jq '.[] | select(.parent == "'"$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/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 3caf72bb9c6a..a2489ec398fe 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -468,10 +468,26 @@ out_bits() 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 + 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" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 ${bit2type[$i]} 123 + fi done bit2size[22]=$tmp @@ -544,7 +560,7 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) - for i in {0..22} + 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 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/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/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/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 7db9cf822dc7..8109b17dc764 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -62,6 +62,17 @@ enum pid_type {PIDTYPE_PID = 0, PIDTYPE_TGID, PIDTYPE_PGID}; const int THREAD_CLONE_FLAGS = CLONE_THREAD | CLONE_SIGHAND | CLONE_FS | CLONE_VM | CLONE_FILES; +struct child_args { + int num_threads; + int pfd[2]; + int cpid; + int thr_tids[MAX_THREADS]; +}; + +static struct child_args procs[MAX_PROCESSES]; +static int num_processes = 2; +static int need_cleanup = 0; + static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { @@ -78,8 +89,14 @@ static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned l #define handle_error(msg) __handle_error(__FILE__, __LINE__, msg) static void __handle_error(char *fn, int ln, char *msg) { + int pidx; printf("(%s:%d) - ", fn, ln); perror(msg); + if (need_cleanup) { + for (pidx = 0; pidx < num_processes; ++pidx) + kill(procs[pidx].cpid, 15); + need_cleanup = 0; + } exit(EXIT_FAILURE); } @@ -106,13 +123,6 @@ static unsigned long get_cs_cookie(int pid) return cookie; } -struct child_args { - int num_threads; - int pfd[2]; - int cpid; - int thr_tids[MAX_THREADS]; -}; - static int child_func_thread(void __attribute__((unused))*arg) { while (1) @@ -212,10 +222,7 @@ void _validate(int line, int val, char *msg) int main(int argc, char *argv[]) { - struct child_args procs[MAX_PROCESSES]; - int keypress = 0; - int num_processes = 2; int num_threads = 3; int delay = 0; int res = 0; @@ -262,6 +269,7 @@ int main(int argc, char *argv[]) printf("\n## Create a thread/process/process group hiearchy\n"); create_processes(num_processes, num_threads, procs); + need_cleanup = 1; disp_processes(num_processes, procs); validate(get_cs_cookie(0) == 0); diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 1af16d2c2a0a..52497b7b9f1d 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -341,7 +341,7 @@ void split_file_backed_thp(void) } /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc)); + num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); close(fd); if (num_written < 1) { 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/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index b4142cd1c5c2..8a1f62ab3c8e 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ - corrupt_xstate_header + corrupt_xstate_header amx # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c new file mode 100644 index 000000000000..3615ef4a48bb --- /dev/null +++ b/tools/testing/selftests/x86/amx.c @@ -0,0 +1,851 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <err.h> +#include <errno.h> +#include <pthread.h> +#include <setjmp.h> +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <unistd.h> +#include <x86intrin.h> + +#include <sys/auxv.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <sys/wait.h> + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +#define XSAVE_HDR_OFFSET 512 +#define XSAVE_HDR_SIZE 64 + +struct xsave_buffer { + union { + struct { + char legacy[XSAVE_HDR_OFFSET]; + char header[XSAVE_HDR_SIZE]; + char extended[0]; + }; + char bytes[0]; + }; +}; + +static inline uint64_t xgetbv(uint32_t index) +{ + uint32_t eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((uint64_t)edx << 32); +} + +static inline void cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx) +{ + asm volatile("cpuid;" + : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsave (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xrstor (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)); +} + +/* err() exits and will not return */ +#define fatal_error(msg, ...) err(1, "[FAIL]\t" msg, ##__VA_ARGS__) + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define CPUID_LEAF1_ECX_XSAVE_MASK (1 << 26) +#define CPUID_LEAF1_ECX_OSXSAVE_MASK (1 << 27) +static inline void check_cpuid_xsave(void) +{ + uint32_t eax, ebx, ecx, edx; + + /* + * CPUID.1:ECX.XSAVE[bit 26] enumerates general + * support for the XSAVE feature set, including + * XGETBV. + */ + eax = 1; + ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (!(ecx & CPUID_LEAF1_ECX_XSAVE_MASK)) + fatal_error("cpuid: no CPU xsave support"); + if (!(ecx & CPUID_LEAF1_ECX_OSXSAVE_MASK)) + fatal_error("cpuid: no OS xsave support"); +} + +static uint32_t xbuf_size; + +static struct { + uint32_t xbuf_offset; + uint32_t size; +} xtiledata; + +#define CPUID_LEAF_XSTATE 0xd +#define CPUID_SUBLEAF_XSTATE_USER 0x0 +#define TILE_CPUID 0x1d +#define TILE_PALETTE_ID 0x1 + +static void check_cpuid_xtiledata(void) +{ + uint32_t eax, ebx, ecx, edx; + + eax = CPUID_LEAF_XSTATE; + ecx = CPUID_SUBLEAF_XSTATE_USER; + cpuid(&eax, &ebx, &ecx, &edx); + + /* + * EBX enumerates the size (in bytes) required by the XSAVE + * instruction for an XSAVE area containing all the user state + * components corresponding to bits currently set in XCR0. + * + * Stash that off so it can be used to allocate buffers later. + */ + xbuf_size = ebx; + + eax = CPUID_LEAF_XSTATE; + ecx = XFEATURE_XTILEDATA; + + cpuid(&eax, &ebx, &ecx, &edx); + /* + * eax: XTILEDATA state component size + * ebx: XTILEDATA state component offset in user buffer + */ + if (!eax || !ebx) + fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d", + eax, ebx); + + xtiledata.size = eax; + xtiledata.xbuf_offset = ebx; +} + +/* The helpers for managing XSAVE buffer and tile states: */ + +struct xsave_buffer *alloc_xbuf(void) +{ + struct xsave_buffer *xbuf; + + /* XSAVE buffer should be 64B-aligned. */ + xbuf = aligned_alloc(64, xbuf_size); + if (!xbuf) + fatal_error("aligned_alloc()"); + return xbuf; +} + +static inline void clear_xstate_header(struct xsave_buffer *buffer) +{ + memset(&buffer->header, 0, sizeof(buffer->header)); +} + +static inline uint64_t get_xstatebv(struct xsave_buffer *buffer) +{ + /* XSTATE_BV is at the beginning of the header: */ + return *(uint64_t *)&buffer->header; +} + +static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv) +{ + /* XSTATE_BV is at the beginning of the header: */ + *(uint64_t *)(&buffer->header) = bv; +} + +static void set_rand_tiledata(struct xsave_buffer *xbuf) +{ + int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset]; + int data; + int i; + + /* + * Ensure that 'data' is never 0. This ensures that + * the registers are never in their initial configuration + * and thus never tracked as being in the init state. + */ + data = rand() | 1; + + for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++) + *ptr = data; +} + +struct xsave_buffer *stashed_xsave; + +static void init_stashed_xsave(void) +{ + stashed_xsave = alloc_xbuf(); + if (!stashed_xsave) + fatal_error("failed to allocate stashed_xsave\n"); + clear_xstate_header(stashed_xsave); +} + +static void free_stashed_xsave(void) +{ + free(stashed_xsave); +} + +/* See 'struct _fpx_sw_bytes' at sigcontext.h */ +#define SW_BYTES_OFFSET 464 +/* N.B. The struct's field name varies so read from the offset. */ +#define SW_BYTES_BV_OFFSET (SW_BYTES_OFFSET + 8) + +static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer) +{ + return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET); +} + +static inline uint64_t get_fpx_sw_bytes_features(void *buffer) +{ + return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET); +} + +/* Work around printf() being unsafe in signals: */ +#define SIGNAL_BUF_LEN 1000 +char signal_message_buffer[SIGNAL_BUF_LEN]; +void sig_print(char *msg) +{ + int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1; + + strncat(signal_message_buffer, msg, left); +} + +static volatile bool noperm_signaled; +static int noperm_errs; +/* + * Signal handler for when AMX is used but + * permission has not been obtained. + */ +static void handle_noperm(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + void *xbuf = ctx->uc_mcontext.fpregs; + struct _fpx_sw_bytes *sw_bytes; + uint64_t features; + + /* Reset the signal message buffer: */ + signal_message_buffer[0] = '\0'; + sig_print("\tAt SIGILL handler,\n"); + + if (si->si_code != ILL_ILLOPC) { + noperm_errs++; + sig_print("[FAIL]\tInvalid signal code.\n"); + } else { + sig_print("[OK]\tValid signal code (ILL_ILLOPC).\n"); + } + + sw_bytes = get_fpx_sw_bytes(xbuf); + /* + * Without permission, the signal XSAVE buffer should not + * have room for AMX register state (aka. xtiledata). + * Check that the size does not overlap with where xtiledata + * will reside. + * + * This also implies that no state components *PAST* + * XTILEDATA (features >=19) can be present in the buffer. + */ + if (sw_bytes->xstate_size <= xtiledata.xbuf_offset) { + sig_print("[OK]\tValid xstate size\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate size\n"); + } + + features = get_fpx_sw_bytes_features(xbuf); + /* + * Without permission, the XTILEDATA feature + * bit should not be set. + */ + if ((features & XFEATURE_MASK_XTILEDATA) == 0) { + sig_print("[OK]\tValid xstate mask\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate mask\n"); + } + + noperm_signaled = true; + ctx->uc_mcontext.gregs[REG_RIP] += 3; /* Skip the faulting XRSTOR */ +} + +/* Return true if XRSTOR is successful; otherwise, false. */ +static inline bool xrstor_safe(struct xsave_buffer *xbuf, uint64_t mask) +{ + noperm_signaled = false; + xrstor(xbuf, mask); + + /* Print any messages produced by the signal code: */ + printf("%s", signal_message_buffer); + /* + * Reset the buffer to make sure any future printing + * only outputs new messages: + */ + signal_message_buffer[0] = '\0'; + + if (noperm_errs) + fatal_error("saw %d errors in noperm signal handler\n", noperm_errs); + + return !noperm_signaled; +} + +/* + * Use XRSTOR to populate the XTILEDATA registers with + * random data. + * + * Return true if successful; otherwise, false. + */ +static inline bool load_rand_tiledata(struct xsave_buffer *xbuf) +{ + clear_xstate_header(xbuf); + set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA); + set_rand_tiledata(xbuf); + return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA); +} + +/* Return XTILEDATA to its initial configuration. */ +static inline void init_xtiledata(void) +{ + clear_xstate_header(stashed_xsave); + xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA); +} + +enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED }; + +/* arch_prctl() and sigaltstack() test */ + +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 + +static void req_xtiledata_perm(void) +{ + syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); +} + +static void validate_req_xcomp_perm(enum expected_result exp) +{ + unsigned long bitmask; + long rc; + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tARCH_REQ_XCOMP_PERM saw expected failure..\n"); + return; + } + + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected success.\n"); + } else if (rc) { + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n"); + } + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask); + if (rc) { + fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc); + } else if (bitmask & XFEATURE_MASK_XTILE) { + printf("\tARCH_REQ_XCOMP_PERM is successful.\n"); + } +} + +static void validate_xcomp_perm(enum expected_result exp) +{ + bool load_success = load_rand_tiledata(stashed_xsave); + + if (exp == FAIL_EXPECTED) { + if (load_success) { + noperm_errs++; + printf("[FAIL]\tLoad tiledata succeeded.\n"); + } else { + printf("[OK]\tLoad tiledata failed.\n"); + } + } else if (exp == SUCCESS_EXPECTED) { + if (load_success) { + printf("[OK]\tLoad tiledata succeeded.\n"); + } else { + noperm_errs++; + printf("[FAIL]\tLoad tiledata failed.\n"); + } + } +} + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static void *alloc_altstack(unsigned int size) +{ + void *altstack; + + altstack = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + + if (altstack == MAP_FAILED) + fatal_error("mmap() for altstack"); + + return altstack; +} + +static void setup_altstack(void *addr, unsigned long size, enum expected_result exp) +{ + stack_t ss; + int rc; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = addr; + + rc = sigaltstack(&ss, NULL); + + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tsigaltstack() failed.\n"); + } else { + fatal_error("sigaltstack() succeeded unexpectedly.\n"); + } + } else if (rc) { + fatal_error("sigaltstack()"); + } +} + +static void test_dynamic_sigaltstack(void) +{ + unsigned int small_size, enough_size; + unsigned long minsigstksz; + void *altstack; + + minsigstksz = getauxval(AT_MINSIGSTKSZ); + printf("\tAT_MINSIGSTKSZ = %lu\n", minsigstksz); + /* + * getauxval() itself can return 0 for failure or + * success. But, in this case, AT_MINSIGSTKSZ + * will always return a >=0 value if implemented. + * Just check for 0. + */ + if (minsigstksz == 0) { + printf("no support for AT_MINSIGSTKSZ, skipping sigaltstack tests\n"); + return; + } + + enough_size = minsigstksz * 2; + + altstack = alloc_altstack(enough_size); + printf("\tAllocate memory for altstack (%u bytes).\n", enough_size); + + /* + * Try setup_altstack() with a size which can not fit + * XTILEDATA. ARCH_REQ_XCOMP_PERM should fail. + */ + small_size = minsigstksz - xtiledata.size; + printf("\tAfter sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(FAIL_EXPECTED); + + /* + * Try setup_altstack() with a size derived from + * AT_MINSIGSTKSZ. It should be more than large enough + * and thus ARCH_REQ_XCOMP_PERM should succeed. + */ + printf("\tAfter sigaltstack() with enough size (%u bytes).\n", enough_size); + setup_altstack(altstack, enough_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(SUCCESS_EXPECTED); + + /* + * Try to coerce setup_altstack() to again accept a + * too-small altstack. This ensures that big-enough + * sigaltstacks can not shrink to a too-small value + * once XTILEDATA permission is established. + */ + printf("\tThen, sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, FAIL_EXPECTED); +} + +static void test_dynamic_state(void) +{ + pid_t parent, child, grandchild; + + parent = fork(); + if (parent < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (parent > 0) { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test parent exit"); + return; + } + /* fork() succeeded. Now in the child . */ + + printf("[RUN]\tCheck ARCH_REQ_XCOMP_PERM around process fork() and sigaltack() test.\n"); + + printf("\tFork a child.\n"); + child = fork(); + if (child < 0) { + fatal_error("fork"); + } else if (child > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test child exit"); + _exit(0); + } + + /* + * The permission request should fail without an + * XTILEDATA-compatible signal stack + */ + printf("\tTest XCOMP_PERM at child.\n"); + validate_xcomp_perm(FAIL_EXPECTED); + + /* + * Set up an XTILEDATA-compatible signal stack and + * also obtain permission to populate XTILEDATA. + */ + printf("\tTest dynamic sigaltstack at child:\n"); + test_dynamic_sigaltstack(); + + /* Ensure that XTILEDATA can be populated. */ + printf("\tTest XCOMP_PERM again at child.\n"); + validate_xcomp_perm(SUCCESS_EXPECTED); + + printf("\tFork a grandchild.\n"); + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (!grandchild) { + /* fork() succeeded. Now in the (grand)child. */ + printf("\tTest XCOMP_PERM at grandchild.\n"); + + /* + * Ensure that the grandchild inherited + * permission and a compatible sigaltstack: + */ + validate_xcomp_perm(SUCCESS_EXPECTED); + } else { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grandchild"); + } + + _exit(0); +} + +/* + * Save current register state and compare it to @xbuf1.' + * + * Returns false if @xbuf1 matches the registers. + * Returns true if @xbuf1 differs from the registers. + */ +static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1) +{ + struct xsave_buffer *xbuf2; + int ret; + + xbuf2 = alloc_xbuf(); + if (!xbuf2) + fatal_error("failed to allocate XSAVE buffer\n"); + + xsave(xbuf2, XFEATURE_MASK_XTILEDATA); + ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset], + &xbuf2->bytes[xtiledata.xbuf_offset], + xtiledata.size); + + free(xbuf2); + + if (ret == 0) + return false; + return true; +} + +static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret != 0) + fatal_error("TILEDATA registers changed"); +} + +static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret == 0) + fatal_error("TILEDATA registers did not change"); +} + +/* tiledata inheritance test */ + +static void test_fork(void) +{ + pid_t child, grandchild; + + child = fork(); + if (child < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (child > 0) { + /* fork() succeeded. Now in the parent. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test child"); + return; + } + /* fork() succeeded. Now in the child. */ + printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tiledata\n"); + + load_rand_tiledata(stashed_xsave); + + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (grandchild > 0) { + /* fork() succeeded. Still in the first child. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grand child"); + _exit(0); + } + /* fork() succeeded. Now in the (grand)child. */ + + /* + * TILEDATA registers are not preserved across fork(). + * Ensure that their value has changed: + */ + validate_tiledata_regs_changed(stashed_xsave); + + _exit(0); +} + +/* Context switching test */ + +static struct _ctxtswtest_cfg { + unsigned int iterations; + unsigned int num_threads; +} ctxtswtest_config; + +struct futex_info { + pthread_t thread; + int nr; + pthread_mutex_t mutex; + struct futex_info *next; +}; + +static void *check_tiledata(void *info) +{ + struct futex_info *finfo = (struct futex_info *)info; + struct xsave_buffer *xbuf; + int i; + + xbuf = alloc_xbuf(); + if (!xbuf) + fatal_error("unable to allocate XSAVE buffer"); + + /* + * Load random data into 'xbuf' and then restore + * it to the tile registers themselves. + */ + load_rand_tiledata(xbuf); + for (i = 0; i < ctxtswtest_config.iterations; i++) { + pthread_mutex_lock(&finfo->mutex); + + /* + * Ensure the register values have not + * diverged from those recorded in 'xbuf'. + */ + validate_tiledata_regs_same(xbuf); + + /* Load new, random values into xbuf and registers */ + load_rand_tiledata(xbuf); + + /* + * The last thread's last unlock will be for + * thread 0's mutex. However, thread 0 will + * have already exited the loop and the mutex + * will already be unlocked. + * + * Because this is not an ERRORCHECK mutex, + * that inconsistency will be silently ignored. + */ + pthread_mutex_unlock(&finfo->next->mutex); + } + + free(xbuf); + /* + * Return this thread's finfo, which is + * a unique value for this thread. + */ + return finfo; +} + +static int create_threads(int num, struct futex_info *finfo) +{ + int i; + + for (i = 0; i < num; i++) { + int next_nr; + + finfo[i].nr = i; + /* + * Thread 'i' will wait on this mutex to + * be unlocked. Lock it immediately after + * initialization: + */ + pthread_mutex_init(&finfo[i].mutex, NULL); + pthread_mutex_lock(&finfo[i].mutex); + + next_nr = (i + 1) % num; + finfo[i].next = &finfo[next_nr]; + + if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i])) + fatal_error("pthread_create()"); + } + return 0; +} + +static void affinitize_cpu0(void) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + fatal_error("sched_setaffinity to CPU 0"); +} + +static void test_context_switch(void) +{ + struct futex_info *finfo; + int i; + + /* Affinitize to one CPU to force context switches */ + affinitize_cpu0(); + + req_xtiledata_perm(); + + printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n", + ctxtswtest_config.iterations, + ctxtswtest_config.num_threads); + + + finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads); + if (!finfo) + fatal_error("malloc()"); + + create_threads(ctxtswtest_config.num_threads, finfo); + + /* + * This thread wakes up thread 0 + * Thread 0 will wake up 1 + * Thread 1 will wake up 2 + * ... + * the last thread will wake up 0 + * + * ... this will repeat for the configured + * number of iterations. + */ + pthread_mutex_unlock(&finfo[0].mutex); + + /* Wait for all the threads to finish: */ + for (i = 0; i < ctxtswtest_config.num_threads; i++) { + void *thread_retval; + int rc; + + rc = pthread_join(finfo[i].thread, &thread_retval); + + if (rc) + fatal_error("pthread_join() failed for thread %d err: %d\n", + i, rc); + + if (thread_retval != &finfo[i]) + fatal_error("unexpected thread retval for thread %d: %p\n", + i, thread_retval); + + } + + printf("[OK]\tNo incorrect case was found.\n"); + + free(finfo); +} + +int main(void) +{ + /* Check hardware availability at first */ + check_cpuid_xsave(); + check_cpuid_xtiledata(); + + init_stashed_xsave(); + sethandler(SIGILL, handle_noperm, 0); + + test_dynamic_state(); + + /* Request permission for the following tests */ + req_xtiledata_perm(); + + test_fork(); + + ctxtswtest_config.iterations = 10; + ctxtswtest_config.num_threads = 5; + test_context_switch(); + + clearhandler(SIGILL); + free_stashed_xsave(); + + return 0; +} 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) |