diff options
Diffstat (limited to 'tools')
97 files changed, 3952 insertions, 697 deletions
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 568854b14d0a..52c6262e6bfd 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 0b5b8ae56bd9..1e299ac73c86 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -51,14 +49,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -SYM_FUNC_START(memcpy_erms) +SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret SYM_FUNC_END(memcpy_erms) -SYM_FUNC_START(memcpy_orig) +SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fd5d25a474b7..0bfd26e4ca9e 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -4,8 +4,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative-asm.h> - -.weak memset +#include <asm/export.h> /* * ISO C memset - set a memory block to a byte value. This function uses fast @@ -18,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -44,6 +43,8 @@ SYM_FUNC_START(__memset) ret SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) +EXPORT_SYMBOL(memset) +EXPORT_SYMBOL(__memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,7 +57,7 @@ SYM_FUNC_END_ALIAS(memset) * * rax original destination */ -SYM_FUNC_START(memset_erms) +SYM_FUNC_START_LOCAL(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx @@ -65,7 +66,7 @@ SYM_FUNC_START(memset_erms) ret SYM_FUNC_END(memset_erms) -SYM_FUNC_START(memset_orig) +SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 /* expand byte value */ diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index eb92027817a7..7362bef1a368 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -10,6 +10,7 @@ #include <unistd.h> #include <string.h> #include <errno.h> +#include <endian.h> #include <linux/kernel.h> #include <linux/bootconfig.h> @@ -147,6 +148,12 @@ static int load_xbc_file(const char *path, char **buf) return ret; } +static int pr_errno(const char *msg, int err) +{ + pr_err("%s: %d\n", msg, err); + return err; +} + static int load_xbc_from_initrd(int fd, char **buf) { struct stat stat; @@ -162,26 +169,26 @@ static int load_xbc_from_initrd(int fd, char **buf) if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) return 0; - if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) + return pr_errno("Failed to lseek for magic", -errno); + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) - return -errno; + return pr_errno("Failed to read", -errno); + /* Check the bootconfig magic bytes */ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) + return pr_errno("Failed to lseek for size", -errno); if (read(fd, &size, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read size", -errno); + size = le32toh(size); if (read(fd, &csum, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read checksum", -errno); + csum = le32toh(csum); /* Wrong size error */ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { @@ -190,10 +197,8 @@ static int load_xbc_from_initrd(int fd, char **buf) } if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), - SEEK_SET) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + SEEK_SET) < 0) + return pr_errno("Failed to lseek", -errno); ret = load_xbc_fd(fd, buf, size); if (ret < 0) @@ -262,14 +267,16 @@ static int show_xbc(const char *path, bool list) ret = stat(path, &st); if (ret < 0) { - pr_err("Failed to stat %s: %d\n", path, -errno); - return -errno; + ret = -errno; + pr_err("Failed to stat %s: %d\n", path, ret); + return ret; } fd = open(path, O_RDONLY); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } ret = load_xbc_from_initrd(fd, &buf); @@ -307,8 +314,9 @@ static int delete_xbc(const char *path) fd = open(path, O_RDWR); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } size = load_xbc_from_initrd(fd, &buf); @@ -332,11 +340,13 @@ static int delete_xbc(const char *path) static int apply_xbc(const char *path, const char *xbc_path) { + char *buf, *data, *p; + size_t total_size; + struct stat stat; + const char *msg; u32 size, csum; - char *buf, *data; + int pos, pad; int ret, fd; - const char *msg; - int pos; ret = load_xbc_file(xbc_path, &buf); if (ret < 0) { @@ -346,13 +356,12 @@ static int apply_xbc(const char *path, const char *xbc_path) size = strlen(buf) + 1; csum = checksum((unsigned char *)buf, size); - /* Prepare xbc_path data */ - data = malloc(size + 8); + /* Backup the bootconfig data */ + data = calloc(size + BOOTCONFIG_ALIGN + + sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1); if (!data) return -ENOMEM; - strcpy(data, buf); - *(u32 *)(data + size) = size; - *(u32 *)(data + size + 4) = csum; + memcpy(data, buf, size); /* Check the data format */ ret = xbc_init(buf, &msg, &pos); @@ -383,28 +392,61 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Apply new one */ fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { - pr_err("Failed to open %s: %d\n", path, fd); + ret = -errno; + pr_err("Failed to open %s: %d\n", path, ret); free(data); - return fd; + return ret; } /* TODO: Ensure the @path is initramfs/initrd image */ - ret = write(fd, data, size + 8); - if (ret < 0) { - pr_err("Failed to apply a boot config: %d\n", ret); + if (fstat(fd, &stat) < 0) { + pr_err("Failed to get the size of %s\n", path); goto out; } - /* Write a magic word of the bootconfig */ - ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); - if (ret < 0) { - pr_err("Failed to apply a boot config magic: %d\n", ret); - goto out; - } - ret = 0; + + /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */ + total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN; + pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size; + size += pad; + + /* Add a footer */ + p = data + size; + *(u32 *)p = htole32(size); + p += sizeof(u32); + + *(u32 *)p = htole32(csum); + p += sizeof(u32); + + memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + p += BOOTCONFIG_MAGIC_LEN; + + total_size = p - data; + + ret = write(fd, data, total_size); + if (ret < total_size) { + if (ret < 0) + ret = -errno; + pr_err("Failed to apply a boot config: %d\n", ret); + if (ret >= 0) + goto out_rollback; + } else + ret = 0; + out: close(fd); free(data); return ret; + +out_rollback: + /* Map the partial write to -ENOSPC */ + if (ret >= 0) + ret = -ENOSPC; + if (ftruncate(fd, stat.st_size) < 0) { + ret = -errno; + pr_err("Failed to rollback the write error: %d\n", ret); + pr_err("The initrd %s may be corrupted. Recommend to rebuild.\n", path); + } + goto out; } static int usage(void) diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index d295e406a756..baed891d0ba4 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,6 +9,7 @@ else TESTDIR=. fi BOOTCONF=${TESTDIR}/bootconfig +ALIGN=4 INITRD=`mktemp ${TESTDIR}/initrd-XXXX` TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf` @@ -59,7 +60,10 @@ echo "Show command test" xpass $BOOTCONF $INITRD echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) +total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 ) +total_size=$(expr $total_size / $ALIGN) +total_size=$(expr $total_size \* $ALIGN) +xpass test $new_size -eq $total_size echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 8ab142ff5eac..2afb7d5b1aca 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -693,6 +693,7 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, obj_node = calloc(1, sizeof(*obj_node)); if (!obj_node) { p_err("failed to allocate memory: %s", strerror(errno)); + err = -ENOMEM; goto err_free; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index a43a6f10b564..359960a8f1de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -843,9 +843,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 910e7bac6e9e..3fae61ef6339 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -578,8 +578,8 @@ static int do_attach(int argc, char **argv) ifindex = net_parse_dev(&argc, &argv); if (ifindex < 1) { - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } if (argc) { @@ -587,8 +587,8 @@ static int do_attach(int argc, char **argv) overwrite = true; } else { p_err("expected 'overwrite', got: '%s'?", *argv); - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } } @@ -596,17 +596,17 @@ static int do_attach(int argc, char **argv) if (is_prefix("xdp", attach_type_strings[attach_type])) err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); - - if (err < 0) { + if (err) { p_err("interface %s attach failed: %s", attach_type_strings[attach_type], strerror(-err)); - return err; + goto cleanup; } if (json_output) jsonw_null(json_wtr); - - return 0; +cleanup: + close(progfd); + return err; } static int do_detach(int argc, char **argv) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index df7d8ec76036..477e55d59c34 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -89,9 +89,9 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level, int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) { - char buf[4096]; - struct pid_iter_bpf *skel; struct pid_iter_entry *e; + char buf[4096 / sizeof(*e) * sizeof(*e)]; + struct pid_iter_bpf *skel; int err, ret, fd = -1, i; libbpf_print_fn_t default_print; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d942c1e3372c..acdb2c245f0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 4e3512f700c0..ce5b65e07ab1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(u32 id, struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ @@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index d199a3694be8..b0bf56c5f120 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -742,7 +742,11 @@ class DebugfsProvider(Provider): The fields are all available KVM debugfs files """ - return self.walkdir(PATH_DEBUGFS_KVM)[2] + exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns'] + fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2] + if field not in exempt_list] + + return fields def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 5f9abed3e226..55bd78b3496f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -146,6 +146,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 313034117070..28baee7ba1ca 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -560,8 +560,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, const char *name, size_t sec_idx, const char *sec_name, size_t sec_off, void *insn_data, size_t insn_data_sz) { - int i; - if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) { pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n", sec_name, name, sec_off, insn_data_sz); @@ -600,13 +598,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, goto errout; memcpy(prog->insns, insn_data, insn_data_sz); - for (i = 0; i < prog->insns_cnt; i++) { - if (insn_is_subprog_call(&prog->insns[i])) { - obj->has_subcalls = true; - break; - } - } - return 0; errout: pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name); @@ -3280,7 +3271,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls; + /* For legacy reasons, libbpf supports an entry-point BPF programs + * without SEC() attribute, i.e., those in the .text section. But if + * there are 2 or more such programs in the .text section, they all + * must be subprograms called from entry-point BPF programs in + * designated SEC()'tions, otherwise there is no way to distinguish + * which of those programs should be loaded vs which are a subprogram. + * Similarly, if there is a function/program in .text and at least one + * other BPF program with custom SEC() attribute, then we just assume + * .text programs are subprograms (even if they are not called from + * other programs), because libbpf never explicitly supported mixing + * SEC()-designated BPF programs and .text entry-point BPF programs. + */ + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } struct bpf_program * diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 5c6522c89af1..98537ff2679e 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -278,7 +278,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) err = ringbuf_process_ring(ring); if (err < 0) return err; - res += cnt; + res += err; } return cnt < 0 ? -errno : res; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e3c98c007825..9bc537d0b92d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); - struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; + struct xsk_umem *umem; + struct xsk_ctx *ctx; int err; if (!xsk) return; + ctx = xsk->ctx; + umem = ctx->umem; if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); @@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk) xsk_put_ctx(ctx); - ctx->umem->refcount--; + umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != ctx->umem->fd) + if (xsk->fd != umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 4e40402a4f81..478078fb0f22 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample, stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); +#ifdef MEMORY_SANITIZER + /* + * Copying the stack may copy msan poison, avoid false positives in the + * unwinder by removing the poison here. + */ + __msan_unpoison(buf, stack_size); +#endif stack->data = (char *) buf; stack->size = stack_size; return 0; diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 9ad015a1e202..6eb45a2aa8db 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,6 +2,9 @@ /* Various wrappers to make the kernel .S file build in user-space: */ +// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index d550bd526162..6f093c483842 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 584e2e1a3793..cefc71506409 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1222,8 +1222,10 @@ static int __cmd_diff(void) if (compute == COMPUTE_STREAM) { d->evlist_streams = evlist__create_streams( d->session->evlist, 5); - if (!d->evlist_streams) + if (!d->evlist_streams) { + ret = -ENOMEM; goto out_delete; + } } } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 452a75fe68e5..0462dc8db2e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -779,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject) dsos__hit_all(session); /* * The AUX areas have been removed and replaced with - * synthesized hardware events, so clear the feature flag and - * remove the evsel. + * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { - struct evsel *evsel; - perf_header__clear_feat(&session->header, HEADER_AUXTRACE); if (inject->itrace_synth_opts.last_branch || inject->itrace_synth_opts.add_last_branch) perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); - evsel = perf_evlist__id2evsel_strict(session->evlist, - inject->aux_id); - if (evsel) { - pr_debug("Deleting %s\n", evsel__name(evsel)); - evlist__remove(session->evlist, evsel); - evsel__delete(evsel); - } } session->header.data_offset = output_data_offset; session->header.data_size = inject->bytes_written; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index f0a1dbacb46c..a2f1e53f37a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel, struct lock_seq_stat *seq; const char *name = evsel__strval(evsel, sample, "name"); u64 tmp = evsel__intval(evsel, sample, "lockdep_addr"); - int flag = evsel__intval(evsel, sample, "flag"); + int flag = evsel__intval(evsel, sample, "flags"); memcpy(&addr, &tmp, sizeof(void *)); @@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel, case SEQ_STATE_READ_ACQUIRED: seq->read_count--; BUG_ON(seq->read_count < 0); - if (!seq->read_count) { + if (seq->read_count) { ls->nr_release++; goto end; } diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 8d84fdbed6a6..18fde2f179cd 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -44,7 +44,7 @@ perf_script_branch_samples() { # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) perf script -F,-time -i ${perfdata} | \ - egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +" + egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" } perf_report_branch_samples() { @@ -105,7 +105,7 @@ arm_cs_iterate_devices() { # `> device_name = 'tmc_etf0' device_name=$(basename $path) - if is_device_sink $path $devce_name; then + if is_device_sink $path $device_name; then record_touch_file $device_name $2 && perf_script_branch_samples touch && diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index aa898014ad12..7b2d471a6419 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die) bool die_is_func_def(Dwarf_Die *dw_die) { Dwarf_Attribute attr; + Dwarf_Addr addr = 0; + + if (dwarf_tag(dw_die) != DW_TAG_subprogram) + return false; + + if (dwarf_attr(dw_die, DW_AT_declaration, &attr)) + return false; - return (dwarf_tag(dw_die) == DW_TAG_subprogram && - dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); + /* + * DW_AT_declaration can be lost from function declaration + * by gcc's bug #97060. + * So we need to check this subprogram DIE has DW_AT_inline + * or an entry address. + */ + if (!dwarf_attr(dw_die, DW_AT_inline, &attr) && + die_entrypc(dw_die, &addr) < 0) + return false; + + return true; } /** @@ -373,6 +389,7 @@ bool die_is_func_def(Dwarf_Die *dw_die) int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) { Dwarf_Addr base, end; + Dwarf_Attribute attr; if (!addr) return -EINVAL; @@ -380,6 +397,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) if (dwarf_entrypc(dw_die, addr) == 0) return 0; + /* + * Since the dwarf_ranges() will return 0 if there is no + * DW_AT_ranges attribute, we should check it first. + */ + if (!dwarf_attr(dw_die, DW_AT_ranges, &attr)) + return -ENOENT; + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; } diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index b8a5159361b4..5acf053fca7d 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -25,6 +25,7 @@ /* SYM_L_* -- linkage of symbols */ #define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name #define SYM_L_LOCAL(name) /* nothing */ #define ALIGN __ALIGN @@ -84,6 +85,12 @@ SYM_END(name, SYM_T_FUNC) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) +#endif + /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2c4061035f77..76dd349aa48d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1885,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (die_is_func_def(sp_die) && - die_match_name(sp_die, lr->function)) { + if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 4b57c0c07632..a963b5b8eb72 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -324,13 +324,10 @@ static int first_shadow_cpu(struct perf_stat_config *config, struct evlist *evlist = evsel->evlist; int i; - if (!config->aggr_get_id) - return 0; - if (config->aggr_mode == AGGR_NONE) return id; - if (config->aggr_mode == AGGR_GLOBAL) + if (!config->aggr_get_id) return 0; for (i = 0; i < evsel__nr_cpus(evsel); i++) { diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 8a23391558cf..d9c624377da7 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, char cgrp_root[PATH_MAX]; size_t mount_len; /* length of mount point in the path */ + if (!tool || !tool->cgroup_events) + return 0; + if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) { pr_debug("cannot find cgroup mount point\n"); return -1; diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2b6551269e43..f3e3c94ab9bd 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -12,11 +12,12 @@ turbostat : turbostat.c override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FILE_OFFSET_BITS=64 override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a6db83a88e85..f6b7e85b121c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date. .SH REFERENCES Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals/ +https://www.intel.com/products/processor/manuals/ .SH FILES .ta diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 33b370865d16..f3a1746f7f45 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -79,6 +79,7 @@ unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; +unsigned int gfx_act_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_time_units; @@ -210,13 +211,14 @@ struct pkg_data { unsigned long long pkg_both_core_gfxe_c0; long long gfx_rc6_ms; unsigned int gfx_mhz; + unsigned int gfx_act_mhz; unsigned int package_id; - unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ + unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; @@ -259,6 +261,113 @@ struct msr_counter { #define SYSFS_PERCPU (1 << 1) }; +/* + * The accumulated sum of MSR is defined as a monotonic + * increasing MSR, it will be accumulated periodically, + * despite its register's bit width. + */ +enum { + IDX_PKG_ENERGY, + IDX_DRAM_ENERGY, + IDX_PP0_ENERGY, + IDX_PP1_ENERGY, + IDX_PKG_PERF, + IDX_DRAM_PERF, + IDX_COUNT, +}; + +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr); + +struct msr_sum_array { + /* get_msr_sum() = sum + (get_msr() - last) */ + struct { + /*The accumulated MSR value is updated by the timer*/ + unsigned long long sum; + /*The MSR footprint recorded in last timer*/ + unsigned long long last; + } entries[IDX_COUNT]; +}; + +/* The percpu MSR sum array.*/ +struct msr_sum_array *per_cpu_msr_sum; + +int idx_to_offset(int idx) +{ + int offset; + + switch (idx) { + case IDX_PKG_ENERGY: + offset = MSR_PKG_ENERGY_STATUS; + break; + case IDX_DRAM_ENERGY: + offset = MSR_DRAM_ENERGY_STATUS; + break; + case IDX_PP0_ENERGY: + offset = MSR_PP0_ENERGY_STATUS; + break; + case IDX_PP1_ENERGY: + offset = MSR_PP1_ENERGY_STATUS; + break; + case IDX_PKG_PERF: + offset = MSR_PKG_PERF_STATUS; + break; + case IDX_DRAM_PERF: + offset = MSR_DRAM_PERF_STATUS; + break; + default: + offset = -1; + } + return offset; +} + +int offset_to_idx(int offset) +{ + int idx; + + switch (offset) { + case MSR_PKG_ENERGY_STATUS: + idx = IDX_PKG_ENERGY; + break; + case MSR_DRAM_ENERGY_STATUS: + idx = IDX_DRAM_ENERGY; + break; + case MSR_PP0_ENERGY_STATUS: + idx = IDX_PP0_ENERGY; + break; + case MSR_PP1_ENERGY_STATUS: + idx = IDX_PP1_ENERGY; + break; + case MSR_PKG_PERF_STATUS: + idx = IDX_PKG_PERF; + break; + case MSR_DRAM_PERF_STATUS: + idx = IDX_DRAM_PERF; + break; + default: + idx = -1; + } + return idx; +} + +int idx_valid(int idx) +{ + switch (idx) { + case IDX_PKG_ENERGY: + return do_rapl & RAPL_PKG; + case IDX_DRAM_ENERGY: + return do_rapl & RAPL_DRAM; + case IDX_PP0_ENERGY: + return do_rapl & RAPL_CORES_ENERGY_STATUS; + case IDX_PP1_ENERGY: + return do_rapl & RAPL_GFX; + case IDX_PKG_PERF: + return do_rapl & RAPL_PKG_PERF_STATUS; + case IDX_DRAM_PERF: + return do_rapl & RAPL_DRAM_PERF_STATUS; + default: + return 0; + } +} struct sys_counters { unsigned int added_thread_counters; unsigned int added_core_counters; @@ -451,6 +560,7 @@ struct msr_counter bic[] = { { 0x0, "APIC" }, { 0x0, "X2APIC" }, { 0x0, "Die" }, + { 0x0, "GFXAMHz" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -505,6 +615,7 @@ struct msr_counter bic[] = { #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) #define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -724,6 +835,9 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0X\n", + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0X\n", + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c, } } - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); @@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); + /* GFXACTMHz */ + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); @@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ } #define DELTA_WRAP32(new, old) \ - if (new > old) { \ - old = new - old; \ - } else { \ - old = 0x100000000 + new - old; \ - } + old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32); int delta_package(struct pkg_data *new, struct pkg_data *old) @@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms; old->gfx_mhz = new->gfx_mhz; + old->gfx_act_mhz = new->gfx_act_mhz; - DELTA_WRAP32(new->energy_pkg, old->energy_pkg); - DELTA_WRAP32(new->energy_cores, old->energy_cores); - DELTA_WRAP32(new->energy_gfx, old->energy_gfx); - DELTA_WRAP32(new->energy_dram, old->energy_dram); - DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status); - DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status); + old->energy_pkg = new->energy_pkg - old->energy_pkg; + old->energy_cores = new->energy_cores - old->energy_cores; + old->energy_gfx = new->energy_gfx - old->energy_gfx; + old->energy_dram = new->energy_dram - old->energy_dram; + old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; + old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; + p->gfx_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.gfx_mhz = p->gfx_mhz; + average.packages.gfx_act_mhz = p->gfx_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); @@ -1784,7 +1894,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int i; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); return -1; } @@ -1966,39 +2076,39 @@ retry: p->sys_lpi = cpuidle_cur_sys_lpi_us; if (do_rapl & RAPL_PKG) { - if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (do_rapl & RAPL_CORES_ENERGY_STATUS) { - if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; - p->energy_cores = msr & 0xFFFFFFFF; + p->energy_cores = msr; } if (do_rapl & RAPL_DRAM) { - if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; - p->energy_dram = msr & 0xFFFFFFFF; + p->energy_dram = msr; } if (do_rapl & RAPL_GFX) { - if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; - p->energy_gfx = msr & 0xFFFFFFFF; + p->energy_gfx = msr; } if (do_rapl & RAPL_PKG_PERF_STATUS) { - if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; - p->rapl_pkg_perf_status = msr & 0xFFFFFFFF; + p->rapl_pkg_perf_status = msr; } if (do_rapl & RAPL_DRAM_PERF_STATUS) { - if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; - p->rapl_dram_perf_status = msr & 0xFFFFFFFF; + p->rapl_dram_perf_status = msr; } if (do_rapl & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) @@ -2012,6 +2122,9 @@ retry: if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; + if (DO_BIC(BIC_GFXACTMHz)) + p->gfx_act_mhz = gfx_act_mhz; + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) return -10; @@ -2173,6 +2286,7 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_FAM6_ATOM_TREMONT_D: return 1; } return 0; @@ -2650,7 +2764,12 @@ int get_thread_siblings(struct cpu_topology *thiscpu) sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + + if (!filep) { + warnx("%s: open failed", path); + return -1; + } do { offset -= BITMASK_SIZE; if (fscanf(filep, "%lx%c", &map, &character) != 2) @@ -2763,18 +2882,25 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(); - printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } void set_max_cpu_num(void) { FILE *filep; + int base_cpu; unsigned long dummy; + char pathname[64]; + + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(1, "cannot find calling cpu ID"); + sprintf(pathname, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", + base_cpu); + filep = fopen_or_die(pathname, "r"); topo.max_cpu_num = 0; - filep = fopen_or_die( - "/sys/devices/system/cpu/cpu0/topology/thread_siblings", - "r"); while (fscanf(filep, "%lx,", &dummy) == 1) topo.max_cpu_num += BITMASK_SIZE; fclose(filep); @@ -2916,6 +3042,33 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_gfx_cur_mhz() + * + * record snapshot of + * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_gfx_act_mhz(void) +{ + static FILE *fp; + int retval; + + if (fp == NULL) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + else { + rewind(fp); + fflush(fp); + } + + retval = fscanf(fp, "%d", &gfx_act_mhz); + if (retval != 1) + err(1, "GFX ACT MHz"); + + return 0; +} + +/* * snapshot_cpu_lpi() * * record snapshot of @@ -2980,6 +3133,9 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_GFXACTMHz)) + snapshot_gfx_act_mhz(); + if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -3057,6 +3213,111 @@ void do_sleep(void) } } +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) +{ + int ret, idx; + unsigned long long msr_cur, msr_last; + + if (!per_cpu_msr_sum) + return 1; + + idx = offset_to_idx(offset); + if (idx < 0) + return idx; + /* get_msr_sum() = sum + (get_msr() - last) */ + ret = get_msr(cpu, offset, &msr_cur); + if (ret) + return ret; + msr_last = per_cpu_msr_sum[cpu].entries[idx].last; + DELTA_WRAP32(msr_cur, msr_last); + *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum; + + return 0; +} + +timer_t timerid; + +/* Timer callback, update the sum of MSRs periodically. */ +static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + int i, ret; + int cpu = t->cpu_id; + + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { + unsigned long long msr_cur, msr_last; + int offset; + + if (!idx_valid(i)) + continue; + offset = idx_to_offset(i); + if (offset < 0) + continue; + ret = get_msr(cpu, offset, &msr_cur); + if (ret) { + fprintf(outf, "Can not update msr(0x%x)\n", offset); + continue; + } + + msr_last = per_cpu_msr_sum[cpu].entries[i].last; + per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff; + + DELTA_WRAP32(msr_cur, msr_last); + per_cpu_msr_sum[cpu].entries[i].sum += msr_last; + } + return 0; +} + +static void +msr_record_handler(union sigval v) +{ + for_all_cpus(update_msr_sum, EVEN_COUNTERS); +} + +void msr_sum_record(void) +{ + struct itimerspec its; + struct sigevent sev; + + per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array)); + if (!per_cpu_msr_sum) { + fprintf(outf, "Can not allocate memory for long time MSR.\n"); + return; + } + /* + * Signal handler might be restricted, so use thread notifier instead. + */ + memset(&sev, 0, sizeof(struct sigevent)); + sev.sigev_notify = SIGEV_THREAD; + sev.sigev_notify_function = msr_record_handler; + + sev.sigev_value.sival_ptr = &timerid; + if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) { + fprintf(outf, "Can not create timer.\n"); + goto release_msr; + } + + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 1; + /* + * A wraparound time has been calculated early. + * Some sources state that the peak power for a + * microprocessor is usually 1.5 times the TDP rating, + * use 2 * TDP for safety. + */ + its.it_interval.tv_sec = rapl_joule_counter_range / 2; + its.it_interval.tv_nsec = 0; + + if (timer_settime(timerid, 0, &its, NULL) == -1) { + fprintf(outf, "Can not set timer.\n"); + goto release_timer; + } + return; + + release_timer: + timer_delete(timerid); + release_msr: + free(per_cpu_msr_sum); +} void turbostat_loop() { @@ -3075,7 +3336,7 @@ restart: if (retval < -1) { exit(retval); } else if (retval == -1) { - if (restarted > 1) { + if (restarted > 10) { exit(retval); } re_initialize(); @@ -3279,6 +3540,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3361,6 +3623,17 @@ int is_ehl(unsigned int family, unsigned int model) } return 0; } +int is_jvl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT_D: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3475,6 +3748,20 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void +remove_underbar(char *s) +{ + char *to = s; + + while (*s) { + if (*s != '_') + *to++ = *s; + s++; + } + + *to = 0; +} + +static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) @@ -3530,9 +3817,6 @@ dump_sysfs_cstate_config(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { fprintf(outf, "cpuidle not loaded\n"); return; @@ -3559,6 +3843,8 @@ dump_sysfs_cstate_config(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", base_cpu, state); input = fopen(path, "r"); @@ -3645,7 +3931,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3689,7 +3975,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3777,7 +4063,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3881,13 +4167,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { - switch (family) { - case 0x17: - case 0x18: - default: - /* This is the max stock TDP of HEDT/Server Fam17h chips */ - return 250.0; - } + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ + return 280.0; } /* @@ -3959,6 +4240,14 @@ void rapl_probe_intel(unsigned int family, unsigned int model) BIC_PRESENT(BIC_GFXWatt); } break; + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ + do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4069,27 +4358,20 @@ void rapl_probe_amd(unsigned int family, unsigned int model) if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h) */ + /* RAPL (Fam 17h+) */ has_rapl = edx & (1 << 14); } - if (!has_rapl) + if (!has_rapl || family < 0x17) return; - switch (family) { - case 0x17: /* Zen, Zen+ */ - case 0x18: /* Hygon Dhyana */ - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - default: - return; + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); } if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) @@ -4162,7 +4444,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4234,7 +4516,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4361,6 +4643,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ return 1; } return 0; @@ -4507,12 +4790,33 @@ double discover_bclk(unsigned int family, unsigned int model) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int read_tcc_activation_temp() { unsigned long long msr; - unsigned int target_c_local; - int cpu; + unsigned int tcc, target_c, offset_c; + /* Temperature Target MSR is Nehalem and newer only */ + if (!do_nhm_platform_info) + return 0; + + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) + return 0; + + target_c = (msr >> 16) & 0xFF; + + offset_c = (msr >> 24) & 0xF; + + tcc = target_c - offset_c; + + if (!quiet) + fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", + base_cpu, msr, tcc, target_c, offset_c); + + return tcc; +} + +int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ /* tcc_activation_temp is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -4521,43 +4825,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - cpu = t->cpu_id; - if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); - return -1; - } - if (tcc_activation_temp_override != 0) { tcc_activation_temp = tcc_activation_temp_override; - fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n", - cpu, tcc_activation_temp); + fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp); return 0; } - /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) - goto guess; - - if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) - goto guess; - - target_c_local = (msr >> 16) & 0xFF; - - if (!quiet) - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", - cpu, msr, target_c_local); - - if (!target_c_local) - goto guess; - - tcc_activation_temp = target_c_local; - - return 0; + tcc_activation_temp = read_tcc_activation_temp(); + if (tcc_activation_temp) + return 0; -guess: tcc_activation_temp = TJMAX_DEFAULT; - fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n", - cpu, tcc_activation_temp); + fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp); return 0; } @@ -4685,19 +4964,46 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_NNPI: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: + case INTEL_FAM6_ROCKETLAKE: + case INTEL_FAM6_LAKEFIELD: + case INTEL_FAM6_ALDERLAKE: return INTEL_FAM6_CANNONLAKE_L; - case INTEL_FAM6_ATOM_TREMONT_D: - return INTEL_FAM6_ATOM_GOLDMONT_D; - case INTEL_FAM6_ATOM_TREMONT_L: return INTEL_FAM6_ATOM_TREMONT; case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: return INTEL_FAM6_SKYLAKE_X; } return model; } + +void print_dev_latency(void) +{ + char *path = "/dev/cpu_dma_latency"; + int fd; + int value; + int retval; + + fd = open(path, O_RDONLY); + if (fd < 0) { + warn("fopen %s\n", path); + return; + } + + retval = read(fd, (void *)&value, sizeof(int)); + if (retval != sizeof(int)) { + warn("read %s\n", path); + close(fd); + return; + } + fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n", + value, value == 2000000000 ? "default" : "constrained"); + + close(fd); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -4916,6 +5222,14 @@ void process_cpuid() BIC_PRESENT(BIC_Mod_c6); use_c1_residency_msr = 1; } + if (is_jvl(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } if (is_dnv(family, model)) { BIC_PRESENT(BIC_CPU_c1); BIC_NOT_PRESENT(BIC_CPU_c3); @@ -4935,9 +5249,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_Pkgpc7); } if (has_c8910_msrs(family, model)) { - BIC_PRESENT(BIC_Pkgpc8); - BIC_PRESENT(BIC_Pkgpc9); - BIC_PRESENT(BIC_Pkgpc10); + if (pkg_cstate_limit >= PCL__8) + BIC_PRESENT(BIC_Pkgpc8); + if (pkg_cstate_limit >= PCL__9) + BIC_PRESENT(BIC_Pkgpc9); + if (pkg_cstate_limit >= PCL_10) + BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { @@ -4967,6 +5284,8 @@ void process_cpuid() dump_cstate_pstate_config_info(family, model); if (!quiet) + print_dev_latency(); + if (!quiet) dump_sysfs_cstate_config(); if (!quiet) dump_sysfs_pstate_config(); @@ -4980,6 +5299,9 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) BIC_PRESENT(BIC_CPU_LPI); else @@ -5390,7 +5712,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 20.03.20" + fprintf(outf, "turbostat version 20.09.30" " - Len Brown <lenb@kernel.org>\n"); } @@ -5597,6 +5919,8 @@ void probe_sysfs(void) *sp = '%'; *(sp + 1) = '\0'; + remove_underbar(name_buf); + fclose(input); sprintf(path, "cpuidle/state%d/time", state); @@ -5624,6 +5948,8 @@ void probe_sysfs(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "cpuidle/state%d/usage", state); if (is_deferred_skip(name_buf)) @@ -5868,6 +6194,7 @@ int main(int argc, char **argv) return 0; } + msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 3fe1eed900d4..ff6c6661f075 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -622,6 +622,57 @@ void cmdline(int argc, char **argv) } } +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +void err_on_hypervisor(void) +{ + FILE *cpuinfo; + char *flags, *hypervisor; + char *buffer; + + /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */ + cpuinfo = fopen_or_die("/proc/cpuinfo", "ro"); + + buffer = malloc(4096); + if (!buffer) { + fclose(cpuinfo); + err(-ENOMEM, "buffer malloc fail"); + } + + if (!fread(buffer, 1024, 1, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + + flags = strstr(buffer, "flags"); + rewind(cpuinfo); + fseek(cpuinfo, flags - buffer, SEEK_SET); + if (!fgets(buffer, 4096, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + fclose(cpuinfo); + + hypervisor = strstr(buffer, "hypervisor"); + + free(buffer); + + if (hypervisor) + err(-1, + "not supported on this virtual machine"); +} int get_msr(int cpu, int offset, unsigned long long *msr) { @@ -635,8 +686,10 @@ int get_msr(int cpu, int offset, unsigned long long *msr) err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof(*msr), offset); - if (retval != sizeof(*msr)) + if (retval != sizeof(*msr)) { + err_on_hypervisor(); err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + } if (debug > 1) fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); @@ -1086,18 +1139,6 @@ int update_cpu_msrs(int cpu) return 0; } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, "r"); - - if (!filep) - err(1, "%s: open failed", path); - return filep; -} - unsigned int get_pkg_num(int cpu) { FILE *fp; diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index cb16d2aac51c..54188ee16c48 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2040,7 +2040,7 @@ sub reboot_to { if ($reboot_type eq "grub") { run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'"; - } elsif ($reboot_type eq "grub2") { + } elsif (($reboot_type eq "grub2") or ($reboot_type eq "grub2bls")) { run_ssh "$grub_reboot $grub_number"; } elsif ($reboot_type eq "syslinux") { run_ssh "$syslinux --once \\\"$syslinux_label\\\" $syslinux_path"; diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes deleted file mode 100644 index 5b7da1fc3b8f..000000000000 --- a/tools/testing/kunit/.gitattributes +++ /dev/null @@ -1 +0,0 @@ -test_data/* binary diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index ebf5f5763dee..d4f7846d0745 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -11,7 +11,6 @@ import argparse import sys import os import time -import shutil from collections import namedtuple from enum import Enum, auto @@ -44,11 +43,6 @@ class KunitStatus(Enum): BUILD_FAILURE = auto() TEST_FAILURE = auto() -def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.kunitconfig_path): - shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.kunitconfig_path) - def get_kernel_root_path(): parts = sys.argv[0] if not __file__ else __file__ parts = os.path.realpath(parts).split('tools/testing/kunit') @@ -61,7 +55,6 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...') config_start = time.time() - create_default_kunitconfig() success = linux.build_reconfig(request.build_dir, request.make_options) config_end = time.time() if not success: @@ -262,12 +255,12 @@ def main(argv, linux=None): if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitRequest(cli_args.raw_output, cli_args.timeout, cli_args.jobs, @@ -283,12 +276,12 @@ def main(argv, linux=None): not os.path.exists(cli_args.build_dir)): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitConfigRequest(cli_args.build_dir, cli_args.make_options) result = config_tests(linux, request) @@ -301,6 +294,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitBuildRequest(cli_args.jobs, cli_args.build_dir, cli_args.alltests, @@ -315,6 +311,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + exec_request = KunitExecRequest(cli_args.timeout, cli_args.build_dir, cli_args.alltests) @@ -337,7 +336,7 @@ def main(argv, linux=None): kunit_output = f.read().splitlines() request = KunitParseRequest(cli_args.raw_output, kunit_output, - cli_args.build_dir, + None, cli_args.json) result = parse_tests(request) if result.status != KunitStatus.SUCCESS: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index b557b1e93f98..2e3cc0fac726 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,10 +6,10 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> - import logging import subprocess import os +import shutil import signal from contextlib import ExitStack @@ -18,8 +18,10 @@ import kunit_config import kunit_parser KCONFIG_PATH = '.config' -kunitconfig_path = '.kunitconfig' +KUNITCONFIG_PATH = '.kunitconfig' +DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' +OUTFILE_PATH = 'test.log' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -82,36 +84,51 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.STDOUT) + proc = subprocess.Popen(command, + stderr=subprocess.PIPE, + stdout=subprocess.DEVNULL) except OSError as e: - raise BuildError('Could not call execute make: ' + str(e)) - except subprocess.CalledProcessError as e: - raise BuildError(e.output.decode()) - - def linux_bin(self, params, timeout, build_dir, outfile): + raise BuildError('Could not call make command: ' + str(e)) + _, stderr = proc.communicate() + if proc.returncode != 0: + raise BuildError(stderr.decode()) + if stderr: # likely only due to build warnings + print(stderr.decode()) + + def linux_bin(self, params, timeout, build_dir): """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = './linux' if build_dir: linux_bin = os.path.join(build_dir, 'linux') + outfile = get_outfile_path(build_dir) with open(outfile, 'w') as output: process = subprocess.Popen([linux_bin] + params, stdout=output, stderr=subprocess.STDOUT) process.wait(timeout) - def get_kconfig_path(build_dir): kconfig_path = KCONFIG_PATH if build_dir: kconfig_path = os.path.join(build_dir, KCONFIG_PATH) return kconfig_path +def get_kunitconfig_path(build_dir): + kunitconfig_path = KUNITCONFIG_PATH + if build_dir: + kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH) + return kunitconfig_path + +def get_outfile_path(build_dir): + outfile_path = OUTFILE_PATH + if build_dir: + outfile_path = os.path.join(build_dir, OUTFILE_PATH) + return outfile_path + class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" def __init__(self): - self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() signal.signal(signal.SIGINT, self.signal_handler) @@ -123,6 +140,16 @@ class LinuxSourceTree(object): return False return True + def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH): + kunitconfig_path = get_kunitconfig_path(build_dir) + if not os.path.exists(kunitconfig_path): + shutil.copyfile(defconfig, kunitconfig_path) + + def read_kunitconfig(self, build_dir): + kunitconfig_path = get_kunitconfig_path(build_dir) + self._kconfig = kunit_config.Kconfig() + self._kconfig.read_from_file(kunitconfig_path) + def validate_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) validated_kconfig = kunit_config.Kconfig() @@ -178,8 +205,8 @@ class LinuxSourceTree(object): def run_kernel(self, args=[], build_dir='', timeout=None): args.extend(['mem=1G']) - outfile = 'test.log' - self._ops.linux_bin(args, timeout, build_dir, outfile) + self._ops.linux_bin(args, timeout, build_dir) + outfile = get_outfile_path(build_dir) subprocess.call(['stty', 'sane']) with open(outfile, 'r') as file: for line in file: diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 84a1af2581f5..bbfe1b4e4c1c 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,7 +12,7 @@ from collections import namedtuple from datetime import datetime from enum import Enum, auto from functools import reduce -from typing import List +from typing import List, Optional, Tuple TestResult = namedtuple('TestResult', ['status','suites','log']) @@ -54,6 +54,7 @@ kunit_end_re = re.compile('(List of all partitions:|' def isolate_kunit_output(kernel_output): started = False for line in kernel_output: + line = line.rstrip() # line always has a trailing \n if kunit_start_re.search(line): prefix_len = len(line.split('TAP version')[0]) started = True @@ -65,7 +66,7 @@ def isolate_kunit_output(kernel_output): def raw_output(kernel_output): for line in kernel_output: - print(line) + print(line.rstrip()) DIVIDER = '=' * 60 @@ -151,7 +152,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: else: return False -def parse_test_case(lines: List[str]) -> TestCase: +def parse_test_case(lines: List[str]) -> Optional[TestCase]: test_case = TestCase() save_non_diagnositic(lines, test_case) while parse_diagnostic(lines, test_case): @@ -163,7 +164,7 @@ def parse_test_case(lines: List[str]) -> TestCase: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') -def parse_subtest_header(lines: List[str]) -> str: +def parse_subtest_header(lines: List[str]) -> Optional[str]: consume_non_diagnositic(lines) if not lines: return None @@ -176,7 +177,7 @@ def parse_subtest_header(lines: List[str]) -> str: SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') -def parse_subtest_plan(lines: List[str]) -> int: +def parse_subtest_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = SUBTEST_PLAN.match(lines[0]) if match: @@ -230,7 +231,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) return max_status(max_test_case_status, test_suite.status) -def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite: +def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None consume_non_diagnositic(lines) @@ -271,7 +272,7 @@ def parse_tap_header(lines: List[str]) -> bool: TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') -def parse_test_plan(lines: List[str]) -> int: +def parse_test_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = TEST_PLAN.match(lines[0]) if match: @@ -310,7 +311,7 @@ def parse_test_result(lines: List[str]) -> TestResult: else: return TestResult(TestStatus.NO_TESTS, [], lines) -def print_and_count_results(test_result: TestResult) -> None: +def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]: total_tests = 0 failed_tests = 0 crashed_tests = 0 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0b60855fb819..497ab51bc170 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -102,7 +102,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_output_isolated_correctly.log') file = open(log_path) result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: example', result) self.assertContains(' 1..2', result) self.assertContains(' ok 1 - example_simple_test', result) @@ -115,7 +115,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_pound_sign.log') with open(log_path) as file: result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: kunit-resource-test', result) self.assertContains(' 1..5', result) self.assertContains(' ok 1 - kunit_resource_test_init_resources', result) diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 6ae907f375d2..f9a12005fcea 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -33,6 +33,7 @@ typedef unsigned long dma_addr_t; #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index d264bf853034..8a577c95496e 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -52,9 +52,9 @@ int main(void) { const unsigned int sgmax = UINT_MAX; struct test *test, tests[] = { - { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 }, - { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 }, { 0, 1, pfn(0), 1, sgmax, 1 }, { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 }, diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 52414058a627..5861446d0777 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -456,10 +456,10 @@ static struct bpf_align_test tests[] = { */ {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c new file mode 100644 index 000000000000..14a31109dd0e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_init.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include <test_progs.h> +#include "test_map_init.skel.h" + +#define TEST_VALUE 0x1234 +#define FILL_VALUE 0xdeadbeef + +static int nr_cpus; +static int duration; + +typedef unsigned long long map_key_t; +typedef unsigned long long map_value_t; +typedef struct { + map_value_t v; /* padding */ +} __bpf_percpu_val_align pcpu_map_value_t; + + +static int map_populate(int map_fd, int num) +{ + pcpu_map_value_t value[nr_cpus]; + int i, err; + map_key_t key; + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value, i) = FILL_VALUE; + + for (key = 1; key <= num; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz, + int *map_fd, int populate) +{ + struct test_map_init *skel; + int err; + + skel = test_map_init__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hashmap1, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto error; + + err = test_map_init__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + *map_fd = bpf_map__fd(skel->maps.hashmap1); + if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n")) + goto error; + + err = map_populate(*map_fd, populate); + if (!ASSERT_OK(err, "map_populate")) + goto error_map; + + return skel; + +error_map: + close(*map_fd); +error: + test_map_init__destroy(skel); + return NULL; +} + +/* executes bpf program that updates map with key, value */ +static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key, + map_value_t value) +{ + struct test_map_init__bss *bss; + + bss = skel->bss; + + bss->inKey = key; + bss->inValue = value; + bss->inPid = getpid(); + + if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach")) + return -1; + + /* Let tracepoint trigger */ + syscall(__NR_getpgid); + + test_map_init__detach(skel); + + return 0; +} + +static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected) +{ + int i, nzCnt = 0; + map_value_t val; + + for (i = 0; i < nr_cpus; i++) { + val = bpf_percpu(value, i); + if (val) { + if (CHECK(val != expected, "map value", + "unexpected for cpu %d: 0x%llx\n", i, val)) + return -1; + nzCnt++; + } + } + + if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n", + nzCnt)) + return -1; + + return 0; +} + +/* Add key=1 elem with values set for all CPUs + * Delete elem key=1 + * Run bpf prog that inserts new key=1 elem with value=0x1234 + * (bpf prog can only set value for current CPU) + * Lookup Key=1 and check value is as expected for all CPUs: + * value set by bpf prog for one CPU, 0 for all others + */ +static void test_pcpu_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* max 1 elem in map so insertion is forced to reuse freed entry */ + skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* delete element so the entry can be re-used*/ + key = 1; + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "bpf_map_delete_elem")) + goto cleanup; + + /* run bpf prog that inserts new elem, re-using the slot just freed */ + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=1 was re-created by bpf prog */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +/* Add key=1 and key=2 elems with values set for all CPUs + * Run bpf prog that inserts new key=3 elem + * (only for current cpu; other cpus should have initial value = 0) + * Lookup Key=1 and check value is as expected for all CPUs + */ +static void test_pcpu_lru_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* Set up LRU map with 2 elements, values filled for all CPUs. + * With these 2 elements, the LRU map is full + */ + skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* run bpf prog that inserts new key=3 element, re-using LRU slot */ + key = 3; + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=3 replaced one of earlier elements */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +void test_map_init(void) +{ + nr_cpus = bpf_num_possible_cpus(); + if (nr_cpus <= 1) { + printf("%s:SKIP: >1 cpu needed for this test\n", __func__); + test__skip(); + return; + } + + if (test__start_subtest("pcpu_map_init")) + test_pcpu_map_init(); + if (test__start_subtest("pcpu_lru_map_init")) + test_pcpu_lru_map_init(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c new file mode 100644 index 000000000000..e419298132b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "test_probe_read_user_str.skel.h" + +static const char str1[] = "mestring"; +static const char str2[] = "mestringalittlebigger"; +static const char str3[] = "mestringblubblubblubblubblub"; + +static int test_one_str(struct test_probe_read_user_str *skel, const char *str, + size_t len) +{ + int err, duration = 0; + char buf[256]; + + /* Ensure bytes after string are ones */ + memset(buf, 1, sizeof(buf)); + memcpy(buf, str, len); + + /* Give prog our userspace pointer */ + skel->bss->user_ptr = buf; + + /* Trigger tracepoint */ + usleep(1); + + /* Did helper fail? */ + if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n", + skel->bss->ret)) + return 1; + + /* Check that string was copied correctly */ + err = memcmp(skel->bss->buf, str, len); + if (CHECK(err, "memcmp", "prog copied wrong string")) + return 1; + + /* Now check that no extra trailing bytes were copied */ + memset(buf, 0, sizeof(buf)); + err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len); + if (CHECK(err, "memcmp", "trailing bytes were not stripped")) + return 1; + + return 0; +} + +void test_probe_read_user_str(void) +{ + struct test_probe_read_user_str *skel; + int err, duration = 0; + + skel = test_probe_read_user_str__open_and_load(); + if (CHECK(!skel, "test_probe_read_user_str__open_and_load", + "skeleton open and load failed\n")) + return; + + /* Give pid to bpf prog so it doesn't read from anyone else */ + skel->bss->pid = getpid(); + + err = test_probe_read_user_str__attach(skel); + if (CHECK(err, "test_probe_read_user_str__attach", + "skeleton attach failed: %d\n", err)) + goto out; + + if (test_one_str(skel, str1, sizeof(str1))) + goto out; + if (test_one_str(skel, str2, sizeof(str2))) + goto out; + if (test_one_str(skel, str3, sizeof(str3))) + goto out; + +out: + test_probe_read_user_str__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index c1650548433c..fddbc5db5d6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -217,9 +217,15 @@ void test_ringbuf(void) if (CHECK(err, "join_bg", "err %d\n", err)) goto cleanup; - if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret)) + if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret)) goto cleanup; + /* due to timing variations, there could still be non-notified + * samples, so consume them here to collect all the samples + */ + err = ring_buffer__consume(ringbuf); + CHECK(err < 0, "rb_consume", "failed: %d\b", err); + /* 3 rounds, 2 samples each */ cnt = atomic_xchg(&sample_cnt, 0); CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index 78e450609803..d37161e59bb2 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -81,7 +81,7 @@ void test_ringbuf_multi(void) /* poll for samples, should get 2 ringbufs back */ err = ring_buffer__poll(ringbuf, -1); - if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err)) + if (CHECK(err != 2, "poll_res", "expected 2 records, got %d\n", err)) goto cleanup; /* expect extra polling to return nothing */ diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 29188d6f5c8d..51fac975b316 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -138,7 +138,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, */ buf = 0x40; - if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) { + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { log_err("Failed to call setsockopt(IP_TOS)"); goto detach; } diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index a00abf58c037..3f3d2ac4dd57 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -3,12 +3,14 @@ #include <test_progs.h> #include <time.h> #include "test_subprogs.skel.h" +#include "test_subprogs_unused.skel.h" static int duration; void test_subprogs(void) { struct test_subprogs *skel; + struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); @@ -26,6 +28,10 @@ void test_subprogs(void) CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + skel2 = test_subprogs_unused__open_and_load(); + ASSERT_OK_PTR(skel2, "unused_progs_skel"); + test_subprogs_unused__destroy(skel2); + cleanup: test_subprogs__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 193002b14d7f..32e4348b714b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -60,6 +60,7 @@ void test_test_global_funcs(void) { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, { "test_global_func6.o" , "modified ctx ptr R2" }, { "test_global_func7.o" , "foo() doesn't return scalar" }, + { "test_global_func8.o" }, }; libbpf_print_fn_t old_print_fn = NULL; int err, i, duration = 0; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 00578311a423..30982a7e4d0f 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -243,7 +243,10 @@ static ino_t get_inode_from_kernfs(struct kernfs_node* node) } } -int pids_cgrp_id = 1; +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, struct task_struct* task, @@ -253,7 +256,9 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); - if (ENABLE_CGROUP_V1_RESOLVER) { + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); #ifdef UNROLL #pragma unroll #endif @@ -262,7 +267,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, cgroups, subsys[i]); if (subsys != NULL) { int subsys_id = BPF_CORE_READ(subsys, ss, id); - if (subsys_id == pids_cgrp_id) { + if (subsys_id == cgrp_id) { proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); break; diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c new file mode 100644 index 000000000000..d55a6544b1ab --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline int foo(struct __sk_buff *skb) +{ + return bpf_get_prandom_u32(); +} + +SEC("cgroup_skb/ingress") +int test_cls(struct __sk_buff *skb) +{ + if (!foo(skb)) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 000000000000..c89d28ead673 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c new file mode 100644 index 000000000000..3ae398b75dcd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include <sys/types.h> + +pid_t pid = 0; +long ret = 0; +void *user_ptr = 0; +char buf[256] = {}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int on_write(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c new file mode 100644 index 000000000000..bc49e050d342 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -0,0 +1,21 @@ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +const char LICENSE[] SEC("license") = "GPL"; + +__attribute__((unused)) __noinline int unused1(int x) +{ + return x + 1; +} + +static __attribute__((unused)) __noinline int unused2(int x) +{ + return x + 2; +} + +SEC("raw_tp/sys_enter") +int main_prog(void *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 43c9cda199b8..b99bb8ed3ed4 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -184,9 +184,7 @@ def bpftool_prog_list(expected=None, ns=""): def bpftool_map_list(expected=None, ns=""): _, maps = bpftool("map show", JSON=True, ns=ns, fail=True) # Remove the base maps - for m in base_maps: - if m in maps: - maps.remove(m) + maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names] if expected is not None: if len(maps) != expected: fail(True, "%d BPF maps loaded, expected %d" % @@ -716,13 +714,11 @@ def test_multi_prog(simdev, sim, obj, modename, modeid): fail(ret == 0, "Replaced one of programs without -force") check_extack(err, "XDP program already attached.", args) - if modename == "" or modename == "drv": - othermode = "" if modename == "drv" else "drv" - start_test("Test multi-attachment XDP - detach...") - ret, _, err = sim.unset_xdp(othermode, force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) + start_test("Test multi-attachment XDP - remove without mode...") + ret, _, err = sim.unset_xdp("", force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Removed program without a mode flag") + check_extack(err, "More than one program loaded, unset mode is ambiguous.", args) sim.unset_xdp("offload") xdp = sim.ip_link_show(xdp=True)["xdp"] @@ -772,6 +768,9 @@ ret, progs = bpftool("prog", fail=False) skip(ret != 0, "bpftool not installed") base_progs = progs _, base_maps = bpftool("map") +base_map_names = [ + 'pid_iter.rodata' # created on each bpftool invocation +] # Check netdevsim ret, out = cmd("modprobe netdevsim", fail=False) @@ -913,11 +912,18 @@ try: sim.tc_flush_filters() + start_test("Test TC offloads failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, + fail=False, include_stderr=True) + fail(ret == 0, "TC filter did not reject with TC offloads enabled") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + start_test("Test TC offloads work...") ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, fail=False, include_stderr=True) fail(ret != 0, "TC filter did not load with TC offloads enabled") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test TC offload basics...") dfs = simdev.dfs_get_bound_progs(expected=1) @@ -941,6 +947,7 @@ try: start_test("Test disabling TC offloads is rejected while filters installed...") ret, _ = sim.set_ethtool_tc_offloads(False, fail=False) fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...") + sim.set_ethtool_tc_offloads(True) start_test("Test qdisc removal frees things...") sim.tc_flush_filters() @@ -999,18 +1006,8 @@ try: fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") check_extack(err, - "native and generic XDP can't be active at the same time.", + "Native and generic XDP can't be active at the same time.", args) - ret, _, err = sim.set_xdp(obj, "", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack(err, "program loaded with different flags.", args) - - start_test("Test XDP prog remove with bad flags...") - ret, _, err = sim.unset_xdp("", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) start_test("Test MTU restrictions...") ret, _ = sim.set_mtu(9000, fail=False) @@ -1040,10 +1037,19 @@ try: offload = bpf_pinned("/sys/fs/bpf/offload") ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True) fail(ret == 0, "attached offloaded XDP program to drv") - check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args) + check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args) rm("/sys/fs/bpf/offload") sim.wait_for_flush() + start_test("Test XDP load failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload", + dev=sim['ifname'], fail=False, include_stderr=True) + fail(ret == 0, "verifier should fail on load") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + sim.wait_for_flush() + start_test("Test XDP offload...") _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True) ipl = sim.ip_link_show(xdp=True) @@ -1051,7 +1057,6 @@ try: progs = bpftool_prog_list(expected=1) prog = progs[0] fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test XDP offload is device bound...") dfs = simdev.dfs_get_bound_progs(expected=1) diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index 1c4b1939f5a8..bed53b561e04 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -68,7 +68,7 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), - BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), + BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), BPF_MOV32_IMM(BPF_REG_1, 0), BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index dac40de3f868..57ed67b86074 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -703,3 +703,44 @@ .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, +{ + "bounds checks after 32-bit truncation. test 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + /* This used to reduce the max bound to 0x7fffffff */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, +{ + "bounds checks after 32-bit truncation. test 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1), + BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d2c2d6205008..7a2c242b7152 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,10 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/get-reg-list +/aarch64/get-reg-list-sve /s390x/memop /s390x/resets /s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/kvm_pv_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test @@ -24,6 +27,7 @@ /clear_dirty_log_test /demand_paging_test /dirty_log_test +/dirty_log_perf_test /kvm_create_max_vcpus /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 30afbad36cd5..3d14ef77755e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,13 +34,14 @@ ifeq ($(ARCH),s390) endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test -TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus @@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option) include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a -LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.* + +x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) -$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS) $(AR) crs $@ $^ x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c new file mode 100644 index 000000000000..efba76682b4b --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define REG_LIST_SVE +#include "get-reg-list.c" diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c new file mode 100644 index 000000000000..33218a395d9f --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * Note, the blessed list should be created from the oldest possible + * kernel. We can't go older than v4.15, though, because that's the first + * release to expose the ID system registers in KVM_GET_REG_LIST, see + * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features + * from guests"). Also, one must use the --core-reg-fixup command line + * option when running on an older kernel that doesn't include df205b5c6328 + * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#ifdef REG_LIST_SVE +#define reg_list_sve() (true) +#else +#define reg_list_sve() (false) +#endif + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + + +static struct kvm_reg_list *reg_list; + +static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; +static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; +static __u64 *blessed_reg, blessed_n; + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +static const char *str_with_index(const char *template, __u64 index) +{ + char *str, *p; + int n; + + str = strdup(template); + p = strstr(str, "##"); + n = sprintf(p, "%lld", index); + strcat(p + n, strstr(template, "##") + 2); + + return (const char *)str; +} + +#define CORE_REGS_XX_NR_WORDS 2 +#define CORE_SPSR_XX_NR_WORDS 2 +#define CORE_FPREGS_XX_NR_WORDS 4 + +static const char *core_id_to_str(__u64 id) +{ + __u64 core_off = id & ~REG_MASK, idx; + + /* + * core_off is the offset into struct kvm_regs + */ + switch (core_off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; + TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + case KVM_REG_ARM_CORE_REG(regs.sp): + return "KVM_REG_ARM_CORE_REG(regs.sp)"; + case KVM_REG_ARM_CORE_REG(regs.pc): + return "KVM_REG_ARM_CORE_REG(regs.pc)"; + case KVM_REG_ARM_CORE_REG(regs.pstate): + return "KVM_REG_ARM_CORE_REG(regs.pstate)"; + case KVM_REG_ARM_CORE_REG(sp_el1): + return "KVM_REG_ARM_CORE_REG(sp_el1)"; + case KVM_REG_ARM_CORE_REG(elr_el1): + return "KVM_REG_ARM_CORE_REG(elr_el1)"; + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; + TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; + TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; + } + + TEST_FAIL("Unknown core reg id: 0x%llx", id); + return NULL; +} + +static const char *sve_id_to_str(__u64 id) +{ + __u64 sve_off, n, i; + + if (id == KVM_REG_ARM64_SVE_VLS) + return "KVM_REG_ARM64_SVE_VLS"; + + sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); + i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); + + TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id); + + switch (sve_off) { + case KVM_REG_ARM64_SVE_ZREG_BASE ... + KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), + "Unexpected bits set in SVE ZREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + case KVM_REG_ARM64_SVE_PREG_BASE ... + KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), + "Unexpected bits set in SVE PREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + case KVM_REG_ARM64_SVE_FFR_BASE: + TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), + "Unexpected bits set in SVE FFR id: 0x%llx", id); + return "KVM_REG_ARM64_SVE_FFR(0)"; + } + + return NULL; +} + +static void print_reg(__u64 id) +{ + unsigned op0, op1, crn, crm, op2; + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, + "KVM_REG_ARM64 missing in reg id: 0x%llx", id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U8: + reg_size = "KVM_REG_SIZE_U8"; + break; + case KVM_REG_SIZE_U16: + reg_size = "KVM_REG_SIZE_U16"; + break; + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + case KVM_REG_SIZE_U256: + reg_size = "KVM_REG_SIZE_U256"; + break; + case KVM_REG_SIZE_U512: + reg_size = "KVM_REG_SIZE_U512"; + break; + case KVM_REG_SIZE_U1024: + reg_size = "KVM_REG_SIZE_U1024"; + break; + case KVM_REG_SIZE_U2048: + reg_size = "KVM_REG_SIZE_U2048"; + break; + default: + TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id)); + break; + case KVM_REG_ARM_DEMUX: + TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), + "Unexpected bits set in DEMUX reg id: 0x%llx", id); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", + reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); + break; + case KVM_REG_ARM64_SYSREG: + op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT; + op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT; + crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT; + crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; + op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; + TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), + "Unexpected bits set in SYSREG reg id: 0x%llx", id); + printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); + break; + case KVM_REG_ARM_FW: + TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), + "Unexpected bits set in FW reg id: 0x%llx", id); + printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); + break; + case KVM_REG_ARM64_SVE: + if (reg_list_sve()) + printf("\t%s,\n", sve_id_to_str(id)); + else + TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id); + break; + default: + TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); + } +} + +/* + * Older kernels listed each 32-bit word of CORE registers separately. + * For 64 and 128-bit registers we need to ignore the extra words. We + * also need to fixup the sizes, because the older kernels stated all + * registers were 64-bit, even when they weren't. + */ +static void core_reg_fixup(void) +{ + struct kvm_reg_list *tmp; + __u64 id, core_off; + int i; + + tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); + + for (i = 0; i < reg_list->n; ++i) { + id = reg_list->reg[i]; + + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { + tmp->reg[tmp->n++] = id; + continue; + } + + core_off = id & ~REG_MASK; + + switch (core_off) { + case 0x52: case 0xd2: case 0xd6: + /* + * These offsets are pointing at padding. + * We need to ignore them too. + */ + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + if (core_off & 3) + continue; + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U128; + tmp->reg[tmp->n++] = id; + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U32; + tmp->reg[tmp->n++] = id; + continue; + default: + if (core_off & 1) + continue; + tmp->reg[tmp->n++] = id; + break; + } + } + + free(reg_list); + reg_list = tmp; +} + +static void prepare_vcpu_init(struct kvm_vcpu_init *init) +{ + if (reg_list_sve()) + init->features[0] |= 1 << KVM_ARM_VCPU_SVE; +} + +static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + int feature; + + if (reg_list_sve()) { + feature = KVM_ARM_VCPU_SVE; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + } +} + +static void check_supported(void) +{ + if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) { + fprintf(stderr, "SVE not available, skipping tests\n"); + exit(KSFT_SKIP); + } +} + +int main(int ac, char **av) +{ + struct kvm_vcpu_init init = { .target = -1, }; + int new_regs = 0, missing_regs = 0, i; + int failed_get = 0, failed_set = 0, failed_reject = 0; + bool print_list = false, fixup_core_regs = false; + struct kvm_vm *vm; + __u64 *vec_regs; + + check_supported(); + + for (i = 1; i < ac; ++i) { + if (strcmp(av[i], "--core-reg-fixup") == 0) + fixup_core_regs = true; + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else + fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + } + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + prepare_vcpu_init(&init); + aarch64_vcpu_add_default(vm, 0, &init, NULL); + finalize_vcpu(vm, 0); + + reg_list = vcpu_get_reg_list(vm, 0); + + if (fixup_core_regs) + core_reg_fixup(); + + if (print_list) { + putchar('\n'); + for_each_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + return 0; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + */ + for_each_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + int ret; + + ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + if (ret) { + puts("Failed to get "); + print_reg(reg.id); + putchar('\n'); + ++failed_get; + } + + /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ + if (find_reg(rejects_set, rejects_set_n, reg.id)) { + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret != -1 || errno != EPERM) { + printf("Failed to reject (ret=%d, errno=%d) ", ret, errno); + print_reg(reg.id); + putchar('\n'); + ++failed_reject; + } + continue; + } + + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret) { + puts("Failed to set "); + print_reg(reg.id); + putchar('\n'); + ++failed_set; + } + } + + if (reg_list_sve()) { + blessed_n = base_regs_n + sve_regs_n; + vec_regs = sve_regs; + } else { + blessed_n = base_regs_n + vregs_n; + vec_regs = vregs; + } + + blessed_reg = calloc(blessed_n, sizeof(__u64)); + for (i = 0; i < base_regs_n; ++i) + blessed_reg[i] = base_regs[i]; + for (i = 0; i < blessed_n - base_regs_n; ++i) + blessed_reg[base_regs_n + i] = vec_regs[i]; + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + printf("Number blessed registers: %5lld\n", blessed_n); + printf("Number registers: %5lld\n", reg_list->n); + } + + if (new_regs) { + printf("\nThere are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", new_regs); + for_each_new_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\nThere are %d missing registers.\n" + "The following lines are missing registers:\n\n", missing_regs); + for_each_missing_reg(i) + print_reg(blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "There are %d missing registers; " + "%d registers failed get; %d registers failed set; %d registers failed reject", + missing_regs, failed_get, failed_set, failed_reject); + + return 0; +} + +/* + * The current blessed list was primed with the output of kernel version + * v4.15 with --core-reg-fixup and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), + KVM_REG_ARM_FW_REG(0), + KVM_REG_ARM_FW_REG(1), + KVM_REG_ARM_FW_REG(2), + ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 2), + ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ + ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ + ARM64_SYS_REG(2, 0, 0, 0, 4), + ARM64_SYS_REG(2, 0, 0, 0, 5), + ARM64_SYS_REG(2, 0, 0, 0, 6), + ARM64_SYS_REG(2, 0, 0, 0, 7), + ARM64_SYS_REG(2, 0, 0, 1, 4), + ARM64_SYS_REG(2, 0, 0, 1, 5), + ARM64_SYS_REG(2, 0, 0, 1, 6), + ARM64_SYS_REG(2, 0, 0, 1, 7), + ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 4), + ARM64_SYS_REG(2, 0, 0, 2, 5), + ARM64_SYS_REG(2, 0, 0, 2, 6), + ARM64_SYS_REG(2, 0, 0, 2, 7), + ARM64_SYS_REG(2, 0, 0, 3, 4), + ARM64_SYS_REG(2, 0, 0, 3, 5), + ARM64_SYS_REG(2, 0, 0, 3, 6), + ARM64_SYS_REG(2, 0, 0, 3, 7), + ARM64_SYS_REG(2, 0, 0, 4, 4), + ARM64_SYS_REG(2, 0, 0, 4, 5), + ARM64_SYS_REG(2, 0, 0, 4, 6), + ARM64_SYS_REG(2, 0, 0, 4, 7), + ARM64_SYS_REG(2, 0, 0, 5, 4), + ARM64_SYS_REG(2, 0, 0, 5, 5), + ARM64_SYS_REG(2, 0, 0, 5, 6), + ARM64_SYS_REG(2, 0, 0, 5, 7), + ARM64_SYS_REG(2, 0, 0, 6, 4), + ARM64_SYS_REG(2, 0, 0, 6, 5), + ARM64_SYS_REG(2, 0, 0, 6, 6), + ARM64_SYS_REG(2, 0, 0, 6, 7), + ARM64_SYS_REG(2, 0, 0, 7, 4), + ARM64_SYS_REG(2, 0, 0, 7, 5), + ARM64_SYS_REG(2, 0, 0, 7, 6), + ARM64_SYS_REG(2, 0, 0, 7, 7), + ARM64_SYS_REG(2, 0, 0, 8, 4), + ARM64_SYS_REG(2, 0, 0, 8, 5), + ARM64_SYS_REG(2, 0, 0, 8, 6), + ARM64_SYS_REG(2, 0, 0, 8, 7), + ARM64_SYS_REG(2, 0, 0, 9, 4), + ARM64_SYS_REG(2, 0, 0, 9, 5), + ARM64_SYS_REG(2, 0, 0, 9, 6), + ARM64_SYS_REG(2, 0, 0, 9, 7), + ARM64_SYS_REG(2, 0, 0, 10, 4), + ARM64_SYS_REG(2, 0, 0, 10, 5), + ARM64_SYS_REG(2, 0, 0, 10, 6), + ARM64_SYS_REG(2, 0, 0, 10, 7), + ARM64_SYS_REG(2, 0, 0, 11, 4), + ARM64_SYS_REG(2, 0, 0, 11, 5), + ARM64_SYS_REG(2, 0, 0, 11, 6), + ARM64_SYS_REG(2, 0, 0, 11, 7), + ARM64_SYS_REG(2, 0, 0, 12, 4), + ARM64_SYS_REG(2, 0, 0, 12, 5), + ARM64_SYS_REG(2, 0, 0, 12, 6), + ARM64_SYS_REG(2, 0, 0, 12, 7), + ARM64_SYS_REG(2, 0, 0, 13, 4), + ARM64_SYS_REG(2, 0, 0, 13, 5), + ARM64_SYS_REG(2, 0, 0, 13, 6), + ARM64_SYS_REG(2, 0, 0, 13, 7), + ARM64_SYS_REG(2, 0, 0, 14, 4), + ARM64_SYS_REG(2, 0, 0, 14, 5), + ARM64_SYS_REG(2, 0, 0, 14, 6), + ARM64_SYS_REG(2, 0, 0, 14, 7), + ARM64_SYS_REG(2, 0, 0, 15, 4), + ARM64_SYS_REG(2, 0, 0, 15, 5), + ARM64_SYS_REG(2, 0, 0, 15, 6), + ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ + ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 3), + ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 7), + ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 3), + ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 6), + ARM64_SYS_REG(3, 0, 0, 4, 7), + ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 2), + ARM64_SYS_REG(3, 0, 0, 5, 3), + ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 6), + ARM64_SYS_REG(3, 0, 0, 5, 7), + ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 3), + ARM64_SYS_REG(3, 0, 0, 6, 4), + ARM64_SYS_REG(3, 0, 0, 6, 5), + ARM64_SYS_REG(3, 0, 0, 6, 6), + ARM64_SYS_REG(3, 0, 0, 6, 7), + ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), + ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 5), + ARM64_SYS_REG(3, 0, 0, 7, 6), + ARM64_SYS_REG(3, 0, 0, 7, 7), + ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ + ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ + ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ + ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ + ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 8, 0), + ARM64_SYS_REG(3, 3, 14, 8, 1), + ARM64_SYS_REG(3, 3, 14, 8, 2), + ARM64_SYS_REG(3, 3, 14, 8, 3), + ARM64_SYS_REG(3, 3, 14, 8, 4), + ARM64_SYS_REG(3, 3, 14, 8, 5), + ARM64_SYS_REG(3, 3, 14, 8, 6), + ARM64_SYS_REG(3, 3, 14, 8, 7), + ARM64_SYS_REG(3, 3, 14, 9, 0), + ARM64_SYS_REG(3, 3, 14, 9, 1), + ARM64_SYS_REG(3, 3, 14, 9, 2), + ARM64_SYS_REG(3, 3, 14, 9, 3), + ARM64_SYS_REG(3, 3, 14, 9, 4), + ARM64_SYS_REG(3, 3, 14, 9, 5), + ARM64_SYS_REG(3, 3, 14, 9, 6), + ARM64_SYS_REG(3, 3, 14, 9, 7), + ARM64_SYS_REG(3, 3, 14, 10, 0), + ARM64_SYS_REG(3, 3, 14, 10, 1), + ARM64_SYS_REG(3, 3, 14, 10, 2), + ARM64_SYS_REG(3, 3, 14, 10, 3), + ARM64_SYS_REG(3, 3, 14, 10, 4), + ARM64_SYS_REG(3, 3, 14, 10, 5), + ARM64_SYS_REG(3, 3, 14, 10, 6), + ARM64_SYS_REG(3, 3, 14, 10, 7), + ARM64_SYS_REG(3, 3, 14, 11, 0), + ARM64_SYS_REG(3, 3, 14, 11, 1), + ARM64_SYS_REG(3, 3, 14, 11, 2), + ARM64_SYS_REG(3, 3, 14, 11, 3), + ARM64_SYS_REG(3, 3, 14, 11, 4), + ARM64_SYS_REG(3, 3, 14, 11, 5), + ARM64_SYS_REG(3, 3, 14, 11, 6), + ARM64_SYS_REG(3, 3, 14, 12, 0), + ARM64_SYS_REG(3, 3, 14, 12, 1), + ARM64_SYS_REG(3, 3, 14, 12, 2), + ARM64_SYS_REG(3, 3, 14, 12, 3), + ARM64_SYS_REG(3, 3, 14, 12, 4), + ARM64_SYS_REG(3, 3, 14, 12, 5), + ARM64_SYS_REG(3, 3, 14, 12, 6), + ARM64_SYS_REG(3, 3, 14, 12, 7), + ARM64_SYS_REG(3, 3, 14, 13, 0), + ARM64_SYS_REG(3, 3, 14, 13, 1), + ARM64_SYS_REG(3, 3, 14, 13, 2), + ARM64_SYS_REG(3, 3, 14, 13, 3), + ARM64_SYS_REG(3, 3, 14, 13, 4), + ARM64_SYS_REG(3, 3, 14, 13, 5), + ARM64_SYS_REG(3, 3, 14, 13, 6), + ARM64_SYS_REG(3, 3, 14, 13, 7), + ARM64_SYS_REG(3, 3, 14, 14, 0), + ARM64_SYS_REG(3, 3, 14, 14, 1), + ARM64_SYS_REG(3, 3, 14, 14, 2), + ARM64_SYS_REG(3, 3, 14, 14, 3), + ARM64_SYS_REG(3, 3, 14, 14, 4), + ARM64_SYS_REG(3, 3, 14, 14, 5), + ARM64_SYS_REG(3, 3, 14, 14, 6), + ARM64_SYS_REG(3, 3, 14, 14, 7), + ARM64_SYS_REG(3, 3, 14, 15, 0), + ARM64_SYS_REG(3, 3, 14, 15, 1), + ARM64_SYS_REG(3, 3, 14, 15, 2), + ARM64_SYS_REG(3, 3, 14, 15, 3), + ARM64_SYS_REG(3, 3, 14, 15, 4), + ARM64_SYS_REG(3, 3, 14, 15, 5), + ARM64_SYS_REG(3, 3, 14, 15, 6), + ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */ + ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, +}; +static __u64 base_regs_n = ARRAY_SIZE(base_regs); + +static __u64 vregs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]), +}; +static __u64 vregs_n = ARRAY_SIZE(vregs); + +static __u64 sve_regs[] = { + KVM_REG_ARM64_SVE_VLS, + KVM_REG_ARM64_SVE_ZREG(0, 0), + KVM_REG_ARM64_SVE_ZREG(1, 0), + KVM_REG_ARM64_SVE_ZREG(2, 0), + KVM_REG_ARM64_SVE_ZREG(3, 0), + KVM_REG_ARM64_SVE_ZREG(4, 0), + KVM_REG_ARM64_SVE_ZREG(5, 0), + KVM_REG_ARM64_SVE_ZREG(6, 0), + KVM_REG_ARM64_SVE_ZREG(7, 0), + KVM_REG_ARM64_SVE_ZREG(8, 0), + KVM_REG_ARM64_SVE_ZREG(9, 0), + KVM_REG_ARM64_SVE_ZREG(10, 0), + KVM_REG_ARM64_SVE_ZREG(11, 0), + KVM_REG_ARM64_SVE_ZREG(12, 0), + KVM_REG_ARM64_SVE_ZREG(13, 0), + KVM_REG_ARM64_SVE_ZREG(14, 0), + KVM_REG_ARM64_SVE_ZREG(15, 0), + KVM_REG_ARM64_SVE_ZREG(16, 0), + KVM_REG_ARM64_SVE_ZREG(17, 0), + KVM_REG_ARM64_SVE_ZREG(18, 0), + KVM_REG_ARM64_SVE_ZREG(19, 0), + KVM_REG_ARM64_SVE_ZREG(20, 0), + KVM_REG_ARM64_SVE_ZREG(21, 0), + KVM_REG_ARM64_SVE_ZREG(22, 0), + KVM_REG_ARM64_SVE_ZREG(23, 0), + KVM_REG_ARM64_SVE_ZREG(24, 0), + KVM_REG_ARM64_SVE_ZREG(25, 0), + KVM_REG_ARM64_SVE_ZREG(26, 0), + KVM_REG_ARM64_SVE_ZREG(27, 0), + KVM_REG_ARM64_SVE_ZREG(28, 0), + KVM_REG_ARM64_SVE_ZREG(29, 0), + KVM_REG_ARM64_SVE_ZREG(30, 0), + KVM_REG_ARM64_SVE_ZREG(31, 0), + KVM_REG_ARM64_SVE_PREG(0, 0), + KVM_REG_ARM64_SVE_PREG(1, 0), + KVM_REG_ARM64_SVE_PREG(2, 0), + KVM_REG_ARM64_SVE_PREG(3, 0), + KVM_REG_ARM64_SVE_PREG(4, 0), + KVM_REG_ARM64_SVE_PREG(5, 0), + KVM_REG_ARM64_SVE_PREG(6, 0), + KVM_REG_ARM64_SVE_PREG(7, 0), + KVM_REG_ARM64_SVE_PREG(8, 0), + KVM_REG_ARM64_SVE_PREG(9, 0), + KVM_REG_ARM64_SVE_PREG(10, 0), + KVM_REG_ARM64_SVE_PREG(11, 0), + KVM_REG_ARM64_SVE_PREG(12, 0), + KVM_REG_ARM64_SVE_PREG(13, 0), + KVM_REG_ARM64_SVE_PREG(14, 0), + KVM_REG_ARM64_SVE_PREG(15, 0), + KVM_REG_ARM64_SVE_FFR(0), + ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */ +}; +static __u64 sve_regs_n = ARRAY_SIZE(sve_regs); + +static __u64 rejects_set[] = { +#ifdef REG_LIST_SVE + KVM_REG_ARM64_SVE_VLS, +#endif +}; +static __u64 rejects_set_n = ARRAY_SIZE(rejects_set); diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c deleted file mode 100644 index 11672ec6f74e..000000000000 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ /dev/null @@ -1,6 +0,0 @@ -#define USE_CLEAR_DIRTY_LOG -#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) -#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ - KVM_DIRTY_LOG_INITIALLY_SET) -#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 360cd3ea4cd6..3d96a7bfaff3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -21,20 +21,12 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "test_util.h" -#include "kvm_util.h" +#include "perf_test_util.h" #include "processor.h" +#include "test_util.h" #ifdef __NR_userfaultfd -/* The memory slot index demand page */ -#define TEST_MEM_SLOT_INDEX 1 - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ - #ifdef PRINT_PER_PAGE_UPDATES #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) #else @@ -47,77 +39,17 @@ #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) #endif -#define MAX_VCPUS 512 - -/* - * Guest/Host shared variables. Ensure addr_gva2hva() and/or - * sync_global_to/from_guest() are used when accessing from - * the host. READ/WRITE_ONCE() should also be used with anything - * that may change. - */ -static uint64_t host_page_size; -static uint64_t guest_page_size; - static char *guest_data_prototype; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -static uint64_t guest_test_phys_mem; - -/* - * Guest virtual memory offset of the testing memory slot. - * Must not conflict with identity mapped test code. - */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; - -struct vcpu_args { - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; - struct kvm_vm *vm; -}; - -static struct vcpu_args vcpu_args[MAX_VCPUS]; - -/* - * Continuously write to the first 8 bytes of each page in the demand paging - * memory region. - */ -static void guest_code(uint32_t vcpu_id) -{ - uint64_t gva; - uint64_t pages; - int i; - - /* Make sure vCPU args data structure is not corrupt. */ - GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); - - gva = vcpu_args[vcpu_id].gva; - pages = vcpu_args[vcpu_id].pages; - - for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * guest_page_size); - - addr &= ~(host_page_size - 1); - *(uint64_t *)addr = 0x0123456789ABCDEF; - } - - GUEST_SYNC(1); -} - static void *vcpu_worker(void *data) { int ret; - struct vcpu_args *args = (struct vcpu_args *)data; - struct kvm_vm *vm = args->vm; - int vcpu_id = args->vcpu_id; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; vcpu_args_set(vm, vcpu_id, 1, vcpu_id); run = vcpu_state(vm, vcpu_id); @@ -133,52 +65,18 @@ static void *vcpu_worker(void *data) exit_reason_str(run->exit_reason)); } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); return NULL; } -#define PAGE_SHIFT_4K 12 -#define PTES_PER_4K_PT 512 - -static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, - uint64_t vcpu_memory_bytes) -{ - struct kvm_vm *vm; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES; - - /* Account for a few pages per-vCPU for stacks */ - pages += DEFAULT_STACK_PGS * vcpus; - - /* - * Reserve twice the ammount of memory needed to map the test region and - * the page table / stacks region, at 4k, for page tables. Do the - * calculation with 4K page size: the smallest of all archs. (e.g., 64K - * page size guest will need even less memory for page tables). - */ - pages += (2 * pages) / PTES_PER_4K_PT; - pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / - PTES_PER_4K_PT; - pages = vm_adjust_num_guest_pages(mode, pages); - - pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - - vm = _vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - return vm; -} - static int handle_uffd_page_request(int uffd, uint64_t addr) { pid_t tid; struct timespec start; - struct timespec end; + struct timespec ts_diff; struct uffdio_copy copy; int r; @@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) copy.src = (uint64_t)guest_data_prototype; copy.dst = addr; - copy.len = host_page_size; + copy.len = perf_test_args.host_page_size; copy.mode = 0; clock_gettime(CLOCK_MONOTONIC, &start); @@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) return r; } - clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_diff_now(start); PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, - timespec_to_ns(timespec_sub(end, start))); + timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - host_page_size, addr, tid); + perf_test_args.host_page_size, addr, tid); return 0; } @@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg) int pipefd = uffd_args->pipefd; useconds_t delay = uffd_args->delay; int64_t pages = 0; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; clock_gettime(CLOCK_MONOTONIC, &start); while (!quit_uffd_thread) { @@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg) pages++; } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", pages, ts_diff.tv_sec, ts_diff.tv_nsec, pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); @@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm, } static void run_test(enum vm_guest_mode mode, bool use_uffd, - useconds_t uffd_delay, int vcpus, - uint64_t vcpu_memory_bytes) + useconds_t uffd_delay) { pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - uint64_t guest_num_pages; int vcpu_id; int r; - vm = create_vm(mode, vcpus, vcpu_memory_bytes); - - guest_page_size = vm_get_page_size(vm); - - TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, - "Guest memory size is not guest page size aligned."); - - guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; - guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); - - /* - * If there should be more memory in the guest test region than there - * can be pages in the guest, it will definitely cause problems. - */ - TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), - "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", - guest_num_pages, vm_get_max_gfn(vm), vcpus, - vcpu_memory_bytes); - - host_page_size = getpagesize(); - TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, - "Guest memory size is not host page size aligned."); + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + perf_test_args.wr_fract = 1; -#ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); -#endif - - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); - - /* Add an extra memory slot for testing demand paging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - guest_test_phys_mem, - TEST_MEM_SLOT_INDEX, - guest_num_pages, 0); - - /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); - - ucall_init(vm, NULL); - - guest_data_prototype = malloc(host_page_size); + guest_data_prototype = malloc(perf_test_args.host_page_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, host_page_size); + memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); - vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + if (use_uffd) { uffd_handler_threads = - malloc(vcpus * sizeof(*uffd_handler_threads)); + malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); - uffd_args = malloc(vcpus * sizeof(*uffd_args)); + uffd_args = malloc(nr_vcpus * sizeof(*uffd_args)); TEST_ASSERT(uffd_args, "Memory allocation failed"); - pipefds = malloc(sizeof(int) * vcpus * 2); + pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - } - - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; - void *vcpu_hva; - vm_vcpu_add_default(vm, vcpu_id, guest_code); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; - vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size); - /* Cache the HVA pointer of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - if (use_uffd) { /* * Set up user fault fd to handle demand paging * requests. @@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, &uffd_handler_threads[vcpu_id], pipefds[vcpu_id * 2], uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_memory_bytes); + vcpu_hva, guest_percpu_mem_size); if (r < 0) exit(-r); } - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - - vcpu_args[vcpu_id].vm = vm; - vcpu_args[vcpu_id].vcpu_id = vcpu_id; - vcpu_args[vcpu_id].gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; } /* Export the shared variables to the guest */ - sync_global_to_guest(vm, host_page_size); - sync_global_to_guest(vm, guest_page_size); - sync_global_to_guest(vm, vcpu_args); + sync_global_to_guest(vm, perf_test_args); pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &vcpu_args[vcpu_id]); + &perf_test_args.vcpu_args[vcpu_id]); } pr_info("Started all vCPUs\n"); /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_join(vcpu_threads[vcpu_id], NULL); PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); } - pr_info("All vCPU threads joined\n"); + ts_diff = timespec_diff_now(start); - clock_gettime(CLOCK_MONOTONIC, &end); + pr_info("All vCPU threads joined\n"); if (use_uffd) { char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { r = write(pipefds[vcpu_id * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); @@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, } } - ts_diff = timespec_sub(end, start); pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + perf_test_args.vcpu_args[0].pages * nr_vcpus / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); ucall_uninit(vm); kvm_vm_free(vm); @@ -568,9 +409,8 @@ static void help(char *name) int main(int argc, char *argv[]) { + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); bool mode_selected = false; - uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; - int vcpus = 1; unsigned int mode; int opt, i; bool use_uffd = false; @@ -619,15 +459,12 @@ int main(int argc, char *argv[]) "A negative UFFD delay is not supported."); break; case 'b': - vcpu_memory_bytes = parse_size(optarg); + guest_percpu_mem_size = parse_size(optarg); break; case 'v': - vcpus = atoi(optarg); - TEST_ASSERT(vcpus > 0, - "Must have a positive number of vCPUs"); - TEST_ASSERT(vcpus <= MAX_VCPUS, - "This test does not currently support\n" - "more than %d vCPUs.", MAX_VCPUS); + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'h': default: @@ -642,7 +479,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + run_test(i, use_uffd, uffd_delay); } return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c new file mode 100644 index 000000000000..85c9b8f73142 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging performance test + * + * Based on dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2020, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "kvm_util.h" +#include "perf_test_util.h" +#include "processor.h" +#include "test_util.h" + +/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ +#define TEST_HOST_LOOP_N 2UL + +/* Host variables */ +static bool host_quit; +static uint64_t iteration; +static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = perf_test_args.vm; + uint64_t pages_count = 0; + struct kvm_run *run; + struct timespec start; + struct timespec ts_diff; + struct timespec total = (struct timespec){0}; + struct timespec avg; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + while (!READ_ONCE(host_quit)) { + uint64_t current_iteration = READ_ONCE(iteration); + + clock_gettime(CLOCK_MONOTONIC, &start); + ret = _vcpu_run(vm, vcpu_id); + ts_diff = timespec_diff_now(start); + + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + + pr_debug("Got sync event from vCPU %d\n", vcpu_id); + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + pr_debug("vCPU %d updated last completed iteration to %lu\n", + vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + + if (current_iteration) { + pages_count += vcpu_args->pages; + total = timespec_add(total, ts_diff); + pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } else { + pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } + + while (current_iteration == READ_ONCE(iteration) && + !READ_ONCE(host_quit)) {} + } + + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], + total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); + + return NULL; +} + +#ifdef USE_CLEAR_DIRTY_LOG +static u64 dirty_log_manual_caps; +#endif + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + uint64_t phys_offset, int wr_fract) +{ + pthread_t *vcpu_threads; + struct kvm_vm *vm; + unsigned long *bmap; + uint64_t guest_num_pages; + uint64_t host_num_pages; + int vcpu_id; + struct timespec start; + struct timespec ts_diff; + struct timespec get_dirty_log_total = (struct timespec){0}; + struct timespec vcpu_dirty_total = (struct timespec){0}; + struct timespec avg; +#ifdef USE_CLEAR_DIRTY_LOG + struct kvm_enable_cap cap = {}; + struct timespec clear_dirty_log_total = (struct timespec){0}; +#endif + + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); + + perf_test_args.wr_fract = wr_fract; + + 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_alloc(host_num_pages); + +#ifdef USE_CLEAR_DIRTY_LOG + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); +#endif + + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + + sync_global_to_guest(vm, perf_test_args); + + /* Start the iterations */ + iteration = 0; + host_quit = false; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &perf_test_args.vcpu_args[vcpu_id]); + } + + /* Allow the vCPU to populate memory */ + pr_debug("Starting iteration %lu - Populating\n", iteration); + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n", + iteration); + + ts_diff = timespec_diff_now(start); + pr_info("Populate memory time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + /* Enable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, + KVM_MEM_LOG_DIRTY_PAGES); + ts_diff = timespec_diff_now(start); + pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + while (iteration < iterations) { + /* + * Incrementing the iteration number will start the vCPUs + * dirtying memory again. + */ + clock_gettime(CLOCK_MONOTONIC, &start); + iteration++; + + pr_debug("Starting iteration %lu\n", iteration); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n", + vcpu_id, iteration); + } + + ts_diff = timespec_diff_now(start); + vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff); + pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + ts_diff = timespec_diff_now(start); + get_dirty_log_total = timespec_add(get_dirty_log_total, + ts_diff); + pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); + + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); +#endif + } + + /* Tell the vcpu thread to quit */ + host_quit = true; + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id], NULL); + + /* Disable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0); + ts_diff = timespec_diff_now(start); + pr_info("Disabling dirty logging time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + avg = timespec_div(get_dirty_log_total, iterations); + pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, get_dirty_log_total.tv_sec, + get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); +#endif + + free(bmap); + free(vcpu_threads); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-p offset] " + "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -p: specify guest physical test memory offset\n" + " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -f: specify the fraction of pages which should be written to\n" + " as opposed to simply read, in the form\n" + " 1/<fraction of pages to write>.\n" + " (default: 1 i.e. all pages are written to.)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + bool mode_selected = false; + uint64_t phys_offset = 0; + unsigned int mode; + int opt, i; + int wr_fract = 1; + +#ifdef USE_CLEAR_DIRTY_LOG + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + if (!dirty_log_manual_caps) { + print_skip("KVM_CLEAR_DIRTY_LOG not available"); + exit(KSFT_SKIP); + } + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); +#endif + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'p': + phys_offset = strtoull(optarg, NULL, 0); + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'f': + wr_fract = atoi(optarg); + TEST_ASSERT(wr_fract >= 1, + "Write fraction cannot be less than one"); + break; + case 'v': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(nr_vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations >= 2, "The test should have at least two iterations"); + + pr_info("Test iterations: %"PRIu64"\n", iterations); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, iterations, phys_offset, wr_fract); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 752ec158ac59..54da9cc20db4 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -128,6 +128,78 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +enum log_mode_t { + /* Only use KVM_GET_DIRTY_LOG for logging */ + LOG_MODE_DIRTY_LOG = 0, + + /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ + LOG_MODE_CLEAR_LOG = 1, + + LOG_MODE_NUM, + + /* Run all supported modes */ + LOG_MODE_ALL = LOG_MODE_NUM, +}; + +/* Mode of logging to test. Default is to run all supported modes */ +static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; +/* Logging mode for current run */ +static enum log_mode_t host_log_mode; + +static bool clear_log_supported(void) +{ + return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); +} + +static void clear_log_create_vm_done(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = {}; + u64 manual_caps; + + manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!"); + manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = manual_caps; + vm_enable_cap(vm, &cap); +} + +static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); +} + +static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); +} + +struct log_mode { + const char *name; + /* Return true if this mode is supported, otherwise false */ + bool (*supported)(void); + /* Hook when the vm creation is done (before vcpu creation) */ + void (*create_vm_done)(struct kvm_vm *vm); + /* Hook to collect the dirty pages into the bitmap provided */ + void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages); +} log_modes[LOG_MODE_NUM] = { + { + .name = "dirty-log", + .collect_dirty_pages = dirty_log_collect_dirty_pages, + }, + { + .name = "clear-log", + .supported = clear_log_supported, + .create_vm_done = clear_log_create_vm_done, + .collect_dirty_pages = clear_log_collect_dirty_pages, + }, +}; + /* * We use this bitmap to track some pages that should have its dirty * bit set in the _next_ iteration. For example, if we detected the @@ -137,6 +209,44 @@ static uint64_t host_track_next_count; */ static unsigned long *host_bmap_track; +static void log_modes_dump(void) +{ + int i; + + printf("all"); + for (i = 0; i < LOG_MODE_NUM; i++) + printf(", %s", log_modes[i].name); + printf("\n"); +} + +static bool log_mode_supported(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->supported) + return mode->supported(); + + return true; +} + +static void log_mode_create_vm_done(struct kvm_vm *vm) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->create_vm_done) + mode->create_vm_done(vm); +} + +static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + TEST_ASSERT(mode->collect_dirty_pages != NULL, + "collect_dirty_pages() is required for any log mode!"); + mode->collect_dirty_pages(vm, slot, bitmap, num_pages); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) page); } - if (test_bit_le(page, bmap)) { + if (test_and_clear_bit_le(page, bmap)) { host_dirty_count++; /* * If the bit is set, the value written onto @@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); #ifdef __x86_64__ vm_create_irqchip(vm); #endif + log_mode_create_vm_done(vm); vm_vcpu_add_default(vm, vcpuid, guest_code); return vm; } @@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { @@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct kvm_vm *vm; unsigned long *bmap; + if (!log_mode_supported()) { + print_skip("Log mode '%s' not supported", + log_modes[host_log_mode].name); + return; + } + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif - /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_phys_mem, @@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, while (iteration < iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); -#ifdef USE_CLEAR_DIRTY_LOG - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); -#endif + log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + bmap, host_num_pages); vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -410,6 +512,9 @@ static void help(char *name) TEST_HOST_LOOP_INTERVAL); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -M: specify the host logging mode " + "(default: run all log modes). Supported modes: \n\t"); + log_modes_dump(); printf(" -m: specify the guest mode ID to test " "(default: test all supported modes)\n" " This option may be used multiple times.\n" @@ -429,18 +534,7 @@ int main(int argc, char *argv[]) bool mode_selected = false; uint64_t phys_offset = 0; unsigned int mode; - int opt, i; - -#ifdef USE_CLEAR_DIRTY_LOG - dirty_log_manual_caps = - kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); -#endif + int opt, i, j; #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); @@ -464,7 +558,7 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) { switch (opt) { case 'i': iterations = strtol(optarg, NULL, 10); @@ -486,6 +580,26 @@ int main(int argc, char *argv[]) "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; break; + case 'M': + if (!strcmp(optarg, "all")) { + host_log_mode_option = LOG_MODE_ALL; + break; + } + for (i = 0; i < LOG_MODE_NUM; i++) { + if (!strcmp(optarg, log_modes[i].name)) { + pr_info("Setting log mode to: '%s'\n", + optarg); + host_log_mode_option = i; + break; + } + } + if (i == LOG_MODE_NUM) { + printf("Log mode '%s' invalid. Please choose " + "from: ", optarg); + log_modes_dump(); + exit(1); + } + break; case 'h': default: help(argv[0]); @@ -507,7 +621,18 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, iterations, interval, phys_offset); + if (host_log_mode_option == LOG_MODE_ALL) { + /* Run each log mode */ + for (j = 0; j < LOG_MODE_NUM; j++) { + pr_info("Testing Log Mode '%s'\n", + log_modes[j].name); + host_log_mode = j; + run_test(i, iterations, interval, phys_offset); + } + } else { + host_log_mode = host_log_mode_option; + run_test(i, iterations, interval, phys_offset); + } } return 0; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 919e161dd289..7d29aa786959 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -63,9 +63,11 @@ enum vm_mem_backing_src_type { int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); @@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); @@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ }) +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + /* Common ucalls */ enum { UCALL_NONE, diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h new file mode 100644 index 000000000000..2618052057b1 --- /dev/null +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/perf_test_util.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H +#define SELFTEST_KVM_PERF_TEST_UTIL_H + +#include "kvm_util.h" +#include "processor.h" + +#define MAX_VCPUS 512 + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static uint64_t guest_test_phys_mem; + +/* + * Guest virtual memory offset of the testing memory slot. + * Must not conflict with identity mapped test code. + */ +static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; + +/* Number of VCPUs for the test */ +static int nr_vcpus = 1; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; +}; + +struct perf_test_args { + struct kvm_vm *vm; + uint64_t host_page_size; + uint64_t guest_page_size; + int wr_fract; + + struct vcpu_args vcpu_args[MAX_VCPUS]; +}; + +static struct perf_test_args perf_test_args; + +/* + * Continuously write to the first 8 bytes of each page in the + * specified region. + */ +static void guest_code(uint32_t vcpu_id) +{ + struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); + + gva = vcpu_args->gva; + pages = vcpu_args->pages; + + while (true) { + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * perf_test_args.guest_page_size); + + if (i % perf_test_args.wr_fract == 0) + *(uint64_t *)addr = 0x0123456789ABCDEF; + else + READ_ONCE(*(uint64_t *)addr); + } + + GUEST_SYNC(1); + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + perf_test_args.vm = vm; + perf_test_args.guest_page_size = vm_get_page_size(vm); + perf_test_args.host_page_size = getpagesize(); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / + perf_test_args.guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), + "Requested more guest memory than address space allows.\n" + " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + guest_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + "Guest memory size is not host page size aligned."); + + guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + perf_test_args.guest_page_size; + guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, 0); + + /* Do mapping for the demand paging memory slot */ + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + + ucall_init(vm, NULL); + + return vm; +} + +static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) +{ + vm_paddr_t vcpu_gpa; + struct vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); +#endif + + vcpu_args->vcpu_id = vcpu_id; + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + perf_test_args.guest_page_size; + + vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + } +} + +#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 5eb01bf51b86..ffffa560436b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts); struct timespec timespec_add_ns(struct timespec ts, int64_t ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); +struct timespec timespec_diff_now(struct timespec start); +struct timespec timespec_div(struct timespec ts, int divisor); #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 82b7fe16a824..8e61340b3911 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,6 +36,8 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +#define UNEXPECTED_VECTOR_PORT 0xfff0u + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; @@ -59,7 +61,7 @@ struct gpr64_regs { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; @@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void) return idt; } +static inline void outl(uint16_t port, uint32_t value) +{ + __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void); uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +struct ex_regs { + uint64_t rax, rcx, rdx, rbx; + uint64_t rbp, rsi, rdi; + uint64_t r8, r9, r10, r11; + uint64_t r12, r13, r14, r15; + uint64_t vector; + uint64_t error_code; + uint64_t rip; + uint64_t cs; + uint64_t rflags; +}; + +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)); + +/* + * set_cpuid() - overwrites a matching cpuid entry with the provided value. + * matches based on ent->function && ent->index. returns true + * if a match was found and successfully overwritten. + * @cpuid: the kvm cpuid list to modify. + * @ent: cpuid entry to insert + */ +bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3); + /* * Basic CPU control in CR0 */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 2afa6618b396..d6c32c328e9a 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index c8e0ec20d3bf..2f37b90ee1a9 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { vm_vaddr_t gva; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 3327cebc1095..126c6727a6b0 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) return ret; } +/* VCPU Enable Capability + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - VCPU + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VCPU. + */ +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpu_id); + int r; + + TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + + r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" + " rc: %i, errno: %i", r, errno); + + return r; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * descriptor to control the created VM is created with the permissions * given by perm (e.g. O_RDWR). */ -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; @@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) -{ - return _vm_create(mode, phy_pages, perm); -} - /* * VM Restart * @@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); + + assert_on_unhandled_exception(vm, vcpuid); + return rc; } @@ -1261,6 +1287,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, } /* + * VM VCPU Get Reg List + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * + * Output Args: + * None + * + * Return: + * A pointer to an allocated struct kvm_reg_list + * + * Get the list of guest registers which are supported for + * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + */ +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); + reg_list->n = reg_list_n.n; + vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + return reg_list; +} + +/* * VM VCPU Regs Get * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 2ef446520748..f07d383d03a1 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -50,6 +50,8 @@ struct kvm_vm { vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index a88c5d665725..7349bb2e1a24 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index fd589dc9bfab..9d3b0f15249a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 689e97c27ee2..8e04c0b1608e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,10 +4,13 @@ * * Copyright (C) 2020, Google LLC. */ -#include <stdlib.h> + +#include <assert.h> #include <ctype.h> #include <limits.h> -#include <assert.h> +#include <stdlib.h> +#include <time.h> + #include "test_util.h" /* @@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) return timespec_add_ns((struct timespec){0}, ns1 - ns2); } +struct timespec timespec_diff_now(struct timespec start) +{ + struct timespec end; + + clock_gettime(CLOCK_MONOTONIC, &end); + return timespec_sub(end, start); +} + +struct timespec timespec_div(struct timespec ts, int divisor) +{ + int64_t ns = timespec_to_ns(ts) / divisor; + + return timespec_add_ns((struct timespec){0}, ns); +} + void print_skip(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S new file mode 100644 index 000000000000..aaf7bc7d2ce1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -0,0 +1,81 @@ +handle_exception: + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + + push %rdi + push %rsi + push %rbp + push %rbx + push %rdx + push %rcx + push %rax + mov %rsp, %rdi + + call route_exception + + pop %rax + pop %rcx + pop %rdx + pop %rbx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + /* Discard vector and error code. */ + add $16, %rsp + iretq + +/* + * Build the handle_exception wrappers which push the vector/error code on the + * stack and an array of pointers to those wrappers. + */ +.pushsection .rodata +.globl idt_handlers +idt_handlers: +.popsection + +.macro HANDLERS has_error from to + vector = \from + .rept \to - \from + 1 + .align 8 + + /* Fetch current address and append it to idt_handlers. */ + current_handler = . +.pushsection .rodata +.quad current_handler +.popsection + + .if ! \has_error + pushq $0 + .endif + pushq $vector + jmp handle_exception + vector = vector + 1 + .endr +.endm + +.global idt_handler_code +idt_handler_code: + HANDLERS has_error=0 from=0 to=7 + HANDLERS has_error=1 from=8 to=8 + HANDLERS has_error=0 from=9 to=9 + HANDLERS has_error=1 from=10 to=14 + HANDLERS has_error=0 from=15 to=16 + HANDLERS has_error=1 from=17 to=17 + HANDLERS has_error=0 from=18 to=255 + +.section .note.GNU-stack, "", %progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f6eb34eaa0d2..d10c5c05bdf0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -12,9 +12,18 @@ #include "../kvm_util_internal.h" #include "processor.h" +#ifndef NUM_INTERRUPTS +#define NUM_INTERRUPTS 256 +#endif + +#define DEFAULT_CODE_SELECTOR 0x8 +#define DEFAULT_DATA_SELECTOR 0x10 + /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +vm_vaddr_t exception_handlers; + /* Virtual translation table structure declarations */ struct pageMapL4Entry { uint64_t present:1; @@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g; @@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; @@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) *va_bits = (entry->eax >> 8) & 0xff; } } + +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +void kvm_exit_unexpected_vector(uint32_t value) +{ + outl(UNEXPECTED_VECTOR_PORT, value); +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; + } + + kvm_exit_unexpected_vector(regs->vector); +} + +void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + int i; + + vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); + vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, + DEFAULT_CODE_SELECTOR); +} + +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_sregs sregs; + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.base = vm->idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->gdt; + sregs.gdt.limit = getpagesize() - 1; + kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); + vcpu_sregs_set(vm, vcpuid, &sregs); + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ + if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO + && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT + && vcpu_state(vm, vcpuid)->io.size == 4) { + /* Grab pointer to io data */ + uint32_t *data = (void *)vcpu_state(vm, vcpuid) + + vcpu_state(vm, vcpuid)->io.data_offset; + + TEST_ASSERT(false, + "Unexpected vectored event in guest (vector:0x%x)", + *data); + } +} + +bool set_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *ent) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function != ent->function || cur->index != ent->index) + continue; + + memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2)); + return true; + } + + return false; +} + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3) +{ + uint64_t r; + + asm volatile("vmcall" + : "=a"(r) + : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + return r; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index da4d89ad5419..a3489973e290 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b3ece55a2da6..6f441dd9f33c 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -156,14 +156,23 @@ static void guest_code_move_memory_region(void) GUEST_SYNC(0); /* - * Spin until the memory region is moved to a misaligned address. This - * may or may not trigger MMIO, as the window where the memslot is - * invalid is quite small. + * Spin until the memory region starts getting moved to a + * misaligned address. + * Every region move may or may not trigger MMIO, as the + * window where the memslot is invalid is usually quite small. */ val = guest_spin_on_val(0); GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); - /* Spin until the memory region is realigned. */ + /* Spin until the misaligning memory region move completes. */ + val = guest_spin_on_val(MMIO_VAL); + GUEST_ASSERT_1(val == 1 || val == 0, val); + + /* Spin until the memory region starts to get re-aligned. */ + val = guest_spin_on_val(0); + GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); + + /* Spin until the re-aligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); GUEST_ASSERT_1(val == 1, val); diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c new file mode 100644 index 000000000000..b10a27485bad --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + const char *name; +}; + +#define TEST_MSR(msr) { .idx = msr, .name = #msr } +#define UCALL_PR_MSR 0xdeadbeef +#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr) + +/* + * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or + * written, as the KVM_CPUID_FEATURES leaf is cleared. + */ +static struct msr_data msrs_to_test[] = { + TEST_MSR(MSR_KVM_SYSTEM_TIME), + TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW), + TEST_MSR(MSR_KVM_WALL_CLOCK), + TEST_MSR(MSR_KVM_WALL_CLOCK_NEW), + TEST_MSR(MSR_KVM_ASYNC_PF_EN), + TEST_MSR(MSR_KVM_STEAL_TIME), + TEST_MSR(MSR_KVM_PV_EOI_EN), + TEST_MSR(MSR_KVM_POLL_CONTROL), + TEST_MSR(MSR_KVM_ASYNC_PF_INT), + TEST_MSR(MSR_KVM_ASYNC_PF_ACK), +}; + +static void test_msr(struct msr_data *msr) +{ + PR_MSR(msr); + do_rdmsr(msr->idx); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + nr_gp = 0; + do_wrmsr(msr->idx, 0); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + nr_gp = 0; +} + +struct hcall_data { + uint64_t nr; + const char *name; +}; + +#define TEST_HCALL(hc) { .nr = hc, .name = #hc } +#define UCALL_PR_HCALL 0xdeadc0de +#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc) + +/* + * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding + * features have been cleared in KVM_CPUID_FEATURES. + */ +static struct hcall_data hcalls_to_test[] = { + TEST_HCALL(KVM_HC_KICK_CPU), + TEST_HCALL(KVM_HC_SEND_IPI), + TEST_HCALL(KVM_HC_SCHED_YIELD), +}; + +static void test_hcall(struct hcall_data *hc) +{ + uint64_t r; + + PR_HCALL(hc); + r = kvm_hypercall(hc->nr, 0, 0, 0, 0); + GUEST_ASSERT(r == -KVM_ENOSYS); +} + +static void guest_main(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) { + test_msr(&msrs_to_test[i]); + } + + for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) { + test_hcall(&hcalls_to_test[i]); + } + + GUEST_DONE(); +} + +static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 ent = {0}; + + ent.function = KVM_CPUID_FEATURES; + TEST_ASSERT(set_cpuid(cpuid, &ent), + "failed to clear KVM_CPUID_FEATURES leaf"); +} + +static void pr_msr(struct ucall *uc) +{ + struct msr_data *msr = (struct msr_data *)uc->args[0]; + + pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx); +} + +static void pr_hcall(struct ucall *uc) +{ + struct hcall_data *hc = (struct hcall_data *)uc->args[0]; + + pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); +} + +static void handle_abort(struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], + __FILE__, uc->args[1]); +} + +#define VCPU_ID 0 + +static void enter_guest(struct kvm_vm *vm) +{ + struct kvm_run *run; + struct ucall uc; + int r; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_PR_MSR: + pr_msr(&uc); + break; + case UCALL_PR_HCALL: + pr_hcall(&uc); + break; + case UCALL_ABORT: + handle_abort(&uc); + return; + case UCALL_DONE: + return; + } + } +} + +int main(void) +{ + struct kvm_enable_cap cap = {0}; + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + + if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { + pr_info("will skip kvm paravirt restriction tests.\n"); + return 0; + } + + vm = vm_create_default(VCPU_ID, 0, guest_main); + + cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; + cap.args[0] = 1; + vcpu_enable_cap(vm, VCPU_ID, &cap); + + best = kvm_get_supported_cpuid(); + clear_kvm_cpuid_features(best); + vcpu_set_cpuid(vm, VCPU_ID, best); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + enter_guest(vm); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index fb5c55dd6df8..02b0b9ead40b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -256,6 +256,28 @@ setup_cmd_nsb() fi } +setup_cmd_nsc() +{ + local cmd="$*" + local rc + + run_cmd_nsc ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + # set sysctl values in NS-A set_sysctl() { @@ -471,6 +493,36 @@ setup() sleep 1 } +setup_lla_only() +{ + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} "-" "-" + create_ns ${NSB} "-" "-" + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV} "-" "-" \ + ${NSB} ${NSB_DEV} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} "-" "-" \ + ${NSC} ${NSC_DEV} "-" "-" + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV}) + + create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-" + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF} + + set +e + + sleep 1 +} + ################################################################################ # IPv4 @@ -3787,10 +3839,53 @@ use_case_br() setup_cmd_nsb ip li del vlan100 2>/dev/null } +# VRF only. +# ns-A device is connected to both ns-B and ns-C on a single VRF but only has +# LLA on the interfaces +use_case_ping_lla_multi() +{ + setup_lla_only + # only want reply from ns-A + setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B" + + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C" + + # cycle/flap the first ns-A interface + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip link set ${NSA_DEV} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C" + + # cycle/flap the second ns-A interface + setup_cmd ip link set ${NSA_DEV2} down + setup_cmd ip link set ${NSA_DEV2} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C" +} + use_cases() { log_section "Use cases" + log_subsection "Device enslaved to bridge" use_case_br + log_subsection "Ping LLA with multiple interfaces" + use_case_ping_lla_multi } ################################################################################ diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index db3d4a8b5a4c..76a24052f4b4 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -113,6 +113,9 @@ static void do_poll(int fd, int timeout_ms) interrupted = true; break; } + + /* no events and more time to wait, do poll again */ + continue; } if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 052b5a775dc2..b7d188fc87c7 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -42,6 +42,11 @@ int perf_event_enable(int fd); int perf_event_disable(int fd); int perf_event_reset(int fd); +struct perf_event_read { + __u64 nr; + __u64 l1d_misses; +}; + #if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30) #include <unistd.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index f795e06f5ae3..4257a1f156bb 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only rfi_flush +entry_flush diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index eadbbff50be6..f25e854fe370 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0+ -TEST_GEN_PROGS := rfi_flush spectre_v2 +TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2 top_srcdir = ../../../../.. CFLAGS += -I../../../../../usr/include @@ -11,3 +11,5 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c $(OUTPUT)/spectre_v2: CFLAGS += -m64 $(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S +$(OUTPUT)/rfi_flush: flush_utils.c +$(OUTPUT)/entry_flush: flush_utils.c diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c new file mode 100644 index 000000000000..78cf914fa321 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <malloc.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +int entry_flush_test(void) +{ + char *p; + int repetitions = 10; + int fd, passes = 0, iter, rc = 0; + struct perf_event_read v; + __u64 l1d_misses_total = 0; + unsigned long iterations = 100000, zero_size = 24 * 1024; + unsigned long l1d_misses_expected; + int rfi_flush_orig; + int entry_flush, entry_flush_orig; + + SKIP_IF(geteuid() != 0); + + // The PMU event we use only works on Power7 or later + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + perror("Unable to read powerpc/rfi_flush debugfs file"); + SKIP_IF(1); + } + + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + perror("Unable to read powerpc/entry_flush debugfs file"); + SKIP_IF(1); + } + + if (rfi_flush_orig != 0) { + if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + perror("error writing to powerpc/rfi_flush debugfs file"); + FAIL_IF(1); + } + } + + entry_flush = entry_flush_orig; + + fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); + FAIL_IF(fd < 0); + + p = (char *)memalign(zero_size, CACHELINE_SIZE); + + FAIL_IF(perf_event_enable(fd)); + + // disable L1 prefetching + set_dscr(1); + + iter = repetitions; + + /* + * We expect to see l1d miss for each cacheline access when entry_flush + * is set. Allow a small variation on this. + */ + l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2); + +again: + FAIL_IF(perf_event_reset(fd)); + + syscall_loop(p, iterations, zero_size); + + FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v)); + + if (entry_flush && v.l1d_misses >= l1d_misses_expected) + passes++; + else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2)) + passes++; + + l1d_misses_total += v.l1d_misses; + + while (--iter) + goto again; + + if (passes < repetitions) { + printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n", + entry_flush, l1d_misses_total, entry_flush ? '<' : '>', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + repetitions - passes, repetitions); + rc = 1; + } else { + printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n", + entry_flush, l1d_misses_total, entry_flush ? '>' : '<', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + passes, repetitions); + } + + if (entry_flush == entry_flush_orig) { + entry_flush = !entry_flush_orig; + if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + iter = repetitions; + l1d_misses_total = 0; + passes = 0; + goto again; + } + + perf_event_disable(fd); + close(fd); + + set_dscr(0); + + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + perror("unable to restore original value of powerpc/rfi_flush debugfs file"); + return 1; + } + + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush debugfs file"); + return 1; + } + + return rc; +} + +int main(int argc, char *argv[]) +{ + return test_harness(entry_flush_test, "entry_flush_test"); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.c b/tools/testing/selftests/powerpc/security/flush_utils.c new file mode 100644 index 000000000000..0c3c4c40c7fb --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +static inline __u64 load(void *addr) +{ + __u64 tmp; + + asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); + + return tmp; +} + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size) +{ + for (unsigned long i = 0; i < iterations; i++) { + for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) + load(p + j); + getppid(); + } +} + +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +void set_dscr(unsigned long val) +{ + static int init; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.h b/tools/testing/selftests/powerpc/security/flush_utils.h new file mode 100644 index 000000000000..07a5eb301466 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +/* + * Copyright 2018 IBM Corporation. + */ + +#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H +#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H + +#define CACHELINE_SIZE 128 + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size); + +void set_dscr(unsigned long val); + +#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */ diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 93a65bd1f231..7565fd786640 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -10,71 +10,12 @@ #include <stdint.h> #include <malloc.h> #include <unistd.h> -#include <signal.h> #include <stdlib.h> #include <string.h> #include <stdio.h> #include "utils.h" +#include "flush_utils.h" -#define CACHELINE_SIZE 128 - -struct perf_event_read { - __u64 nr; - __u64 l1d_misses; -}; - -static inline __u64 load(void *addr) -{ - __u64 tmp; - - asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); - - return tmp; -} - -static void syscall_loop(char *p, unsigned long iterations, - unsigned long zero_size) -{ - for (unsigned long i = 0; i < iterations; i++) { - for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) - load(p + j); - getppid(); - } -} - -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned = 0; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -static void set_dscr(unsigned long val) -{ - static int init = 0; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} int rfi_flush_test(void) { @@ -85,19 +26,33 @@ int rfi_flush_test(void) __u64 l1d_misses_total = 0; unsigned long iterations = 100000, zero_size = 24 * 1024; unsigned long l1d_misses_expected; - int rfi_flush_org, rfi_flush; + int rfi_flush_orig, rfi_flush; + int have_entry_flush, entry_flush_orig; SKIP_IF(geteuid() != 0); // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) { + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - rfi_flush = rfi_flush_org; + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + have_entry_flush = 0; + } else { + have_entry_flush = 1; + + if (entry_flush_orig != 0) { + if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + } + } + + rfi_flush = rfi_flush_orig; fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); FAIL_IF(fd < 0); @@ -106,6 +61,7 @@ int rfi_flush_test(void) FAIL_IF(perf_event_enable(fd)); + // disable L1 prefetching set_dscr(1); iter = repetitions; @@ -147,8 +103,8 @@ again: repetitions * l1d_misses_expected / 2, passes, repetitions); - if (rfi_flush == rfi_flush_org) { - rfi_flush = !rfi_flush_org; + if (rfi_flush == rfi_flush_orig) { + rfi_flush = !rfi_flush_orig; if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; @@ -164,11 +120,19 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) { + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } + if (have_entry_flush) { + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush " + "debugfs file"); + return 1; + } + } + return rc; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4a180439ee9e..26c72f2b61b1 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1758,10 +1758,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) * and the code is stored as a positive value. \ */ \ if (_result < 0) { \ - SYSCALL_RET(_regs) = -result; \ + SYSCALL_RET(_regs) = -_result; \ (_regs).ccr |= 0x10000000; \ } else { \ - SYSCALL_RET(_regs) = result; \ + SYSCALL_RET(_regs) = _result; \ (_regs).ccr &= ~0x10000000; \ } \ } while (0) @@ -1804,8 +1804,8 @@ TEST_F(TRACE_poke, getpid_runs_normally) #define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2] #elif defined(__sh__) # define ARCH_REGS struct pt_regs -# define SYSCALL_NUM(_regs) (_regs).gpr[3] -# define SYSCALL_RET(_regs) (_regs).gpr[0] +# define SYSCALL_NUM(_regs) (_regs).regs[3] +# define SYSCALL_RET(_regs) (_regs).regs[0] #else # error "Do not know how to find your architecture's registers and syscalls" #endif diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index c33a7aac27ff..b71828df5a6d 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -59,6 +59,7 @@ CONFIG_NET_IFE_SKBPRIO=m CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_RED=m # ## Network testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index bb543bf69d69..361235ad574b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -100,7 +100,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle", "matchCount": "1", "teardown": [ @@ -119,7 +119,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": " dst_mac e4:11:22:11:4a:51", "matchCount": "0", "teardown": [ diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 30873b19d04b..691893afc15d 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -60,9 +60,13 @@ ifeq ($(CAN_BUILD_X86_64),1) TEST_GEN_FILES += $(BINARIES_64) endif else + +ifneq (,$(findstring $(ARCH),powerpc)) TEST_GEN_FILES += protection_keys endif +endif + ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 9b0912a01777..c4425597769a 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -206,19 +206,19 @@ static int hugetlb_release_pages(char *rel_area) return ret; } - static void hugetlb_allocate_area(void **alloc_area) { void *area_alias = NULL; char **alloc_area_alias; + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, (map_shared ? MAP_SHARED : MAP_PRIVATE) | MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) { - fprintf(stderr, "mmap of hugetlbfs file failed\n"); - *alloc_area = NULL; + perror("mmap of hugetlbfs file failed"); + goto fail; } if (map_shared) { @@ -227,14 +227,11 @@ static void hugetlb_allocate_area(void **alloc_area) huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) { - if (munmap(*alloc_area, nr_pages * page_size) < 0) { - perror("hugetlb munmap"); - exit(1); - } - *alloc_area = NULL; - return; + perror("mmap of hugetlb file alias failed"); + goto fail_munmap; } } + if (*alloc_area == area_src) { huge_fd_off0 = *alloc_area; alloc_area_alias = &area_src_alias; @@ -243,6 +240,16 @@ static void hugetlb_allocate_area(void **alloc_area) } if (area_alias) *alloc_area_alias = area_alias; + + return; + +fail_munmap: + if (munmap(*alloc_area, nr_pages * page_size) < 0) { + perror("hugetlb munmap"); + exit(1); + } +fail: + *alloc_area = NULL; } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) |