diff options
Diffstat (limited to 'tools/testing/selftests')
206 files changed, 11159 insertions, 5535 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 5047d8eef53e..10b34bb03bc1 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -17,6 +17,7 @@ TARGETS += exec TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll +TARGETS += filesystems/fat TARGETS += firmware TARGETS += fpu TARGETS += ftrace diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index a33874b081b6..e89685bd587c 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -28,6 +28,7 @@ #include "bpf_iter_test_kern6.skel.h" #include "bpf_iter_bpf_link.skel.h" #include "bpf_iter_ksym.skel.h" +#include "bpf_iter_sockmap.skel.h" static int duration; @@ -67,6 +68,50 @@ free_link: bpf_link__destroy(link); } +static void do_read_map_iter_fd(struct bpf_object_skeleton **skel, struct bpf_program *prog, + struct bpf_map *map) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + union bpf_iter_link_info linfo; + struct bpf_link *link; + char buf[16] = {}; + int iter_fd, len; + + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = bpf_map__fd(map); + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); + link = bpf_program__attach_iter(prog, &opts); + if (!ASSERT_OK_PTR(link, "attach_map_iter")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "create_map_iter")) { + bpf_link__destroy(link); + return; + } + + /* Close link and map fd prematurely */ + bpf_link__destroy(link); + bpf_object__destroy_skeleton(*skel); + *skel = NULL; + + /* Try to let map free work to run first if map is freed */ + usleep(100); + /* Memory used by both sock map and sock local storage map are + * freed after two synchronize_rcu() calls, so wait for it + */ + kern_sync_rcu(); + kern_sync_rcu(); + + /* Read after both map fd and link fd are closed */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + ASSERT_GE(len, 0, "read_iterator"); + + close(iter_fd); +} + static int read_fd_into_buffer(int fd, char *buf, int size) { int bufleft = size; @@ -634,6 +679,12 @@ static void test_bpf_hash_map(void) goto out; } + /* Sleepable program is prohibited for hash map iterator */ + linfo.map.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.sleepable_dummy_dump, &opts); + if (!ASSERT_ERR_PTR(link, "attach_sleepable_prog_to_iter")) + goto out; + linfo.map.map_fd = map_fd; link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); if (!ASSERT_OK_PTR(link, "attach_iter")) @@ -827,6 +878,20 @@ out: bpf_iter_bpf_array_map__destroy(skel); } +static void test_bpf_array_map_iter_fd(void) +{ + struct bpf_iter_bpf_array_map *skel; + + skel = bpf_iter_bpf_array_map__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_array_map__open_and_load")) + return; + + do_read_map_iter_fd(&skel->skeleton, skel->progs.dump_bpf_array_map, + skel->maps.arraymap1); + + bpf_iter_bpf_array_map__destroy(skel); +} + static void test_bpf_percpu_array_map(void) { DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); @@ -1009,6 +1074,20 @@ out: bpf_iter_bpf_sk_storage_helpers__destroy(skel); } +static void test_bpf_sk_stoarge_map_iter_fd(void) +{ + struct bpf_iter_bpf_sk_storage_map *skel; + + skel = bpf_iter_bpf_sk_storage_map__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_sk_storage_map__open_and_load")) + return; + + do_read_map_iter_fd(&skel->skeleton, skel->progs.rw_bpf_sk_storage_map, + skel->maps.sk_stg_map); + + bpf_iter_bpf_sk_storage_map__destroy(skel); +} + static void test_bpf_sk_storage_map(void) { DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); @@ -1044,7 +1123,15 @@ static void test_bpf_sk_storage_map(void) linfo.map.map_fd = map_fd; opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); - link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts); + link = bpf_program__attach_iter(skel->progs.oob_write_bpf_sk_storage_map, &opts); + err = libbpf_get_error(link); + if (!ASSERT_EQ(err, -EACCES, "attach_oob_write_iter")) { + if (!err) + bpf_link__destroy(link); + goto out; + } + + link = bpf_program__attach_iter(skel->progs.rw_bpf_sk_storage_map, &opts); if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; @@ -1052,6 +1139,7 @@ static void test_bpf_sk_storage_map(void) if (!ASSERT_GE(iter_fd, 0, "create_iter")) goto free_link; + skel->bss->to_add_val = time(NULL); /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; @@ -1065,6 +1153,13 @@ static void test_bpf_sk_storage_map(void) if (!ASSERT_EQ(skel->bss->val_sum, expected_val, "val_sum")) goto close_iter; + for (i = 0; i < num_sockets; i++) { + err = bpf_map_lookup_elem(map_fd, &sock_fd[i], &val); + if (!ASSERT_OK(err, "map_lookup") || + !ASSERT_EQ(val, i + 1 + skel->bss->to_add_val, "check_map_value")) + break; + } + close_iter: close(iter_fd); free_link: @@ -1217,6 +1312,19 @@ out: bpf_iter_task_vma__destroy(skel); } +void test_bpf_sockmap_map_iter_fd(void) +{ + struct bpf_iter_sockmap *skel; + + skel = bpf_iter_sockmap__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_sockmap__open_and_load")) + return; + + do_read_map_iter_fd(&skel->skeleton, skel->progs.copy, skel->maps.sockmap); + + bpf_iter_sockmap__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -1267,10 +1375,14 @@ void test_bpf_iter(void) test_bpf_percpu_hash_map(); if (test__start_subtest("bpf_array_map")) test_bpf_array_map(); + if (test__start_subtest("bpf_array_map_iter_fd")) + test_bpf_array_map_iter_fd(); if (test__start_subtest("bpf_percpu_array_map")) test_bpf_percpu_array_map(); if (test__start_subtest("bpf_sk_storage_map")) test_bpf_sk_storage_map(); + if (test__start_subtest("bpf_sk_storage_map_iter_fd")) + test_bpf_sk_stoarge_map_iter_fd(); if (test__start_subtest("bpf_sk_storage_delete")) test_bpf_sk_storage_delete(); if (test__start_subtest("bpf_sk_storage_get")) @@ -1283,4 +1395,6 @@ void test_bpf_iter(void) test_link_iter(); if (test__start_subtest("ksym")) test_ksym_iter(); + if (test__start_subtest("bpf_sockmap_map_iter_fd")) + test_bpf_sockmap_map_iter_fd(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 02bb8cbf9194..da860b07abb5 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -3,6 +3,7 @@ #include <test_progs.h> #include <network_helpers.h> #include <bpf/btf.h> +#include "bind4_prog.skel.h" typedef int (*test_cb)(struct bpf_object *obj); @@ -407,6 +408,98 @@ static void test_func_replace_global_func(void) prog_name, false, NULL); } +static int find_prog_btf_id(const char *name, __u32 attach_prog_fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *btf; + int ret; + + ret = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); + if (ret) + return ret; + + if (!info.btf_id) + return -EINVAL; + + btf = btf__load_from_kernel_by_id(info.btf_id); + ret = libbpf_get_error(btf); + if (ret) + return ret; + + ret = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + btf__free(btf); + return ret; +} + +static int load_fentry(int attach_prog_fd, int attach_btf_id) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = BPF_TRACE_FENTRY, + .attach_prog_fd = attach_prog_fd, + .attach_btf_id = attach_btf_id, + ); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + return bpf_prog_load(BPF_PROG_TYPE_TRACING, + "bind4_fentry", + "GPL", + insns, + ARRAY_SIZE(insns), + &opts); +} + +static void test_fentry_to_cgroup_bpf(void) +{ + struct bind4_prog *skel = NULL; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int cgroup_fd = -1; + int fentry_fd = -1; + int btf_id; + + cgroup_fd = test__join_cgroup("/fentry_to_cgroup_bpf"); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + return; + + skel = bind4_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel")) + goto cleanup; + + skel->links.bind_v4_prog = bpf_program__attach_cgroup(skel->progs.bind_v4_prog, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.bind_v4_prog, "bpf_program__attach_cgroup")) + goto cleanup; + + btf_id = find_prog_btf_id("bind_v4_prog", bpf_program__fd(skel->progs.bind_v4_prog)); + if (!ASSERT_GE(btf_id, 0, "find_prog_btf_id")) + goto cleanup; + + fentry_fd = load_fentry(bpf_program__fd(skel->progs.bind_v4_prog), btf_id); + if (!ASSERT_GE(fentry_fd, 0, "load_fentry")) + goto cleanup; + + /* Make sure bpf_obj_get_info_by_fd works correctly when attaching + * to another BPF program. + */ + + ASSERT_OK(bpf_obj_get_info_by_fd(fentry_fd, &info, &info_len), + "bpf_obj_get_info_by_fd"); + + ASSERT_EQ(info.btf_id, 0, "info.btf_id"); + ASSERT_EQ(info.attach_btf_id, btf_id, "info.attach_btf_id"); + ASSERT_GT(info.attach_btf_obj_id, 0, "info.attach_btf_obj_id"); + +cleanup: + if (cgroup_fd >= 0) + close(cgroup_fd); + if (fentry_fd >= 0) + close(fentry_fd); + bind4_prog__destroy(skel); +} + /* NOTE: affect other tests, must run in serial mode */ void serial_test_fexit_bpf2bpf(void) { @@ -430,4 +523,6 @@ void serial_test_fexit_bpf2bpf(void) test_fmod_ret_freplace(); if (test__start_subtest("func_replace_global_func")) test_func_replace_global_func(); + if (test__start_subtest("fentry_to_cgroup_bpf")) + test_fentry_to_cgroup_bpf(); } diff --git a/tools/testing/selftests/bpf/prog_tests/lru_bug.c b/tools/testing/selftests/bpf/prog_tests/lru_bug.c new file mode 100644 index 000000000000..3c7822390827 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lru_bug.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +#include "lru_bug.skel.h" + +void test_lru_bug(void) +{ + struct lru_bug *skel; + int ret; + + skel = lru_bug__open_and_load(); + if (!ASSERT_OK_PTR(skel, "lru_bug__open_and_load")) + return; + ret = lru_bug__attach(skel); + if (!ASSERT_OK(ret, "lru_bug__attach")) + goto end; + usleep(1); + ASSERT_OK(skel->data->result, "prealloc_lru_pop doesn't call check_and_init_map_value"); +end: + lru_bug__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c index 0aa3cd34cbe3..d7a69217fb68 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -112,3 +112,12 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) return 0; } + +SEC("iter.s/bpf_map_elem") +int sleepable_dummy_dump(struct bpf_iter__bpf_map_elem *ctx) +{ + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(ctx->meta->seq, "map dump starts\n"); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c index 6b70ccaba301..c7b8e006b171 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c @@ -16,19 +16,37 @@ struct { __u32 val_sum = 0; __u32 ipv6_sk_count = 0; +__u32 to_add_val = 0; SEC("iter/bpf_sk_storage_map") -int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +int rw_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) { struct sock *sk = ctx->sk; __u32 *val = ctx->value; - if (sk == (void *)0 || val == (void *)0) + if (sk == NULL || val == NULL) return 0; if (sk->sk_family == AF_INET6) ipv6_sk_count++; val_sum += *val; + + *val += to_add_val; + + return 0; +} + +SEC("iter/bpf_sk_storage_map") +int oob_write_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + struct sock *sk = ctx->sk; + __u32 *val = ctx->value; + + if (sk == NULL || val == NULL) + return 0; + + *(val + 1) = 0xdeadbeef; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/lru_bug.c b/tools/testing/selftests/bpf/progs/lru_bug.c new file mode 100644 index 000000000000..687081a724b3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lru_bug.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_value { + struct task_struct __kptr *ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_value); +} lru_map SEC(".maps"); + +int pid = 0; +int result = 1; + +SEC("fentry/bpf_ktime_get_ns") +int printk(void *ctx) +{ + struct map_value v = {}; + + if (pid == bpf_get_current_task_btf()->pid) + bpf_map_update_elem(&lru_map, &(int){0}, &v, 0); + return 0; +} + +SEC("fentry/do_nanosleep") +int nanosleep(void *ctx) +{ + struct map_value val = {}, *v; + struct task_struct *current; + + bpf_map_update_elem(&lru_map, &(int){0}, &val, 0); + v = bpf_map_lookup_elem(&lru_map, &(int){0}); + if (!v) + return 0; + bpf_map_delete_elem(&lru_map, &(int){0}); + current = bpf_get_current_task_btf(); + v->ptr = current; + pid = current->pid; + bpf_ktime_get_ns(); + result = !v->ptr; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config index 02dd6cc9cf99..7b4fc6ee6205 100644 --- a/tools/testing/selftests/filesystems/binderfs/config +++ b/tools/testing/selftests/filesystems/binderfs/config @@ -1,3 +1,2 @@ -CONFIG_ANDROID=y CONFIG_ANDROID_BINDERFS=y CONFIG_ANDROID_BINDER_IPC=y diff --git a/tools/testing/selftests/filesystems/fat/.gitignore b/tools/testing/selftests/filesystems/fat/.gitignore new file mode 100644 index 000000000000..b89920ed841c --- /dev/null +++ b/tools/testing/selftests/filesystems/fat/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +rename_exchange diff --git a/tools/testing/selftests/filesystems/fat/Makefile b/tools/testing/selftests/filesystems/fat/Makefile new file mode 100644 index 000000000000..902033f6ef09 --- /dev/null +++ b/tools/testing/selftests/filesystems/fat/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_PROGS := run_fat_tests.sh +TEST_GEN_PROGS_EXTENDED := rename_exchange +CFLAGS += -O2 -g -Wall $(KHDR_INCLUDES) + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/fat/config b/tools/testing/selftests/filesystems/fat/config new file mode 100644 index 000000000000..6cf95e787a17 --- /dev/null +++ b/tools/testing/selftests/filesystems/fat/config @@ -0,0 +1,2 @@ +CONFIG_BLK_DEV_LOOP=y +CONFIG_VFAT_FS=y diff --git a/tools/testing/selftests/filesystems/fat/rename_exchange.c b/tools/testing/selftests/filesystems/fat/rename_exchange.c new file mode 100644 index 000000000000..e488ad354fce --- /dev/null +++ b/tools/testing/selftests/filesystems/fat/rename_exchange.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Program that atomically exchanges two paths using + * the renameat2() system call RENAME_EXCHANGE flag. + * + * Copyright 2022 Red Hat Inc. + * Author: Javier Martinez Canillas <javierm@redhat.com> + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> + +void print_usage(const char *program) +{ + printf("Usage: %s [oldpath] [newpath]\n", program); + printf("Atomically exchange oldpath and newpath\n"); +} + +int main(int argc, char *argv[]) +{ + int ret; + + if (argc != 3) { + print_usage(argv[0]); + exit(EXIT_FAILURE); + } + + ret = renameat2(AT_FDCWD, argv[1], AT_FDCWD, argv[2], RENAME_EXCHANGE); + if (ret) { + perror("rename exchange failed"); + exit(EXIT_FAILURE); + } + + exit(EXIT_SUCCESS); +} diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh new file mode 100644 index 000000000000..7f35dc3d15df --- /dev/null +++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh @@ -0,0 +1,82 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run filesystem operations tests on an 1 MiB disk image that is formatted with +# a vfat filesystem and mounted in a temporary directory using a loop device. +# +# Copyright 2022 Red Hat Inc. +# Author: Javier Martinez Canillas <javierm@redhat.com> + +set -e +set -u +set -o pipefail + +BASE_DIR="$(dirname $0)" +TMP_DIR="$(mktemp -d /tmp/fat_tests_tmp.XXXX)" +IMG_PATH="${TMP_DIR}/fat.img" +MNT_PATH="${TMP_DIR}/mnt" + +cleanup() +{ + mountpoint -q "${MNT_PATH}" && unmount_image + rm -rf "${TMP_DIR}" +} +trap cleanup SIGINT SIGTERM EXIT + +create_loopback() +{ + touch "${IMG_PATH}" + chattr +C "${IMG_PATH}" >/dev/null 2>&1 || true + + truncate -s 1M "${IMG_PATH}" + mkfs.vfat "${IMG_PATH}" >/dev/null 2>&1 +} + +mount_image() +{ + mkdir -p "${MNT_PATH}" + sudo mount -o loop "${IMG_PATH}" "${MNT_PATH}" +} + +rename_exchange_test() +{ + local rename_exchange="${BASE_DIR}/rename_exchange" + local old_path="${MNT_PATH}/old_file" + local new_path="${MNT_PATH}/new_file" + + echo old | sudo tee "${old_path}" >/dev/null 2>&1 + echo new | sudo tee "${new_path}" >/dev/null 2>&1 + sudo "${rename_exchange}" "${old_path}" "${new_path}" >/dev/null 2>&1 + sudo sync -f "${MNT_PATH}" + grep new "${old_path}" >/dev/null 2>&1 + grep old "${new_path}" >/dev/null 2>&1 +} + +rename_exchange_subdir_test() +{ + local rename_exchange="${BASE_DIR}/rename_exchange" + local dir_path="${MNT_PATH}/subdir" + local old_path="${MNT_PATH}/old_file" + local new_path="${dir_path}/new_file" + + sudo mkdir -p "${dir_path}" + echo old | sudo tee "${old_path}" >/dev/null 2>&1 + echo new | sudo tee "${new_path}" >/dev/null 2>&1 + sudo "${rename_exchange}" "${old_path}" "${new_path}" >/dev/null 2>&1 + sudo sync -f "${MNT_PATH}" + grep new "${old_path}" >/dev/null 2>&1 + grep old "${new_path}" >/dev/null 2>&1 +} + +unmount_image() +{ + sudo umount "${MNT_PATH}" &> /dev/null +} + +create_loopback +mount_image +rename_exchange_test +rename_exchange_subdir_test +unmount_image + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index 60c02b482be8..c300eb020262 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - add/remove eprobe events -# requires: dynamic_events events/syscalls/sys_enter_openat "e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events events/syscalls/sys_enter_openat "<attached-group>.<attached-event> [<args>]":README echo 0 > events/enable @@ -87,4 +87,11 @@ echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events ! grep -q "$EPROBE" dynamic_events ! test -d events/eprobes/$EPROBE +if grep -q "e\[:\[<group>/]\[<event>]]" README; then + echo "e:mygroup/ $SYSTEM/$EVENT $OPTIONS" >> dynamic_events + test -d events/mygroup + echo "-:mygroup/" >> dynamic_events + ! test -d events/mygroup +fi + clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc index b4da41d126d5..13d43f40a6fc 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc @@ -23,4 +23,11 @@ grep -q myevent1 dynamic_events echo > dynamic_events +if grep -q "p\[:\[<group>/]\[<event>]]" README; then + echo "p:mygroup/ $PLACE" >> dynamic_events + test -d events/mygroup + echo "-:mygroup/" >> dynamic_events + ! test -d events/mygroup +fi + clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc index fa928b431555..9e85d3019ff0 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc @@ -21,7 +21,7 @@ check_error 'p:^/bar vfs_read' # NO_GROUP_NAME check_error 'p:^12345678901234567890123456789012345678901234567890123456789012345/bar vfs_read' # GROUP_TOO_LONG check_error 'p:^foo.1/bar vfs_read' # BAD_GROUP_NAME -check_error 'p:foo/^ vfs_read' # NO_EVENT_NAME +check_error 'p:^ vfs_read' # NO_EVENT_NAME check_error 'p:foo/^12345678901234567890123456789012345678901234567890123456789012345 vfs_read' # EVENT_TOO_LONG check_error 'p:foo/^bar.1 vfs_read' # BAD_EVENT_NAME diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 4509a3a7eeae..d625a3f83780 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -25,8 +25,10 @@ /x86_64/hyperv_cpuid /x86_64/hyperv_features /x86_64/hyperv_svm_test +/x86_64/max_vcpuid_cap_test /x86_64/mmio_warning_test -/x86_64/mmu_role_test +/x86_64/monitor_mwait_test +/x86_64/nx_huge_pages_test /x86_64/platform_info_test /x86_64/pmu_event_filter_test /x86_64/set_boot_cpu_id @@ -36,9 +38,11 @@ /x86_64/state_test /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test -/x86_64/tsc_scaling_sync +/x86_64/svm_nested_soft_inject_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test +/x86_64/tsc_scaling_sync +/x86_64/ucna_injection_test /x86_64/userspace_io_test /x86_64/userspace_msr_exit_test /x86_64/vmx_apic_access_test @@ -46,6 +50,7 @@ /x86_64/vmx_dirty_log_test /x86_64/vmx_exception_with_invalid_guest_state /x86_64/vmx_invalid_nested_guest_state +/x86_64/vmx_msrs_test /x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test @@ -56,6 +61,7 @@ /x86_64/xen_vmcall_test /x86_64/xss_msr_test /x86_64/vmx_pmu_caps_test +/x86_64/triple_fault_event_test /access_tracking_perf_test /demand_paging_test /dirty_log_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 120951fc304a..4c122f1b1737 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -4,6 +4,8 @@ include ../../../build/Build.include all: top_srcdir = ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) # For cross-builds to work, UNAME_M has to map to ARCH and arch specific # directories and targets in this Makefile. "uname -m" doesn't map to @@ -69,6 +71,10 @@ LIBKVM_s390x += lib/s390x/ucall.c LIBKVM_riscv += lib/riscv/processor.c LIBKVM_riscv += lib/riscv/ucall.c +# Non-compiled test targets +TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh + +# Compiled test targets TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features @@ -82,7 +88,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test 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/mmu_role_test +TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id @@ -92,14 +98,17 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/ucna_injection_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state +TEST_GEN_PROGS_x86_64 += x86_64/vmx_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test @@ -114,6 +123,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test +TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test +TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test @@ -130,6 +141,9 @@ TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test TEST_GEN_PROGS_x86_64 += system_counter_offset_test +# Compiled outputs used by test targets +TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test + TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list @@ -169,7 +183,9 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test TEST_GEN_PROGS_riscv += kvm_binary_stats_test +TEST_PROGS += $(TEST_PROGS_$(UNAME_M)) TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr @@ -183,7 +199,8 @@ endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) + -I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \ + $(KHDR_INCLUDES) no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) @@ -192,7 +209,7 @@ no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) - +LDLIBS += -ldl LDFLAGS += -pthread $(no-pie-option) $(pgste-option) # After inclusion, $(OUTPUT) is defined and @@ -216,6 +233,7 @@ $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) $(TEST_GEN_PROGS): $(LIBKVM_OBJS) +$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. cscope: diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 3b940a101bc0..574eb73f0e90 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -76,13 +76,8 @@ struct test_vcpu_shared_data { uint64_t xcnt; }; -struct test_vcpu { - uint32_t vcpuid; - pthread_t pt_vcpu_run; - struct kvm_vm *vm; -}; - -static struct test_vcpu test_vcpu[KVM_MAX_VCPUS]; +static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; +static pthread_t pt_vcpu_run[KVM_MAX_VCPUS]; static struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS]; static int vtimer_irq, ptimer_irq; @@ -217,29 +212,32 @@ static void guest_code(void) static void *test_vcpu_run(void *arg) { + unsigned int vcpu_idx = (unsigned long)arg; struct ucall uc; - struct test_vcpu *vcpu = arg; + struct kvm_vcpu *vcpu = vcpus[vcpu_idx]; struct kvm_vm *vm = vcpu->vm; - uint32_t vcpuid = vcpu->vcpuid; - struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpuid]; + struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpu_idx]; - vcpu_run(vm, vcpuid); + vcpu_run(vcpu); /* Currently, any exit from guest is an indication of completion */ pthread_mutex_lock(&vcpu_done_map_lock); - set_bit(vcpuid, vcpu_done_map); + set_bit(vcpu_idx, vcpu_done_map); pthread_mutex_unlock(&vcpu_done_map_lock); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: case UCALL_DONE: break; case UCALL_ABORT: sync_global_from_guest(vm, *shared_data); - TEST_FAIL("%s at %s:%ld\n\tvalues: %lu, %lu; %lu, vcpu: %u; stage: %u; iter: %u", - (const char *)uc.args[0], __FILE__, uc.args[1], - uc.args[2], uc.args[3], uc.args[4], vcpuid, - shared_data->guest_stage, shared_data->nr_iter); + REPORT_GUEST_ASSERT_N(uc, "values: %lu, %lu; %lu, vcpu %u; stage; %u; iter: %u", + GUEST_ASSERT_ARG(uc, 0), + GUEST_ASSERT_ARG(uc, 1), + GUEST_ASSERT_ARG(uc, 2), + vcpu_idx, + shared_data->guest_stage, + shared_data->nr_iter); break; default: TEST_FAIL("Unexpected guest exit\n"); @@ -265,7 +263,7 @@ static uint32_t test_get_pcpu(void) return pcpu; } -static int test_migrate_vcpu(struct test_vcpu *vcpu) +static int test_migrate_vcpu(unsigned int vcpu_idx) { int ret; cpu_set_t cpuset; @@ -274,15 +272,15 @@ static int test_migrate_vcpu(struct test_vcpu *vcpu) CPU_ZERO(&cpuset); CPU_SET(new_pcpu, &cpuset); - pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu->vcpuid, new_pcpu); + pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); - ret = pthread_setaffinity_np(vcpu->pt_vcpu_run, - sizeof(cpuset), &cpuset); + ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx], + sizeof(cpuset), &cpuset); /* Allow the error where the vCPU thread is already finished */ TEST_ASSERT(ret == 0 || ret == ESRCH, - "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n", - vcpu->vcpuid, new_pcpu, ret); + "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n", + vcpu_idx, new_pcpu, ret); return ret; } @@ -305,7 +303,7 @@ static void *test_vcpu_migration(void *arg) continue; } - test_migrate_vcpu(&test_vcpu[i]); + test_migrate_vcpu(i); } } while (test_args.nr_vcpus != n_done); @@ -314,16 +312,17 @@ static void *test_vcpu_migration(void *arg) static void test_run(struct kvm_vm *vm) { - int i, ret; pthread_t pt_vcpu_migration; + unsigned int i; + int ret; pthread_mutex_init(&vcpu_done_map_lock, NULL); vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus); TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap\n"); - for (i = 0; i < test_args.nr_vcpus; i++) { - ret = pthread_create(&test_vcpu[i].pt_vcpu_run, NULL, - test_vcpu_run, &test_vcpu[i]); + for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) { + ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run, + (void *)(unsigned long)i); TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread\n", i); } @@ -338,7 +337,7 @@ static void test_run(struct kvm_vm *vm) for (i = 0; i < test_args.nr_vcpus; i++) - pthread_join(test_vcpu[i].pt_vcpu_run, NULL); + pthread_join(pt_vcpu_run[i], NULL); if (test_args.migration_freq_ms) pthread_join(pt_vcpu_migration, NULL); @@ -349,12 +348,10 @@ static void test_run(struct kvm_vm *vm) static void test_init_timer_irq(struct kvm_vm *vm) { /* Timer initid should be same for all the vCPUs, so query only vCPU-0 */ - int vcpu0_fd = vcpu_get_fd(vm, 0); - - kvm_device_access(vcpu0_fd, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq, false); - kvm_device_access(vcpu0_fd, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq, false); + vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, + KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq); + vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, + KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq); sync_global_to_guest(vm, ptimer_irq); sync_global_to_guest(vm, vtimer_irq); @@ -370,25 +367,18 @@ static struct kvm_vm *test_vm_create(void) unsigned int i; int nr_vcpus = test_args.nr_vcpus; - vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); + vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); vm_init_descriptor_tables(vm); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler); - for (i = 0; i < nr_vcpus; i++) { - vcpu_init_descriptor_tables(vm, i); - - test_vcpu[i].vcpuid = i; - test_vcpu[i].vm = vm; - } + for (i = 0; i < nr_vcpus; i++) + vcpu_init_descriptor_tables(vcpus[i]); ucall_init(vm, NULL); test_init_timer_irq(vm); gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); - if (gic_fd < 0) { - print_skip("Failed to create vgic-v3"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); @@ -478,10 +468,8 @@ int main(int argc, char *argv[]) if (!parse_args(argc, argv)) exit(KSFT_SKIP); - if (test_args.migration_freq_ms && get_nprocs() < 2) { - print_skip("At least two physical CPUs needed for vCPU migration"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(!test_args.migration_freq_ms || get_nprocs() >= 2, + "At least two physical CPUs needed for vCPU migration"); vm = test_vm_create(); test_run(vm); diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index 63b2178210c4..2ee35cf9801e 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -3,8 +3,6 @@ #include <kvm_util.h> #include <processor.h> -#define VCPU_ID 0 - #define MDSCR_KDE (1 << 13) #define MDSCR_MDE (1 << 15) #define MDSCR_SS (1 << 0) @@ -240,31 +238,29 @@ static void guest_svc_handler(struct ex_regs *regs) svc_addr = regs->pc; } -static int debug_version(struct kvm_vm *vm) +static int debug_version(struct kvm_vcpu *vcpu) { uint64_t id_aa64dfr0; - get_reg(vm, VCPU_ID, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &id_aa64dfr0); + vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &id_aa64dfr0); return id_aa64dfr0 & 0xf; } int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; int stage; - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); ucall_init(vm, NULL); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); - if (debug_version(vm) < 6) { - print_skip("Armv8 debug architecture not supported."); - kvm_vm_free(vm); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(debug_version(vcpu) >= 6, + "Armv8 debug architecture not supported."); vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, ESR_EC_BRK_INS, guest_sw_bp_handler); @@ -278,18 +274,16 @@ int main(int argc, char *argv[]) ESR_EC_SVC64, guest_svc_handler); for (stage = 0; stage < 11; stage++) { - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(uc.args[1] == stage, "Stage %d: Unexpected sync ucall, got %lx", stage, (ulong)uc.args[1]); break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx", - (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d3a7dbfcbb3d..d287dd2cac0a 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -377,7 +377,7 @@ static void prepare_vcpu_init(struct vcpu_config *c, struct kvm_vcpu_init *init) init->features[s->feature / 32] |= 1 << (s->feature % 32); } -static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid, struct vcpu_config *c) +static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_config *c) { struct reg_sublist *s; int feature; @@ -385,7 +385,7 @@ static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid, struct vcpu_config for_each_sublist(c, s) { if (s->finalize) { feature = s->feature; - vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature); } } } @@ -395,10 +395,12 @@ static void check_supported(struct vcpu_config *c) struct reg_sublist *s; for_each_sublist(c, s) { - if (s->capability && !kvm_check_cap(s->capability)) { - fprintf(stderr, "%s: %s not available, skipping tests\n", config_name(c), s->name); - exit(KSFT_SKIP); - } + if (!s->capability) + continue; + + __TEST_REQUIRE(kvm_has_cap(s->capability), + "%s: %s not available, skipping tests\n", + config_name(c), s->name); } } @@ -411,17 +413,19 @@ static void run_test(struct vcpu_config *c) struct kvm_vcpu_init init = { .target = -1, }; int new_regs = 0, missing_regs = 0, i, n; int failed_get = 0, failed_set = 0, failed_reject = 0; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct reg_sublist *s; check_supported(c); - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create_barebones(); prepare_vcpu_init(c, &init); - aarch64_vcpu_add_default(vm, 0, &init, NULL); - finalize_vcpu(vm, 0, c); + vcpu = __vm_vcpu_add(vm, 0); + aarch64_vcpu_setup(vcpu, &init); + finalize_vcpu(vcpu, c); - reg_list = vcpu_get_reg_list(vm, 0); + reg_list = vcpu_get_reg_list(vcpu); if (fixup_core_regs) core_reg_fixup(); @@ -457,7 +461,7 @@ static void run_test(struct vcpu_config *c) bool reject_reg = false; int ret; - ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr); if (ret) { printf("%s: Failed to get ", config_name(c)); print_reg(c, reg.id); @@ -469,7 +473,7 @@ static void run_test(struct vcpu_config *c) for_each_sublist(c, s) { if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) { reject_reg = true; - ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); if (ret != -1 || errno != EPERM) { printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno); print_reg(c, reg.id); @@ -481,7 +485,7 @@ static void run_test(struct vcpu_config *c) } if (!reject_reg) { - ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); if (ret) { printf("%s: Failed to set ", config_name(c)); print_reg(c, reg.id); diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c index 41e0210b7a5e..a39da3fe4952 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -141,26 +141,6 @@ static void guest_code(void) GUEST_DONE(); } -static int set_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t val) -{ - struct kvm_one_reg reg = { - .id = id, - .addr = (uint64_t)&val, - }; - - return _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); -} - -static void get_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t *addr) -{ - struct kvm_one_reg reg = { - .id = id, - .addr = (uint64_t)addr, - }; - - vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); -} - struct st_time { uint32_t rev; uint32_t attr; @@ -170,23 +150,19 @@ struct st_time { #define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63) #define ST_GPA_BASE (1 << 30) -static void steal_time_init(struct kvm_vm *vm) +static void steal_time_init(struct kvm_vcpu *vcpu) { uint64_t st_ipa = (ulong)ST_GPA_BASE; unsigned int gpages; - struct kvm_device_attr dev = { - .group = KVM_ARM_VCPU_PVTIME_CTRL, - .attr = KVM_ARM_VCPU_PVTIME_IPA, - .addr = (uint64_t)&st_ipa, - }; gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); + vm_userspace_mem_region_add(vcpu->vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); - vcpu_ioctl(vm, 0, KVM_SET_DEVICE_ATTR, &dev); + vcpu_device_attr_set(vcpu, KVM_ARM_VCPU_PVTIME_CTRL, + KVM_ARM_VCPU_PVTIME_IPA, &st_ipa); } -static void test_fw_regs_before_vm_start(struct kvm_vm *vm) +static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) { uint64_t val; unsigned int i; @@ -196,18 +172,18 @@ static void test_fw_regs_before_vm_start(struct kvm_vm *vm) const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; /* First 'read' should be an upper limit of the features supported */ - get_fw_reg(vm, reg_info->reg, &val); + vcpu_get_reg(vcpu, reg_info->reg, &val); TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n", reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); /* Test a 'write' by disabling all the features of the register map */ - ret = set_fw_reg(vm, reg_info->reg, 0); + ret = __vcpu_set_reg(vcpu, reg_info->reg, 0); TEST_ASSERT(ret == 0, "Failed to clear all the features of reg: 0x%lx; ret: %d\n", reg_info->reg, errno); - get_fw_reg(vm, reg_info->reg, &val); + vcpu_get_reg(vcpu, reg_info->reg, &val); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg); @@ -216,7 +192,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vm *vm) * Avoid this check if all the bits are occupied. */ if (reg_info->max_feat_bit < 63) { - ret = set_fw_reg(vm, reg_info->reg, BIT(reg_info->max_feat_bit + 1)); + ret = __vcpu_set_reg(vcpu, reg_info->reg, BIT(reg_info->max_feat_bit + 1)); TEST_ASSERT(ret != 0 && errno == EINVAL, "Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n", errno, reg_info->reg); @@ -224,7 +200,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vm *vm) } } -static void test_fw_regs_after_vm_start(struct kvm_vm *vm) +static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu) { uint64_t val; unsigned int i; @@ -237,7 +213,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vm *vm) * Before starting the VM, the test clears all the bits. * Check if that's still the case. */ - get_fw_reg(vm, reg_info->reg, &val); + vcpu_get_reg(vcpu, reg_info->reg, &val); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg); @@ -247,77 +223,78 @@ static void test_fw_regs_after_vm_start(struct kvm_vm *vm) * the registers and should return EBUSY. Set the registers and check for * the expected errno. */ - ret = set_fw_reg(vm, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit)); + ret = __vcpu_set_reg(vcpu, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit)); TEST_ASSERT(ret != 0 && errno == EBUSY, "Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n", errno, reg_info->reg); } } -static struct kvm_vm *test_vm_create(void) +static struct kvm_vm *test_vm_create(struct kvm_vcpu **vcpu) { struct kvm_vm *vm; - vm = vm_create_default(0, 0, guest_code); + vm = vm_create_with_one_vcpu(vcpu, guest_code); ucall_init(vm, NULL); - steal_time_init(vm); + steal_time_init(*vcpu); return vm; } -static struct kvm_vm *test_guest_stage(struct kvm_vm *vm) +static void test_guest_stage(struct kvm_vm **vm, struct kvm_vcpu **vcpu) { - struct kvm_vm *ret_vm = vm; + int prev_stage = stage; + + pr_debug("Stage: %d\n", prev_stage); - pr_debug("Stage: %d\n", stage); + /* Sync the stage early, the VM might be freed below. */ + stage++; + sync_global_to_guest(*vm, stage); - switch (stage) { + switch (prev_stage) { case TEST_STAGE_REG_IFACE: - test_fw_regs_after_vm_start(vm); + test_fw_regs_after_vm_start(*vcpu); break; case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: /* Start a new VM so that all the features are now enabled by default */ - kvm_vm_free(vm); - ret_vm = test_vm_create(); + kvm_vm_free(*vm); + *vm = test_vm_create(vcpu); break; case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: case TEST_STAGE_HVC_IFACE_FALSE_INFO: break; default: - TEST_FAIL("Unknown test stage: %d\n", stage); + TEST_FAIL("Unknown test stage: %d\n", prev_stage); } - - stage++; - sync_global_to_guest(vm, stage); - - return ret_vm; } static void test_run(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; bool guest_done = false; - vm = test_vm_create(); + vm = test_vm_create(&vcpu); - test_fw_regs_before_vm_start(vm); + test_fw_regs_before_vm_start(vcpu); while (!guest_done) { - vcpu_run(vm, 0); + vcpu_run(vcpu); - switch (get_ucall(vm, 0, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: - vm = test_guest_stage(vm); + test_guest_stage(&vm, &vcpu); break; case UCALL_DONE: guest_done = true; break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld\n\tvalues: 0x%lx, 0x%lx; 0x%lx, stage: %u", - (const char *)uc.args[0], __FILE__, uc.args[1], - uc.args[2], uc.args[3], uc.args[4], stage); + REPORT_GUEST_ASSERT_N(uc, "values: 0x%lx, 0x%lx; 0x%lx, stage: %u", + GUEST_ASSERT_ARG(uc, 0), + GUEST_ASSERT_ARG(uc, 1), + GUEST_ASSERT_ARG(uc, 2), stage); break; default: TEST_FAIL("Unexpected guest exit\n"); diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c index 88541de21c41..f7621f6e938e 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -17,9 +17,6 @@ #include "processor.h" #include "test_util.h" -#define VCPU_ID_SOURCE 0 -#define VCPU_ID_TARGET 1 - #define CPU_ON_ENTRY_ADDR 0xfeedf00dul #define CPU_ON_CONTEXT_ID 0xdeadc0deul @@ -64,49 +61,48 @@ static uint64_t psci_features(uint32_t func_id) return res.a0; } -static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid) +static void vcpu_power_off(struct kvm_vcpu *vcpu) { struct kvm_mp_state mp_state = { .mp_state = KVM_MP_STATE_STOPPED, }; - vcpu_set_mp_state(vm, vcpuid, &mp_state); + vcpu_mp_state_set(vcpu, &mp_state); } -static struct kvm_vm *setup_vm(void *guest_code) +static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source, + struct kvm_vcpu **target) { struct kvm_vcpu_init init; struct kvm_vm *vm; - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); + vm = vm_create(2); ucall_init(vm, NULL); vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); - aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_code); - aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_code); + *source = aarch64_vcpu_add(vm, 0, &init, guest_code); + *target = aarch64_vcpu_add(vm, 1, &init, guest_code); return vm; } -static void enter_guest(struct kvm_vm *vm, uint32_t vcpuid) +static void enter_guest(struct kvm_vcpu *vcpu) { struct ucall uc; - vcpu_run(vm, vcpuid); - if (get_ucall(vm, vcpuid, &uc) == UCALL_ABORT) - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, - uc.args[1]); + vcpu_run(vcpu); + if (get_ucall(vcpu, &uc) == UCALL_ABORT) + REPORT_GUEST_ASSERT(uc); } -static void assert_vcpu_reset(struct kvm_vm *vm, uint32_t vcpuid) +static void assert_vcpu_reset(struct kvm_vcpu *vcpu) { uint64_t obs_pc, obs_x0; - get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &obs_pc); - get_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &obs_pc); + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]), &obs_x0); TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, "unexpected target cpu pc: %lx (expected: %lx)", @@ -134,37 +130,29 @@ static void guest_test_cpu_on(uint64_t target_cpu) static void host_test_cpu_on(void) { + struct kvm_vcpu *source, *target; uint64_t target_mpidr; struct kvm_vm *vm; struct ucall uc; - vm = setup_vm(guest_test_cpu_on); + vm = setup_vm(guest_test_cpu_on, &source, &target); /* * make sure the target is already off when executing the test. */ - vcpu_power_off(vm, VCPU_ID_TARGET); + vcpu_power_off(target); - get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); - vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); - enter_guest(vm, VCPU_ID_SOURCE); + vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + vcpu_args_set(source, 1, target_mpidr & MPIDR_HWID_BITMASK); + enter_guest(source); - if (get_ucall(vm, VCPU_ID_SOURCE, &uc) != UCALL_DONE) + if (get_ucall(source, &uc) != UCALL_DONE) TEST_FAIL("Unhandled ucall: %lu", uc.cmd); - assert_vcpu_reset(vm, VCPU_ID_TARGET); + assert_vcpu_reset(target); kvm_vm_free(vm); } -static void enable_system_suspend(struct kvm_vm *vm) -{ - struct kvm_enable_cap cap = { - .cap = KVM_CAP_ARM_SYSTEM_SUSPEND, - }; - - vm_enable_cap(vm, &cap); -} - static void guest_test_system_suspend(void) { uint64_t ret; @@ -179,16 +167,17 @@ static void guest_test_system_suspend(void) static void host_test_system_suspend(void) { + struct kvm_vcpu *source, *target; struct kvm_run *run; struct kvm_vm *vm; - vm = setup_vm(guest_test_system_suspend); - enable_system_suspend(vm); + vm = setup_vm(guest_test_system_suspend, &source, &target); + vm_enable_cap(vm, KVM_CAP_ARM_SYSTEM_SUSPEND, 0); - vcpu_power_off(vm, VCPU_ID_TARGET); - run = vcpu_state(vm, VCPU_ID_SOURCE); + vcpu_power_off(target); + run = source->run; - enter_guest(vm, VCPU_ID_SOURCE); + enter_guest(source); TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT, "Unhandled exit reason: %u (%s)", @@ -202,10 +191,7 @@ static void host_test_system_suspend(void) int main(void) { - if (!kvm_check_cap(KVM_CAP_ARM_SYSTEM_SUSPEND)) { - print_skip("KVM_CAP_ARM_SYSTEM_SUSPEND not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SYSTEM_SUSPEND)); host_test_cpu_on(); host_test_system_suspend(); diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c index 6e9402679229..80b74c6f152b 100644 --- a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c +++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c @@ -15,24 +15,25 @@ /* - * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then - * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2. + * Add a vCPU, run KVM_ARM_VCPU_INIT with @init0, and then + * add another vCPU, and run KVM_ARM_VCPU_INIT with @init1. */ -static int add_init_2vcpus(struct kvm_vcpu_init *init1, - struct kvm_vcpu_init *init2) +static int add_init_2vcpus(struct kvm_vcpu_init *init0, + struct kvm_vcpu_init *init1) { + struct kvm_vcpu *vcpu0, *vcpu1; struct kvm_vm *vm; int ret; - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create_barebones(); - vm_vcpu_add(vm, 0); - ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + vcpu0 = __vm_vcpu_add(vm, 0); + ret = __vcpu_ioctl(vcpu0, KVM_ARM_VCPU_INIT, init0); if (ret) goto free_exit; - vm_vcpu_add(vm, 1); - ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + vcpu1 = __vm_vcpu_add(vm, 1); + ret = __vcpu_ioctl(vcpu1, KVM_ARM_VCPU_INIT, init1); free_exit: kvm_vm_free(vm); @@ -40,25 +41,26 @@ free_exit: } /* - * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1, - * and run KVM_ARM_VCPU_INIT for another vCPU with @init2. + * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init0, + * and run KVM_ARM_VCPU_INIT for another vCPU with @init1. */ -static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1, - struct kvm_vcpu_init *init2) +static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init0, + struct kvm_vcpu_init *init1) { + struct kvm_vcpu *vcpu0, *vcpu1; struct kvm_vm *vm; int ret; - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create_barebones(); - vm_vcpu_add(vm, 0); - vm_vcpu_add(vm, 1); + vcpu0 = __vm_vcpu_add(vm, 0); + vcpu1 = __vm_vcpu_add(vm, 1); - ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + ret = __vcpu_ioctl(vcpu0, KVM_ARM_VCPU_INIT, init0); if (ret) goto free_exit; - ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + ret = __vcpu_ioctl(vcpu1, KVM_ARM_VCPU_INIT, init1); free_exit: kvm_vm_free(vm); @@ -76,45 +78,42 @@ free_exit: */ int main(void) { - struct kvm_vcpu_init init1, init2; + struct kvm_vcpu_init init0, init1; struct kvm_vm *vm; int ret; - if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) { - print_skip("KVM_CAP_ARM_EL1_32BIT is not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_EL1_32BIT)); - /* Get the preferred target type and copy that to init2 for later use */ - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1); + /* Get the preferred target type and copy that to init1 for later use */ + vm = vm_create_barebones(); + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init0); kvm_vm_free(vm); - init2 = init1; + init1 = init0; /* Test with 64bit vCPUs */ - ret = add_init_2vcpus(&init1, &init1); + ret = add_init_2vcpus(&init0, &init0); TEST_ASSERT(ret == 0, "Configuring 64bit EL1 vCPUs failed unexpectedly"); - ret = add_2vcpus_init_2vcpus(&init1, &init1); + ret = add_2vcpus_init_2vcpus(&init0, &init0); TEST_ASSERT(ret == 0, "Configuring 64bit EL1 vCPUs failed unexpectedly"); /* Test with 32bit vCPUs */ - init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); - ret = add_init_2vcpus(&init1, &init1); + init0.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init0, &init0); TEST_ASSERT(ret == 0, "Configuring 32bit EL1 vCPUs failed unexpectedly"); - ret = add_2vcpus_init_2vcpus(&init1, &init1); + ret = add_2vcpus_init_2vcpus(&init0, &init0); TEST_ASSERT(ret == 0, "Configuring 32bit EL1 vCPUs failed unexpectedly"); /* Test with mixed-width vCPUs */ - init1.features[0] = 0; - init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); - ret = add_init_2vcpus(&init1, &init2); + init0.features[0] = 0; + init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init0, &init1); TEST_ASSERT(ret != 0, "Configuring mixed-width vCPUs worked unexpectedly"); - ret = add_2vcpus_init_2vcpus(&init1, &init2); + ret = add_2vcpus_init_2vcpus(&init0, &init1); TEST_ASSERT(ret != 0, "Configuring mixed-width vCPUs worked unexpectedly"); diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index 34379c98d2f4..e05ecb31823f 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -32,14 +32,28 @@ struct vm_gic { static uint64_t max_phys_size; -/* helper to access a redistributor register */ -static int access_v3_redist_reg(int gicv3_fd, int vcpu, int offset, - uint32_t *val, bool write) +/* + * Helpers to access a redistributor register and verify the ioctl() failed or + * succeeded as expected, and provided the correct value on success. + */ +static void v3_redist_reg_get_errno(int gicv3_fd, int vcpu, int offset, + int want, const char *msg) { - uint64_t attr = REG_OFFSET(vcpu, offset); + uint32_t ignored_val; + int ret = __kvm_device_attr_get(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, + REG_OFFSET(vcpu, offset), &ignored_val); - return _kvm_device_access(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, - attr, val, write); + TEST_ASSERT(ret && errno == want, "%s; want errno = %d", msg, want); +} + +static void v3_redist_reg_get(int gicv3_fd, int vcpu, int offset, uint32_t want, + const char *msg) +{ + uint32_t val; + + kvm_device_attr_get(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, + REG_OFFSET(vcpu, offset), &val); + TEST_ASSERT(val == want, "%s; want '0x%x', got '0x%x'", msg, want, val); } /* dummy guest code */ @@ -52,22 +66,22 @@ static void guest_code(void) } /* we don't want to assert on run execution, hence that helper */ -static int run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +static int run_vcpu(struct kvm_vcpu *vcpu) { - ucall_init(vm, NULL); - int ret = _vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL); - if (ret) - return -errno; - return 0; + ucall_init(vcpu->vm, NULL); + + return __vcpu_run(vcpu) ? -errno : 0; } -static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, uint32_t nr_vcpus) +static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, + uint32_t nr_vcpus, + struct kvm_vcpu *vcpus[]) { struct vm_gic v; v.gic_dev_type = gic_dev_type; - v.vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); - v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false); + v.vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); return v; } @@ -129,63 +143,60 @@ static void subtest_dist_rdist(struct vm_gic *v) : gic_v2_dist_region; /* Check existing group/attributes */ - kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - dist.attr); + kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, dist.attr); - kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr); + kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, rdist.attr); /* check non existing attribute */ - ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, -1); + ret = __kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, -1); TEST_ASSERT(ret && errno == ENXIO, "attribute not supported"); /* misaligned DIST and REDIST address settings */ addr = dist.alignment / 0x10; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - dist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + dist.attr, &addr); TEST_ASSERT(ret && errno == EINVAL, "GIC dist base not aligned"); addr = rdist.alignment / 0x10; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr); TEST_ASSERT(ret && errno == EINVAL, "GIC redist/cpu base not aligned"); /* out of range address */ addr = max_phys_size; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - dist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + dist.attr, &addr); TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit"); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr); TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit"); /* Space for half a rdist (a rdist is: 2 * rdist.alignment). */ addr = max_phys_size - dist.alignment; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr); TEST_ASSERT(ret && errno == E2BIG, "half of the redist is beyond IPA limit"); /* set REDIST base address @0x0*/ addr = 0x00000; - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr, &addr, true); + kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr); /* Attempt to create a second legacy redistributor region */ addr = 0xE0000; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - rdist.attr, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr); TEST_ASSERT(ret && errno == EEXIST, "GIC redist base set again"); - ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + ret = __kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST); if (!ret) { /* Attempt to mix legacy and new redistributor regions */ addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, - &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "attempt to mix GICv3 REDIST and REDIST_REGION"); } @@ -195,8 +206,8 @@ static void subtest_dist_rdist(struct vm_gic *v) * on first vcpu run instead. */ addr = rdist.size - rdist.alignment; - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - dist.attr, &addr, true); + kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + dist.attr, &addr); } /* Test the new REDIST region API */ @@ -205,71 +216,71 @@ static void subtest_v3_redist_regions(struct vm_gic *v) uint64_t addr, expected_addr; int ret; - ret = kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST); + ret = __kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST); TEST_ASSERT(!ret, "Multiple redist regions advertised"); addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 2, 0); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "redist region attr value with flags != 0"); addr = REDIST_REGION_ATTR_ADDR(0, 0x100000, 0, 0); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "redist region attr value with count== 0"); addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 1); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "attempt to register the first rdist region with index != 0"); addr = REDIST_REGION_ATTR_ADDR(2, 0x201000, 0, 1); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "rdist region with misaligned address"); addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0); - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 1); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "register an rdist region with already used index"); addr = REDIST_REGION_ATTR_ADDR(1, 0x210000, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "register an rdist region overlapping with another one"); addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "register redist region with index not +1"); addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 1); - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); addr = REDIST_REGION_ATTR_ADDR(1, max_phys_size, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == E2BIG, "register redist region with base address beyond IPA range"); /* The last redist is above the pa range. */ addr = REDIST_REGION_ATTR_ADDR(2, max_phys_size - 0x30000, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == E2BIG, "register redist region with top address beyond IPA range"); addr = 0x260000; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr); TEST_ASSERT(ret && errno == EINVAL, "Mix KVM_VGIC_V3_ADDR_TYPE_REDIST and REDIST_REGION"); @@ -282,28 +293,28 @@ static void subtest_v3_redist_regions(struct vm_gic *v) addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 0); expected_addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false); + ret = __kvm_device_attr_get(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(!ret && addr == expected_addr, "read characteristics of region #0"); addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 1); expected_addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 1); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false); + ret = __kvm_device_attr_get(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(!ret && addr == expected_addr, "read characteristics of region #1"); addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false); + ret = __kvm_device_attr_get(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == ENOENT, "read characteristics of non existing region"); addr = 0x260000; - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true); + kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_DIST, &addr); addr = REDIST_REGION_ATTR_ADDR(1, 0x260000, 0, 2); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "register redist region colliding with dist"); } @@ -313,18 +324,19 @@ static void subtest_v3_redist_regions(struct vm_gic *v) */ static void test_vgic_then_vcpus(uint32_t gic_dev_type) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; int ret, i; - v = vm_gic_create_with_vcpus(gic_dev_type, 1); + v = vm_gic_create_with_vcpus(gic_dev_type, 1, vcpus); subtest_dist_rdist(&v); /* Add the rest of the VCPUs */ for (i = 1; i < NR_VCPUS; ++i) - vm_vcpu_add_default(v.vm, i, guest_code); + vcpus[i] = vm_vcpu_add(v.vm, i, guest_code); - ret = run_vcpu(v.vm, 3); + ret = run_vcpu(vcpus[3]); TEST_ASSERT(ret == -EINVAL, "dist/rdist overlap detected on 1st vcpu run"); vm_gic_destroy(&v); @@ -333,14 +345,15 @@ static void test_vgic_then_vcpus(uint32_t gic_dev_type) /* All the VCPUs are created before the VGIC KVM device gets initialized */ static void test_vcpus_then_vgic(uint32_t gic_dev_type) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; int ret; - v = vm_gic_create_with_vcpus(gic_dev_type, NR_VCPUS); + v = vm_gic_create_with_vcpus(gic_dev_type, NR_VCPUS, vcpus); subtest_dist_rdist(&v); - ret = run_vcpu(v.vm, 3); + ret = run_vcpu(vcpus[3]); TEST_ASSERT(ret == -EINVAL, "dist/rdist overlap detected on 1st vcpu run"); vm_gic_destroy(&v); @@ -348,52 +361,53 @@ static void test_vcpus_then_vgic(uint32_t gic_dev_type) static void test_v3_new_redist_regions(void) { + struct kvm_vcpu *vcpus[NR_VCPUS]; void *dummy = NULL; struct vm_gic v; uint64_t addr; int ret; - v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); subtest_v3_redist_regions(&v); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); - ret = run_vcpu(v.vm, 3); + ret = run_vcpu(vcpus[3]); TEST_ASSERT(ret == -ENXIO, "running without sufficient number of rdists"); vm_gic_destroy(&v); /* step2 */ - v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); subtest_v3_redist_regions(&v); addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); - ret = run_vcpu(v.vm, 3); + ret = run_vcpu(vcpus[3]); TEST_ASSERT(ret == -EBUSY, "running without vgic explicit init"); vm_gic_destroy(&v); /* step 3 */ - v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); subtest_v3_redist_regions(&v); - _kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, dummy, true); + ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, dummy); TEST_ASSERT(ret && errno == EFAULT, "register a third region allowing to cover the 4 vcpus"); addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); - ret = run_vcpu(v.vm, 3); + ret = run_vcpu(vcpus[3]); TEST_ASSERT(!ret, "vcpu run"); vm_gic_destroy(&v); @@ -403,71 +417,77 @@ static void test_v3_typer_accesses(void) { struct vm_gic v; uint64_t addr; - uint32_t val; int ret, i; - v.vm = vm_create_default(0, 0, guest_code); + v.vm = vm_create(NR_VCPUS); + (void)vm_vcpu_add(v.vm, 0, guest_code); - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3); - vm_vcpu_add_default(v.vm, 3, guest_code); + (void)vm_vcpu_add(v.vm, 3, guest_code); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(ret && errno == EINVAL, "attempting to read GICR_TYPER of non created vcpu"); + v3_redist_reg_get_errno(v.gic_fd, 1, GICR_TYPER, EINVAL, + "attempting to read GICR_TYPER of non created vcpu"); - vm_vcpu_add_default(v.vm, 1, guest_code); + (void)vm_vcpu_add(v.vm, 1, guest_code); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(ret && errno == EBUSY, "read GICR_TYPER before GIC initialized"); + v3_redist_reg_get_errno(v.gic_fd, 1, GICR_TYPER, EBUSY, + "read GICR_TYPER before GIC initialized"); - vm_vcpu_add_default(v.vm, 2, guest_code); + (void)vm_vcpu_add(v.vm, 2, guest_code); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); for (i = 0; i < NR_VCPUS ; i++) { - ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && !val, "read GICR_TYPER before rdist region setting"); + v3_redist_reg_get(v.gic_fd, i, GICR_TYPER, i * 0x100, + "read GICR_TYPER before rdist region setting"); } addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); /* The 2 first rdists should be put there (vcpu 0 and 3) */ - ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && !val, "read typer of rdist #0"); - - ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #1"); + v3_redist_reg_get(v.gic_fd, 0, GICR_TYPER, 0x0, "read typer of rdist #0"); + v3_redist_reg_get(v.gic_fd, 3, GICR_TYPER, 0x310, "read typer of rdist #1"); addr = REDIST_REGION_ATTR_ADDR(10, 0x100000, 0, 1); - ret = _kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); TEST_ASSERT(ret && errno == EINVAL, "collision with previous rdist region"); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x100, - "no redist region attached to vcpu #1 yet, last cannot be returned"); - - ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x200, - "no redist region attached to vcpu #2, last cannot be returned"); + v3_redist_reg_get(v.gic_fd, 1, GICR_TYPER, 0x100, + "no redist region attached to vcpu #1 yet, last cannot be returned"); + v3_redist_reg_get(v.gic_fd, 2, GICR_TYPER, 0x200, + "no redist region attached to vcpu #2, last cannot be returned"); addr = REDIST_REGION_ATTR_ADDR(10, 0x20000, 0, 1); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1"); - - ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x210, - "read typer of rdist #1, last properly returned"); + v3_redist_reg_get(v.gic_fd, 1, GICR_TYPER, 0x100, "read typer of rdist #1"); + v3_redist_reg_get(v.gic_fd, 2, GICR_TYPER, 0x210, + "read typer of rdist #1, last properly returned"); vm_gic_destroy(&v); } +static struct vm_gic vm_gic_v3_create_with_vcpuids(int nr_vcpus, + uint32_t vcpuids[]) +{ + struct vm_gic v; + int i; + + v.vm = vm_create(nr_vcpus); + for (i = 0; i < nr_vcpus; i++) + vm_vcpu_add(v.vm, vcpuids[i], guest_code); + + v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3); + + return v; +} + /** * Test GICR_TYPER last bit with new redist regions * rdist regions #1 and #2 are contiguous @@ -483,45 +503,30 @@ static void test_v3_last_bit_redist_regions(void) uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; uint64_t addr; - uint32_t val; - int ret; - - v.vm = vm_create_default_with_vcpus(6, 0, 0, guest_code, vcpuids); - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + v = vm_gic_v3_create_with_vcpuids(ARRAY_SIZE(vcpuids), vcpuids); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); addr = REDIST_REGION_ATTR_ADDR(2, 0x100000, 0, 0); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); addr = REDIST_REGION_ATTR_ADDR(2, 0x240000, 0, 1); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 2); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); - - ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0"); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1"); - - ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x200, "read typer of rdist #2"); - - ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #3"); - - ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #5"); - - ret = access_v3_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x410, "read typer of rdist #4"); + v3_redist_reg_get(v.gic_fd, 0, GICR_TYPER, 0x000, "read typer of rdist #0"); + v3_redist_reg_get(v.gic_fd, 1, GICR_TYPER, 0x100, "read typer of rdist #1"); + v3_redist_reg_get(v.gic_fd, 2, GICR_TYPER, 0x200, "read typer of rdist #2"); + v3_redist_reg_get(v.gic_fd, 3, GICR_TYPER, 0x310, "read typer of rdist #3"); + v3_redist_reg_get(v.gic_fd, 5, GICR_TYPER, 0x500, "read typer of rdist #5"); + v3_redist_reg_get(v.gic_fd, 4, GICR_TYPER, 0x410, "read typer of rdist #4"); vm_gic_destroy(&v); } @@ -532,34 +537,21 @@ static void test_v3_last_bit_single_rdist(void) uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; uint64_t addr; - uint32_t val; - int ret; - - v.vm = vm_create_default_with_vcpus(6, 0, 0, guest_code, vcpuids); - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + v = vm_gic_v3_create_with_vcpuids(ARRAY_SIZE(vcpuids), vcpuids); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); addr = 0x10000; - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); - - ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0"); - - ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x300, "read typer of rdist #1"); - - ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #2"); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr); - ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #3"); - - ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); - TEST_ASSERT(!ret && val == 0x210, "read typer of rdist #3"); + v3_redist_reg_get(v.gic_fd, 0, GICR_TYPER, 0x000, "read typer of rdist #0"); + v3_redist_reg_get(v.gic_fd, 3, GICR_TYPER, 0x300, "read typer of rdist #1"); + v3_redist_reg_get(v.gic_fd, 5, GICR_TYPER, 0x500, "read typer of rdist #2"); + v3_redist_reg_get(v.gic_fd, 1, GICR_TYPER, 0x100, "read typer of rdist #3"); + v3_redist_reg_get(v.gic_fd, 2, GICR_TYPER, 0x210, "read typer of rdist #3"); vm_gic_destroy(&v); } @@ -567,30 +559,31 @@ static void test_v3_last_bit_single_rdist(void) /* Uses the legacy REDIST region API. */ static void test_v3_redist_ipa_range_check_at_vcpu_run(void) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; int ret, i; uint64_t addr; - v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, 1); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, 1, vcpus); /* Set space for 3 redists, we have 1 vcpu, so this succeeds. */ addr = max_phys_size - (3 * 2 * 0x10000); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr); addr = 0x00000; - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_DIST, &addr); /* Add the rest of the VCPUs */ for (i = 1; i < NR_VCPUS; ++i) - vm_vcpu_add_default(v.vm, i, guest_code); + vcpus[i] = vm_vcpu_add(v.vm, i, guest_code); - kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); /* Attempt to run a vcpu without enough redist space. */ - ret = run_vcpu(v.vm, 2); + ret = run_vcpu(vcpus[2]); TEST_ASSERT(ret && errno == EINVAL, "redist base+size above PA range detected on 1st vcpu run"); @@ -599,39 +592,40 @@ static void test_v3_redist_ipa_range_check_at_vcpu_run(void) static void test_v3_its_region(void) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; uint64_t addr; int its_fd, ret; - v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); - its_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_ITS, false); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); + its_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_ITS); addr = 0x401000; - ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + ret = __kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr); TEST_ASSERT(ret && errno == EINVAL, "ITS region with misaligned address"); addr = max_phys_size; - ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + ret = __kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr); TEST_ASSERT(ret && errno == E2BIG, "register ITS region with base address beyond IPA range"); addr = max_phys_size - 0x10000; - ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + ret = __kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr); TEST_ASSERT(ret && errno == E2BIG, "Half of ITS region is beyond IPA range"); /* This one succeeds setting the ITS base */ addr = 0x400000; - kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr); addr = 0x300000; - ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + ret = __kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr); TEST_ASSERT(ret && errno == EEXIST, "ITS base set again"); close(its_fd); @@ -643,34 +637,33 @@ static void test_v3_its_region(void) */ int test_kvm_device(uint32_t gic_dev_type) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; - int ret, fd; uint32_t other; + int ret; - v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL); + v.vm = vm_create_with_vcpus(NR_VCPUS, guest_code, vcpus); /* try to create a non existing KVM device */ - ret = _kvm_create_device(v.vm, 0, true, &fd); + ret = __kvm_test_create_device(v.vm, 0); TEST_ASSERT(ret && errno == ENODEV, "unsupported device"); /* trial mode */ - ret = _kvm_create_device(v.vm, gic_dev_type, true, &fd); + ret = __kvm_test_create_device(v.vm, gic_dev_type); if (ret) return ret; - v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false); - - ret = _kvm_create_device(v.vm, gic_dev_type, false, &fd); - TEST_ASSERT(ret && errno == EEXIST, "create GIC device twice"); + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); - kvm_create_device(v.vm, gic_dev_type, true); + ret = __kvm_create_device(v.vm, gic_dev_type); + TEST_ASSERT(ret < 0 && errno == EEXIST, "create GIC device twice"); /* try to create the other gic_dev_type */ other = VGIC_DEV_IS_V2(gic_dev_type) ? KVM_DEV_TYPE_ARM_VGIC_V3 : KVM_DEV_TYPE_ARM_VGIC_V2; - if (!_kvm_create_device(v.vm, other, true, &fd)) { - ret = _kvm_create_device(v.vm, other, false, &fd); - TEST_ASSERT(ret && errno == EINVAL, + if (!__kvm_test_create_device(v.vm, other)) { + ret = __kvm_test_create_device(v.vm, other); + TEST_ASSERT(ret && (errno == EINVAL || errno == EEXIST), "create GIC device while other version exists"); } @@ -698,6 +691,7 @@ int main(int ac, char **av) { int ret; int pa_bits; + int cnt_impl = 0; pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits; max_phys_size = 1ULL << pa_bits; @@ -706,17 +700,19 @@ int main(int ac, char **av) if (!ret) { pr_info("Running GIC_v3 tests.\n"); run_tests(KVM_DEV_TYPE_ARM_VGIC_V3); - return 0; + cnt_impl++; } ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V2); if (!ret) { pr_info("Running GIC_v2 tests.\n"); run_tests(KVM_DEV_TYPE_ARM_VGIC_V2); - return 0; + cnt_impl++; } - print_skip("No GICv2 nor GICv3 support"); - exit(KSFT_SKIP); + if (!cnt_impl) { + print_skip("No GICv2 nor GICv3 support"); + exit(KSFT_SKIP); + } return 0; } diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index 554ca649d470..17417220a083 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -22,7 +22,6 @@ #define GICD_BASE_GPA 0x08000000ULL #define GICR_BASE_GPA 0x080A0000ULL -#define VCPU_ID 0 /* * Stores the user specified args; it's passed to the guest and to every test @@ -589,7 +588,8 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, } static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid, - uint32_t vcpu, bool expect_failure) + struct kvm_vcpu *vcpu, + bool expect_failure) { /* * Ignore this when expecting failure as invalid intids will lead to @@ -630,8 +630,7 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { fd[f] = eventfd(0, 0); - TEST_ASSERT(fd[f] != -1, - "eventfd failed, errno: %i\n", errno); + TEST_ASSERT(fd[f] != -1, __KVM_SYSCALL_ERROR("eventfd()", fd[f])); } for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { @@ -647,7 +646,7 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, val = 1; ret = write(fd[f], &val, sizeof(uint64_t)); TEST_ASSERT(ret == sizeof(uint64_t), - "Write to KVM_IRQFD failed with ret: %d\n", ret); + __KVM_SYSCALL_ERROR("write()", ret)); } for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) @@ -660,15 +659,16 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, (tmp) < (uint64_t)(first) + (uint64_t)(num); \ (tmp)++, (i)++) -static void run_guest_cmd(struct kvm_vm *vm, int gic_fd, - struct kvm_inject_args *inject_args, - struct test_args *test_args) +static void run_guest_cmd(struct kvm_vcpu *vcpu, int gic_fd, + struct kvm_inject_args *inject_args, + struct test_args *test_args) { kvm_inject_cmd cmd = inject_args->cmd; uint32_t intid = inject_args->first_intid; uint32_t num = inject_args->num; int level = inject_args->level; bool expect_failure = inject_args->expect_failure; + struct kvm_vm *vm = vcpu->vm; uint64_t tmp; uint32_t i; @@ -706,12 +706,12 @@ static void run_guest_cmd(struct kvm_vm *vm, int gic_fd, break; case KVM_WRITE_ISPENDR: for (i = intid; i < intid + num; i++) - kvm_irq_write_ispendr_check(gic_fd, i, - VCPU_ID, expect_failure); + kvm_irq_write_ispendr_check(gic_fd, i, vcpu, + expect_failure); break; case KVM_WRITE_ISACTIVER: for (i = intid; i < intid + num; i++) - kvm_irq_write_isactiver(gic_fd, i, VCPU_ID); + kvm_irq_write_isactiver(gic_fd, i, vcpu); break; default: break; @@ -740,6 +740,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) { struct ucall uc; int gic_fd; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_inject_args inject_args; vm_vaddr_t args_gva; @@ -754,39 +755,34 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) print_args(&args); - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); ucall_init(vm, NULL); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); /* Setup the guest args page (so it gets the args). */ args_gva = vm_vaddr_alloc_page(vm); memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args)); - vcpu_args_set(vm, 0, 1, args_gva); + vcpu_args_set(vcpu, 1, args_gva); gic_fd = vgic_v3_setup(vm, 1, nr_irqs, GICD_BASE_GPA, GICR_BASE_GPA); - if (gic_fd < 0) { - print_skip("Failed to create vgic-v3, skipping"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3, skipping"); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handlers[args.eoi_split][args.level_sensitive]); while (1) { - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: kvm_inject_get_call(vm, &uc, &inject_args); - run_guest_cmd(vm, gic_fd, &inject_args, &args); + run_guest_cmd(vcpu, gic_fd, &inject_args, &args); break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx", - (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index d8909032317a..1c2749b1481a 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -74,7 +74,7 @@ struct test_params { uint64_t vcpu_memory_bytes; /* The number of vCPUs to create in the VM. */ - int vcpus; + int nr_vcpus; }; static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) @@ -104,10 +104,7 @@ static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) return 0; pfn = entry & PAGEMAP_PFN_MASK; - if (!pfn) { - print_skip("Looking up PFNs requires CAP_SYS_ADMIN"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(pfn, "Looking up PFNs requires CAP_SYS_ADMIN"); return pfn; } @@ -127,10 +124,12 @@ static void mark_page_idle(int page_idle_fd, uint64_t pfn) "Set page_idle bits for PFN 0x%" PRIx64, pfn); } -static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) +static void mark_vcpu_memory_idle(struct kvm_vm *vm, + struct perf_test_vcpu_args *vcpu_args) { - uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva; - uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages; + int vcpu_idx = vcpu_args->vcpu_idx; + uint64_t base_gva = vcpu_args->gva; + uint64_t pages = vcpu_args->pages; uint64_t page; uint64_t still_idle = 0; uint64_t no_pfn = 0; @@ -138,7 +137,7 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) int pagemap_fd; /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */ - if (overlap_memory_access && vcpu_id) + if (overlap_memory_access && vcpu_idx) return; page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); @@ -170,7 +169,7 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) */ TEST_ASSERT(no_pfn < pages / 100, "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.", - vcpu_id, no_pfn, pages); + vcpu_idx, no_pfn, pages); /* * Test that at least 90% of memory has been marked idle (the rest might @@ -183,17 +182,16 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) TEST_ASSERT(still_idle < pages / 10, "vCPU%d: Too many pages still idle (%"PRIu64 " out of %" PRIu64 ").\n", - vcpu_id, still_idle, pages); + vcpu_idx, still_idle, pages); close(page_idle_fd); close(pagemap_fd); } -static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id, - uint64_t expected_ucall) +static void assert_ucall(struct kvm_vcpu *vcpu, uint64_t expected_ucall) { struct ucall uc; - uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc); + uint64_t actual_ucall = get_ucall(vcpu, &uc); TEST_ASSERT(expected_ucall == actual_ucall, "Guest exited unexpectedly (expected ucall %" PRIu64 @@ -217,28 +215,29 @@ static bool spin_wait_for_next_iteration(int *current_iteration) static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args) { + struct kvm_vcpu *vcpu = vcpu_args->vcpu; struct kvm_vm *vm = perf_test_args.vm; - int vcpu_id = vcpu_args->vcpu_id; + int vcpu_idx = vcpu_args->vcpu_idx; int current_iteration = 0; while (spin_wait_for_next_iteration(¤t_iteration)) { switch (READ_ONCE(iteration_work)) { case ITERATION_ACCESS_MEMORY: - vcpu_run(vm, vcpu_id); - assert_ucall(vm, vcpu_id, UCALL_SYNC); + vcpu_run(vcpu); + assert_ucall(vcpu, UCALL_SYNC); break; case ITERATION_MARK_IDLE: - mark_vcpu_memory_idle(vm, vcpu_id); + mark_vcpu_memory_idle(vm, vcpu_args); break; }; - vcpu_last_completed_iteration[vcpu_id] = current_iteration; + vcpu_last_completed_iteration[vcpu_idx] = current_iteration; } } -static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) +static void spin_wait_for_vcpu(int vcpu_idx, int target_iteration) { - while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_idx]) != target_iteration) { continue; } @@ -250,12 +249,11 @@ enum access_type { ACCESS_WRITE, }; -static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) +static void run_iteration(struct kvm_vm *vm, int nr_vcpus, const char *description) { struct timespec ts_start; struct timespec ts_elapsed; - int next_iteration; - int vcpu_id; + int next_iteration, i; /* Kick off the vCPUs by incrementing iteration. */ next_iteration = ++iteration; @@ -263,23 +261,23 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) clock_gettime(CLOCK_MONOTONIC, &ts_start); /* Wait for all vCPUs to finish the iteration. */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) - spin_wait_for_vcpu(vcpu_id, next_iteration); + for (i = 0; i < nr_vcpus; i++) + spin_wait_for_vcpu(i, next_iteration); ts_elapsed = timespec_elapsed(ts_start); pr_info("%-30s: %ld.%09lds\n", description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec); } -static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, - const char *description) +static void access_memory(struct kvm_vm *vm, int nr_vcpus, + enum access_type access, const char *description) { perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1); iteration_work = ITERATION_ACCESS_MEMORY; - run_iteration(vm, vcpus, description); + run_iteration(vm, nr_vcpus, description); } -static void mark_memory_idle(struct kvm_vm *vm, int vcpus) +static void mark_memory_idle(struct kvm_vm *vm, int nr_vcpus) { /* * Even though this parallelizes the work across vCPUs, this is still a @@ -289,37 +287,37 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus) */ pr_debug("Marking VM memory idle (slow)...\n"); iteration_work = ITERATION_MARK_IDLE; - run_iteration(vm, vcpus, "Mark memory idle"); + run_iteration(vm, nr_vcpus, "Mark memory idle"); } static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *params = arg; struct kvm_vm *vm; - int vcpus = params->vcpus; + int nr_vcpus = params->nr_vcpus; - vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1, + vm = perf_test_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1, params->backing_src, !overlap_memory_access); - perf_test_start_vcpu_threads(vcpus, vcpu_thread_main); + perf_test_start_vcpu_threads(nr_vcpus, vcpu_thread_main); pr_info("\n"); - access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); + access_memory(vm, nr_vcpus, ACCESS_WRITE, "Populating memory"); /* As a control, read and write to the populated memory first. */ - access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory"); - access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory"); + access_memory(vm, nr_vcpus, ACCESS_WRITE, "Writing to populated memory"); + access_memory(vm, nr_vcpus, ACCESS_READ, "Reading from populated memory"); /* Repeat on memory that has been marked as idle. */ - mark_memory_idle(vm, vcpus); - access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory"); - mark_memory_idle(vm, vcpus); - access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); + mark_memory_idle(vm, nr_vcpus); + access_memory(vm, nr_vcpus, ACCESS_WRITE, "Writing to idle memory"); + mark_memory_idle(vm, nr_vcpus); + access_memory(vm, nr_vcpus, ACCESS_READ, "Reading from idle memory"); /* Set done to signal the vCPU threads to exit */ done = true; - perf_test_join_vcpu_threads(vcpus); + perf_test_join_vcpu_threads(nr_vcpus); perf_test_destroy_vm(vm); } @@ -347,7 +345,7 @@ int main(int argc, char *argv[]) struct test_params params = { .backing_src = DEFAULT_VM_MEM_SRC, .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, - .vcpus = 1, + .nr_vcpus = 1, }; int page_idle_fd; int opt; @@ -363,7 +361,7 @@ int main(int argc, char *argv[]) params.vcpu_memory_bytes = parse_size(optarg); break; case 'v': - params.vcpus = atoi(optarg); + params.nr_vcpus = atoi(optarg); break; case 'o': overlap_memory_access = true; @@ -379,10 +377,8 @@ int main(int argc, char *argv[]) } page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); - if (page_idle_fd < 0) { - print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(page_idle_fd >= 0, + "CONFIG_IDLE_PAGE_TRACKING is not enabled"); close(page_idle_fd); for_each_guest_mode(run_test, ¶ms); diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 6a719d065599..779ae54f89c4 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -44,28 +44,26 @@ static char *guest_data_prototype; static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { - int ret; - int vcpu_id = vcpu_args->vcpu_id; - struct kvm_vm *vm = perf_test_args.vm; - struct kvm_run *run; + struct kvm_vcpu *vcpu = vcpu_args->vcpu; + int vcpu_idx = vcpu_args->vcpu_idx; + struct kvm_run *run = vcpu->run; struct timespec start; struct timespec ts_diff; - - run = vcpu_state(vm, vcpu_id); + int ret; clock_gettime(CLOCK_MONOTONIC, &start); /* Let the guest access its memory */ - ret = _vcpu_run(vm, vcpu_id); + ret = _vcpu_run(vcpu); TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - if (get_ucall(vm, vcpu_id, NULL) != UCALL_SYNC) { + if (get_ucall(vcpu, NULL) != UCALL_SYNC) { TEST_ASSERT(false, "Invalid guest sync status: exit_reason=%s\n", exit_reason_str(run->exit_reason)); } ts_diff = timespec_elapsed(start); - PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, + PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_idx, ts_diff.tv_sec, ts_diff.tv_nsec); } @@ -223,6 +221,7 @@ static void setup_demand_paging(struct kvm_vm *vm, struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; + int ret; PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", is_minor ? "MINOR" : "MISSING", @@ -242,19 +241,18 @@ static void setup_demand_paging(struct kvm_vm *vm, } uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + TEST_ASSERT(uffd >= 0, __KVM_SYSCALL_ERROR("userfaultfd()", uffd)); uffdio_api.api = UFFD_API; uffdio_api.features = 0; - TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, - "ioctl UFFDIO_API failed: %" PRIu64, - (uint64_t)uffdio_api.api); + ret = ioctl(uffd, UFFDIO_API, &uffdio_api); + TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_API", ret)); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; uffdio_register.mode = uffd_mode; - TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, - "ioctl UFFDIO_REGISTER failed"); + ret = ioctl(uffd, UFFDIO_REGISTER, &uffdio_register); + TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_REGISTER", ret)); TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == expected_ioctls, "missing userfaultfd ioctls"); @@ -285,8 +283,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - int vcpu_id; - int r; + int r, i; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, p->src_type, p->partition_vcpu_memory_access); @@ -309,12 +306,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + for (i = 0; i < nr_vcpus; i++) { struct perf_test_vcpu_args *vcpu_args; void *vcpu_hva; void *vcpu_alias; - vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + vcpu_args = &perf_test_args.vcpu_args[i]; /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa); @@ -324,13 +321,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) * Set up user fault fd to handle demand paging * requests. */ - r = pipe2(&pipefds[vcpu_id * 2], + r = pipe2(&pipefds[i * 2], O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], p->uffd_mode, - p->uffd_delay, &uffd_args[vcpu_id], + setup_demand_paging(vm, &uffd_handler_threads[i], + pipefds[i * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[i], vcpu_hva, vcpu_alias, vcpu_args->pages * perf_test_args.guest_page_size); } @@ -350,11 +347,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - r = write(pipefds[vcpu_id * 2 + 1], &c, 1); + for (i = 0; i < nr_vcpus; i++) { + r = write(pipefds[i * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); - pthread_join(uffd_handler_threads[vcpu_id], NULL); + pthread_join(uffd_handler_threads[i], NULL); } } diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index d60a34cdfaee..f99e39a672d3 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -59,6 +59,7 @@ static void arch_cleanup_vm(struct kvm_vm *vm) static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static bool run_vcpus_while_disabling_dirty_logging; /* Host variables */ static u64 dirty_log_manual_caps; @@ -68,54 +69,59 @@ static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { - int ret; - struct kvm_vm *vm = perf_test_args.vm; + struct kvm_vcpu *vcpu = vcpu_args->vcpu; + int vcpu_idx = vcpu_args->vcpu_idx; 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; - int vcpu_id = vcpu_args->vcpu_id; + int ret; - run = vcpu_state(vm, vcpu_id); + run = vcpu->run; while (!READ_ONCE(host_quit)) { int current_iteration = READ_ONCE(iteration); clock_gettime(CLOCK_MONOTONIC, &start); - ret = _vcpu_run(vm, vcpu_id); + ret = _vcpu_run(vcpu); ts_diff = timespec_elapsed(start); TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + TEST_ASSERT(get_ucall(vcpu, 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("Got sync event from vCPU %d\n", vcpu_idx); + vcpu_last_completed_iteration[vcpu_idx] = current_iteration; pr_debug("vCPU %d updated last completed iteration to %d\n", - vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + vcpu_idx, vcpu_last_completed_iteration[vcpu_idx]); if (current_iteration) { pages_count += vcpu_args->pages; total = timespec_add(total, ts_diff); pr_debug("vCPU %d iteration %d dirty memory time: %ld.%.9lds\n", - vcpu_id, current_iteration, ts_diff.tv_sec, + vcpu_idx, current_iteration, ts_diff.tv_sec, ts_diff.tv_nsec); } else { pr_debug("vCPU %d iteration %d populate memory time: %ld.%.9lds\n", - vcpu_id, current_iteration, ts_diff.tv_sec, + vcpu_idx, current_iteration, ts_diff.tv_sec, ts_diff.tv_nsec); } + /* + * Keep running the guest while dirty logging is being disabled + * (iteration is negative) so that vCPUs are accessing memory + * for the entire duration of zapping collapsible SPTEs. + */ while (current_iteration == READ_ONCE(iteration) && - !READ_ONCE(host_quit)) {} + READ_ONCE(iteration) >= 0 && !READ_ONCE(host_quit)) {} } - avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_idx]); pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", - vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], + vcpu_idx, pages_count, vcpu_last_completed_iteration[vcpu_idx], total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); } @@ -207,14 +213,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) uint64_t guest_num_pages; uint64_t host_num_pages; uint64_t pages_per_slot; - int vcpu_id; struct timespec start; struct timespec ts_diff; struct timespec get_dirty_log_total = (struct timespec){0}; struct timespec vcpu_dirty_total = (struct timespec){0}; struct timespec avg; - struct kvm_enable_cap cap = {}; struct timespec clear_dirty_log_total = (struct timespec){0}; + int i; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, p->slots, p->backing_src, @@ -222,18 +227,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_set_wr_fract(vm, p->wr_fract); - guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); + guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift; guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_num_pages = vm_num_host_pages(mode, guest_num_pages); pages_per_slot = host_num_pages / p->slots; bitmaps = alloc_bitmaps(p->slots, pages_per_slot); - if (dirty_log_manual_caps) { - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); - } + if (dirty_log_manual_caps) + vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, + dirty_log_manual_caps); arch_setup_vm(vm, nr_vcpus); @@ -242,15 +245,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) host_quit = false; clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - vcpu_last_completed_iteration[vcpu_id] = -1; + for (i = 0; i < nr_vcpus; i++) + vcpu_last_completed_iteration[i] = -1; perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); /* Allow the vCPUs to populate memory */ pr_debug("Starting iteration %d - Populating\n", iteration); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != + for (i = 0; i < nr_vcpus; i++) { + while (READ_ONCE(vcpu_last_completed_iteration[i]) != iteration) ; } @@ -275,8 +278,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) iteration++; pr_debug("Starting iteration %d\n", iteration); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) + for (i = 0; i < nr_vcpus; i++) { + while (READ_ONCE(vcpu_last_completed_iteration[i]) != iteration) ; } @@ -305,6 +308,14 @@ static void run_test(enum vm_guest_mode mode, void *arg) } } + /* + * Run vCPUs while dirty logging is being disabled to stress disabling + * in terms of both performance and correctness. Opt-in via command + * line as this significantly increases time to disable dirty logging. + */ + if (run_vcpus_while_disabling_dirty_logging) + WRITE_ONCE(iteration, -1); + /* Disable dirty logging */ clock_gettime(CLOCK_MONOTONIC, &start); disable_dirty_logging(vm, p->slots); @@ -312,7 +323,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Disabling dirty logging time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); - /* Tell the vcpu thread to quit */ + /* + * Tell the vCPU threads to quit. No need to manually check that vCPUs + * have stopped running after disabling dirty logging, the join will + * wait for them to exit. + */ host_quit = true; perf_test_join_vcpu_threads(nr_vcpus); @@ -352,6 +367,9 @@ static void help(char *name) " Warning: a low offset can conflict with the loaded test code.\n"); guest_modes_help(); printf(" -n: Run the vCPUs in nested mode (L2)\n"); + printf(" -e: Run vCPUs while dirty logging is being disabled. This\n" + " can significantly increase runtime, especially if there\n" + " isn't a dedicated pCPU for the main thread.\n"); 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"); @@ -388,8 +406,11 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) { + while ((opt = getopt(argc, argv, "eghi:p:m:nb:f:v:os:x:")) != -1) { switch (opt) { + case 'e': + /* 'e' is for evil. */ + run_vcpus_while_disabling_dirty_logging = true; case 'g': dirty_log_manual_caps = 0; break; diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 3fcd89e195c7..9c883c94d478 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -23,8 +23,6 @@ #include "guest_modes.h" #include "processor.h" -#define VCPU_ID 1 - /* The memory slot index to track dirty pages */ #define TEST_MEM_SLOT_INDEX 1 @@ -212,34 +210,31 @@ static void sem_wait_until(sem_t *sem) static bool clear_log_supported(void) { - return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + return kvm_has_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); + vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, manual_caps); } -static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, +static void dirty_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, void *bitmap, uint32_t num_pages) { - kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); } -static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, +static void clear_log_collect_dirty_pages(struct kvm_vcpu *vcpu, 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); + kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); + kvm_vm_clear_dirty_log(vcpu->vm, slot, bitmap, 0, num_pages); } /* Should only be called after a GUEST_SYNC */ @@ -253,14 +248,14 @@ static void vcpu_handle_sync_stop(void) } } -static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR), "vcpu run failed: errno=%d", err); - TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC, "Invalid guest sync status: exit_reason=%s\n", exit_reason_str(run->exit_reason)); @@ -269,7 +264,7 @@ static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err) static bool dirty_ring_supported(void) { - return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING); + return kvm_has_cap(KVM_CAP_DIRTY_LOG_RING); } static void dirty_ring_create_vm_done(struct kvm_vm *vm) @@ -331,7 +326,7 @@ static void dirty_ring_continue_vcpu(void) sem_post(&sem_vcpu_cont); } -static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot, +static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, void *bitmap, uint32_t num_pages) { /* We only have one vcpu */ @@ -351,10 +346,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot, } /* Only have one vcpu */ - count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID), + count = dirty_ring_collect_one(vcpu_map_dirty_ring(vcpu), slot, bitmap, num_pages, &fetch_index); - cleared = kvm_vm_reset_dirty_ring(vm); + cleared = kvm_vm_reset_dirty_ring(vcpu->vm); /* Cleared pages should be the same as collected */ TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " @@ -369,12 +364,12 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot, pr_info("Iteration %ld collected %u pages\n", iteration, count); } -static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; /* A ucall-sync or ring-full event is allowed */ - if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { + if (get_ucall(vcpu, NULL) == UCALL_SYNC) { /* We should allow this to continue */ ; } else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL || @@ -408,10 +403,10 @@ struct log_mode { /* 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 (*collect_dirty_pages) (struct kvm_vcpu *vcpu, int slot, void *bitmap, uint32_t num_pages); /* Hook to call when after each vcpu run */ - void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err); + void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err); void (*before_vcpu_join) (void); } log_modes[LOG_MODE_NUM] = { { @@ -473,22 +468,22 @@ static void log_mode_create_vm_done(struct kvm_vm *vm) mode->create_vm_done(vm); } -static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, +static void log_mode_collect_dirty_pages(struct kvm_vcpu *vcpu, 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); + mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages); } -static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) { struct log_mode *mode = &log_modes[host_log_mode]; if (mode->after_vcpu_run) - mode->after_vcpu_run(vm, ret, err); + mode->after_vcpu_run(vcpu, ret, err); } static void log_mode_before_vcpu_join(void) @@ -509,16 +504,15 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size) static void *vcpu_worker(void *data) { - int ret, vcpu_fd; - struct kvm_vm *vm = data; + int ret; + struct kvm_vcpu *vcpu = data; + struct kvm_vm *vm = vcpu->vm; uint64_t *guest_array; uint64_t pages_count = 0; struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset) + sizeof(sigset_t)); sigset_t *sigset = (sigset_t *) &sigmask->sigset; - vcpu_fd = vcpu_get_fd(vm, VCPU_ID); - /* * SIG_IPI is unblocked atomically while in KVM_RUN. It causes the * ioctl to return with -EINTR, but it is still pending and we need @@ -527,7 +521,7 @@ static void *vcpu_worker(void *data) sigmask->len = 8; pthread_sigmask(0, NULL, sigset); sigdelset(sigset, SIG_IPI); - vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask); + vcpu_ioctl(vcpu, KVM_SET_SIGNAL_MASK, sigmask); sigemptyset(sigset); sigaddset(sigset, SIG_IPI); @@ -539,13 +533,13 @@ static void *vcpu_worker(void *data) generate_random_array(guest_array, TEST_PAGES_PER_LOOP); pages_count += TEST_PAGES_PER_LOOP; /* Let the guest dirty the random pages */ - ret = ioctl(vcpu_fd, KVM_RUN, NULL); + ret = __vcpu_run(vcpu); if (ret == -1 && errno == EINTR) { int sig = -1; sigwait(sigset, &sig); assert(sig == SIG_IPI); } - log_mode_after_vcpu_run(vm, ret, errno); + log_mode_after_vcpu_run(vcpu, ret, errno); } pr_info("Dirtied %"PRIu64" pages\n", pages_count); @@ -671,21 +665,17 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) } } -static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, +static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, uint64_t extra_mem_pages, void *guest_code) { struct kvm_vm *vm; - uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; 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); - kvm_vm_elf_load(vm, program_invocation_name); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif + vm = __vm_create(mode, 1, extra_mem_pages); + log_mode_create_vm_done(vm); - vm_vcpu_add_default(vm, vcpuid, guest_code); + *vcpu = vm_vcpu_add(vm, 0, guest_code); return vm; } @@ -701,6 +691,7 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; unsigned long *bmap; @@ -718,25 +709,23 @@ static void run_test(enum vm_guest_mode mode, void *arg) * (e.g., 64K page size guest will need even less memory for * page tables). */ - vm = create_vm(mode, VCPU_ID, - 2ul << (DIRTY_MEM_BITS - PAGE_SHIFT_4K), - guest_code); + vm = create_vm(mode, &vcpu, + 2ul << (DIRTY_MEM_BITS - PAGE_SHIFT_4K), guest_code); - guest_page_size = vm_get_page_size(vm); + guest_page_size = vm->page_size; /* * A little more than 1G of guest page sized pages. Cover the * case where the size is not aligned to 64 pages. */ - guest_num_pages = (1ul << (DIRTY_MEM_BITS - - vm_get_page_shift(vm))) + 3; + guest_num_pages = (1ul << (DIRTY_MEM_BITS - vm->page_shift)) + 3; guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_page_size = getpagesize(); host_num_pages = vm_num_host_pages(mode, guest_num_pages); if (!p->phys_offset) { - guest_test_phys_mem = (vm_get_max_gfn(vm) - - guest_num_pages) * guest_page_size; + guest_test_phys_mem = (vm->max_gfn - guest_num_pages) * + guest_page_size; guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size); } else { guest_test_phys_mem = p->phys_offset; @@ -781,12 +770,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) host_clear_count = 0; host_track_next_count = 0; - pthread_create(&vcpu_thread, NULL, vcpu_worker, vm); + pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu); while (iteration < p->iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(p->interval * 1000); - log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + log_mode_collect_dirty_pages(vcpu, TEST_MEM_SLOT_INDEX, bmap, host_num_pages); /* diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index b21c69a56daa..f5d59b9934f1 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -27,12 +27,6 @@ sem_t *sem; -/* Arguments for the pthreads */ -struct payload { - struct kvm_vm *vm; - uint32_t index; -}; - static void guest_code(void) { for (;;) @@ -42,14 +36,14 @@ static void guest_code(void) static void *run_vcpu(void *arg) { - struct payload *payload = (struct payload *)arg; - struct kvm_run *state = vcpu_state(payload->vm, payload->index); + struct kvm_vcpu *vcpu = arg; + struct kvm_run *run = vcpu->run; - vcpu_run(payload->vm, payload->index); + vcpu_run(vcpu); TEST_ASSERT(false, "%s: exited with reason %d: %s\n", - __func__, state->exit_reason, - exit_reason_str(state->exit_reason)); + __func__, run->exit_reason, + exit_reason_str(run->exit_reason)); pthread_exit(NULL); } @@ -92,11 +86,11 @@ static inline void check_join(pthread_t thread, void **retval) static void run_test(uint32_t run) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; cpu_set_t cpu_set; pthread_t threads[VCPU_NUM]; pthread_t throw_away; - struct payload payloads[VCPU_NUM]; void *b; uint32_t i, j; @@ -104,18 +98,13 @@ static void run_test(uint32_t run) for (i = 0; i < VCPU_NUM; i++) CPU_SET(i, &cpu_set); - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); - vm_create_irqchip(vm); + vm = vm_create(VCPU_NUM); pr_debug("%s: [%d] start vcpus\n", __func__, run); for (i = 0; i < VCPU_NUM; ++i) { - vm_vcpu_add_default(vm, i, guest_code); - payloads[i].vm = vm; - payloads[i].index = i; + vcpu = vm_vcpu_add(vm, i, guest_code); - check_create_thread(&threads[i], NULL, run_vcpu, - (void *)&payloads[i]); + check_create_thread(&threads[i], NULL, run_vcpu, vcpu); check_set_affinity(threads[i], &cpu_set); for (j = 0; j < SLEEPING_THREAD_NUM; ++j) { diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 59ece9d4e0d1..a8124f9dd68a 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -19,7 +19,7 @@ /* * KVM_ARM64_SYS_REG(sys_reg_id): Helper macro to convert * SYS_* register definitions in asm/sysreg.h to use in KVM - * calls such as get_reg() and set_reg(). + * calls such as vcpu_get_reg() and vcpu_set_reg(). */ #define KVM_ARM64_SYS_REG(sys_reg_id) \ ARM64_SYS_REG(sys_reg_Op0(sys_reg_id), \ @@ -47,25 +47,9 @@ #define MPIDR_HWID_BITMASK (0xff00fffffful) -static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr) -{ - struct kvm_one_reg reg; - reg.id = id; - reg.addr = (uint64_t)addr; - vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, ®); -} - -static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val) -{ - struct kvm_one_reg reg; - reg.id = id; - reg.addr = (uint64_t)&val; - vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, ®); -} - -void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init); -void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_init *init, void *guest_code); +void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init); +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init, void *guest_code); struct ex_regs { u64 regs[31]; @@ -117,7 +101,7 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, bool *ps4k, bool *ps16k, bool *ps64k); void vm_init_descriptor_tables(struct kvm_vm *vm); -void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); typedef void(*handler_fn)(struct ex_regs *); void vm_install_exception_handler(struct kvm_vm *vm, @@ -207,4 +191,6 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res); +uint32_t guest_get_vcpuid(void); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h index 4442081221a0..0ac6f05c63f9 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h @@ -8,6 +8,8 @@ #include <linux/kvm.h> +#include "kvm_util.h" + #define REDIST_REGION_ATTR_ADDR(count, base, flags, index) \ (((uint64_t)(count) << 52) | \ ((uint64_t)((base) >> 16) << 16) | \ @@ -26,8 +28,8 @@ void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); /* The vcpu arg only applies to private interrupts. */ -void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu); -void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu); +void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); +void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); #define KVM_IRQCHIP_NUM_PINS (1020 - 32) diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 92cef0ffb19e..24fde97f6121 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -9,9 +9,14 @@ #include "test_util.h" -#include "asm/kvm.h" +#include <linux/compiler.h> +#include "linux/hashtable.h" #include "linux/list.h" -#include "linux/kvm.h" +#include <linux/kernel.h> +#include <linux/kvm.h> +#include "linux/rbtree.h" + + #include <sys/ioctl.h> #include "sparsebit.h" @@ -21,20 +26,88 @@ #define NSEC_PER_SEC 1000000000L -/* - * Callers of kvm_util only have an incomplete/opaque description of the - * structure kvm_util is using to maintain the state of a VM. - */ -struct kvm_vm; - typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ +struct userspace_mem_region { + struct kvm_userspace_memory_region region; + struct sparsebit *unused_phy_pages; + int fd; + off_t offset; + void *host_mem; + void *host_alias; + void *mmap_start; + void *mmap_alias; + size_t mmap_size; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; +}; + +struct kvm_vcpu { + struct list_head list; + uint32_t id; + int fd; + struct kvm_vm *vm; + struct kvm_run *run; +#ifdef __x86_64__ + struct kvm_cpuid2 *cpuid; +#endif + struct kvm_dirty_gfn *dirty_gfns; + uint32_t fetch_index; + uint32_t dirty_gfns_count; +}; + +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + +struct kvm_vm { + int mode; + unsigned long type; + int kvm_fd; + int fd; + unsigned int pgtable_levels; + unsigned int page_size; + unsigned int page_shift; + unsigned int pa_bits; + unsigned int va_bits; + uint64_t max_gfn; + struct list_head vcpus; + struct userspace_mem_regions regions; + struct sparsebit *vpages_valid; + struct sparsebit *vpages_mapped; + bool has_irqchip; + bool pgd_created; + vm_paddr_t pgd; + vm_vaddr_t gdt; + vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; + uint32_t dirty_ring_size; + + /* Cache of information for binary stats interface */ + int stats_fd; + struct kvm_stats_header stats_header; + struct kvm_stats_desc *stats_desc; +}; + + +#define kvm_for_each_vcpu(vm, i, vcpu) \ + for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \ + if (!((vcpu) = vm->vcpus[i])) \ + continue; \ + else + +struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot); + /* Minimum allocated guest virtual and physical addresses */ #define KVM_UTIL_MIN_VADDR 0x2000 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 -#define DEFAULT_GUEST_PHY_PAGES 512 #define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 #define DEFAULT_STACK_PGS 5 @@ -102,49 +175,194 @@ extern const struct vm_guest_mode_params vm_guest_mode_params[]; int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); -int kvm_check_cap(long cap); -int vm_check_cap(struct kvm_vm *vm, 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); +unsigned int kvm_check_cap(long cap); + +static inline bool kvm_has_cap(long cap) +{ + return kvm_check_cap(cap); +} + +#define __KVM_SYSCALL_ERROR(_name, _ret) \ + "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) + +#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) +#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) + +#define kvm_do_ioctl(fd, cmd, arg) \ +({ \ + static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd), ""); \ + ioctl(fd, cmd, arg); \ +}) + +#define __kvm_ioctl(kvm_fd, cmd, arg) \ + kvm_do_ioctl(kvm_fd, cmd, arg) + + +#define _kvm_ioctl(kvm_fd, cmd, name, arg) \ +({ \ + int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ +}) + +#define kvm_ioctl(kvm_fd, cmd, arg) \ + _kvm_ioctl(kvm_fd, cmd, #cmd, arg) + +static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } + +#define __vm_ioctl(vm, cmd, arg) \ +({ \ + static_assert_is_vm(vm); \ + kvm_do_ioctl((vm)->fd, cmd, arg); \ +}) + +#define _vm_ioctl(vm, cmd, name, arg) \ +({ \ + int ret = __vm_ioctl(vm, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ +}) + +#define vm_ioctl(vm, cmd, arg) \ + _vm_ioctl(vm, cmd, #cmd, arg) + + +static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } + +#define __vcpu_ioctl(vcpu, cmd, arg) \ +({ \ + static_assert_is_vcpu(vcpu); \ + kvm_do_ioctl((vcpu)->fd, cmd, arg); \ +}) + +#define _vcpu_ioctl(vcpu, cmd, name, arg) \ +({ \ + int ret = __vcpu_ioctl(vcpu, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ +}) + +#define vcpu_ioctl(vcpu, cmd, arg) \ + _vcpu_ioctl(vcpu, cmd, #cmd, arg) + +/* + * Looks up and returns the value corresponding to the capability + * (KVM_CAP_*) given by cap. + */ +static inline int vm_check_cap(struct kvm_vm *vm, long cap) +{ + int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); + + TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret)); + return ret; +} + +static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} +static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} + void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); const char *vm_guest_mode_string(uint32_t i); -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_restart(struct kvm_vm *vmp); void kvm_vm_release(struct kvm_vm *vmp); -void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); -void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages); -uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); - int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); - void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); int kvm_memfd_alloc(size_t size, bool hugepages); void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); -/* - * VM VCPU Dump - * - * Input Args: - * stream - Output FILE stream - * vm - Virtual Machine - * vcpuid - VCPU ID - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the current state of the VCPU specified by @vcpuid, within the VM - * given by @vm, to the FILE stream given by @stream. - */ -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, - uint8_t indent); +static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +{ + struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; + + vm_ioctl(vm, KVM_GET_DIRTY_LOG, &args); +} + +static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages) +{ + struct kvm_clear_dirty_log args = { + .dirty_bitmap = log, + .slot = slot, + .first_page = first_page, + .num_pages = num_pages + }; + + vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); +} + +static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +{ + return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); +} + +static inline int vm_get_stats_fd(struct kvm_vm *vm) +{ + int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + return fd; +} + +static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) +{ + ssize_t ret; + + ret = read(stats_fd, header, sizeof(*header)); + TEST_ASSERT(ret == sizeof(*header), "Read stats header"); +} + +struct kvm_stats_desc *read_stats_descriptors(int stats_fd, + struct kvm_stats_header *header); + +static inline ssize_t get_stats_descriptor_size(struct kvm_stats_header *header) +{ + /* + * The base size of the descriptor is defined by KVM's ABI, but the + * size of the name field is variable, as far as KVM's ABI is + * concerned. For a given instance of KVM, the name field is the same + * size for all stats and is provided in the overall stats header. + */ + return sizeof(struct kvm_stats_desc) + header->name_size; +} + +static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc *stats, + int index, + struct kvm_stats_header *header) +{ + /* + * Note, size_desc includes the size of the name field, which is + * variable. i.e. this is NOT equivalent to &stats_desc[i]. + */ + return (void *)stats + index * get_stats_descriptor_size(header); +} + +void read_stat_data(int stats_fd, struct kvm_stats_header *header, + struct kvm_stats_desc *desc, uint64_t *data, + size_t max_elements); + +void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, + size_t max_elements); + +static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) +{ + uint64_t data; + + __vm_get_stat(vm, stat_name, &data, 1); + return data; +} void vm_create_irqchip(struct kvm_vm *vm); @@ -157,18 +375,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, uint64_t guest_paddr, uint32_t slot, uint64_t npages, uint32_t flags); -void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, - void *arg); -int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, - void *arg); -void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); -int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg); -void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); -int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); @@ -180,42 +390,219 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); -/* - * Address Guest Virtual to Guest Physical - * - * Input Args: - * vm - Virtual Machine - * gva - VM virtual address - * - * Output Args: None - * - * Return: - * Equivalent VM physical address - * - * Returns the VM physical address of the translated VM virtual - * address given by @gva. - */ -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); - -struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); -int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); -int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); -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); +void vcpu_run(struct kvm_vcpu *vcpu); +int _vcpu_run(struct kvm_vcpu *vcpu); + +static inline int __vcpu_run(struct kvm_vcpu *vcpu) +{ + return __vcpu_ioctl(vcpu, KVM_RUN, NULL); +} + +void vcpu_run_complete_io(struct kvm_vcpu *vcpu); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); + +static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, + uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vcpu_ioctl(vcpu, KVM_ENABLE_CAP, &enable_cap); +} + +static inline void vcpu_guest_debug_set(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *debug) +{ + vcpu_ioctl(vcpu, KVM_SET_GUEST_DEBUG, debug); +} + +static inline void vcpu_mp_state_get(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_GET_MP_STATE, mp_state); +} +static inline void vcpu_mp_state_set(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_SET_MP_STATE, mp_state); +} + +static inline void vcpu_regs_get(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_GET_REGS, regs); +} + +static inline void vcpu_regs_set(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_SET_REGS, regs); +} +static inline void vcpu_sregs_get(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_GET_SREGS, sregs); + +} +static inline void vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline int _vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + return __vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline void vcpu_fpu_get(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_GET_FPU, fpu); +} +static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); +} + +static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + + return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); +} +static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} +static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + + vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); +} +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} + +#ifdef __KVM_HAVE_VCPU_EVENTS +static inline void vcpu_events_get(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_GET_VCPU_EVENTS, events); +} +static inline void vcpu_events_set(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_SET_VCPU_EVENTS, events); +} +#endif +#ifdef __x86_64__ +static inline void vcpu_nested_state_get(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_GET_NESTED_STATE, state); +} +static inline int __vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + return __vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} + +static inline void vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} +#endif +static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + return fd; +} + +int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); + +static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +{ + int ret = __kvm_has_device_attr(dev_fd, group, attr); + + TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); +} + +int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_get(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_get(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); +} + +int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_set(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_set(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); +} + +static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + return __kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); +int __kvm_create_device(struct kvm_vm *vm, uint64_t type); + +static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) +{ + int fd = __kvm_create_device(vm, type); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_DEVICE, fd)); + return fd; +} + +void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); /* * VM VCPU Args Set * * Input Args: * vm - Virtual Machine - * vcpuid - VCPU ID * num - number of arguments * ... - arguments, each of type uint64_t * @@ -223,59 +610,16 @@ void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); * * Return: None * - * Sets the first @num function input registers of the VCPU with @vcpuid, - * per the C calling convention of the architecture, to the values given - * as variable args. Each of the variable args is expected to be of type - * uint64_t. The maximum @num can be is specific to the architecture. + * Sets the first @num input parameters for the function at @vcpu's entry point, + * per the C calling convention of the architecture, to the values given as + * variable args. Each of the variable args is expected to be of type uint64_t. + * The maximum @num can be is specific to the architecture. */ -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...); - -void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_fpu *fpu); -void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_fpu *fpu); -void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); -void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); -#ifdef __KVM_HAVE_VCPU_EVENTS -void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); -void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); -#endif -#ifdef __x86_64__ -void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state); -int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state, bool ignore_error); -#endif -void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid); - -int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); -int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); -int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd); -int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test); -int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write); -int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write); +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); + void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); -int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr); -int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr); -int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write); -int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write); - #define KVM_MAX_IRQ_ROUTES 4096 struct kvm_irq_routing *kvm_gsi_routing_create(void); @@ -286,26 +630,6 @@ void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); const char *exit_reason_str(unsigned int exit_reason); -void virt_pgd_alloc(struct kvm_vm *vm); - -/* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * - * Within @vm, creates a virtual translation for the page starting - * at @vaddr to the page starting at @paddr. - */ -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); - vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, uint32_t memslot); vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, @@ -313,55 +637,54 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); /* - * Create a VM with reasonable defaults - * - * Input Args: - * vcpuid - The id of the single VCPU to add to the VM. - * extra_mem_pages - The number of extra pages to add (this will - * decide how much extra space we will need to - * setup the page tables using memslot 0) - * guest_code - The vCPU's entry point - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. + * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also + * loads the test binary into guest memory and creates an IRQ chip (x86 only). + * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to + * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code); +struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages); +struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, + uint64_t nr_extra_pages); + +static inline struct kvm_vm *vm_create_barebones(void) +{ + return ____vm_create(VM_MODE_DEFAULT, 0); +} -/* Same as vm_create_default, but can be used for more than one vcpu */ -struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]); +static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) +{ + return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0); +} -/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ -struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t slot0_mem_pages, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]); +struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, + void *guest_code, struct kvm_vcpu *vcpus[]); -/* Create a default VM without any vcpus. */ -struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages); +static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, + void *guest_code, + struct kvm_vcpu *vcpus[]) +{ + return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0, + guest_code, vcpus); +} /* - * Adds a vCPU with reasonable defaults (e.g. a stack) - * - * Input Args: - * vm - Virtual Machine - * vcpuid - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point + * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages + * additional pages of guest memory. Returns the VM and vCPU (via out param). */ -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); +struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code); -bool vm_is_unrestricted_guest(struct kvm_vm *vm); +static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_with_one_vcpu(vcpu, 0, guest_code); +} -unsigned int vm_get_page_size(struct kvm_vm *vm); -unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned long vm_compute_max_gfn(struct kvm_vm *vm); -uint64_t vm_get_max_gfn(struct kvm_vm *vm); -int vm_get_fd(struct kvm_vm *vm); +struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); @@ -381,11 +704,6 @@ struct kvm_userspace_memory_region * kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end); -struct kvm_dirty_log * -allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region); - -int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); - #define sync_global_to_guest(vm, g) ({ \ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ @@ -396,11 +714,124 @@ 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); +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); + +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent); + +static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent) +{ + vcpu_arch_dump(stream, vcpu, indent); +} + +/* + * Adds a vCPU with reasonable defaults (e.g. a stack) + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - The id of the VCPU to add to the VM. + * guest_code - The vCPU's entry point + */ +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code); + +static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) +{ + return vm_arch_vcpu_add(vm, vcpu_id, guest_code); +} + +/* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); + +static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, + uint32_t vcpu_id) +{ + return vm_arch_vcpu_recreate(vm, vcpu_id); +} + +void vcpu_arch_free(struct kvm_vcpu *vcpu); + +void virt_arch_pgd_alloc(struct kvm_vm *vm); + +static inline void virt_pgd_alloc(struct kvm_vm *vm) +{ + virt_arch_pgd_alloc(vm); +} + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within @vm, creates a virtual translation for the page starting + * at @vaddr to the page starting at @paddr. + */ +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); + +static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + virt_arch_pg_map(vm, vaddr, paddr); +} + + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gva - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Returns the VM physical address of the translated VM virtual + * address given by @gva. + */ +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); + +static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + return addr_arch_gva2gpa(vm, gva); +} + +/* + * Virtual Translation Tables Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps to the FILE stream given by @stream, the contents of all the + * virtual translation tables for the VM given by @vm. + */ +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + virt_arch_dump(stream, vm, indent); +} -int vm_get_stats_fd(struct kvm_vm *vm); -int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid); -uint32_t guest_get_vcpuid(void); +static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) +{ + return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); +} #endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h index d822cb670f1c..eaa88df0555a 100644 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -25,7 +25,8 @@ struct perf_test_vcpu_args { uint64_t pages; /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; + struct kvm_vcpu *vcpu; + int vcpu_idx; }; struct perf_test_args { @@ -44,7 +45,7 @@ struct perf_test_args { extern struct perf_test_args perf_test_args; -struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, +struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, uint64_t vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access); @@ -57,6 +58,6 @@ void perf_test_join_vcpu_threads(int vcpus); void perf_test_guest_code(uint32_t vcpu_id); uint64_t perf_test_nested_pages(int nr_vcpus); -void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus); +void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]); #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 4fcfd1c0389d..d00d213c3805 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -38,26 +38,6 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, KVM_REG_RISCV_TIMER_REG(name), \ KVM_REG_SIZE_U64) -static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, - unsigned long *addr) -{ - struct kvm_one_reg reg; - - reg.id = id; - reg.addr = (unsigned long)addr; - vcpu_get_reg(vm, vcpuid, ®); -} - -static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, - unsigned long val) -{ - struct kvm_one_reg reg; - - reg.id = id; - reg.addr = (unsigned long)&val; - vcpu_set_reg(vm, vcpuid, ®); -} - /* L3 index Bit[47:39] */ #define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL #define PGTBL_L3_INDEX_SHIFT 39 diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 99e0dcdc923f..5c5a88180b6c 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -34,6 +34,13 @@ static inline int _no_printf(const char *format, ...) { return 0; } #endif void print_skip(const char *fmt, ...) __attribute__((format(printf, 1, 2))); +#define __TEST_REQUIRE(f, fmt, ...) \ +do { \ + if (!(f)) \ + ksft_exit_skip("- " fmt "\n", ##__VA_ARGS__); \ +} while (0) + +#define TEST_REQUIRE(f) __TEST_REQUIRE(f, "Requirement not met: %s", #f) ssize_t test_write(int fd, const void *buf, size_t count); ssize_t test_read(int fd, void *buf, size_t count); diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index 9eecc9d40b79..ee79d180e07e 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -6,6 +6,7 @@ */ #ifndef SELFTEST_KVM_UCALL_COMMON_H #define SELFTEST_KVM_UCALL_COMMON_H +#include "test_util.h" /* Common ucalls */ enum { @@ -16,7 +17,7 @@ enum { UCALL_UNHANDLED, }; -#define UCALL_MAX_ARGS 6 +#define UCALL_MAX_ARGS 7 struct ucall { uint64_t cmd; @@ -26,17 +27,26 @@ struct ucall { void ucall_init(struct kvm_vm *vm, void *arg); void ucall_uninit(struct kvm_vm *vm); void ucall(uint64_t cmd, int nargs, ...); -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) #define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) #define GUEST_DONE() ucall(UCALL_DONE, 0) -#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \ - if (!(_condition)) \ - ucall(UCALL_ABORT, 2 + _nargs, \ - "Failed guest assert: " \ - _condstr, __LINE__, _args); \ + +enum guest_assert_builtin_args { + GUEST_ERROR_STRING, + GUEST_FILE, + GUEST_LINE, + GUEST_ASSERT_BUILTIN_NARGS +}; + +#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) \ +do { \ + if (!(_condition)) \ + ucall(UCALL_ABORT, GUEST_ASSERT_BUILTIN_NARGS + _nargs, \ + "Failed guest assert: " _condstr, \ + __FILE__, __LINE__, ##_args); \ } while (0) #define GUEST_ASSERT(_condition) \ @@ -56,4 +66,45 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); #define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) +#define __REPORT_GUEST_ASSERT(_ucall, fmt, _args...) \ + TEST_FAIL("%s at %s:%ld\n" fmt, \ + (const char *)(_ucall).args[GUEST_ERROR_STRING], \ + (const char *)(_ucall).args[GUEST_FILE], \ + (_ucall).args[GUEST_LINE], \ + ##_args) + +#define GUEST_ASSERT_ARG(ucall, i) ((ucall).args[GUEST_ASSERT_BUILTIN_NARGS + i]) + +#define REPORT_GUEST_ASSERT(ucall) \ + __REPORT_GUEST_ASSERT((ucall), "") + +#define REPORT_GUEST_ASSERT_1(ucall, fmt) \ + __REPORT_GUEST_ASSERT((ucall), \ + fmt, \ + GUEST_ASSERT_ARG((ucall), 0)) + +#define REPORT_GUEST_ASSERT_2(ucall, fmt) \ + __REPORT_GUEST_ASSERT((ucall), \ + fmt, \ + GUEST_ASSERT_ARG((ucall), 0), \ + GUEST_ASSERT_ARG((ucall), 1)) + +#define REPORT_GUEST_ASSERT_3(ucall, fmt) \ + __REPORT_GUEST_ASSERT((ucall), \ + fmt, \ + GUEST_ASSERT_ARG((ucall), 0), \ + GUEST_ASSERT_ARG((ucall), 1), \ + GUEST_ASSERT_ARG((ucall), 2)) + +#define REPORT_GUEST_ASSERT_4(ucall, fmt) \ + __REPORT_GUEST_ASSERT((ucall), \ + fmt, \ + GUEST_ASSERT_ARG((ucall), 0), \ + GUEST_ASSERT_ARG((ucall), 1), \ + GUEST_ASSERT_ARG((ucall), 2), \ + GUEST_ASSERT_ARG((ucall), 3)) + +#define REPORT_GUEST_ASSERT_N(ucall, fmt, args...) \ + __REPORT_GUEST_ASSERT((ucall), fmt, ##args) + #endif /* SELFTEST_KVM_UCALL_COMMON_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index ac88557dcc9a..bed316fdecd5 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -35,6 +35,7 @@ #define APIC_SPIV_APIC_ENABLED (1 << 8) #define APIC_IRR 0x200 #define APIC_ICR 0x300 +#define APIC_LVTCMCI 0x2f0 #define APIC_DEST_SELF 0x40000 #define APIC_DEST_ALLINC 0x80000 #define APIC_DEST_ALLBUT 0xC0000 diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index cc5d14a45702..3c9260f8e116 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -241,7 +241,7 @@ struct hv_enlightened_vmcs { extern struct hv_enlightened_vmcs *current_evmcs; extern struct hv_vp_assist_page *current_vp_assist; -int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); +int vcpu_enable_evmcs(struct kvm_vcpu *vcpu); static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) { diff --git a/tools/testing/selftests/kvm/include/x86_64/mce.h b/tools/testing/selftests/kvm/include/x86_64/mce.h new file mode 100644 index 000000000000..6119321f3f5d --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/mce.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/mce.h + * + * Copyright (C) 2022, Google LLC. + */ + +#ifndef SELFTEST_KVM_MCE_H +#define SELFTEST_KVM_MCE_H + +#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */ +#define MCG_SER_P BIT_ULL(24) /* MCA recovery/new status bits */ +#define MCG_LMCE_P BIT_ULL(27) /* Local machine check supported */ +#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */ +#define KVM_MAX_MCE_BANKS 32 +#define MCG_CAP_BANKS_MASK 0xff /* Bit 0-7 of the MCG_CAP register are #banks */ +#define MCI_STATUS_VAL (1ULL << 63) /* valid error */ +#define MCI_STATUS_UC (1ULL << 61) /* uncorrected error */ +#define MCI_STATUS_EN (1ULL << 60) /* error enabled */ +#define MCI_STATUS_MISCV (1ULL << 59) /* misc error reg. valid */ +#define MCI_STATUS_ADDRV (1ULL << 58) /* addr reg. valid */ +#define MCM_ADDR_PHYS 2 /* physical address */ +#define MCI_CTL2_CMCI_EN BIT_ULL(30) + +#endif /* SELFTEST_KVM_MCE_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 6ce185449259..45edf45821d0 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -15,8 +15,12 @@ #include <asm/msr-index.h> #include <asm/prctl.h> +#include <linux/stringify.h> + #include "../kvm_util.h" +#define NMI_VECTOR 0x02 + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -41,24 +45,122 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) -/* CPUID.1.ECX */ -#define CPUID_VMX (1ul << 5) -#define CPUID_SMX (1ul << 6) -#define CPUID_PCID (1ul << 17) -#define CPUID_XSAVE (1ul << 26) +/* Note, these are ordered alphabetically to match kvm_cpuid_entry2. Eww. */ +enum cpuid_output_regs { + KVM_CPUID_EAX, + KVM_CPUID_EBX, + KVM_CPUID_ECX, + KVM_CPUID_EDX +}; -/* CPUID.7.EBX */ -#define CPUID_FSGSBASE (1ul << 0) -#define CPUID_SMEP (1ul << 7) -#define CPUID_SMAP (1ul << 20) +/* + * Pack the information into a 64-bit value so that each X86_FEATURE_XXX can be + * passed by value with no overhead. + */ +struct kvm_x86_cpu_feature { + u32 function; + u16 index; + u8 reg; + u8 bit; +}; +#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \ +({ \ + struct kvm_x86_cpu_feature feature = { \ + .function = fn, \ + .index = idx, \ + .reg = KVM_CPUID_##gpr, \ + .bit = __bit, \ + }; \ + \ + feature; \ +}) -/* CPUID.7.ECX */ -#define CPUID_UMIP (1ul << 2) -#define CPUID_PKU (1ul << 3) -#define CPUID_LA57 (1ul << 16) +/* + * Basic Leafs, a.k.a. Intel defined + */ +#define X86_FEATURE_MWAIT KVM_X86_CPU_FEATURE(0x1, 0, ECX, 3) +#define X86_FEATURE_VMX KVM_X86_CPU_FEATURE(0x1, 0, ECX, 5) +#define X86_FEATURE_SMX KVM_X86_CPU_FEATURE(0x1, 0, ECX, 6) +#define X86_FEATURE_PDCM KVM_X86_CPU_FEATURE(0x1, 0, ECX, 15) +#define X86_FEATURE_PCID KVM_X86_CPU_FEATURE(0x1, 0, ECX, 17) +#define X86_FEATURE_X2APIC KVM_X86_CPU_FEATURE(0x1, 0, ECX, 21) +#define X86_FEATURE_MOVBE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 22) +#define X86_FEATURE_TSC_DEADLINE_TIMER KVM_X86_CPU_FEATURE(0x1, 0, ECX, 24) +#define X86_FEATURE_XSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 26) +#define X86_FEATURE_OSXSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 27) +#define X86_FEATURE_RDRAND KVM_X86_CPU_FEATURE(0x1, 0, ECX, 30) +#define X86_FEATURE_MCE KVM_X86_CPU_FEATURE(0x1, 0, EDX, 7) +#define X86_FEATURE_APIC KVM_X86_CPU_FEATURE(0x1, 0, EDX, 9) +#define X86_FEATURE_CLFLUSH KVM_X86_CPU_FEATURE(0x1, 0, EDX, 19) +#define X86_FEATURE_XMM KVM_X86_CPU_FEATURE(0x1, 0, EDX, 25) +#define X86_FEATURE_XMM2 KVM_X86_CPU_FEATURE(0x1, 0, EDX, 26) +#define X86_FEATURE_FSGSBASE KVM_X86_CPU_FEATURE(0x7, 0, EBX, 0) +#define X86_FEATURE_TSC_ADJUST KVM_X86_CPU_FEATURE(0x7, 0, EBX, 1) +#define X86_FEATURE_HLE KVM_X86_CPU_FEATURE(0x7, 0, EBX, 4) +#define X86_FEATURE_SMEP KVM_X86_CPU_FEATURE(0x7, 0, EBX, 7) +#define X86_FEATURE_INVPCID KVM_X86_CPU_FEATURE(0x7, 0, EBX, 10) +#define X86_FEATURE_RTM KVM_X86_CPU_FEATURE(0x7, 0, EBX, 11) +#define X86_FEATURE_MPX KVM_X86_CPU_FEATURE(0x7, 0, EBX, 14) +#define X86_FEATURE_SMAP KVM_X86_CPU_FEATURE(0x7, 0, EBX, 20) +#define X86_FEATURE_PCOMMIT KVM_X86_CPU_FEATURE(0x7, 0, EBX, 22) +#define X86_FEATURE_CLFLUSHOPT KVM_X86_CPU_FEATURE(0x7, 0, EBX, 23) +#define X86_FEATURE_CLWB KVM_X86_CPU_FEATURE(0x7, 0, EBX, 24) +#define X86_FEATURE_UMIP KVM_X86_CPU_FEATURE(0x7, 0, ECX, 2) +#define X86_FEATURE_PKU KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3) +#define X86_FEATURE_LA57 KVM_X86_CPU_FEATURE(0x7, 0, ECX, 16) +#define X86_FEATURE_RDPID KVM_X86_CPU_FEATURE(0x7, 0, ECX, 22) +#define X86_FEATURE_SHSTK KVM_X86_CPU_FEATURE(0x7, 0, ECX, 7) +#define X86_FEATURE_IBT KVM_X86_CPU_FEATURE(0x7, 0, EDX, 20) +#define X86_FEATURE_AMX_TILE KVM_X86_CPU_FEATURE(0x7, 0, EDX, 24) +#define X86_FEATURE_SPEC_CTRL KVM_X86_CPU_FEATURE(0x7, 0, EDX, 26) +#define X86_FEATURE_ARCH_CAPABILITIES KVM_X86_CPU_FEATURE(0x7, 0, EDX, 29) +#define X86_FEATURE_PKS KVM_X86_CPU_FEATURE(0x7, 0, ECX, 31) +#define X86_FEATURE_XTILECFG KVM_X86_CPU_FEATURE(0xD, 0, EAX, 17) +#define X86_FEATURE_XTILEDATA KVM_X86_CPU_FEATURE(0xD, 0, EAX, 18) +#define X86_FEATURE_XSAVES KVM_X86_CPU_FEATURE(0xD, 1, EAX, 3) +#define X86_FEATURE_XFD KVM_X86_CPU_FEATURE(0xD, 1, EAX, 4) -/* CPUID.0x8000_0001.EDX */ -#define CPUID_GBPAGES (1ul << 26) +/* + * Extended Leafs, a.k.a. AMD defined + */ +#define X86_FEATURE_SVM KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 2) +#define X86_FEATURE_NX KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 20) +#define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) +#define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) +#define X86_FEATURE_LM KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 29) +#define X86_FEATURE_RDPRU KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 4) +#define X86_FEATURE_AMD_IBPB KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 12) +#define X86_FEATURE_NPT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 0) +#define X86_FEATURE_LBRV KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 1) +#define X86_FEATURE_NRIPS KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 3) +#define X86_FEATURE_TSCRATEMSR KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 4) +#define X86_FEATURE_PAUSEFILTER KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 10) +#define X86_FEATURE_PFTHRESHOLD KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 12) +#define X86_FEATURE_VGIF KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 16) +#define X86_FEATURE_SEV KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1) +#define X86_FEATURE_SEV_ES KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3) + +/* + * KVM defined paravirt features. + */ +#define X86_FEATURE_KVM_CLOCKSOURCE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 0) +#define X86_FEATURE_KVM_NOP_IO_DELAY KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 1) +#define X86_FEATURE_KVM_MMU_OP KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 2) +#define X86_FEATURE_KVM_CLOCKSOURCE2 KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 3) +#define X86_FEATURE_KVM_ASYNC_PF KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 4) +#define X86_FEATURE_KVM_STEAL_TIME KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 5) +#define X86_FEATURE_KVM_PV_EOI KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 6) +#define X86_FEATURE_KVM_PV_UNHALT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 7) +/* Bit 8 apparently isn't used?!?! */ +#define X86_FEATURE_KVM_PV_TLB_FLUSH KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 9) +#define X86_FEATURE_KVM_ASYNC_PF_VMEXIT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 10) +#define X86_FEATURE_KVM_PV_SEND_IPI KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 11) +#define X86_FEATURE_KVM_POLL_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 12) +#define X86_FEATURE_KVM_PV_SCHED_YIELD KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 13) +#define X86_FEATURE_KVM_ASYNC_PF_INT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 14) +#define X86_FEATURE_KVM_MSI_EXT_DEST_ID KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 15) +#define X86_FEATURE_KVM_HC_MAP_GPA_RANGE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 16) +#define X86_FEATURE_KVM_MIGRATION_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 17) /* Page table bitfield declarations */ #define PTE_PRESENT_MASK BIT_ULL(0) @@ -300,10 +402,13 @@ static inline void outl(uint16_t port, uint32_t value) __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); } -static inline void cpuid(uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void __cpuid(uint32_t function, uint32_t index, + uint32_t *eax, uint32_t *ebx, + uint32_t *ecx, uint32_t *edx) { - /* ecx is often an input as well as an output. */ + *eax = function; + *ecx = index; + asm volatile("cpuid" : "=a" (*eax), "=b" (*ebx), @@ -313,6 +418,24 @@ static inline void cpuid(uint32_t *eax, uint32_t *ebx, : "memory"); } +static inline void cpuid(uint32_t function, + uint32_t *eax, uint32_t *ebx, + uint32_t *ecx, uint32_t *edx) +{ + return __cpuid(function, 0, eax, ebx, ecx, edx); +} + +static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) +{ + uint32_t gprs[4]; + + __cpuid(feature.function, feature.index, + &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX], + &gprs[KVM_CPUID_ECX], &gprs[KVM_CPUID_EDX]); + + return gprs[feature.reg] & BIT(feature.bit); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -385,6 +508,21 @@ static inline void cpu_relax(void) asm volatile("rep; nop" ::: "memory"); } +#define vmmcall() \ + __asm__ __volatile__( \ + "vmmcall\n" \ + ) + +#define ud2() \ + __asm__ __volatile__( \ + "ud2\n" \ + ) + +#define hlt() \ + __asm__ __volatile__( \ + "hlt\n" \ + ) + bool is_intel_cpu(void); bool is_amd_cpu(void); @@ -405,39 +543,198 @@ static inline unsigned int x86_model(unsigned int eax) return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f); } -struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_x86_state *state); +struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu); +void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state); void kvm_x86_state_cleanup(struct kvm_x86_state *state); -struct kvm_msr_list *kvm_get_msr_index_list(void); +const struct kvm_msr_list *kvm_get_msr_index_list(void); +const struct kvm_msr_list *kvm_get_feature_msr_index_list(void); +bool kvm_msr_is_in_save_restore_list(uint32_t msr_index); uint64_t kvm_get_feature_msr(uint64_t msr_index); -struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid); -int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_cpuid2 *cpuid); -void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_cpuid2 *cpuid); +static inline void vcpu_msrs_get(struct kvm_vcpu *vcpu, + struct kvm_msrs *msrs) +{ + int r = __vcpu_ioctl(vcpu, KVM_GET_MSRS, msrs); + + TEST_ASSERT(r == msrs->nmsrs, + "KVM_GET_MSRS failed, r: %i (failed on MSR %x)", + r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index); +} +static inline void vcpu_msrs_set(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) +{ + int r = __vcpu_ioctl(vcpu, KVM_SET_MSRS, msrs); + + TEST_ASSERT(r == msrs->nmsrs, + "KVM_GET_MSRS failed, r: %i (failed on MSR %x)", + r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index); +} +static inline void vcpu_debugregs_get(struct kvm_vcpu *vcpu, + struct kvm_debugregs *debugregs) +{ + vcpu_ioctl(vcpu, KVM_GET_DEBUGREGS, debugregs); +} +static inline void vcpu_debugregs_set(struct kvm_vcpu *vcpu, + struct kvm_debugregs *debugregs) +{ + vcpu_ioctl(vcpu, KVM_SET_DEBUGREGS, debugregs); +} +static inline void vcpu_xsave_get(struct kvm_vcpu *vcpu, + struct kvm_xsave *xsave) +{ + vcpu_ioctl(vcpu, KVM_GET_XSAVE, xsave); +} +static inline void vcpu_xsave2_get(struct kvm_vcpu *vcpu, + struct kvm_xsave *xsave) +{ + vcpu_ioctl(vcpu, KVM_GET_XSAVE2, xsave); +} +static inline void vcpu_xsave_set(struct kvm_vcpu *vcpu, + struct kvm_xsave *xsave) +{ + vcpu_ioctl(vcpu, KVM_SET_XSAVE, xsave); +} +static inline void vcpu_xcrs_get(struct kvm_vcpu *vcpu, + struct kvm_xcrs *xcrs) +{ + vcpu_ioctl(vcpu, KVM_GET_XCRS, xcrs); +} +static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) +{ + vcpu_ioctl(vcpu, KVM_SET_XCRS, xcrs); +} + +const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); -struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_index(uint32_t function, uint32_t index); +bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_feature feature); -static inline struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_entry(uint32_t function) +static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature) { - return kvm_get_supported_cpuid_index(function, 0); + return kvm_cpuid_has(kvm_get_supported_cpuid(), feature); +} + +static inline size_t kvm_cpuid2_size(int nr_entries) +{ + return sizeof(struct kvm_cpuid2) + + sizeof(struct kvm_cpuid_entry2) * nr_entries; +} + +/* + * Allocate a "struct kvm_cpuid2* instance, with the 0-length arrary of + * entries sized to hold @nr_entries. The caller is responsible for freeing + * the struct. + */ +static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) +{ + struct kvm_cpuid2 *cpuid; + + cpuid = malloc(kvm_cpuid2_size(nr_entries)); + TEST_ASSERT(cpuid, "-ENOMEM when allocating kvm_cpuid2"); + + cpuid->nent = nr_entries; + + return cpuid; } -uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); -int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, - uint64_t msr_value); -void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, - uint64_t msr_value); +const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + uint32_t function, uint32_t index); +void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); + +static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, + uint32_t function, + uint32_t index) +{ + return (struct kvm_cpuid_entry2 *)get_cpuid_entry(vcpu->cpuid, + function, index); +} + +static inline struct kvm_cpuid_entry2 *vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, + uint32_t function) +{ + return __vcpu_get_cpuid_entry(vcpu, function, 0); +} + +static inline int __vcpu_set_cpuid(struct kvm_vcpu *vcpu) +{ + int r; + + TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first"); + r = __vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid); + if (r) + return r; + + /* On success, refresh the cache to pick up adjustments made by KVM. */ + vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); + return 0; +} + +static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) +{ + TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first"); + vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid); + + /* Refresh the cache to pick up adjustments made by KVM. */ + vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); +} + +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); + +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); +void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature, + bool set); + +static inline void vcpu_set_cpuid_feature(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature) +{ + vcpu_set_or_clear_cpuid_feature(vcpu, feature, true); + +} + +static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature) +{ + vcpu_set_or_clear_cpuid_feature(vcpu, feature, false); +} + +static inline const struct kvm_cpuid_entry2 *__kvm_get_supported_cpuid_entry(uint32_t function, + uint32_t index) +{ + return get_cpuid_entry(kvm_get_supported_cpuid(), function, index); +} + +static inline const struct kvm_cpuid_entry2 *kvm_get_supported_cpuid_entry(uint32_t function) +{ + return __kvm_get_supported_cpuid_entry(function, 0); +} + +uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index); +int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value); + +static inline void vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, + uint64_t msr_value) +{ + int r = _vcpu_set_msr(vcpu, msr_index, msr_value); + + TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); +} + +static inline uint32_t kvm_get_cpuid_max_basic(void) +{ + return kvm_get_supported_cpuid_entry(0)->eax; +} + +static inline uint32_t kvm_get_cpuid_max_extended(void) +{ + return kvm_get_supported_cpuid_entry(0x80000000)->eax; +} -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); +bool vm_is_unrestricted_guest(struct kvm_vm *vm); struct ex_regs { uint64_t rax, rcx, rdx, rbx; @@ -452,35 +749,94 @@ struct ex_regs { }; void vm_init_descriptor_tables(struct kvm_vm *vm); -void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); -uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr); -void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, - uint64_t pte); +/* If a toddler were to say "abracadabra". */ +#define KVM_EXCEPTION_MAGIC 0xabacadabaull /* - * get_cpuid() - find matching CPUID entry and return pointer to it. - */ -struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function, - uint32_t index); -/* - * 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 + * KVM selftest exception fixup uses registers to coordinate with the exception + * handler, versus the kernel's in-memory tables and KVM-Unit-Tests's in-memory + * per-CPU data. Using only registers avoids having to map memory into the + * guest, doesn't require a valid, stable GS.base, and reduces the risk of + * for recursive faults when accessing memory in the handler. The downside to + * using registers is that it restricts what registers can be used by the actual + * instruction. But, selftests are 64-bit only, making register* pressure a + * minor concern. Use r9-r11 as they are volatile, i.e. don't need* to be saved + * by the callee, and except for r11 are not implicit parameters to any + * instructions. Ideally, fixup would use r8-r10 and thus avoid implicit + * parameters entirely, but Hyper-V's hypercall ABI uses r8 and testing Hyper-V + * is higher priority than testing non-faulting SYSCALL/SYSRET. + * + * Note, the fixup handler deliberately does not handle #DE, i.e. the vector + * is guaranteed to be non-zero on fault. + * + * REGISTER INPUTS: + * r9 = MAGIC + * r10 = RIP + * r11 = new RIP on fault + * + * REGISTER OUTPUTS: + * r9 = exception vector (non-zero) */ -bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); +#define KVM_ASM_SAFE(insn) \ + "mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \ + "lea 1f(%%rip), %%r10\n\t" \ + "lea 2f(%%rip), %%r11\n\t" \ + "1: " insn "\n\t" \ + "mov $0, %[vector]\n\t" \ + "jmp 3f\n\t" \ + "2:\n\t" \ + "mov %%r9b, %[vector]\n\t" \ + "3:\n\t" + +#define KVM_ASM_SAFE_OUTPUTS(v) [vector] "=qm"(v) +#define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11" + +#define kvm_asm_safe(insn, inputs...) \ +({ \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) + +static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val) +{ + uint8_t vector; + uint32_t a, d; + + asm volatile(KVM_ASM_SAFE("rdmsr") + : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector) + : "c"(msr) + : KVM_ASM_SAFE_CLOBBERS); + + *val = (uint64_t)a | ((uint64_t)d << 32); + return vector; +} + +static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) +{ + return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); +} + +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t vaddr); +void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t vaddr, uint64_t pte); uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t a3); -struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); -void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); -struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); -void vm_xsave_req_perm(int bit); +void __vm_xsave_require_permission(int bit, const char *name); + +#define vm_xsave_require_permission(perm) \ + __vm_xsave_require_permission(perm, #perm) enum pg_level { PG_LEVEL_NONE, diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h index 2225e5077350..c8343ff84f7f 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -218,8 +218,6 @@ struct __attribute__ ((__packed__)) vmcb { struct vmcb_save_area save; }; -#define SVM_CPUID_FUNC 0x8000000a - #define SVM_VM_CR_SVM_DISABLE 4 #define SVM_SELECTOR_S_SHIFT 4 diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index a25aabd8f5e7..a339b537a575 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -13,9 +13,8 @@ #include "svm.h" #include "processor.h" -#define CPUID_SVM_BIT 2 -#define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) - +#define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_HLT 0x078 #define SVM_EXIT_MSR 0x07c #define SVM_EXIT_VMMCALL 0x081 @@ -36,21 +35,19 @@ struct svm_test_data { uint64_t msr_gpa; }; +#define stgi() \ + __asm__ __volatile__( \ + "stgi\n" \ + ) + +#define clgi() \ + __asm__ __volatile__( \ + "clgi\n" \ + ) + struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); -bool nested_svm_supported(void); -void nested_svm_check_supported(void); - -static inline bool cpu_has_svm(void) -{ - u32 eax = 0x80000001, ecx; - - asm("cpuid" : - "=a" (eax), "=c" (ecx) : "0" (eax) : "ebx", "edx"); - - return ecx & CPUID_SVM; -} int open_sev_dev_path_or_exit(void); diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index cc3604f8f1d3..99fa1410964c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -607,8 +607,6 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); -bool nested_vmx_supported(void); -void nested_vmx_check_supported(void); bool ept_1g_pages_supported(void); void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c index 17f65d514915..0b45ac593387 100644 --- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -26,163 +26,167 @@ static void stats_test(int stats_fd) int i; size_t size_desc; size_t size_data = 0; - struct kvm_stats_header *header; + struct kvm_stats_header header; char *id; struct kvm_stats_desc *stats_desc; u64 *stats_data; struct kvm_stats_desc *pdesc; + u32 type, unit, base; /* Read kvm stats header */ - header = malloc(sizeof(*header)); - TEST_ASSERT(header, "Allocate memory for stats header"); + read_stats_header(stats_fd, &header); - ret = read(stats_fd, header, sizeof(*header)); - TEST_ASSERT(ret == sizeof(*header), "Read stats header"); - size_desc = sizeof(*stats_desc) + header->name_size; + size_desc = get_stats_descriptor_size(&header); /* Read kvm stats id string */ - id = malloc(header->name_size); + id = malloc(header.name_size); TEST_ASSERT(id, "Allocate memory for id string"); - ret = read(stats_fd, id, header->name_size); - TEST_ASSERT(ret == header->name_size, "Read id string"); + + ret = read(stats_fd, id, header.name_size); + TEST_ASSERT(ret == header.name_size, "Read id string"); /* Check id string, that should start with "kvm" */ - TEST_ASSERT(!strncmp(id, "kvm", 3) && strlen(id) < header->name_size, - "Invalid KVM stats type, id: %s", id); + TEST_ASSERT(!strncmp(id, "kvm", 3) && strlen(id) < header.name_size, + "Invalid KVM stats type, id: %s", id); /* Sanity check for other fields in header */ - if (header->num_desc == 0) { + if (header.num_desc == 0) { printf("No KVM stats defined!"); return; } - /* Check overlap */ - TEST_ASSERT(header->desc_offset > 0 && header->data_offset > 0 - && header->desc_offset >= sizeof(*header) - && header->data_offset >= sizeof(*header), - "Invalid offset fields in header"); - TEST_ASSERT(header->desc_offset > header->data_offset || - (header->desc_offset + size_desc * header->num_desc <= - header->data_offset), - "Descriptor block is overlapped with data block"); - - /* Allocate memory for stats descriptors */ - stats_desc = calloc(header->num_desc, size_desc); - TEST_ASSERT(stats_desc, "Allocate memory for stats descriptors"); + /* + * The descriptor and data offsets must be valid, they must not overlap + * the header, and the descriptor and data blocks must not overlap each + * other. Note, the data block is rechecked after its size is known. + */ + TEST_ASSERT(header.desc_offset && header.desc_offset >= sizeof(header) && + header.data_offset && header.data_offset >= sizeof(header), + "Invalid offset fields in header"); + + TEST_ASSERT(header.desc_offset > header.data_offset || + (header.desc_offset + size_desc * header.num_desc <= header.data_offset), + "Descriptor block is overlapped with data block"); + /* Read kvm stats descriptors */ - ret = pread(stats_fd, stats_desc, - size_desc * header->num_desc, header->desc_offset); - TEST_ASSERT(ret == size_desc * header->num_desc, - "Read KVM stats descriptors"); + stats_desc = read_stats_descriptors(stats_fd, &header); /* Sanity check for fields in descriptors */ - for (i = 0; i < header->num_desc; ++i) { - pdesc = (void *)stats_desc + i * size_desc; + for (i = 0; i < header.num_desc; ++i) { + pdesc = get_stats_descriptor(stats_desc, i, &header); + type = pdesc->flags & KVM_STATS_TYPE_MASK; + unit = pdesc->flags & KVM_STATS_UNIT_MASK; + base = pdesc->flags & KVM_STATS_BASE_MASK; + + /* Check name string */ + TEST_ASSERT(strlen(pdesc->name) < header.name_size, + "KVM stats name (index: %d) too long", i); + /* Check type,unit,base boundaries */ - TEST_ASSERT((pdesc->flags & KVM_STATS_TYPE_MASK) - <= KVM_STATS_TYPE_MAX, "Unknown KVM stats type"); - TEST_ASSERT((pdesc->flags & KVM_STATS_UNIT_MASK) - <= KVM_STATS_UNIT_MAX, "Unknown KVM stats unit"); - TEST_ASSERT((pdesc->flags & KVM_STATS_BASE_MASK) - <= KVM_STATS_BASE_MAX, "Unknown KVM stats base"); - /* Check exponent for stats unit + TEST_ASSERT(type <= KVM_STATS_TYPE_MAX, + "Unknown KVM stats (%s) type: %u", pdesc->name, type); + TEST_ASSERT(unit <= KVM_STATS_UNIT_MAX, + "Unknown KVM stats (%s) unit: %u", pdesc->name, unit); + TEST_ASSERT(base <= KVM_STATS_BASE_MAX, + "Unknown KVM stats (%s) base: %u", pdesc->name, base); + + /* + * Check exponent for stats unit * Exponent for counter should be greater than or equal to 0 * Exponent for unit bytes should be greater than or equal to 0 * Exponent for unit seconds should be less than or equal to 0 * Exponent for unit clock cycles should be greater than or * equal to 0 + * Exponent for unit boolean should be 0 */ switch (pdesc->flags & KVM_STATS_UNIT_MASK) { case KVM_STATS_UNIT_NONE: case KVM_STATS_UNIT_BYTES: case KVM_STATS_UNIT_CYCLES: TEST_ASSERT(pdesc->exponent >= 0, - "Unsupported KVM stats unit"); + "Unsupported KVM stats (%s) exponent: %i", + pdesc->name, pdesc->exponent); break; case KVM_STATS_UNIT_SECONDS: TEST_ASSERT(pdesc->exponent <= 0, - "Unsupported KVM stats unit"); + "Unsupported KVM stats (%s) exponent: %i", + pdesc->name, pdesc->exponent); + break; + case KVM_STATS_UNIT_BOOLEAN: + TEST_ASSERT(pdesc->exponent == 0, + "Unsupported KVM stats (%s) exponent: %d", + pdesc->name, pdesc->exponent); break; } - /* Check name string */ - TEST_ASSERT(strlen(pdesc->name) < header->name_size, - "KVM stats name(%s) too long", pdesc->name); + /* Check size field, which should not be zero */ - TEST_ASSERT(pdesc->size, "KVM descriptor(%s) with size of 0", - pdesc->name); + TEST_ASSERT(pdesc->size, + "KVM descriptor(%s) with size of 0", pdesc->name); /* Check bucket_size field */ switch (pdesc->flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_LINEAR_HIST: TEST_ASSERT(pdesc->bucket_size, - "Bucket size of Linear Histogram stats (%s) is zero", - pdesc->name); + "Bucket size of Linear Histogram stats (%s) is zero", + pdesc->name); break; default: TEST_ASSERT(!pdesc->bucket_size, - "Bucket size of stats (%s) is not zero", - pdesc->name); + "Bucket size of stats (%s) is not zero", + pdesc->name); } size_data += pdesc->size * sizeof(*stats_data); } - /* Check overlap */ - TEST_ASSERT(header->data_offset >= header->desc_offset - || header->data_offset + size_data <= header->desc_offset, - "Data block is overlapped with Descriptor block"); + + /* + * Now that the size of the data block is known, verify the data block + * doesn't overlap the descriptor block. + */ + TEST_ASSERT(header.data_offset >= header.desc_offset || + header.data_offset + size_data <= header.desc_offset, + "Data block is overlapped with Descriptor block"); + /* Check validity of all stats data size */ - TEST_ASSERT(size_data >= header->num_desc * sizeof(*stats_data), - "Data size is not correct"); + TEST_ASSERT(size_data >= header.num_desc * sizeof(*stats_data), + "Data size is not correct"); + /* Check stats offset */ - for (i = 0; i < header->num_desc; ++i) { - pdesc = (void *)stats_desc + i * size_desc; + for (i = 0; i < header.num_desc; ++i) { + pdesc = get_stats_descriptor(stats_desc, i, &header); TEST_ASSERT(pdesc->offset < size_data, - "Invalid offset (%u) for stats: %s", - pdesc->offset, pdesc->name); + "Invalid offset (%u) for stats: %s", + pdesc->offset, pdesc->name); } /* Allocate memory for stats data */ stats_data = malloc(size_data); TEST_ASSERT(stats_data, "Allocate memory for stats data"); /* Read kvm stats data as a bulk */ - ret = pread(stats_fd, stats_data, size_data, header->data_offset); + ret = pread(stats_fd, stats_data, size_data, header.data_offset); TEST_ASSERT(ret == size_data, "Read KVM stats data"); /* Read kvm stats data one by one */ - size_data = 0; - for (i = 0; i < header->num_desc; ++i) { - pdesc = (void *)stats_desc + i * size_desc; - ret = pread(stats_fd, stats_data, - pdesc->size * sizeof(*stats_data), - header->data_offset + size_data); - TEST_ASSERT(ret == pdesc->size * sizeof(*stats_data), - "Read data of KVM stats: %s", pdesc->name); - size_data += pdesc->size * sizeof(*stats_data); + for (i = 0; i < header.num_desc; ++i) { + pdesc = get_stats_descriptor(stats_desc, i, &header); + read_stat_data(stats_fd, &header, pdesc, stats_data, + pdesc->size); } free(stats_data); free(stats_desc); free(id); - free(header); } static void vm_stats_test(struct kvm_vm *vm) { - int stats_fd; - - /* Get fd for VM stats */ - stats_fd = vm_get_stats_fd(vm); - TEST_ASSERT(stats_fd >= 0, "Get VM stats fd"); + int stats_fd = vm_get_stats_fd(vm); stats_test(stats_fd); close(stats_fd); TEST_ASSERT(fcntl(stats_fd, F_GETFD) == -1, "Stats fd not freed"); } -static void vcpu_stats_test(struct kvm_vm *vm, int vcpu_id) +static void vcpu_stats_test(struct kvm_vcpu *vcpu) { - int stats_fd; - - /* Get fd for VCPU stats */ - stats_fd = vcpu_get_stats_fd(vm, vcpu_id); - TEST_ASSERT(stats_fd >= 0, "Get VCPU stats fd"); + int stats_fd = vcpu_get_stats_fd(vcpu); stats_test(stats_fd); close(stats_fd); @@ -203,6 +207,7 @@ static void vcpu_stats_test(struct kvm_vm *vm, int vcpu_id) int main(int argc, char *argv[]) { int i, j; + struct kvm_vcpu **vcpus; struct kvm_vm **vms; int max_vm = DEFAULT_NUM_VM; int max_vcpu = DEFAULT_NUM_VCPU; @@ -220,26 +225,26 @@ int main(int argc, char *argv[]) } /* Check the extension for binary stats */ - if (kvm_check_cap(KVM_CAP_BINARY_STATS_FD) <= 0) { - print_skip("Binary form statistics interface is not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_BINARY_STATS_FD)); /* Create VMs and VCPUs */ vms = malloc(sizeof(vms[0]) * max_vm); TEST_ASSERT(vms, "Allocate memory for storing VM pointers"); + + vcpus = malloc(sizeof(struct kvm_vcpu *) * max_vm * max_vcpu); + TEST_ASSERT(vcpus, "Allocate memory for storing vCPU pointers"); + for (i = 0; i < max_vm; ++i) { - vms[i] = vm_create(VM_MODE_DEFAULT, - DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vms[i] = vm_create_barebones(); for (j = 0; j < max_vcpu; ++j) - vm_vcpu_add(vms[i], j); + vcpus[i * max_vcpu + j] = __vm_vcpu_add(vms[i], j); } /* Check stats read for every VM and VCPU */ for (i = 0; i < max_vm; ++i) { vm_stats_test(vms[i]); for (j = 0; j < max_vcpu; ++j) - vcpu_stats_test(vms[i], j); + vcpu_stats_test(vcpus[i * max_vcpu + j]); } for (i = 0; i < max_vm; ++i) diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index aed9dc3ca1e9..31b3cb24b9a7 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -28,11 +28,11 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus) pr_info("Testing creating %d vCPUs, with IDs %d...%d.\n", num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1); - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create_barebones(); for (i = first_vcpu_id; i < first_vcpu_id + num_vcpus; i++) /* This asserts that the vCPU was created. */ - vm_vcpu_add(vm, i); + __vm_vcpu_add(vm, i); kvm_vm_free(vm); } @@ -64,11 +64,9 @@ int main(int argc, char *argv[]) rl.rlim_max = nr_fds_wanted; int r = setrlimit(RLIMIT_NOFILE, &rl); - if (r < 0) { - printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n", + __TEST_REQUIRE(r >= 0, + "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n", old_rlim_max, nr_fds_wanted); - exit(KSFT_SKIP); - } } else { TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!"); } diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 2c4a7563a4f8..f42c6ac6d71d 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -46,11 +46,6 @@ static const char * const test_stage_string[] = { "KVM_ADJUST_MAPPINGS", }; -struct vcpu_args { - int vcpu_id; - bool vcpu_write; -}; - struct test_args { struct kvm_vm *vm; uint64_t guest_test_virt_mem; @@ -60,7 +55,7 @@ struct test_args { uint64_t large_num_pages; uint64_t host_pages_per_lpage; enum vm_mem_backing_src_type src_type; - struct vcpu_args vcpu_args[KVM_MAX_VCPUS]; + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; }; /* @@ -92,17 +87,13 @@ static uint64_t guest_test_phys_mem; */ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; -static void guest_code(int vcpu_id) +static void guest_code(bool do_write) { struct test_args *p = &test_args; - struct vcpu_args *vcpu_args = &p->vcpu_args[vcpu_id]; enum test_stage *current_stage = &guest_test_stage; uint64_t addr; int i, j; - /* Make sure vCPU args data structure is not corrupt */ - GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); - while (true) { addr = p->guest_test_virt_mem; @@ -123,7 +114,7 @@ static void guest_code(int vcpu_id) */ case KVM_CREATE_MAPPINGS: for (i = 0; i < p->large_num_pages; i++) { - if (vcpu_args->vcpu_write) + if (do_write) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -193,17 +184,14 @@ static void guest_code(int vcpu_id) static void *vcpu_worker(void *data) { - int ret; - struct vcpu_args *vcpu_args = data; - struct kvm_vm *vm = test_args.vm; - int vcpu_id = vcpu_args->vcpu_id; - struct kvm_run *run; + struct kvm_vcpu *vcpu = data; + bool do_write = !(vcpu->id % 2); struct timespec start; struct timespec ts_diff; enum test_stage stage; + int ret; - vcpu_args_set(vm, vcpu_id, 1, vcpu_id); - run = vcpu_state(vm, vcpu_id); + vcpu_args_set(vcpu, 1, do_write); while (!READ_ONCE(host_quit)) { ret = sem_wait(&test_stage_updated); @@ -213,15 +201,15 @@ static void *vcpu_worker(void *data) return NULL; clock_gettime(CLOCK_MONOTONIC_RAW, &start); - ret = _vcpu_run(vm, vcpu_id); + ret = _vcpu_run(vcpu); ts_diff = timespec_elapsed(start); TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC, "Invalid guest sync status: exit_reason=%s\n", - exit_reason_str(run->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); - pr_debug("Got sync event from vCPU %d\n", vcpu_id); + pr_debug("Got sync event from vCPU %d\n", vcpu->id); stage = READ_ONCE(*current_stage); /* @@ -230,7 +218,7 @@ static void *vcpu_worker(void *data) */ pr_debug("vCPU %d has completed stage %s\n" "execution time is: %ld.%.9lds\n\n", - vcpu_id, test_stage_string[stage], + vcpu->id, test_stage_string[stage], ts_diff.tv_sec, ts_diff.tv_nsec); ret = sem_post(&test_stage_completed); @@ -250,7 +238,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) { int ret; struct test_params *p = arg; - struct vcpu_args *vcpu_args; enum vm_mem_backing_src_type src_type = p->src_type; uint64_t large_page_size = get_backing_src_pagesz(src_type); uint64_t guest_page_size = vm_guest_mode_params[mode].page_size; @@ -260,7 +247,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) uint64_t alignment; void *host_test_mem; struct kvm_vm *vm; - int vcpu_id; /* Align up the test memory size */ alignment = max(large_page_size, guest_page_size); @@ -268,12 +254,12 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, - guest_num_pages, 0, guest_code, NULL); + vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages, + guest_code, test_args.vcpus); /* Align down GPA of the testing memslot */ if (!p->phys_offset) - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + guest_test_phys_mem = (vm->max_gfn - guest_num_pages) * guest_page_size; else guest_test_phys_mem = p->phys_offset; @@ -292,12 +278,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) test_args.host_pages_per_lpage = large_page_size / host_page_size; test_args.src_type = src_type; - for (vcpu_id = 0; vcpu_id < KVM_MAX_VCPUS; vcpu_id++) { - vcpu_args = &test_args.vcpu_args[vcpu_id]; - vcpu_args->vcpu_id = vcpu_id; - vcpu_args->vcpu_write = !(vcpu_id % 2); - } - /* Add an extra memory slot with specified backing src type */ vm_userspace_mem_region_add(vm, src_type, guest_test_phys_mem, TEST_MEM_SLOT_INDEX, guest_num_pages, 0); @@ -363,12 +343,11 @@ static void vcpus_complete_new_stage(enum test_stage stage) static void run_test(enum vm_guest_mode mode, void *arg) { - int ret; pthread_t *vcpu_threads; struct kvm_vm *vm; - int vcpu_id; struct timespec start; struct timespec ts_diff; + int ret, i; /* Create VM with vCPUs and make some pre-initialization */ vm = pre_init_before_test(mode, arg); @@ -379,10 +358,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) host_quit = false; *current_stage = KVM_BEFORE_MAPPINGS; - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &test_args.vcpu_args[vcpu_id]); - } + for (i = 0; i < nr_vcpus; i++) + pthread_create(&vcpu_threads[i], NULL, vcpu_worker, + test_args.vcpus[i]); vcpus_complete_new_stage(*current_stage); pr_info("Started all vCPUs successfully\n"); @@ -424,13 +402,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Tell the vcpu thread to quit */ host_quit = true; - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + for (i = 0; i < nr_vcpus; i++) { ret = sem_post(&test_stage_updated); TEST_ASSERT(ret == 0, "Error in sem_post"); } - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); + for (i = 0; i < nr_vcpus; i++) + pthread_join(vcpu_threads[i], NULL); ret = sem_destroy(&test_stage_updated); TEST_ASSERT(ret == 0, "Error in sem_destroy"); diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 6a041289fa80..6f5551368944 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -10,7 +10,6 @@ #include "guest_modes.h" #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000 @@ -75,7 +74,7 @@ static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm) return 1 << (vm->page_shift - 3); } -void virt_pgd_alloc(struct kvm_vm *vm) +void virt_arch_pgd_alloc(struct kvm_vm *vm) { if (!vm->pgd_created) { vm_paddr_t paddr = vm_phy_pages_alloc(vm, @@ -132,14 +131,14 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */; } -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) { uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */ _virt_pg_map(vm, vaddr, paddr, attr_idx); } -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint64_t *ptep; @@ -196,7 +195,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p #endif } -void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { int level = 4 - (vm->pgtable_levels - 1); uint64_t pgd, *ptep; @@ -213,9 +212,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init) +void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; + struct kvm_vm *vm = vcpu->vm; uint64_t sctlr_el1, tcr_el1; if (!init) @@ -227,16 +227,16 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init init->target = preferred.target; } - vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, init); + vcpu_ioctl(vcpu, KVM_ARM_VCPU_INIT, init); /* * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 * registers, which the variable argument list macros do. */ - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); - get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); - get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); + vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); /* Configure base granule size */ switch (vm->mode) { @@ -297,46 +297,49 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12); tcr_el1 |= (64 - vm->va_bits) /* T0SZ */; - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd); - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpuid); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id); } -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { uint64_t pstate, pc; - get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate); - get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc); + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate); + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n", indent, "", pstate, pc); } -void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_init *init, void *guest_code) +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init, void *guest_code) { size_t stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size : vm->page_size; uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size, DEFAULT_ARM64_GUEST_STACK_VADDR_MIN); + struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id); - vm_vcpu_add(vm, vcpuid); - aarch64_vcpu_setup(vm, vcpuid, init); + aarch64_vcpu_setup(vcpu, init); - set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); - set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + + return vcpu; } -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) { - aarch64_vcpu_add_default(vm, vcpuid, NULL, guest_code); + return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code); } -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) { va_list ap; int i; @@ -347,8 +350,8 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_start(ap, num); for (i = 0; i < num; i++) { - set_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[i]), - va_arg(ap, uint64_t)); + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.regs[i]), + va_arg(ap, uint64_t)); } va_end(ap); @@ -361,11 +364,11 @@ void kvm_exit_unexpected_exception(int vector, uint64_t ec, bool valid_ec) ; } -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vm, vcpuid, &uc) != UCALL_UNHANDLED) + if (get_ucall(vcpu, &uc) != UCALL_UNHANDLED) return; if (uc.args[2]) /* valid_ec */ { @@ -383,11 +386,11 @@ struct handlers { handler_fn exception_handlers[VECTOR_NUM][ESR_EC_NUM]; }; -void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) { extern char vectors; - set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors); } void route_exception(struct ex_regs *regs, int vector) @@ -469,19 +472,19 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, }; kvm_fd = open_kvm_dev_path_or_exit(); - vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, ipa); - TEST_ASSERT(vm_fd >= 0, "Can't create VM"); + vm_fd = __kvm_ioctl(kvm_fd, KVM_CREATE_VM, (void *)(unsigned long)ipa); + TEST_ASSERT(vm_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm_fd)); vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); - TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu"); + TEST_ASSERT(vcpu_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu_fd)); err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init); - TEST_ASSERT(err == 0, "Can't get target"); + TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_ARM_PREFERRED_TARGET, err)); err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init); - TEST_ASSERT(err == 0, "Can't get init vcpu"); + TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_ARM_VCPU_INIT, err)); err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); - TEST_ASSERT(err == 0, "Can't get MMFR0"); + TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd)); *ps4k = ((val >> 28) & 0xf) != 0xf; *ps64k = ((val >> 24) & 0xf) == 0; diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index be1d9728c4ce..ed237b744690 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -5,7 +5,6 @@ * Copyright (C) 2018, Red Hat, Inc. */ #include "kvm_util.h" -#include "../kvm_util_internal.h" static vm_vaddr_t *ucall_exit_mmio_addr; @@ -52,7 +51,7 @@ void ucall_init(struct kvm_vm *vm, void *arg) * lower and won't match physical addresses. */ bits = vm->va_bits - 1; - bits = vm->pa_bits < bits ? vm->pa_bits : bits; + bits = min(vm->pa_bits, bits); end = 1ul << bits; start = end * 5 / 8; step = end / 16; @@ -78,7 +77,7 @@ void ucall(uint64_t cmd, int nargs, ...) int i; WRITE_ONCE(uc.cmd, cmd); - nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + nargs = min(nargs, UCALL_MAX_ARGS); va_start(va, nargs); for (i = 0; i < nargs; ++i) @@ -88,9 +87,9 @@ void ucall(uint64_t cmd, int nargs, ...) WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc); } -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) { - struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct kvm_run *run = vcpu->run; struct ucall ucall = {}; if (uc) @@ -103,9 +102,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, "Unexpected ucall exit mmio address access"); memcpy(&gva, run->mmio.data, sizeof(gva)); - memcpy(&ucall, addr_gva2hva(vm, gva), sizeof(ucall)); + memcpy(&ucall, addr_gva2hva(vcpu->vm, gva), sizeof(ucall)); - vcpu_run_complete_io(vm, vcpu_id); + vcpu_run_complete_io(vcpu); if (uc) memcpy(uc, &ucall, sizeof(ucall)); } diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c index 5d45046c1b80..b5f28d21a947 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -9,7 +9,6 @@ #include <asm/kvm.h> #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "vgic.h" #include "gic.h" #include "gic_v3.h" @@ -52,31 +51,30 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, nr_vcpus, nr_vcpus_created); /* Distributor setup */ - if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, - false, &gic_fd) != 0) - return -1; + gic_fd = __kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); + if (gic_fd < 0) + return gic_fd; - kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, - 0, &nr_irqs, true); + kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs); - kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); - kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true); + kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa); nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE); virt_map(vm, gicd_base_gpa, gicd_base_gpa, nr_gic_pages); /* Redistributor setup */ redist_attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, gicr_base_gpa, 0, 0); - kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr, true); + kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr); nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_REDIST_SIZE * nr_vcpus); virt_map(vm, gicr_base_gpa, gicr_base_gpa, nr_gic_pages); - kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); return gic_fd; } @@ -89,14 +87,14 @@ int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) uint64_t val; int ret; - ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, - attr, &val, false); + ret = __kvm_device_attr_get(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val); if (ret != 0) return ret; val |= 1U << index; - ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, - attr, &val, true); + ret = __kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val); return ret; } @@ -104,8 +102,7 @@ void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) { int ret = _kvm_irq_set_level_info(gic_fd, intid, level); - TEST_ASSERT(ret == 0, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO failed, " - "rc: %i errno: %i", ret, errno); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, ret)); } int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) @@ -127,12 +124,11 @@ void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) { int ret = _kvm_arm_irq_line(vm, intid, level); - TEST_ASSERT(ret == 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", - ret, errno); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret)); } -static void vgic_poke_irq(int gic_fd, uint32_t intid, - uint32_t vcpu, uint64_t reg_off) +static void vgic_poke_irq(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu, + uint64_t reg_off) { uint64_t reg = intid / 32; uint64_t index = intid % 32; @@ -145,7 +141,7 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid, if (intid_is_private) { /* TODO: only vcpu 0 implemented for now. */ - assert(vcpu == 0); + assert(vcpu->id == 0); attr += SZ_64K; } @@ -158,17 +154,17 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid, * intid will just make the read/writes point to above the intended * register space (i.e., ICPENDR after ISPENDR). */ - kvm_device_access(gic_fd, group, attr, &val, false); + kvm_device_attr_get(gic_fd, group, attr, &val); val |= 1ULL << index; - kvm_device_access(gic_fd, group, attr, &val, true); + kvm_device_attr_set(gic_fd, group, attr, &val); } -void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu) +void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu) { vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR); } -void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu) +void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu) { vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER); } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index 13e8e3dcf984..9f54c098d9d0 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -11,7 +11,6 @@ #include <linux/elf.h> #include "kvm_util.h" -#include "kvm_util_internal.h" static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp) { diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 8784013b747c..99a575bbbc52 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -65,9 +65,9 @@ void guest_modes_append_default(void) struct kvm_s390_vm_cpu_processor info; kvm_fd = open_kvm_dev_path_or_exit(); - vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0); - kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL, - KVM_S390_VM_CPU_PROCESSOR, &info, false); + vm_fd = __kvm_ioctl(kvm_fd, KVM_CREATE_VM, NULL); + kvm_device_attr_get(vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info); close(vm_fd); close(kvm_fd); /* Starting with z13 we have 47bits of physical address */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 1665a220abcb..9889fe0d8919 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -8,7 +8,6 @@ #define _GNU_SOURCE /* for program_invocation_name */ #include "test_util.h" #include "kvm_util.h" -#include "kvm_util_internal.h" #include "processor.h" #include <assert.h> @@ -27,10 +26,7 @@ int open_path_or_exit(const char *path, int flags) int fd; fd = open(path, flags); - if (fd < 0) { - print_skip("%s not available (errno: %d)", path, errno); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno); return fd; } @@ -70,121 +66,34 @@ int open_kvm_dev_path_or_exit(void) * Looks up and returns the value corresponding to the capability * (KVM_CAP_*) given by cap. */ -int kvm_check_cap(long cap) +unsigned int kvm_check_cap(long cap) { int ret; int kvm_fd; kvm_fd = open_kvm_dev_path_or_exit(); - ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); + ret = __kvm_ioctl(kvm_fd, KVM_CHECK_EXTENSION, (void *)cap); + TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret)); close(kvm_fd); - return ret; -} - -/* VM Check Capability - * - * Input Args: - * vm - Virtual Machine - * cap - Capability - * - * Output Args: None - * - * Return: - * On success, the Value corresponding to the capability (KVM_CAP_*) - * specified by the value of cap. On failure a TEST_ASSERT failure - * is produced. - * - * Looks up and returns the value corresponding to the capability - * (KVM_CAP_*) given by cap. - */ -int vm_check_cap(struct kvm_vm *vm, long cap) -{ - int ret; - - ret = ioctl(vm->fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION VM IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); - - return ret; -} - -/* VM Enable Capability - * - * Input Args: - * vm - Virtual Machine - * cap - Capability - * - * Output Args: None - * - * Return: On success, 0. On failure a TEST_ASSERT failure is produced. - * - * Enables a capability (KVM_CAP_*) on the VM. - */ -int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) -{ - int ret; - - ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); - TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); - - 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; + return (unsigned int)ret; } void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) { - struct kvm_enable_cap cap = { 0 }; - - cap.cap = KVM_CAP_DIRTY_LOG_RING; - cap.args[0] = ring_size; - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING, ring_size); vm->dirty_ring_size = ring_size; } -static void vm_open(struct kvm_vm *vm, int perm) +static void vm_open(struct kvm_vm *vm) { - vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); + vm->kvm_fd = _open_kvm_dev_path_or_exit(O_RDWR); - if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { - print_skip("immediate_exit not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_IMMEDIATE_EXIT)); - vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, vm->type); - TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " - "rc: %i errno: %i", vm->fd, errno); + vm->fd = __kvm_ioctl(vm->kvm_fd, KVM_CREATE_VM, (void *)vm->type); + TEST_ASSERT(vm->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm->fd)); } const char *vm_guest_mode_string(uint32_t i) @@ -234,31 +143,12 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); -/* - * VM Create - * - * Input Args: - * mode - VM Mode (e.g. VM_MODE_P52V48_4K) - * phy_pages - Physical memory pages - * perm - permission - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. - * - * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K). - * When phy_pages is non-zero, a memory region of phy_pages physical pages - * is created and mapped starting at guest physical address 0. The file - * 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 nr_pages) { struct kvm_vm *vm; - pr_debug("%s: mode='%s' pages='%ld' perm='%d'\n", __func__, - vm_guest_mode_string(mode), phy_pages, perm); + pr_debug("%s: mode='%s' pages='%ld'\n", __func__, + vm_guest_mode_string(mode), nr_pages); vm = calloc(1, sizeof(*vm)); TEST_ASSERT(vm != NULL, "Insufficient Memory"); @@ -340,7 +230,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits); #endif - vm_open(vm, perm); + vm_open(vm); /* Limit to VA-bit canonical virtual addresses. */ vm->vpages_valid = sparsebit_alloc(); @@ -355,18 +245,56 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); - if (phy_pages != 0) + if (nr_pages != 0) vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - 0, 0, phy_pages, 0); + 0, 0, nr_pages, 0); return vm; } -struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages) +static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, + uint32_t nr_runnable_vcpus, + uint64_t extra_mem_pages) +{ + uint64_t nr_pages; + + TEST_ASSERT(nr_runnable_vcpus, + "Use vm_create_barebones() for VMs that _never_ have vCPUs\n"); + + TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), + "nr_vcpus = %d too large for host, max-vcpus = %d", + nr_runnable_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); + + /* + * Arbitrarily allocate 512 pages (2mb when page size is 4kb) for the + * test code and other per-VM assets that will be loaded into memslot0. + */ + nr_pages = 512; + + /* Account for the per-vCPU stacks on behalf of the test. */ + nr_pages += nr_runnable_vcpus * DEFAULT_STACK_PGS; + + /* + * Account for the number of pages needed for the page tables. The + * maximum page table size for a memory region will be when the + * smallest page size is used. Considering each page contains x page + * table descriptors, the total extra size for page tables (for extra + * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller + * than N/x*2. + */ + nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2; + + return vm_adjust_num_guest_pages(mode, nr_pages); +} + +struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, + uint64_t nr_extra_pages) { + uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus, + nr_extra_pages); struct kvm_vm *vm; - vm = vm_create(mode, pages, O_RDWR); + vm = ____vm_create(mode, nr_pages); kvm_vm_elf_load(vm, program_invocation_name); @@ -382,9 +310,7 @@ struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages) * Input Args: * mode - VM Mode (e.g. VM_MODE_P52V48_4K) * nr_vcpus - VCPU count - * slot0_mem_pages - Slot0 physical memory size * extra_mem_pages - Non-slot0 physical memory total size - * num_percpu_pages - Per-cpu physical memory pages * guest_code - Guest entry point * vcpuids - VCPU IDs * @@ -393,64 +319,39 @@ struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages) * Return: * Pointer to opaque structure that describes the created VM. * - * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), - * with customized slot0 memory size, at least 512 pages currently. + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K). * extra_mem_pages is only used to calculate the maximum page table size, * no real memory allocation for non-slot0 memory in this function. */ -struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t slot0_mem_pages, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]) +struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, + void *guest_code, struct kvm_vcpu *vcpus[]) { - uint64_t vcpu_pages, extra_pg_pages, pages; struct kvm_vm *vm; int i; - /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ - if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) - slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; - - /* The maximum page table size for a memory region will be when the - * smallest pages are used. Considering each page contains x page - * table descriptors, the total extra size for page tables (for extra - * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller - * than N/x*2. - */ - vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; - - TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), - "nr_vcpus = %d too large for host, max-vcpus = %d", - nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); - - pages = vm_adjust_num_guest_pages(mode, pages); - - vm = vm_create_without_vcpus(mode, pages); + TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array"); - for (i = 0; i < nr_vcpus; ++i) { - uint32_t vcpuid = vcpuids ? vcpuids[i] : i; + vm = __vm_create(mode, nr_vcpus, extra_mem_pages); - vm_vcpu_add_default(vm, vcpuid, guest_code); - } + for (i = 0; i < nr_vcpus; ++i) + vcpus[i] = vm_vcpu_add(vm, i, guest_code); return vm; } -struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]) +struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, - extra_mem_pages, num_percpu_pages, guest_code, vcpuids); -} + struct kvm_vcpu *vcpus[1]; + struct kvm_vm *vm; -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code, - (uint32_t []){ vcpuid }); + vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages, + guest_code, vcpus); + + *vcpu = vcpus[0]; + return vm; } /* @@ -458,7 +359,6 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, * * Input Args: * vm - VM that has been released before - * perm - permission * * Output Args: None * @@ -466,12 +366,12 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, * global state, such as the irqchip and the memory regions that are mapped * into the guest. */ -void kvm_vm_restart(struct kvm_vm *vmp, int perm) +void kvm_vm_restart(struct kvm_vm *vmp) { int ctr; struct userspace_mem_region *region; - vm_open(vmp, perm); + vm_open(vmp); if (vmp->has_irqchip) vm_create_irqchip(vmp); @@ -488,34 +388,17 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm) } } -void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +__weak struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, + uint32_t vcpu_id) { - struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; - int ret; - - ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args); - TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s", - __func__, strerror(-ret)); + return __vm_vcpu_add(vm, vcpu_id); } -void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages) +struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm) { - struct kvm_clear_dirty_log args = { - .dirty_bitmap = log, .slot = slot, - .first_page = first_page, - .num_pages = num_pages - }; - int ret; - - ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args); - TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s", - __func__, strerror(-ret)); -} + kvm_vm_restart(vm); -uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) -{ - return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS); + return vm_vcpu_recreate(vm, 0); } /* @@ -589,32 +472,9 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, return ®ion->region; } -/* - * VCPU Find - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: - * Pointer to VCPU structure - * - * Locates a vcpu structure that describes the VCPU specified by vcpuid and - * returns a pointer to it. Returns NULL if the VM doesn't contain a VCPU - * for the specified vcpuid. - */ -struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) +__weak void vcpu_arch_free(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu; - - list_for_each_entry(vcpu, &vm->vcpus, list) { - if (vcpu->id == vcpuid) - return vcpu; - } - return NULL; } /* @@ -629,43 +489,41 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) * * Removes a vCPU from a VM and frees its resources. */ -static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu) +static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { int ret; if (vcpu->dirty_gfns) { ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size); - TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, " - "rc: %i errno: %i", ret, errno); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); vcpu->dirty_gfns = NULL; } - ret = munmap(vcpu->state, vcpu_mmap_sz()); - TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i " - "errno: %i", ret, errno); + ret = munmap(vcpu->run, vcpu_mmap_sz()); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); + ret = close(vcpu->fd); - TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i " - "errno: %i", ret, errno); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("close()", ret)); list_del(&vcpu->list); + + vcpu_arch_free(vcpu); free(vcpu); } void kvm_vm_release(struct kvm_vm *vmp) { - struct vcpu *vcpu, *tmp; + struct kvm_vcpu *vcpu, *tmp; int ret; list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list) vm_vcpu_rm(vmp, vcpu); ret = close(vmp->fd); - TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" - " vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("close()", ret)); ret = close(vmp->kvm_fd); - TEST_ASSERT(ret == 0, "Close of /dev/kvm fd failed,\n" - " vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("close()", ret)); } static void __vm_mem_region_delete(struct kvm_vm *vm, @@ -681,13 +539,11 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, } region->region.memory_size = 0; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, " - "rc: %i errno: %i", ret, errno); + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); sparsebit_free(®ion->unused_phy_pages); ret = munmap(region->mmap_start, region->mmap_size); - TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i", ret, errno); + TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); free(region); } @@ -704,6 +560,12 @@ void kvm_vm_free(struct kvm_vm *vmp) if (vmp == NULL) return; + /* Free cached stats metadata and close FD */ + if (vmp->stats_fd) { + free(vmp->stats_desc); + close(vmp->stats_fd); + } + /* Free userspace_mem_regions. */ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) __vm_mem_region_delete(vmp, region, false); @@ -727,14 +589,13 @@ int kvm_memfd_alloc(size_t size, bool hugepages) memfd_flags |= MFD_HUGETLB; fd = memfd_create("kvm_selftest", memfd_flags); - TEST_ASSERT(fd != -1, "memfd_create() failed, errno: %i (%s)", - errno, strerror(errno)); + TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd)); r = ftruncate(fd, size); - TEST_ASSERT(!r, "ftruncate() failed, errno: %i (%s)", errno, strerror(errno)); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("ftruncate()", r)); r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size); - TEST_ASSERT(!r, "fallocate() failed, errno: %i (%s)", errno, strerror(errno)); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); return fd; } @@ -1000,8 +861,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, vm_mem_backing_src_alias(src_type)->flag, region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, - "test_malloc failed, mmap_start: %p errno: %i", - region->mmap_start, errno); + __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); TEST_ASSERT(!is_backing_src_hugetlb(src_type) || region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), @@ -1029,7 +889,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->region.guest_phys_addr = guest_paddr; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" @@ -1049,7 +909,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, vm_mem_backing_src_alias(src_type)->flag, region->fd, 0); TEST_ASSERT(region->mmap_alias != MAP_FAILED, - "mmap of alias failed, errno: %i", errno); + __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); /* Align host alias address */ region->host_alias = align_ptr_up(region->mmap_alias, alignment); @@ -1112,7 +972,7 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) region->region.flags = flags; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i slot: %u flags: 0x%x", @@ -1142,7 +1002,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) region->region.guest_phys_addr = new_gpa; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n" "ret: %i errno: %i slot: %u new_gpa: 0x%lx", @@ -1167,19 +1027,7 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } -/* - * VCPU mmap Size - * - * Input Args: None - * - * Output Args: None - * - * Return: - * Size of VCPU state - * - * Returns the size of the structure pointed to by the return value - * of vcpu_state(). - */ +/* Returns the size of a vCPU's kvm_run structure. */ static int vcpu_mmap_sz(void) { int dev_fd, ret; @@ -1188,59 +1036,57 @@ static int vcpu_mmap_sz(void) ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), - "%s KVM_GET_VCPU_MMAP_SIZE ioctl failed, rc: %i errno: %i", - __func__, ret, errno); + KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret)); close(dev_fd); return ret; } +static bool vcpu_exists(struct kvm_vm *vm, uint32_t vcpu_id) +{ + struct kvm_vcpu *vcpu; + + list_for_each_entry(vcpu, &vm->vcpus, list) { + if (vcpu->id == vcpu_id) + return true; + } + + return false; +} + /* - * VM VCPU Add - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: None - * - * Adds a virtual CPU to the VM specified by vm with the ID given by vcpuid. - * No additional VCPU setup is done. + * Adds a virtual CPU to the VM specified by vm with the ID given by vcpu_id. + * No additional vCPU setup is done. Returns the vCPU. */ -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { - struct vcpu *vcpu; + struct kvm_vcpu *vcpu; /* Confirm a vcpu with the specified id doesn't already exist. */ - vcpu = vcpu_find(vm, vcpuid); - if (vcpu != NULL) - TEST_FAIL("vcpu with the specified id " - "already exists,\n" - " requested vcpuid: %u\n" - " existing vcpuid: %u state: %p", - vcpuid, vcpu->id, vcpu->state); + TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id); /* Allocate and initialize new vcpu structure. */ vcpu = calloc(1, sizeof(*vcpu)); TEST_ASSERT(vcpu != NULL, "Insufficient Memory"); - vcpu->id = vcpuid; - vcpu->fd = ioctl(vm->fd, KVM_CREATE_VCPU, vcpuid); - TEST_ASSERT(vcpu->fd >= 0, "KVM_CREATE_VCPU failed, rc: %i errno: %i", - vcpu->fd, errno); - TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->state), "vcpu mmap size " + vcpu->vm = vm; + vcpu->id = vcpu_id; + vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id); + TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd)); + + TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi", - vcpu_mmap_sz(), sizeof(*vcpu->state)); - vcpu->state = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(), + vcpu_mmap_sz(), sizeof(*vcpu->run)); + vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(), PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0); - TEST_ASSERT(vcpu->state != MAP_FAILED, "mmap vcpu_state failed, " - "vcpu id: %u errno: %i", vcpuid, errno); + TEST_ASSERT(vcpu->run != MAP_FAILED, + __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED)); /* Add to linked-list of VCPUs. */ list_add(&vcpu->list, &vm->vcpus); + + return vcpu; } /* @@ -1336,8 +1182,6 @@ va_found: * vm - Virtual Machine * sz - Size in bytes * vaddr_min - Minimum starting virtual address - * data_memslot - Memory region slot for data pages - * pgd_memslot - Memory region slot for new virtual translation tables * * Output Args: None * @@ -1423,7 +1267,6 @@ vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm) * vaddr - Virtuall address to map * paddr - VM Physical Address * npages - The number of pages to map - * pgd_memslot - Memory region slot for new virtual translation tables * * Output Args: None * @@ -1534,11 +1377,10 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) * (without failing the test) if the guest memory is not shared (so * no alias exists). * - * When vm_create() and related functions are called with a shared memory - * src_type, we also create a writable, shared alias mapping of the - * underlying guest memory. This allows the host to manipulate guest memory - * without mapping that memory in the guest's address space. And, for - * userfaultfd-based demand paging, we can do so without triggering userfaults. + * Create a writable, shared virtual=>physical alias for the specific GPA. + * The primary use case is to allow the host selftest to manipulate guest + * memory without mapping said memory in the guest's address space. And, for + * userfaultfd-based demand paging, to do so without triggering userfaults. */ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) { @@ -1556,452 +1398,90 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) return (void *) ((uintptr_t) region->host_alias + offset); } -/* - * VM Create IRQ Chip - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: None - * - * Creates an interrupt controller chip for the VM specified by vm. - */ +/* Create an interrupt controller chip for the specified VM. */ void vm_create_irqchip(struct kvm_vm *vm) { - int ret; - - ret = ioctl(vm->fd, KVM_CREATE_IRQCHIP, 0); - TEST_ASSERT(ret == 0, "KVM_CREATE_IRQCHIP IOCTL failed, " - "rc: %i errno: %i", ret, errno); + vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); vm->has_irqchip = true; } -/* - * VM VCPU State - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: - * Pointer to structure that describes the state of the VCPU. - * - * Locates and returns a pointer to a structure that describes the - * state of the VCPU with the given vcpuid. - */ -struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return vcpu->state; -} - -/* - * VM VCPU Run - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: None - * - * Switch to executing the code for the VCPU given by vcpuid, within the VM - * given by vm. - */ -void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) -{ - int ret = _vcpu_run(vm, vcpuid); - TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - -int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) +int _vcpu_run(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); int rc; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); do { - rc = ioctl(vcpu->fd, KVM_RUN, NULL); + rc = __vcpu_run(vcpu); } while (rc == -1 && errno == EINTR); - assert_on_unhandled_exception(vm, vcpuid); + assert_on_unhandled_exception(vcpu); return rc; } -int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid) +/* + * Invoke KVM_RUN on a vCPU until KVM returns something other than -EINTR. + * Assert if the KVM returns an error (other than -EINTR). + */ +void vcpu_run(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret = _vcpu_run(vcpu); - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return vcpu->fd; + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_RUN, ret)); } -void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_run_complete_io(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - vcpu->state->immediate_exit = 1; - ret = ioctl(vcpu->fd, KVM_RUN, NULL); - vcpu->state->immediate_exit = 0; + vcpu->run->immediate_exit = 1; + ret = __vcpu_run(vcpu); + vcpu->run->immediate_exit = 0; TEST_ASSERT(ret == -1 && errno == EINTR, "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", ret, errno); } -void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_guest_debug *debug) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret = ioctl(vcpu->fd, KVM_SET_GUEST_DEBUG, debug); - - TEST_ASSERT(ret == 0, "KVM_SET_GUEST_DEBUG failed: %d", ret); -} - -/* - * VM VCPU Set MP State - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * mp_state - mp_state to be set - * - * Output Args: None - * - * Return: None - * - * Sets the MP state of the VCPU given by vcpuid, to the state given - * by mp_state. - */ -void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_mp_state *mp_state) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_MP_STATE, mp_state); - TEST_ASSERT(ret == 0, "KVM_SET_MP_STATE IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - /* - * 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 + * KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls. Returns a kvm_reg_list pointer, + * it is the caller's responsibility to free the list. */ -struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu) { struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; int ret; - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + ret = __vcpu_ioctl(vcpu, 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); + vcpu_ioctl(vcpu, KVM_GET_REG_LIST, reg_list); return reg_list; } -/* - * VM VCPU Regs Get - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: - * regs - current state of VCPU regs - * - * Return: None - * - * Obtains the current register state for the VCPU specified by vcpuid - * and stores it at the location given by regs. - */ -void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_REGS, regs); - TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i", - ret, errno); -} - -/* - * VM VCPU Regs Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * regs - Values to set VCPU regs to - * - * Output Args: None - * - * Return: None - * - * Sets the regs of the VCPU specified by vcpuid to the values - * given by regs. - */ -void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) +void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_REGS, regs); - TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i", - ret, errno); -} - -#ifdef __KVM_HAVE_VCPU_EVENTS -void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events); - TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i", - ret, errno); -} - -void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events); - TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i", - ret, errno); -} -#endif - -#ifdef __x86_64__ -void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, state); - TEST_ASSERT(ret == 0, - "KVM_SET_NESTED_STATE failed, ret: %i errno: %i", - ret, errno); -} - -int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state, bool ignore_error) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, state); - if (!ignore_error) { - TEST_ASSERT(ret == 0, - "KVM_SET_NESTED_STATE failed, ret: %i errno: %i", - ret, errno); - } - - return ret; -} -#endif - -/* - * VM VCPU System Regs Get - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: - * sregs - current state of VCPU system regs - * - * Return: None - * - * Obtains the current system register state for the VCPU specified by - * vcpuid and stores it at the location given by sregs. - */ -void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs); - TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i", - ret, errno); -} - -/* - * VM VCPU System Regs Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * sregs - Values to set VCPU system regs to - * - * Output Args: None - * - * Return: None - * - * Sets the system regs of the VCPU specified by vcpuid to the values - * given by sregs. - */ -void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - int ret = _vcpu_sregs_set(vm, vcpuid, sregs); - TEST_ASSERT(ret == 0, "KVM_SET_SREGS IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - -int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return ioctl(vcpu->fd, KVM_SET_SREGS, sregs); -} - -void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_FPU, fpu); - TEST_ASSERT(ret == 0, "KVM_GET_FPU failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_FPU, fpu); - TEST_ASSERT(ret == 0, "KVM_SET_FPU failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, reg); - TEST_ASSERT(ret == 0, "KVM_GET_ONE_REG failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, reg); - TEST_ASSERT(ret == 0, "KVM_SET_ONE_REG failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -/* - * VCPU Ioctl - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a VCPU fd. - */ -void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, - unsigned long cmd, void *arg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, cmd, arg); - TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, - unsigned long cmd, void *arg) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, cmd, arg); - - return ret; -} - -void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) -{ - struct vcpu *vcpu; - uint32_t size = vm->dirty_ring_size; + uint32_t page_size = vcpu->vm->page_size; + uint32_t size = vcpu->vm->dirty_ring_size; TEST_ASSERT(size > 0, "Should enable dirty ring first"); - vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid); - if (!vcpu->dirty_gfns) { void *addr; - addr = mmap(NULL, size, PROT_READ, - MAP_PRIVATE, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + addr = mmap(NULL, size, PROT_READ, MAP_PRIVATE, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private"); - addr = mmap(NULL, size, PROT_READ | PROT_EXEC, - MAP_PRIVATE, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + addr = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_PRIVATE, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec"); - addr = mmap(NULL, size, PROT_READ | PROT_WRITE, - MAP_SHARED, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed"); vcpu->dirty_gfns = addr; @@ -2012,62 +1492,10 @@ void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) } /* - * VM Ioctl - * - * Input Args: - * vm - Virtual Machine - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a VM fd. - */ -void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - int ret; - - ret = _vm_ioctl(vm, cmd, arg); - TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - return ioctl(vm->fd, cmd, arg); -} - -/* - * KVM system ioctl - * - * Input Args: - * vm - Virtual Machine - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a KVM fd. - */ -void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - int ret; - - ret = ioctl(vm->kvm_fd, cmd, arg); - TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - return ioctl(vm->kvm_fd, cmd, arg); -} - -/* * Device Ioctl */ -int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) +int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) { struct kvm_device_attr attribute = { .group = group, @@ -2078,43 +1506,31 @@ int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) return ioctl(dev_fd, KVM_HAS_DEVICE_ATTR, &attribute); } -int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) -{ - int ret = _kvm_device_check_attr(dev_fd, group, attr); - - TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); - return ret; -} - -int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd) +int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type) { - struct kvm_create_device create_dev; - int ret; + struct kvm_create_device create_dev = { + .type = type, + .flags = KVM_CREATE_DEVICE_TEST, + }; - create_dev.type = type; - create_dev.fd = -1; - create_dev.flags = test ? KVM_CREATE_DEVICE_TEST : 0; - ret = ioctl(vm_get_fd(vm), KVM_CREATE_DEVICE, &create_dev); - *fd = create_dev.fd; - return ret; + return __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev); } -int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test) +int __kvm_create_device(struct kvm_vm *vm, uint64_t type) { - int fd, ret; - - ret = _kvm_create_device(vm, type, test, &fd); + struct kvm_create_device create_dev = { + .type = type, + .fd = -1, + .flags = 0, + }; + int err; - if (!test) { - TEST_ASSERT(!ret, - "KVM_CREATE_DEVICE IOCTL failed, rc: %i errno: %i", ret, errno); - return fd; - } - return ret; + err = __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev); + TEST_ASSERT(err <= 0, "KVM_CREATE_DEVICE shouldn't return a positive value"); + return err ? : create_dev.fd; } -int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write) +int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val) { struct kvm_device_attr kvmattr = { .group = group, @@ -2122,58 +1538,20 @@ int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, .flags = 0, .addr = (uintptr_t)val, }; - int ret; - - ret = ioctl(dev_fd, write ? KVM_SET_DEVICE_ATTR : KVM_GET_DEVICE_ATTR, - &kvmattr); - return ret; -} - -int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write) -{ - int ret = _kvm_device_access(dev_fd, group, attr, val, write); - - TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; -} - -int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); - - return _kvm_device_check_attr(vcpu->fd, group, attr); -} - -int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr) -{ - int ret = _vcpu_has_device_attr(vm, vcpuid, group, attr); - - TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; -} -int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); - - return _kvm_device_access(vcpu->fd, group, attr, val, write); + return __kvm_ioctl(dev_fd, KVM_GET_DEVICE_ATTR, &kvmattr); } -int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write) +int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val) { - int ret = _vcpu_access_device_attr(vm, vcpuid, group, attr, val, write); + struct kvm_device_attr kvmattr = { + .group = group, + .attr = attr, + .flags = 0, + .addr = (uintptr_t)val, + }; - TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; + return __kvm_ioctl(dev_fd, KVM_SET_DEVICE_ATTR, &kvmattr); } /* @@ -2187,14 +1565,14 @@ int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) .level = level, }; - return _vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); + return __vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); } void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) { int ret = _kvm_irq_line(vm, irq, level); - TEST_ASSERT(ret >= 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", ret, errno); + TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret)); } struct kvm_irq_routing *kvm_gsi_routing_create(void) @@ -2233,7 +1611,7 @@ int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) int ret; assert(routing); - ret = ioctl(vm_get_fd(vm), KVM_SET_GSI_ROUTING, routing); + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); free(routing); return ret; @@ -2244,8 +1622,7 @@ void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) int ret; ret = _kvm_gsi_routing_write(vm, routing); - TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING failed, rc: %i errno: %i", - ret, errno); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_GSI_ROUTING, ret)); } /* @@ -2267,7 +1644,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { int ctr; struct userspace_mem_region *region; - struct vcpu *vcpu; + struct kvm_vcpu *vcpu; fprintf(stream, "%*smode: 0x%x\n", indent, "", vm->mode); fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); @@ -2292,8 +1669,9 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump(stream, vm, indent + 4); } fprintf(stream, "%*sVCPUs:\n", indent, ""); + list_for_each_entry(vcpu, &vm->vcpus, list) - vcpu_dump(stream, vm, vcpu->id, indent + 2); + vcpu_dump(stream, vcpu, indent + 2); } /* Known KVM exit reasons */ @@ -2447,64 +1825,11 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva) return addr_gpa2hva(vm, addr_gva2gpa(vm, gva)); } -/* - * Is Unrestricted Guest - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: True if the unrestricted guest is set to 'Y', otherwise return false. - * - * Check if the unrestricted guest flag is enabled. - */ -bool vm_is_unrestricted_guest(struct kvm_vm *vm) -{ - char val = 'N'; - size_t count; - FILE *f; - - if (vm == NULL) { - /* Ensure that the KVM vendor-specific module is loaded. */ - close(open_kvm_dev_path_or_exit()); - } - - f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); - if (f) { - count = fread(&val, sizeof(char), 1, f); - TEST_ASSERT(count == 1, "Unable to read from param file."); - fclose(f); - } - - return val == 'Y'; -} - -unsigned int vm_get_page_size(struct kvm_vm *vm) -{ - return vm->page_size; -} - -unsigned int vm_get_page_shift(struct kvm_vm *vm) -{ - return vm->page_shift; -} - -unsigned long __attribute__((weak)) vm_compute_max_gfn(struct kvm_vm *vm) +unsigned long __weak vm_compute_max_gfn(struct kvm_vm *vm) { return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; } -uint64_t vm_get_max_gfn(struct kvm_vm *vm) -{ - return vm->max_gfn; -} - -int vm_get_fd(struct kvm_vm *vm) -{ - return vm->fd; -} - static unsigned int vm_calc_num_pages(unsigned int num_pages, unsigned int page_shift, unsigned int new_page_shift, @@ -2545,14 +1870,112 @@ unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size) return vm_adjust_num_guest_pages(mode, n); } -int vm_get_stats_fd(struct kvm_vm *vm) +/* + * Read binary stats descriptors + * + * Input Args: + * stats_fd - the file descriptor for the binary stats file from which to read + * header - the binary stats metadata header corresponding to the given FD + * + * Output Args: None + * + * Return: + * A pointer to a newly allocated series of stat descriptors. + * Caller is responsible for freeing the returned kvm_stats_desc. + * + * Read the stats descriptors from the binary stats interface. + */ +struct kvm_stats_desc *read_stats_descriptors(int stats_fd, + struct kvm_stats_header *header) { - return ioctl(vm->fd, KVM_GET_STATS_FD, NULL); + struct kvm_stats_desc *stats_desc; + ssize_t desc_size, total_size, ret; + + desc_size = get_stats_descriptor_size(header); + total_size = header->num_desc * desc_size; + + stats_desc = calloc(header->num_desc, desc_size); + TEST_ASSERT(stats_desc, "Allocate memory for stats descriptors"); + + ret = pread(stats_fd, stats_desc, total_size, header->desc_offset); + TEST_ASSERT(ret == total_size, "Read KVM stats descriptors"); + + return stats_desc; } -int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid) +/* + * Read stat data for a particular stat + * + * Input Args: + * stats_fd - the file descriptor for the binary stats file from which to read + * header - the binary stats metadata header corresponding to the given FD + * desc - the binary stat metadata for the particular stat to be read + * max_elements - the maximum number of 8-byte values to read into data + * + * Output Args: + * data - the buffer into which stat data should be read + * + * Read the data values of a specified stat from the binary stats interface. + */ +void read_stat_data(int stats_fd, struct kvm_stats_header *header, + struct kvm_stats_desc *desc, uint64_t *data, + size_t max_elements) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); + size_t nr_elements = min_t(ssize_t, desc->size, max_elements); + size_t size = nr_elements * sizeof(*data); + ssize_t ret; - return ioctl(vcpu->fd, KVM_GET_STATS_FD, NULL); + TEST_ASSERT(desc->size, "No elements in stat '%s'", desc->name); + TEST_ASSERT(max_elements, "Zero elements requested for stat '%s'", desc->name); + + ret = pread(stats_fd, data, size, + header->data_offset + desc->offset); + + TEST_ASSERT(ret >= 0, "pread() failed on stat '%s', errno: %i (%s)", + desc->name, errno, strerror(errno)); + TEST_ASSERT(ret == size, + "pread() on stat '%s' read %ld bytes, wanted %lu bytes", + desc->name, size, ret); +} + +/* + * Read the data of the named stat + * + * Input Args: + * vm - the VM for which the stat should be read + * stat_name - the name of the stat to read + * max_elements - the maximum number of 8-byte values to read into data + * + * Output Args: + * data - the buffer into which stat data should be read + * + * Read the data values of a specified stat from the binary stats interface. + */ +void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, + size_t max_elements) +{ + struct kvm_stats_desc *desc; + size_t size_desc; + int i; + + if (!vm->stats_fd) { + vm->stats_fd = vm_get_stats_fd(vm); + read_stats_header(vm->stats_fd, &vm->stats_header); + vm->stats_desc = read_stats_descriptors(vm->stats_fd, + &vm->stats_header); + } + + size_desc = get_stats_descriptor_size(&vm->stats_header); + + for (i = 0; i < vm->stats_header.num_desc; ++i) { + desc = (void *)vm->stats_desc + (i * size_desc); + + if (strcmp(desc->name, stat_name)) + continue; + + read_stat_data(vm->stats_fd, &vm->stats_header, desc, + data, max_elements); + + break; + } } diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h deleted file mode 100644 index a03febc24ba6..000000000000 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ /dev/null @@ -1,128 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * tools/testing/selftests/kvm/lib/kvm_util_internal.h - * - * Copyright (C) 2018, Google LLC. - */ - -#ifndef SELFTEST_KVM_UTIL_INTERNAL_H -#define SELFTEST_KVM_UTIL_INTERNAL_H - -#include "linux/hashtable.h" -#include "linux/rbtree.h" - -#include "sparsebit.h" - -struct userspace_mem_region { - struct kvm_userspace_memory_region region; - struct sparsebit *unused_phy_pages; - int fd; - off_t offset; - void *host_mem; - void *host_alias; - void *mmap_start; - void *mmap_alias; - size_t mmap_size; - struct rb_node gpa_node; - struct rb_node hva_node; - struct hlist_node slot_node; -}; - -struct vcpu { - struct list_head list; - uint32_t id; - int fd; - struct kvm_run *state; - struct kvm_dirty_gfn *dirty_gfns; - uint32_t fetch_index; - uint32_t dirty_gfns_count; -}; - -struct userspace_mem_regions { - struct rb_root gpa_tree; - struct rb_root hva_tree; - DECLARE_HASHTABLE(slot_hash, 9); -}; - -struct kvm_vm { - int mode; - unsigned long type; - int kvm_fd; - int fd; - unsigned int pgtable_levels; - unsigned int page_size; - unsigned int page_shift; - unsigned int pa_bits; - unsigned int va_bits; - uint64_t max_gfn; - struct list_head vcpus; - struct userspace_mem_regions regions; - struct sparsebit *vpages_valid; - struct sparsebit *vpages_mapped; - bool has_irqchip; - bool pgd_created; - vm_paddr_t pgd; - vm_vaddr_t gdt; - vm_vaddr_t tss; - vm_vaddr_t idt; - vm_vaddr_t handlers; - uint32_t dirty_ring_size; -}; - -struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); - -/* - * Virtual Translation Tables Dump - * - * Input Args: - * stream - Output FILE stream - * vm - Virtual Machine - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps to the FILE stream given by @stream, the contents of all the - * virtual translation tables for the VM given by @vm. - */ -void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); - -/* - * Register Dump - * - * Input Args: - * stream - Output FILE stream - * regs - Registers - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the state of the registers given by @regs, to the FILE stream - * given by @stream. - */ -void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); - -/* - * System Register Dump - * - * Input Args: - * stream - Output FILE stream - * sregs - System registers - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the state of the system registers given by @sregs, to the FILE stream - * given by @stream. - */ -void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); - -struct userspace_mem_region * -memslot2region(struct kvm_vm *vm, uint32_t memslot); - -#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */ diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index f989ff91f022..9618b37c66f7 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -17,8 +17,8 @@ struct perf_test_args perf_test_args; static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; struct vcpu_thread { - /* The id of the vCPU. */ - int vcpu_id; + /* The index of the vCPU. */ + int vcpu_idx; /* The pthread backing the vCPU. */ pthread_t thread; @@ -36,24 +36,26 @@ static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *); /* Set to true once all vCPU threads are up and running. */ static bool all_vcpu_threads_running; +static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + /* * Continuously write to the first 8 bytes of each page in the * specified region. */ -void perf_test_guest_code(uint32_t vcpu_id) +void perf_test_guest_code(uint32_t vcpu_idx) { struct perf_test_args *pta = &perf_test_args; - struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id]; + struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_idx]; 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; + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_idx == vcpu_idx); + while (true) { for (i = 0; i < pages; i++) { uint64_t addr = gva + (i * pta->guest_page_size); @@ -68,47 +70,50 @@ void perf_test_guest_code(uint32_t vcpu_id) } } -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, +void perf_test_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, + struct kvm_vcpu *vcpus[], uint64_t vcpu_memory_bytes, bool partition_vcpu_memory_access) { struct perf_test_args *pta = &perf_test_args; struct perf_test_vcpu_args *vcpu_args; - int vcpu_id; + int i; + + for (i = 0; i < nr_vcpus; i++) { + vcpu_args = &pta->vcpu_args[i]; - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vcpu_args = &pta->vcpu_args[vcpu_id]; + vcpu_args->vcpu = vcpus[i]; + vcpu_args->vcpu_idx = i; - vcpu_args->vcpu_id = vcpu_id; if (partition_vcpu_memory_access) { vcpu_args->gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); + (i * vcpu_memory_bytes); vcpu_args->pages = vcpu_memory_bytes / pta->guest_page_size; - vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes); + vcpu_args->gpa = pta->gpa + (i * vcpu_memory_bytes); } else { vcpu_args->gva = guest_test_virt_mem; - vcpu_args->pages = (vcpus * vcpu_memory_bytes) / + vcpu_args->pages = (nr_vcpus * vcpu_memory_bytes) / pta->guest_page_size; vcpu_args->gpa = pta->gpa; } - vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + vcpu_args_set(vcpus[i], 1, i); pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_args->gpa, vcpu_args->gpa + + i, vcpu_args->gpa, vcpu_args->gpa + (vcpu_args->pages * pta->guest_page_size)); } } -struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, +struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, uint64_t vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access) { struct perf_test_args *pta = &perf_test_args; struct kvm_vm *vm; - uint64_t guest_num_pages, slot0_pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages, slot0_pages = 0; uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); uint64_t region_end_gfn; int i; @@ -125,7 +130,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, pta->guest_page_size = vm_guest_mode_params[mode].page_size; guest_num_pages = vm_adjust_num_guest_pages(mode, - (vcpus * vcpu_memory_bytes) / pta->guest_page_size); + (nr_vcpus * vcpu_memory_bytes) / pta->guest_page_size); TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0, "Guest memory size is not host page size aligned."); @@ -140,20 +145,20 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, * in-memory data structures. */ if (pta->nested) - slot0_pages += perf_test_nested_pages(vcpus); + slot0_pages += perf_test_nested_pages(nr_vcpus); /* * Pass guest_num_pages to populate the page tables for test memory. * The memory is also added to memslot 0, but that's a benign side * effect as KVM allows aliasing HVAs in meslots. */ - vm = vm_create_with_vcpus(mode, vcpus, slot0_pages, guest_num_pages, 0, - perf_test_guest_code, NULL); + vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages, + perf_test_guest_code, vcpus); pta->vm = vm; /* Put the test region at the top guest physical memory. */ - region_end_gfn = vm_get_max_gfn(vm) + 1; + region_end_gfn = vm->max_gfn + 1; #ifdef __x86_64__ /* @@ -170,11 +175,10 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, TEST_ASSERT(guest_num_pages < region_end_gfn, "Requested more guest memory than address space allows.\n" " guest pages: %" PRIx64 " max gfn: %" PRIx64 - " vcpus: %d wss: %" PRIx64 "]\n", - guest_num_pages, region_end_gfn - 1, vcpus, - vcpu_memory_bytes); + " nr_vcpus: %d wss: %" PRIx64 "]\n", + guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes); - pta->gpa = (region_end_gfn - guest_num_pages) * pta->guest_page_size; + pta->gpa = (region_end_gfn - guest_num_pages - 1) * pta->guest_page_size; pta->gpa = align_down(pta->gpa, backing_src_pagesz); #ifdef __s390x__ /* Align to 1M (segment size) */ @@ -197,11 +201,12 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, /* Do mapping for the demand paging memory slot */ virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages); - perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access); + perf_test_setup_vcpus(vm, nr_vcpus, vcpus, vcpu_memory_bytes, + partition_vcpu_memory_access); if (pta->nested) { pr_info("Configuring vCPUs to run in L2 (nested).\n"); - perf_test_setup_nested(vm, vcpus); + perf_test_setup_nested(vm, nr_vcpus, vcpus); } ucall_init(vm, NULL); @@ -229,7 +234,7 @@ uint64_t __weak perf_test_nested_pages(int nr_vcpus) return 0; } -void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus) +void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu **vcpus) { pr_info("%s() not support on this architecture, skipping.\n", __func__); exit(KSFT_SKIP); @@ -250,39 +255,40 @@ static void *vcpu_thread_main(void *data) while (!READ_ONCE(all_vcpu_threads_running)) ; - vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]); + vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_idx]); return NULL; } -void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)) +void perf_test_start_vcpu_threads(int nr_vcpus, + void (*vcpu_fn)(struct perf_test_vcpu_args *)) { - int vcpu_id; + int i; vcpu_thread_fn = vcpu_fn; WRITE_ONCE(all_vcpu_threads_running, false); - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id]; + for (i = 0; i < nr_vcpus; i++) { + struct vcpu_thread *vcpu = &vcpu_threads[i]; - vcpu->vcpu_id = vcpu_id; + vcpu->vcpu_idx = i; WRITE_ONCE(vcpu->running, false); pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu); } - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - while (!READ_ONCE(vcpu_threads[vcpu_id].running)) + for (i = 0; i < nr_vcpus; i++) { + while (!READ_ONCE(vcpu_threads[i].running)) ; } WRITE_ONCE(all_vcpu_threads_running, true); } -void perf_test_join_vcpu_threads(int vcpus) +void perf_test_join_vcpu_threads(int nr_vcpus) { - int vcpu_id; + int i; - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id].thread, NULL); + for (i = 0; i < nr_vcpus; i++) + pthread_join(vcpu_threads[i].thread, NULL); } diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index abc0ae5a4fe1..604478151212 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -9,7 +9,6 @@ #include <assert.h> #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 @@ -54,7 +53,7 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) return (gva & pte_index_mask[level]) >> pte_index_shift[level]; } -void virt_pgd_alloc(struct kvm_vm *vm) +void virt_arch_pgd_alloc(struct kvm_vm *vm) { if (!vm->pgd_created) { vm_paddr_t paddr = vm_phy_pages_alloc(vm, @@ -65,7 +64,7 @@ void virt_pgd_alloc(struct kvm_vm *vm) } } -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) { uint64_t *ptep, next_ppn; int level = vm->pgtable_levels - 1; @@ -109,7 +108,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK; } -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint64_t *ptep; int level = vm->pgtable_levels - 1; @@ -160,7 +159,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, #endif } -void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { int level = vm->pgtable_levels - 1; uint64_t pgd, *ptep; @@ -179,8 +178,9 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid) +void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu) { + struct kvm_vm *vm = vcpu->vm; unsigned long satp; /* @@ -199,46 +199,46 @@ void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid) satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN; satp |= SATP_MODE_48; - set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp); + vcpu_set_reg(vcpu, RISCV_CSR_REG(satp), satp); } -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { struct kvm_riscv_core core; - get_reg(vm, vcpuid, RISCV_CORE_REG(mode), &core.mode); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), &core.regs.pc); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.ra), &core.regs.ra); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), &core.regs.sp); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), &core.regs.gp); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.tp), &core.regs.tp); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t0), &core.regs.t0); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t1), &core.regs.t1); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t2), &core.regs.t2); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s0), &core.regs.s0); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s1), &core.regs.s1); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a0), &core.regs.a0); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a1), &core.regs.a1); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a2), &core.regs.a2); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a3), &core.regs.a3); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a4), &core.regs.a4); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a5), &core.regs.a5); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a6), &core.regs.a6); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a7), &core.regs.a7); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s2), &core.regs.s2); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s3), &core.regs.s3); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s4), &core.regs.s4); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s5), &core.regs.s5); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s6), &core.regs.s6); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s7), &core.regs.s7); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s8), &core.regs.s8); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s9), &core.regs.s9); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s10), &core.regs.s10); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s11), &core.regs.s11); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t3), &core.regs.t3); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t4), &core.regs.t4); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t5), &core.regs.t5); - get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t6), &core.regs.t6); + vcpu_get_reg(vcpu, RISCV_CORE_REG(mode), &core.mode); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &core.regs.pc); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra), &core.regs.ra); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp), &core.regs.sp); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp), &core.regs.gp); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp), &core.regs.tp); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0), &core.regs.t0); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1), &core.regs.t1); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2), &core.regs.t2); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0), &core.regs.s0); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1), &core.regs.s1); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0), &core.regs.a0); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1), &core.regs.a1); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2), &core.regs.a2); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3), &core.regs.a3); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4), &core.regs.a4); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5), &core.regs.a5); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6), &core.regs.a6); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7), &core.regs.a7); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2), &core.regs.s2); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3), &core.regs.s3); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4), &core.regs.s4); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5), &core.regs.s5); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6), &core.regs.s6); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7), &core.regs.s7); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8), &core.regs.s8); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9), &core.regs.s9); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10), &core.regs.s10); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11), &core.regs.s11); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3), &core.regs.t3); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4), &core.regs.t4); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5), &core.regs.t5); + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6), &core.regs.t6); fprintf(stream, " MODE: 0x%lx\n", core.mode); @@ -275,7 +275,8 @@ static void __aligned(16) guest_unexp_trap(void) 0, 0, 0, 0, 0, 0); } -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) { int r; size_t stack_size = vm->page_size == 4096 ? @@ -285,9 +286,10 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) DEFAULT_RISCV_GUEST_STACK_VADDR_MIN); unsigned long current_gp = 0; struct kvm_mp_state mps; + struct kvm_vcpu *vcpu; - vm_vcpu_add(vm, vcpuid); - riscv_vcpu_mmu_setup(vm, vcpuid); + vcpu = __vm_vcpu_add(vm, vcpu_id); + riscv_vcpu_mmu_setup(vcpu); /* * With SBI HSM support in KVM RISC-V, all secondary VCPUs are @@ -295,26 +297,25 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) * are powered-on using KVM_SET_MP_STATE ioctl(). */ mps.mp_state = KVM_MP_STATE_RUNNABLE; - r = _vcpu_ioctl(vm, vcpuid, KVM_SET_MP_STATE, &mps); + r = __vcpu_ioctl(vcpu, KVM_SET_MP_STATE, &mps); TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r); /* Setup global pointer of guest to be same as the host */ asm volatile ( "add %0, gp, zero" : "=r" (current_gp) : : "memory"); - set_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), current_gp); + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.gp), current_gp); /* Setup stack pointer and program counter of guest */ - set_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), - stack_vaddr + stack_size); - set_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), - (unsigned long)guest_code); + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); /* Setup default exception vector of guest */ - set_reg(vm, vcpuid, RISCV_CSR_REG(stvec), - (unsigned long)guest_unexp_trap); + vcpu_set_reg(vcpu, RISCV_CSR_REG(stvec), (unsigned long)guest_unexp_trap); + + return vcpu; } -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) { va_list ap; uint64_t id = RISCV_CORE_REG(regs.a0); @@ -352,12 +353,12 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) id = RISCV_CORE_REG(regs.a7); break; } - set_reg(vm, vcpuid, id, va_arg(ap, uint64_t)); + vcpu_set_reg(vcpu, id, va_arg(ap, uint64_t)); } va_end(ap); } -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { } diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c index 8550f424d093..087b9740bc8f 100644 --- a/tools/testing/selftests/kvm/lib/riscv/ucall.c +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -8,7 +8,6 @@ #include <linux/kvm.h> #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" void ucall_init(struct kvm_vm *vm, void *arg) @@ -53,7 +52,7 @@ void ucall(uint64_t cmd, int nargs, ...) va_list va; int i; - nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + nargs = min(nargs, UCALL_MAX_ARGS); va_start(va, nargs); for (i = 0; i < nargs; ++i) @@ -65,9 +64,9 @@ void ucall(uint64_t cmd, int nargs, ...) (vm_vaddr_t)&uc, 0, 0, 0, 0, 0); } -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) { - struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct kvm_run *run = vcpu->run; struct ucall ucall = {}; if (uc) @@ -77,16 +76,17 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT) { switch (run->riscv_sbi.function_id) { case KVM_RISCV_SELFTESTS_SBI_UCALL: - memcpy(&ucall, addr_gva2hva(vm, - run->riscv_sbi.args[0]), sizeof(ucall)); + memcpy(&ucall, + addr_gva2hva(vcpu->vm, run->riscv_sbi.args[0]), + sizeof(ucall)); - vcpu_run_complete_io(vm, vcpu_id); + vcpu_run_complete_io(vcpu); if (uc) memcpy(uc, &ucall, sizeof(ucall)); break; case KVM_RISCV_SELFTESTS_SBI_UNEXP: - vcpu_dump(stderr, vm, vcpu_id, 2); + vcpu_dump(stderr, vcpu, 2); TEST_ASSERT(0, "Unexpected trap taken by guest"); break; default: diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c index 86b9e611ad87..cdb7daeed5fd 100644 --- a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c +++ b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c @@ -8,8 +8,6 @@ #include "test_util.h" #include "kvm_util.h" -#define VCPU_ID 6 - #define ICPT_INSTRUCTION 0x04 #define IPA0_DIAG 0x8300 @@ -27,14 +25,15 @@ static void guest_code(void) */ static uint64_t diag318_handler(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; uint64_t reg; uint64_t diag318_info; - vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_run(vm, VCPU_ID); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_run(vcpu); + run = vcpu->run; TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, "DIAGNOSE 0x0318 instruction was not intercepted"); @@ -62,7 +61,7 @@ uint64_t get_diag318_info(void) * If KVM does not support diag318, then return 0 to * ensure tests do not break. */ - if (!kvm_check_cap(KVM_CAP_S390_DIAG318)) { + if (!kvm_has_cap(KVM_CAP_S390_DIAG318)) { if (!printed_skip) { fprintf(stdout, "KVM_CAP_S390_DIAG318 not supported. " "Skipping diag318 test.\n"); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index f87c7137598e..89d7340d9cbd 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -7,11 +7,10 @@ #include "processor.h" #include "kvm_util.h" -#include "../kvm_util_internal.h" #define PAGES_PER_REGION 4 -void virt_pgd_alloc(struct kvm_vm *vm) +void virt_arch_pgd_alloc(struct kvm_vm *vm) { vm_paddr_t paddr; @@ -47,7 +46,7 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri) | ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH); } -void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) { int ri, idx; uint64_t *entry; @@ -86,7 +85,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) entry[idx] = gpa; } -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { int ri, idx; uint64_t *entry; @@ -147,7 +146,7 @@ static void virt_dump_region(FILE *stream, struct kvm_vm *vm, uint8_t indent, } } -void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { if (!vm->pgd_created) return; @@ -155,12 +154,14 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); uint64_t stack_vaddr; struct kvm_regs regs; struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; struct kvm_run *run; TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", @@ -169,24 +170,26 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) stack_vaddr = vm_vaddr_alloc(vm, stack_size, DEFAULT_GUEST_STACK_VADDR_MIN); - vm_vcpu_add(vm, vcpuid); + vcpu = __vm_vcpu_add(vm, vcpu_id); /* Setup guest registers */ - vcpu_regs_get(vm, vcpuid, ®s); + vcpu_regs_get(vcpu, ®s); regs.gprs[15] = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()) - 160; - vcpu_regs_set(vm, vcpuid, ®s); + vcpu_regs_set(vcpu, ®s); - vcpu_sregs_get(vm, vcpuid, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.crs[0] |= 0x00040000; /* Enable floating point regs */ sregs.crs[1] = vm->pgd | 0xf; /* Primary region table */ - vcpu_sregs_set(vm, vcpuid, &sregs); + vcpu_sregs_set(vcpu, &sregs); - run = vcpu_state(vm, vcpuid); + run = vcpu->run; run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ run->psw_addr = (uintptr_t)guest_code; + + return vcpu; } -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) { va_list ap; struct kvm_regs regs; @@ -197,26 +200,21 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) num); va_start(ap, num); - vcpu_regs_get(vm, vcpuid, ®s); + vcpu_regs_get(vcpu, ®s); for (i = 0; i < num; i++) regs.gprs[i + 2] = va_arg(ap, uint64_t); - vcpu_regs_set(vm, vcpuid, ®s); + vcpu_regs_set(vcpu, ®s); va_end(ap); } -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - if (!vcpu) - return; - fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", - indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); + indent, "", vcpu->run->psw_mask, vcpu->run->psw_addr); } -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { } diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index 9d3b0f15249a..73dc4e21190f 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -22,7 +22,7 @@ void ucall(uint64_t cmd, int nargs, ...) va_list va; int i; - nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + nargs = min(nargs, UCALL_MAX_ARGS); va_start(va, nargs); for (i = 0; i < nargs; ++i) @@ -33,9 +33,9 @@ void ucall(uint64_t cmd, int nargs, ...) asm volatile ("diag 0,%0,0x501" : : "a"(&uc) : "memory"); } -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) { - struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct kvm_run *run = vcpu->run; struct ucall ucall = {}; if (uc) @@ -47,10 +47,10 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) (run->s390_sieic.ipb >> 16) == 0x501) { int reg = run->s390_sieic.ipa & 0xf; - memcpy(&ucall, addr_gva2hva(vm, run->s.regs.gprs[reg]), + memcpy(&ucall, addr_gva2hva(vcpu->vm, run->s.regs.gprs[reg]), sizeof(ucall)); - vcpu_run_complete_io(vm, vcpu_id); + vcpu_run_complete_io(vcpu); if (uc) memcpy(uc, &ucall, sizeof(ucall)); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c index e258524435a0..0f344a7c89c4 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c @@ -12,7 +12,6 @@ #include "test_util.h" #include "kvm_util.h" #include "perf_test_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #include "vmx.h" @@ -78,14 +77,14 @@ void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) nested_identity_map_1g(vmx, vm, start, end - start); } -void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus) +void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) { struct vmx_pages *vmx, *vmx0 = NULL; struct kvm_regs regs; vm_vaddr_t vmx_gva; int vcpu_id; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vmx = vcpu_alloc_vmx(vm, &vmx_gva); @@ -104,9 +103,9 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus) * Override the vCPU to run perf_test_l1_guest_code() which will * bounce it into L2 before calling perf_test_guest_code(). */ - vcpu_regs_get(vm, vcpu_id, ®s); + vcpu_regs_get(vcpus[vcpu_id], ®s); regs.rip = (unsigned long) perf_test_l1_guest_code; - vcpu_regs_set(vm, vcpu_id, ®s); - vcpu_args_set(vm, vcpu_id, 2, vmx_gva, vcpu_id); + vcpu_regs_set(vcpus[vcpu_id], ®s); + vcpu_args_set(vcpus[vcpu_id], 2, vmx_gva, vcpu_id); } } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index ead7011ee8f6..2e6e61bbe81b 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -7,7 +7,6 @@ #include "test_util.h" #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #ifndef NUM_INTERRUPTS @@ -17,10 +16,11 @@ #define DEFAULT_CODE_SELECTOR 0x8 #define DEFAULT_DATA_SELECTOR 0x10 +#define MAX_NR_CPUID_ENTRIES 100 + vm_vaddr_t exception_handlers; -void regs_dump(FILE *stream, struct kvm_regs *regs, - uint8_t indent) +static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx " "rcx: 0x%.16llx rdx: 0x%.16llx\n", @@ -43,21 +43,6 @@ void regs_dump(FILE *stream, struct kvm_regs *regs, regs->rip, regs->rflags); } -/* - * Segment Dump - * - * Input Args: - * stream - Output FILE stream - * segment - KVM segment - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the state of the KVM segment given by @segment, to the FILE stream - * given by @stream. - */ static void segment_dump(FILE *stream, struct kvm_segment *segment, uint8_t indent) { @@ -75,21 +60,6 @@ static void segment_dump(FILE *stream, struct kvm_segment *segment, segment->unusable, segment->padding); } -/* - * dtable Dump - * - * Input Args: - * stream - Output FILE stream - * dtable - KVM dtable - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the state of the KVM dtable given by @dtable, to the FILE stream - * given by @stream. - */ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, uint8_t indent) { @@ -99,8 +69,7 @@ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, dtable->padding[0], dtable->padding[1], dtable->padding[2]); } -void sregs_dump(FILE *stream, struct kvm_sregs *sregs, - uint8_t indent) +static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) { unsigned int i; @@ -142,7 +111,7 @@ void sregs_dump(FILE *stream, struct kvm_sregs *sregs, } } -void virt_pgd_alloc(struct kvm_vm *vm) +void virt_arch_pgd_alloc(struct kvm_vm *vm) { TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -240,27 +209,24 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); } -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) { __virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K); } -static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, - uint64_t vaddr) +static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, + struct kvm_vcpu *vcpu, + uint64_t vaddr) { uint16_t index[4]; uint64_t *pml4e, *pdpe, *pde; uint64_t *pte; - struct kvm_cpuid_entry2 *entry; struct kvm_sregs sregs; - int max_phy_addr; uint64_t rsvd_mask = 0; - entry = kvm_get_supported_cpuid_index(0x80000008, 0); - max_phy_addr = entry->eax & 0x000000ff; /* Set the high bits in the reserved mask. */ - if (max_phy_addr < 52) - rsvd_mask = GENMASK_ULL(51, max_phy_addr); + if (vm->pa_bits < 52) + rsvd_mask = GENMASK_ULL(51, vm->pa_bits); /* * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries @@ -268,7 +234,7 @@ static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1, * the XD flag (bit 63) is reserved. */ - vcpu_sregs_get(vm, vcpuid, &sregs); + vcpu_sregs_get(vcpu, &sregs); if ((sregs.efer & EFER_NX) == 0) { rsvd_mask |= PTE_NX_MASK; } @@ -320,22 +286,23 @@ static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, return &pte[index[0]]; } -uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t vaddr) { - uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); + uint64_t *pte = _vm_get_page_table_entry(vm, vcpu, vaddr); return *(uint64_t *)pte; } -void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, - uint64_t pte) +void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t vaddr, uint64_t pte) { - uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); + uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpu, vaddr); *(uint64_t *)new_pte = pte; } -void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { uint64_t *pml4e, *pml4e_start; uint64_t *pdpe, *pdpe_start; @@ -516,7 +483,7 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, kvm_seg_fill_gdt_64bit(vm, segp); } -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; uint64_t *pml4e, *pdpe, *pde; @@ -579,12 +546,12 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, kvm_seg_fill_gdt_64bit(vm, segp); } -static void vcpu_setup(struct kvm_vm *vm, int vcpuid) +static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { struct kvm_sregs sregs; /* Set mode specific system register values. */ - vcpu_sregs_get(vm, vcpuid, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.idt.limit = 0; @@ -608,25 +575,10 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid) } sregs.cr3 = vm->pgd; - vcpu_sregs_set(vm, vcpuid, &sregs); + vcpu_sregs_set(vcpu, &sregs); } -#define CPUID_XFD_BIT (1 << 4) -static bool is_xfd_supported(void) -{ - int eax, ebx, ecx, edx; - const int leaf = 0xd, subleaf = 0x1; - - __asm__ __volatile__( - "cpuid" - : /* output */ "=a"(eax), "=b"(ebx), - "=c"(ecx), "=d"(edx) - : /* input */ "0"(leaf), "2"(subleaf)); - - return !!(eax & CPUID_XFD_BIT); -} - -void vm_xsave_req_perm(int bit) +void __vm_xsave_require_permission(int bit, const char *name) { int kvm_fd; u64 bitmask; @@ -637,26 +589,21 @@ void vm_xsave_req_perm(int bit) .addr = (unsigned long) &bitmask }; + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD)); + kvm_fd = open_kvm_dev_path_or_exit(); - rc = ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); + rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); close(kvm_fd); + if (rc == -1 && (errno == ENXIO || errno == EINVAL)) - exit(KSFT_SKIP); - TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); - if (!(bitmask & (1ULL << bit))) - exit(KSFT_SKIP); + __TEST_REQUIRE(0, "KVM_X86_XCOMP_GUEST_SUPP not supported"); - if (!is_xfd_supported()) - exit(KSFT_SKIP); + TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); - rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit); + __TEST_REQUIRE(bitmask & (1ULL << bit), + "Required XSAVE feature '%s' not supported", name); - /* - * The older kernel version(<5.15) can't support - * ARCH_REQ_XCOMP_GUEST_PERM and directly return. - */ - if (rc) - return; + TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit)); rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); @@ -665,108 +612,89 @@ void vm_xsave_req_perm(int bit) bitmask); } -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) { struct kvm_mp_state mp_state; struct kvm_regs regs; vm_vaddr_t stack_vaddr; + struct kvm_vcpu *vcpu; + stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), DEFAULT_GUEST_STACK_VADDR_MIN); - /* Create VCPU */ - vm_vcpu_add(vm, vcpuid); - vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); - vcpu_setup(vm, vcpuid); + vcpu = __vm_vcpu_add(vm, vcpu_id); + vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); + vcpu_setup(vm, vcpu); /* Setup guest general purpose registers */ - vcpu_regs_get(vm, vcpuid, ®s); + vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); regs.rip = (unsigned long) guest_code; - vcpu_regs_set(vm, vcpuid, ®s); + vcpu_regs_set(vcpu, ®s); /* Setup the MP state */ mp_state.mp_state = 0; - vcpu_set_mp_state(vm, vcpuid, &mp_state); + vcpu_mp_state_set(vcpu, &mp_state); + + return vcpu; } -/* - * Allocate an instance of struct kvm_cpuid2 - * - * Input Args: None - * - * Output Args: None - * - * Return: A pointer to the allocated struct. The caller is responsible - * for freeing this struct. - * - * Since kvm_cpuid2 uses a 0-length array to allow a the size of the - * array to be decided at allocation time, allocation is slightly - * complicated. This function uses a reasonable default length for - * the array and performs the appropriate allocation. - */ -static struct kvm_cpuid2 *allocate_kvm_cpuid2(void) +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id) { - struct kvm_cpuid2 *cpuid; - int nent = 100; - size_t size; - - size = sizeof(*cpuid); - size += nent * sizeof(struct kvm_cpuid_entry2); - cpuid = malloc(size); - if (!cpuid) { - perror("malloc"); - abort(); - } + struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id); - cpuid->nent = nent; + vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); - return cpuid; + return vcpu; } -/* - * KVM Supported CPUID Get - * - * Input Args: None - * - * Output Args: - * - * Return: The supported KVM CPUID - * - * Get the guest CPUID supported by KVM. - */ -struct kvm_cpuid2 *kvm_get_supported_cpuid(void) +void vcpu_arch_free(struct kvm_vcpu *vcpu) +{ + if (vcpu->cpuid) + free(vcpu->cpuid); +} + +const struct kvm_cpuid2 *kvm_get_supported_cpuid(void) { static struct kvm_cpuid2 *cpuid; - int ret; int kvm_fd; if (cpuid) return cpuid; - cpuid = allocate_kvm_cpuid2(); + cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); kvm_fd = open_kvm_dev_path_or_exit(); - ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); - TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", - ret, errno); + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); close(kvm_fd); return cpuid; } -/* - * KVM Get MSR - * - * Input Args: - * msr_index - Index of MSR - * - * Output Args: None - * - * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. - * - * Get value of MSR for VCPU. - */ +bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_feature feature) +{ + const struct kvm_cpuid_entry2 *entry; + int i; + + for (i = 0; i < cpuid->nent; i++) { + entry = &cpuid->entries[i]; + + /* + * The output registers in kvm_cpuid_entry2 are in alphabetical + * order, but kvm_x86_cpu_feature matches that mess, so yay + * pointer shenanigans! + */ + if (entry->function == feature.function && + entry->index == feature.index) + return (&entry->eax)[feature.reg] & BIT(feature.bit); + } + + return false; +} + uint64_t kvm_get_feature_msr(uint64_t msr_index) { struct { @@ -779,218 +707,98 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.entry.index = msr_index; kvm_fd = open_kvm_dev_path_or_exit(); - r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); - TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" - " rc: %i errno: %i", r, errno); + r = __kvm_ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_GET_MSRS, r)); close(kvm_fd); return buffer.entry.data; } -/* - * VM VCPU CPUID Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU id - * - * Output Args: None - * - * Return: KVM CPUID (KVM_GET_CPUID2) - * - * Set the VCPU's CPUID. - */ -struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - struct kvm_cpuid2 *cpuid; - int max_ent; - int rc = -1; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - cpuid = allocate_kvm_cpuid2(); - max_ent = cpuid->nent; - - for (cpuid->nent = 1; cpuid->nent <= max_ent; cpuid->nent++) { - rc = ioctl(vcpu->fd, KVM_GET_CPUID2, cpuid); - if (!rc) - break; + TEST_ASSERT(cpuid != vcpu->cpuid, "@cpuid can't be the vCPU's CPUID"); - TEST_ASSERT(rc == -1 && errno == E2BIG, - "KVM_GET_CPUID2 should either succeed or give E2BIG: %d %d", - rc, errno); + /* Allow overriding the default CPUID. */ + if (vcpu->cpuid && vcpu->cpuid->nent < cpuid->nent) { + free(vcpu->cpuid); + vcpu->cpuid = NULL; } - TEST_ASSERT(rc == 0, "KVM_GET_CPUID2 failed, rc: %i errno: %i", - rc, errno); + if (!vcpu->cpuid) + vcpu->cpuid = allocate_kvm_cpuid2(cpuid->nent); - return cpuid; + memcpy(vcpu->cpuid, cpuid, kvm_cpuid2_size(cpuid->nent)); + vcpu_set_cpuid(vcpu); } - - -/* - * Locate a cpuid entry. - * - * Input Args: - * function: The function of the cpuid entry to find. - * index: The index of the cpuid entry. - * - * Output Args: None - * - * Return: A pointer to the cpuid entry. Never returns NULL. - */ -struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr) { - struct kvm_cpuid2 *cpuid; - struct kvm_cpuid_entry2 *entry = NULL; - int i; - - cpuid = kvm_get_supported_cpuid(); - for (i = 0; i < cpuid->nent; i++) { - if (cpuid->entries[i].function == function && - cpuid->entries[i].index == index) { - entry = &cpuid->entries[i]; - break; - } - } + struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, 0x80000008); - TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).", - function, index); - return entry; + entry->eax = (entry->eax & ~0xff) | maxphyaddr; + vcpu_set_cpuid(vcpu); } - -int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_cpuid2 *cpuid) +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, function); - return ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid); + entry->eax = 0; + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + vcpu_set_cpuid(vcpu); } -/* - * VM VCPU CPUID Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU id - * cpuid - The CPUID values to set. - * - * Output Args: None - * - * Return: void - * - * Set the VCPU's CPUID. - */ -void vcpu_set_cpuid(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_cpuid2 *cpuid) +void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature, + bool set) { - int rc; + struct kvm_cpuid_entry2 *entry; + u32 *reg; - rc = __vcpu_set_cpuid(vm, vcpuid, cpuid); - TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i", - rc, errno); + entry = __vcpu_get_cpuid_entry(vcpu, feature.function, feature.index); + reg = (&entry->eax) + feature.reg; + if (set) + *reg |= BIT(feature.bit); + else + *reg &= ~BIT(feature.bit); + + vcpu_set_cpuid(vcpu); } -/* - * VCPU Get MSR - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * msr_index - Index of MSR - * - * Output Args: None - * - * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. - * - * Get value of MSR for VCPU. - */ -uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) +uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); struct { struct kvm_msrs header; struct kvm_msr_entry entry; } buffer = {}; - int r; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header); - TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" - " rc: %i errno: %i", r, errno); + + vcpu_msrs_get(vcpu, &buffer.header); return buffer.entry.data; } -/* - * _VCPU Set MSR - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * msr_index - Index of MSR - * msr_value - New value of MSR - * - * Output Args: None - * - * Return: The result of KVM_SET_MSRS. - * - * Sets the value of an MSR for the given VCPU. - */ -int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, - uint64_t msr_value) +int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); struct { struct kvm_msrs header; struct kvm_msr_entry entry; } buffer = {}; - int r; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); memset(&buffer, 0, sizeof(buffer)); buffer.header.nmsrs = 1; buffer.entry.index = msr_index; buffer.entry.data = msr_value; - r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); - return r; -} - -/* - * VCPU Set MSR - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * msr_index - Index of MSR - * msr_value - New value of MSR - * - * Output Args: None - * - * Return: On success, nothing. On failure a TEST_ASSERT is produced. - * - * Set value of MSR for VCPU. - */ -void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, - uint64_t msr_value) -{ - int r; - r = _vcpu_set_msr(vm, vcpuid, msr_index, msr_value); - TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" - " rc: %i errno: %i", r, errno); + return __vcpu_ioctl(vcpu, KVM_SET_MSRS, &buffer.header); } -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) { va_list ap; struct kvm_regs regs; @@ -1000,7 +808,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) num); va_start(ap, num); - vcpu_regs_get(vm, vcpuid, ®s); + vcpu_regs_get(vcpu, ®s); if (num >= 1) regs.rdi = va_arg(ap, uint64_t); @@ -1020,85 +828,112 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) if (num >= 6) regs.r9 = va_arg(ap, uint64_t); - vcpu_regs_set(vm, vcpuid, ®s); + vcpu_regs_set(vcpu, ®s); va_end(ap); } -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { struct kvm_regs regs; struct kvm_sregs sregs; - fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid); + fprintf(stream, "%*svCPU ID: %u\n", indent, "", vcpu->id); fprintf(stream, "%*sregs:\n", indent + 2, ""); - vcpu_regs_get(vm, vcpuid, ®s); + vcpu_regs_get(vcpu, ®s); regs_dump(stream, ®s, indent + 4); fprintf(stream, "%*ssregs:\n", indent + 2, ""); - vcpu_sregs_get(vm, vcpuid, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs_dump(stream, &sregs, indent + 4); } -static int kvm_get_num_msrs_fd(int kvm_fd) +static struct kvm_msr_list *__kvm_get_msr_index_list(bool feature_msrs) { + struct kvm_msr_list *list; struct kvm_msr_list nmsrs; - int r; + int kvm_fd, r; + + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs.nmsrs = 0; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs); - TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i", - r); + if (!feature_msrs) + r = __kvm_ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs); + else + r = __kvm_ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, &nmsrs); - return nmsrs.nmsrs; -} + TEST_ASSERT(r == -1 && errno == E2BIG, + "Expected -E2BIG, got rc: %i errno: %i (%s)", + r, errno, strerror(errno)); -static int kvm_get_num_msrs(struct kvm_vm *vm) -{ - return kvm_get_num_msrs_fd(vm->kvm_fd); + list = malloc(sizeof(*list) + nmsrs.nmsrs * sizeof(list->indices[0])); + TEST_ASSERT(list, "-ENOMEM when allocating MSR index list"); + list->nmsrs = nmsrs.nmsrs; + + if (!feature_msrs) + kvm_ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); + else + kvm_ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list); + close(kvm_fd); + + TEST_ASSERT(list->nmsrs == nmsrs.nmsrs, + "Number of MSRs in list changed, was %d, now %d", + nmsrs.nmsrs, list->nmsrs); + return list; } -struct kvm_msr_list *kvm_get_msr_index_list(void) +const struct kvm_msr_list *kvm_get_msr_index_list(void) { - struct kvm_msr_list *list; - int nmsrs, r, kvm_fd; + static const struct kvm_msr_list *list; - kvm_fd = open_kvm_dev_path_or_exit(); + if (!list) + list = __kvm_get_msr_index_list(false); + return list; +} - nmsrs = kvm_get_num_msrs_fd(kvm_fd); - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - close(kvm_fd); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", - r); +const struct kvm_msr_list *kvm_get_feature_msr_index_list(void) +{ + static const struct kvm_msr_list *list; + if (!list) + list = __kvm_get_msr_index_list(true); return list; } -static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu, - struct kvm_x86_state *state) +bool kvm_msr_is_in_save_restore_list(uint32_t msr_index) { - int size; + const struct kvm_msr_list *list = kvm_get_msr_index_list(); + int i; - size = vm_check_cap(vm, KVM_CAP_XSAVE2); - if (!size) - size = sizeof(struct kvm_xsave); + for (i = 0; i < list->nmsrs; ++i) { + if (list->indices[i] == msr_index) + return true; + } - state->xsave = malloc(size); - if (size == sizeof(struct kvm_xsave)) - return ioctl(vcpu->fd, KVM_GET_XSAVE, state->xsave); - else - return ioctl(vcpu->fd, KVM_GET_XSAVE2, state->xsave); + return false; } -struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) +static void vcpu_save_xsave_state(struct kvm_vcpu *vcpu, + struct kvm_x86_state *state) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - struct kvm_msr_list *list; + int size = vm_check_cap(vcpu->vm, KVM_CAP_XSAVE2); + + if (size) { + state->xsave = malloc(size); + vcpu_xsave2_get(vcpu, state->xsave); + } else { + state->xsave = malloc(sizeof(struct kvm_xsave)); + vcpu_xsave_get(vcpu, state->xsave); + } +} + +struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu) +{ + const struct kvm_msr_list *msr_list = kvm_get_msr_index_list(); struct kvm_x86_state *state; - int nmsrs, r, i; + int i; + static int nested_size = -1; if (nested_size == -1) { @@ -1114,113 +949,57 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) * kernel with KVM_RUN. Complete IO prior to migrating state * to a new VM. */ - vcpu_run_complete_io(vm, vcpuid); - - nmsrs = kvm_get_num_msrs(vm); - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", - r); - - state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0])); - r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i", - r); - - r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i", - r); - - r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i", - r); - - r = vcpu_save_xsave_state(vm, vcpu, state); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", - r); - - if (kvm_check_cap(KVM_CAP_XCRS)) { - r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", - r); - } + vcpu_run_complete_io(vcpu); + + state = malloc(sizeof(*state) + msr_list->nmsrs * sizeof(state->msrs.entries[0])); + + vcpu_events_get(vcpu, &state->events); + vcpu_mp_state_get(vcpu, &state->mp_state); + vcpu_regs_get(vcpu, &state->regs); + vcpu_save_xsave_state(vcpu, state); - r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", - r); + if (kvm_has_cap(KVM_CAP_XCRS)) + vcpu_xcrs_get(vcpu, &state->xcrs); + + vcpu_sregs_get(vcpu, &state->sregs); if (nested_size) { state->nested.size = sizeof(state->nested_); - r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i", - r); + + vcpu_nested_state_get(vcpu, &state->nested); TEST_ASSERT(state->nested.size <= nested_size, "Nested state size too big, %i (KVM_CHECK_CAP gave %i)", state->nested.size, nested_size); - } else + } else { state->nested.size = 0; + } - state->msrs.nmsrs = nmsrs; - for (i = 0; i < nmsrs; i++) - state->msrs.entries[i].index = list->indices[i]; - r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs); - TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)", - r, r == nmsrs ? -1 : list->indices[r]); + state->msrs.nmsrs = msr_list->nmsrs; + for (i = 0; i < msr_list->nmsrs; i++) + state->msrs.entries[i].index = msr_list->indices[i]; + vcpu_msrs_get(vcpu, &state->msrs); - r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i", - r); + vcpu_debugregs_get(vcpu, &state->debugregs); - free(list); return state; } -void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state) +void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int r; - - r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", - r); - - r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs); - TEST_ASSERT(r == state->msrs.nmsrs, - "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)", - r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index); - - if (kvm_check_cap(KVM_CAP_XCRS)) { - r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", - r); - } - - r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", - r); - - r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i", - r); + vcpu_sregs_set(vcpu, &state->sregs); + vcpu_msrs_set(vcpu, &state->msrs); - r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i", - r); + if (kvm_has_cap(KVM_CAP_XCRS)) + vcpu_xcrs_set(vcpu, &state->xcrs); - r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i", - r); + vcpu_xsave_set(vcpu, state->xsave); + vcpu_events_set(vcpu, &state->events); + vcpu_mp_state_set(vcpu, &state->mp_state); + vcpu_debugregs_set(vcpu, &state->debugregs); + vcpu_regs_set(vcpu, &state->regs); - r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", - r); - - if (state->nested.size) { - r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", - r); - } + if (state->nested.size) + vcpu_nested_state_set(vcpu, &state->nested); } void kvm_x86_state_cleanup(struct kvm_x86_state *state) @@ -1232,15 +1011,9 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state) static bool cpu_vendor_string_is(const char *vendor) { const uint32_t *chunk = (const uint32_t *)vendor; - int eax, ebx, ecx, edx; - const int leaf = 0; - - __asm__ __volatile__( - "cpuid" - : /* output */ "=a"(eax), "=b"(ebx), - "=c"(ecx), "=d"(edx) - : /* input */ "0"(leaf), "2"(0)); + uint32_t eax, ebx, ecx, edx; + cpuid(0, &eax, &ebx, &ecx, &edx); return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); } @@ -1257,19 +1030,9 @@ bool is_amd_cpu(void) return cpu_vendor_string_is("AuthenticAMD"); } -uint32_t kvm_get_cpuid_max_basic(void) -{ - return kvm_get_supported_cpuid_entry(0)->eax; -} - -uint32_t kvm_get_cpuid_max_extended(void) -{ - return kvm_get_supported_cpuid_entry(0x80000000)->eax; -} - void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { - struct kvm_cpuid_entry2 *entry; + const struct kvm_cpuid_entry2 *entry; bool pae; /* SDM 4.1.4 */ @@ -1315,6 +1078,20 @@ static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, e->offset2 = addr >> 32; } + +static bool kvm_fixup_exception(struct ex_regs *regs) +{ + if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10) + return false; + + if (regs->vector == DE_VECTOR) + return false; + + regs->rip = regs->r11; + regs->r9 = regs->vector; + return true; +} + void kvm_exit_unexpected_vector(uint32_t value) { ucall(UCALL_UNHANDLED, 1, value); @@ -1330,6 +1107,9 @@ void route_exception(struct ex_regs *regs) return; } + if (kvm_fixup_exception(regs)) + return; + kvm_exit_unexpected_vector(regs->vector); } @@ -1346,17 +1126,18 @@ void vm_init_descriptor_tables(struct kvm_vm *vm) DEFAULT_CODE_SELECTOR); } -void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) { + struct kvm_vm *vm = vcpu->vm; struct kvm_sregs sregs; - vcpu_sregs_get(vm, vcpuid, &sregs); + vcpu_sregs_get(vcpu, &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); + vcpu_sregs_set(vcpu, &sregs); *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; } @@ -1368,11 +1149,11 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, handlers[vector] = (vm_vaddr_t)handler; } -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vm, vcpuid, &uc) == UCALL_UNHANDLED) { + if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) { uint64_t vector = uc.args[0]; TEST_FAIL("Unexpected vectored event in guest (vector:0x%lx)", @@ -1380,16 +1161,15 @@ void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) } } -struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function, - uint32_t index) +const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + uint32_t function, uint32_t index) { int i; for (i = 0; i < cpuid->nent; i++) { - struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; - - if (cur->function == function && cur->index == index) - return cur; + if (cpuid->entries[i].function == function && + cpuid->entries[i].index == index) + return &cpuid->entries[i]; } TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index); @@ -1397,24 +1177,6 @@ struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function, return NULL; } -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) { @@ -1422,43 +1184,38 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, asm volatile("vmcall" : "=a"(r) - : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); return r; } -struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) { static struct kvm_cpuid2 *cpuid; - int ret; int kvm_fd; if (cpuid) return cpuid; - cpuid = allocate_kvm_cpuid2(); + cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); kvm_fd = open_kvm_dev_path_or_exit(); - ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", - ret, errno); + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); close(kvm_fd); return cpuid; } -void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 *cpuid_full; - struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; + const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; int i, nent = 0; if (!cpuid_full) { cpuid_sys = kvm_get_supported_cpuid(); cpuid_hv = kvm_get_supported_hv_cpuid(); - cpuid_full = malloc(sizeof(*cpuid_full) + - (cpuid_sys->nent + cpuid_hv->nent) * - sizeof(struct kvm_cpuid_entry2)); + cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); if (!cpuid_full) { perror("malloc"); abort(); @@ -1478,16 +1235,14 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid) cpuid_full->nent = nent + cpuid_hv->nent; } - vcpu_set_cpuid(vm, vcpuid, cpuid_full); + vcpu_init_cpuid(vcpu, cpuid_full); } -struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid) +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) { - static struct kvm_cpuid2 *cpuid; + struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - cpuid = allocate_kvm_cpuid2(); - - vcpu_ioctl(vm, vcpuid, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); return cpuid; } @@ -1510,9 +1265,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) /* Before family 17h, the HyperTransport area is just below 1T. */ ht_gfn = (1 << 28) - num_ht_pages; - eax = 1; - ecx = 0; - cpuid(&eax, &ebx, &ecx, &edx); + cpuid(1, &eax, &ebx, &ecx, &edx); if (x86_family(eax) < 0x17) goto done; @@ -1521,18 +1274,15 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use * the old conservative value if MAXPHYADDR is not enumerated. */ - eax = 0x80000000; - cpuid(&eax, &ebx, &ecx, &edx); + cpuid(0x80000000, &eax, &ebx, &ecx, &edx); max_ext_leaf = eax; if (max_ext_leaf < 0x80000008) goto done; - eax = 0x80000008; - cpuid(&eax, &ebx, &ecx, &edx); + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; if (max_ext_leaf >= 0x8000001f) { - eax = 0x8000001f; - cpuid(&eax, &ebx, &ecx, &edx); + cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); max_pfn >>= (ebx >> 6) & 0x3f; } @@ -1540,3 +1290,24 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) done: return min(max_gfn, ht_gfn - 1); } + +/* Returns true if kvm_intel was loaded with unrestricted_guest=1. */ +bool vm_is_unrestricted_guest(struct kvm_vm *vm) +{ + char val = 'N'; + size_t count; + FILE *f; + + /* Ensure that a KVM vendor-specific module is loaded. */ + if (vm == NULL) + close(open_kvm_dev_path_or_exit()); + + f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); + if (f) { + count = fread(&val, sizeof(char), 1, f); + TEST_ASSERT(count == 1, "Unable to read from param file."); + fclose(f); + } + + return val == 'Y'; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 736ee4a23df6..6d445886e16c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -9,7 +9,6 @@ #include "test_util.h" #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #include "svm_util.h" @@ -165,22 +164,6 @@ void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa) : "r15", "memory"); } -bool nested_svm_supported(void) -{ - struct kvm_cpuid_entry2 *entry = - kvm_get_supported_cpuid_entry(0x80000001); - - return entry->ecx & CPUID_SVM; -} - -void nested_svm_check_supported(void) -{ - if (!nested_svm_supported()) { - print_skip("nested SVM not enabled"); - exit(KSFT_SKIP); - } -} - /* * Open SEV_DEV_PATH if available, otherwise exit the entire program. * diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index a3489973e290..e5f0f9e0d3ee 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -24,7 +24,7 @@ void ucall(uint64_t cmd, int nargs, ...) va_list va; int i; - nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + nargs = min(nargs, UCALL_MAX_ARGS); va_start(va, nargs); for (i = 0; i < nargs; ++i) @@ -35,9 +35,9 @@ void ucall(uint64_t cmd, int nargs, ...) : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax", "memory"); } -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) { - struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct kvm_run *run = vcpu->run; struct ucall ucall = {}; if (uc) @@ -46,11 +46,11 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; - vcpu_regs_get(vm, vcpu_id, ®s); - memcpy(&ucall, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), + vcpu_regs_get(vcpu, ®s); + memcpy(&ucall, addr_gva2hva(vcpu->vm, (vm_vaddr_t)regs.rdi), sizeof(ucall)); - vcpu_run_complete_io(vm, vcpu_id); + vcpu_run_complete_io(vcpu); if (uc) memcpy(uc, &ucall, sizeof(ucall)); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index b77a01d0a271..80a568c439b8 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -7,7 +7,6 @@ #include "test_util.h" #include "kvm_util.h" -#include "../kvm_util_internal.h" #include "processor.h" #include "vmx.h" @@ -43,16 +42,12 @@ struct eptPageTablePointer { uint64_t address:40; uint64_t reserved_63_52:12; }; -int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) +int vcpu_enable_evmcs(struct kvm_vcpu *vcpu) { uint16_t evmcs_ver; - struct kvm_enable_cap enable_evmcs_cap = { - .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, - .args[0] = (unsigned long)&evmcs_ver - }; - - vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap); + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, + (unsigned long)&evmcs_ver); /* KVM should return supported EVMCS version range */ TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) && @@ -387,21 +382,6 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) init_vmcs_guest_state(guest_rip, guest_rsp); } -bool nested_vmx_supported(void) -{ - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - - return entry->ecx & CPUID_VMX; -} - -void nested_vmx_check_supported(void) -{ - if (!nested_vmx_supported()) { - print_skip("nested VMX not enabled"); - exit(KSFT_SKIP); - } -} - static void nested_create_pte(struct kvm_vm *vm, struct eptPageTableEntry *pte, uint64_t nested_paddr, diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 15f046e19cb2..9a6e4f3ad6b5 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -28,8 +28,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) } struct vcpu_info { - struct kvm_vm *vm; - uint32_t id; + struct kvm_vcpu *vcpu; uint64_t start_gpa; uint64_t end_gpa; }; @@ -52,45 +51,45 @@ static void rendezvous_with_boss(void) } } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpu_id) +static void run_vcpu(struct kvm_vcpu *vcpu) { - vcpu_run(vm, vcpu_id); - ASSERT_EQ(get_ucall(vm, vcpu_id, NULL), UCALL_DONE); + vcpu_run(vcpu); + ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); } static void *vcpu_worker(void *data) { - struct vcpu_info *vcpu = data; + struct vcpu_info *info = data; + struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; struct kvm_sregs sregs; struct kvm_regs regs; - vcpu_args_set(vm, vcpu->id, 3, vcpu->start_gpa, vcpu->end_gpa, - vm_get_page_size(vm)); + vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); /* Snapshot regs before the first run. */ - vcpu_regs_get(vm, vcpu->id, ®s); + vcpu_regs_get(vcpu, ®s); rendezvous_with_boss(); - run_vcpu(vm, vcpu->id); + run_vcpu(vcpu); rendezvous_with_boss(); - vcpu_regs_set(vm, vcpu->id, ®s); - vcpu_sregs_get(vm, vcpu->id, &sregs); + vcpu_regs_set(vcpu, ®s); + vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ /* Toggle CR0.WP to trigger a MMU context reset. */ sregs.cr0 ^= X86_CR0_WP; #endif - vcpu_sregs_set(vm, vcpu->id, &sregs); + vcpu_sregs_set(vcpu, &sregs); rendezvous_with_boss(); - run_vcpu(vm, vcpu->id); + run_vcpu(vcpu); rendezvous_with_boss(); return NULL; } -static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa, - uint64_t end_gpa) +static pthread_t *spawn_workers(struct kvm_vm *vm, struct kvm_vcpu **vcpus, + uint64_t start_gpa, uint64_t end_gpa) { struct vcpu_info *info; uint64_t gpa, nr_bytes; @@ -104,12 +103,11 @@ static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa, TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges"); nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) & - ~((uint64_t)vm_get_page_size(vm) - 1); + ~((uint64_t)vm->page_size - 1); TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus); for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) { - info[i].vm = vm; - info[i].id = i; + info[i].vcpu = vcpus[i]; info[i].start_gpa = gpa; info[i].end_gpa = gpa + nr_bytes; pthread_create(&threads[i], NULL, vcpu_worker, &info[i]); @@ -172,6 +170,7 @@ int main(int argc, char *argv[]) uint64_t max_gpa, gpa, slot_size, max_mem, i; int max_slots, slot, opt, fd; bool hugepages = false; + struct kvm_vcpu **vcpus; pthread_t *threads; struct kvm_vm *vm; void *mem; @@ -215,9 +214,12 @@ int main(int argc, char *argv[]) } } - vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); + vcpus = malloc(nr_vcpus * sizeof(*vcpus)); + TEST_ASSERT(vcpus, "Failed to allocate vCPU array"); + + vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); - max_gpa = vm_get_max_gfn(vm) << vm_get_page_shift(vm); + max_gpa = vm->max_gfn << vm->page_shift; TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); fd = kvm_memfd_alloc(slot_size, hugepages); @@ -227,7 +229,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed"); /* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */ - for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + for (i = 0; i < slot_size; i += vm->page_size) ((uint8_t *)mem)[i] = 0xaa; gpa = 0; @@ -246,13 +248,16 @@ int main(int argc, char *argv[]) for (i = 0; i < slot_size; i += size_1gb) __virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G); #else - for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + for (i = 0; i < slot_size; i += vm->page_size) virt_pg_map(vm, gpa + i, gpa + i); #endif } atomic_set(&rendezvous, nr_vcpus + 1); - threads = spawn_workers(vm, start_gpa, gpa); + threads = spawn_workers(vm, vcpus, start_gpa, gpa); + + free(vcpus); + vcpus = NULL; pr_info("Running with %lugb of guest memory and %u vCPUs\n", (gpa - start_gpa) / size_1gb, nr_vcpus); diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 1410d0a9141a..6ee7e1dde404 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -38,19 +38,18 @@ static bool run_vcpus = true; static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { - int ret; - int vcpu_id = vcpu_args->vcpu_id; - struct kvm_vm *vm = perf_test_args.vm; + struct kvm_vcpu *vcpu = vcpu_args->vcpu; struct kvm_run *run; + int ret; - run = vcpu_state(vm, vcpu_id); + run = vcpu->run; /* Let the guest access its memory until a stop signal is received */ while (READ_ONCE(run_vcpus)) { - ret = _vcpu_run(vm, vcpu_id); + ret = _vcpu_run(vcpu); TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - if (get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC) + if (get_ucall(vcpu, NULL) == UCALL_SYNC) continue; TEST_ASSERT(false, @@ -76,7 +75,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, * Add the dummy memslot just below the perf_test_util memslot, which is * at the top of the guest physical address space. */ - gpa = perf_test_args.gpa - pages * vm_get_page_size(vm); + gpa = perf_test_args.gpa - pages * vm->page_size; for (i = 0; i < nr_modifications; i++) { usleep(delay); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 1727f75e0c2c..44995446d942 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -25,8 +25,6 @@ #include <kvm_util.h> #include <processor.h> -#define VCPU_ID 0 - #define MEM_SIZE ((512U << 20) + 4096) #define MEM_SIZE_PAGES (MEM_SIZE / 4096) #define MEM_GPA 0x10000000UL @@ -90,6 +88,7 @@ static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, struct vm_data { struct kvm_vm *vm; + struct kvm_vcpu *vcpu; pthread_t vcpu_thread; uint32_t nslots; uint64_t npages; @@ -127,29 +126,29 @@ static bool verbose; pr_info(__VA_ARGS__); \ } while (0) -static void check_mmio_access(struct vm_data *vm, struct kvm_run *run) +static void check_mmio_access(struct vm_data *data, struct kvm_run *run) { - TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(data->mmio_ok, "Unexpected mmio exit"); TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); TEST_ASSERT(run->mmio.len == 8, "Unexpected exit mmio size = %u", run->mmio.len); - TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && - run->mmio.phys_addr <= vm->mmio_gpa_max, + TEST_ASSERT(run->mmio.phys_addr >= data->mmio_gpa_min && + run->mmio.phys_addr <= data->mmio_gpa_max, "Unexpected exit mmio address = 0x%llx", run->mmio.phys_addr); } -static void *vcpu_worker(void *data) +static void *vcpu_worker(void *__data) { - struct vm_data *vm = data; - struct kvm_run *run; + struct vm_data *data = __data; + struct kvm_vcpu *vcpu = data->vcpu; + struct kvm_run *run = vcpu->run; struct ucall uc; - run = vcpu_state(vm->vm, VCPU_ID); while (1) { - vcpu_run(vm->vm, VCPU_ID); + vcpu_run(vcpu); - switch (get_ucall(vm->vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(uc.args[1] == 0, "Unexpected sync ucall, got %lx", @@ -158,14 +157,12 @@ static void *vcpu_worker(void *data) continue; case UCALL_NONE: if (run->exit_reason == KVM_EXIT_MMIO) - check_mmio_access(vm, run); + check_mmio_access(data, run); else goto done; break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld, val = %lu", - (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2]); + REPORT_GUEST_ASSERT_1(uc, "val = %lu"); break; case UCALL_DONE: goto done; @@ -238,6 +235,7 @@ static struct vm_data *alloc_vm(void) TEST_ASSERT(data, "malloc(vmdata) failed"); data->vm = NULL; + data->vcpu = NULL; data->hva_slots = NULL; return data; @@ -278,7 +276,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); TEST_ASSERT(data->hva_slots, "malloc() fail"); - data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code); ucall_init(data->vm, NULL); pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 2237d1aac801..fac248a43666 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -20,17 +20,7 @@ #include "processor.h" #include "test_util.h" -#define VCPU_ID 0 - -static __thread volatile struct rseq __rseq = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, -}; - -/* - * Use an arbitrary, bogus signature for configuring rseq, this test does not - * actually enter an rseq critical section. - */ -#define RSEQ_SIG 0xdeadbeef +#include "../rseq/rseq.c" /* * Any bug related to task migration is likely to be timing-dependent; perform @@ -51,12 +41,16 @@ static void guest_code(void) GUEST_SYNC(0); } -static void sys_rseq(int flags) +/* + * We have to perform direct system call for getcpu() because it's + * not available until glic 2.29. + */ +static void sys_getcpu(unsigned *cpu) { int r; - r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG); - TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); + r = syscall(__NR_getcpu, cpu, NULL, NULL); + TEST_ASSERT(!r, "getcpu failed, errno = %d (%s)", errno, strerror(errno)); } static int next_cpu(int cpu) @@ -103,7 +97,7 @@ static void *migration_worker(void *__rseq_tid) atomic_inc(&seq_cnt); /* - * Ensure the odd count is visible while sched_getcpu() isn't + * Ensure the odd count is visible while getcpu() isn't * stable, i.e. while changing affinity is in-progress. */ smp_wmb(); @@ -144,10 +138,10 @@ static void *migration_worker(void *__rseq_tid) * check completes. * * 3. To ensure the read-side makes efficient forward progress, - * e.g. if sched_getcpu() involves a syscall. Stalling the - * read-side means the test will spend more time waiting for - * sched_getcpu() to stabilize and less time trying to hit - * the timing-dependent bug. + * e.g. if getcpu() involves a syscall. Stalling the read-side + * means the test will spend more time waiting for getcpu() + * to stabilize and less time trying to hit the timing-dependent + * bug. * * Because any bug in this area is likely to be timing-dependent, * run with a range of delays at 1us intervals from 1us to 10us @@ -174,12 +168,11 @@ static void *migration_worker(void *__rseq_tid) return NULL; } -static int calc_min_max_cpu(void) +static void calc_min_max_cpu(void) { int i, cnt, nproc; - if (CPU_COUNT(&possible_mask) < 2) - return -EINVAL; + TEST_REQUIRE(CPU_COUNT(&possible_mask) >= 2); /* * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that @@ -201,13 +194,15 @@ static int calc_min_max_cpu(void) cnt++; } - return (cnt < 2) ? -EINVAL : 0; + __TEST_REQUIRE(cnt >= 2, + "Only one usable CPU, task migration not possible"); } int main(int argc, char *argv[]) { int r, i, snapshot; struct kvm_vm *vm; + struct kvm_vcpu *vcpu; u32 cpu, rseq_cpu; /* Tell stdout not to buffer its content */ @@ -217,34 +212,33 @@ int main(int argc, char *argv[]) TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); - if (calc_min_max_cpu()) { - print_skip("Only one usable CPU, task migration not possible"); - exit(KSFT_SKIP); - } + calc_min_max_cpu(); - sys_rseq(0); + r = rseq_register_current_thread(); + TEST_ASSERT(!r, "rseq_register_current_thread failed, errno = %d (%s)", + errno, strerror(errno)); /* * Create and run a dummy VM that immediately exits to userspace via * GUEST_SYNC, while concurrently migrating the process by setting its * CPU affinity. */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); ucall_init(vm, NULL); pthread_create(&migration_thread, NULL, migration_worker, (void *)(unsigned long)gettid()); for (i = 0; !done; i++) { - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + vcpu_run(vcpu); + TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC, "Guest failed?"); /* * Verify rseq's CPU matches sched's CPU. Ensure migration - * doesn't occur between sched_getcpu() and reading the rseq - * cpu_id by rereading both if the sequence count changes, or - * if the count is odd (migration in-progress). + * doesn't occur between getcpu() and reading the rseq cpu_id + * by rereading both if the sequence count changes, or if the + * count is odd (migration in-progress). */ do { /* @@ -254,13 +248,13 @@ int main(int argc, char *argv[]) snapshot = atomic_read(&seq_cnt) & ~1; /* - * Ensure reading sched_getcpu() and rseq.cpu_id - * complete in a single "no migration" window, i.e. are - * not reordered across the seq_cnt reads. + * Ensure calling getcpu() and reading rseq.cpu_id complete + * in a single "no migration" window, i.e. are not reordered + * across the seq_cnt reads. */ smp_rmb(); - cpu = sched_getcpu(); - rseq_cpu = READ_ONCE(__rseq.cpu_id); + sys_getcpu(&cpu); + rseq_cpu = rseq_current_cpu_raw(); smp_rmb(); } while (snapshot != atomic_read(&seq_cnt)); @@ -271,9 +265,9 @@ int main(int argc, char *argv[]) /* * Sanity check that the test was able to enter the guest a reasonable * number of times, e.g. didn't get stalled too often/long waiting for - * sched_getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a - * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs - * than migrations given the 1us+ delay in the migration task. + * getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a fairly + * conservative ratio on x86-64, which can do _more_ KVM_RUNs than + * migrations given the 1us+ delay in the migration task. */ TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2), "Only performed %d KVM_RUNs, task stalled too much?\n", i); @@ -282,7 +276,7 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); - sys_rseq(RSEQ_FLAG_UNREGISTER); + rseq_unregister_current_thread(); return 0; } diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 49f26f544127..9113696d5178 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -14,6 +14,7 @@ #include "test_util.h" #include "kvm_util.h" +#include "kselftest.h" enum mop_target { LOGICAL, @@ -98,21 +99,18 @@ static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc) return ksmo; } -/* vcpu dummy id signifying that vm instead of vcpu ioctl is to occur */ -const uint32_t VM_VCPU_ID = (uint32_t)-1; - -struct test_vcpu { +struct test_info { struct kvm_vm *vm; - uint32_t id; + struct kvm_vcpu *vcpu; }; #define PRINT_MEMOP false -static void print_memop(uint32_t vcpu_id, const struct kvm_s390_mem_op *ksmo) +static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksmo) { if (!PRINT_MEMOP) return; - if (vcpu_id == VM_VCPU_ID) + if (!vcpu) printf("vm memop("); else printf("vcpu memop("); @@ -147,25 +145,29 @@ static void print_memop(uint32_t vcpu_id, const struct kvm_s390_mem_op *ksmo) puts(")"); } -static void memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) { - if (vcpu.id == VM_VCPU_ID) - vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + struct kvm_vcpu *vcpu = info.vcpu; + + if (!vcpu) + vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); else - vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); + vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); } -static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) { - if (vcpu.id == VM_VCPU_ID) - return _vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + struct kvm_vcpu *vcpu = info.vcpu; + + if (!vcpu) + return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); else - return _vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); + return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); } -#define MEMOP(err, vcpu_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ +#define MEMOP(err, info_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ ({ \ - struct test_vcpu __vcpu = (vcpu_p); \ + struct test_info __info = (info_p); \ struct mop_desc __desc = { \ .target = (mop_target_p), \ .mode = (access_mode_p), \ @@ -177,13 +179,13 @@ static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) \ if (__desc._gaddr_v) { \ if (__desc.target == ABSOLUTE) \ - __desc.gaddr = addr_gva2gpa(__vcpu.vm, __desc.gaddr_v); \ + __desc.gaddr = addr_gva2gpa(__info.vm, __desc.gaddr_v); \ else \ __desc.gaddr = __desc.gaddr_v; \ } \ __ksmo = ksmo_from_desc(__desc); \ - print_memop(__vcpu.id, &__ksmo); \ - err##memop_ioctl(__vcpu, &__ksmo); \ + print_memop(__info.vcpu, &__ksmo); \ + err##memop_ioctl(__info, &__ksmo); \ }) #define MOP(...) MEMOP(, __VA_ARGS__) @@ -200,7 +202,6 @@ static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) -#define VCPU_ID 1 #define PAGE_SHIFT 12 #define PAGE_SIZE (1ULL << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE - 1)) @@ -212,21 +213,22 @@ static uint8_t mem2[65536]; struct test_default { struct kvm_vm *kvm_vm; - struct test_vcpu vm; - struct test_vcpu vcpu; + struct test_info vm; + struct test_info vcpu; struct kvm_run *run; int size; }; static struct test_default test_default_init(void *guest_code) { + struct kvm_vcpu *vcpu; struct test_default t; t.size = min((size_t)kvm_check_cap(KVM_CAP_S390_MEM_OP), sizeof(mem1)); - t.kvm_vm = vm_create_default(VCPU_ID, 0, guest_code); - t.vm = (struct test_vcpu) { t.kvm_vm, VM_VCPU_ID }; - t.vcpu = (struct test_vcpu) { t.kvm_vm, VCPU_ID }; - t.run = vcpu_state(t.kvm_vm, VCPU_ID); + t.kvm_vm = vm_create_with_one_vcpu(&vcpu, guest_code); + t.vm = (struct test_info) { t.kvm_vm, NULL }; + t.vcpu = (struct test_info) { t.kvm_vm, vcpu }; + t.run = vcpu->run; return t; } @@ -241,14 +243,15 @@ enum stage { STAGE_COPIED, }; -#define HOST_SYNC(vcpu_p, stage) \ +#define HOST_SYNC(info_p, stage) \ ({ \ - struct test_vcpu __vcpu = (vcpu_p); \ + struct test_info __info = (info_p); \ + struct kvm_vcpu *__vcpu = __info.vcpu; \ struct ucall uc; \ int __stage = (stage); \ \ - vcpu_run(__vcpu.vm, __vcpu.id); \ - get_ucall(__vcpu.vm, __vcpu.id, &uc); \ + vcpu_run(__vcpu); \ + get_ucall(__vcpu, &uc); \ ASSERT_EQ(uc.cmd, UCALL_SYNC); \ ASSERT_EQ(uc.args[1], __stage); \ }) \ @@ -267,7 +270,7 @@ static void prepare_mem12(void) #define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ ({ \ - struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ enum mop_target __target = (mop_target_p); \ uint32_t __size = (size); \ \ @@ -282,7 +285,7 @@ static void prepare_mem12(void) #define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ ({ \ - struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ enum mop_target __target = (mop_target_p); \ uint32_t __size = (size); \ \ @@ -623,34 +626,34 @@ static void guest_idle(void) GUEST_SYNC(STAGE_IDLED); } -static void _test_errors_common(struct test_vcpu vcpu, enum mop_target target, int size) +static void _test_errors_common(struct test_info info, enum mop_target target, int size) { int rv; /* Bad size: */ - rv = ERR_MOP(vcpu, target, WRITE, mem1, -1, GADDR_V(mem1)); + rv = ERR_MOP(info, target, WRITE, mem1, -1, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == E2BIG, "ioctl allows insane sizes"); /* Zero size: */ - rv = ERR_MOP(vcpu, target, WRITE, mem1, 0, GADDR_V(mem1)); + rv = ERR_MOP(info, target, WRITE, mem1, 0, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && (errno == EINVAL || errno == ENOMEM), "ioctl allows 0 as size"); /* Bad flags: */ - rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1)); + rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows all flags"); /* Bad guest address: */ - rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); + rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access"); /* Bad host address: */ - rv = ERR_MOP(vcpu, target, WRITE, 0, size, GADDR_V(mem1)); + rv = ERR_MOP(info, target, WRITE, 0, size, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == EFAULT, "ioctl does not report bad host memory address"); /* Bad key: */ - rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17)); + rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows invalid key"); } @@ -691,34 +694,89 @@ static void test_errors(void) kvm_vm_free(t.kvm_vm); } +struct testdef { + const char *name; + void (*test)(void); + int extension; +} testlist[] = { + { + .name = "simple copy", + .test = test_copy, + }, + { + .name = "generic error checks", + .test = test_errors, + }, + { + .name = "copy with storage keys", + .test = test_copy_key, + .extension = 1, + }, + { + .name = "copy with key storage protection override", + .test = test_copy_key_storage_prot_override, + .extension = 1, + }, + { + .name = "copy with key fetch protection", + .test = test_copy_key_fetch_prot, + .extension = 1, + }, + { + .name = "copy with key fetch protection override", + .test = test_copy_key_fetch_prot_override, + .extension = 1, + }, + { + .name = "error checks with key", + .test = test_errors_key, + .extension = 1, + }, + { + .name = "termination", + .test = test_termination, + .extension = 1, + }, + { + .name = "error checks with key storage protection override", + .test = test_errors_key_storage_prot_override, + .extension = 1, + }, + { + .name = "error checks without key fetch prot override", + .test = test_errors_key_fetch_prot_override_not_enabled, + .extension = 1, + }, + { + .name = "error checks with key fetch prot override", + .test = test_errors_key_fetch_prot_override_enabled, + .extension = 1, + }, +}; + int main(int argc, char *argv[]) { - int memop_cap, extension_cap; + int extension_cap, idx; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP)); setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ - memop_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP); - extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); - if (!memop_cap) { - print_skip("CAP_S390_MEM_OP not supported"); - exit(KSFT_SKIP); - } + ksft_print_header(); - test_copy(); - if (extension_cap > 0) { - test_copy_key(); - test_copy_key_storage_prot_override(); - test_copy_key_fetch_prot(); - test_copy_key_fetch_prot_override(); - test_errors_key(); - test_termination(); - test_errors_key_storage_prot_override(); - test_errors_key_fetch_prot_override_not_enabled(); - test_errors_key_fetch_prot_override_enabled(); - } else { - print_skip("storage key memop extension not supported"); + ksft_set_plan(ARRAY_SIZE(testlist)); + + extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); + for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { + if (extension_cap >= testlist[idx].extension) { + testlist[idx].test(); + ksft_test_result_pass("%s\n", testlist[idx].name); + } else { + ksft_test_result_skip("%s - extension level %d not supported\n", + testlist[idx].name, + testlist[idx].extension); + } } - test_errors(); - return 0; + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c index b143db6d8693..19486084eb30 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390x/resets.c @@ -12,15 +12,14 @@ #include "test_util.h" #include "kvm_util.h" +#include "kselftest.h" -#define VCPU_ID 3 #define LOCAL_IRQS 32 -struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS]; +#define ARBITRARY_NON_ZERO_VCPU_ID 3 + +struct kvm_s390_irq buf[ARBITRARY_NON_ZERO_VCPU_ID + LOCAL_IRQS]; -struct kvm_vm *vm; -struct kvm_run *run; -struct kvm_sync_regs *sync_regs; static uint8_t regs_null[512]; static void guest_code_initial(void) @@ -58,25 +57,22 @@ static void guest_code_initial(void) ); } -static void test_one_reg(uint64_t id, uint64_t value) +static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value) { - struct kvm_one_reg reg; uint64_t eval_reg; - reg.addr = (uintptr_t)&eval_reg; - reg.id = id; - vcpu_get_reg(vm, VCPU_ID, ®); + vcpu_get_reg(vcpu, id, &eval_reg); TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); } -static void assert_noirq(void) +static void assert_noirq(struct kvm_vcpu *vcpu) { struct kvm_s390_irq_state irq_state; int irqs; irq_state.len = sizeof(buf); irq_state.buf = (unsigned long)buf; - irqs = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_GET_IRQ_STATE, &irq_state); + irqs = __vcpu_ioctl(vcpu, KVM_S390_GET_IRQ_STATE, &irq_state); /* * irqs contains the number of retrieved interrupts. Any interrupt * (notably, the emergency call interrupt we have injected) should @@ -86,19 +82,20 @@ static void assert_noirq(void) TEST_ASSERT(!irqs, "IRQ pending"); } -static void assert_clear(void) +static void assert_clear(struct kvm_vcpu *vcpu) { + struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs; struct kvm_sregs sregs; struct kvm_regs regs; struct kvm_fpu fpu; - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); TEST_ASSERT(!memcmp(®s.gprs, regs_null, sizeof(regs.gprs)), "grs == 0"); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(!memcmp(&sregs.acrs, regs_null, sizeof(sregs.acrs)), "acrs == 0"); - vcpu_fpu_get(vm, VCPU_ID, &fpu); + vcpu_fpu_get(vcpu, &fpu); TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0"); /* sync regs */ @@ -112,8 +109,10 @@ static void assert_clear(void) "vrs0-15 == 0 (sync_regs)"); } -static void assert_initial_noclear(void) +static void assert_initial_noclear(struct kvm_vcpu *vcpu) { + struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs; + TEST_ASSERT(sync_regs->gprs[0] == 0xffff000000000000UL, "gpr0 == 0xffff000000000000 (sync_regs)"); TEST_ASSERT(sync_regs->gprs[1] == 0x0000555500000000UL, @@ -127,13 +126,14 @@ static void assert_initial_noclear(void) TEST_ASSERT(sync_regs->acrs[9] == 1, "ar9 == 1 (sync_regs)"); } -static void assert_initial(void) +static void assert_initial(struct kvm_vcpu *vcpu) { + struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs; struct kvm_sregs sregs; struct kvm_fpu fpu; /* KVM_GET_SREGS */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0 (KVM_GET_SREGS)"); TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000 (KVM_GET_SREGS)"); @@ -156,36 +156,38 @@ static void assert_initial(void) TEST_ASSERT(sync_regs->gbea == 1, "gbea == 1 (sync_regs)"); /* kvm_run */ - TEST_ASSERT(run->psw_addr == 0, "psw_addr == 0 (kvm_run)"); - TEST_ASSERT(run->psw_mask == 0, "psw_mask == 0 (kvm_run)"); + TEST_ASSERT(vcpu->run->psw_addr == 0, "psw_addr == 0 (kvm_run)"); + TEST_ASSERT(vcpu->run->psw_mask == 0, "psw_mask == 0 (kvm_run)"); - vcpu_fpu_get(vm, VCPU_ID, &fpu); + vcpu_fpu_get(vcpu, &fpu); TEST_ASSERT(!fpu.fpc, "fpc == 0"); - test_one_reg(KVM_REG_S390_GBEA, 1); - test_one_reg(KVM_REG_S390_PP, 0); - test_one_reg(KVM_REG_S390_TODPR, 0); - test_one_reg(KVM_REG_S390_CPU_TIMER, 0); - test_one_reg(KVM_REG_S390_CLOCK_COMP, 0); + test_one_reg(vcpu, KVM_REG_S390_GBEA, 1); + test_one_reg(vcpu, KVM_REG_S390_PP, 0); + test_one_reg(vcpu, KVM_REG_S390_TODPR, 0); + test_one_reg(vcpu, KVM_REG_S390_CPU_TIMER, 0); + test_one_reg(vcpu, KVM_REG_S390_CLOCK_COMP, 0); } -static void assert_normal_noclear(void) +static void assert_normal_noclear(struct kvm_vcpu *vcpu) { + struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs; + TEST_ASSERT(sync_regs->crs[2] == 0x10, "cr2 == 10 (sync_regs)"); TEST_ASSERT(sync_regs->crs[8] == 1, "cr10 == 1 (sync_regs)"); TEST_ASSERT(sync_regs->crs[10] == 1, "cr10 == 1 (sync_regs)"); TEST_ASSERT(sync_regs->crs[11] == -1, "cr11 == -1 (sync_regs)"); } -static void assert_normal(void) +static void assert_normal(struct kvm_vcpu *vcpu) { - test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID); - TEST_ASSERT(sync_regs->pft == KVM_S390_PFAULT_TOKEN_INVALID, + test_one_reg(vcpu, KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID); + TEST_ASSERT(vcpu->run->s.regs.pft == KVM_S390_PFAULT_TOKEN_INVALID, "pft == 0xff..... (sync_regs)"); - assert_noirq(); + assert_noirq(vcpu); } -static void inject_irq(int cpu_id) +static void inject_irq(struct kvm_vcpu *vcpu) { struct kvm_s390_irq_state irq_state; struct kvm_s390_irq *irq = &buf[0]; @@ -195,85 +197,119 @@ static void inject_irq(int cpu_id) irq_state.len = sizeof(struct kvm_s390_irq); irq_state.buf = (unsigned long)buf; irq->type = KVM_S390_INT_EMERGENCY; - irq->u.emerg.code = cpu_id; - irqs = _vcpu_ioctl(vm, cpu_id, KVM_S390_SET_IRQ_STATE, &irq_state); + irq->u.emerg.code = vcpu->id; + irqs = __vcpu_ioctl(vcpu, KVM_S390_SET_IRQ_STATE, &irq_state); TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno); } +static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu) +{ + struct kvm_vm *vm; + + vm = vm_create(1); + + *vcpu = vm_vcpu_add(vm, ARBITRARY_NON_ZERO_VCPU_ID, guest_code_initial); + + return vm; +} + static void test_normal(void) { - pr_info("Testing normal reset\n"); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_initial); - run = vcpu_state(vm, VCPU_ID); - sync_regs = &run->s.regs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + ksft_print_msg("Testing normal reset\n"); + vm = create_vm(&vcpu); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - inject_irq(VCPU_ID); + inject_irq(vcpu); - vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0); + vcpu_ioctl(vcpu, KVM_S390_NORMAL_RESET, NULL); /* must clears */ - assert_normal(); + assert_normal(vcpu); /* must not clears */ - assert_normal_noclear(); - assert_initial_noclear(); + assert_normal_noclear(vcpu); + assert_initial_noclear(vcpu); kvm_vm_free(vm); } static void test_initial(void) { - pr_info("Testing initial reset\n"); - vm = vm_create_default(VCPU_ID, 0, guest_code_initial); - run = vcpu_state(vm, VCPU_ID); - sync_regs = &run->s.regs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; - vcpu_run(vm, VCPU_ID); + ksft_print_msg("Testing initial reset\n"); + vm = create_vm(&vcpu); - inject_irq(VCPU_ID); + vcpu_run(vcpu); - vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0); + inject_irq(vcpu); + + vcpu_ioctl(vcpu, KVM_S390_INITIAL_RESET, NULL); /* must clears */ - assert_normal(); - assert_initial(); + assert_normal(vcpu); + assert_initial(vcpu); /* must not clears */ - assert_initial_noclear(); + assert_initial_noclear(vcpu); kvm_vm_free(vm); } static void test_clear(void) { - pr_info("Testing clear reset\n"); - vm = vm_create_default(VCPU_ID, 0, guest_code_initial); - run = vcpu_state(vm, VCPU_ID); - sync_regs = &run->s.regs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + ksft_print_msg("Testing clear reset\n"); + vm = create_vm(&vcpu); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - inject_irq(VCPU_ID); + inject_irq(vcpu); - vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0); + vcpu_ioctl(vcpu, KVM_S390_CLEAR_RESET, NULL); /* must clears */ - assert_normal(); - assert_initial(); - assert_clear(); + assert_normal(vcpu); + assert_initial(vcpu); + assert_clear(vcpu); kvm_vm_free(vm); } +struct testdef { + const char *name; + void (*test)(void); + bool needs_cap; +} testlist[] = { + { "initial", test_initial, false }, + { "normal", test_normal, true }, + { "clear", test_clear, true }, +}; + int main(int argc, char *argv[]) { + bool has_s390_vcpu_resets = kvm_check_cap(KVM_CAP_S390_VCPU_RESETS); + int idx; + setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ - test_initial(); - if (kvm_check_cap(KVM_CAP_S390_VCPU_RESETS)) { - test_normal(); - test_clear(); + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(testlist)); + + for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { + if (!testlist[idx].needs_cap || has_s390_vcpu_resets) { + testlist[idx].test(); + ksft_test_result_pass("%s\n", testlist[idx].name); + } else { + ksft_test_result_skip("%s - no VCPU_RESETS capability\n", + testlist[idx].name); + } } - return 0; + + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index caf7b8859a94..3fdb6e2598eb 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -21,8 +21,7 @@ #include "test_util.h" #include "kvm_util.h" #include "diag318_test_handler.h" - -#define VCPU_ID 5 +#include "kselftest.h" static void guest_code(void) { @@ -74,61 +73,58 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right) #define TEST_SYNC_FIELDS (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS|KVM_SYNC_DIAG318) #define INVALID_SYNC_FIELD 0x80000000 -int main(int argc, char *argv[]) +void test_read_invalid(struct kvm_vcpu *vcpu) { - struct kvm_vm *vm; - struct kvm_run *run; - struct kvm_regs regs; - struct kvm_sregs sregs; - int rv, cap; - - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - - cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - if (!cap) { - print_skip("CAP_SYNC_REGS not supported"); - exit(KSFT_SKIP); - } - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - - run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; + int rv; /* Request reading invalid register set from VCPU. */ run->kvm_valid_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; +} + +void test_set_invalid(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + int rv; /* Request setting invalid register set into VCPU. */ run->kvm_dirty_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; +} + +void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_sregs sregs; + struct kvm_regs regs; + int rv; /* Request and verify all valid register sets. */ run->kvm_valid_regs = TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, "Unexpected exit reason: %u (%s)\n", @@ -141,11 +137,19 @@ int main(int argc, char *argv[]) run->s390_sieic.icptcode, run->s390_sieic.ipa, run->s390_sieic.ipb); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs); +} + +void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_sregs sregs; + struct kvm_regs regs; + int rv; /* Set and verify various register values */ run->s.regs.gprs[11] = 0xBAD1DEA; @@ -159,7 +163,7 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs |= KVM_SYNC_DIAG318; } - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, "Unexpected exit reason: %u (%s)\n", @@ -175,11 +179,17 @@ int main(int argc, char *argv[]) "diag318 sync regs value incorrect 0x%llx.", run->s.regs.diag318); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs); +} + +void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + int rv; /* Clear kvm_dirty_regs bits, verify new s.regs values are * overwritten with existing guest values. @@ -188,7 +198,7 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs = 0; run->s.regs.gprs[11] = 0xDEADBEEF; run->s.regs.diag318 = 0x4B1D; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, "Unexpected exit reason: %u (%s)\n", @@ -200,8 +210,43 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.diag318 != 0x4B1D, "diag318 sync regs value incorrect 0x%llx.", run->s.regs.diag318); +} + +struct testdef { + const char *name; + void (*test)(struct kvm_vcpu *vcpu); +} testlist[] = { + { "read invalid", test_read_invalid }, + { "set invalid", test_set_invalid }, + { "request+verify all valid regs", test_req_and_verify_all_valid_regs }, + { "set+verify various regs", test_set_and_verify_various_reg_values }, + { "clear kvm_dirty_regs bits", test_clear_kvm_dirty_regs_bits }, +}; + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int idx; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SYNC_REGS)); + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + ksft_print_header(); + + ksft_set_plan(ARRAY_SIZE(testlist)); + + /* Create VM */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { + testlist[idx].test(vcpu); + ksft_test_result_pass("%s\n", testlist[idx].name); + } kvm_vm_free(vm); - return 0; + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index c097b9db495e..a9a0b76e5fa4 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -8,14 +8,13 @@ #include <sys/mman.h> #include "test_util.h" #include "kvm_util.h" +#include "kselftest.h" #define PAGE_SHIFT 12 #define PAGE_SIZE (1 << PAGE_SHIFT) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) -#define VCPU_ID 1 - static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE]; static uint8_t *const page_store_prot = pages[0]; static uint8_t *const page_fetch_prot = pages[1]; @@ -63,12 +62,12 @@ static enum permission test_protection(void *addr, uint8_t key) } enum stage { - STAGE_END, STAGE_INIT_SIMPLE, TEST_SIMPLE, STAGE_INIT_FETCH_PROT_OVERRIDE, TEST_FETCH_PROT_OVERRIDE, TEST_STORAGE_PROT_OVERRIDE, + STAGE_END /* must be the last entry (it's the amount of tests) */ }; struct test { @@ -182,46 +181,63 @@ static void guest_code(void) GUEST_SYNC(perform_next_stage(&i, mapped_0)); } -#define HOST_SYNC(vmp, stage) \ -({ \ - struct kvm_vm *__vm = (vmp); \ - struct ucall uc; \ - int __stage = (stage); \ - \ - vcpu_run(__vm, VCPU_ID); \ - get_ucall(__vm, VCPU_ID, &uc); \ - if (uc.cmd == UCALL_ABORT) { \ - TEST_FAIL("line %lu: %s, hints: %lu, %lu", uc.args[1], \ - (const char *)uc.args[0], uc.args[2], uc.args[3]); \ - } \ - ASSERT_EQ(uc.cmd, UCALL_SYNC); \ - ASSERT_EQ(uc.args[1], __stage); \ +#define HOST_SYNC_NO_TAP(vcpup, stage) \ +({ \ + struct kvm_vcpu *__vcpu = (vcpup); \ + struct ucall uc; \ + int __stage = (stage); \ + \ + vcpu_run(__vcpu); \ + get_ucall(__vcpu, &uc); \ + if (uc.cmd == UCALL_ABORT) \ + REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu"); \ + ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + ASSERT_EQ(uc.args[1], __stage); \ +}) + +#define HOST_SYNC(vcpu, stage) \ +({ \ + HOST_SYNC_NO_TAP(vcpu, stage); \ + ksft_test_result_pass("" #stage "\n"); \ }) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; vm_vaddr_t guest_0_page; - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + ksft_print_header(); + ksft_set_plan(STAGE_END); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; - HOST_SYNC(vm, STAGE_INIT_SIMPLE); + HOST_SYNC(vcpu, STAGE_INIT_SIMPLE); mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ); - HOST_SYNC(vm, TEST_SIMPLE); + HOST_SYNC(vcpu, TEST_SIMPLE); guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0); - if (guest_0_page != 0) - print_skip("Did not allocate page at 0 for fetch protection override tests"); - HOST_SYNC(vm, STAGE_INIT_FETCH_PROT_OVERRIDE); + if (guest_0_page != 0) { + /* Use NO_TAP so we don't get a PASS print */ + HOST_SYNC_NO_TAP(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE); + ksft_test_result_skip("STAGE_INIT_FETCH_PROT_OVERRIDE - " + "Did not allocate page at 0\n"); + } else { + HOST_SYNC(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE); + } if (guest_0_page == 0) mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ); run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; run->kvm_dirty_regs = KVM_SYNC_CRS; - HOST_SYNC(vm, TEST_FETCH_PROT_OVERRIDE); + HOST_SYNC(vcpu, TEST_FETCH_PROT_OVERRIDE); run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; run->kvm_dirty_regs = KVM_SYNC_CRS; - HOST_SYNC(vm, TEST_STORAGE_PROT_OVERRIDE); + HOST_SYNC(vcpu, TEST_STORAGE_PROT_OVERRIDE); + + kvm_vm_free(vm); + + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 73bc297dabe6..0d55f508d595 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -17,8 +17,6 @@ #include <kvm_util.h> #include <processor.h> -#define VCPU_ID 0 - /* * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a * 2MB sized and aligned region so that the initial region corresponds to @@ -54,8 +52,8 @@ static inline uint64_t guest_spin_on_val(uint64_t spin_val) static void *vcpu_worker(void *data) { - struct kvm_vm *vm = data; - struct kvm_run *run; + struct kvm_vcpu *vcpu = data; + struct kvm_run *run = vcpu->run; struct ucall uc; uint64_t cmd; @@ -64,13 +62,11 @@ static void *vcpu_worker(void *data) * which will occur if the guest attempts to access a memslot after it * has been deleted or while it is being moved . */ - run = vcpu_state(vm, VCPU_ID); - while (1) { - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); if (run->exit_reason == KVM_EXIT_IO) { - cmd = get_ucall(vm, VCPU_ID, &uc); + cmd = get_ucall(vcpu, &uc); if (cmd != UCALL_SYNC) break; @@ -92,8 +88,7 @@ static void *vcpu_worker(void *data) } if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) - TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2]); + REPORT_GUEST_ASSERT_1(uc, "val = %lu"); return NULL; } @@ -113,13 +108,14 @@ static void wait_for_vcpu(void) usleep(100000); } -static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code) +static struct kvm_vm *spawn_vm(struct kvm_vcpu **vcpu, pthread_t *vcpu_thread, + void *guest_code) { struct kvm_vm *vm; uint64_t *hva; uint64_t gpa; - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(vcpu, guest_code); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP, MEM_REGION_GPA, MEM_REGION_SLOT, @@ -138,7 +134,7 @@ static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code) hva = addr_gpa2hva(vm, MEM_REGION_GPA); memset(hva, 0, 2 * 4096); - pthread_create(vcpu_thread, NULL, vcpu_worker, vm); + pthread_create(vcpu_thread, NULL, vcpu_worker, *vcpu); /* Ensure the guest thread is spun up. */ wait_for_vcpu(); @@ -180,10 +176,11 @@ static void guest_code_move_memory_region(void) static void test_move_memory_region(void) { pthread_t vcpu_thread; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t *hva; - vm = spawn_vm(&vcpu_thread, guest_code_move_memory_region); + vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region); hva = addr_gpa2hva(vm, MEM_REGION_GPA); @@ -258,11 +255,12 @@ static void guest_code_delete_memory_region(void) static void test_delete_memory_region(void) { pthread_t vcpu_thread; + struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_run *run; struct kvm_vm *vm; - vm = spawn_vm(&vcpu_thread, guest_code_delete_memory_region); + vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region); /* Delete the memory region, the guest should not die. */ vm_mem_region_delete(vm, MEM_REGION_SLOT); @@ -286,13 +284,13 @@ static void test_delete_memory_region(void) pthread_join(vcpu_thread, NULL); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN || run->exit_reason == KVM_EXIT_INTERNAL_ERROR, "Unexpected exit reason = %d", run->exit_reason); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); /* * On AMD, after KVM_EXIT_SHUTDOWN the VMCB has been reinitialized already, @@ -309,19 +307,19 @@ static void test_delete_memory_region(void) static void test_zero_memory_regions(void) { + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; pr_info("Testing KVM_RUN with zero added memory regions\n"); - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); - TEST_ASSERT(!ioctl(vm_get_fd(vm), KVM_SET_NR_MMU_PAGES, 64), - "KVM_SET_NR_MMU_PAGES failed, errno = %d\n", errno); - vcpu_run(vm, VCPU_ID); + vm_ioctl(vm, KVM_SET_NR_MMU_PAGES, (void *)64ul); + vcpu_run(vcpu); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, "Unexpected exit_reason = %u\n", run->exit_reason); @@ -354,7 +352,7 @@ static void test_add_max_memory_regions(void) "KVM_CAP_NR_MEMSLOTS should be greater than 0"); pr_info("Allowed number of memory slots: %i\n", max_mem_slots); - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm = vm_create_barebones(); /* Check it can be added memory slots up to the maximum allowed */ pr_info("Adding slots 0..%i, each memory region with %dK size\n", diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 8c4e811bd586..db8967f1a17b 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -58,36 +58,32 @@ static void guest_code(int cpu) GUEST_DONE(); } -static void steal_time_init(struct kvm_vm *vm) +static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { - int i; - - if (!(kvm_get_supported_cpuid_entry(KVM_CPUID_FEATURES)->eax & - KVM_FEATURE_STEAL_TIME)) { - print_skip("steal-time not supported"); - exit(KSFT_SKIP); - } + return kvm_cpu_has(X86_FEATURE_KVM_STEAL_TIME); +} - for (i = 0; i < NR_VCPUS; ++i) { - int ret; +static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +{ + int ret; - /* ST_GPA_BASE is identity mapped */ - st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); - sync_global_to_guest(vm, st_gva[i]); + /* ST_GPA_BASE is identity mapped */ + st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); + sync_global_to_guest(vcpu->vm, st_gva[i]); - ret = _vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK); - TEST_ASSERT(ret == 0, "Bad GPA didn't fail"); + ret = _vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, + (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK); + TEST_ASSERT(ret == 0, "Bad GPA didn't fail"); - vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED); - } + vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) +static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) { - struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]); + struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); int i; - pr_info("VCPU%d:\n", vcpuid); + pr_info("VCPU%d:\n", vcpu_idx); pr_info(" steal: %lld\n", st->steal); pr_info(" version: %d\n", st->version); pr_info(" flags: %d\n", st->flags); @@ -158,49 +154,50 @@ static void guest_code(int cpu) GUEST_DONE(); } -static void steal_time_init(struct kvm_vm *vm) +static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { struct kvm_device_attr dev = { .group = KVM_ARM_VCPU_PVTIME_CTRL, .attr = KVM_ARM_VCPU_PVTIME_IPA, }; - int i, ret; - - ret = _vcpu_ioctl(vm, 0, KVM_HAS_DEVICE_ATTR, &dev); - if (ret != 0 && errno == ENXIO) { - print_skip("steal-time not supported"); - exit(KSFT_SKIP); - } - for (i = 0; i < NR_VCPUS; ++i) { - uint64_t st_ipa; + return !__vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); +} - vcpu_ioctl(vm, i, KVM_HAS_DEVICE_ATTR, &dev); +static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +{ + struct kvm_vm *vm = vcpu->vm; + uint64_t st_ipa; + int ret; - dev.addr = (uint64_t)&st_ipa; + struct kvm_device_attr dev = { + .group = KVM_ARM_VCPU_PVTIME_CTRL, + .attr = KVM_ARM_VCPU_PVTIME_IPA, + .addr = (uint64_t)&st_ipa, + }; - /* ST_GPA_BASE is identity mapped */ - st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); - sync_global_to_guest(vm, st_gva[i]); + vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); - st_ipa = (ulong)st_gva[i] | 1; - ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); - TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL"); + /* ST_GPA_BASE is identity mapped */ + st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); + sync_global_to_guest(vm, st_gva[i]); - st_ipa = (ulong)st_gva[i]; - vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); + st_ipa = (ulong)st_gva[i] | 1; + ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL"); - ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); - TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST"); + st_ipa = (ulong)st_gva[i]; + vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); - } + ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST"); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) +static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) { - struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]); + struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); - pr_info("VCPU%d:\n", vcpuid); + pr_info("VCPU%d:\n", vcpu_idx); pr_info(" rev: %d\n", st->rev); pr_info(" attr: %d\n", st->attr); pr_info(" st_time: %ld\n", st->st_time); @@ -224,29 +221,27 @@ static void *do_steal_time(void *arg) return NULL; } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +static void run_vcpu(struct kvm_vcpu *vcpu) { struct ucall uc; - vcpu_args_set(vm, vcpuid, 1, vcpuid); - - vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: case UCALL_DONE: break; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } int main(int ac, char **av) { + struct kvm_vcpu *vcpus[NR_VCPUS]; struct kvm_vm *vm; pthread_attr_t attr; pthread_t thread; @@ -266,26 +261,26 @@ int main(int ac, char **av) pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset); pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); - /* Create a one VCPU guest and an identity mapped memslot for the steal time structure */ - vm = vm_create_default(0, 0, guest_code); + /* Create a VM and an identity mapped memslot for the steal time structure */ + vm = vm_create_with_vcpus(NR_VCPUS, guest_code, vcpus); gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages); ucall_init(vm, NULL); - /* Add the rest of the VCPUs */ - for (i = 1; i < NR_VCPUS; ++i) - vm_vcpu_add_default(vm, i, guest_code); - - steal_time_init(vm); + TEST_REQUIRE(is_steal_time_supported(vcpus[0])); /* Run test on each VCPU */ for (i = 0; i < NR_VCPUS; ++i) { + steal_time_init(vcpus[i], i); + + vcpu_args_set(vcpus[i], 1, i); + /* First VCPU run initializes steal-time */ - run_vcpu(vm, i); + run_vcpu(vcpus[i]); /* Second VCPU run, expect guest stolen time to be <= run_delay */ - run_vcpu(vm, i); + run_vcpu(vcpus[i]); sync_global_from_guest(vm, guest_stolen_time[i]); stolen_time = guest_stolen_time[i]; run_delay = get_run_delay(); @@ -306,7 +301,7 @@ int main(int ac, char **av) MIN_RUN_DELAY_NS, run_delay); /* Run VCPU again to confirm stolen time is consistent with run_delay */ - run_vcpu(vm, i); + run_vcpu(vcpus[i]); sync_global_from_guest(vm, guest_stolen_time[i]); stolen_time = guest_stolen_time[i] - stolen_time; TEST_ASSERT(stolen_time >= run_delay, diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c index b337bbbfa41f..1c274933912b 100644 --- a/tools/testing/selftests/kvm/system_counter_offset_test.c +++ b/tools/testing/selftests/kvm/system_counter_offset_test.c @@ -14,8 +14,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - #ifdef __x86_64__ struct test_case { @@ -28,19 +26,17 @@ static struct test_case test_cases[] = { { -180 * NSEC_PER_SEC }, }; -static void check_preconditions(struct kvm_vm *vm) +static void check_preconditions(struct kvm_vcpu *vcpu) { - if (!_vcpu_has_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL, KVM_VCPU_TSC_OFFSET)) - return; - - print_skip("KVM_VCPU_TSC_OFFSET not supported; skipping test"); - exit(KSFT_SKIP); + __TEST_REQUIRE(!__vcpu_has_device_attr(vcpu, KVM_VCPU_TSC_CTRL, + KVM_VCPU_TSC_OFFSET), + "KVM_VCPU_TSC_OFFSET not supported; skipping test"); } -static void setup_system_counter(struct kvm_vm *vm, struct test_case *test) +static void setup_system_counter(struct kvm_vcpu *vcpu, struct test_case *test) { - vcpu_access_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL, - KVM_VCPU_TSC_OFFSET, &test->tsc_offset, true); + vcpu_device_attr_set(vcpu, KVM_VCPU_TSC_CTRL, KVM_VCPU_TSC_OFFSET, + &test->tsc_offset); } static uint64_t guest_read_system_counter(struct test_case *test) @@ -87,11 +83,10 @@ static void handle_sync(struct ucall *uc, uint64_t start, uint64_t end) static void handle_abort(struct ucall *uc) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], - __FILE__, uc->args[1]); + REPORT_GUEST_ASSERT(*uc); } -static void enter_guest(struct kvm_vm *vm) +static void enter_guest(struct kvm_vcpu *vcpu) { uint64_t start, end; struct ucall uc; @@ -100,12 +95,12 @@ static void enter_guest(struct kvm_vm *vm) for (i = 0; i < ARRAY_SIZE(test_cases); i++) { struct test_case *test = &test_cases[i]; - setup_system_counter(vm, test); + setup_system_counter(vcpu, test); start = host_read_guest_system_counter(test); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); end = host_read_guest_system_counter(test); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: handle_sync(&uc, start, end); break; @@ -114,19 +109,20 @@ static void enter_guest(struct kvm_vm *vm) return; default: TEST_ASSERT(0, "unhandled ucall %ld\n", - get_ucall(vm, VCPU_ID, &uc)); + get_ucall(vcpu, &uc)); } } } int main(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm = vm_create_default(VCPU_ID, 0, guest_main); - check_preconditions(vm); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + check_preconditions(vcpu); ucall_init(vm, NULL); - enter_guest(vm); + enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 76f65c22796f..dadcbad10a1d 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -25,10 +25,6 @@ # error This test is 64-bit only #endif -#define VCPU_ID 0 -#define X86_FEATURE_XSAVE (1 << 26) -#define X86_FEATURE_OSXSAVE (1 << 27) - #define NUM_TILES 8 #define TILE_SIZE 1024 #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) @@ -124,15 +120,8 @@ static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) static inline void check_cpuid_xsave(void) { - uint32_t eax, ebx, ecx, edx; - - eax = 1; - ecx = 0; - cpuid(&eax, &ebx, &ecx, &edx); - if (!(ecx & X86_FEATURE_XSAVE)) - GUEST_ASSERT(!"cpuid: no CPU xsave support!"); - if (!(ecx & X86_FEATURE_OSXSAVE)) - GUEST_ASSERT(!"cpuid: no OS xsave support!"); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); } static bool check_xsave_supports_xtile(void) @@ -144,10 +133,7 @@ static bool enum_xtile_config(void) { u32 eax, ebx, ecx, edx; - eax = TILE_CPUID; - ecx = TILE_PALETTE_CPUID_SUBLEAVE; - - cpuid(&eax, &ebx, &ecx, &edx); + __cpuid(TILE_CPUID, TILE_PALETTE_CPUID_SUBLEAVE, &eax, &ebx, &ecx, &edx); if (!eax || !ebx || !ecx) return false; @@ -169,10 +155,7 @@ static bool enum_xsave_tile(void) { u32 eax, ebx, ecx, edx; - eax = XSTATE_CPUID; - ecx = XFEATURE_XTILEDATA; - - cpuid(&eax, &ebx, &ecx, &edx); + __cpuid(XSTATE_CPUID, XFEATURE_XTILEDATA, &eax, &ebx, &ecx, &edx); if (!eax || !ebx) return false; @@ -187,10 +170,7 @@ static bool check_xsave_size(void) u32 eax, ebx, ecx, edx; bool valid = false; - eax = XSTATE_CPUID; - ecx = XSTATE_USER_STATE_SUBLEAVE; - - cpuid(&eax, &ebx, &ecx, &edx); + __cpuid(XSTATE_CPUID, XSTATE_USER_STATE_SUBLEAVE, &eax, &ebx, &ecx, &edx); if (ebx && ebx <= XSAVE_SIZE) valid = true; @@ -316,46 +296,36 @@ void guest_nm_handler(struct ex_regs *regs) int main(int argc, char *argv[]) { - struct kvm_cpuid_entry2 *entry; struct kvm_regs regs1, regs2; - bool amx_supported = false; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct kvm_x86_state *state; - int xsave_restore_size = 0; + int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xsavedata; struct ucall uc; u32 amx_offset; int stage, ret; - vm_xsave_req_perm(XSTATE_XTILE_DATA_BIT); + vm_xsave_require_permission(XSTATE_XTILE_DATA_BIT); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & X86_FEATURE_XSAVE)) { - print_skip("XSAVE feature not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_AMX_TILE)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA)); - if (kvm_get_cpuid_max_basic() >= 0xd) { - entry = kvm_get_supported_cpuid_index(0xd, 0); - amx_supported = entry && !!(entry->eax & XFEATURE_MASK_XTILE); - if (!amx_supported) { - print_skip("AMX is not supported by the vCPU (eax=0x%x)", entry->eax); - exit(KSFT_SKIP); - } - /* Get xsave/restore max size */ - xsave_restore_size = entry->ecx; - } + /* Get xsave/restore max size */ + xsave_restore_size = kvm_get_supported_cpuid_entry(0xd)->ecx; - run = vcpu_state(vm, VCPU_ID); - vcpu_regs_get(vm, VCPU_ID, ®s1); + run = vcpu->run; + vcpu_regs_get(vcpu, ®s1); /* Register #NM handler */ vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); /* amx cfg for guest_code */ @@ -369,19 +339,18 @@ int main(int argc, char *argv[]) /* xsave data for guest_code */ xsavedata = vm_vaddr_alloc_pages(vm, 3); memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize()); - vcpu_args_set(vm, VCPU_ID, 3, amx_cfg, tiledata, xsavedata); + vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xsavedata); for (stage = 1; ; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: switch (uc.args[1]) { @@ -403,7 +372,7 @@ int main(int argc, char *argv[]) * size subtract 8K amx size. */ amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); void *amx_start = (void *)state->xsave + amx_offset; void *tiles_data = (void *)addr_gva2hva(vm, tiledata); /* Only check TMM0 register, 1 tile */ @@ -424,22 +393,20 @@ int main(int argc, char *argv[]) TEST_FAIL("Unknown ucall %lu", uc.cmd); } - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®s2); TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c index 16d2465c5634..a6aeee2e62e4 100644 --- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -12,8 +12,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - /* CPUIDs known to differ */ struct { u32 function; @@ -33,10 +31,9 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) u32 eax, ebx, ecx, edx; for (i = 0; i < guest_cpuid->nent; i++) { - eax = guest_cpuid->entries[i].function; - ecx = guest_cpuid->entries[i].index; - - cpuid(&eax, &ebx, &ecx, &edx); + __cpuid(guest_cpuid->entries[i].function, + guest_cpuid->entries[i].index, + &eax, &ebx, &ecx, &edx); GUEST_ASSERT(eax == guest_cpuid->entries[i].eax && ebx == guest_cpuid->entries[i].ebx && @@ -48,9 +45,9 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) static void test_cpuid_40000000(struct kvm_cpuid2 *guest_cpuid) { - u32 eax = 0x40000000, ebx, ecx = 0, edx; + u32 eax, ebx, ecx, edx; - cpuid(&eax, &ebx, &ecx, &edx); + cpuid(0x40000000, &eax, &ebx, &ecx, &edx); GUEST_ASSERT(eax == 0x40000001); } @@ -68,7 +65,7 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid) GUEST_DONE(); } -static bool is_cpuid_mangled(struct kvm_cpuid_entry2 *entrie) +static bool is_cpuid_mangled(const struct kvm_cpuid_entry2 *entrie) { int i; @@ -81,50 +78,44 @@ static bool is_cpuid_mangled(struct kvm_cpuid_entry2 *entrie) return false; } -static void check_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *entrie) +static void compare_cpuids(const struct kvm_cpuid2 *cpuid1, + const struct kvm_cpuid2 *cpuid2) { + const struct kvm_cpuid_entry2 *e1, *e2; int i; - for (i = 0; i < cpuid->nent; i++) { - if (cpuid->entries[i].function == entrie->function && - cpuid->entries[i].index == entrie->index) { - if (is_cpuid_mangled(entrie)) - return; - - TEST_ASSERT(cpuid->entries[i].eax == entrie->eax && - cpuid->entries[i].ebx == entrie->ebx && - cpuid->entries[i].ecx == entrie->ecx && - cpuid->entries[i].edx == entrie->edx, - "CPUID 0x%x.%x differ: 0x%x:0x%x:0x%x:0x%x vs 0x%x:0x%x:0x%x:0x%x", - entrie->function, entrie->index, - cpuid->entries[i].eax, cpuid->entries[i].ebx, - cpuid->entries[i].ecx, cpuid->entries[i].edx, - entrie->eax, entrie->ebx, entrie->ecx, entrie->edx); - return; - } - } + TEST_ASSERT(cpuid1->nent == cpuid2->nent, + "CPUID nent mismatch: %d vs. %d", cpuid1->nent, cpuid2->nent); - TEST_ASSERT(false, "CPUID 0x%x.%x not found", entrie->function, entrie->index); -} + for (i = 0; i < cpuid1->nent; i++) { + e1 = &cpuid1->entries[i]; + e2 = &cpuid2->entries[i]; -static void compare_cpuids(struct kvm_cpuid2 *cpuid1, struct kvm_cpuid2 *cpuid2) -{ - int i; + TEST_ASSERT(e1->function == e2->function && + e1->index == e2->index && e1->flags == e2->flags, + "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x\n", + i, e1->function, e1->index, e1->flags, + e2->function, e2->index, e2->flags); - for (i = 0; i < cpuid1->nent; i++) - check_cpuid(cpuid2, &cpuid1->entries[i]); + if (is_cpuid_mangled(e1)) + continue; - for (i = 0; i < cpuid2->nent; i++) - check_cpuid(cpuid1, &cpuid2->entries[i]); + TEST_ASSERT(e1->eax == e2->eax && e1->ebx == e2->ebx && + e1->ecx == e2->ecx && e1->edx == e2->edx, + "CPUID 0x%x.%x differ: 0x%x:0x%x:0x%x:0x%x vs 0x%x:0x%x:0x%x:0x%x", + e1->function, e1->index, + e1->eax, e1->ebx, e1->ecx, e1->edx, + e2->eax, e2->ebx, e2->ecx, e2->edx); + } } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) { struct ucall uc; - _vcpu_run(vm, vcpuid); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && uc.args[1] == stage + 1, @@ -134,11 +125,10 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) case UCALL_DONE: return; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } @@ -154,56 +144,53 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct return guest_cpuids; } -static void set_cpuid_after_run(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid) +static void set_cpuid_after_run(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *ent; int rc; u32 eax, ebx, x; /* Setting unmodified CPUID is allowed */ - rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + rc = __vcpu_set_cpuid(vcpu); TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc); /* Changing CPU features is forbidden */ - ent = get_cpuid(cpuid, 0x7, 0); + ent = vcpu_get_cpuid_entry(vcpu, 0x7); ebx = ent->ebx; ent->ebx--; - rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + rc = __vcpu_set_cpuid(vcpu); TEST_ASSERT(rc, "Changing CPU features should fail"); ent->ebx = ebx; /* Changing MAXPHYADDR is forbidden */ - ent = get_cpuid(cpuid, 0x80000008, 0); + ent = vcpu_get_cpuid_entry(vcpu, 0x80000008); eax = ent->eax; x = eax & 0xff; ent->eax = (eax & ~0xffu) | (x - 1); - rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + rc = __vcpu_set_cpuid(vcpu); TEST_ASSERT(rc, "Changing MAXPHYADDR should fail"); ent->eax = eax; } int main(void) { - struct kvm_cpuid2 *supp_cpuid, *cpuid2; + struct kvm_vcpu *vcpu; vm_vaddr_t cpuid_gva; struct kvm_vm *vm; int stage; - vm = vm_create_default(VCPU_ID, 0, guest_main); - - supp_cpuid = kvm_get_supported_cpuid(); - cpuid2 = vcpu_get_cpuid(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); - compare_cpuids(supp_cpuid, cpuid2); + compare_cpuids(kvm_get_supported_cpuid(), vcpu->cpuid); - vcpu_alloc_cpuid(vm, &cpuid_gva, cpuid2); + vcpu_alloc_cpuid(vm, &cpuid_gva, vcpu->cpuid); - vcpu_args_set(vm, VCPU_ID, 1, cpuid_gva); + vcpu_args_set(vcpu, 1, cpuid_gva); for (stage = 0; stage < 3; stage++) - run_vcpu(vm, VCPU_ID, stage); + run_vcpu(vcpu, stage); - set_cpuid_after_run(vm, cpuid2); + set_cpuid_after_run(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 6f6fd189dda3..4208487652f8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -19,25 +19,11 @@ #include "kvm_util.h" #include "processor.h" -#define X86_FEATURE_XSAVE (1<<26) -#define X86_FEATURE_OSXSAVE (1<<27) -#define VCPU_ID 1 - static inline bool cr4_cpuid_is_sync(void) { - int func, subfunc; - uint32_t eax, ebx, ecx, edx; - uint64_t cr4; - - func = 0x1; - subfunc = 0x0; - __asm__ __volatile__("cpuid" - : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx) - : "a"(func), "c"(subfunc)); + uint64_t cr4 = get_cr4(); - cr4 = get_cr4(); - - return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE)); + return (this_cpu_has(X86_FEATURE_OSXSAVE) == !!(cr4 & X86_CR4_OSXSAVE)); } static void guest_code(void) @@ -63,44 +49,37 @@ static void guest_code(void) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct kvm_sregs sregs; - struct kvm_cpuid_entry2 *entry; struct ucall uc; - int rc; - entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & X86_FEATURE_XSAVE)) { - print_skip("XSAVE feature not supported"); - return 0; - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; while (1) { - rc = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); + vcpu_sregs_set(vcpu, &sregs); break; case UCALL_ABORT: - TEST_FAIL("Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 5f078db1bcba..7ef99c3359a0 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -10,8 +10,6 @@ #include "processor.h" #include "apic.h" -#define VCPU_ID 0 - #define DR6_BD (1 << 13) #define DR7_GD (1 << 13) @@ -66,21 +64,22 @@ static void guest_code(void) GUEST_DONE(); } -#define CLEAR_DEBUG() memset(&debug, 0, sizeof(debug)) -#define APPLY_DEBUG() vcpu_set_guest_debug(vm, VCPU_ID, &debug) #define CAST_TO_RIP(v) ((unsigned long long)&(v)) -#define SET_RIP(v) do { \ - vcpu_regs_get(vm, VCPU_ID, ®s); \ - regs.rip = (v); \ - vcpu_regs_set(vm, VCPU_ID, ®s); \ - } while (0) -#define MOVE_RIP(v) SET_RIP(regs.rip + (v)); + +static void vcpu_skip_insn(struct kvm_vcpu *vcpu, int insn_len) +{ + struct kvm_regs regs; + + vcpu_regs_get(vcpu, ®s); + regs.rip += insn_len; + vcpu_regs_set(vcpu, ®s); +} int main(void) { struct kvm_guest_debug debug; unsigned long long target_dr6, target_rip; - struct kvm_regs regs; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; @@ -96,35 +95,32 @@ int main(void) 1, /* cli */ }; - if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) { - print_skip("KVM_CAP_SET_GUEST_DEBUG not supported"); - return 0; - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_GUEST_DEBUG)); - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; /* Test software BPs - int3 */ - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == BP_VECTOR && run->debug.arch.pc == CAST_TO_RIP(sw_bp), "INT3: exit %d exception %d rip 0x%llx (should be 0x%llx)", run->exit_reason, run->debug.arch.exception, run->debug.arch.pc, CAST_TO_RIP(sw_bp)); - MOVE_RIP(1); + vcpu_skip_insn(vcpu, 1); /* Test instruction HW BP over DR[0-3] */ for (i = 0; i < 4; i++) { - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[i] = CAST_TO_RIP(hw_bp); debug.arch.debugreg[7] = 0x400 | (1UL << (2*i+1)); - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | (1UL << i); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -137,17 +133,17 @@ int main(void) run->debug.arch.dr6, target_dr6); } /* Skip "nop" */ - MOVE_RIP(1); + vcpu_skip_insn(vcpu, 1); /* Test data access HW BP over DR[0-3] */ for (i = 0; i < 4; i++) { - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[i] = CAST_TO_RIP(guest_value); debug.arch.debugreg[7] = 0x00000400 | (1UL << (2*i+1)) | (0x000d0000UL << (4*i)); - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | (1UL << i); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -159,23 +155,22 @@ int main(void) run->debug.arch.pc, CAST_TO_RIP(write_data), run->debug.arch.dr6, target_dr6); /* Rollback the 4-bytes "mov" */ - MOVE_RIP(-7); + vcpu_skip_insn(vcpu, -7); } /* Skip the 4-bytes "mov" */ - MOVE_RIP(7); + vcpu_skip_insn(vcpu, 7); /* Test single step */ target_rip = CAST_TO_RIP(ss_start); target_dr6 = 0xffff4ff0ULL; - vcpu_regs_get(vm, VCPU_ID, ®s); for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) { target_rip += ss_size[i]; - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_BLOCKIRQ; debug.arch.debugreg[7] = 0x00000400; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && run->debug.arch.pc == target_rip && @@ -188,11 +183,11 @@ int main(void) } /* Finally test global disable */ - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[7] = 0x400 | DR7_GD; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | DR6_BD; TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -205,12 +200,12 @@ int main(void) target_dr6); /* Disable all debug controls, run to the end */ - CLEAR_DEBUG(); - APPLY_DEBUG(); + memset(&debug, 0, sizeof(debug)); + vcpu_guest_debug_set(vcpu, &debug); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO"); - cmd = get_ucall(vm, VCPU_ID, &uc); + cmd = get_ucall(vcpu, &uc); TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE"); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c index aeb3850f81bd..236e11755ba6 100644 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -11,7 +11,6 @@ #include "kvm_util.h" #include "vmx.h" -#define VCPU_ID 1 #define MAXPHYADDR 36 #define MEM_REGION_GVA 0x0000123456789000 @@ -27,14 +26,6 @@ static void guest_code(void) GUEST_DONE(); } -static void run_guest(struct kvm_vm *vm) -{ - int rc; - - rc = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); -} - /* * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2, * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)". @@ -56,9 +47,9 @@ static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size) GET_RM(insn_bytes[1]) != 0x5; } -static void process_exit_on_emulation_error(struct kvm_vm *vm) +static void process_exit_on_emulation_error(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct kvm_regs regs; uint8_t *insn_bytes; uint8_t insn_size; @@ -92,50 +83,48 @@ static void process_exit_on_emulation_error(struct kvm_vm *vm) * contained an flds instruction that is 2-bytes in * length (ie: no prefix, no SIB, no displacement). */ - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); regs.rip += 2; - vcpu_regs_set(vm, VCPU_ID, ®s); + vcpu_regs_set(vcpu, ®s); } } } -static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc) +static void do_guest_assert(struct ucall *uc) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__, - uc->args[1]); + REPORT_GUEST_ASSERT(*uc); } -static void check_for_guest_assert(struct kvm_vm *vm) +static void check_for_guest_assert(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; - if (run->exit_reason == KVM_EXIT_IO && - get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { - do_guest_assert(vm, &uc); + if (vcpu->run->exit_reason == KVM_EXIT_IO && + get_ucall(vcpu, &uc) == UCALL_ABORT) { + do_guest_assert(&uc); } } -static void process_ucall_done(struct kvm_vm *vm) +static void process_ucall_done(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vm *vm) +static uint64_t process_ucall(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -143,14 +132,14 @@ static uint64_t process_ucall(struct kvm_vm *vm) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: break; case UCALL_ABORT: - do_guest_assert(vm, &uc); + do_guest_assert(&uc); break; case UCALL_DONE: - process_ucall_done(vm); + process_ucall_done(vcpu); break; default: TEST_ASSERT(false, "Unexpected ucall"); @@ -161,12 +150,7 @@ static uint64_t process_ucall(struct kvm_vm *vm) int main(int argc, char *argv[]) { - struct kvm_enable_cap emul_failure_cap = { - .cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE, - .args[0] = 1, - }; - struct kvm_cpuid_entry2 *entry; - struct kvm_cpuid2 *cpuid; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t gpa, pte; uint64_t *hva; @@ -175,24 +159,15 @@ int main(int argc, char *argv[]) /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - vm = vm_create_default(VCPU_ID, 0, guest_code); - - if (!kvm_check_cap(KVM_CAP_SMALLER_MAXPHYADDR)) { - printf("module parameter 'allow_smaller_maxphyaddr' is not set. Skipping test.\n"); - return 0; - } - - cpuid = kvm_get_supported_cpuid(); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); - entry = kvm_get_supported_cpuid_index(0x80000008, 0); - entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR; - set_cpuid(cpuid, entry); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, cpuid); + vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); - vm_enable_cap(vm, &emul_failure_cap); + vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, MEM_REGION_GPA, MEM_REGION_SLOT, @@ -203,14 +178,14 @@ int main(int argc, char *argv[]) virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1); hva = addr_gpa2hva(vm, MEM_REGION_GPA); memset(hva, 0, PAGE_SIZE); - pte = vm_get_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA); - vm_set_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA, pte | (1ull << 36)); + pte = vm_get_page_table_entry(vm, vcpu, MEM_REGION_GVA); + vm_set_page_table_entry(vm, vcpu, MEM_REGION_GVA, pte | (1ull << 36)); - run_guest(vm); - process_exit_on_emulation_error(vm); - run_guest(vm); + vcpu_run(vcpu); + process_exit_on_emulation_error(vcpu); + vcpu_run(vcpu); - TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE"); + TEST_ASSERT(process_ucall(vcpu) == UCALL_DONE, "Expected UCALL_DONE"); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index d12e043aa2ee..99bc202243d2 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -18,9 +18,6 @@ #include "vmx.h" -#define VCPU_ID 5 -#define NMI_VECTOR 2 - static int ud_count; static void guest_ud_handler(struct ex_regs *regs) @@ -160,88 +157,86 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } -void inject_nmi(struct kvm_vm *vm) +void inject_nmi(struct kvm_vcpu *vcpu) { struct kvm_vcpu_events events; - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); events.nmi.pending = 1; events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING; - vcpu_events_set(vm, VCPU_ID, &events); + vcpu_events_set(vcpu, &events); } -static void save_restore_vm(struct kvm_vm *vm) +static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm, + struct kvm_vcpu *vcpu) { struct kvm_regs regs1, regs2; struct kvm_x86_state *state; - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); - vcpu_load_state(vm, VCPU_ID, state); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_load_state(vcpu, state); kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®s2); TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); + return vcpu; } int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva = 0; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; int stage; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_NESTED_STATE) || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - print_skip("Enlightened VMCS is unsupported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); pr_info("Running L1 which uses EVMCS to run L2\n"); for (stage = 1;; stage++) { - run = vcpu_state(vm, VCPU_ID); - _vcpu_run(vm, VCPU_ID); + run = vcpu->run; + + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -256,12 +251,12 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - save_restore_vm(vm); + vcpu = save_restore_vm(vm, vcpu); /* Force immediate L2->L1 exit before resuming */ if (stage == 8) { pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); - inject_nmi(vm); + inject_nmi(vcpu); } /* @@ -271,7 +266,7 @@ int main(int argc, char *argv[]) */ if (stage == 9) { pr_info("Trying extra KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE cycle\n"); - save_restore_vm(vm); + vcpu = save_restore_vm(vm, vcpu); } } diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 1f5c32146f3d..b1905d280ef5 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -14,8 +14,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - static bool ud_expected; static void guest_ud_handler(struct ex_regs *regs) @@ -94,29 +92,27 @@ static void guest_main(void) GUEST_DONE(); } -static void setup_ud_vector(struct kvm_vm *vm) +static void setup_ud_vector(struct kvm_vcpu *vcpu) { - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + vm_init_descriptor_tables(vcpu->vm); + vcpu_init_descriptor_tables(vcpu); + vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler); } -static void enter_guest(struct kvm_vm *vm) +static void enter_guest(struct kvm_vcpu *vcpu) { - struct kvm_run *run; + struct kvm_run *run = vcpu->run; struct ucall uc; - run = vcpu_state(vm, VCPU_ID); - - vcpu_run(vm, VCPU_ID); - switch (get_ucall(vm, VCPU_ID, &uc)) { + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: pr_info("%s: %016lx\n", (const char *)uc.args[2], uc.args[3]); break; case UCALL_DONE: return; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); default: TEST_FAIL("Unhandled ucall: %ld\nexit_reason: %u (%s)", uc.cmd, run->exit_reason, exit_reason_str(run->exit_reason)); @@ -125,45 +121,42 @@ static void enter_guest(struct kvm_vm *vm) static void test_fix_hypercall(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm = vm_create_default(VCPU_ID, 0, guest_main); - setup_ud_vector(vm); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + setup_ud_vector(vcpu); ud_expected = false; sync_global_to_guest(vm, ud_expected); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); - enter_guest(vm); + enter_guest(vcpu); } static void test_fix_hypercall_disabled(void) { - struct kvm_enable_cap cap = {0}; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm = vm_create_default(VCPU_ID, 0, guest_main); - setup_ud_vector(vm); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + setup_ud_vector(vcpu); - cap.cap = KVM_CAP_DISABLE_QUIRKS2; - cap.args[0] = KVM_X86_QUIRK_FIX_HYPERCALL_INSN; - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, + KVM_X86_QUIRK_FIX_HYPERCALL_INSN); ud_expected = true; sync_global_to_guest(vm, ud_expected); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); - enter_guest(vm); + enter_guest(vcpu); } int main(void) { - if (!(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) { - print_skip("KVM_X86_QUIRK_HYPERCALL_INSN not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN); test_fix_hypercall(); test_fix_hypercall_disabled(); diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index 8aed0db1331d..d09b3cbcadc6 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -15,116 +15,21 @@ #include "kvm_util.h" #include "processor.h" -static int kvm_num_index_msrs(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - TEST_ASSERT(r == -1 && errno == E2BIG, - "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i", - r); - - r = list->nmsrs; - free(list); - return r; -} - -static void test_get_msr_index(void) -{ - int old_res, res, kvm_fd, r; - struct kvm_msr_list *list; - - kvm_fd = open_kvm_dev_path_or_exit(); - - old_res = kvm_num_index_msrs(kvm_fd, 0); - TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); - - if (old_res != 1) { - res = kvm_num_index_msrs(kvm_fd, 1); - TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1"); - TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical"); - } - - list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0])); - list->nmsrs = old_res; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - - TEST_ASSERT(r == 0, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i", - r); - TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical"); - free(list); - - close(kvm_fd); -} - -static int kvm_num_feature_msrs(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list); - TEST_ASSERT(r == -1 && errno == E2BIG, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i", - r); - - r = list->nmsrs; - free(list); - return r; -} - -struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list); - - TEST_ASSERT(r == 0, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i", - r); - - return list; -} - -static void test_get_msr_feature(void) +int main(int argc, char *argv[]) { - int res, old_res, i, kvm_fd; - struct kvm_msr_list *feature_list; + const struct kvm_msr_list *feature_list; + int i; - kvm_fd = open_kvm_dev_path_or_exit(); + /* + * Skip the entire test if MSR_FEATURES isn't supported, other tests + * will cover the "regular" list of MSRs, the coverage here is purely + * opportunistic and not interesting on its own. + */ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GET_MSR_FEATURES)); - old_res = kvm_num_feature_msrs(kvm_fd, 0); - TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); - - if (old_res != 1) { - res = kvm_num_feature_msrs(kvm_fd, 1); - TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1"); - TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical"); - } - - feature_list = kvm_get_msr_feature_list(kvm_fd, old_res); - TEST_ASSERT(old_res == feature_list->nmsrs, - "Unmatching number of msr indexes"); + (void)kvm_get_msr_index_list(); + feature_list = kvm_get_feature_msr_index_list(); for (i = 0; i < feature_list->nmsrs; i++) kvm_get_feature_msr(feature_list->indices[i]); - - free(feature_list); - close(kvm_fd); -} - -int main(int argc, char *argv[]) -{ - if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES)) - test_get_msr_feature(); - - test_get_msr_index(); } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index 3330fb183c68..d576bc8ce823 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -173,23 +173,21 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ GUEST_DONE(); } -#define VCPU_ID 0 - -static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm) +static void host_check_tsc_msr_rdtsc(struct kvm_vcpu *vcpu) { u64 tsc_freq, r1, r2, t1, t2; s64 delta_ns; - tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY); + tsc_freq = vcpu_get_msr(vcpu, HV_X64_MSR_TSC_FREQUENCY); TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero"); /* For increased accuracy, take mean rdtsc() before and afrer ioctl */ r1 = rdtsc(); - t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT); + t1 = vcpu_get_msr(vcpu, HV_X64_MSR_TIME_REF_COUNT); r1 = (r1 + rdtsc()) / 2; nop_loop(); r2 = rdtsc(); - t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT); + t2 = vcpu_get_msr(vcpu, HV_X64_MSR_TIME_REF_COUNT); r2 = (r2 + rdtsc()) / 2; TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2); @@ -207,36 +205,36 @@ static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm) int main(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; vm_vaddr_t tsc_page_gva; int stage; - vm = vm_create_default(VCPU_ID, 0, guest_main); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + run = vcpu->run; - vcpu_set_hv_cpuid(vm, VCPU_ID); + vcpu_set_hv_cpuid(vcpu); tsc_page_gva = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned\n"); - vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); + vcpu_args_set(vcpu, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); - host_check_tsc_msr_rdtsc(vm); + host_check_tsc_msr_rdtsc(vcpu); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 8c245ab2d98a..e804eb08dff9 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -20,8 +20,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 0 - static void guest_code(void) { } @@ -45,7 +43,7 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, +static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, bool evmcs_expected) { int i; @@ -58,7 +56,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, nent_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { - struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; + const struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; TEST_ASSERT((entry->function >= 0x40000000) && (entry->function <= 0x40000082), @@ -115,64 +113,62 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, } } -void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) +void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; - if (!system) - ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + if (vcpu) + ret = __vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); else - ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + ret = __kvm_ioctl(vm->kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); TEST_ASSERT(ret == -1 && errno == E2BIG, "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" - " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno); + " it should have: %d %d", !vcpu ? "KVM" : "vCPU", ret, errno); } int main(int argc, char *argv[]) { struct kvm_vm *vm; - struct kvm_cpuid2 *hv_cpuid_entries; + const struct kvm_cpuid2 *hv_cpuid_entries; + struct kvm_vcpu *vcpu; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) { - print_skip("KVM_CAP_HYPERV_CPUID not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Test vCPU ioctl version */ - test_hv_cpuid_e2big(vm, false); + test_hv_cpuid_e2big(vm, vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vm, VCPU_ID); + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); test_hv_cpuid(hv_cpuid_entries, false); - free(hv_cpuid_entries); + free((void *)hv_cpuid_entries); - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { + if (!kvm_cpu_has(X86_FEATURE_VMX) || + !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { print_skip("Enlightened VMCS is unsupported"); goto do_sys; } - vcpu_enable_evmcs(vm, VCPU_ID); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vm, VCPU_ID); + vcpu_enable_evmcs(vcpu); + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); test_hv_cpuid(hv_cpuid_entries, true); - free(hv_cpuid_entries); + free((void *)hv_cpuid_entries); do_sys: /* Test system ioctl version */ - if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) { + if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID)) { print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported"); goto out; } - test_hv_cpuid_e2big(vm, true); + test_hv_cpuid_e2big(vm, NULL); hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported()); + test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 672915ce73d8..79ab0152d281 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,78 +13,22 @@ #include "processor.h" #include "hyperv.h" -#define VCPU_ID 0 #define LINUX_OS_ID ((u64)0x8100 << 48) -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 int nr_ud; - -static inline u64 hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address) -{ - u64 hv_status; - - asm volatile("mov %3, %%r8\n" - "vmcall" - : "=a" (hv_status), - "+c" (control), "+d" (input_address) - : "r" (output_address) - : "cc", "memory", "r8", "r9", "r10", "r11"); - - return hv_status; -} - -static void guest_gp_handler(struct ex_regs *regs) +static inline uint8_t hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address, uint64_t *hv_status) { - 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; -} - -static void guest_ud_handler(struct ex_regs *regs) -{ - nr_ud++; - regs->rip += 3; + uint8_t vector; + + /* Note both the hypercall and the "asm safe" clobber r9-r11. */ + asm volatile("mov %[output_address], %%r8\n\t" + KVM_ASM_SAFE("vmcall") + : "=a" (*hv_status), + "+c" (control), "+d" (input_address), + KVM_ASM_SAFE_OUTPUTS(vector) + : [output_address] "r"(output_address) + : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS); + return vector; } struct msr_data { @@ -102,111 +46,105 @@ struct hcall_data { static void guest_msr(struct msr_data *msr) { - int i = 0; - - while (msr->idx) { - WRITE_ONCE(nr_gp, 0); - if (!msr->write) - do_rdmsr(msr->idx); - else - do_wrmsr(msr->idx, msr->write_val); + uint64_t ignored; + uint8_t vector; - if (msr->available) - GUEST_ASSERT(READ_ONCE(nr_gp) == 0); - else - GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + GUEST_ASSERT(msr->idx); - GUEST_SYNC(i++); - } + if (!msr->write) + vector = rdmsr_safe(msr->idx, &ignored); + else + vector = wrmsr_safe(msr->idx, msr->write_val); + if (msr->available) + GUEST_ASSERT_2(!vector, msr->idx, vector); + else + GUEST_ASSERT_2(vector == GP_VECTOR, msr->idx, vector); GUEST_DONE(); } static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) { - int i = 0; u64 res, input, output; + uint8_t vector; + + GUEST_ASSERT(hcall->control); wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); - while (hcall->control) { - nr_ud = 0; - if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { - input = pgs_gpa; - output = pgs_gpa + 4096; - } else { - input = output = 0; - } - - res = hypercall(hcall->control, input, output); - if (hcall->ud_expected) - GUEST_ASSERT(nr_ud == 1); - else - GUEST_ASSERT(res == hcall->expect); - - GUEST_SYNC(i++); + if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { + input = pgs_gpa; + output = pgs_gpa + 4096; + } else { + input = output = 0; } + vector = hypercall(hcall->control, input, output, &res); + if (hcall->ud_expected) + GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector); + else + GUEST_ASSERT_2(!vector, hcall->control, vector); + + GUEST_ASSERT_2(!hcall->ud_expected || res == hcall->expect, + hcall->expect, res); GUEST_DONE(); } -static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 *feat, - struct kvm_cpuid_entry2 *recomm, - struct kvm_cpuid_entry2 *dbg) +static void vcpu_reset_hv_cpuid(struct kvm_vcpu *vcpu) { - TEST_ASSERT(set_cpuid(cpuid, feat), - "failed to set KVM_CPUID_FEATURES leaf"); - TEST_ASSERT(set_cpuid(cpuid, recomm), - "failed to set HYPERV_CPUID_ENLIGHTMENT_INFO leaf"); - TEST_ASSERT(set_cpuid(cpuid, dbg), - "failed to set HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES leaf"); - vcpu_set_cpuid(vm, VCPU_ID, cpuid); + /* + * Enable all supported Hyper-V features, then clear the leafs holding + * the features that will be tested one by one. + */ + vcpu_set_hv_cpuid(vcpu); + + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); } static void guest_test_msrs_access(void) { + struct kvm_cpuid2 *prev_cpuid = NULL; + struct kvm_cpuid_entry2 *feat, *dbg; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int stage = 0, r; - struct kvm_cpuid_entry2 feat = { - .function = HYPERV_CPUID_FEATURES - }; - struct kvm_cpuid_entry2 recomm = { - .function = HYPERV_CPUID_ENLIGHTMENT_INFO - }; - struct kvm_cpuid_entry2 dbg = { - .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES - }; - struct kvm_cpuid2 *best; + int stage = 0; vm_vaddr_t msr_gva; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; struct msr_data *msr; while (true) { - vm = vm_create_default(VCPU_ID, 0, guest_msr); + vm = vm_create_with_one_vcpu(&vcpu, guest_msr); msr_gva = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); msr = addr_gva2hva(vm, msr_gva); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); + vcpu_args_set(vcpu, 1, msr_gva); + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENFORCE_CPUID, 1); - vcpu_set_hv_cpuid(vm, VCPU_ID); + if (!prev_cpuid) { + vcpu_reset_hv_cpuid(vcpu); - best = kvm_get_supported_hv_cpuid(); + prev_cpuid = allocate_kvm_cpuid2(vcpu->cpuid->nent); + } else { + vcpu_init_cpuid(vcpu, prev_cpuid); + } + + feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + vcpu_init_descriptor_tables(vcpu); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; + + /* TODO: Make this entire test easier to maintain. */ + if (stage >= 21) + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_SYNIC2, 0); switch (stage) { case 0: @@ -223,7 +161,7 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 2: - feat.eax |= HV_MSR_HYPERCALL_AVAILABLE; + feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; /* * HV_X64_MSR_GUEST_OS_ID has to be written first to make * HV_X64_MSR_HYPERCALL available. @@ -250,12 +188,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 6: - feat.eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + feat->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + msr->idx = HV_X64_MSR_VP_RUNTIME; msr->write = 0; msr->available = 1; break; case 7: /* Read only */ + msr->idx = HV_X64_MSR_VP_RUNTIME; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -267,12 +207,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 9: - feat.eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + feat->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + msr->idx = HV_X64_MSR_TIME_REF_COUNT; msr->write = 0; msr->available = 1; break; case 10: /* Read only */ + msr->idx = HV_X64_MSR_TIME_REF_COUNT; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -284,12 +226,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 12: - feat.eax |= HV_MSR_VP_INDEX_AVAILABLE; + feat->eax |= HV_MSR_VP_INDEX_AVAILABLE; + msr->idx = HV_X64_MSR_VP_INDEX; msr->write = 0; msr->available = 1; break; case 13: /* Read only */ + msr->idx = HV_X64_MSR_VP_INDEX; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -301,11 +245,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 15: - feat.eax |= HV_MSR_RESET_AVAILABLE; + feat->eax |= HV_MSR_RESET_AVAILABLE; + msr->idx = HV_X64_MSR_RESET; msr->write = 0; msr->available = 1; break; case 16: + msr->idx = HV_X64_MSR_RESET; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -317,11 +263,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 18: - feat.eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + feat->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + msr->idx = HV_X64_MSR_REFERENCE_TSC; msr->write = 0; msr->available = 1; break; case 19: + msr->idx = HV_X64_MSR_REFERENCE_TSC; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -337,16 +285,18 @@ static void guest_test_msrs_access(void) * Remains unavailable even with KVM_CAP_HYPERV_SYNIC2 * capability enabled and guest visible CPUID bit unset. */ - cap.cap = KVM_CAP_HYPERV_SYNIC2; - cap.args[0] = 0; - vcpu_enable_cap(vm, VCPU_ID, &cap); + msr->idx = HV_X64_MSR_EOM; + msr->write = 0; + msr->available = 0; break; case 22: - feat.eax |= HV_MSR_SYNIC_AVAILABLE; + feat->eax |= HV_MSR_SYNIC_AVAILABLE; + msr->idx = HV_X64_MSR_EOM; msr->write = 0; msr->available = 1; break; case 23: + msr->idx = HV_X64_MSR_EOM; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -358,23 +308,29 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 25: - feat.eax |= HV_MSR_SYNTIMER_AVAILABLE; + feat->eax |= HV_MSR_SYNTIMER_AVAILABLE; + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 0; msr->available = 1; break; case 26: + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 1; msr->write_val = 0; msr->available = 1; break; case 27: /* Direct mode test */ + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 1; msr->write_val = 1 << 12; msr->available = 0; break; case 28: - feat.edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + feat->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + msr->idx = HV_X64_MSR_STIMER0_CONFIG; + msr->write = 1; + msr->write_val = 1 << 12; msr->available = 1; break; @@ -384,7 +340,8 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 30: - feat.eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + feat->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + msr->idx = HV_X64_MSR_EOI; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -396,12 +353,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 32: - feat.eax |= HV_ACCESS_FREQUENCY_MSRS; + feat->eax |= HV_ACCESS_FREQUENCY_MSRS; + msr->idx = HV_X64_MSR_TSC_FREQUENCY; msr->write = 0; msr->available = 1; break; case 33: /* Read only */ + msr->idx = HV_X64_MSR_TSC_FREQUENCY; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -413,11 +372,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 35: - feat.eax |= HV_ACCESS_REENLIGHTENMENT; + feat->eax |= HV_ACCESS_REENLIGHTENMENT; + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; msr->write = 0; msr->available = 1; break; case 36: + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -436,11 +397,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 39: - feat.edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + feat->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + msr->idx = HV_X64_MSR_CRASH_P0; msr->write = 0; msr->available = 1; break; case 40: + msr->idx = HV_X64_MSR_CRASH_P0; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -452,48 +415,44 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 42: - feat.edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; - dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + feat->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + msr->idx = HV_X64_MSR_SYNDBG_STATUS; msr->write = 0; msr->available = 1; break; case 43: + msr->idx = HV_X64_MSR_SYNDBG_STATUS; msr->write = 1; msr->write_val = 0; msr->available = 1; break; case 44: - /* END */ - msr->idx = 0; - break; + kvm_vm_free(vm); + return; } - hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + vcpu_set_cpuid(vcpu); + + memcpy(prev_cpuid, vcpu->cpuid, kvm_cpuid2_size(vcpu->cpuid->nent)); - if (msr->idx) - pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, - msr->idx, msr->write ? "write" : "read"); - else - pr_debug("Stage %d: finish\n", stage); + pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, + msr->idx, msr->write ? "write" : "read"); - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == 0, - "Unexpected stage: %ld (0 expected)\n", - uc.args[1]); - break; + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT_2(uc, "MSR = %lx, vector = %lx"); return; case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); return; } @@ -504,54 +463,50 @@ static void guest_test_msrs_access(void) static void guest_test_hcalls_access(void) { + struct kvm_cpuid_entry2 *feat, *recomm, *dbg; + struct kvm_cpuid2 *prev_cpuid = NULL; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int stage = 0, r; - struct kvm_cpuid_entry2 feat = { - .function = HYPERV_CPUID_FEATURES, - .eax = HV_MSR_HYPERCALL_AVAILABLE - }; - struct kvm_cpuid_entry2 recomm = { - .function = HYPERV_CPUID_ENLIGHTMENT_INFO - }; - struct kvm_cpuid_entry2 dbg = { - .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES - }; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; + int stage = 0; vm_vaddr_t hcall_page, hcall_params; struct hcall_data *hcall; - struct kvm_cpuid2 *best; while (true) { - vm = vm_create_default(VCPU_ID, 0, guest_hcall); + vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + vcpu_init_descriptor_tables(vcpu); /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); - hcall = addr_gva2hva(vm, hcall_page); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); hcall_params = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + hcall = addr_gva2hva(vm, hcall_params); + + vcpu_args_set(vcpu, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENFORCE_CPUID, 1); - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); + if (!prev_cpuid) { + vcpu_reset_hv_cpuid(vcpu); - vcpu_set_hv_cpuid(vm, VCPU_ID); + prev_cpuid = allocate_kvm_cpuid2(vcpu->cpuid->nent); + } else { + vcpu_init_cpuid(vcpu, prev_cpuid); + } - best = kvm_get_supported_hv_cpuid(); + feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + recomm = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); + dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; switch (stage) { case 0: + feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; hcall->control = 0xdeadbeef; hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -561,7 +516,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 2: - feat.ebx |= HV_POST_MESSAGES; + feat->ebx |= HV_POST_MESSAGES; + hcall->control = HVCALL_POST_MESSAGE; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -570,7 +526,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 4: - feat.ebx |= HV_SIGNAL_EVENTS; + feat->ebx |= HV_SIGNAL_EVENTS; + hcall->control = HVCALL_SIGNAL_EVENT; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -579,11 +536,13 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; case 6: - dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 7: - feat.ebx |= HV_DEBUGGING; + feat->ebx |= HV_DEBUGGING; + hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_OPERATION_DENIED; break; @@ -592,7 +551,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 9: - recomm.eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + recomm->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; hcall->expect = HV_STATUS_SUCCESS; break; case 10: @@ -600,7 +560,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 11: - recomm.eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + recomm->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; hcall->expect = HV_STATUS_SUCCESS; break; @@ -609,7 +570,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 13: - recomm.eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + recomm->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + hcall->control = HVCALL_SEND_IPI; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; case 14: @@ -623,7 +585,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 16: - recomm.ebx = 0xfff; + recomm->ebx = 0xfff; + hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; hcall->expect = HV_STATUS_SUCCESS; break; case 17: @@ -632,42 +595,35 @@ static void guest_test_hcalls_access(void) hcall->ud_expected = true; break; case 18: - feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + feat->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; hcall->ud_expected = false; hcall->expect = HV_STATUS_SUCCESS; break; - case 19: - /* END */ - hcall->control = 0; - break; + kvm_vm_free(vm); + return; } - hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + vcpu_set_cpuid(vcpu); + + memcpy(prev_cpuid, vcpu->cpuid, kvm_cpuid2_size(vcpu->cpuid->nent)); - if (hcall->control) - pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, - hcall->control); - else - pr_debug("Stage %d: finish\n", stage); + pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, hcall->control); - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == 0, - "Unexpected stage: %ld (0 expected)\n", - uc.args[1]); - break; + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT_2(uc, "arg1 = %lx, arg2 = %lx"); return; case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); return; } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index 21f5ca9197da..a380ad7bb9b3 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -21,7 +21,6 @@ #include "svm_util.h" #include "hyperv.h" -#define VCPU_ID 1 #define L2_GUEST_STACK_SIZE 256 struct hv_enlightenments { @@ -42,11 +41,6 @@ struct hv_enlightenments { */ #define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31) -static inline void vmmcall(void) -{ - __asm__ __volatile__("vmmcall"); -} - void l2_guest_code(void) { GUEST_SYNC(3); @@ -127,33 +121,31 @@ int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; int stage; - if (!nested_svm_supported()) { - print_skip("Nested SVM not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_hv_cpuid(vm, VCPU_ID); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_set_hv_cpuid(vcpu); + run = vcpu->run; vcpu_alloc_svm(vm, &nested_gva); - vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c index 97731454f3f3..813ce282cf56 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c @@ -16,8 +16,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - struct test_case { uint64_t kvmclock_base; int64_t realtime_offset; @@ -73,8 +71,7 @@ static void handle_sync(struct ucall *uc, struct kvm_clock_data *start, static void handle_abort(struct ucall *uc) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], - __FILE__, uc->args[1]); + REPORT_GUEST_ASSERT(*uc); } static void setup_clock(struct kvm_vm *vm, struct test_case *test_case) @@ -105,29 +102,27 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case) vm_ioctl(vm, KVM_SET_CLOCK, &data); } -static void enter_guest(struct kvm_vm *vm) +static void enter_guest(struct kvm_vcpu *vcpu) { struct kvm_clock_data start, end; - struct kvm_run *run; + struct kvm_run *run = vcpu->run; + struct kvm_vm *vm = vcpu->vm; struct ucall uc; - int i, r; - - run = vcpu_state(vm, VCPU_ID); + int i; for (i = 0; i < ARRAY_SIZE(test_cases); i++) { setup_clock(vm, &test_cases[i]); vm_ioctl(vm, KVM_GET_CLOCK, &start); - r = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); vm_ioctl(vm, KVM_GET_CLOCK, &end); - 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)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: handle_sync(&uc, &start, &end); break; @@ -178,26 +173,23 @@ out: int main(void) { + struct kvm_vcpu *vcpu; vm_vaddr_t pvti_gva; vm_paddr_t pvti_gpa; struct kvm_vm *vm; int flags; flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK); - if (!(flags & KVM_CLOCK_REALTIME)) { - print_skip("KVM_CLOCK_REALTIME not supported; flags: %x", - flags); - exit(KSFT_SKIP); - } + TEST_REQUIRE(flags & KVM_CLOCK_REALTIME); check_clocksource(); - vm = vm_create_default(VCPU_ID, 0, guest_main); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); pvti_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000); pvti_gpa = addr_gva2gpa(vm, pvti_gva); - vcpu_args_set(vm, VCPU_ID, 2, pvti_gpa, pvti_gva); + vcpu_args_set(vcpu, 2, pvti_gpa, pvti_gva); - enter_guest(vm); + enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 04ed975662c9..619655c1a1f3 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -12,55 +12,6 @@ #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; @@ -89,14 +40,16 @@ static struct msr_data msrs_to_test[] = { static void test_msr(struct msr_data *msr) { + uint64_t ignored; + uint8_t vector; + 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; + vector = rdmsr_safe(msr->idx, &ignored); + GUEST_ASSERT_1(vector == GP_VECTOR, vector); + + vector = wrmsr_safe(msr->idx, 0); + GUEST_ASSERT_1(vector == GP_VECTOR, vector); } struct hcall_data { @@ -142,15 +95,6 @@ static void guest_main(void) 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]; @@ -165,30 +109,18 @@ static void pr_hcall(struct ucall *uc) pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); } -static void handle_abort(struct ucall *uc) +static void enter_guest(struct kvm_vcpu *vcpu) { - 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 kvm_run *run = vcpu->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); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_PR_MSR: pr_msr(&uc); break; @@ -196,7 +128,7 @@ static void enter_guest(struct kvm_vm *vm) pr_hcall(&uc); break; case UCALL_ABORT: - handle_abort(&uc); + REPORT_GUEST_ASSERT_1(uc, "vector = %lu"); return; case UCALL_DONE: return; @@ -206,29 +138,20 @@ static void enter_guest(struct kvm_vm *vm) int main(void) { - struct kvm_enable_cap cap = {0}; - struct kvm_cpuid2 *best; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { - print_skip("KVM_CAP_ENFORCE_PV_FEATURE_CPUID not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)); - vm = vm_create_default(VCPU_ID, 0, guest_main); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); - cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; - cap.args[0] = 1; - vcpu_enable_cap(vm, VCPU_ID, &cap); + vcpu_enable_cap(vcpu, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 1); - best = kvm_get_supported_cpuid(); - clear_kvm_cpuid_features(best); - vcpu_set_cpuid(vm, VCPU_ID, best); + vcpu_clear_cpuid_entry(vcpu, KVM_CPUID_FEATURES); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + vcpu_init_descriptor_tables(vcpu); - enter_guest(vm); + enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c new file mode 100644 index 000000000000..3cc4b86832fe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * maximum APIC ID capability tests + * + * Copyright (C) 2022, Intel, Inc. + * + * Tests for getting/setting maximum APIC ID capability + */ + +#include "kvm_util.h" + +#define MAX_VCPU_ID 2 + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create_barebones(); + + /* Get KVM_CAP_MAX_VCPU_ID cap supported in KVM */ + ret = vm_check_cap(vm, KVM_CAP_MAX_VCPU_ID); + + /* Try to set KVM_CAP_MAX_VCPU_ID beyond KVM cap */ + ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, ret + 1); + TEST_ASSERT(ret < 0, + "Setting KVM_CAP_MAX_VCPU_ID beyond KVM cap should fail"); + + /* Set KVM_CAP_MAX_VCPU_ID */ + vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID); + + + /* Try to set KVM_CAP_MAX_VCPU_ID again */ + ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID + 1); + TEST_ASSERT(ret < 0, + "Setting KVM_CAP_MAX_VCPU_ID multiple times should fail"); + + /* Create vCPU with id beyond KVM_CAP_MAX_VCPU_ID cap*/ + ret = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)MAX_VCPU_ID); + TEST_ASSERT(ret < 0, "Creating vCPU with ID > MAX_VCPU_ID should fail"); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index 9f55ccd169a1..fb02581953a3 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -59,10 +59,10 @@ void test(void) kvm = open("/dev/kvm", O_RDWR); TEST_ASSERT(kvm != -1, "failed to open /dev/kvm"); - kvmvm = ioctl(kvm, KVM_CREATE_VM, 0); - TEST_ASSERT(kvmvm != -1, "KVM_CREATE_VM failed"); + kvmvm = __kvm_ioctl(kvm, KVM_CREATE_VM, NULL); + TEST_ASSERT(kvmvm > 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, kvmvm)); kvmcpu = ioctl(kvmvm, KVM_CREATE_VCPU, 0); - TEST_ASSERT(kvmcpu != -1, "KVM_CREATE_VCPU failed"); + TEST_ASSERT(kvmcpu != -1, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, kvmcpu)); run = (struct kvm_run *)mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, kvmcpu, 0); tc.kvmcpu = kvmcpu; @@ -93,15 +93,9 @@ int main(void) { int warnings_before, warnings_after; - if (!is_intel_cpu()) { - print_skip("Must be run on an Intel CPU"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(is_intel_cpu()); - if (vm_is_unrestricted_guest(NULL)) { - print_skip("Unrestricted guest must be disabled"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); warnings_before = get_warnings_count(); diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c deleted file mode 100644 index bdecd532f935..000000000000 --- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c +++ /dev/null @@ -1,147 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include "kvm_util.h" -#include "processor.h" - -#define VCPU_ID 1 - -#define MMIO_GPA 0x100000000ull - -static void guest_code(void) -{ - (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); - (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); - - GUEST_ASSERT(0); -} - -static void guest_pf_handler(struct ex_regs *regs) -{ - /* PFEC == RSVD | PRESENT (read, kernel). */ - GUEST_ASSERT(regs->error_code == 0x9); - GUEST_DONE(); -} - -static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val) -{ - u32 good_cpuid_val = *cpuid_reg; - struct kvm_run *run; - struct kvm_vm *vm; - uint64_t cmd; - int r; - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); - - /* Map 1gb page without a backing memlot. */ - __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G); - - r = _vcpu_run(vm, VCPU_ID); - - /* Guest access to the 1gb page should trigger MMIO. */ - TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); - TEST_ASSERT(run->exit_reason == KVM_EXIT_MMIO, - "Unexpected exit reason: %u (%s), expected MMIO exit (1gb page w/o memslot)\n", - run->exit_reason, exit_reason_str(run->exit_reason)); - - TEST_ASSERT(run->mmio.len == 8, "Unexpected exit mmio size = %u", run->mmio.len); - - TEST_ASSERT(run->mmio.phys_addr == MMIO_GPA, - "Unexpected exit mmio address = 0x%llx", run->mmio.phys_addr); - - /* - * Effect the CPUID change for the guest and re-enter the guest. Its - * access should now #PF due to the PAGE_SIZE bit being reserved or - * the resulting GPA being invalid. Note, kvm_get_supported_cpuid() - * returns the struct that contains the entry being modified. Eww. - */ - *cpuid_reg = evil_cpuid_val; - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - - /* - * Add a dummy memslot to coerce KVM into bumping the MMIO generation. - * KVM does not "officially" support mucking with CPUID after KVM_RUN, - * and will incorrectly reuse MMIO SPTEs. Don't delete the memslot! - * KVM x86 zaps all shadow pages on memslot deletion. - */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - MMIO_GPA << 1, 10, 1, 0); - - /* Set up a #PF handler to eat the RSVD #PF and signal all done! */ - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler); - - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); - - cmd = get_ucall(vm, VCPU_ID, NULL); - TEST_ASSERT(cmd == UCALL_DONE, - "Unexpected guest exit, exit_reason=%s, ucall.cmd = %lu\n", - exit_reason_str(run->exit_reason), cmd); - - /* - * Restore the happy CPUID value for the next test. Yes, changes are - * indeed persistent across VM destruction. - */ - *cpuid_reg = good_cpuid_val; - - kvm_vm_free(vm); -} - -int main(int argc, char *argv[]) -{ - struct kvm_cpuid_entry2 *entry; - int opt; - - /* - * All tests are opt-in because TDP doesn't play nice with reserved #PF - * in the GVA->GPA translation. The hardware page walker doesn't let - * software change GBPAGES or MAXPHYADDR, and KVM doesn't manually walk - * the GVA on fault for performance reasons. - */ - bool do_gbpages = false; - bool do_maxphyaddr = false; - - setbuf(stdout, NULL); - - while ((opt = getopt(argc, argv, "gm")) != -1) { - switch (opt) { - case 'g': - do_gbpages = true; - break; - case 'm': - do_maxphyaddr = true; - break; - case 'h': - default: - printf("usage: %s [-g (GBPAGES)] [-m (MAXPHYADDR)]\n", argv[0]); - break; - } - } - - if (!do_gbpages && !do_maxphyaddr) { - print_skip("No sub-tests selected"); - return 0; - } - - entry = kvm_get_supported_cpuid_entry(0x80000001); - if (!(entry->edx & CPUID_GBPAGES)) { - print_skip("1gb hugepages not supported"); - return 0; - } - - if (do_gbpages) { - pr_info("Test MMIO after toggling CPUID.GBPAGES\n\n"); - mmu_role_test(&entry->edx, entry->edx & ~CPUID_GBPAGES); - } - - if (do_maxphyaddr) { - pr_info("Test MMIO after changing CPUID.MAXPHYADDR\n\n"); - entry = kvm_get_supported_cpuid_entry(0x80000008); - mmu_role_test(&entry->eax, (entry->eax & ~0xff) | 0x20); - } - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c new file mode 100644 index 000000000000..016070cad36e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "kvm_util.h" +#include "processor.h" + +#define CPUID_MWAIT (1u << 3) + +enum monitor_mwait_testcases { + MWAIT_QUIRK_DISABLED = BIT(0), + MISC_ENABLES_QUIRK_DISABLED = BIT(1), + MWAIT_DISABLED = BIT(2), +}; + +static void guest_monitor_wait(int testcase) +{ + /* + * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD, + * in all other scenarios KVM should emulate them as nops. + */ + bool fault_wanted = (testcase & MWAIT_QUIRK_DISABLED) && + (testcase & MWAIT_DISABLED); + u8 vector; + + GUEST_SYNC(testcase); + + /* + * Arbitrarily MONITOR this function, SVM performs fault checks before + * intercept checks, so the inputs for MONITOR and MWAIT must be valid. + */ + vector = kvm_asm_safe("monitor", "a"(guest_monitor_wait), "c"(0), "d"(0)); + if (fault_wanted) + GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); + else + GUEST_ASSERT_2(!vector, testcase, vector); + + vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0)); + if (fault_wanted) + GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); + else + GUEST_ASSERT_2(!vector, testcase, vector); +} + +static void guest_code(void) +{ + guest_monitor_wait(MWAIT_DISABLED); + + guest_monitor_wait(MWAIT_QUIRK_DISABLED | MWAIT_DISABLED); + + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_DISABLED); + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED); + + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED | MWAIT_DISABLED); + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + uint64_t disabled_quirks; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + int testcase; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); + + run = vcpu->run; + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + while (1) { + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + testcase = uc.args[1]; + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "testcase = %lx, vector = %ld"); + goto done; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + goto done; + } + + disabled_quirks = 0; + if (testcase & MWAIT_QUIRK_DISABLED) + disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS; + if (testcase & MISC_ENABLES_QUIRK_DISABLED) + disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT; + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks); + + /* + * If the MISC_ENABLES quirk (KVM neglects to update CPUID to + * enable/disable MWAIT) is disabled, toggle the ENABLE_MWAIT + * bit in MISC_ENABLES accordingly. If the quirk is enabled, + * the only valid configuration is MWAIT disabled, as CPUID + * can't be manually changed after running the vCPU. + */ + if (!(testcase & MISC_ENABLES_QUIRK_DISABLED)) { + TEST_ASSERT(testcase & MWAIT_DISABLED, + "Can't toggle CPUID features after running vCPU"); + continue; + } + + vcpu_set_msr(vcpu, MSR_IA32_MISC_ENABLE, + (testcase & MWAIT_DISABLED) ? 0 : MSR_IA32_MISC_ENABLE_MWAIT); + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c new file mode 100644 index 000000000000..cc6421716400 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/nx_huge_page_test.c + * + * Usage: to be run via nx_huge_page_test.sh, which does the necessary + * environment setup and teardown + * + * Copyright (C) 2022, Google LLC. + */ + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <stdint.h> +#include <time.h> + +#include <test_util.h> +#include "kvm_util.h" +#include "processor.h" + +#define HPAGE_SLOT 10 +#define HPAGE_GPA (4UL << 30) /* 4G prevents collision w/ slot 0 */ +#define HPAGE_GVA HPAGE_GPA /* GVA is arbitrary, so use GPA. */ +#define PAGES_PER_2MB_HUGE_PAGE 512 +#define HPAGE_SLOT_NPAGES (3 * PAGES_PER_2MB_HUGE_PAGE) + +/* + * Passed by nx_huge_pages_test.sh to provide an easy warning if this test is + * being run without it. + */ +#define MAGIC_TOKEN 887563923 + +/* + * x86 opcode for the return instruction. Used to call into, and then + * immediately return from, memory backed with hugepages. + */ +#define RETURN_OPCODE 0xC3 + +/* Call the specified memory address. */ +static void guest_do_CALL(uint64_t target) +{ + ((void (*)(void)) target)(); +} + +/* + * Exit the VM after each memory access so that the userspace component of the + * test can make assertions about the pages backing the VM. + * + * See the below for an explanation of how each access should affect the + * backing mappings. + */ +void guest_code(void) +{ + uint64_t hpage_1 = HPAGE_GVA; + uint64_t hpage_2 = hpage_1 + (PAGE_SIZE * 512); + uint64_t hpage_3 = hpage_2 + (PAGE_SIZE * 512); + + READ_ONCE(*(uint64_t *)hpage_1); + GUEST_SYNC(1); + + READ_ONCE(*(uint64_t *)hpage_2); + GUEST_SYNC(2); + + guest_do_CALL(hpage_1); + GUEST_SYNC(3); + + guest_do_CALL(hpage_3); + GUEST_SYNC(4); + + READ_ONCE(*(uint64_t *)hpage_1); + GUEST_SYNC(5); + + READ_ONCE(*(uint64_t *)hpage_3); + GUEST_SYNC(6); +} + +static void check_2m_page_count(struct kvm_vm *vm, int expected_pages_2m) +{ + int actual_pages_2m; + + actual_pages_2m = vm_get_stat(vm, "pages_2m"); + + TEST_ASSERT(actual_pages_2m == expected_pages_2m, + "Unexpected 2m page count. Expected %d, got %d", + expected_pages_2m, actual_pages_2m); +} + +static void check_split_count(struct kvm_vm *vm, int expected_splits) +{ + int actual_splits; + + actual_splits = vm_get_stat(vm, "nx_lpage_splits"); + + TEST_ASSERT(actual_splits == expected_splits, + "Unexpected NX huge page split count. Expected %d, got %d", + expected_splits, actual_splits); +} + +static void wait_for_reclaim(int reclaim_period_ms) +{ + long reclaim_wait_ms; + struct timespec ts; + + reclaim_wait_ms = reclaim_period_ms * 5; + ts.tv_sec = reclaim_wait_ms / 1000; + ts.tv_nsec = (reclaim_wait_ms - (ts.tv_sec * 1000)) * 1000000; + nanosleep(&ts, NULL); +} + +void run_test(int reclaim_period_ms, bool disable_nx_huge_pages, + bool reboot_permissions) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + void *hva; + int r; + + vm = vm_create(1); + + if (disable_nx_huge_pages) { + /* + * Cannot run the test without NX huge pages if the kernel + * does not support it. + */ + if (!kvm_check_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES)) + return; + + r = __vm_disable_nx_huge_pages(vm); + if (reboot_permissions) { + TEST_ASSERT(!r, "Disabling NX huge pages should succeed if process has reboot permissions"); + } else { + TEST_ASSERT(r == -1 && errno == EPERM, + "This process should not have permission to disable NX huge pages"); + return; + } + } + + vcpu = vm_vcpu_add(vm, 0, guest_code); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_HUGETLB, + HPAGE_GPA, HPAGE_SLOT, + HPAGE_SLOT_NPAGES, 0); + + virt_map(vm, HPAGE_GVA, HPAGE_GPA, HPAGE_SLOT_NPAGES); + + hva = addr_gpa2hva(vm, HPAGE_GPA); + memset(hva, RETURN_OPCODE, HPAGE_SLOT_NPAGES * PAGE_SIZE); + + check_2m_page_count(vm, 0); + check_split_count(vm, 0); + + /* + * The guest code will first read from the first hugepage, resulting + * in a huge page mapping being created. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, 1); + check_split_count(vm, 0); + + /* + * Then the guest code will read from the second hugepage, resulting + * in another huge page mapping being created. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, 2); + check_split_count(vm, 0); + + /* + * Next, the guest will execute from the first huge page, causing it + * to be remapped at 4k. + * + * If NX huge pages are disabled, this should have no effect. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 2 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 1); + + /* + * Executing from the third huge page (previously unaccessed) will + * cause part to be mapped at 4k. + * + * If NX huge pages are disabled, it should be mapped at 2M. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 2); + + /* Reading from the first huge page again should have no effect. */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 2); + + /* Give recovery thread time to run. */ + wait_for_reclaim(reclaim_period_ms); + + /* + * Now that the reclaimer has run, all the split pages should be gone. + * + * If NX huge pages are disabled, the relaimer will not run, so + * nothing should change from here on. + */ + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, 0); + + /* + * The 4k mapping on hpage 3 should have been removed, so check that + * reading from it causes a huge page mapping to be installed. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 2); + check_split_count(vm, 0); + + kvm_vm_free(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-p period_ms] [-t token]\n", name); + puts(""); + printf(" -p: The NX reclaim period in miliseconds.\n"); + printf(" -t: The magic token to indicate environment setup is done.\n"); + printf(" -r: The test has reboot permissions and can disable NX huge pages.\n"); + puts(""); + exit(0); +} + +int main(int argc, char **argv) +{ + int reclaim_period_ms = 0, token = 0, opt; + bool reboot_permissions = false; + + while ((opt = getopt(argc, argv, "hp:t:r")) != -1) { + switch (opt) { + case 'p': + reclaim_period_ms = atoi(optarg); + break; + case 't': + token = atoi(optarg); + break; + case 'r': + reboot_permissions = true; + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + if (token != MAGIC_TOKEN) { + print_skip("This test must be run with the magic token %d.\n" + "This is done by nx_huge_pages_test.sh, which\n" + "also handles environment setup for the test.", + MAGIC_TOKEN); + exit(KSFT_SKIP); + } + + if (!reclaim_period_ms) { + print_skip("The NX reclaim period must be specified and non-zero"); + exit(KSFT_SKIP); + } + + run_test(reclaim_period_ms, false, reboot_permissions); + run_test(reclaim_period_ms, true, reboot_permissions); + + return 0; +} + diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh new file mode 100755 index 000000000000..0560149e66ed --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only */ +# +# Wrapper script which performs setup and cleanup for nx_huge_pages_test. +# Makes use of root privileges to set up huge pages and KVM module parameters. +# +# tools/testing/selftests/kvm/nx_huge_page_test.sh +# Copyright (C) 2022, Google LLC. + +set -e + +NX_HUGE_PAGES=$(cat /sys/module/kvm/parameters/nx_huge_pages) +NX_HUGE_PAGES_RECOVERY_RATIO=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio) +NX_HUGE_PAGES_RECOVERY_PERIOD=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms) +HUGE_PAGES=$(cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages) + +set +e + +function sudo_echo () { + echo "$1" | sudo tee -a "$2" > /dev/null +} + +NXECUTABLE="$(dirname $0)/nx_huge_pages_test" + +sudo_echo test /dev/null || exit 4 # KSFT_SKIP=4 + +( + set -e + + sudo_echo 1 /sys/module/kvm/parameters/nx_huge_pages + sudo_echo 1 /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio + sudo_echo 100 /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms + sudo_echo "$(( $HUGE_PAGES + 3 ))" /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + + # Test with reboot permissions + if [ $(whoami) == "root" ] || sudo setcap cap_sys_boot+ep $NXECUTABLE 2> /dev/null; then + echo Running test with CAP_SYS_BOOT enabled + $NXECUTABLE -t 887563923 -p 100 -r + test $(whoami) == "root" || sudo setcap cap_sys_boot-ep $NXECUTABLE + else + echo setcap failed, skipping nx_huge_pages_test with CAP_SYS_BOOT enabled + fi + + # Test without reboot permissions + if [ $(whoami) != "root" ] ; then + echo Running test with CAP_SYS_BOOT disabled + $NXECUTABLE -t 887563923 -p 100 + else + echo Running as root, skipping nx_huge_pages_test with CAP_SYS_BOOT disabled + fi +) +RET=$? + +sudo_echo "$NX_HUGE_PAGES" /sys/module/kvm/parameters/nx_huge_pages +sudo_echo "$NX_HUGE_PAGES_RECOVERY_RATIO" /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio +sudo_echo "$NX_HUGE_PAGES_RECOVERY_PERIOD" /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms +sudo_echo "$HUGE_PAGES" /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + +exit $RET diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 1e89688cbbbf..76417c7d687b 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -21,7 +21,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 #define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 static void guest_code(void) @@ -35,28 +34,18 @@ static void guest_code(void) } } -static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) { - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MSR_PLATFORM_INFO; - cap.flags = 0; - cap.args[0] = (int)enable; - vm_enable_cap(vm, &cap); -} - -static void test_msr_platform_info_enabled(struct kvm_vm *vm) -{ - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - set_msr_platform_info_enabled(vm, true); - vcpu_run(vm, VCPU_ID); + vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, true); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - get_ucall(vm, VCPU_ID, &uc); + get_ucall(vcpu, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd); TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == @@ -65,12 +54,12 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm) MSR_PLATFORM_INFO_MAX_TURBO_RATIO); } -static void test_msr_platform_info_disabled(struct kvm_vm *vm) +static void test_msr_platform_info_disabled(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - set_msr_platform_info_enabled(vm, false); - vcpu_run(vm, VCPU_ID); + vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, false); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", run->exit_reason, @@ -79,27 +68,23 @@ static void test_msr_platform_info_disabled(struct kvm_vm *vm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - int rv; uint64_t msr_platform_info; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); - if (!rv) { - print_skip("KVM_CAP_MSR_PLATFORM_INFO not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); - vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, - msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - test_msr_platform_info_enabled(vm); - test_msr_platform_info_disabled(vm); - vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + msr_platform_info = vcpu_get_msr(vcpu, MSR_PLATFORM_INFO); + vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, + msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); + test_msr_platform_info_enabled(vcpu); + test_msr_platform_info_disabled(vcpu); + vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 93d77574b255..ea4e259a1e2e 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -49,7 +49,6 @@ union cpuid10_ebx { /* Oddly, this isn't in perf_event.h. */ #define ARCH_PERFMON_BRANCHES_RETIRED 5 -#define VCPU_ID 0 #define NUM_BRANCHES 42 /* @@ -173,17 +172,17 @@ static void amd_guest_code(void) * Run the VM to the next GUEST_SYNC(value), and return the value passed * to the sync. Any other exit from the guest is fatal. */ -static uint64_t run_vm_to_sync(struct kvm_vm *vm) +static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - get_ucall(vm, VCPU_ID, &uc); + get_ucall(vcpu, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, "Received ucall other than UCALL_SYNC: %lu", uc.cmd); return uc.args[1]; @@ -197,13 +196,13 @@ static uint64_t run_vm_to_sync(struct kvm_vm *vm) * a sanity check and then GUEST_SYNC(success). In the case of failure, * the behavior of the guest on resumption is undefined. */ -static bool sanity_check_pmu(struct kvm_vm *vm) +static bool sanity_check_pmu(struct kvm_vcpu *vcpu) { bool success; - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); - success = run_vm_to_sync(vm); - vm_install_exception_handler(vm, GP_VECTOR, NULL); + vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); + success = run_vcpu_to_sync(vcpu); + vm_install_exception_handler(vcpu->vm, GP_VECTOR, NULL); return success; } @@ -264,9 +263,9 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, return f; } -static void test_without_filter(struct kvm_vm *vm) +static void test_without_filter(struct kvm_vcpu *vcpu) { - uint64_t count = run_vm_to_sync(vm); + uint64_t count = run_vcpu_to_sync(vcpu); if (count != NUM_BRANCHES) pr_info("%s: Branch instructions retired = %lu (expected %u)\n", @@ -274,21 +273,21 @@ static void test_without_filter(struct kvm_vm *vm) TEST_ASSERT(count, "Allowed PMU event is not counting"); } -static uint64_t test_with_filter(struct kvm_vm *vm, +static uint64_t test_with_filter(struct kvm_vcpu *vcpu, struct kvm_pmu_event_filter *f) { - vm_ioctl(vm, KVM_SET_PMU_EVENT_FILTER, (void *)f); - return run_vm_to_sync(vm); + vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); + return run_vcpu_to_sync(vcpu); } -static void test_amd_deny_list(struct kvm_vm *vm) +static void test_amd_deny_list(struct kvm_vcpu *vcpu) { uint64_t event = EVENT(0x1C2, 0); struct kvm_pmu_event_filter *f; uint64_t count; f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); - count = test_with_filter(vm, f); + count = test_with_filter(vcpu, f); free(f); if (count != NUM_BRANCHES) @@ -297,10 +296,10 @@ static void test_amd_deny_list(struct kvm_vm *vm) TEST_ASSERT(count, "Allowed PMU event is not counting"); } -static void test_member_deny_list(struct kvm_vm *vm) +static void test_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); - uint64_t count = test_with_filter(vm, f); + uint64_t count = test_with_filter(vcpu, f); free(f); if (count) @@ -309,10 +308,10 @@ static void test_member_deny_list(struct kvm_vm *vm) TEST_ASSERT(!count, "Disallowed PMU Event is counting"); } -static void test_member_allow_list(struct kvm_vm *vm) +static void test_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); - uint64_t count = test_with_filter(vm, f); + uint64_t count = test_with_filter(vcpu, f); free(f); if (count != NUM_BRANCHES) @@ -321,14 +320,14 @@ static void test_member_allow_list(struct kvm_vm *vm) TEST_ASSERT(count, "Allowed PMU event is not counting"); } -static void test_not_member_deny_list(struct kvm_vm *vm) +static void test_not_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); uint64_t count; remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vm, f); + count = test_with_filter(vcpu, f); free(f); if (count != NUM_BRANCHES) pr_info("%s: Branch instructions retired = %lu (expected %u)\n", @@ -336,14 +335,14 @@ static void test_not_member_deny_list(struct kvm_vm *vm) TEST_ASSERT(count, "Allowed PMU event is not counting"); } -static void test_not_member_allow_list(struct kvm_vm *vm) +static void test_not_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); uint64_t count; remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vm, f); + count = test_with_filter(vcpu, f); free(f); if (count) pr_info("%s: Branch instructions retired = %lu (expected 0)\n", @@ -358,25 +357,23 @@ static void test_not_member_allow_list(struct kvm_vm *vm) */ static void test_pmu_config_disable(void (*guest_code)(void)) { + struct kvm_vcpu *vcpu; int r; struct kvm_vm *vm; - struct kvm_enable_cap cap = { 0 }; r = kvm_check_cap(KVM_CAP_PMU_CAPABILITY); if (!(r & KVM_PMU_CAP_DISABLE)) return; - vm = vm_create_without_vcpus(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES); + vm = vm_create(1); - cap.cap = KVM_CAP_PMU_CAPABILITY; - cap.args[0] = KVM_PMU_CAP_DISABLE; - TEST_ASSERT(!vm_enable_cap(vm, &cap), "Failed to set KVM_PMU_CAP_DISABLE."); + vm_enable_cap(vm, KVM_CAP_PMU_CAPABILITY, KVM_PMU_CAP_DISABLE); - vm_vcpu_add_default(vm, VCPU_ID, guest_code); + vcpu = vm_vcpu_add(vm, 0, guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); - TEST_ASSERT(!sanity_check_pmu(vm), + TEST_ASSERT(!sanity_check_pmu(vcpu), "Guest should not be able to use disabled PMU."); kvm_vm_free(vm); @@ -387,7 +384,7 @@ static void test_pmu_config_disable(void (*guest_code)(void)) * counter per logical processor, an EBX bit vector of length greater * than 5, and EBX[5] clear. */ -static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry) +static bool check_intel_pmu_leaf(const struct kvm_cpuid_entry2 *entry) { union cpuid10_eax eax = { .full = entry->eax }; union cpuid10_ebx ebx = { .full = entry->ebx }; @@ -403,10 +400,10 @@ static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry) */ static bool use_intel_pmu(void) { - struct kvm_cpuid_entry2 *entry; + const struct kvm_cpuid_entry2 *entry; - entry = kvm_get_supported_cpuid_index(0xa, 0); - return is_intel_cpu() && entry && check_intel_pmu_leaf(entry); + entry = kvm_get_supported_cpuid_entry(0xa); + return is_intel_cpu() && check_intel_pmu_leaf(entry); } static bool is_zen1(uint32_t eax) @@ -435,10 +432,10 @@ static bool is_zen3(uint32_t eax) */ static bool use_amd_pmu(void) { - struct kvm_cpuid_entry2 *entry; + const struct kvm_cpuid_entry2 *entry; - entry = kvm_get_supported_cpuid_index(1, 0); - return is_amd_cpu() && entry && + entry = kvm_get_supported_cpuid_entry(1); + return is_amd_cpu() && (is_zen1(entry->eax) || is_zen2(entry->eax) || is_zen3(entry->eax)); @@ -446,47 +443,33 @@ static bool use_amd_pmu(void) int main(int argc, char *argv[]) { - void (*guest_code)(void) = NULL; + void (*guest_code)(void); + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - int r; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - r = kvm_check_cap(KVM_CAP_PMU_EVENT_FILTER); - if (!r) { - print_skip("KVM_CAP_PMU_EVENT_FILTER not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); - if (use_intel_pmu()) - guest_code = intel_guest_code; - else if (use_amd_pmu()) - guest_code = amd_guest_code; + TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); + guest_code = use_intel_pmu() ? intel_guest_code : amd_guest_code; - if (!guest_code) { - print_skip("Don't know how to test this guest PMU"); - exit(KSFT_SKIP); - } - - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); - if (!sanity_check_pmu(vm)) { - print_skip("Guest PMU is not functional"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(sanity_check_pmu(vcpu)); if (use_amd_pmu()) - test_amd_deny_list(vm); + test_amd_deny_list(vcpu); - test_without_filter(vm); - test_member_deny_list(vm); - test_member_allow_list(vm); - test_not_member_deny_list(vm); - test_not_member_allow_list(vm); + test_without_filter(vcpu); + test_member_deny_list(vcpu); + test_member_allow_list(vcpu); + test_not_member_deny_list(vcpu); + test_not_member_allow_list(vcpu); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index ae76436af0cc..b25d7556b638 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -16,10 +16,6 @@ #include "processor.h" #include "apic.h" -#define N_VCPU 2 -#define VCPU_ID0 0 -#define VCPU_ID1 1 - static void guest_bsp_vcpu(void *arg) { GUEST_SYNC(1); @@ -38,31 +34,30 @@ static void guest_not_bsp_vcpu(void *arg) GUEST_DONE(); } -static void test_set_boot_busy(struct kvm_vm *vm) +static void test_set_bsp_busy(struct kvm_vcpu *vcpu, const char *msg) { - int res; + int r = __vm_ioctl(vcpu->vm, KVM_SET_BOOT_CPU_ID, + (void *)(unsigned long)vcpu->id); - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0); - TEST_ASSERT(res == -1 && errno == EBUSY, - "KVM_SET_BOOT_CPU_ID set while running vm"); + TEST_ASSERT(r == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set %s", msg); } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +static void run_vcpu(struct kvm_vcpu *vcpu) { struct ucall uc; int stage; for (stage = 0; stage < 2; stage++) { - vcpu_run(vm, vcpuid); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", stage + 1, (ulong)uc.args[1]); - test_set_boot_busy(vm); + test_set_bsp_busy(vcpu, "while running vm"); break; case UCALL_DONE: TEST_ASSERT(stage == 1, @@ -70,91 +65,67 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) stage); break; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx", - (const char *)uc.args[0], __FILE__, - uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } } -static struct kvm_vm *create_vm(void) +static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, + struct kvm_vcpu *vcpus[]) { struct kvm_vm *vm; - uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2; - uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + uint32_t i; - pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages); - vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR); + vm = vm_create(nr_vcpus); - kvm_vm_elf_load(vm, program_invocation_name); - vm_create_irqchip(vm); + vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(unsigned long)bsp_vcpu_id); + for (i = 0; i < nr_vcpus; i++) + vcpus[i] = vm_vcpu_add(vm, i, i == bsp_vcpu_id ? guest_bsp_vcpu : + guest_not_bsp_vcpu); return vm; } -static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code) -{ - if (bsp_code) - vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu); - else - vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu); -} - -static void run_vm_bsp(uint32_t bsp_vcpu) +static void run_vm_bsp(uint32_t bsp_vcpu_id) { + struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; - bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1; - vm = create_vm(); + vm = create_vm(ARRAY_SIZE(vcpus), bsp_vcpu_id, vcpus); - if (is_bsp_vcpu1) - vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - - add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1); - add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1); - - run_vcpu(vm, VCPU_ID0); - run_vcpu(vm, VCPU_ID1); + run_vcpu(vcpus[0]); + run_vcpu(vcpus[1]); kvm_vm_free(vm); } static void check_set_bsp_busy(void) { + struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; - int res; - vm = create_vm(); + vm = create_vm(ARRAY_SIZE(vcpus), 0, vcpus); - add_x86_vcpu(vm, VCPU_ID0, true); - add_x86_vcpu(vm, VCPU_ID1, false); + test_set_bsp_busy(vcpus[1], "after adding vcpu"); - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu"); + run_vcpu(vcpus[0]); + run_vcpu(vcpus[1]); - run_vcpu(vm, VCPU_ID0); - run_vcpu(vm, VCPU_ID1); - - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu"); + test_set_bsp_busy(vcpus[1], "to a terminated vcpu"); kvm_vm_free(vm); } int main(int argc, char *argv[]) { - if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) { - print_skip("set_boot_cpu_id not available"); - return 0; - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_BOOT_CPU_ID)); - run_vm_bsp(VCPU_ID0); - run_vm_bsp(VCPU_ID1); - run_vm_bsp(VCPU_ID0); + run_vm_bsp(0); + run_vm_bsp(1); + run_vm_bsp(0); check_set_bsp_busy(); } diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 318be0bf77ab..2bb08bf2125d 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -22,9 +22,7 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - -static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, +static void test_cr4_feature_bit(struct kvm_vcpu *vcpu, struct kvm_sregs *orig, uint64_t feature_bit) { struct kvm_sregs sregs; @@ -37,44 +35,40 @@ static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, memcpy(&sregs, orig, sizeof(sregs)); sregs.cr4 |= feature_bit; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit); /* Sanity check that KVM didn't change anything. */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs"); } -static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) +static uint64_t calc_supported_cr4_feature_bits(void) { - struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7; uint64_t cr4; - cpuid_1 = kvm_get_supported_cpuid_entry(1); - cpuid_7 = kvm_get_supported_cpuid_entry(7); - cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; - if (cpuid_7->ecx & CPUID_UMIP) + if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; - if (cpuid_7->ecx & CPUID_LA57) + if (kvm_cpu_has(X86_FEATURE_LA57)) cr4 |= X86_CR4_LA57; - if (cpuid_1->ecx & CPUID_VMX) + if (kvm_cpu_has(X86_FEATURE_VMX)) cr4 |= X86_CR4_VMXE; - if (cpuid_1->ecx & CPUID_SMX) + if (kvm_cpu_has(X86_FEATURE_SMX)) cr4 |= X86_CR4_SMXE; - if (cpuid_7->ebx & CPUID_FSGSBASE) + if (kvm_cpu_has(X86_FEATURE_FSGSBASE)) cr4 |= X86_CR4_FSGSBASE; - if (cpuid_1->ecx & CPUID_PCID) + if (kvm_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; - if (cpuid_1->ecx & CPUID_XSAVE) + if (kvm_cpu_has(X86_FEATURE_XSAVE)) cr4 |= X86_CR4_OSXSAVE; - if (cpuid_7->ebx & CPUID_SMEP) + if (kvm_cpu_has(X86_FEATURE_SMEP)) cr4 |= X86_CR4_SMEP; - if (cpuid_7->ebx & CPUID_SMAP) + if (kvm_cpu_has(X86_FEATURE_SMAP)) cr4 |= X86_CR4_SMAP; - if (cpuid_7->ecx & CPUID_PKU) + if (kvm_cpu_has(X86_FEATURE_PKU)) cr4 |= X86_CR4_PKE; return cr4; @@ -83,6 +77,7 @@ static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) int main(int argc, char *argv[]) { struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t cr4; int rc; @@ -95,44 +90,44 @@ int main(int argc, char *argv[]) * use it to verify all supported CR4 bits can be set prior to defining * the vCPU model, i.e. without doing KVM_SET_CPUID2. */ - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); - sregs.cr4 |= calc_cr4_feature_bits(vm); + sregs.cr4 |= calc_supported_cr4_feature_bits(); cr4 = sregs.cr4; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", sregs.cr4, cr4); /* Verify all unsupported features are rejected by KVM. */ - test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57); - test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_UMIP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_LA57); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_VMXE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMXE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_FSGSBASE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_PCIDE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_OSXSAVE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMEP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMAP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_PKE); kvm_vm_free(vm); /* Create a "real" VM and verify APIC_BASE can be set. */ - vm = vm_create_default(VCPU_ID, 0, NULL); + vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.apic_base = 1 << 10; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)", sregs.apic_base); sregs.apic_base = 1 << 11; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)", sregs.apic_base); diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index d1dc1acf997c..c7ef97561038 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -12,7 +12,6 @@ #include "processor.h" #include "svm_util.h" #include "kselftest.h" -#include "../lib/kvm_util_internal.h" #define SEV_POLICY_ES 0b100 @@ -54,10 +53,10 @@ static struct kvm_vm *sev_vm_create(bool es) struct kvm_sev_launch_start start = { 0 }; int i; - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm = vm_create_barebones(); sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL); for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(vm, i); + __vm_vcpu_add(vm, i); if (es) start.policy |= SEV_POLICY_ES; sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start); @@ -71,32 +70,27 @@ static struct kvm_vm *aux_vm_create(bool with_vcpus) struct kvm_vm *vm; int i; - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm = vm_create_barebones(); if (!with_vcpus) return vm; for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(vm, i); + __vm_vcpu_add(vm, i); return vm; } -static int __sev_migrate_from(int dst_fd, int src_fd) +static int __sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, - .args = { src_fd } - }; - - return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); + return __vm_enable_cap(dst, KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, src->fd); } -static void sev_migrate_from(int dst_fd, int src_fd) +static void sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src) { int ret; - ret = __sev_migrate_from(dst_fd, src_fd); + ret = __sev_migrate_from(dst, src); TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno); } @@ -111,13 +105,13 @@ static void test_sev_migrate_from(bool es) dst_vms[i] = aux_vm_create(true); /* Initial migration from the src to the first dst. */ - sev_migrate_from(dst_vms[0]->fd, src_vm->fd); + sev_migrate_from(dst_vms[0], src_vm); for (i = 1; i < NR_MIGRATE_TEST_VMS; i++) - sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); + sev_migrate_from(dst_vms[i], dst_vms[i - 1]); /* Migrate the guest back to the original VM. */ - ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + ret = __sev_migrate_from(src_vm, dst_vms[NR_MIGRATE_TEST_VMS - 1]); TEST_ASSERT(ret == -1 && errno == EIO, "VM that was migrated from should be dead. ret %d, errno: %d\n", ret, errno); @@ -129,7 +123,7 @@ static void test_sev_migrate_from(bool es) struct locking_thread_input { struct kvm_vm *vm; - int source_fds[NR_LOCK_TESTING_THREADS]; + struct kvm_vm *source_vms[NR_LOCK_TESTING_THREADS]; }; static void *locking_test_thread(void *arg) @@ -139,7 +133,7 @@ static void *locking_test_thread(void *arg) for (i = 0; i < NR_LOCK_TESTING_ITERATIONS; ++i) { j = i % NR_LOCK_TESTING_THREADS; - __sev_migrate_from(input->vm->fd, input->source_fds[j]); + __sev_migrate_from(input->vm, input->source_vms[j]); } return NULL; @@ -153,11 +147,11 @@ static void test_sev_migrate_locking(void) for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) { input[i].vm = sev_vm_create(/* es= */ false); - input[0].source_fds[i] = input[i].vm->fd; + input[0].source_vms[i] = input[i].vm; } for (i = 1; i < NR_LOCK_TESTING_THREADS; ++i) - memcpy(input[i].source_fds, input[0].source_fds, - sizeof(input[i].source_fds)); + memcpy(input[i].source_vms, input[0].source_vms, + sizeof(input[i].source_vms)); for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) pthread_create(&pt[i], NULL, locking_test_thread, &input[i]); @@ -174,9 +168,9 @@ static void test_sev_migrate_parameters(void) *sev_es_vm_no_vmsa; int ret; - vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm_no_vcpu = vm_create_barebones(); vm_no_sev = aux_vm_create(true); - ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); + ret = __sev_migrate_from(vm_no_vcpu, vm_no_sev); TEST_ASSERT(ret == -1 && errno == EINVAL, "Migrations require SEV enabled. ret %d, errno: %d\n", ret, errno); @@ -186,29 +180,29 @@ static void test_sev_migrate_parameters(void) sev_vm = sev_vm_create(/* es= */ false); sev_es_vm = sev_vm_create(/* es= */ true); - sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_es_vm_no_vmsa = vm_create_barebones(); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); - vm_vcpu_add(sev_es_vm_no_vmsa, 1); + __vm_vcpu_add(sev_es_vm_no_vmsa, 1); - ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); + ret = __sev_migrate_from(sev_vm, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(sev_es_vm->fd, sev_vm->fd); + ret = __sev_migrate_from(sev_es_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm->fd); + ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm_no_vmsa->fd); + ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm_no_vmsa); TEST_ASSERT( ret == -1 && errno == EINVAL, "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", @@ -222,22 +216,17 @@ out: kvm_vm_free(vm_no_sev); } -static int __sev_mirror_create(int dst_fd, int src_fd) +static int __sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, - .args = { src_fd } - }; - - return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); + return __vm_enable_cap(dst, KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, src->fd); } -static void sev_mirror_create(int dst_fd, int src_fd) +static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src) { int ret; - ret = __sev_mirror_create(dst_fd, src_fd); + ret = __sev_mirror_create(dst, src); TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); } @@ -285,11 +274,11 @@ static void test_sev_mirror(bool es) src_vm = sev_vm_create(es); dst_vm = aux_vm_create(false); - sev_mirror_create(dst_vm->fd, src_vm->fd); + sev_mirror_create(dst_vm, src_vm); /* Check that we can complete creation of the mirror VM. */ for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(dst_vm, i); + __vm_vcpu_add(dst_vm, i); if (es) sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); @@ -309,18 +298,18 @@ static void test_sev_mirror_parameters(void) vm_with_vcpu = aux_vm_create(true); vm_no_vcpu = aux_vm_create(false); - ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd); + ret = __sev_mirror_create(sev_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able copy context to self. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + ret = __sev_mirror_create(vm_no_vcpu, vm_with_vcpu); TEST_ASSERT(ret == -1 && errno == EINVAL, "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + ret = __sev_mirror_create(vm_with_vcpu, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", @@ -330,13 +319,13 @@ static void test_sev_mirror_parameters(void) goto out; sev_es_vm = sev_vm_create(/* es= */ true); - ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); + ret = __sev_mirror_create(sev_vm, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd); + ret = __sev_mirror_create(sev_es_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", @@ -364,16 +353,16 @@ static void test_sev_move_copy(void) dst2_mirror_vm = aux_vm_create(false); dst3_mirror_vm = aux_vm_create(false); - sev_mirror_create(mirror_vm->fd, sev_vm->fd); + sev_mirror_create(mirror_vm, sev_vm); - sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); - sev_migrate_from(dst_vm->fd, sev_vm->fd); + sev_migrate_from(dst_mirror_vm, mirror_vm); + sev_migrate_from(dst_vm, sev_vm); - sev_migrate_from(dst2_vm->fd, dst_vm->fd); - sev_migrate_from(dst2_mirror_vm->fd, dst_mirror_vm->fd); + sev_migrate_from(dst2_vm, dst_vm); + sev_migrate_from(dst2_mirror_vm, dst_mirror_vm); - sev_migrate_from(dst3_mirror_vm->fd, dst2_mirror_vm->fd); - sev_migrate_from(dst3_vm->fd, dst2_vm->fd); + sev_migrate_from(dst3_mirror_vm, dst2_mirror_vm); + sev_migrate_from(dst3_vm, dst2_vm); kvm_vm_free(dst_vm); kvm_vm_free(sev_vm); @@ -393,10 +382,10 @@ static void test_sev_move_copy(void) mirror_vm = aux_vm_create(false); dst_mirror_vm = aux_vm_create(false); - sev_mirror_create(mirror_vm->fd, sev_vm->fd); + sev_mirror_create(mirror_vm, sev_vm); - sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); - sev_migrate_from(dst_vm->fd, sev_vm->fd); + sev_migrate_from(dst_mirror_vm, mirror_vm); + sev_migrate_from(dst_vm, sev_vm); kvm_vm_free(mirror_vm); kvm_vm_free(dst_mirror_vm); @@ -404,41 +393,25 @@ static void test_sev_move_copy(void) kvm_vm_free(sev_vm); } -#define X86_FEATURE_SEV (1 << 1) -#define X86_FEATURE_SEV_ES (1 << 3) - int main(int argc, char *argv[]) { - struct kvm_cpuid_entry2 *cpuid; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)); - if (!kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM) && - !kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { - print_skip("Capabilities not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); - cpuid = kvm_get_supported_cpuid_entry(0x80000000); - if (cpuid->eax < 0x8000001f) { - print_skip("AMD memory encryption not available"); - exit(KSFT_SKIP); - } - cpuid = kvm_get_supported_cpuid_entry(0x8000001f); - if (!(cpuid->eax & X86_FEATURE_SEV)) { - print_skip("AMD SEV not available"); - exit(KSFT_SKIP); - } - have_sev_es = !!(cpuid->eax & X86_FEATURE_SEV_ES); + have_sev_es = kvm_cpu_has(X86_FEATURE_SEV_ES); - if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { + if (kvm_has_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { test_sev_migrate_from(/* es= */ false); if (have_sev_es) test_sev_migrate_from(/* es= */ true); test_sev_migrate_locking(); test_sev_migrate_parameters(); - if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) + if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) test_sev_move_copy(); } - if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); if (have_sev_es) test_sev_mirror(/* es= */ true); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index b4e0c860769e..1f136a81858e 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -19,8 +19,6 @@ #include "vmx.h" #include "svm_util.h" -#define VCPU_ID 1 - #define SMRAM_SIZE 65536 #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) @@ -85,7 +83,7 @@ static void guest_code(void *arg) sync_with_host(4); if (arg) { - if (cpu_has_svm()) { + if (this_cpu_has(X86_FEATURE_SVM)) { generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); } else { @@ -101,7 +99,7 @@ static void guest_code(void *arg) sync_with_host(7); - if (cpu_has_svm()) { + if (this_cpu_has(X86_FEATURE_SVM)) { run_guest(svm->vmcb, svm->vmcb_gpa); run_guest(svm->vmcb, svm->vmcb_gpa); } else { @@ -116,22 +114,23 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vm *vm) +void inject_smi(struct kvm_vcpu *vcpu) { struct kvm_vcpu_events events; - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); events.smi.pending = 1; events.flags |= KVM_VCPUEVENT_VALID_SMM; - vcpu_events_set(vm, VCPU_ID, &events); + vcpu_events_set(vcpu, &events); } int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; + struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_vm *vm; struct kvm_run *run; @@ -139,9 +138,9 @@ int main(int argc, char *argv[]) int stage, stage_reported; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, SMRAM_MEMSLOT, SMRAM_PAGES, 0); @@ -152,29 +151,29 @@ int main(int argc, char *argv[]) memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, sizeof(smi_handler)); - vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); + vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - if (nested_svm_supported()) + if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { + if (kvm_cpu_has(X86_FEATURE_SVM)) vcpu_alloc_svm(vm, &nested_gva); - else if (nested_vmx_supported()) + else if (kvm_cpu_has(X86_FEATURE_VMX)) vcpu_alloc_vmx(vm, &nested_gva); } if (!nested_gva) pr_info("will skip SMM test with VMX enabled\n"); - vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); memset(®s, 0, sizeof(regs)); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); stage_reported = regs.rax & 0xff; @@ -191,7 +190,7 @@ int main(int argc, char *argv[]) * return from it. Do not perform save/restore while in SMM yet. */ if (stage == 8) { - inject_smi(vm); + inject_smi(vcpu); continue; } @@ -200,15 +199,14 @@ int main(int argc, char *argv[]) * during L2 execution. */ if (stage == 10) - inject_smi(vm); + inject_smi(vcpu); - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); kvm_vm_release(vm); - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); + + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; kvm_x86_state_cleanup(state); } diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 2e0a92da8ff5..ea578971fb9f 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -20,7 +20,6 @@ #include "vmx.h" #include "svm_util.h" -#define VCPU_ID 5 #define L2_GUEST_STACK_SIZE 256 void svm_l2_guest_code(void) @@ -143,7 +142,7 @@ static void __attribute__((__flatten__)) guest_code(void *arg) GUEST_SYNC(2); if (arg) { - if (cpu_has_svm()) + if (this_cpu_has(X86_FEATURE_SVM)) svm_l1_guest_code(arg); else vmx_l1_guest_code(arg); @@ -157,6 +156,7 @@ int main(int argc, char *argv[]) vm_vaddr_t nested_gva = 0; struct kvm_regs regs1, regs2; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct kvm_x86_state *state; @@ -164,34 +164,33 @@ int main(int argc, char *argv[]) int stage; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - if (nested_svm_supported()) + if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { + if (kvm_cpu_has(X86_FEATURE_SVM)) vcpu_alloc_svm(vm, &nested_gva); - else if (nested_vmx_supported()) + else if (kvm_cpu_has(X86_FEATURE_VMX)) vcpu_alloc_vmx(vm, &nested_gva); } if (!nested_gva) pr_info("will skip nested state checks\n"); - vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -206,22 +205,20 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®s2); TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index 30a81038df46..4a07ba227b99 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -13,10 +13,6 @@ #include "svm_util.h" #include "apic.h" -#define VCPU_ID 0 - -static struct kvm_vm *vm; - bool vintr_irq_called; bool intr_irq_called; @@ -88,33 +84,36 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; + struct kvm_run *run; vm_vaddr_t svm_gva; + struct kvm_vm *vm; + struct ucall uc; - nested_svm_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); - struct kvm_run *run = vcpu_state(vm, VCPU_ID); - struct ucall uc; + run = vcpu->run; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); break; /* NOT REACHED */ case UCALL_DONE: diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c new file mode 100644 index 000000000000..e637d7736012 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 Oracle and/or its affiliates. + * + * Based on: + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + */ + +#include <stdatomic.h> +#include <stdio.h> +#include <unistd.h> +#include "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "test_util.h" + +#define INT_NR 0x20 + +static_assert(ATOMIC_INT_LOCK_FREE == 2, "atomic int is not lockless"); + +static unsigned int bp_fired; +static void guest_bp_handler(struct ex_regs *regs) +{ + bp_fired++; +} + +static unsigned int int_fired; +static void l2_guest_code_int(void); + +static void guest_int_handler(struct ex_regs *regs) +{ + int_fired++; + GUEST_ASSERT_2(regs->rip == (unsigned long)l2_guest_code_int, + regs->rip, (unsigned long)l2_guest_code_int); +} + +static void l2_guest_code_int(void) +{ + GUEST_ASSERT_1(int_fired == 1, int_fired); + vmmcall(); + ud2(); + + GUEST_ASSERT_1(bp_fired == 1, bp_fired); + hlt(); +} + +static atomic_int nmi_stage; +#define nmi_stage_get() atomic_load_explicit(&nmi_stage, memory_order_acquire) +#define nmi_stage_inc() atomic_fetch_add_explicit(&nmi_stage, 1, memory_order_acq_rel) +static void guest_nmi_handler(struct ex_regs *regs) +{ + nmi_stage_inc(); + + if (nmi_stage_get() == 1) { + vmmcall(); + GUEST_ASSERT(false); + } else { + GUEST_ASSERT_1(nmi_stage_get() == 3, nmi_stage_get()); + GUEST_DONE(); + } +} + +static void l2_guest_code_nmi(void) +{ + ud2(); +} + +static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t idt_alt) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + if (is_nmi) + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, + is_nmi ? l2_guest_code_nmi : l2_guest_code_int, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + vmcb->control.intercept_exceptions |= BIT(PF_VECTOR) | BIT(UD_VECTOR); + vmcb->control.intercept |= BIT(INTERCEPT_NMI) | BIT(INTERCEPT_HLT); + + if (is_nmi) { + vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + } else { + vmcb->control.event_inj = INT_NR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_SOFT; + /* The return address pushed on stack */ + vmcb->control.next_rip = vmcb->save.rip; + } + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_VMMCALL, + vmcb->control.exit_code, + vmcb->control.exit_info_1, vmcb->control.exit_info_2); + + if (is_nmi) { + clgi(); + x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_NMI); + + GUEST_ASSERT_1(nmi_stage_get() == 1, nmi_stage_get()); + nmi_stage_inc(); + + stgi(); + /* self-NMI happens here */ + while (true) + cpu_relax(); + } + + /* Skip over VMMCALL */ + vmcb->save.rip += 3; + + /* Switch to alternate IDT to cause intervening NPF again */ + vmcb->save.idtr.base = idt_alt; + vmcb->control.clean = 0; /* &= ~BIT(VMCB_DT) would be enough */ + + vmcb->control.event_inj = BP_VECTOR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; + /* The return address pushed on stack, skip over UD2 */ + vmcb->control.next_rip = vmcb->save.rip + 2; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_HLT, + vmcb->control.exit_code, + vmcb->control.exit_info_1, vmcb->control.exit_info_2); + + GUEST_DONE(); +} + +static void run_test(bool is_nmi) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + vm_vaddr_t svm_gva; + vm_vaddr_t idt_alt_vm; + struct kvm_guest_debug debug; + + pr_info("Running %s test\n", is_nmi ? "NMI" : "soft int"); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); + vm_install_exception_handler(vm, BP_VECTOR, guest_bp_handler); + vm_install_exception_handler(vm, INT_NR, guest_int_handler); + + vcpu_alloc_svm(vm, &svm_gva); + + if (!is_nmi) { + void *idt, *idt_alt; + + idt_alt_vm = vm_vaddr_alloc_page(vm); + idt_alt = addr_gva2hva(vm, idt_alt_vm); + idt = addr_gva2hva(vm, vm->idt); + memcpy(idt_alt, idt, getpagesize()); + } else { + idt_alt_vm = 0; + } + vcpu_args_set(vcpu, 3, svm_gva, (uint64_t)is_nmi, (uint64_t)idt_alt_vm); + + memset(&debug, 0, sizeof(debug)); + vcpu_guest_debug_set(vcpu, &debug); + + struct kvm_run *run = vcpu->run; + struct ucall uc; + + alarm(2); + vcpu_run(vcpu); + alarm(0); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_3(uc, "vals = 0x%lx 0x%lx 0x%lx"); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + TEST_ASSERT(kvm_cpu_has(X86_FEATURE_NRIPS), + "KVM with nSVM is supposed to unconditionally advertise nRIP Save"); + + atomic_init(&nmi_stage, 0); + + run_test(false); + run_test(true); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index be2ca157485b..c3ac45df7483 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -12,10 +12,6 @@ #include "processor.h" #include "svm_util.h" -#define VCPU_ID 5 - -static struct kvm_vm *vm; - static void l2_guest_code(struct svm_test_data *svm) { __asm__ __volatile__("vmcall"); @@ -39,28 +35,30 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; vm_vaddr_t svm_gva; + struct kvm_vm *vm; - nested_svm_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index fc03a150278d..9b6db0b0b13e 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -20,8 +20,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - #define UCALL_PIO_PORT ((uint16_t)0x1000) struct ucall uc_none = { @@ -84,6 +82,7 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left, int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct kvm_regs regs; @@ -95,66 +94,59 @@ int main(int argc, char *argv[]) setbuf(stdout, NULL); cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) { - print_skip("KVM_CAP_SYNC_REGS not supported"); - exit(KSFT_SKIP); - } - if ((cap & INVALID_SYNC_FIELD) != 0) { - print_skip("The \"invalid\" field is not invalid"); - exit(KSFT_SKIP); - } + TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS); + TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD)); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; /* Request reading invalid register set from VCPU. */ run->kvm_valid_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; /* Request setting invalid register set into VCPU. */ run->kvm_dirty_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; /* Request and verify all valid register sets. */ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ run->kvm_valid_regs = TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs.sregs); - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); /* Set and verify various register values. */ @@ -164,7 +156,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -176,13 +168,13 @@ int main(int argc, char *argv[]) "apic_base sync regs value incorrect 0x%llx.", run->s.regs.sregs.apic_base); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs.sregs); - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); /* Clear kvm_dirty_regs bits, verify new s.regs values are @@ -191,7 +183,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xDEADBEEF; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -208,8 +200,8 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xAAAA; regs.rbx = 0xBAC0; - vcpu_regs_set(vm, VCPU_ID, ®s); - rv = _vcpu_run(vm, VCPU_ID); + vcpu_regs_set(vcpu, ®s); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -217,7 +209,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); TEST_ASSERT(regs.rbx == 0xBAC0 + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); @@ -229,7 +221,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = 0; run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.rbx = 0xBBBB; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -237,7 +229,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); TEST_ASSERT(regs.rbx == 0xBBBB + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c new file mode 100644 index 000000000000..70b44f0b52fe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#include <string.h> +#include <sys/ioctl.h> + +#include "kselftest.h" + +#define ARBITRARY_IO_PORT 0x2000 + +/* The virtual machine object. */ +static struct kvm_vm *vm; + +static void l2_guest_code(void) +{ + asm volatile("inb %%dx, %%al" + : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); +} + +void l1_guest_code(struct vmx_pages *vmx) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(vmx->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx)); + GUEST_ASSERT(load_vmcs(vmx)); + + prepare_vmcs(vmx, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + /* L2 should triple fault after a triple fault event injected. */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_TRIPLE_FAULT); + GUEST_DONE(); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vcpu_events events; + vm_vaddr_t vmx_pages_gva; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); + + run = vcpu->run; + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Expected KVM_EXIT_IO, got: %u (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, + "Expected IN from port %d from L2, got port %d", + ARBITRARY_IO_PORT, run->io.port); + vcpu_events_get(vcpu, &events); + events.flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; + events.triple_fault.pending = true; + vcpu_events_set(vcpu, &events); + run->immediate_exit = true; + vcpu_run_complete_io(vcpu); + + vcpu_events_get(vcpu, &events); + TEST_ASSERT(events.flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT, + "Triple fault event invalid"); + TEST_ASSERT(events.triple_fault.pending, + "No triple fault pending"); + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + +} diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index a426078b16a3..22d366c697f7 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -9,14 +9,12 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - #define UNITY (1ull << 30) #define HOST_ADJUST (UNITY * 64) #define GUEST_STEP (UNITY * 4) #define ROUND(x) ((x + UNITY / 2) & -UNITY) #define rounded_rdmsr(x) ROUND(rdmsr(x)) -#define rounded_host_rdmsr(x) ROUND(vcpu_get_msr(vm, 0, x)) +#define rounded_host_rdmsr(x) ROUND(vcpu_get_msr(vcpu, x)) static void guest_code(void) { @@ -66,15 +64,13 @@ static void guest_code(void) GUEST_DONE(); } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) { struct ucall uc; - vcpu_args_set(vm, vcpuid, 1, vcpuid); - - vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", @@ -83,34 +79,33 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) case UCALL_DONE: return; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n" \ - "\tvalues: %#lx, %#lx", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } int main(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t val; - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 1); + run_vcpu(vcpu, 1); val = 1ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 2); + run_vcpu(vcpu, 2); val = 2ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -119,18 +114,18 @@ int main(void) * Host: writes to MSR_IA32_TSC set the host-side offset * and therefore do not change MSR_IA32_TSC_ADJUST. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC, HOST_ADJUST + val); + vcpu_set_msr(vcpu, MSR_IA32_TSC, HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); - run_vcpu(vm, VCPU_ID, 3); + run_vcpu(vcpu, 3); /* Host: writes to MSR_IA32_TSC_ADJUST do not modify the TSC. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, UNITY * 123456); + vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, UNITY * 123456); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(vcpu_get_msr(vm, 0, MSR_IA32_TSC_ADJUST), UNITY * 123456); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456); /* Restore previous value. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, val); + vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -138,7 +133,7 @@ int main(void) * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the * host-side offset and affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 4); + run_vcpu(vcpu, 4); val = 3ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -147,7 +142,7 @@ int main(void) * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side * offset is now visible in MSR_IA32_TSC_ADJUST. */ - run_vcpu(vm, VCPU_ID, 5); + run_vcpu(vcpu, 5); val = 4ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c index f0083d8cfe98..47139aab7408 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c @@ -46,38 +46,40 @@ static void guest_code(void) static void *run_vcpu(void *_cpu_nr) { - unsigned long cpu = (unsigned long)_cpu_nr; + unsigned long vcpu_id = (unsigned long)_cpu_nr; unsigned long failures = 0; static bool first_cpu_done; + struct kvm_vcpu *vcpu; - /* The kernel is fine, but vm_vcpu_add_default() needs locking */ + /* The kernel is fine, but vm_vcpu_add() needs locking */ pthread_spin_lock(&create_lock); - vm_vcpu_add_default(vm, cpu, guest_code); + vcpu = vm_vcpu_add(vm, vcpu_id, guest_code); if (!first_cpu_done) { first_cpu_done = true; - vcpu_set_msr(vm, cpu, MSR_IA32_TSC, TEST_TSC_OFFSET); + vcpu_set_msr(vcpu, MSR_IA32_TSC, TEST_TSC_OFFSET); } pthread_spin_unlock(&create_lock); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, cpu); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, cpu); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, cpu, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_DONE: goto out; case UCALL_SYNC: - printf("Guest %ld sync %lx %lx %ld\n", cpu, uc.args[2], uc.args[3], uc.args[2] - uc.args[3]); + printf("Guest %d sync %lx %lx %ld\n", vcpu->id, + uc.args[2], uc.args[3], uc.args[2] - uc.args[3]); failures++; break; @@ -91,12 +93,9 @@ static void *run_vcpu(void *_cpu_nr) int main(int argc, char *argv[]) { - if (!kvm_check_cap(KVM_CAP_VM_TSC_CONTROL)) { - print_skip("KVM_CAP_VM_TSC_CONTROL not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_TSC_CONTROL)); - vm = vm_create_default_with_vcpus(0, DEFAULT_STACK_PGS * NR_TEST_VCPUS, 0, guest_code, NULL); + vm = vm_create(NR_TEST_VCPUS); vm_ioctl(vm, KVM_SET_TSC_KHZ, (void *) TEST_TSC_KHZ); pthread_spin_init(&create_lock, PTHREAD_PROCESS_PRIVATE); diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c new file mode 100644 index 000000000000..a897c7fd8abe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucna_injection_test + * + * Copyright (C) 2022, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Test that user space can inject UnCorrectable No Action required (UCNA) + * memory errors to the guest. + * + * The test starts one vCPU with the MCG_CMCI_P enabled. It verifies that + * proper UCNA errors can be injected to a vCPU with MCG_CMCI_P and + * corresponding per-bank control register (MCI_CTL2) bit enabled. + * The test also checks that the UCNA errors get recorded in the + * Machine Check bank registers no matter the error signal interrupts get + * delivered into the guest or not. + * + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <pthread.h> +#include <inttypes.h> +#include <string.h> +#include <time.h> + +#include "kvm_util_base.h" +#include "kvm_util.h" +#include "mce.h" +#include "processor.h" +#include "test_util.h" +#include "apic.h" + +#define SYNC_FIRST_UCNA 9 +#define SYNC_SECOND_UCNA 10 +#define SYNC_GP 11 +#define FIRST_UCNA_ADDR 0xdeadbeef +#define SECOND_UCNA_ADDR 0xcafeb0ba + +/* + * Vector for the CMCI interrupt. + * Value is arbitrary. Any value in 0x20-0xFF should work: + * https://wiki.osdev.org/Interrupt_Vector_Table + */ +#define CMCI_VECTOR 0xa9 + +#define UCNA_BANK 0x7 // IMC0 bank + +#define MCI_CTL2_RESERVED_BIT BIT_ULL(29) + +static uint64_t supported_mcg_caps; + +/* + * Record states about the injected UCNA. + * The variables started with the 'i_' prefixes are recorded in interrupt + * handler. Variables without the 'i_' prefixes are recorded in guest main + * execution thread. + */ +static volatile uint64_t i_ucna_rcvd; +static volatile uint64_t i_ucna_addr; +static volatile uint64_t ucna_addr; +static volatile uint64_t ucna_addr2; + +struct thread_params { + struct kvm_vcpu *vcpu; + uint64_t *p_i_ucna_rcvd; + uint64_t *p_i_ucna_addr; + uint64_t *p_ucna_addr; + uint64_t *p_ucna_addr2; +}; + +static void verify_apic_base_addr(void) +{ + uint64_t msr = rdmsr(MSR_IA32_APICBASE); + uint64_t base = GET_APIC_BASE(msr); + + GUEST_ASSERT(base == APIC_DEFAULT_GPA); +} + +static void ucna_injection_guest_code(void) +{ + uint64_t ctl2; + verify_apic_base_addr(); + xapic_enable(); + + /* Sets up the interrupt vector and enables per-bank CMCI sigaling. */ + xapic_write_reg(APIC_LVTCMCI, CMCI_VECTOR | APIC_DM_FIXED); + ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); + + /* Enables interrupt in guest. */ + asm volatile("sti"); + + /* Let user space inject the first UCNA */ + GUEST_SYNC(SYNC_FIRST_UCNA); + + ucna_addr = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + + /* Disables the per-bank CMCI signaling. */ + ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 & ~MCI_CTL2_CMCI_EN); + + /* Let the user space inject the second UCNA */ + GUEST_SYNC(SYNC_SECOND_UCNA); + + ucna_addr2 = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + GUEST_DONE(); +} + +static void cmci_disabled_guest_code(void) +{ + uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); + + GUEST_DONE(); +} + +static void cmci_enabled_guest_code(void) +{ + uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_RESERVED_BIT); + + GUEST_DONE(); +} + +static void guest_cmci_handler(struct ex_regs *regs) +{ + i_ucna_rcvd++; + i_ucna_addr = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + xapic_write_reg(APIC_EOI, 0); +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + GUEST_SYNC(SYNC_GP); +} + +static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu) +{ + unsigned int exit_reason; + struct ucall uc; + + vcpu_run(vcpu); + + exit_reason = vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected."); + printf("vCPU received GP in guest.\n"); +} + +static void inject_ucna(struct kvm_vcpu *vcpu, uint64_t addr) { + /* + * A UCNA error is indicated with VAL=1, UC=1, PCC=0, S=0 and AR=0 in + * the IA32_MCi_STATUS register. + * MSCOD=1 (BIT[16] - MscodDataRdErr). + * MCACOD=0x0090 (Memory controller error format, channel 0) + */ + uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_MISCV | MCI_STATUS_ADDRV | 0x10090; + struct kvm_x86_mce mce = {}; + mce.status = status; + mce.mcg_status = 0; + /* + * MCM_ADDR_PHYS indicates the reported address is a physical address. + * Lowest 6 bits is the recoverable address LSB, i.e., the injected MCE + * is at 4KB granularity. + */ + mce.misc = (MCM_ADDR_PHYS << 6) | 0xc; + mce.addr = addr; + mce.bank = UCNA_BANK; + + vcpu_ioctl(vcpu, KVM_X86_SET_MCE, &mce); +} + +static void *run_ucna_injection(void *arg) +{ + struct thread_params *params = (struct thread_params *)arg; + struct ucall uc; + int old; + int r; + unsigned int exit_reason; + + r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); + TEST_ASSERT(r == 0, + "pthread_setcanceltype failed with errno=%d", + r); + + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA."); + + printf("Injecting first UCNA at %#x.\n", FIRST_UCNA_ADDR); + + inject_ucna(params->vcpu, FIRST_UCNA_ADDR); + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA."); + + printf("Injecting second UCNA at %#x.\n", SECOND_UCNA_ADDR); + + inject_ucna(params->vcpu, SECOND_UCNA_ADDR); + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) { + TEST_ASSERT(false, "vCPU assertion failure: %s.\n", + (const char *)uc.args[0]); + } + + return NULL; +} + +static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *params) +{ + struct kvm_vm *vm = vcpu->vm; + params->vcpu = vcpu; + params->p_i_ucna_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_rcvd); + params->p_i_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_addr); + params->p_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr); + params->p_ucna_addr2 = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr2); + + run_ucna_injection(params); + + TEST_ASSERT(*params->p_i_ucna_rcvd == 1, "Only first UCNA get signaled."); + TEST_ASSERT(*params->p_i_ucna_addr == FIRST_UCNA_ADDR, + "Only first UCNA reported addr get recorded via interrupt."); + TEST_ASSERT(*params->p_ucna_addr == FIRST_UCNA_ADDR, + "First injected UCNAs should get exposed via registers."); + TEST_ASSERT(*params->p_ucna_addr2 == SECOND_UCNA_ADDR, + "Second injected UCNAs should get exposed via registers."); + + printf("Test successful.\n" + "UCNA CMCI interrupts received: %ld\n" + "Last UCNA address received via CMCI: %lx\n" + "First UCNA address in vCPU thread: %lx\n" + "Second UCNA address in vCPU thread: %lx\n", + *params->p_i_ucna_rcvd, *params->p_i_ucna_addr, + *params->p_ucna_addr, *params->p_ucna_addr2); +} + +static void setup_mce_cap(struct kvm_vcpu *vcpu, bool enable_cmci_p) +{ + uint64_t mcg_caps = MCG_CTL_P | MCG_SER_P | MCG_LMCE_P | KVM_MAX_MCE_BANKS; + if (enable_cmci_p) + mcg_caps |= MCG_CMCI_P; + + mcg_caps &= supported_mcg_caps | MCG_CAP_BANKS_MASK; + vcpu_ioctl(vcpu, KVM_X86_SETUP_MCE, &mcg_caps); +} + +static struct kvm_vcpu *create_vcpu_with_mce_cap(struct kvm_vm *vm, uint32_t vcpuid, + bool enable_cmci_p, void *guest_code) +{ + struct kvm_vcpu *vcpu = vm_vcpu_add(vm, vcpuid, guest_code); + setup_mce_cap(vcpu, enable_cmci_p); + return vcpu; +} + +int main(int argc, char *argv[]) +{ + struct thread_params params; + struct kvm_vm *vm; + struct kvm_vcpu *ucna_vcpu; + struct kvm_vcpu *cmcidis_vcpu; + struct kvm_vcpu *cmci_vcpu; + + kvm_check_cap(KVM_CAP_MCE); + + vm = __vm_create(VM_MODE_DEFAULT, 3, 0); + + kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED, + &supported_mcg_caps); + + if (!(supported_mcg_caps & MCG_CMCI_P)) { + print_skip("MCG_CMCI_P is not supported"); + exit(KSFT_SKIP); + } + + ucna_vcpu = create_vcpu_with_mce_cap(vm, 0, true, ucna_injection_guest_code); + cmcidis_vcpu = create_vcpu_with_mce_cap(vm, 1, false, cmci_disabled_guest_code); + cmci_vcpu = create_vcpu_with_mce_cap(vm, 2, true, cmci_enabled_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(ucna_vcpu); + vcpu_init_descriptor_tables(cmcidis_vcpu); + vcpu_init_descriptor_tables(cmci_vcpu); + vm_install_exception_handler(vm, CMCI_VECTOR, guest_cmci_handler); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + + test_ucna_injection(ucna_vcpu, ¶ms); + run_vcpu_expect_gp(cmcidis_vcpu); + run_vcpu_expect_gp(cmci_vcpu); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c index e4bef2e05686..7316521428f8 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -10,8 +10,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 1 - static void guest_ins_port80(uint8_t *buffer, unsigned int count) { unsigned long end; @@ -52,31 +50,29 @@ static void guest_code(void) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int rc; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; memset(®s, 0, sizeof(regs)); while (1) { - rc = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - if (get_ucall(vm, VCPU_ID, &uc)) + if (get_ucall(vcpu, &uc)) break; TEST_ASSERT(run->io.port == 0x80, @@ -89,22 +85,20 @@ int main(int argc, char *argv[]) * scope from a testing perspective as it's not ABI in any way, * i.e. it really is abusing internal KVM knowledge. */ - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); if (regs.rcx == 2) regs.rcx = 1; if (regs.rcx == 3) regs.rcx = 8192; memset((void *)run + run->io.data_offset, 0xaa, 4096); - vcpu_regs_set(vm, VCPU_ID, ®s); + vcpu_regs_set(vcpu, ®s); } switch (uc.cmd) { case UCALL_DONE: break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx", - (const char *)uc.args[0], __FILE__, uc.args[1], - uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "argN+1 = 0x%lx, argN+2 = 0x%lx"); default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index e3e20e8848d0..a4f06370a245 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -17,7 +17,6 @@ #define KVM_FEP_LENGTH 5 static int fep_available = 1; -#define VCPU_ID 1 #define MSR_NON_EXISTENT 0x474f4f00 static u64 deny_bits = 0; @@ -395,31 +394,21 @@ static void guest_ud_handler(struct ex_regs *regs) regs->rip += KVM_FEP_LENGTH; } -static void run_guest(struct kvm_vm *vm) +static void check_for_guest_assert(struct kvm_vcpu *vcpu) { - int rc; - - rc = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); -} - -static void check_for_guest_assert(struct kvm_vm *vm) -{ - struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; - if (run->exit_reason == KVM_EXIT_IO && - get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + if (vcpu->run->exit_reason == KVM_EXIT_IO && + get_ucall(vcpu, &uc) == UCALL_ABORT) { + REPORT_GUEST_ASSERT(uc); } } -static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR, "Unexpected exit reason: %u (%s),\n", @@ -450,11 +439,11 @@ static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) } } -static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR, "Unexpected exit reason: %u (%s),\n", @@ -481,43 +470,43 @@ static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) } } -static void process_ucall_done(struct kvm_vm *vm) +static void process_ucall_done(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vm *vm) +static uint64_t process_ucall(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc = {}; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: break; case UCALL_ABORT: - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); break; case UCALL_DONE: - process_ucall_done(vm); + process_ucall_done(vcpu); break; default: TEST_ASSERT(false, "Unexpected ucall"); @@ -526,45 +515,43 @@ static uint64_t process_ucall(struct kvm_vm *vm) return uc.cmd; } -static void run_guest_then_process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +static void run_guest_then_process_rdmsr(struct kvm_vcpu *vcpu, + uint32_t msr_index) { - run_guest(vm); - process_rdmsr(vm, msr_index); + vcpu_run(vcpu); + process_rdmsr(vcpu, msr_index); } -static void run_guest_then_process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +static void run_guest_then_process_wrmsr(struct kvm_vcpu *vcpu, + uint32_t msr_index) { - run_guest(vm); - process_wrmsr(vm, msr_index); + vcpu_run(vcpu); + process_wrmsr(vcpu, msr_index); } -static uint64_t run_guest_then_process_ucall(struct kvm_vm *vm) +static uint64_t run_guest_then_process_ucall(struct kvm_vcpu *vcpu) { - run_guest(vm); - return process_ucall(vm); + vcpu_run(vcpu); + return process_ucall(vcpu); } -static void run_guest_then_process_ucall_done(struct kvm_vm *vm) +static void run_guest_then_process_ucall_done(struct kvm_vcpu *vcpu) { - run_guest(vm); - process_ucall_done(vm); + vcpu_run(vcpu); + process_ucall_done(vcpu); } -static void test_msr_filter_allow(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_filter_allow(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_filter_allow); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_allow); rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); @@ -572,43 +559,43 @@ static void test_msr_filter_allow(void) { vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); /* Process guest code userspace exits. */ - run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); - run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); - run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - run_guest(vm); + vcpu_run(vcpu); vm_install_exception_handler(vm, UD_VECTOR, NULL); - if (process_ucall(vm) != UCALL_DONE) { + if (process_ucall(vcpu) != UCALL_DONE) { vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler); /* Process emulated rdmsr and wrmsr instructions. */ - run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); - run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); - run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); /* Confirm the guest completed without issues. */ - run_guest_then_process_ucall_done(vm); + run_guest_then_process_ucall_done(vcpu); } else { printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n"); } @@ -616,16 +603,16 @@ static void test_msr_filter_allow(void) { kvm_vm_free(vm); } -static int handle_ucall(struct kvm_vm *vm) +static int handle_ucall(struct kvm_vcpu *vcpu) { struct ucall uc; - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("Guest assertion not met"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_SYNC: - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); + vm_ioctl(vcpu->vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); break; case UCALL_DONE: return 1; @@ -673,25 +660,21 @@ static void handle_wrmsr(struct kvm_run *run) } } -static void test_msr_filter_deny(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_filter_deny(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_filter_deny); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_deny); + run = vcpu->run; rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); @@ -700,9 +683,7 @@ static void test_msr_filter_deny(void) { vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_deny); while (1) { - rc = _vcpu_run(vm, VCPU_ID); - - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + vcpu_run(vcpu); switch (run->exit_reason) { case KVM_EXIT_X86_RDMSR: @@ -712,7 +693,7 @@ static void test_msr_filter_deny(void) { handle_wrmsr(run); break; case KVM_EXIT_IO: - if (handle_ucall(vm)) + if (handle_ucall(vcpu)) goto done; break; } @@ -726,31 +707,28 @@ done: kvm_vm_free(vm); } -static void test_msr_permission_bitmap(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_permission_bitmap(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_permission_bitmap); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_permission_bitmap); rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_fs); - run_guest_then_process_rdmsr(vm, MSR_FS_BASE); - TEST_ASSERT(run_guest_then_process_ucall(vm) == UCALL_SYNC, "Expected ucall state to be UCALL_SYNC."); + run_guest_then_process_rdmsr(vcpu, MSR_FS_BASE); + TEST_ASSERT(run_guest_then_process_ucall(vcpu) == UCALL_SYNC, + "Expected ucall state to be UCALL_SYNC."); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); - run_guest_then_process_rdmsr(vm, MSR_GS_BASE); - run_guest_then_process_ucall_done(vm); + run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); + run_guest_then_process_ucall_done(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index d438c4d3228a..5abecf06329e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -28,11 +28,6 @@ #include "kselftest.h" -#define VCPU_ID 0 - -/* The virtual machine object. */ -static struct kvm_vm *vm; - static void l2_guest_code(void) { /* Exit to L1 */ @@ -77,33 +72,29 @@ static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa) int main(int argc, char *argv[]) { unsigned long apic_access_addr = ~0ul; - unsigned int paddr_width; - unsigned int vaddr_width; vm_vaddr_t vmx_pages_gva; unsigned long high_gpa; struct vmx_pages *vmx; bool done = false; - nested_vmx_check_supported(); + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - kvm_get_cpu_address_width(&paddr_width, &vaddr_width); - high_gpa = (1ul << paddr_width) - getpagesize(); - if ((unsigned long)DEFAULT_GUEST_PHY_PAGES * getpagesize() > high_gpa) { - print_skip("No unbacked physical page available"); - exit(KSFT_SKIP); - } + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + high_gpa = (vm->max_gfn - 1) << vm->page_shift; vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); prepare_virtualize_apic_accesses(vmx, vm); - vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa); + vcpu_args_set(vcpu, 2, vmx_pages_gva, high_gpa); while (!done) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); if (apic_access_addr == high_gpa) { TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, @@ -121,10 +112,9 @@ int main(int argc, char *argv[]) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: apic_access_addr = uc.args[1]; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index edac8839e717..d79651b02740 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -18,15 +18,10 @@ #include "kselftest.h" -#define VCPU_ID 5 - enum { PORT_L0_EXIT = 0x2000, }; -/* The virtual machine object. */ -static struct kvm_vm *vm; - static void l2_guest_code(void) { /* Exit to L0 */ @@ -53,20 +48,22 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, @@ -75,9 +72,9 @@ int main(int argc, char *argv[]) if (run->io.port == PORT_L0_EXIT) break; - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ default: TEST_FAIL("Unknown ucall %lu", uc.cmd); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 68f26a8b4f42..2d8c23d639f7 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -17,8 +17,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 1 - /* The memory slot index to track dirty pages */ #define TEST_MEM_SLOT_INDEX 1 #define TEST_MEM_PAGES 3 @@ -73,18 +71,19 @@ int main(int argc, char *argv[]) unsigned long *bmap; uint64_t *host_test_mem; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; bool done = false; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); - run = vcpu_state(vm, VCPU_ID); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + run = vcpu->run; /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, @@ -116,16 +115,15 @@ int main(int argc, char *argv[]) while (!done) { memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096); - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: /* diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index 27a850f3d7ce..2641b286b4ed 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -10,10 +10,6 @@ #include "kselftest.h" -#define VCPU_ID 0 - -static struct kvm_vm *vm; - static void guest_ud_handler(struct ex_regs *regs) { /* Loop on the ud2 until guest state is made invalid. */ @@ -24,11 +20,11 @@ static void guest_code(void) asm volatile("ud2"); } -static void __run_vcpu_with_invalid_state(void) +static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n", @@ -38,15 +34,15 @@ static void __run_vcpu_with_invalid_state(void) run->emulation_failure.suberror); } -static void run_vcpu_with_invalid_state(void) +static void run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu) { /* * Always run twice to verify KVM handles the case where _KVM_ queues * an exception with invalid state and then exits to userspace, i.e. * that KVM doesn't explode if userspace ignores the initial error. */ - __run_vcpu_with_invalid_state(); - __run_vcpu_with_invalid_state(); + __run_vcpu_with_invalid_state(vcpu); + __run_vcpu_with_invalid_state(vcpu); } static void set_timer(void) @@ -59,33 +55,43 @@ static void set_timer(void) ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0); } -static void set_or_clear_invalid_guest_state(bool set) +static void set_or_clear_invalid_guest_state(struct kvm_vcpu *vcpu, bool set) { static struct kvm_sregs sregs; if (!sregs.cr0) - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.tr.unusable = !!set; - vcpu_sregs_set(vm, VCPU_ID, &sregs); + vcpu_sregs_set(vcpu, &sregs); +} + +static void set_invalid_guest_state(struct kvm_vcpu *vcpu) +{ + set_or_clear_invalid_guest_state(vcpu, true); } -static void set_invalid_guest_state(void) +static void clear_invalid_guest_state(struct kvm_vcpu *vcpu) { - set_or_clear_invalid_guest_state(true); + set_or_clear_invalid_guest_state(vcpu, false); } -static void clear_invalid_guest_state(void) +static struct kvm_vcpu *get_set_sigalrm_vcpu(struct kvm_vcpu *__vcpu) { - set_or_clear_invalid_guest_state(false); + static struct kvm_vcpu *vcpu = NULL; + + if (__vcpu) + vcpu = __vcpu; + return vcpu; } static void sigalrm_handler(int sig) { + struct kvm_vcpu *vcpu = get_set_sigalrm_vcpu(NULL); struct kvm_vcpu_events events; TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig); - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); /* * If an exception is pending, attempt KVM_RUN with invalid guest, @@ -93,8 +99,8 @@ static void sigalrm_handler(int sig) * between KVM queueing an exception and re-entering the guest. */ if (events.exception.pending) { - set_invalid_guest_state(); - run_vcpu_with_invalid_state(); + set_invalid_guest_state(vcpu); + run_vcpu_with_invalid_state(vcpu); } else { set_timer(); } @@ -102,15 +108,17 @@ static void sigalrm_handler(int sig) int main(int argc, char *argv[]) { - if (!is_intel_cpu() || vm_is_unrestricted_guest(NULL)) { - print_skip("Must be run with kvm_intel.unrestricted_guest=0"); - exit(KSFT_SKIP); - } + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); - vm = vm_create_default(VCPU_ID, 0, (void *)guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + get_set_sigalrm_vcpu(vcpu); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); @@ -119,8 +127,8 @@ int main(int argc, char *argv[]) * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support * emulating invalid guest state for L2. */ - set_invalid_guest_state(); - run_vcpu_with_invalid_state(); + set_invalid_guest_state(vcpu); + run_vcpu_with_invalid_state(vcpu); /* * Verify KVM also handles the case where userspace gains control while @@ -129,11 +137,11 @@ int main(int argc, char *argv[]) * guest with invalid state when the handler interrupts KVM with an * exception pending. */ - clear_invalid_guest_state(); + clear_invalid_guest_state(vcpu); TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR, "Failed to register SIGALRM handler, errno = %d (%s)", errno, strerror(errno)); set_timer(); - run_vcpu_with_invalid_state(); + run_vcpu_with_invalid_state(vcpu); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c index 489fbed4ca6f..6bfb4bb471ca 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c @@ -9,7 +9,6 @@ #include "kselftest.h" -#define VCPU_ID 0 #define ARBITRARY_IO_PORT 0x2000 static struct kvm_vm *vm; @@ -55,20 +54,21 @@ int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct ucall uc; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; /* * The first exit to L0 userspace should be an I/O access from L2. @@ -88,17 +88,17 @@ int main(int argc, char *argv[]) * emulating invalid guest state for L2. */ memset(&sregs, 0, sizeof(sregs)); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.tr.unusable = 1; - vcpu_sregs_set(vm, VCPU_ID, &sregs); + vcpu_sregs_set(vcpu, &sregs); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_DONE: break; case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); default: TEST_FAIL("Unexpected ucall: %lu", uc.cmd); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c new file mode 100644 index 000000000000..322d561b4260 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VMX control MSR test + * + * Copyright (C) 2022 Google LLC. + * + * Tests for KVM ownership of bits in the VMX entry/exit control MSRs. Checks + * that KVM will set owned bits where appropriate, and will not if + * KVM_X86_QUIRK_TWEAK_VMX_CTRL_MSRS is disabled. + */ +#include <linux/bitmap.h> +#include "kvm_util.h" +#include "vmx.h" + +static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, + uint64_t mask) +{ + uint64_t val = vcpu_get_msr(vcpu, msr_index); + uint64_t bit; + + mask &= val; + + for_each_set_bit(bit, &mask, 64) { + vcpu_set_msr(vcpu, msr_index, val & ~BIT_ULL(bit)); + vcpu_set_msr(vcpu, msr_index, val); + } +} + +static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, + uint64_t mask) +{ + uint64_t val = vcpu_get_msr(vcpu, msr_index); + uint64_t bit; + + mask = ~mask | val; + + for_each_clear_bit(bit, &mask, 64) { + vcpu_set_msr(vcpu, msr_index, val | BIT_ULL(bit)); + vcpu_set_msr(vcpu, msr_index, val); + } +} + +static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index) +{ + vmx_fixed0_msr_test(vcpu, msr_index, GENMASK_ULL(31, 0)); + vmx_fixed1_msr_test(vcpu, msr_index, GENMASK_ULL(63, 32)); +} + +static void vmx_save_restore_msrs_test(struct kvm_vcpu *vcpu) +{ + vcpu_set_msr(vcpu, MSR_IA32_VMX_VMCS_ENUM, 0); + vcpu_set_msr(vcpu, MSR_IA32_VMX_VMCS_ENUM, -1ull); + + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_BASIC, + BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55)); + + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_MISC, + BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | + BIT_ULL(15) | BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30)); + + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2); + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_EPT_VPID_CAP, -1ull); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_PINBASED_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_EXIT_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_ENTRY_CTLS); + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_VMFUNC, -1ull); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + /* No need to actually do KVM_RUN, thus no guest code. */ + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + vmx_save_restore_msrs_test(vcpu); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c index 280c01fd2412..465a9434d61c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -15,9 +15,6 @@ #include "vmx.h" #include "kselftest.h" - -#define VCPU_ID 0 - /* L2 is scaled up (from L1's perspective) by this factor */ #define L2_SCALE_FACTOR 4ULL @@ -119,14 +116,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } -static void tsc_scaling_check_supported(void) -{ - if (!kvm_check_cap(KVM_CAP_TSC_CONTROL)) { - print_skip("TSC scaling not supported by the HW"); - exit(KSFT_SKIP); - } -} - static void stable_tsc_check_supported(void) { FILE *fp; @@ -150,6 +139,7 @@ skip_test: int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; vm_vaddr_t vmx_pages_gva; @@ -160,8 +150,8 @@ int main(int argc, char *argv[]) uint64_t l1_tsc_freq = 0; uint64_t l2_tsc_freq = 0; - nested_vmx_check_supported(); - tsc_scaling_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL)); stable_tsc_check_supported(); /* @@ -182,30 +172,29 @@ int main(int argc, char *argv[]) l0_tsc_freq = tsc_end - tsc_start; printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); - tsc_khz = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_TSC_KHZ, NULL); + tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL); TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed"); /* scale down L1's TSC frequency */ - vcpu_ioctl(vm, VCPU_ID, KVM_SET_TSC_KHZ, - (void *) (tsc_khz / l1_scale_factor)); + vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *) (tsc_khz / l1_scale_factor)); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *) uc.args[0]); + REPORT_GUEST_ASSERT(uc); case UCALL_SYNC: switch (uc.args[0]) { case USLEEP: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 97b7fd4a9a3d..069589c52f41 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -17,9 +17,6 @@ #include "kvm_util.h" #include "vmx.h" -#define VCPU_ID 0 - -#define X86_FEATURE_PDCM (1<<15) #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f @@ -56,60 +53,56 @@ static void guest_code(void) int main(int argc, char *argv[]) { - struct kvm_cpuid2 *cpuid; - struct kvm_cpuid_entry2 *entry_1_0; - struct kvm_cpuid_entry2 *entry_a_0; - bool pdcm_supported = false; + const struct kvm_cpuid_entry2 *entry_a_0; struct kvm_vm *vm; + struct kvm_vcpu *vcpu; int ret; union cpuid10_eax eax; union perf_capabilities host_cap; + uint64_t val; host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - cpuid = kvm_get_supported_cpuid(); - - if (kvm_get_cpuid_max_basic() >= 0xa) { - entry_1_0 = kvm_get_supported_cpuid_index(1, 0); - entry_a_0 = kvm_get_supported_cpuid_index(0xa, 0); - pdcm_supported = entry_1_0 && !!(entry_1_0->ecx & X86_FEATURE_PDCM); - eax.full = entry_a_0->eax; - } - if (!pdcm_supported) { - print_skip("MSR_IA32_PERF_CAPABILITIES is not supported by the vCPU"); - exit(KSFT_SKIP); - } - if (!eax.split.version_id) { - print_skip("PMU is not supported by the vCPU"); - exit(KSFT_SKIP); - } + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); + + TEST_REQUIRE(kvm_get_cpuid_max_basic() >= 0xa); + entry_a_0 = kvm_get_supported_cpuid_entry(0xa); + + eax.full = entry_a_0->eax; + __TEST_REQUIRE(eax.split.version_id, "PMU is not supported by the vCPU"); /* testcase 1, set capabilities when we have PDCM bit */ - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); /* check capabilities can be retrieved with KVM_GET_MSR */ - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); /* check whatever we write with KVM_SET_MSR is _not_ modified */ - vcpu_run(vm, VCPU_ID); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + vcpu_run(vcpu); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); /* testcase 2, check valid LBR formats are accepted */ - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); - - /* testcase 3, check invalid LBR format is rejected */ - /* Note, on Arch LBR capable platforms, LBR_FMT in perf capability msr is 0x3f, - * to avoid the failure, use a true invalid format 0x30 for the test. */ - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0x30); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); + + /* + * Testcase 3, check that an "invalid" LBR format is rejected. Only an + * exact match of the host's format (and 0/disabled) is allowed. + */ + for (val = 1; val <= PMU_CAP_LBR_FMT; val++) { + if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) + continue; + + ret = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); + TEST_ASSERT(!ret, "Bad LBR FMT = 0x%lx didn't fail", val); + } printf("Completed perf capability tests.\n"); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index ff92e25b6f1e..0efdc05969a5 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -22,7 +22,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 5 #define PREEMPTION_TIMER_VALUE 100000000ull #define PREEMPTION_TIMER_VALUE_THRESHOLD1 80000000ull @@ -159,6 +158,7 @@ int main(int argc, char *argv[]) struct kvm_regs regs1, regs2; struct kvm_vm *vm; struct kvm_run *run; + struct kvm_vcpu *vcpu; struct kvm_x86_state *state; struct ucall uc; int stage; @@ -167,33 +167,29 @@ int main(int argc, char *argv[]) * AMD currently does not implement any VMX features, so for now we * just early out. */ - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { - print_skip("KVM_CAP_NESTED_STATE not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -232,22 +228,20 @@ int main(int argc, char *argv[]) stage, uc.args[4], uc.args[5]); } - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®s2); TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 5827b9bae468..41ea7028a1f8 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -23,38 +23,37 @@ * changes this should be updated. */ #define VMCS12_REVISION 0x11e57ed0 -#define VCPU_ID 5 bool have_evmcs; -void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state) +void test_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - vcpu_nested_state_set(vm, VCPU_ID, state, false); + vcpu_nested_state_set(vcpu, state); } -void test_nested_state_expect_errno(struct kvm_vm *vm, +void test_nested_state_expect_errno(struct kvm_vcpu *vcpu, struct kvm_nested_state *state, int expected_errno) { int rv; - rv = vcpu_nested_state_set(vm, VCPU_ID, state, true); + rv = __vcpu_nested_state_set(vcpu, state); TEST_ASSERT(rv == -1 && errno == expected_errno, "Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)", strerror(expected_errno), expected_errno, rv, strerror(errno), errno); } -void test_nested_state_expect_einval(struct kvm_vm *vm, +void test_nested_state_expect_einval(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - test_nested_state_expect_errno(vm, state, EINVAL); + test_nested_state_expect_errno(vcpu, state, EINVAL); } -void test_nested_state_expect_efault(struct kvm_vm *vm, +void test_nested_state_expect_efault(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - test_nested_state_expect_errno(vm, state, EFAULT); + test_nested_state_expect_errno(vcpu, state, EFAULT); } void set_revision_id_for_vmcs12(struct kvm_nested_state *state, @@ -86,7 +85,7 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size) set_revision_id_for_vmcs12(state, VMCS12_REVISION); } -void test_vmx_nested_state(struct kvm_vm *vm) +void test_vmx_nested_state(struct kvm_vcpu *vcpu) { /* Add a page for VMCS12. */ const int state_sz = sizeof(struct kvm_nested_state) + getpagesize(); @@ -96,14 +95,14 @@ void test_vmx_nested_state(struct kvm_vm *vm) /* The format must be set to 0. 0 for VMX, 1 for SVM. */ set_default_vmx_state(state, state_sz); state->format = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * We cannot virtualize anything if the guest does not have VMX * enabled. */ set_default_vmx_state(state, state_sz); - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * We cannot virtualize anything if the guest does not have VMX @@ -112,17 +111,17 @@ void test_vmx_nested_state(struct kvm_vm *vm) */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->hdr.vmx.vmcs12_pa = -1ull; state->flags = KVM_STATE_NESTED_EVMCS; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->flags = 0; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* Enable VMX in the guest CPUID. */ - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_VMX); /* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without @@ -133,34 +132,34 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->flags &= KVM_STATE_NESTED_EVMCS; if (have_evmcs) { - test_nested_state_expect_einval(vm, state); - vcpu_enable_evmcs(vm, VCPU_ID); + test_nested_state_expect_einval(vcpu, state); + vcpu_enable_evmcs(vcpu); } - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */ state->hdr.vmx.smm.flags = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* Invalid flags are rejected. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.flags = ~0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->flags = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* It is invalid to have vmxon_pa set to a non-page aligned address. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * It is invalid to have KVM_STATE_NESTED_SMM_GUEST_MODE and @@ -170,7 +169,7 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->flags = KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING; state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * It is invalid to have any of the SMM flags set besides: @@ -180,13 +179,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->hdr.vmx.smm.flags = ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON); - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* Outside SMM, SMM flags must be zero. */ set_default_vmx_state(state, state_sz); state->flags = 0; state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * Size must be large enough to fit kvm_nested_state and vmcs12 @@ -195,13 +194,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->size = sizeof(*state); state->flags = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); set_default_vmx_state(state, state_sz); state->size = sizeof(*state); state->flags = 0; state->hdr.vmx.vmcs12_pa = -1; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* * KVM_SET_NESTED_STATE succeeds with invalid VMCS @@ -209,7 +208,7 @@ void test_vmx_nested_state(struct kvm_vm *vm) */ set_default_vmx_state(state, state_sz); state->flags = 0; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* Invalid flags are rejected, even if no VMCS loaded. */ set_default_vmx_state(state, state_sz); @@ -217,13 +216,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->flags = 0; state->hdr.vmx.vmcs12_pa = -1; state->hdr.vmx.flags = ~0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = 0; state->hdr.vmx.vmcs12_pa = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * Test that if we leave nesting the state reflects that when we get @@ -233,8 +232,8 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; state->flags = 0; - test_nested_state(vm, state); - vcpu_nested_state_get(vm, VCPU_ID, state); + test_nested_state(vcpu, state); + vcpu_nested_state_get(vcpu, state); TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz, "Size must be between %ld and %d. The size returned was %d.", sizeof(*state), state_sz, state->size); @@ -244,54 +243,36 @@ void test_vmx_nested_state(struct kvm_vm *vm) free(state); } -void disable_vmx(struct kvm_vm *vm) -{ - struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid(); - int i; - - for (i = 0; i < cpuid->nent; ++i) - if (cpuid->entries[i].function == 1 && - cpuid->entries[i].index == 0) - break; - TEST_ASSERT(i != cpuid->nent, "CPUID function 1 not found"); - - cpuid->entries[i].ecx &= ~CPUID_VMX; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - cpuid->entries[i].ecx |= CPUID_VMX; -} - int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_nested_state state; + struct kvm_vcpu *vcpu; have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); - if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { - print_skip("KVM_CAP_NESTED_STATE not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); /* * AMD currently does not implement set_nested_state, so for now we * just early out. */ - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, 0); + vm = vm_create_with_one_vcpu(&vcpu, NULL); /* * First run tests with VMX disabled to check error handling. */ - disable_vmx(vm); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_VMX); /* Passing a NULL kvm_nested_state causes a EFAULT. */ - test_nested_state_expect_efault(vm, NULL); + test_nested_state_expect_efault(vcpu, NULL); /* 'size' cannot be smaller than sizeof(kvm_nested_state). */ set_default_state(&state); state.size = 0; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); /* * Setting the flags 0xf fails the flags check. The only flags that @@ -302,7 +283,7 @@ int main(int argc, char *argv[]) */ set_default_state(&state); state.flags = 0xf; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); /* * If KVM_STATE_NESTED_RUN_PENDING is set then @@ -310,9 +291,9 @@ int main(int argc, char *argv[]) */ set_default_state(&state); state.flags = KVM_STATE_NESTED_RUN_PENDING; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); - test_vmx_nested_state(vm); + test_vmx_nested_state(vcpu); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 19b35c607dc6..5943187e8594 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -32,8 +32,6 @@ #define MSR_IA32_TSC_ADJUST 0x3b #endif -#define VCPU_ID 5 - #define TSC_ADJUST_VALUE (1ll << 32) #define TSC_OFFSET_VALUE -(1ll << 48) @@ -127,28 +125,29 @@ static void report(int64_t val) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; + struct kvm_vcpu *vcpu; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, (void *) l1_guest_code); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: report(uc.args[1]); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index afbbc40df884..3d272d7f961e 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -39,9 +39,6 @@ /* Default delay between migrate_pages calls (microseconds) */ #define DEFAULT_DELAY_USECS 500000 -#define HALTER_VCPU_ID 0 -#define SENDER_VCPU_ID 1 - /* * Vector for IPI from sender vCPU to halting vCPU. * Value is arbitrary and was chosen for the alternating bit pattern. Any @@ -79,8 +76,7 @@ struct test_data_page { struct thread_params { struct test_data_page *data; - struct kvm_vm *vm; - uint32_t vcpu_id; + struct kvm_vcpu *vcpu; uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ }; @@ -198,6 +194,7 @@ static void sender_guest_code(struct test_data_page *data) static void *vcpu_thread(void *arg) { struct thread_params *params = (struct thread_params *)arg; + struct kvm_vcpu *vcpu = params->vcpu; struct ucall uc; int old; int r; @@ -206,17 +203,17 @@ static void *vcpu_thread(void *arg) r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); TEST_ASSERT(r == 0, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d", - params->vcpu_id, r); + vcpu->id, r); - fprintf(stderr, "vCPU thread running vCPU %u\n", params->vcpu_id); - vcpu_run(params->vm, params->vcpu_id); - exit_reason = vcpu_state(params->vm, params->vcpu_id)->exit_reason; + fprintf(stderr, "vCPU thread running vCPU %u\n", vcpu->id); + vcpu_run(vcpu); + exit_reason = vcpu->run->exit_reason; TEST_ASSERT(exit_reason == KVM_EXIT_IO, "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", - params->vcpu_id, exit_reason, exit_reason_str(exit_reason)); + vcpu->id, exit_reason, exit_reason_str(exit_reason)); - if (get_ucall(params->vm, params->vcpu_id, &uc) == UCALL_ABORT) { + if (get_ucall(vcpu, &uc) == UCALL_ABORT) { TEST_ASSERT(false, "vCPU %u exited with error: %s.\n" "Sending vCPU sent %lu IPIs to halting vCPU\n" @@ -224,7 +221,7 @@ static void *vcpu_thread(void *arg) "Halter TPR=%#x PPR=%#x LVR=%#x\n" "Migrations attempted: %lu\n" "Migrations completed: %lu\n", - params->vcpu_id, (const char *)uc.args[0], + vcpu->id, (const char *)uc.args[0], params->data->ipis_sent, params->data->hlt_count, params->data->wake_count, *params->pipis_rcvd, params->data->halter_tpr, @@ -236,7 +233,7 @@ static void *vcpu_thread(void *arg) return NULL; } -static void cancel_join_vcpu_thread(pthread_t thread, uint32_t vcpu_id) +static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) { void *retval; int r; @@ -244,12 +241,12 @@ static void cancel_join_vcpu_thread(pthread_t thread, uint32_t vcpu_id) r = pthread_cancel(thread); TEST_ASSERT(r == 0, "pthread_cancel on vcpu_id=%d failed with errno=%d", - vcpu_id, r); + vcpu->id, r); r = pthread_join(thread, &retval); TEST_ASSERT(r == 0, "pthread_join on vcpu_id=%d failed with errno=%d", - vcpu_id, r); + vcpu->id, r); TEST_ASSERT(retval == PTHREAD_CANCELED, "expected retval=%p, got %p", PTHREAD_CANCELED, retval); @@ -415,34 +412,30 @@ int main(int argc, char *argv[]) if (delay_usecs <= 0) delay_usecs = DEFAULT_DELAY_USECS; - vm = vm_create_default(HALTER_VCPU_ID, 0, halter_guest_code); - params[0].vm = vm; - params[1].vm = vm; + vm = vm_create_with_one_vcpu(¶ms[0].vcpu, halter_guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, HALTER_VCPU_ID); + vcpu_init_descriptor_tables(params[0].vcpu); vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); - vm_vcpu_add_default(vm, SENDER_VCPU_ID, sender_guest_code); + params[1].vcpu = vm_vcpu_add(vm, 1, sender_guest_code); test_data_page_vaddr = vm_vaddr_alloc_page(vm); - data = - (struct test_data_page *)addr_gva2hva(vm, test_data_page_vaddr); + data = addr_gva2hva(vm, test_data_page_vaddr); memset(data, 0, sizeof(*data)); params[0].data = data; params[1].data = data; - vcpu_args_set(vm, HALTER_VCPU_ID, 1, test_data_page_vaddr); - vcpu_args_set(vm, SENDER_VCPU_ID, 1, test_data_page_vaddr); + vcpu_args_set(params[0].vcpu, 1, test_data_page_vaddr); + vcpu_args_set(params[1].vcpu, 1, test_data_page_vaddr); pipis_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ipis_rcvd); params[0].pipis_rcvd = pipis_rcvd; params[1].pipis_rcvd = pipis_rcvd; /* Start halter vCPU thread and wait for it to execute first HLT. */ - params[0].vcpu_id = HALTER_VCPU_ID; r = pthread_create(&threads[0], NULL, vcpu_thread, ¶ms[0]); TEST_ASSERT(r == 0, "pthread_create halter failed errno=%d", errno); @@ -462,7 +455,6 @@ int main(int argc, char *argv[]) "Halter vCPU thread reported its APIC ID: %u after %d seconds.\n", data->halter_apic_id, wait_secs); - params[1].vcpu_id = SENDER_VCPU_ID; r = pthread_create(&threads[1], NULL, vcpu_thread, ¶ms[1]); TEST_ASSERT(r == 0, "pthread_create sender failed errno=%d", errno); @@ -478,8 +470,8 @@ int main(int argc, char *argv[]) /* * Cancel threads and wait for them to stop. */ - cancel_join_vcpu_thread(threads[0], HALTER_VCPU_ID); - cancel_join_vcpu_thread(threads[1], SENDER_VCPU_ID); + cancel_join_vcpu_thread(threads[0], params[0].vcpu); + cancel_join_vcpu_thread(threads[1], params[1].vcpu); fprintf(stderr, "Test successful after running for %d seconds.\n" diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 0792334ba243..6f7a5ef66718 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -11,8 +11,8 @@ #include "processor.h" #include "test_util.h" -struct kvm_vcpu { - uint32_t id; +struct xapic_vcpu { + struct kvm_vcpu *vcpu; bool is_x2apic; }; @@ -47,8 +47,9 @@ static void x2apic_guest_code(void) } while (1); } -static void ____test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +static void ____test_icr(struct xapic_vcpu *x, uint64_t val) { + struct kvm_vcpu *vcpu = x->vcpu; struct kvm_lapic_state xapic; struct ucall uc; uint64_t icr; @@ -58,40 +59,55 @@ static void ____test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) * all bits are valid and should not be modified by KVM (ignoring the * fact that vectors 0-15 are technically illegal). */ - vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); *((u32 *)&xapic.regs[APIC_IRR]) = val; *((u32 *)&xapic.regs[APIC_IRR + 0x10]) = val >> 32; - vcpu_ioctl(vm, vcpu->id, KVM_SET_LAPIC, &xapic); + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &xapic); - vcpu_run(vm, vcpu->id); - ASSERT_EQ(get_ucall(vm, vcpu->id, &uc), UCALL_SYNC); + vcpu_run(vcpu); + ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); ASSERT_EQ(uc.args[1], val); - vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; - if (!vcpu->is_x2apic) + if (!x->is_x2apic) { val &= (-1u | (0xffull << (32 + 24))); - ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); + ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); + } else { + ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + } } -static void __test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +#define X2APIC_RSVED_BITS_MASK (GENMASK_ULL(31,20) | \ + GENMASK_ULL(17,16) | \ + GENMASK_ULL(13,13)) + +static void __test_icr(struct xapic_vcpu *x, uint64_t val) { - ____test_icr(vm, vcpu, val | APIC_ICR_BUSY); - ____test_icr(vm, vcpu, val & ~(u64)APIC_ICR_BUSY); + if (x->is_x2apic) { + /* Hardware writing vICR register requires reserved bits 31:20, + * 17:16 and 13 kept as zero to avoid #GP exception. Data value + * written to vICR should mask out those bits above. + */ + val &= ~X2APIC_RSVED_BITS_MASK; + } + ____test_icr(x, val | APIC_ICR_BUSY); + ____test_icr(x, val & ~(u64)APIC_ICR_BUSY); } -static void test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void test_icr(struct xapic_vcpu *x) { + struct kvm_vcpu *vcpu = x->vcpu; uint64_t icr, i, j; icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; for (i = 0; i <= 0xff; i++) - __test_icr(vm, vcpu, icr | i); + __test_icr(x, icr | i); icr = APIC_INT_ASSERT | APIC_DM_FIXED; for (i = 0; i <= 0xff; i++) - __test_icr(vm, vcpu, icr | i); + __test_icr(x, icr | i); /* * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of @@ -100,32 +116,30 @@ static void test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu) icr = APIC_INT_ASSERT | 0xff; for (i = vcpu->id + 1; i < 0xff; i++) { for (j = 0; j < 8; j++) - __test_icr(vm, vcpu, i << (32 + 24) | APIC_INT_ASSERT | (j << 8)); + __test_icr(x, i << (32 + 24) | icr | (j << 8)); } /* And again with a shorthand destination for all types of IPIs. */ icr = APIC_DEST_ALLBUT | APIC_INT_ASSERT; for (i = 0; i < 8; i++) - __test_icr(vm, vcpu, icr | (i << 8)); + __test_icr(x, icr | (i << 8)); /* And a few garbage value, just make sure it's an IRQ (blocked). */ - __test_icr(vm, vcpu, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK); - __test_icr(vm, vcpu, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK); - __test_icr(vm, vcpu, -1ull & ~APIC_DM_FIXED_MASK); + __test_icr(x, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK); + __test_icr(x, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK); + __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); } int main(int argc, char *argv[]) { - struct kvm_vcpu vcpu = { - .id = 0, + struct xapic_vcpu x = { + .vcpu = NULL, .is_x2apic = true, }; - struct kvm_cpuid2 *cpuid; struct kvm_vm *vm; - int i; - vm = vm_create_default(vcpu.id, 0, x2apic_guest_code); - test_icr(vm, &vcpu); + vm = vm_create_with_one_vcpu(&x.vcpu, x2apic_guest_code); + test_icr(&x); kvm_vm_free(vm); /* @@ -133,18 +147,12 @@ int main(int argc, char *argv[]) * the guest in order to test AVIC. KVM disallows changing CPUID after * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC. */ - vm = vm_create_default(vcpu.id, 0, xapic_guest_code); - vcpu.is_x2apic = false; + vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code); + x.is_x2apic = false; - cpuid = vcpu_get_cpuid(vm, vcpu.id); - for (i = 0; i < cpuid->nent; i++) { - if (cpuid->entries[i].function == 1) - break; - } - cpuid->entries[i].ecx &= ~BIT(21); - vcpu_set_cpuid(vm, vcpu.id, cpuid); + vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); - test_icr(vm, &vcpu); + test_icr(&x); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 7a51bb648fbb..8a5cb800f50e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -18,8 +18,6 @@ #include <sys/eventfd.h> -#define VCPU_ID 5 - #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 @@ -42,8 +40,6 @@ #define EVTCHN_TEST2 66 #define EVTCHN_TIMER 13 -static struct kvm_vm *vm; - #define XEN_HYPERCALL_MSR 0x40000000 #define MIN_STEAL_TIME 50000 @@ -344,29 +340,29 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) else return 0; } -struct vcpu_info *vinfo; + +static struct vcpu_info *vinfo; +static struct kvm_vcpu *vcpu; static void handle_alrm(int sig) { if (vinfo) printf("evtchn_upcall_pending 0x%x\n", vinfo->evtchn_upcall_pending); - vcpu_dump(stdout, vm, VCPU_ID, 0); + vcpu_dump(stdout, vcpu, 0); TEST_FAIL("IRQ delivery timed out"); } int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + struct kvm_vm *vm; bool verbose; verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || !strncmp(argv[1], "--verbose", 10)); int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); - if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { - print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO); bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); @@ -374,8 +370,7 @@ int main(int argc, char *argv[]) clock_gettime(CLOCK_REALTIME, &min_ts); - vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Map a region for the shared_info page */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, @@ -425,13 +420,13 @@ int main(int argc, char *argv[]) .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vi); struct kvm_xen_vcpu_attr pvclock = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO, .u.gpa = PVTIME_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &pvclock); struct kvm_xen_hvm_attr vec = { .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR, @@ -440,7 +435,7 @@ int main(int argc, char *argv[]) vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); if (do_runstate_tests) { @@ -448,7 +443,7 @@ int main(int argc, char *argv[]) .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, .u.gpa = RUNSTATE_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &st); } int irq_fd[2] = { -1, -1 }; @@ -468,16 +463,16 @@ int main(int argc, char *argv[]) irq_routes.entries[0].gsi = 32; irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; irq_routes.entries[0].u.xen_evtchn.port = EVTCHN_TEST1; - irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[0].u.xen_evtchn.vcpu = vcpu->id; irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; irq_routes.entries[1].gsi = 33; irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN; irq_routes.entries[1].u.xen_evtchn.port = EVTCHN_TEST2; - irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[1].u.xen_evtchn.vcpu = vcpu->id; irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; - vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes); + vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes.info); struct kvm_irqfd ifd = { }; @@ -508,14 +503,14 @@ int main(int argc, char *argv[]) .u.evtchn.type = EVTCHNSTAT_interdomain, .u.evtchn.flags = 0, .u.evtchn.deliver.port.port = EVTCHN_TEST1, - .u.evtchn.deliver.port.vcpu = VCPU_ID + 1, + .u.evtchn.deliver.port.vcpu = vcpu->id + 1, .u.evtchn.deliver.port.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL, }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); /* Test migration to a different vCPU */ inj.u.evtchn.flags = KVM_XEN_EVTCHN_UPDATE; - inj.u.evtchn.deliver.port.vcpu = VCPU_ID; + inj.u.evtchn.deliver.port.vcpu = vcpu->id; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); inj.u.evtchn.send_port = 197; @@ -524,7 +519,7 @@ int main(int argc, char *argv[]) inj.u.evtchn.flags = 0; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); } vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; @@ -535,19 +530,19 @@ int main(int argc, char *argv[]) bool evtchn_irq_expected = false; for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: { struct kvm_xen_vcpu_attr rst; @@ -574,7 +569,7 @@ int main(int argc, char *argv[]) printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; case 4: @@ -589,7 +584,7 @@ int main(int argc, char *argv[]) 0x6b6b - rs->time[RUNSTATE_offline]; rst.u.runstate.time_runnable = -rst.u.runstate.time_blocked - rst.u.runstate.time_offline; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; case 5: @@ -601,7 +596,7 @@ int main(int argc, char *argv[]) rst.u.runstate.state_entry_time = 0x6b6b + 0x5a; rst.u.runstate.time_blocked = 0x6b6b; rst.u.runstate.time_offline = 0x5a; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; case 6: @@ -660,7 +655,7 @@ int main(int argc, char *argv[]) struct kvm_irq_routing_xen_evtchn e; e.port = EVTCHN_TEST2; - e.vcpu = VCPU_ID; + e.vcpu = vcpu->id; e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &e); @@ -702,7 +697,7 @@ int main(int argc, char *argv[]) case 14: memset(&tmr, 0, sizeof(tmr)); tmr.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); TEST_ASSERT(tmr.u.timer.port == EVTCHN_TIMER, "Timer port not returned"); TEST_ASSERT(tmr.u.timer.priority == KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL, @@ -721,8 +716,8 @@ int main(int argc, char *argv[]) if (verbose) printf("Testing restored oneshot timer\n"); - tmr.u.timer.expires_ns = rs->state_entry_time + 100000000, - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr); + tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); evtchn_irq_expected = true; alarm(1); break; @@ -748,8 +743,8 @@ int main(int argc, char *argv[]) if (verbose) printf("Testing SCHEDOP_poll wake on masked event\n"); - tmr.u.timer.expires_ns = rs->state_entry_time + 100000000, - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr); + tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); alarm(1); break; @@ -760,11 +755,11 @@ int main(int argc, char *argv[]) evtchn_irq_expected = true; tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); /* Read it back and check the pending time is reported correctly */ tmr.u.timer.expires_ns = 0; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); TEST_ASSERT(tmr.u.timer.expires_ns == rs->state_entry_time + 100000000, "Timer not reported pending"); alarm(1); @@ -774,7 +769,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); /* Read timer and check it is no longer pending */ - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); TEST_ASSERT(!tmr.u.timer.expires_ns, "Timer still reported pending"); shinfo->evtchn_pending[0] = 0; @@ -783,7 +778,7 @@ int main(int argc, char *argv[]) evtchn_irq_expected = true; tmr.u.timer.expires_ns = rs->state_entry_time - 100000000ULL; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); alarm(1); break; @@ -853,7 +848,7 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr rst = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &rst); if (verbose) { printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index b30fe9de1d4f..88914d48c65e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -11,13 +11,9 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 -static struct kvm_vm *vm; - #define INPUTVALUE 17 #define ARGVALUE(x) (0xdeadbeef5a5a0000UL + x) #define RETVALUE 0xcafef00dfbfbffffUL @@ -84,14 +80,15 @@ static void guest_code(void) int main(int argc, char *argv[]) { - if (!(kvm_check_cap(KVM_CAP_XEN_HVM) & - KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) ) { - print_skip("KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL not available"); - exit(KSFT_SKIP); - } + unsigned int xen_caps; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); + TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL); - vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); - vcpu_set_hv_cpuid(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_set_hv_cpuid(vcpu); struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, @@ -105,10 +102,10 @@ int main(int argc, char *argv[]) virt_map(vm, HCALL_REGION_GPA, HCALL_REGION_GPA, 2); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); if (run->exit_reason == KVM_EXIT_XEN) { ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL); @@ -130,9 +127,9 @@ int main(int argc, char *argv[]) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c index 3529376747c2..e0ddf47362e7 100644 --- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c @@ -12,64 +12,44 @@ #include "kvm_util.h" #include "vmx.h" -#define VCPU_ID 1 #define MSR_BITS 64 -#define X86_FEATURE_XSAVES (1<<3) - -bool is_supported_msr(u32 msr_index) -{ - struct kvm_msr_list *list; - bool found = false; - int i; - - list = kvm_get_msr_index_list(); - for (i = 0; i < list->nmsrs; ++i) { - if (list->indices[i] == msr_index) { - found = true; - break; - } - } - - free(list); - return found; -} - int main(int argc, char *argv[]) { - struct kvm_cpuid_entry2 *entry; - bool xss_supported = false; + bool xss_in_msr_list; struct kvm_vm *vm; + struct kvm_vcpu *vcpu; uint64_t xss_val; int i, r; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, 0); + vm = vm_create_with_one_vcpu(&vcpu, NULL); - if (kvm_get_cpuid_max_basic() >= 0xd) { - entry = kvm_get_supported_cpuid_index(0xd, 1); - xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES); - } - if (!xss_supported) { - print_skip("IA32_XSS is not supported by the vCPU"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVES)); - xss_val = vcpu_get_msr(vm, VCPU_ID, MSR_IA32_XSS); + xss_val = vcpu_get_msr(vcpu, MSR_IA32_XSS); TEST_ASSERT(xss_val == 0, "MSR_IA32_XSS should be initialized to zero\n"); - vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, xss_val); + vcpu_set_msr(vcpu, MSR_IA32_XSS, xss_val); + /* * At present, KVM only supports a guest IA32_XSS value of 0. Verify * that trying to set the guest IA32_XSS to an unsupported value fails. * Also, in the future when a non-zero value succeeds check that - * IA32_XSS is in the KVM_GET_MSR_INDEX_LIST. + * IA32_XSS is in the list of MSRs to save/restore. */ + xss_in_msr_list = kvm_msr_is_in_save_restore_list(MSR_IA32_XSS); for (i = 0; i < MSR_BITS; ++i) { - r = _vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, 1ull << i); - TEST_ASSERT(r == 0 || is_supported_msr(MSR_IA32_XSS), - "IA32_XSS was able to be set, but was not found in KVM_GET_MSR_INDEX_LIST.\n"); + r = _vcpu_set_msr(vcpu, MSR_IA32_XSS, 1ull << i); + + /* + * Setting a list of MSRs returns the entry that "faulted", or + * the last entry +1 if all MSRs were successfully written. + */ + TEST_ASSERT(!r || r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); + TEST_ASSERT(r != 1 || xss_in_msr_list, + "IA32_XSS was able to be set, but was not in save/restore list"); } kvm_vm_free(vm); diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index a15d21dc035a..56eb83d1a3bd 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -181,37 +181,43 @@ ping_ipv6() send_src_ipv4() { - $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { - $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } @@ -226,13 +232,15 @@ send_flowlabel() send_src_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:4::2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:4::2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index a73f52efcb6c..0446db9c6f74 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -276,37 +276,43 @@ ping_ipv6() send_src_ipv4() { - $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { - $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } @@ -321,13 +327,15 @@ send_flowlabel() send_src_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index 8fea2c2e0b25..d40183b4eccc 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -278,37 +278,43 @@ ping_ipv6() send_src_ipv4() { - $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { - $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + ip vrf exec v$h1 $MZ $h1 -q -p 64 \ + -A 198.51.100.2 -B 203.0.113.2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { - $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ -d 1msec -c 50 -t udp "sp=20000,dp=30000" } @@ -323,13 +329,15 @@ send_flowlabel() send_src_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d 1msec -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { - $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ + -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d 1msec -t udp "sp=20000,dp=0-32768" } diff --git a/tools/testing/selftests/powerpc/include/basic_asm.h b/tools/testing/selftests/powerpc/include/basic_asm.h index 886dc026fe7a..26cde8ea1f49 100644 --- a/tools/testing/selftests/powerpc/include/basic_asm.h +++ b/tools/testing/selftests/powerpc/include/basic_asm.h @@ -5,6 +5,16 @@ #include <ppc-asm.h> #include <asm/unistd.h> +#ifdef __powerpc64__ +#define PPC_LL ld +#define PPC_STL std +#define PPC_STLU stdu +#else +#define PPC_LL lwz +#define PPC_STL stw +#define PPC_STLU stwu +#endif + #define LOAD_REG_IMMEDIATE(reg, expr) \ lis reg, (expr)@highest; \ ori reg, reg, (expr)@higher; \ @@ -14,16 +24,20 @@ /* * Note: These macros assume that variables being stored on the stack are - * doublewords, while this is usually the case it may not always be the + * sizeof(long), while this is usually the case it may not always be the * case for each use case. */ +#ifdef __powerpc64__ + +// ABIv2 #if defined(_CALL_ELF) && _CALL_ELF == 2 #define STACK_FRAME_MIN_SIZE 32 #define STACK_FRAME_TOC_POS 24 #define __STACK_FRAME_PARAM(_param) (32 + ((_param)*8)) #define __STACK_FRAME_LOCAL(_num_params, _var_num) \ ((STACK_FRAME_PARAM(_num_params)) + ((_var_num)*8)) -#else + +#else // ABIv1 below #define STACK_FRAME_MIN_SIZE 112 #define STACK_FRAME_TOC_POS 40 #define __STACK_FRAME_PARAM(i) (48 + ((i)*8)) @@ -34,7 +48,24 @@ */ #define __STACK_FRAME_LOCAL(_num_params, _var_num) \ (112 + ((_var_num)*8)) -#endif + + +#endif // ABIv2 + +// Common 64-bit +#define STACK_FRAME_LR_POS 16 +#define STACK_FRAME_CR_POS 8 + +#else // 32-bit below + +#define STACK_FRAME_MIN_SIZE 16 +#define STACK_FRAME_LR_POS 4 + +#define __STACK_FRAME_PARAM(_param) (STACK_FRAME_MIN_SIZE + ((_param)*4)) +#define __STACK_FRAME_LOCAL(_num_params, _var_num) \ + ((STACK_FRAME_PARAM(_num_params)) + ((_var_num)*4)) + +#endif // __powerpc64__ /* Parameter x saved to the stack */ #define STACK_FRAME_PARAM(var) __STACK_FRAME_PARAM(var) @@ -42,8 +73,6 @@ /* Local variable x saved to the stack after x parameters */ #define STACK_FRAME_LOCAL(num_params, var) \ __STACK_FRAME_LOCAL(num_params, var) -#define STACK_FRAME_LR_POS 16 -#define STACK_FRAME_CR_POS 8 /* * It is very important to note here that _extra is the extra amount of @@ -56,19 +85,21 @@ * preprocessed incorrectly, hence r0. */ #define PUSH_BASIC_STACK(_extra) \ - mflr r0; \ - std r0, STACK_FRAME_LR_POS(%r1); \ - stdu %r1, -(_extra + STACK_FRAME_MIN_SIZE)(%r1); \ - mfcr r0; \ - stw r0, STACK_FRAME_CR_POS(%r1); \ - std %r2, STACK_FRAME_TOC_POS(%r1); + mflr r0; \ + PPC_STL r0, STACK_FRAME_LR_POS(%r1); \ + PPC_STLU %r1, -(((_extra + 15) & ~15) + STACK_FRAME_MIN_SIZE)(%r1); #define POP_BASIC_STACK(_extra) \ - ld %r2, STACK_FRAME_TOC_POS(%r1); \ - lwz r0, STACK_FRAME_CR_POS(%r1); \ - mtcr r0; \ - addi %r1, %r1, (_extra + STACK_FRAME_MIN_SIZE); \ - ld r0, STACK_FRAME_LR_POS(%r1); \ + addi %r1, %r1, (((_extra + 15) & ~15) + STACK_FRAME_MIN_SIZE); \ + PPC_LL r0, STACK_FRAME_LR_POS(%r1); \ mtlr r0; +.macro OP_REGS op, reg_width, start_reg, end_reg, base_reg, base_reg_offset=0, skip=0 + .set i, \start_reg + .rept (\end_reg - \start_reg + 1) + \op i, (\reg_width * (i - \skip) + \base_reg_offset)(\base_reg) + .set i, i + 1 + .endr +.endm + #endif /* _SELFTESTS_POWERPC_BASIC_ASM_H */ diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h index c422be8a42b2..d5a547f72669 100644 --- a/tools/testing/selftests/powerpc/include/reg.h +++ b/tools/testing/selftests/powerpc/include/reg.h @@ -55,6 +55,10 @@ #define PVR_VER(pvr) (((pvr) >> 16) & 0xFFFF) #define SPRN_PVR 0x11F +#define PVR_CFG(pvr) (((pvr) >> 8) & 0xF) /* Configuration field */ +#define PVR_MAJ(pvr) (((pvr) >> 4) & 0xF) /* Major revision field */ +#define PVR_MIN(pvr) (((pvr) >> 0) & 0xF) /* Minor revision field */ + #define SPRN_DSCR_PRIV 0x11 /* Privilege State DSCR */ #define SPRN_DSCR 0x03 /* Data Stream Control Register */ #define SPRN_PPR 896 /* Program Priority Register */ @@ -123,45 +127,44 @@ "li 30, %[" #_asm_symbol_name_immed "];" \ "li 31, %[" #_asm_symbol_name_immed "];" -#define ASM_LOAD_FPR_SINGLE_PRECISION(_asm_symbol_name_addr) \ - "lfs 0, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 1, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 2, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 3, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 4, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 5, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 6, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 7, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 8, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 9, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 10, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 11, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 12, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 13, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 14, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 15, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 16, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 17, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 18, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 19, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 20, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 21, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 22, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 23, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 24, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 25, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 26, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 27, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 28, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 29, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 30, 0(%[" #_asm_symbol_name_addr "]);" \ - "lfs 31, 0(%[" #_asm_symbol_name_addr "]);" +#define ASM_LOAD_FPR(_asm_symbol_name_addr) \ + "lfd 0, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 1, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 2, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 3, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 4, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 5, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 6, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 7, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 8, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 9, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 10, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 11, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 12, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 13, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 14, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 15, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 16, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 17, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 18, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 19, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 20, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 21, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 22, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 23, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 24, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 25, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 26, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 27, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 28, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 29, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 30, 0(%[" #_asm_symbol_name_addr "]);" \ + "lfd 31, 0(%[" #_asm_symbol_name_addr "]);" #ifndef __ASSEMBLER__ void store_gpr(unsigned long *addr); void load_gpr(unsigned long *addr); -void load_fpr_single_precision(float *addr); -void store_fpr_single_precision(float *addr); +void store_fpr(double *addr); #endif /* end of __ASSEMBLER__ */ #endif /* _SELFTESTS_POWERPC_REG_H */ diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index b9fa9cd709df..e222a5858450 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -74,6 +74,16 @@ static inline bool have_hwcap2(unsigned long ftr2) } #endif +static inline char *auxv_base_platform(void) +{ + return ((char *)get_auxv_entry(AT_BASE_PLATFORM)); +} + +static inline char *auxv_platform(void) +{ + return ((char *)get_auxv_entry(AT_PLATFORM)); +} + bool is_ppc64le(void); int using_hash_mmu(bool *using_hash); diff --git a/tools/testing/selftests/powerpc/lib/reg.S b/tools/testing/selftests/powerpc/lib/reg.S index 9304ea7d59b9..6d1af4a9a6b4 100644 --- a/tools/testing/selftests/powerpc/lib/reg.S +++ b/tools/testing/selftests/powerpc/lib/reg.S @@ -53,79 +53,42 @@ FUNC_START(store_gpr) blr FUNC_END(store_gpr) -/* Single Precision Float - float buf[32] */ -FUNC_START(load_fpr_single_precision) - lfs 0, 0*4(3) - lfs 1, 1*4(3) - lfs 2, 2*4(3) - lfs 3, 3*4(3) - lfs 4, 4*4(3) - lfs 5, 5*4(3) - lfs 6, 6*4(3) - lfs 7, 7*4(3) - lfs 8, 8*4(3) - lfs 9, 9*4(3) - lfs 10, 10*4(3) - lfs 11, 11*4(3) - lfs 12, 12*4(3) - lfs 13, 13*4(3) - lfs 14, 14*4(3) - lfs 15, 15*4(3) - lfs 16, 16*4(3) - lfs 17, 17*4(3) - lfs 18, 18*4(3) - lfs 19, 19*4(3) - lfs 20, 20*4(3) - lfs 21, 21*4(3) - lfs 22, 22*4(3) - lfs 23, 23*4(3) - lfs 24, 24*4(3) - lfs 25, 25*4(3) - lfs 26, 26*4(3) - lfs 27, 27*4(3) - lfs 28, 28*4(3) - lfs 29, 29*4(3) - lfs 30, 30*4(3) - lfs 31, 31*4(3) +/* Double Precision Float - double buf[32] */ +FUNC_START(store_fpr) + stfd 0, 0*8(3) + stfd 1, 1*8(3) + stfd 2, 2*8(3) + stfd 3, 3*8(3) + stfd 4, 4*8(3) + stfd 5, 5*8(3) + stfd 6, 6*8(3) + stfd 7, 7*8(3) + stfd 8, 8*8(3) + stfd 9, 9*8(3) + stfd 10, 10*8(3) + stfd 11, 11*8(3) + stfd 12, 12*8(3) + stfd 13, 13*8(3) + stfd 14, 14*8(3) + stfd 15, 15*8(3) + stfd 16, 16*8(3) + stfd 17, 17*8(3) + stfd 18, 18*8(3) + stfd 19, 19*8(3) + stfd 20, 20*8(3) + stfd 21, 21*8(3) + stfd 22, 22*8(3) + stfd 23, 23*8(3) + stfd 24, 24*8(3) + stfd 25, 25*8(3) + stfd 26, 26*8(3) + stfd 27, 27*8(3) + stfd 28, 28*8(3) + stfd 29, 29*8(3) + stfd 30, 30*8(3) + stfd 31, 31*8(3) blr -FUNC_END(load_fpr_single_precision) - -/* Single Precision Float - float buf[32] */ -FUNC_START(store_fpr_single_precision) - stfs 0, 0*4(3) - stfs 1, 1*4(3) - stfs 2, 2*4(3) - stfs 3, 3*4(3) - stfs 4, 4*4(3) - stfs 5, 5*4(3) - stfs 6, 6*4(3) - stfs 7, 7*4(3) - stfs 8, 8*4(3) - stfs 9, 9*4(3) - stfs 10, 10*4(3) - stfs 11, 11*4(3) - stfs 12, 12*4(3) - stfs 13, 13*4(3) - stfs 14, 14*4(3) - stfs 15, 15*4(3) - stfs 16, 16*4(3) - stfs 17, 17*4(3) - stfs 18, 18*4(3) - stfs 19, 19*4(3) - stfs 20, 20*4(3) - stfs 21, 21*4(3) - stfs 22, 22*4(3) - stfs 23, 23*4(3) - stfs 24, 24*4(3) - stfs 25, 25*4(3) - stfs 26, 26*4(3) - stfs 27, 27*4(3) - stfs 28, 28*4(3) - stfs 29, 29*4(3) - stfs 30, 30*4(3) - stfs 31, 31*4(3) - blr -FUNC_END(store_fpr_single_precision) +FUNC_END(store_fpr) /* VMX/VSX registers - unsigned long buf[128] */ FUNC_START(loadvsx) diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore index d0c23b2e4b60..07b4893ef7af 100644 --- a/tools/testing/selftests/powerpc/math/.gitignore +++ b/tools/testing/selftests/powerpc/math/.gitignore @@ -7,3 +7,4 @@ fpu_signal vmx_signal vsx_preempt fpu_denormal +mma diff --git a/tools/testing/selftests/powerpc/math/mma.S b/tools/testing/selftests/powerpc/math/mma.S index 8528c9849565..61cc88b1b26b 100644 --- a/tools/testing/selftests/powerpc/math/mma.S +++ b/tools/testing/selftests/powerpc/math/mma.S @@ -20,6 +20,9 @@ test_mma: /* xvi16ger2s */ .long 0xec042958 + /* Deprime the accumulator - xxmfacc 0 */ + .long 0x7c000162 + /* Store result in image passed in r5 */ stxvw4x 0,0,5 addi 5,5,16 diff --git a/tools/testing/selftests/powerpc/mce/.gitignore b/tools/testing/selftests/powerpc/mce/.gitignore new file mode 100644 index 000000000000..f5921462a495 --- /dev/null +++ b/tools/testing/selftests/powerpc/mce/.gitignore @@ -0,0 +1 @@ +inject-ra-err diff --git a/tools/testing/selftests/powerpc/papr_attributes/attr_test.c b/tools/testing/selftests/powerpc/papr_attributes/attr_test.c index bab0dc06e90b..9b655be641c9 100644 --- a/tools/testing/selftests/powerpc/papr_attributes/attr_test.c +++ b/tools/testing/selftests/powerpc/papr_attributes/attr_test.c @@ -7,6 +7,7 @@ * Copyright 2022, Pratik Rajesh Sampat, IBM Corp. */ +#include <errno.h> #include <stdio.h> #include <string.h> #include <dirent.h> @@ -32,7 +33,7 @@ enum type { NUM_VAL }; -int value_type(int id) +static int value_type(int id) { int val_type; @@ -54,15 +55,21 @@ int value_type(int id) return val_type; } -int verify_energy_info(void) +static int verify_energy_info(void) { const char *path = "/sys/firmware/papr/energy_scale_info"; struct dirent *entry; struct stat s; DIR *dirp; - if (stat(path, &s) || !S_ISDIR(s.st_mode)) - return -1; + errno = 0; + if (stat(path, &s)) { + SKIP_IF(errno == ENOENT); + FAIL_IF(errno); + } + + FAIL_IF(!S_ISDIR(s.st_mode)); + dirp = opendir(path); while ((entry = readdir(dirp)) != NULL) { @@ -76,25 +83,24 @@ int verify_energy_info(void) id = atoi(entry->d_name); attr_type = value_type(id); - if (attr_type == INVALID) - return -1; + FAIL_IF(attr_type == INVALID); /* Check if the files exist and have data in them */ sprintf(file_name, "%s/%d/desc", path, id); f = fopen(file_name, "r"); - if (!f || fgetc(f) == EOF) - return -1; + FAIL_IF(!f); + FAIL_IF(fgetc(f) == EOF); sprintf(file_name, "%s/%d/value", path, id); f = fopen(file_name, "r"); - if (!f || fgetc(f) == EOF) - return -1; + FAIL_IF(!f); + FAIL_IF(fgetc(f) == EOF); if (attr_type == STR_VAL) { sprintf(file_name, "%s/%d/value_desc", path, id); f = fopen(file_name, "r"); - if (!f || fgetc(f) == EOF) - return -1; + FAIL_IF(!f); + FAIL_IF(fgetc(f) == EOF); } } diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index edbd96d3b2ab..30803353bd7c 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -8,7 +8,7 @@ EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c top_srcdir = ../../../../.. include ../../lib.mk -all: $(TEST_GEN_PROGS) ebb sampling_tests +all: $(TEST_GEN_PROGS) ebb sampling_tests event_code_tests $(TEST_GEN_PROGS): $(EXTRA_SOURCES) @@ -27,6 +27,7 @@ override define RUN_TESTS $(DEFAULT_RUN_TESTS) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) @@ -34,6 +35,7 @@ override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) @@ -41,12 +43,14 @@ override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef clean: $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean ebb: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all @@ -54,4 +58,7 @@ ebb: sampling_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests clean ebb sampling_tests +event_code_tests: + TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all + +.PHONY: all run_tests clean ebb sampling_tests event_code_tests diff --git a/tools/testing/selftests/powerpc/pmu/branch_loops.S b/tools/testing/selftests/powerpc/pmu/branch_loops.S new file mode 100644 index 000000000000..de758dd3cecf --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/branch_loops.S @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <ppc-asm.h> + + .text + +#define ITER_SHIFT 31 + +FUNC_START(indirect_branch_loop) + li r3, 1 + sldi r3, r3, ITER_SHIFT + +1: cmpdi r3, 0 + beqlr + + addi r3, r3, -1 + + ld r4, 2f@got(%r2) + mtctr r4 + bctr + + .balign 32 +2: b 1b + +FUNC_END(indirect_branch_loop) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore index 2920fb39439b..64d8dfdac74a 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore +++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore @@ -21,3 +21,4 @@ back_to_back_ebbs_test lost_exception_test no_handler_test cycles_with_mmcr2_test +regs_access_pmccext_test diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c index 4b45a2e70f62..fc32187d483d 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c @@ -50,6 +50,7 @@ int cycles_with_mmcr2(void) expected[1] = MMCR2_EXPECTED_2; i = 0; bad_mmcr2 = false; + actual = 0; /* Make sure we loop until we take at least one EBB */ while ((ebb_state.stats.ebb_count < 20 && !bad_mmcr2) || diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/Makefile b/tools/testing/selftests/powerpc/pmu/event_code_tests/Makefile new file mode 100644 index 000000000000..4e07d7046457 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -m64 + +TEST_GEN_PROGS := group_constraint_pmc56_test group_pmc56_exclude_constraints_test group_constraint_pmc_count_test \ + group_constraint_repeat_test group_constraint_radix_scope_qual_test reserved_bits_mmcra_sample_elig_mode_test \ + group_constraint_mmcra_sample_test invalid_event_code_test reserved_bits_mmcra_thresh_ctl_test \ + blacklisted_events_test event_alternatives_tests_p9 event_alternatives_tests_p10 generic_events_valid_test \ + group_constraint_l2l3_sel_test group_constraint_cache_test group_constraint_thresh_cmp_test \ + group_constraint_unit_test group_constraint_thresh_ctl_test group_constraint_thresh_sel_test \ + hw_cache_event_type_test + +top_srcdir = ../../../../../.. +include ../../../lib.mk + +$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c ../sampling_tests/misc.h ../sampling_tests/misc.c diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/blacklisted_events_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/blacklisted_events_test.c new file mode 100644 index 000000000000..fafeff19cb34 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/blacklisted_events_test.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <sys/prctl.h> +#include <limits.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +#define PM_DTLB_MISS_16G 0x1c058 +#define PM_DERAT_MISS_2M 0x1c05a +#define PM_DTLB_MISS_2M 0x1c05c +#define PM_MRK_DTLB_MISS_1G 0x1d15c +#define PM_DTLB_MISS_4K 0x2c056 +#define PM_DERAT_MISS_1G 0x2c05a +#define PM_MRK_DERAT_MISS_2M 0x2d152 +#define PM_MRK_DTLB_MISS_4K 0x2d156 +#define PM_MRK_DTLB_MISS_16G 0x2d15e +#define PM_DTLB_MISS_64K 0x3c056 +#define PM_MRK_DERAT_MISS_1G 0x3d152 +#define PM_MRK_DTLB_MISS_64K 0x3d156 +#define PM_DISP_HELD_SYNC_HOLD 0x4003c +#define PM_DTLB_MISS_16M 0x4c056 +#define PM_DTLB_MISS_1G 0x4c05a +#define PM_MRK_DTLB_MISS_16M 0x4c15e +#define PM_MRK_ST_DONE_L2 0x10134 +#define PM_RADIX_PWC_L1_HIT 0x1f056 +#define PM_FLOP_CMPL 0x100f4 +#define PM_MRK_NTF_FIN 0x20112 +#define PM_RADIX_PWC_L2_HIT 0x2d024 +#define PM_IFETCH_THROTTLE 0x3405e +#define PM_MRK_L2_TM_ST_ABORT_SISTER 0x3e15c +#define PM_RADIX_PWC_L3_HIT 0x3f056 +#define PM_RUN_CYC_SMT2_MODE 0x3006c +#define PM_TM_TX_PASS_RUN_INST 0x4e014 + +#define PVR_POWER9_CUMULUS 0x00002000 + +int blacklist_events_dd21[] = { + PM_MRK_ST_DONE_L2, + PM_RADIX_PWC_L1_HIT, + PM_FLOP_CMPL, + PM_MRK_NTF_FIN, + PM_RADIX_PWC_L2_HIT, + PM_IFETCH_THROTTLE, + PM_MRK_L2_TM_ST_ABORT_SISTER, + PM_RADIX_PWC_L3_HIT, + PM_RUN_CYC_SMT2_MODE, + PM_TM_TX_PASS_RUN_INST, + PM_DISP_HELD_SYNC_HOLD, +}; + +int blacklist_events_dd22[] = { + PM_DTLB_MISS_16G, + PM_DERAT_MISS_2M, + PM_DTLB_MISS_2M, + PM_MRK_DTLB_MISS_1G, + PM_DTLB_MISS_4K, + PM_DERAT_MISS_1G, + PM_MRK_DERAT_MISS_2M, + PM_MRK_DTLB_MISS_4K, + PM_MRK_DTLB_MISS_16G, + PM_DTLB_MISS_64K, + PM_MRK_DERAT_MISS_1G, + PM_MRK_DTLB_MISS_64K, + PM_DISP_HELD_SYNC_HOLD, + PM_DTLB_MISS_16M, + PM_DTLB_MISS_1G, + PM_MRK_DTLB_MISS_16M, +}; + +int pvr_min; + +/* + * check for power9 support for 2.1 and + * 2.2 model where blacklist is applicable. + */ +int check_for_power9_version(void) +{ + pvr_min = PVR_MIN(mfspr(SPRN_PVR)); + + SKIP_IF(PVR_VER(pvr) != POWER9); + SKIP_IF(!(pvr & PVR_POWER9_CUMULUS)); + + SKIP_IF(!(3 - pvr_min)); + + return 0; +} + +/* + * Testcase to ensure that using blacklisted bits in + * event code should cause event_open to fail in power9 + */ + +static int blacklisted_events(void) +{ + struct event event; + int i = 0; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * check for power9 support for 2.1 and + * 2.2 model where blacklist is applicable. + */ + SKIP_IF(check_for_power9_version()); + + /* Skip for Generic compat mode */ + SKIP_IF(check_for_generic_compat_pmu()); + + if (pvr_min == 1) { + for (i = 0; i < ARRAY_SIZE(blacklist_events_dd21); i++) { + event_init(&event, blacklist_events_dd21[i]); + FAIL_IF(!event_open(&event)); + } + } else if (pvr_min == 2) { + for (i = 0; i < ARRAY_SIZE(blacklist_events_dd22); i++) { + event_init(&event, blacklist_events_dd22[i]); + FAIL_IF(!event_open(&event)); + } + } + + return 0; +} + +int main(void) +{ + return test_harness(blacklisted_events, "blacklisted_events"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p10.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p10.c new file mode 100644 index 000000000000..8be7aada6523 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p10.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +#define PM_RUN_CYC_ALT 0x200f4 +#define PM_INST_DISP 0x200f2 +#define PM_BR_2PATH 0x20036 +#define PM_LD_MISS_L1 0x3e054 +#define PM_RUN_INST_CMPL_ALT 0x400fa + +#define EventCode_1 0x100fc +#define EventCode_2 0x200fa +#define EventCode_3 0x300fc +#define EventCode_4 0x400fc + +/* + * Check for event alternatives. + */ + +static int event_alternatives_tests_p10(void) +{ + struct event *e, events[5]; + int i; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * PVR check is used here since PMU specific data like + * alternative events is handled by respective PMU driver + * code and using PVR will work correctly for all cases + * including generic compat mode. + */ + SKIP_IF(PVR_VER(mfspr(SPRN_PVR)) != POWER10); + + SKIP_IF(check_for_generic_compat_pmu()); + + /* + * Test for event alternative for 0x0001e + * and 0x00002. + */ + e = &events[0]; + event_init(e, 0x0001e); + + e = &events[1]; + event_init(e, EventCode_1); + + e = &events[2]; + event_init(e, EventCode_2); + + e = &events[3]; + event_init(e, EventCode_3); + + e = &events[4]; + event_init(e, EventCode_4); + + FAIL_IF(event_open(&events[0])); + + /* + * Expected to pass since 0x0001e has alternative event + * 0x600f4 in PMC6. So it can go in with other events + * in PMC1 to PMC4. + */ + for (i = 1; i < 5; i++) + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + + for (i = 0; i < 5; i++) + event_close(&events[i]); + + e = &events[0]; + event_init(e, 0x00002); + + e = &events[1]; + event_init(e, EventCode_1); + + e = &events[2]; + event_init(e, EventCode_2); + + e = &events[3]; + event_init(e, EventCode_3); + + e = &events[4]; + event_init(e, EventCode_4); + + FAIL_IF(event_open(&events[0])); + + /* + * Expected to pass since 0x00020 has alternative event + * 0x500fa in PMC5. So it can go in with other events + * in PMC1 to PMC4. + */ + for (i = 1; i < 5; i++) + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + + for (i = 0; i < 5; i++) + event_close(&events[i]); + + return 0; +} + +int main(void) +{ + return test_harness(event_alternatives_tests_p10, "event_alternatives_tests_p10"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p9.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p9.c new file mode 100644 index 000000000000..f7dcf0e0447c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/event_alternatives_tests_p9.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +#define PM_RUN_CYC_ALT 0x200f4 +#define PM_INST_DISP 0x200f2 +#define PM_BR_2PATH 0x20036 +#define PM_LD_MISS_L1 0x3e054 +#define PM_RUN_INST_CMPL_ALT 0x400fa + +#define EventCode_1 0x200fa +#define EventCode_2 0x200fc +#define EventCode_3 0x300fc +#define EventCode_4 0x400fc + +/* + * Check for event alternatives. + */ + +static int event_alternatives_tests_p9(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * PVR check is used here since PMU specific data like + * alternative events is handled by respective PMU driver + * code and using PVR will work correctly for all cases + * including generic compat mode. + */ + SKIP_IF(PVR_VER(mfspr(SPRN_PVR)) != POWER9); + + /* Skip for generic compat PMU */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* Init the event for PM_RUN_CYC_ALT */ + event_init(&leader, PM_RUN_CYC_ALT); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_1); + + /* + * Expected to pass since PM_RUN_CYC_ALT in PMC2 has alternative event + * 0x600f4. So it can go in with EventCode_1 which is using PMC2 + */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + event_init(&leader, PM_INST_DISP); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + /* + * Expected to pass since PM_INST_DISP in PMC2 has alternative event + * 0x300f2 in PMC3. So it can go in with EventCode_2 which is using PMC2 + */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + event_init(&leader, PM_BR_2PATH); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + /* + * Expected to pass since PM_BR_2PATH in PMC2 has alternative event + * 0x40036 in PMC4. So it can go in with EventCode_2 which is using PMC2 + */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + event_init(&leader, PM_LD_MISS_L1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_3); + /* + * Expected to pass since PM_LD_MISS_L1 in PMC3 has alternative event + * 0x400f0 in PMC4. So it can go in with EventCode_3 which is using PMC3 + */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + event_init(&leader, PM_RUN_INST_CMPL_ALT); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_4); + /* + * Expected to pass since PM_RUN_INST_CMPL_ALT in PMC4 has alternative event + * 0x500fa in PMC5. So it can go in with EventCode_4 which is using PMC4 + */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(event_alternatives_tests_p9, "event_alternatives_tests_p9"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/generic_events_valid_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/generic_events_valid_test.c new file mode 100644 index 000000000000..0d237c15d3f2 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/generic_events_valid_test.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <sys/prctl.h> +#include <limits.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* + * Testcase to ensure that using invalid event in generic + * event for PERF_TYPE_HARDWARE should fail + */ + +static int generic_events_valid_test(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* generic events is different in compat_mode */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* + * Invalid generic events in power10: + * - PERF_COUNT_HW_BUS_CYCLES + * - PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * - PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * - PERF_COUNT_HW_REF_CPU_CYCLES + */ + if (PVR_VER(mfspr(SPRN_PVR)) == POWER10) { + event_init_opts(&event, PERF_COUNT_HW_CPU_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_CACHE_REFERENCES, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_CACHE_MISSES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BRANCH_MISSES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BUS_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + + event_init_opts(&event, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + + event_init_opts(&event, PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + + event_init_opts(&event, PERF_COUNT_HW_REF_CPU_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + } else if (PVR_VER(mfspr(SPRN_PVR)) == POWER9) { + /* + * Invalid generic events in power9: + * - PERF_COUNT_HW_BUS_CYCLES + * - PERF_COUNT_HW_REF_CPU_CYCLES + */ + event_init_opts(&event, PERF_COUNT_HW_CPU_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_INSTRUCTIONS, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_CACHE_REFERENCES, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_CACHE_MISSES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BRANCH_MISSES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_BUS_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + + event_init_opts(&event, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + PERF_TYPE_HARDWARE, "event"); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init_opts(&event, PERF_COUNT_HW_REF_CPU_CYCLES, PERF_TYPE_HARDWARE, "event"); + FAIL_IF(!event_open(&event)); + } + + return 0; +} + +int main(void) +{ + return test_harness(generic_events_valid_test, "generic_events_valid_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_cache_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_cache_test.c new file mode 100644 index 000000000000..f4be05aa3a3d --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_cache_test.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* All L1 D cache load references counted at finish, gated by reject */ +#define EventCode_1 0x1100fc +/* Load Missed L1 */ +#define EventCode_2 0x23e054 +/* Load Missed L1 */ +#define EventCode_3 0x13e054 + +/* + * Testcase for group constraint check of data and instructions + * cache qualifier bits which is used to program cache select field in + * Monitor Mode Control Register 1 (MMCR1: 16-17) for l1 cache. + * All events in the group should match cache select bits otherwise + * event_open for the group will fail. + */ +static int group_constraint_cache(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Init the events for the group contraint check for l1 cache select bits */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + + /* Expected to fail as sibling event doesn't request same l1 cache select bits as leader */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint l1 cache select test */ + event_init(&event, EventCode_3); + + /* Expected to succeed as sibling event request same l1 cache select bits as leader */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_cache, "group_constraint_cache"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_l2l3_sel_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_l2l3_sel_test.c new file mode 100644 index 000000000000..85a636886069 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_l2l3_sel_test.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* All successful D-side store dispatches for this thread */ +#define EventCode_1 0x010000046080 +/* All successful D-side store dispatches for this thread that were L2 Miss */ +#define EventCode_2 0x26880 +/* All successful D-side store dispatches for this thread that were L2 Miss */ +#define EventCode_3 0x010000026880 + +/* + * Testcase for group constraint check of l2l3_sel bits which is + * used to program l2l3 select field in Monitor Mode Control Register 0 + * (MMCR0: 56-60). + * All events in the group should match l2l3_sel bits otherwise + * event_open for the group should fail. + */ +static int group_constraint_l2l3_sel(void) +{ + struct event event, leader; + + /* + * Check for platform support for the test. + * This test is only aplicable on power10 + */ + SKIP_IF(platform_check_for_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the events for the group contraint check for l2l3_sel bits */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + + /* Expected to fail as sibling event doesn't request same l2l3_sel bits as leader */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint l2l3_sel test */ + event_init(&event, EventCode_3); + + /* Expected to succeed as sibling event request same l2l3_sel bits as leader */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_l2l3_sel, "group_constraint_l2l3_sel"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_mmcra_sample_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_mmcra_sample_test.c new file mode 100644 index 000000000000..ff625b5d80eb --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_mmcra_sample_test.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +#define EventCode_1 0x35340401e0 +#define EventCode_2 0x353c0101ec +#define EventCode_3 0x35340101ec +/* + * Test that using different sample bits in + * event code cause failure in schedule for + * group of events. + */ + +static int group_constraint_mmcra_sample(void) +{ + struct event event, leader; + + SKIP_IF(platform_check_for_tests()); + + /* + * Events with different "sample" field values + * in a group will fail to schedule. + * Use event with load only sampling mode as + * group leader. Use event with store only sampling + * as sibling event. + */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + + /* Expected to fail as sibling event doesn't use same sampling bits as leader */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_init(&event, EventCode_3); + + /* Expected to pass as sibling event use same sampling bits as leader */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_mmcra_sample, "group_constraint_mmcra_sample"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc56_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc56_test.c new file mode 100644 index 000000000000..f5ee4796d46c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc56_test.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* + * Testcase for checking constraint checks for + * Performance Monitor Counter 5 (PMC5) and also + * Performance Monitor Counter 6 (PMC6). Events using + * PMC5/PMC6 shouldn't have other fields in event + * code like cache bits, thresholding or marked bit. + */ + +static int group_constraint_pmc56(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * Events using PMC5 and PMC6 with cache bit + * set in event code is expected to fail. + */ + event_init(&event, 0x2500fa); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x2600f4); + FAIL_IF(!event_open(&event)); + + /* + * PMC5 and PMC6 only supports base events: + * ie 500fa and 600f4. Other combinations + * should fail. + */ + event_init(&event, 0x501e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x6001e); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x501fa); + FAIL_IF(!event_open(&event)); + + /* + * Events using PMC5 and PMC6 with random + * sampling bits set in event code should fail + * to schedule. + */ + event_init(&event, 0x35340500fa); + FAIL_IF(!event_open(&event)); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_pmc56, "group_constraint_pmc56"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc_count_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc_count_test.c new file mode 100644 index 000000000000..af7c5c75101c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_pmc_count_test.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* + * Testcase for number of counters in use. + * The number of programmable counters is from + * performance monitor counter 1 to performance + * monitor counter 4 (PMC1-PMC4). If number of + * counters in use exceeds the limit, next event + * should fail to schedule. + */ + +static int group_constraint_pmc_count(void) +{ + struct event *e, events[5]; + int i; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * Test for number of counters in use. + * Use PMC1 to PMC4 for leader and 3 sibling + * events. Trying to open fourth event should + * fail here. + */ + e = &events[0]; + event_init(e, 0x1001a); + + e = &events[1]; + event_init(e, 0x200fc); + + e = &events[2]; + event_init(e, 0x30080); + + e = &events[3]; + event_init(e, 0x40054); + + e = &events[4]; + event_init(e, 0x0002c); + + FAIL_IF(event_open(&events[0])); + + /* + * The event_open will fail on event 4 if constraint + * check fails + */ + for (i = 1; i < 5; i++) { + if (i == 4) + FAIL_IF(!event_open_with_group(&events[i], events[0].fd)); + else + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + } + + for (i = 1; i < 4; i++) + event_close(&events[i]); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_pmc_count, "group_constraint_pmc_count"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_radix_scope_qual_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_radix_scope_qual_test.c new file mode 100644 index 000000000000..9225618b846a --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_radix_scope_qual_test.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* PM_DATA_RADIX_PROCESS_L2_PTE_FROM_L2 */ +#define EventCode_1 0x14242 +/* PM_DATA_RADIX_PROCESS_L2_PTE_FROM_L3 */ +#define EventCode_2 0x24242 + +/* + * Testcase for group constraint check for radix_scope_qual + * field which is used to program Monitor Mode Control + * egister (MMCR1) bit 18. + * All events in the group should match radix_scope_qual, + * bits otherwise event_open for the group should fail. + */ + +static int group_constraint_radix_scope_qual(void) +{ + struct event event, leader; + + /* + * Check for platform support for the test. + * This test is aplicable on power10 only. + */ + SKIP_IF(platform_check_for_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the events for the group contraint check for radix_scope_qual bits */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, 0x200fc); + + /* Expected to fail as sibling event doesn't request same radix_scope_qual bits as leader */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_init(&event, EventCode_2); + /* Expected to pass as sibling event request same radix_scope_qual bits as leader */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_radix_scope_qual, + "group_constraint_radix_scope_qual"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_repeat_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_repeat_test.c new file mode 100644 index 000000000000..371cd05bb3ed --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_repeat_test.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* The processor's L1 data cache was reloaded */ +#define EventCode1 0x21C040 +#define EventCode2 0x22C040 + +/* + * Testcase for group constraint check + * when using events with same PMC. + * Multiple events in a group shouldn't + * ask for same PMC. If so it should fail. + */ + +static int group_constraint_repeat(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * Two events in a group using same PMC + * should fail to get scheduled. Usei same PMC2 + * for leader and sibling event which is expected + * to fail. + */ + event_init(&leader, EventCode1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode1); + + /* Expected to fail since sibling event is requesting same PMC as leader */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_init(&event, EventCode2); + + /* Expected to pass since sibling event is requesting different PMC */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_repeat, "group_constraint_repeat"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_cmp_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_cmp_test.c new file mode 100644 index 000000000000..9f1197104e8c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_cmp_test.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* + * Primary PMU events used here is PM_MRK_INST_CMPL (0x401e0) and + * PM_THRESH_MET (0x101ec) + * Threshold event selection used is issue to complete for cycles + * Sampling criteria is Load or Store only sampling + */ +#define p9_EventCode_1 0x13e35340401e0 +#define p9_EventCode_2 0x17d34340101ec +#define p9_EventCode_3 0x13e35340101ec +#define p10_EventCode_1 0x35340401e0 +#define p10_EventCode_2 0x35340101ec + +/* + * Testcase for group constraint check of thresh_cmp bits which is + * used to program thresh compare field in Monitor Mode Control Register A + * (MMCRA: 9-18 bits for power9 and MMCRA: 8-18 bits for power10). + * All events in the group should match thresh compare bits otherwise + * event_open for the group will fail. + */ +static int group_constraint_thresh_cmp(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + if (have_hwcap2(PPC_FEATURE2_ARCH_3_1)) { + /* Init the events for the group contraint check for thresh_cmp bits */ + event_init(&leader, p10_EventCode_1); + + /* Add the thresh_cmp value for leader in config1 */ + leader.attr.config1 = 1000; + FAIL_IF(event_open(&leader)); + + event_init(&event, p10_EventCode_2); + + /* Add the different thresh_cmp value from the leader event in config1 */ + event.attr.config1 = 2000; + + /* Expected to fail as sibling and leader event request different thresh_cmp bits */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint thresh compare test */ + event_init(&event, p10_EventCode_2); + + /* Add the same thresh_cmp value for leader and sibling event in config1 */ + event.attr.config1 = 1000; + + /* Expected to succeed as sibling and leader event request same thresh_cmp bits */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + } else { + /* Init the events for the group contraint check for thresh_cmp bits */ + event_init(&leader, p9_EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, p9_EventCode_2); + + /* Expected to fail as sibling and leader event request different thresh_cmp bits */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint thresh compare test */ + event_init(&event, p9_EventCode_3); + + /* Expected to succeed as sibling and leader event request same thresh_cmp bits */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + } + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_thresh_cmp, "group_constraint_thresh_cmp"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_ctl_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_ctl_test.c new file mode 100644 index 000000000000..e0852ebc1671 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_ctl_test.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* + * Primary PMU events used here are PM_MRK_INST_CMPL (0x401e0) and + * PM_THRESH_MET (0x101ec). + * Threshold event selection used is issue to complete and issue to + * finished for cycles + * Sampling criteria is Load or Store only sampling + */ +#define EventCode_1 0x35340401e0 +#define EventCode_2 0x34340101ec +#define EventCode_3 0x35340101ec + +/* + * Testcase for group constraint check of thresh_ctl bits which is + * used to program thresh compare field in Monitor Mode Control Register A + * (MMCR0: 48-55). + * All events in the group should match thresh ctl bits otherwise + * event_open for the group will fail. + */ +static int group_constraint_thresh_ctl(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Init the events for the group contraint thresh control test */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + + /* Expected to fail as sibling and leader event request different thresh_ctl bits */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint thresh control test */ + event_init(&event, EventCode_3); + + /* Expected to succeed as sibling and leader event request same thresh_ctl bits */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_thresh_ctl, "group_constraint_thresh_ctl"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_sel_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_sel_test.c new file mode 100644 index 000000000000..50a8cd843ce7 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_thresh_sel_test.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* + * Primary PMU events used here are PM_MRK_INST_CMPL (0x401e0) and + * PM_THRESH_MET (0x101ec). + * Threshold event selection used is issue to complete + * Sampling criteria is Load or Store only sampling + */ +#define EventCode_1 0x35340401e0 +#define EventCode_2 0x35540101ec +#define EventCode_3 0x35340101ec + +/* + * Testcase for group constraint check of thresh_sel bits which is + * used to program thresh select field in Monitor Mode Control Register A + * (MMCRA: 45-57). + * All events in the group should match thresh sel bits otherwise + * event_open for the group will fail. + */ +static int group_constraint_thresh_sel(void) +{ + struct event event, leader; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Init the events for the group contraint thresh select test */ + event_init(&leader, EventCode_1); + FAIL_IF(event_open(&leader)); + + event_init(&event, EventCode_2); + + /* Expected to fail as sibling and leader event request different thresh_sel bits */ + FAIL_IF(!event_open_with_group(&event, leader.fd)); + + event_close(&event); + + /* Init the event for the group contraint thresh select test */ + event_init(&event, EventCode_3); + + /* Expected to succeed as sibling and leader event request same thresh_sel bits */ + FAIL_IF(event_open_with_group(&event, leader.fd)); + + event_close(&leader); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_thresh_sel, "group_constraint_thresh_sel"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_unit_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_unit_test.c new file mode 100644 index 000000000000..a2c18923dcec --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_constraint_unit_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* All successful D-side store dispatches for this thread with PMC 2 */ +#define EventCode_1 0x26080 +/* All successful D-side store dispatches for this thread with PMC 4 */ +#define EventCode_2 0x46080 +/* All successful D-side store dispatches for this thread that were L2 Miss with PMC 3 */ +#define EventCode_3 0x36880 + +/* + * Testcase for group constraint check of unit and pmc bits which is + * used to program corresponding unit and pmc field in Monitor Mode + * Control Register 1 (MMCR1) + * One of the event in the group should use PMC 4 incase units field + * value is within 6 to 9 otherwise event_open for the group will fail. + */ +static int group_constraint_unit(void) +{ + struct event *e, events[3]; + + /* + * Check for platform support for the test. + * Constraint to use PMC4 with one of the event in group, + * when the unit is within 6 to 9 is only applicable on + * power9. + */ + SKIP_IF(platform_check_for_tests()); + SKIP_IF(have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the events for the group contraint check for unit bits */ + e = &events[0]; + event_init(e, EventCode_1); + + /* Expected to fail as PMC 4 is not used with unit field value 6 to 9 */ + FAIL_IF(!event_open(&events[0])); + + /* Init the events for the group contraint check for unit bits */ + e = &events[1]; + event_init(e, EventCode_2); + + /* Expected to pass as PMC 4 is used with unit field value 6 to 9 */ + FAIL_IF(event_open(&events[1])); + + /* Init the event for the group contraint unit test */ + e = &events[2]; + event_init(e, EventCode_3); + + /* Expected to fail as PMC4 is not being used */ + FAIL_IF(!event_open_with_group(&events[2], events[0].fd)); + + /* Expected to succeed as event using PMC4 */ + FAIL_IF(event_open_with_group(&events[2], events[1].fd)); + + event_close(&events[0]); + event_close(&events[1]); + event_close(&events[2]); + + return 0; +} + +int main(void) +{ + return test_harness(group_constraint_unit, "group_constraint_unit"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/group_pmc56_exclude_constraints_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_pmc56_exclude_constraints_test.c new file mode 100644 index 000000000000..cff9ac170df6 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/group_pmc56_exclude_constraints_test.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include <sys/prctl.h> +#include <limits.h> +#include "../sampling_tests/misc.h" + +/* + * Testcase for group constraint check for + * Performance Monitor Counter 5 (PMC5) and also + * Performance Monitor Counter 6 (PMC6). + * Test that pmc5/6 is excluded from constraint + * check when scheduled along with group of events. + */ + +static int group_pmc56_exclude_constraints(void) +{ + struct event *e, events[3]; + int i; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * PMC5/6 is excluded from constraint bit + * check along with group of events. Use + * group of events with PMC5, PMC6 and also + * event with cache bit (dc_ic) set. Test expects + * this set of events to go in as a group. + */ + e = &events[0]; + event_init(e, 0x500fa); + + e = &events[1]; + event_init(e, 0x600f4); + + e = &events[2]; + event_init(e, 0x22C040); + + FAIL_IF(event_open(&events[0])); + + /* + * The event_open will fail if constraint check fails. + * Since we are asking for events in a group and since + * PMC5/PMC6 is excluded from group constraints, even_open + * should pass. + */ + for (i = 1; i < 3; i++) + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + + for (i = 0; i < 3; i++) + event_close(&events[i]); + + return 0; +} + +int main(void) +{ + return test_harness(group_pmc56_exclude_constraints, "group_pmc56_exclude_constraints"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/hw_cache_event_type_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/hw_cache_event_type_test.c new file mode 100644 index 000000000000..a45b1da5b568 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/hw_cache_event_type_test.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "utils.h" +#include "../sampling_tests/misc.h" + +/* + * Load Missed L1, for power9 its pointing to PM_LD_MISS_L1_FIN (0x2c04e) and + * for power10 its pointing to PM_LD_MISS_L1 (0x3e054) + * + * Hardware cache level : PERF_COUNT_HW_CACHE_L1D + * Hardware cache event operation type : PERF_COUNT_HW_CACHE_OP_READ + * Hardware cache event result type : PERF_COUNT_HW_CACHE_RESULT_MISS + */ +#define EventCode_1 0x10000 +/* + * Hardware cache level : PERF_COUNT_HW_CACHE_L1D + * Hardware cache event operation type : PERF_COUNT_HW_CACHE_OP_WRITE + * Hardware cache event result type : PERF_COUNT_HW_CACHE_RESULT_ACCESS + */ +#define EventCode_2 0x0100 +/* + * Hardware cache level : PERF_COUNT_HW_CACHE_DTLB + * Hardware cache event operation type : PERF_COUNT_HW_CACHE_OP_WRITE + * Hardware cache event result type : PERF_COUNT_HW_CACHE_RESULT_ACCESS + */ +#define EventCode_3 0x0103 +/* + * Hardware cache level : PERF_COUNT_HW_CACHE_L1D + * Hardware cache event operation type : PERF_COUNT_HW_CACHE_OP_READ + * Hardware cache event result type : Invalid ( > PERF_COUNT_HW_CACHE_RESULT_MAX) + */ +#define EventCode_4 0x030000 + +/* + * A perf test to check valid hardware cache events. + */ +static int hw_cache_event_type_test(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Skip for Generic compat PMU */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* Init the event to test hardware cache event */ + event_init_opts(&event, EventCode_1, PERF_TYPE_HW_CACHE, "event"); + + /* Expected to success as its pointing to L1 load miss */ + FAIL_IF(event_open(&event)); + event_close(&event); + + /* Init the event to test hardware cache event */ + event_init_opts(&event, EventCode_2, PERF_TYPE_HW_CACHE, "event"); + + /* Expected to fail as the corresponding cache event entry have 0 in that index */ + FAIL_IF(!event_open(&event)); + event_close(&event); + + /* Init the event to test hardware cache event */ + event_init_opts(&event, EventCode_3, PERF_TYPE_HW_CACHE, "event"); + + /* Expected to fail as the corresponding cache event entry have -1 in that index */ + FAIL_IF(!event_open(&event)); + event_close(&event); + + /* Init the event to test hardware cache event */ + event_init_opts(&event, EventCode_4, PERF_TYPE_HW_CACHE, "event"); + + /* Expected to fail as hardware cache event result type is Invalid */ + FAIL_IF(!event_open(&event)); + event_close(&event); + + return 0; +} + +int main(void) +{ + return test_harness(hw_cache_event_type_test, "hw_cache_event_type_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/invalid_event_code_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/invalid_event_code_test.c new file mode 100644 index 000000000000..f51fcab837fc --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/invalid_event_code_test.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <sys/prctl.h> +#include <limits.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* The data cache was reloaded from local core's L3 due to a demand load */ +#define EventCode_1 0x1340000001c040 +/* PM_DATA_RADIX_PROCESS_L2_PTE_FROM_L2 */ +#define EventCode_2 0x14242 +/* Event code with IFM, EBB, BHRB bits set in event code */ +#define EventCode_3 0xf00000000000001e + +/* + * Some of the bits in the event code is + * reserved for specific platforms. + * Event code bits 52-59 are reserved in power9, + * whereas in power10, these are used for programming + * Monitor Mode Control Register 3 (MMCR3). + * Bit 9 in event code is reserved in power9, + * whereas it is used for programming "radix_scope_qual" + * bit 18 in Monitor Mode Control Register 1 (MMCR1). + * + * Testcase to ensure that using reserved bits in + * event code should cause event_open to fail. + */ + +static int invalid_event_code(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * Events using MMCR3 bits and radix scope qual bits + * should fail in power9 and should succeed in power10. + * Init the events and check for pass/fail in event open. + */ + if (have_hwcap2(PPC_FEATURE2_ARCH_3_1)) { + event_init(&event, EventCode_1); + FAIL_IF(event_open(&event)); + event_close(&event); + + event_init(&event, EventCode_2); + FAIL_IF(event_open(&event)); + event_close(&event); + } else { + event_init(&event, EventCode_1); + FAIL_IF(!event_open(&event)); + + event_init(&event, EventCode_2); + FAIL_IF(!event_open(&event)); + } + + return 0; +} + +int main(void) +{ + return test_harness(invalid_event_code, "invalid_event_code"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_sample_elig_mode_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_sample_elig_mode_test.c new file mode 100644 index 000000000000..4c119c821b99 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_sample_elig_mode_test.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* + * Testcase for reserved bits in Monitor Mode Control + * Register A (MMCRA) Random Sampling Mode (SM) value. + * As per Instruction Set Architecture (ISA), the values + * 0x5, 0x9, 0xD, 0x19, 0x1D, 0x1A, 0x1E are reserved + * for sampling mode field. Test that having these reserved + * bit values should cause event_open to fail. + * Input event code uses these sampling bits along with + * 401e0 (PM_MRK_INST_CMPL). + */ + +static int reserved_bits_mmcra_sample_elig_mode(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Skip for Generic compat PMU */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* + * MMCRA Random Sampling Mode (SM) values: 0x5 + * 0x9, 0xD, 0x19, 0x1D, 0x1A, 0x1E is reserved. + * Expected to fail when using these reserved values. + */ + event_init(&event, 0x50401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x90401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0xD0401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x190401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x1D0401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x1A0401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x1E0401e0); + FAIL_IF(!event_open(&event)); + + /* + * MMCRA Random Sampling Mode (SM) value 0x10 + * is reserved in power10 and 0xC is reserved in + * power9. + */ + if (PVR_VER(mfspr(SPRN_PVR)) == POWER10) { + event_init(&event, 0x100401e0); + FAIL_IF(!event_open(&event)); + } else if (PVR_VER(mfspr(SPRN_PVR)) == POWER9) { + event_init(&event, 0xC0401e0); + FAIL_IF(!event_open(&event)); + } + + return 0; +} + +int main(void) +{ + return test_harness(reserved_bits_mmcra_sample_elig_mode, + "reserved_bits_mmcra_sample_elig_mode"); +} diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_thresh_ctl_test.c b/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_thresh_ctl_test.c new file mode 100644 index 000000000000..4ea1c2f8913f --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/reserved_bits_mmcra_thresh_ctl_test.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include "../event.h" +#include "../sampling_tests/misc.h" + +/* + * Testcase for reserved bits in Monitor Mode + * Control Register A (MMCRA) thresh_ctl bits. + * For MMCRA[48:51]/[52:55]) Threshold Start/Stop, + * 0b11110000/0b00001111 is reserved. + */ + +static int reserved_bits_mmcra_thresh_ctl(void) +{ + struct event event; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* Skip for Generic compat PMU */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* + * MMCRA[48:51]/[52:55]) Threshold Start/Stop + * events Selection. 0b11110000/0b00001111 is reserved. + * Expected to fail when using these reserved values. + */ + event_init(&event, 0xf0340401e0); + FAIL_IF(!event_open(&event)); + + event_init(&event, 0x0f340401e0); + FAIL_IF(!event_open(&event)); + + return 0; +} + +int main(void) +{ + return test_harness(reserved_bits_mmcra_thresh_ctl, "reserved_bits_mmcra_thresh_ctl"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile b/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile index a785c6a173b9..9e67351fb252 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile @@ -4,9 +4,12 @@ CFLAGS += -m64 TEST_GEN_PROGS := mmcr0_exceptionbits_test mmcr0_cc56run_test mmcr0_pmccext_test \ mmcr0_pmcjce_test mmcr0_fc56_pmc1ce_test mmcr0_fc56_pmc56_test \ mmcr1_comb_test mmcr2_l2l3_test mmcr2_fcs_fch_test \ - mmcr3_src_test mmcra_thresh_marked_sample_test + mmcr3_src_test mmcra_thresh_marked_sample_test mmcra_thresh_cmp_test \ + mmcra_bhrb_ind_call_test mmcra_bhrb_any_test mmcra_bhrb_cond_test \ + mmcra_bhrb_disable_test bhrb_no_crash_wo_pmu_test intr_regs_no_crash_wo_pmu_test \ + bhrb_filter_map_test mmcr1_sel_unit_cache_test mmcra_bhrb_disable_no_branch_test top_srcdir = ../../../../../.. include ../../../lib.mk -$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c misc.c misc.h ../loop.S +$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c misc.c misc.h ../loop.S ../branch_loops.S diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c new file mode 100644 index 000000000000..8182647c63c8 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* + * A perf sampling test to check bhrb filter + * map. All the branch filters are not supported + * in powerpc. Supported filters in: + * power10: any, any_call, ind_call, cond + * power9: any, any_call + * + * Testcase checks event open for invalid bhrb filter + * types should fail and valid filter types should pass. + * Testcase does validity check for these branch + * sample types. + */ + +/* Invalid types for powerpc */ +/* Valid bhrb filters in power9/power10 */ +int bhrb_filter_map_valid_common[] = { + PERF_SAMPLE_BRANCH_ANY, + PERF_SAMPLE_BRANCH_ANY_CALL, +}; + +/* Valid bhrb filters in power10 */ +int bhrb_filter_map_valid_p10[] = { + PERF_SAMPLE_BRANCH_IND_CALL, + PERF_SAMPLE_BRANCH_COND, +}; + +#define EventCode 0x1001e + +static int bhrb_filter_map_test(void) +{ + struct event event; + int i; + + /* Check for platform support for the test */ + SKIP_IF(platform_check_for_tests()); + + /* + * Skip for Generic compat PMU since + * bhrb filters is not supported + */ + SKIP_IF(check_for_generic_compat_pmu()); + + /* Init the event for the sampling test */ + event_init(&event, EventCode); + + event.attr.sample_period = 1000; + event.attr.sample_type = PERF_SAMPLE_BRANCH_STACK; + event.attr.disabled = 1; + + /* Invalid filter maps which are expected to fail in event_open */ + for (i = PERF_SAMPLE_BRANCH_USER_SHIFT; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) { + /* Skip the valid branch sample type */ + if (i == PERF_SAMPLE_BRANCH_ANY_SHIFT || i == PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT \ + || i == PERF_SAMPLE_BRANCH_IND_CALL_SHIFT || i == PERF_SAMPLE_BRANCH_COND_SHIFT) + continue; + event.attr.branch_sample_type = 1U << i; + FAIL_IF(!event_open(&event)); + } + + /* valid filter maps for power9/power10 which are expected to pass in event_open */ + for (i = 0; i < ARRAY_SIZE(bhrb_filter_map_valid_common); i++) { + event.attr.branch_sample_type = bhrb_filter_map_valid_common[i]; + FAIL_IF(event_open(&event)); + event_close(&event); + } + + /* + * filter maps which are valid in power10 and invalid in power9. + * PVR check is used here since PMU specific data like bhrb filter + * alternative tests is handled by respective PMU driver code and + * using PVR will work correctly for all cases including generic + * compat mode. + */ + if (PVR_VER(mfspr(SPRN_PVR)) == POWER10) { + for (i = 0; i < ARRAY_SIZE(bhrb_filter_map_valid_p10); i++) { + event.attr.branch_sample_type = bhrb_filter_map_valid_p10[i]; + FAIL_IF(event_open(&event)); + event_close(&event); + } + } else { + for (i = 0; i < ARRAY_SIZE(bhrb_filter_map_valid_p10); i++) { + event.attr.branch_sample_type = bhrb_filter_map_valid_p10[i]; + FAIL_IF(!event_open(&event)); + } + } + + return 0; +} + +int main(void) +{ + return test_harness(bhrb_filter_map_test, "bhrb_filter_map_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_no_crash_wo_pmu_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_no_crash_wo_pmu_test.c new file mode 100644 index 000000000000..4644c6782974 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_no_crash_wo_pmu_test.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* + * A perf sampling test for making sure + * enabling branch stack doesn't crash in any + * environment, say: + * - With generic compat PMU + * - without any PMU registered + * - With platform specific PMU + * A fix for bhrb sampling crash was added in kernel + * via commit: b460b512417a ("powerpc/perf: Fix crashes + * with generic_compat_pmu & BHRB") + * + * This testcase exercises this code by doing branch + * stack enable for software event. s/w event is used + * since software event will work even in platform + * without PMU. + */ +static int bhrb_no_crash_wo_pmu_test(void) +{ + struct event event; + + /* + * Init the event for the sampling test. + * This uses software event which works on + * any platform. + */ + event_init_opts(&event, 0, PERF_TYPE_SOFTWARE, "cycles"); + + event.attr.sample_period = 1000; + event.attr.sample_type = PERF_SAMPLE_BRANCH_STACK; + event.attr.disabled = 1; + + /* + * Return code of event_open is not + * considered since test just expects no crash from + * using PERF_SAMPLE_BRANCH_STACK. Also for environment + * like generic compat PMU, branch stack is unsupported. + */ + event_open(&event); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(bhrb_no_crash_wo_pmu_test, "bhrb_no_crash_wo_pmu_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/intr_regs_no_crash_wo_pmu_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/intr_regs_no_crash_wo_pmu_test.c new file mode 100644 index 000000000000..839d2d225da0 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/intr_regs_no_crash_wo_pmu_test.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* + * A perf sampling test for making sure + * sampling with -intr-regs doesn't crash + * in any environment, say: + * - With generic compat PMU + * - without any PMU registered + * - With platform specific PMU. + * A fix for crash with intr_regs was + * addressed in commit: f75e7d73bdf7 in kernel. + * + * This testcase exercises this code path by doing + * intr_regs using software event. Software event is + * used since s/w event will work even in platform + * without PMU. + */ +static int intr_regs_no_crash_wo_pmu_test(void) +{ + struct event event; + + /* + * Init the event for the sampling test. + * This uses software event which works on + * any platform. + */ + event_init_opts(&event, 0, PERF_TYPE_SOFTWARE, "cycles"); + + event.attr.sample_period = 1000; + event.attr.sample_type = PERF_SAMPLE_REGS_INTR; + event.attr.disabled = 1; + + /* + * Return code of event_open is not considered + * since test just expects no crash from using + * PERF_SAMPLE_REGS_INTR. + */ + event_open(&event); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(intr_regs_no_crash_wo_pmu_test, "intr_regs_no_crash_wo_pmu_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c index c01a31d5f4ee..eac6420abdf1 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c @@ -60,6 +60,8 @@ static void init_ev_encodes(void) switch (pvr) { case POWER10: + ev_mask_thd_cmp = 0x3ffff; + ev_shift_thd_cmp = 0; ev_mask_rsq = 1; ev_shift_rsq = 9; ev_mask_comb = 3; @@ -119,12 +121,10 @@ int check_extended_regs_support(void) return -1; } -int check_pvr_for_sampling_tests(void) +int platform_check_for_tests(void) { pvr = PVR_VER(mfspr(SPRN_PVR)); - platform_extended_mask = perf_get_platform_reg_mask(); - /* * Check for supported platforms * for sampling test @@ -136,19 +136,33 @@ int check_pvr_for_sampling_tests(void) * Check PMU driver registered by looking for * PPC_FEATURE2_EBB bit in AT_HWCAP2 */ - if (!have_hwcap2(PPC_FEATURE2_EBB)) + if (!have_hwcap2(PPC_FEATURE2_EBB) || !have_hwcap2(PPC_FEATURE2_ARCH_3_00)) goto out; + return 0; + +out: + printf("%s: Tests unsupported for this platform\n", __func__); + return -1; +} + +int check_pvr_for_sampling_tests(void) +{ + SKIP_IF(platform_check_for_tests()); + + platform_extended_mask = perf_get_platform_reg_mask(); /* check if platform supports extended regs */ if (check_extended_regs_support()) goto out; init_ev_encodes(); return 0; + out: printf("%s: Sampling tests un-supported\n", __func__); return -1; } + /* * Allocate mmap buffer of "mmap_pages" number of * pages. @@ -257,13 +271,32 @@ u64 *get_intr_regs(struct event *event, void *sample_buff) u64 *intr_regs; size_t size = 0; - if ((type ^ PERF_SAMPLE_REGS_INTR)) + if ((type ^ (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_BRANCH_STACK)) && + (type ^ PERF_SAMPLE_REGS_INTR)) return NULL; intr_regs = (u64 *)perf_read_first_sample(sample_buff, &size); if (!intr_regs) return NULL; + if (type & PERF_SAMPLE_BRANCH_STACK) { + /* + * PERF_RECORD_SAMPLE and PERF_SAMPLE_BRANCH_STACK: + * struct { + * struct perf_event_header hdr; + * u64 number_of_branches; + * struct perf_branch_entry[number_of_branches]; + * u64 data[]; + * }; + * struct perf_branch_entry { + * u64 from; + * u64 to; + * u64 misc; + * }; + */ + intr_regs += ((*intr_regs) * 3) + 1; + } + /* * First entry in the sample buffer used to specify * PERF_SAMPLE_REGS_ABI_64, skip perf regs abi to access @@ -410,3 +443,95 @@ u64 get_reg_value(u64 *intr_regs, char *register_name) return *(intr_regs + register_bit_position); } + +int get_thresh_cmp_val(struct event event) +{ + int exp = 0; + u64 result = 0; + u64 value; + + if (!have_hwcap2(PPC_FEATURE2_ARCH_3_1)) + return EV_CODE_EXTRACT(event.attr.config, thd_cmp); + + value = EV_CODE_EXTRACT(event.attr.config1, thd_cmp); + + if (!value) + return value; + + /* + * Incase of P10, thresh_cmp value is not part of raw event code + * and provided via attr.config1 parameter. To program threshold in MMCRA, + * take a 18 bit number N and shift right 2 places and increment + * the exponent E by 1 until the upper 10 bits of N are zero. + * Write E to the threshold exponent and write the lower 8 bits of N + * to the threshold mantissa. + * The max threshold that can be written is 261120. + */ + if (value > 261120) + value = 261120; + while ((64 - __builtin_clzl(value)) > 8) { + exp++; + value >>= 2; + } + + /* + * Note that it is invalid to write a mantissa with the + * upper 2 bits of mantissa being zero, unless the + * exponent is also zero. + */ + if (!(value & 0xC0) && exp) + result = -1; + else + result = (exp << 8) | value; + return result; +} + +/* + * Utility function to check for generic compat PMU + * by comparing base_platform value from auxv and real + * PVR value. + */ +static bool auxv_generic_compat_pmu(void) +{ + int base_pvr = 0; + + if (!strcmp(auxv_base_platform(), "power9")) + base_pvr = POWER9; + else if (!strcmp(auxv_base_platform(), "power10")) + base_pvr = POWER10; + + return (!base_pvr); +} + +/* + * Check for generic compat PMU. + * First check for presence of pmu_name from + * "/sys/bus/event_source/devices/cpu/caps". + * If doesn't exist, fallback to using value + * auxv. + */ +bool check_for_generic_compat_pmu(void) +{ + char pmu_name[256]; + + memset(pmu_name, 0, sizeof(pmu_name)); + if (read_sysfs_file("bus/event_source/devices/cpu/caps/pmu_name", + pmu_name, sizeof(pmu_name)) < 0) + return auxv_generic_compat_pmu(); + + if (!strcmp(pmu_name, "ISAv3")) + return true; + else + return false; +} + +/* + * Check if system is booted in compat mode. + */ +bool check_for_compat_mode(void) +{ + char *platform = auxv_platform(); + char *base_platform = auxv_base_platform(); + + return strcmp(platform, base_platform); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h index 7675f3177725..4181755cf5a0 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h @@ -5,6 +5,7 @@ * Copyright 2022, Kajol Jain, IBM Corp. */ +#include <sys/stat.h> #include "../event.h" #define POWER10 0x80 @@ -17,6 +18,8 @@ #define MMCR1_RSQ 0x200000000000ULL /* radix scope qual field */ #define BHRB_DISABLE 0x2000000000ULL /* MMCRA BHRB DISABLE bit */ +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + extern int ev_mask_pmcxsel, ev_shift_pmcxsel; extern int ev_mask_marked, ev_shift_marked; extern int ev_mask_comb, ev_shift_comb; @@ -35,6 +38,7 @@ extern int ev_mask_mmcr3_src, ev_shift_mmcr3_src; extern int pvr; extern u64 platform_extended_mask; extern int check_pvr_for_sampling_tests(void); +extern int platform_check_for_tests(void); /* * Event code field extraction macro. @@ -52,6 +56,9 @@ void *__event_read_samples(void *sample_buff, size_t *size, u64 *sample_count); int collect_samples(void *sample_buff); u64 *get_intr_regs(struct event *event, void *sample_buff); u64 get_reg_value(u64 *intr_regs, char *register_name); +int get_thresh_cmp_val(struct event event); +bool check_for_generic_compat_pmu(void); +bool check_for_compat_mode(void); static inline int get_mmcr0_fc56(u64 mmcr0, int pmc) { @@ -184,7 +191,7 @@ static inline int get_mmcra_sm(u64 mmcra, int pmc) return ((mmcra >> 42) & 0x3); } -static inline int get_mmcra_bhrb_disable(u64 mmcra, int pmc) +static inline u64 get_mmcra_bhrb_disable(u64 mmcra, int pmc) { if (pvr == POWER10) return mmcra & BHRB_DISABLE; diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_sel_unit_cache_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_sel_unit_cache_test.c new file mode 100644 index 000000000000..f0c003282630 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_sel_unit_cache_test.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +#define MALLOC_SIZE (0x10000 * 10) /* Ought to be enough .. */ + +/* The data cache was reloaded from local core's L3 due to a demand load */ +#define EventCode 0x21c040 + +/* + * A perf sampling test for mmcr1 + * fields : pmcxsel, unit, cache. + */ +static int mmcr1_sel_unit_cache(void) +{ + struct event event; + u64 *intr_regs; + char *p; + int i; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + p = malloc(MALLOC_SIZE); + FAIL_IF(!p); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.sample_period = 1; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + event_enable(&event); + + /* workload to make the event overflow */ + for (i = 0; i < MALLOC_SIZE; i += 0x10000) + p[i] = i; + + event_disable(&event); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that pmcxsel, unit and cache field of MMCR1 + * match with corresponding event code fields + */ + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, pmcxsel) != + get_mmcr1_pmcxsel(get_reg_value(intr_regs, "MMCR1"), 1)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, unit) != + get_mmcr1_unit(get_reg_value(intr_regs, "MMCR1"), 1)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, cache) != + get_mmcr1_cache(get_reg_value(intr_regs, "MMCR1"), 1)); + + free(p); + event_close(&event); + return 0; +} + +int main(void) +{ + FAIL_IF(test_harness(mmcr1_sel_unit_cache, "mmcr1_sel_unit_cache")); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_any_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_any_test.c new file mode 100644 index 000000000000..14854694af62 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_any_test.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* Instructions */ +#define EventCode 0x500fa + +/* ifm field for any branch mode */ +#define IFM_ANY_BRANCH 0x0 + +/* + * A perf sampling test for mmcra + * field: ifm for bhrb any call. + */ +static int mmcra_bhrb_any_test(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + event.attr.branch_sample_type = PERF_SAMPLE_BRANCH_ANY; + event.attr.exclude_kernel = 1; + + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that ifm bit is set properly in MMCRA */ + FAIL_IF(get_mmcra_ifm(get_reg_value(intr_regs, "MMCRA"), 5) != IFM_ANY_BRANCH); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_bhrb_any_test, "mmcra_bhrb_any_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_cond_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_cond_test.c new file mode 100644 index 000000000000..3e08176eb7f8 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_cond_test.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* Instructions */ +#define EventCode 0x500fa + +/* ifm field for conditional branch mode */ +#define IFM_COND_BRANCH 0x3 + +/* + * A perf sampling test for mmcra + * field: ifm for bhrb cond call. + */ +static int mmcra_bhrb_cond_test(void) +{ + struct event event; + u64 *intr_regs; + + /* + * Check for platform support for the test. + * This test is only aplicable on power10 + */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + event.attr.branch_sample_type = PERF_SAMPLE_BRANCH_COND; + event.attr.exclude_kernel = 1; + + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that ifm bit is set properly in MMCRA */ + FAIL_IF(get_mmcra_ifm(get_reg_value(intr_regs, "MMCRA"), 5) != IFM_COND_BRANCH); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_bhrb_cond_test, "mmcra_bhrb_cond_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_no_branch_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_no_branch_test.c new file mode 100644 index 000000000000..488c865387e4 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_no_branch_test.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* Instructions */ +#define EventCode 0x500fa + +/* + * A perf sampling test for mmcra + * field: bhrb_disable. + */ +static int mmcra_bhrb_disable_no_branch_test(void) +{ + struct event event; + u64 *intr_regs; + + /* + * Check for platform support for the test. + * This test is only aplicable on power10 + */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.exclude_kernel = 1; + + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that bhrb_disable bit is set in MMCRA for non-branch samples */ + FAIL_IF(!get_mmcra_bhrb_disable(get_reg_value(intr_regs, "MMCRA"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_bhrb_disable_no_branch_test, "mmcra_bhrb_disable_no_branch_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_test.c new file mode 100644 index 000000000000..186a853c0f62 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_disable_test.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* Instructions */ +#define EventCode 0x500fa + +/* + * A perf sampling test for mmcra + * field: bhrb_disable. + */ +static int mmcra_bhrb_disable_test(void) +{ + struct event event; + u64 *intr_regs; + + /* + * Check for platform support for the test. + * This test is only aplicable on power10 + */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + event.attr.branch_sample_type = PERF_SAMPLE_BRANCH_ANY; + event.attr.exclude_kernel = 1; + + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that bhrb_disable bit is set in MMCRA */ + FAIL_IF(get_mmcra_bhrb_disable(get_reg_value(intr_regs, "MMCRA"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_bhrb_disable_test, "mmcra_bhrb_disable_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_ind_call_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_ind_call_test.c new file mode 100644 index 000000000000..f0706730c099 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_bhrb_ind_call_test.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void indirect_branch_loop(void); + +/* Instructions */ +#define EventCode 0x500fa + +/* ifm field for indirect branch mode */ +#define IFM_IND_BRANCH 0x2 + +/* + * A perf sampling test for mmcra + * field: ifm for bhrb ind_call. + */ +static int mmcra_bhrb_ind_call_test(void) +{ + struct event event; + u64 *intr_regs; + + /* + * Check for platform support for the test. + * This test is only aplicable on power10 + */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + event.attr.branch_sample_type = PERF_SAMPLE_BRANCH_IND_CALL; + event.attr.exclude_kernel = 1; + + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + indirect_branch_loop(); + + FAIL_IF(event_disable(&event)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that ifm bit is set properly in MMCRA */ + FAIL_IF(get_mmcra_ifm(get_reg_value(intr_regs, "MMCRA"), 5) != IFM_IND_BRANCH); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_bhrb_ind_call_test, "mmcra_bhrb_ind_call_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_cmp_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_cmp_test.c new file mode 100644 index 000000000000..904362f172c9 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_cmp_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* + * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0) + * Threshold event selection used is issue to complete for cycles + * Sampling criteria is Load only sampling + */ +#define p9_EventCode 0x13E35340401e0 +#define p10_EventCode 0x35340401e0 + +extern void thirty_two_instruction_loop_with_ll_sc(u64 loops, u64 *ll_sc_target); + +/* A perf sampling test to test mmcra fields */ +static int mmcra_thresh_cmp(void) +{ + struct event event; + u64 *intr_regs; + u64 dummy; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Skip for comapt mode */ + SKIP_IF(check_for_compat_mode()); + + /* Init the event for the sampling test */ + if (!have_hwcap2(PPC_FEATURE2_ARCH_3_1)) { + event_init_sampling(&event, p9_EventCode); + } else { + event_init_sampling(&event, p10_EventCode); + event.attr.config1 = 1000; + } + + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop_with_ll_sc(1000000, &dummy); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that thresh cmp match with the corresponding event code fields */ + FAIL_IF(get_thresh_cmp_val(event) != + get_mmcra_thd_cmp(get_reg_value(intr_regs, "MMCRA"), 4)); + + event_close(&event); + return 0; +} + +int main(void) +{ + FAIL_IF(test_harness(mmcra_thresh_cmp, "mmcra_thresh_cmp")); +} diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index a500639da97a..2f02cb54224d 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -1,15 +1,41 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ - ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \ - ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \ - perf-hwbreak ptrace-syscall ptrace-perf-hwbreak + +TM_TESTS := ptrace-tm-gpr +TM_TESTS += ptrace-tm-spd-gpr +TM_TESTS += ptrace-tm-spd-tar +TM_TESTS += ptrace-tm-spd-vsx +TM_TESTS += ptrace-tm-spr +TM_TESTS += ptrace-tm-tar +TM_TESTS += ptrace-tm-vsx + +TESTS_64 := $(TM_TESTS) +TESTS_64 += core-pkey +TESTS_64 += perf-hwbreak +TESTS_64 += ptrace-hwbreak +TESTS_64 += ptrace-perf-hwbreak +TESTS_64 += ptrace-pkey +TESTS_64 += ptrace-syscall +TESTS_64 += ptrace-tar +TESTS_64 += ptrace-vsx + +TESTS += ptrace-gpr + +TEST_GEN_PROGS := $(TESTS) $(TESTS_64) + +LOCAL_HDRS += $(patsubst %,$(selfdir)/powerpc/ptrace/%,$(wildcard *.h)) top_srcdir = ../../../../.. include ../../lib.mk -CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie +TM_TESTS := $(patsubst %,$(OUTPUT)/%,$(TM_TESTS)) +TESTS_64 := $(patsubst %,$(OUTPUT)/%,$(TESTS_64)) + +$(TESTS_64): CFLAGS += -m64 +$(TM_TESTS): CFLAGS += -I../tm -mhtm + +CFLAGS += -I../../../../../usr/include -fno-pie -$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: child.h +$(OUTPUT)/ptrace-gpr: ptrace-gpr.S $(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread -$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h +$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.S b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.S new file mode 100644 index 000000000000..070e8443e3cc --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.S @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * test helper assembly functions + * + * Copyright (C) 2016 Simon Guo, IBM Corporation. + * Copyright 2022 Michael Ellerman, IBM Corporation. + */ +#include "basic_asm.h" + +#define GPR_SIZE __SIZEOF_LONG__ +#define FIRST_GPR 14 +#define NUM_GPRS (32 - FIRST_GPR) +#define STACK_SIZE (NUM_GPRS * GPR_SIZE) + +// gpr_child_loop(int *read_flag, int *write_flag, +// unsigned long *gpr_buf, double *fpr_buf); +FUNC_START(gpr_child_loop) + // r3 = read_flag + // r4 = write_flag + // r5 = gpr_buf + // r6 = fpr_buf + PUSH_BASIC_STACK(STACK_SIZE) + + // Save non-volatile GPRs + OP_REGS PPC_STL, GPR_SIZE, FIRST_GPR, 31, %r1, STACK_FRAME_LOCAL(0, 0), FIRST_GPR + + // Load GPRs with expected values + OP_REGS PPC_LL, GPR_SIZE, FIRST_GPR, 31, r5, 0, FIRST_GPR + + // Load FPRs with expected values + OP_REGS lfd, 8, 0, 31, r6 + + // Signal to parent that we're ready + li r0, 1 + stw r0, 0(r4) + + // Wait for parent to finish +1: lwz r0, 0(r3) + cmpwi r0, 0 + beq 1b // Loop while flag is zero + + // Save GPRs back to caller buffer + OP_REGS PPC_STL, GPR_SIZE, FIRST_GPR, 31, r5, 0, FIRST_GPR + + // Save FPRs + OP_REGS stfd, 8, 0, 31, r6 + + // Reload non-volatile GPRs + OP_REGS PPC_LL, GPR_SIZE, FIRST_GPR, 31, %r1, STACK_FRAME_LOCAL(0, 0), FIRST_GPR + + POP_BASIC_STACK(STACK_SIZE) + blr diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c index 17cd480c8780..9ed87d297799 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c @@ -7,72 +7,127 @@ #include "ptrace.h" #include "ptrace-gpr.h" #include "reg.h" +#include <time.h> /* Tracer and Tracee Shared Data */ int shm_id; int *cptr, *pptr; -float a = FPR_1; -float b = FPR_2; -float c = FPR_3; +extern void gpr_child_loop(int *read_flag, int *write_flag, + unsigned long *gpr_buf, double *fpr_buf); -void gpr(void) +unsigned long child_gpr_val, parent_gpr_val; +double child_fpr_val, parent_fpr_val; + +static int child(void) { - unsigned long gpr_buf[18]; - float fpr_buf[32]; + unsigned long gpr_buf[32]; + double fpr_buf[32]; + int i; cptr = (int *)shmat(shm_id, NULL, 0); + memset(gpr_buf, 0, sizeof(gpr_buf)); + memset(fpr_buf, 0, sizeof(fpr_buf)); - asm __volatile__( - ASM_LOAD_GPR_IMMED(gpr_1) - ASM_LOAD_FPR_SINGLE_PRECISION(flt_1) - : - : [gpr_1]"i"(GPR_1), [flt_1] "b" (&a) - : "memory", "r6", "r7", "r8", "r9", "r10", - "r11", "r12", "r13", "r14", "r15", "r16", "r17", - "r18", "r19", "r20", "r21", "r22", "r23", "r24", - "r25", "r26", "r27", "r28", "r29", "r30", "r31" - ); - - cptr[1] = 1; + for (i = 0; i < 32; i++) { + gpr_buf[i] = child_gpr_val; + fpr_buf[i] = child_fpr_val; + } - while (!cptr[0]) - asm volatile("" : : : "memory"); + gpr_child_loop(&cptr[0], &cptr[1], gpr_buf, fpr_buf); shmdt((void *)cptr); - store_gpr(gpr_buf); - store_fpr_single_precision(fpr_buf); - - if (validate_gpr(gpr_buf, GPR_3)) - exit(1); - if (validate_fpr_float(fpr_buf, c)) - exit(1); + FAIL_IF(validate_gpr(gpr_buf, parent_gpr_val)); + FAIL_IF(validate_fpr_double(fpr_buf, parent_fpr_val)); - exit(0); + return 0; } int trace_gpr(pid_t child) { + __u64 tmp, fpr[32], *peeked_fprs; unsigned long gpr[18]; - unsigned long fpr[32]; FAIL_IF(start_trace(child)); + + // Check child GPRs match what we expect using GETREGS FAIL_IF(show_gpr(child, gpr)); - FAIL_IF(validate_gpr(gpr, GPR_1)); + FAIL_IF(validate_gpr(gpr, child_gpr_val)); + + // Check child FPRs match what we expect using GETFPREGS FAIL_IF(show_fpr(child, fpr)); - FAIL_IF(validate_fpr(fpr, FPR_1_REP)); - FAIL_IF(write_gpr(child, GPR_3)); - FAIL_IF(write_fpr(child, FPR_3_REP)); + memcpy(&tmp, &child_fpr_val, sizeof(tmp)); + FAIL_IF(validate_fpr(fpr, tmp)); + + // Check child FPRs match what we expect using PEEKUSR + peeked_fprs = peek_fprs(child); + FAIL_IF(!peeked_fprs); + FAIL_IF(validate_fpr(peeked_fprs, tmp)); + free(peeked_fprs); + + // Write child GPRs using SETREGS + FAIL_IF(write_gpr(child, parent_gpr_val)); + + // Write child FPRs using SETFPREGS + memcpy(&tmp, &parent_fpr_val, sizeof(tmp)); + FAIL_IF(write_fpr(child, tmp)); + + // Check child FPRs match what we just set, using PEEKUSR + peeked_fprs = peek_fprs(child); + FAIL_IF(!peeked_fprs); + FAIL_IF(validate_fpr(peeked_fprs, tmp)); + + // Write child FPRs using POKEUSR + FAIL_IF(poke_fprs(child, (unsigned long *)peeked_fprs)); + + // Child will check its FPRs match before exiting FAIL_IF(stop_trace(child)); return TEST_PASS; } +#ifndef __LONG_WIDTH__ +#define __LONG_WIDTH__ (sizeof(long) * 8) +#endif + +static uint64_t rand_reg(void) +{ + uint64_t result; + long r; + + r = random(); + + // Small values are typical + result = r & 0xffff; + if (r & 0x10000) + return result; + + // Pointers tend to have high bits set + result |= random() << (__LONG_WIDTH__ - 31); + if (r & 0x100000) + return result; + + // And sometimes we want a full 64-bit value + result ^= random() << 16; + + return result; +} + int ptrace_gpr(void) { - pid_t pid; + unsigned long seed; int ret, status; + pid_t pid; + + seed = getpid() ^ time(NULL); + printf("srand(%lu)\n", seed); + srand(seed); + + child_gpr_val = rand_reg(); + child_fpr_val = rand_reg(); + parent_gpr_val = rand_reg(); + parent_fpr_val = rand_reg(); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT); pid = fork(); @@ -81,7 +136,7 @@ int ptrace_gpr(void) return TEST_FAIL; } if (pid == 0) - gpr(); + exit(child()); if (pid) { pptr = (int *)shmat(shm_id, NULL, 0); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.h b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.h index c5cd53181e2e..a5470b88bd08 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.h +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.h @@ -12,10 +12,10 @@ #define FPR_3 0.003 #define FPR_4 0.004 -#define FPR_1_REP 0x3f50624de0000000 -#define FPR_2_REP 0x3f60624de0000000 -#define FPR_3_REP 0x3f689374c0000000 -#define FPR_4_REP 0x3f70624de0000000 +#define FPR_1_REP 0x3f50624dd2f1a9fcull +#define FPR_2_REP 0x3f60624dd2f1a9fcull +#define FPR_3_REP 0x3f689374bc6a7efaull +#define FPR_4_REP 0x3f70624dd2f1a9fcull /* Buffer must have 18 elements */ int validate_gpr(unsigned long *gpr, unsigned long val) @@ -36,13 +36,13 @@ int validate_gpr(unsigned long *gpr, unsigned long val) } /* Buffer must have 32 elements */ -int validate_fpr(unsigned long *fpr, unsigned long val) +int validate_fpr(__u64 *fpr, __u64 val) { int i, found = 1; for (i = 0; i < 32; i++) { if (fpr[i] != val) { - printf("FPR[%d]: %lx Expected: %lx\n", i, fpr[i], val); + printf("FPR[%d]: %llx Expected: %llx\n", i, fpr[i], val); found = 0; } } @@ -53,7 +53,7 @@ int validate_fpr(unsigned long *fpr, unsigned long val) } /* Buffer must have 32 elements */ -int validate_fpr_float(float *fpr, float val) +int validate_fpr_double(double *fpr, double val) { int i, found = 1; diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c index 67ca297c5cca..5dc152b162df 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c @@ -12,15 +12,15 @@ int shm_id; unsigned long *cptr, *pptr; -float a = FPR_1; -float b = FPR_2; -float c = FPR_3; +double a = FPR_1; +double b = FPR_2; +double c = FPR_3; void tm_gpr(void) { unsigned long gpr_buf[18]; unsigned long result, texasr; - float fpr_buf[32]; + double fpr_buf[32]; printf("Starting the child\n"); cptr = (unsigned long *)shmat(shm_id, NULL, 0); @@ -29,12 +29,12 @@ trans: cptr[1] = 0; asm __volatile__( ASM_LOAD_GPR_IMMED(gpr_1) - ASM_LOAD_FPR_SINGLE_PRECISION(flt_1) + ASM_LOAD_FPR(flt_1) "1: ;" "tbegin.;" "beq 2f;" ASM_LOAD_GPR_IMMED(gpr_2) - ASM_LOAD_FPR_SINGLE_PRECISION(flt_2) + ASM_LOAD_FPR(flt_2) "tsuspend.;" "li 7, 1;" "stw 7, 0(%[cptr1]);" @@ -70,12 +70,12 @@ trans: shmdt((void *)cptr); store_gpr(gpr_buf); - store_fpr_single_precision(fpr_buf); + store_fpr(fpr_buf); if (validate_gpr(gpr_buf, GPR_3)) exit(1); - if (validate_fpr_float(fpr_buf, c)) + if (validate_fpr_double(fpr_buf, c)) exit(1); exit(0); @@ -87,7 +87,7 @@ trans: int trace_tm_gpr(pid_t child) { unsigned long gpr[18]; - unsigned long fpr[32]; + __u64 fpr[32]; FAIL_IF(start_trace(child)); FAIL_IF(show_gpr(child, gpr)); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c index 6f2bce1b6c5d..458cc1a70ccf 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c @@ -12,10 +12,10 @@ int shm_id; int *cptr, *pptr; -float a = FPR_1; -float b = FPR_2; -float c = FPR_3; -float d = FPR_4; +double a = FPR_1; +double b = FPR_2; +double c = FPR_3; +double d = FPR_4; __attribute__((used)) void wait_parent(void) { @@ -28,7 +28,7 @@ void tm_spd_gpr(void) { unsigned long gpr_buf[18]; unsigned long result, texasr; - float fpr_buf[32]; + double fpr_buf[32]; cptr = (int *)shmat(shm_id, NULL, 0); @@ -36,7 +36,7 @@ trans: cptr[2] = 0; asm __volatile__( ASM_LOAD_GPR_IMMED(gpr_1) - ASM_LOAD_FPR_SINGLE_PRECISION(flt_1) + ASM_LOAD_FPR(flt_1) "1: ;" "tbegin.;" @@ -45,7 +45,7 @@ trans: ASM_LOAD_GPR_IMMED(gpr_2) "tsuspend.;" ASM_LOAD_GPR_IMMED(gpr_4) - ASM_LOAD_FPR_SINGLE_PRECISION(flt_4) + ASM_LOAD_FPR(flt_4) "bl wait_parent;" "tresume.;" @@ -77,12 +77,12 @@ trans: shmdt((void *)cptr); store_gpr(gpr_buf); - store_fpr_single_precision(fpr_buf); + store_fpr(fpr_buf); if (validate_gpr(gpr_buf, GPR_3)) exit(1); - if (validate_fpr_float(fpr_buf, c)) + if (validate_fpr_double(fpr_buf, c)) exit(1); exit(0); } @@ -93,7 +93,7 @@ trans: int trace_tm_spd_gpr(pid_t child) { unsigned long gpr[18]; - unsigned long fpr[32]; + __u64 fpr[32]; FAIL_IF(start_trace(child)); FAIL_IF(show_gpr(child, gpr)); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace.h b/tools/testing/selftests/powerpc/ptrace/ptrace.h index 5181ad9b4b6c..4e0233c0f2b3 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace.h +++ b/tools/testing/selftests/powerpc/ptrace/ptrace.h @@ -4,6 +4,9 @@ * * Copyright (C) 2015 Anshuman Khandual, IBM Corporation. */ + +#define __SANE_USERSPACE_TYPES__ + #include <inttypes.h> #include <unistd.h> #include <stdlib.h> @@ -20,6 +23,7 @@ #include <sys/ipc.h> #include <sys/shm.h> #include <sys/user.h> +#include <sys/syscall.h> #include <linux/elf.h> #include <linux/types.h> #include <linux/auxvec.h> @@ -30,8 +34,8 @@ #define TEST_FAIL 1 struct fpr_regs { - unsigned long fpr[32]; - unsigned long fpscr; + __u64 fpr[32]; + __u64 fpscr; }; struct tm_spr_regs { @@ -318,7 +322,7 @@ fail: } /* FPR */ -int show_fpr(pid_t child, unsigned long *fpr) +int show_fpr(pid_t child, __u64 *fpr) { struct fpr_regs *regs; int ret, i; @@ -337,7 +341,7 @@ int show_fpr(pid_t child, unsigned long *fpr) return TEST_PASS; } -int write_fpr(pid_t child, unsigned long val) +int write_fpr(pid_t child, __u64 val) { struct fpr_regs *regs; int ret, i; @@ -360,7 +364,7 @@ int write_fpr(pid_t child, unsigned long val) return TEST_PASS; } -int show_ckpt_fpr(pid_t child, unsigned long *fpr) +int show_ckpt_fpr(pid_t child, __u64 *fpr) { struct fpr_regs *regs; struct iovec iov; @@ -437,6 +441,70 @@ int show_gpr(pid_t child, unsigned long *gpr) return TEST_PASS; } +long sys_ptrace(enum __ptrace_request request, pid_t pid, unsigned long addr, unsigned long data) +{ + return syscall(__NR_ptrace, request, pid, (void *)addr, data); +} + +// 33 because of FPSCR +#define PT_NUM_FPRS (33 * (sizeof(__u64) / sizeof(unsigned long))) + +__u64 *peek_fprs(pid_t child) +{ + unsigned long *fprs, *p, addr; + long ret; + int i; + + fprs = malloc(sizeof(unsigned long) * PT_NUM_FPRS); + if (!fprs) { + perror("malloc() failed"); + return NULL; + } + + for (i = 0, p = fprs; i < PT_NUM_FPRS; i++, p++) { + addr = sizeof(unsigned long) * (PT_FPR0 + i); + ret = sys_ptrace(PTRACE_PEEKUSER, child, addr, (unsigned long)p); + if (ret) { + perror("ptrace(PTRACE_PEEKUSR) failed"); + return NULL; + } + } + + addr = sizeof(unsigned long) * (PT_FPR0 + i); + ret = sys_ptrace(PTRACE_PEEKUSER, child, addr, (unsigned long)&addr); + if (!ret) { + printf("ptrace(PTRACE_PEEKUSR) succeeded unexpectedly!\n"); + return NULL; + } + + return (__u64 *)fprs; +} + +int poke_fprs(pid_t child, unsigned long *fprs) +{ + unsigned long *p, addr; + long ret; + int i; + + for (i = 0, p = fprs; i < PT_NUM_FPRS; i++, p++) { + addr = sizeof(unsigned long) * (PT_FPR0 + i); + ret = sys_ptrace(PTRACE_POKEUSER, child, addr, *p); + if (ret) { + perror("ptrace(PTRACE_POKEUSR) failed"); + return -1; + } + } + + addr = sizeof(unsigned long) * (PT_FPR0 + i); + ret = sys_ptrace(PTRACE_POKEUSER, child, addr, addr); + if (!ret) { + printf("ptrace(PTRACE_POKEUSR) succeeded unexpectedly!\n"); + return -1; + } + + return 0; +} + int write_gpr(pid_t child, unsigned long val) { struct pt_regs *regs; @@ -742,4 +810,3 @@ void analyse_texasr(unsigned long texasr) } void store_gpr(unsigned long *addr); -void store_fpr(float *addr); diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index 93614b125ded..9357b186b13c 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -2,3 +2,4 @@ rfi_flush entry_flush spectre_v2 +uaccess_flush diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 28604c9f805c..e5962f4794f5 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -211,10 +211,19 @@ static int make_exe(const uint8_t *payload, size_t len) } #endif -static bool g_vsyscall = false; +/* + * 0: vsyscall VMA doesn't exist vsyscall=none + * 1: vsyscall VMA is r-xp vsyscall=emulate + * 2: vsyscall VMA is --xp vsyscall=xonly + */ +static int g_vsyscall; +static const char *str_vsyscall; -static const char str_vsyscall[] = +static const char str_vsyscall_0[] = ""; +static const char str_vsyscall_1[] = "ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall]\n"; +static const char str_vsyscall_2[] = +"ffffffffff600000-ffffffffff601000 --xp 00000000 00:00 0 [vsyscall]\n"; #ifdef __x86_64__ static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___) @@ -223,7 +232,7 @@ static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___) } /* - * vsyscall page can't be unmapped, probe it with memory load. + * vsyscall page can't be unmapped, probe it directly. */ static void vsyscall(void) { @@ -246,13 +255,52 @@ static void vsyscall(void) act.sa_sigaction = sigaction_SIGSEGV; (void)sigaction(SIGSEGV, &act, NULL); + /* gettimeofday(NULL, NULL); */ + asm volatile ( + "call %P0" + : + : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL) + : "rax", "rcx", "r11" + ); + exit(0); + } + waitpid(pid, &wstatus, 0); + if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0) { + /* vsyscall page exists and is executable. */ + } else { + /* vsyscall page doesn't exist. */ + g_vsyscall = 0; + return; + } + + pid = fork(); + if (pid < 0) { + fprintf(stderr, "fork, errno %d\n", errno); + exit(1); + } + if (pid == 0) { + struct rlimit rlim = {0, 0}; + (void)setrlimit(RLIMIT_CORE, &rlim); + + /* Hide "segfault at ffffffffff600000" messages. */ + struct sigaction act; + memset(&act, 0, sizeof(struct sigaction)); + act.sa_flags = SA_SIGINFO; + act.sa_sigaction = sigaction_SIGSEGV; + (void)sigaction(SIGSEGV, &act, NULL); + *(volatile int *)0xffffffffff600000UL; exit(0); } waitpid(pid, &wstatus, 0); if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0) { - g_vsyscall = true; + /* vsyscall page is readable and executable. */ + g_vsyscall = 1; + return; } + + /* vsyscall page is executable but unreadable. */ + g_vsyscall = 2; } int main(void) @@ -261,6 +309,19 @@ int main(void) int exec_fd; vsyscall(); + switch (g_vsyscall) { + case 0: + str_vsyscall = str_vsyscall_0; + break; + case 1: + str_vsyscall = str_vsyscall_1; + break; + case 2: + str_vsyscall = str_vsyscall_2; + break; + default: + abort(); + } atexit(ate); @@ -314,7 +375,7 @@ int main(void) /* Test /proc/$PID/maps */ { - const size_t len = strlen(buf0) + (g_vsyscall ? strlen(str_vsyscall) : 0); + const size_t len = strlen(buf0) + strlen(str_vsyscall); char buf[256]; ssize_t rv; int fd; @@ -327,7 +388,7 @@ int main(void) rv = read(fd, buf, sizeof(buf)); assert(rv == len); assert(memcmp(buf, buf0, strlen(buf0)) == 0); - if (g_vsyscall) { + if (g_vsyscall > 0) { assert(memcmp(buf + strlen(buf0), str_vsyscall, strlen(str_vsyscall)) == 0); } } @@ -374,7 +435,7 @@ int main(void) assert(memmem(buf, rv, S[i], strlen(S[i]))); } - if (g_vsyscall) { + if (g_vsyscall > 0) { assert(memmem(buf, rv, str_vsyscall, strlen(str_vsyscall))); } } diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h index 02d775789ea7..d8587c971941 100644 --- a/tools/testing/selftests/sgx/defines.h +++ b/tools/testing/selftests/sgx/defines.h @@ -24,6 +24,9 @@ enum encl_op_type { ENCL_OP_PUT_TO_ADDRESS, ENCL_OP_GET_FROM_ADDRESS, ENCL_OP_NOP, + ENCL_OP_EACCEPT, + ENCL_OP_EMODPE, + ENCL_OP_INIT_TCS_PAGE, ENCL_OP_MAX, }; @@ -53,4 +56,24 @@ struct encl_op_get_from_addr { uint64_t addr; }; +struct encl_op_eaccept { + struct encl_op_header header; + uint64_t epc_addr; + uint64_t flags; + uint64_t ret; +}; + +struct encl_op_emodpe { + struct encl_op_header header; + uint64_t epc_addr; + uint64_t flags; +}; + +struct encl_op_init_tcs_page { + struct encl_op_header header; + uint64_t tcs_page; + uint64_t ssa; + uint64_t entry; +}; + #endif /* DEFINES_H */ diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 006b464c8fc9..94bdeac1cf04 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -130,6 +130,47 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) return true; } +/* + * Parse the enclave code's symbol table to locate and return address of + * the provided symbol + */ +uint64_t encl_get_entry(struct encl *encl, const char *symbol) +{ + Elf64_Shdr *sections; + Elf64_Sym *symtab; + Elf64_Ehdr *ehdr; + char *sym_names; + int num_sym; + int i; + + ehdr = encl->bin; + sections = encl->bin + ehdr->e_shoff; + + for (i = 0; i < ehdr->e_shnum; i++) { + if (sections[i].sh_type == SHT_SYMTAB) { + symtab = (Elf64_Sym *)((char *)encl->bin + sections[i].sh_offset); + num_sym = sections[i].sh_size / sections[i].sh_entsize; + break; + } + } + + for (i = 0; i < ehdr->e_shnum; i++) { + if (sections[i].sh_type == SHT_STRTAB) { + sym_names = (char *)encl->bin + sections[i].sh_offset; + break; + } + } + + for (i = 0; i < num_sym; i++) { + Elf64_Sym *sym = &symtab[i]; + + if (!strcmp(symbol, sym_names + sym->st_name)) + return (uint64_t)sym->st_value; + } + + return 0; +} + bool encl_load(const char *path, struct encl *encl, unsigned long heap_size) { const char device_path[] = "/dev/sgx_enclave"; diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index dd74fa42302e..9820b3809c69 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -25,6 +25,18 @@ static const uint64_t MAGIC = 0x1122334455667788ULL; static const uint64_t MAGIC2 = 0x8877665544332211ULL; vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave; +/* + * Security Information (SECINFO) data structure needed by a few SGX + * instructions (eg. ENCLU[EACCEPT] and ENCLU[EMODPE]) holds meta-data + * about an enclave page. &enum sgx_secinfo_page_state specifies the + * secinfo flags used for page state. + */ +enum sgx_secinfo_page_state { + SGX_SECINFO_PENDING = (1 << 3), + SGX_SECINFO_MODIFIED = (1 << 4), + SGX_SECINFO_PR = (1 << 5), +}; + struct vdso_symtab { Elf64_Sym *elf_symtab; const char *elf_symstrtab; @@ -74,6 +86,15 @@ static bool vdso_get_symtab(void *addr, struct vdso_symtab *symtab) return true; } +static inline int sgx2_supported(void) +{ + unsigned int eax, ebx, ecx, edx; + + __cpuid_count(SGX_CPUID, 0x0, eax, ebx, ecx, edx); + + return eax & 0x2; +} + static unsigned long elf_sym_hash(const char *name) { unsigned long h = 0, high; @@ -110,6 +131,24 @@ static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name) } /* + * Return the offset in the enclave where the TCS segment can be found. + * The first RW segment loaded is the TCS. + */ +static off_t encl_get_tcs_offset(struct encl *encl) +{ + int i; + + for (i = 0; i < encl->nr_segments; i++) { + struct encl_segment *seg = &encl->segment_tbl[i]; + + if (i == 0 && seg->prot == (PROT_READ | PROT_WRITE)) + return seg->offset; + } + + return -1; +} + +/* * Return the offset in the enclave where the data segment can be found. * The first RW segment loaded is the TCS, skip that to get info on the * data segment. @@ -339,7 +378,127 @@ TEST_F(enclave, unclobbered_vdso_oversubscribed) EXPECT_EQ(get_op.value, MAGIC); EXPECT_EEXIT(&self->run); EXPECT_EQ(self->run.user_data, 0); +} + +TEST_F_TIMEOUT(enclave, unclobbered_vdso_oversubscribed_remove, 900) +{ + struct sgx_enclave_remove_pages remove_ioc; + struct sgx_enclave_modify_types modt_ioc; + struct encl_op_get_from_buf get_op; + struct encl_op_eaccept eaccept_op; + struct encl_op_put_to_buf put_op; + struct encl_segment *heap; + unsigned long total_mem; + int ret, errno_save; + unsigned long addr; + unsigned long i; + + /* + * Create enclave with additional heap that is as big as all + * available physical SGX memory. + */ + total_mem = get_total_epc_mem(); + ASSERT_NE(total_mem, 0); + TH_LOG("Creating an enclave with %lu bytes heap may take a while ...", + total_mem); + ASSERT_TRUE(setup_test_encl(total_mem, &self->encl, _metadata)); + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* SGX2 is supported by kernel and hardware, test can proceed. */ + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + heap = &self->encl.segment_tbl[self->encl.nr_segments - 1]; + + put_op.header.type = ENCL_OP_PUT_TO_BUFFER; + put_op.value = MAGIC; + + EXPECT_EQ(ENCL_CALL(&put_op, &self->run, false), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.user_data, 0); + + get_op.header.type = ENCL_OP_GET_FROM_BUFFER; + get_op.value = 0; + + EXPECT_EQ(ENCL_CALL(&get_op, &self->run, false), 0); + + EXPECT_EQ(get_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.user_data, 0); + + /* Trim entire heap. */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + + modt_ioc.offset = heap->offset; + modt_ioc.length = heap->size; + modt_ioc.page_type = SGX_PAGE_TYPE_TRIM; + + TH_LOG("Changing type of %zd bytes to trimmed may take a while ...", + heap->size); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(modt_ioc.result, 0); + EXPECT_EQ(modt_ioc.count, heap->size); + + /* EACCEPT all removed pages. */ + addr = self->encl.encl_base + heap->offset; + + eaccept_op.flags = SGX_SECINFO_TRIM | SGX_SECINFO_MODIFIED; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + TH_LOG("Entering enclave to run EACCEPT for each page of %zd bytes may take a while ...", + heap->size); + for (i = 0; i < heap->size; i += 4096) { + eaccept_op.epc_addr = addr + i; + eaccept_op.ret = 0; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + ASSERT_EQ(eaccept_op.ret, 0); + ASSERT_EQ(self->run.function, EEXIT); + } + + /* Complete page removal. */ + memset(&remove_ioc, 0, sizeof(remove_ioc)); + + remove_ioc.offset = heap->offset; + remove_ioc.length = heap->size; + + TH_LOG("Removing %zd bytes from enclave may take a while ...", + heap->size); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_REMOVE_PAGES, &remove_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(remove_ioc.count, heap->size); } TEST_F(enclave, clobbered_vdso) @@ -555,4 +714,1280 @@ TEST_F(enclave, pte_permissions) EXPECT_EQ(self->run.exception_addr, 0); } +/* + * Modifying permissions of TCS page should not be possible. + */ +TEST_F(enclave, tcs_permissions) +{ + struct sgx_enclave_restrict_permissions ioc; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + memset(&ioc, 0, sizeof(ioc)); + + /* + * Ensure kernel supports needed ioctl() and system supports needed + * commands. + */ + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS, &ioc); + errno_save = ret == -1 ? errno : 0; + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + ASSERT_EQ(ret, -1); + + /* ret == -1 */ + if (errno_save == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS ioctl()"); + else if (errno_save == ENODEV) + SKIP(return, "System does not support SGX2"); + + /* + * Attempt to make TCS page read-only. This is not allowed and + * should be prevented by the kernel. + */ + ioc.offset = encl_get_tcs_offset(&self->encl); + ioc.length = PAGE_SIZE; + ioc.permissions = SGX_SECINFO_R; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS, &ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno_save, EINVAL); + EXPECT_EQ(ioc.result, 0); + EXPECT_EQ(ioc.count, 0); +} + +/* + * Enclave page permission test. + * + * Modify and restore enclave page's EPCM (enclave) permissions from + * outside enclave (ENCLS[EMODPR] via kernel) as well as from within + * enclave (via ENCLU[EMODPE]). Check for page fault if + * VMA allows access but EPCM permissions do not. + */ +TEST_F(enclave, epcm_permissions) +{ + struct sgx_enclave_restrict_permissions restrict_ioc; + struct encl_op_get_from_addr get_addr_op; + struct encl_op_put_to_addr put_addr_op; + struct encl_op_eaccept eaccept_op; + struct encl_op_emodpe emodpe_op; + unsigned long data_start; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + /* + * Ensure kernel supports needed ioctl() and system supports needed + * commands. + */ + memset(&restrict_ioc, 0, sizeof(restrict_ioc)); + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS, + &restrict_ioc); + errno_save = ret == -1 ? errno : 0; + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + ASSERT_EQ(ret, -1); + + /* ret == -1 */ + if (errno_save == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS ioctl()"); + else if (errno_save == ENODEV) + SKIP(return, "System does not support SGX2"); + + /* + * Page that will have its permissions changed is the second data + * page in the .data segment. This forms part of the local encl_buffer + * within the enclave. + * + * At start of test @data_start should have EPCM as well as PTE and + * VMA permissions of RW. + */ + + data_start = self->encl.encl_base + + encl_get_data_offset(&self->encl) + PAGE_SIZE; + + /* + * Sanity check that page at @data_start is writable before making + * any changes to page permissions. + * + * Start by writing MAGIC to test page. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = data_start; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory that was just written to, confirming that + * page is writable. + */ + get_addr_op.value = 0; + get_addr_op.addr = data_start; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Change EPCM permissions to read-only. Kernel still considers + * the page writable. + */ + memset(&restrict_ioc, 0, sizeof(restrict_ioc)); + + restrict_ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + restrict_ioc.length = PAGE_SIZE; + restrict_ioc.permissions = SGX_SECINFO_R; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS, + &restrict_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(restrict_ioc.result, 0); + EXPECT_EQ(restrict_ioc.count, 4096); + + /* + * EPCM permissions changed from kernel, need to EACCEPT from enclave. + */ + eaccept_op.epc_addr = data_start; + eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_REG | SGX_SECINFO_PR; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* + * EPCM permissions of page is now read-only, expect #PF + * on EPCM when attempting to write to page from within enclave. + */ + put_addr_op.value = MAGIC2; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EQ(self->run.function, ERESUME); + EXPECT_EQ(self->run.exception_vector, 14); + EXPECT_EQ(self->run.exception_error_code, 0x8007); + EXPECT_EQ(self->run.exception_addr, data_start); + + self->run.exception_vector = 0; + self->run.exception_error_code = 0; + self->run.exception_addr = 0; + + /* + * Received AEX but cannot return to enclave at same entrypoint, + * need different TCS from where EPCM permission can be made writable + * again. + */ + self->run.tcs = self->encl.encl_base + PAGE_SIZE; + + /* + * Enter enclave at new TCS to change EPCM permissions to be + * writable again and thus fix the page fault that triggered the + * AEX. + */ + + emodpe_op.epc_addr = data_start; + emodpe_op.flags = SGX_SECINFO_R | SGX_SECINFO_W; + emodpe_op.header.type = ENCL_OP_EMODPE; + + EXPECT_EQ(ENCL_CALL(&emodpe_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Attempt to return to main TCS to resume execution at faulting + * instruction, PTE should continue to allow writing to the page. + */ + self->run.tcs = self->encl.encl_base; + + /* + * Wrong page permissions that caused original fault has + * now been fixed via EPCM permissions. + * Resume execution in main TCS to re-attempt the memory access. + */ + self->run.tcs = self->encl.encl_base; + + EXPECT_EQ(vdso_sgx_enter_enclave((unsigned long)&put_addr_op, 0, 0, + ERESUME, 0, 0, + &self->run), + 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + get_addr_op.value = 0; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC2); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.user_data, 0); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); +} + +/* + * Test the addition of pages to an initialized enclave via writing to + * a page belonging to the enclave's address space but was not added + * during enclave creation. + */ +TEST_F(enclave, augment) +{ + struct encl_op_get_from_addr get_addr_op; + struct encl_op_put_to_addr put_addr_op; + struct encl_op_eaccept eaccept_op; + size_t total_size = 0; + void *addr; + int i; + + if (!sgx2_supported()) + SKIP(return, "SGX2 not supported"); + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + for (i = 0; i < self->encl.nr_segments; i++) { + struct encl_segment *seg = &self->encl.segment_tbl[i]; + + total_size += seg->size; + } + + /* + * Actual enclave size is expected to be larger than the loaded + * test enclave since enclave size must be a power of 2 in bytes + * and test_encl does not consume it all. + */ + EXPECT_LT(total_size + PAGE_SIZE, self->encl.encl_size); + + /* + * Create memory mapping for the page that will be added. New + * memory mapping is for one page right after all existing + * mappings. + * Kernel will allow new mapping using any permissions if it + * falls into the enclave's address range but not backed + * by existing enclave pages. + */ + addr = mmap((void *)self->encl.encl_base + total_size, PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_SHARED | MAP_FIXED, self->encl.fd, 0); + EXPECT_NE(addr, MAP_FAILED); + + self->run.exception_vector = 0; + self->run.exception_error_code = 0; + self->run.exception_addr = 0; + + /* + * Attempt to write to the new page from within enclave. + * Expected to fail since page is not (yet) part of the enclave. + * The first #PF will trigger the addition of the page to the + * enclave, but since the new page needs an EACCEPT from within the + * enclave before it can be used it would not be possible + * to successfully return to the failing instruction. This is the + * cause of the second #PF captured here having the SGX bit set, + * it is from hardware preventing the page from being used. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = (unsigned long)addr; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EQ(self->run.function, ERESUME); + EXPECT_EQ(self->run.exception_vector, 14); + EXPECT_EQ(self->run.exception_addr, (unsigned long)addr); + + if (self->run.exception_error_code == 0x6) { + munmap(addr, PAGE_SIZE); + SKIP(return, "Kernel does not support adding pages to initialized enclave"); + } + + EXPECT_EQ(self->run.exception_error_code, 0x8007); + + self->run.exception_vector = 0; + self->run.exception_error_code = 0; + self->run.exception_addr = 0; + + /* Handle AEX by running EACCEPT from new entry point. */ + self->run.tcs = self->encl.encl_base + PAGE_SIZE; + + eaccept_op.epc_addr = self->encl.encl_base + total_size; + eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_REG | SGX_SECINFO_PENDING; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* Can now return to main TCS to resume execution. */ + self->run.tcs = self->encl.encl_base; + + EXPECT_EQ(vdso_sgx_enter_enclave((unsigned long)&put_addr_op, 0, 0, + ERESUME, 0, 0, + &self->run), + 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory from newly added page that was just written to, + * confirming that data previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = (unsigned long)addr; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + munmap(addr, PAGE_SIZE); +} + +/* + * Test for the addition of pages to an initialized enclave via a + * pre-emptive run of EACCEPT on page to be added. + */ +TEST_F(enclave, augment_via_eaccept) +{ + struct encl_op_get_from_addr get_addr_op; + struct encl_op_put_to_addr put_addr_op; + struct encl_op_eaccept eaccept_op; + size_t total_size = 0; + void *addr; + int i; + + if (!sgx2_supported()) + SKIP(return, "SGX2 not supported"); + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + for (i = 0; i < self->encl.nr_segments; i++) { + struct encl_segment *seg = &self->encl.segment_tbl[i]; + + total_size += seg->size; + } + + /* + * Actual enclave size is expected to be larger than the loaded + * test enclave since enclave size must be a power of 2 in bytes while + * test_encl does not consume it all. + */ + EXPECT_LT(total_size + PAGE_SIZE, self->encl.encl_size); + + /* + * mmap() a page at end of existing enclave to be used for dynamic + * EPC page. + * + * Kernel will allow new mapping using any permissions if it + * falls into the enclave's address range but not backed + * by existing enclave pages. + */ + + addr = mmap((void *)self->encl.encl_base + total_size, PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, MAP_SHARED | MAP_FIXED, + self->encl.fd, 0); + EXPECT_NE(addr, MAP_FAILED); + + self->run.exception_vector = 0; + self->run.exception_error_code = 0; + self->run.exception_addr = 0; + + /* + * Run EACCEPT on new page to trigger the #PF->EAUG->EACCEPT(again + * without a #PF). All should be transparent to userspace. + */ + eaccept_op.epc_addr = self->encl.encl_base + total_size; + eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_REG | SGX_SECINFO_PENDING; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + if (self->run.exception_vector == 14 && + self->run.exception_error_code == 4 && + self->run.exception_addr == self->encl.encl_base + total_size) { + munmap(addr, PAGE_SIZE); + SKIP(return, "Kernel does not support adding pages to initialized enclave"); + } + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* + * New page should be accessible from within enclave - attempt to + * write to it. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = (unsigned long)addr; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory from newly added page that was just written to, + * confirming that data previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = (unsigned long)addr; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + munmap(addr, PAGE_SIZE); +} + +/* + * SGX2 page type modification test in two phases: + * Phase 1: + * Create a new TCS, consisting out of three new pages (stack page with regular + * page type, SSA page with regular page type, and TCS page with TCS page + * type) in an initialized enclave and run a simple workload within it. + * Phase 2: + * Remove the three pages added in phase 1, add a new regular page at the + * same address that previously hosted the TCS page and verify that it can + * be modified. + */ +TEST_F(enclave, tcs_create) +{ + struct encl_op_init_tcs_page init_tcs_page_op; + struct sgx_enclave_remove_pages remove_ioc; + struct encl_op_get_from_addr get_addr_op; + struct sgx_enclave_modify_types modt_ioc; + struct encl_op_put_to_addr put_addr_op; + struct encl_op_get_from_buf get_buf_op; + struct encl_op_put_to_buf put_buf_op; + void *addr, *tcs, *stack_end, *ssa; + struct encl_op_eaccept eaccept_op; + size_t total_size = 0; + uint64_t val_64; + int errno_save; + int ret, i; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, + _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* + * Add three regular pages via EAUG: one will be the TCS stack, one + * will be the TCS SSA, and one will be the new TCS. The stack and + * SSA will remain as regular pages, the TCS page will need its + * type changed after populated with needed data. + */ + for (i = 0; i < self->encl.nr_segments; i++) { + struct encl_segment *seg = &self->encl.segment_tbl[i]; + + total_size += seg->size; + } + + /* + * Actual enclave size is expected to be larger than the loaded + * test enclave since enclave size must be a power of 2 in bytes while + * test_encl does not consume it all. + */ + EXPECT_LT(total_size + 3 * PAGE_SIZE, self->encl.encl_size); + + /* + * mmap() three pages at end of existing enclave to be used for the + * three new pages. + */ + addr = mmap((void *)self->encl.encl_base + total_size, 3 * PAGE_SIZE, + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED, + self->encl.fd, 0); + EXPECT_NE(addr, MAP_FAILED); + + self->run.exception_vector = 0; + self->run.exception_error_code = 0; + self->run.exception_addr = 0; + + stack_end = (void *)self->encl.encl_base + total_size; + tcs = (void *)self->encl.encl_base + total_size + PAGE_SIZE; + ssa = (void *)self->encl.encl_base + total_size + 2 * PAGE_SIZE; + + /* + * Run EACCEPT on each new page to trigger the + * EACCEPT->(#PF)->EAUG->EACCEPT(again without a #PF) flow. + */ + + eaccept_op.epc_addr = (unsigned long)stack_end; + eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_REG | SGX_SECINFO_PENDING; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + if (self->run.exception_vector == 14 && + self->run.exception_error_code == 4 && + self->run.exception_addr == (unsigned long)stack_end) { + munmap(addr, 3 * PAGE_SIZE); + SKIP(return, "Kernel does not support adding pages to initialized enclave"); + } + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + eaccept_op.epc_addr = (unsigned long)ssa; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + eaccept_op.epc_addr = (unsigned long)tcs; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* + * Three new pages added to enclave. Now populate the TCS page with + * needed data. This should be done from within enclave. Provide + * the function that will do the actual data population with needed + * data. + */ + + /* + * New TCS will use the "encl_dyn_entry" entrypoint that expects + * stack to begin in page before TCS page. + */ + val_64 = encl_get_entry(&self->encl, "encl_dyn_entry"); + EXPECT_NE(val_64, 0); + + init_tcs_page_op.tcs_page = (unsigned long)tcs; + init_tcs_page_op.ssa = (unsigned long)total_size + 2 * PAGE_SIZE; + init_tcs_page_op.entry = val_64; + init_tcs_page_op.header.type = ENCL_OP_INIT_TCS_PAGE; + + EXPECT_EQ(ENCL_CALL(&init_tcs_page_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* Change TCS page type to TCS. */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + + modt_ioc.offset = total_size + PAGE_SIZE; + modt_ioc.length = PAGE_SIZE; + modt_ioc.page_type = SGX_PAGE_TYPE_TCS; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(modt_ioc.result, 0); + EXPECT_EQ(modt_ioc.count, 4096); + + /* EACCEPT new TCS page from enclave. */ + eaccept_op.epc_addr = (unsigned long)tcs; + eaccept_op.flags = SGX_SECINFO_TCS | SGX_SECINFO_MODIFIED; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* Run workload from new TCS. */ + self->run.tcs = (unsigned long)tcs; + + /* + * Simple workload to write to data buffer and read value back. + */ + put_buf_op.header.type = ENCL_OP_PUT_TO_BUFFER; + put_buf_op.value = MAGIC; + + EXPECT_EQ(ENCL_CALL(&put_buf_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + get_buf_op.header.type = ENCL_OP_GET_FROM_BUFFER; + get_buf_op.value = 0; + + EXPECT_EQ(ENCL_CALL(&get_buf_op, &self->run, true), 0); + + EXPECT_EQ(get_buf_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Phase 2 of test: + * Remove pages associated with new TCS, create a regular page + * where TCS page used to be and verify it can be used as a regular + * page. + */ + + /* Start page removal by requesting change of page type to PT_TRIM. */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + + modt_ioc.offset = total_size; + modt_ioc.length = 3 * PAGE_SIZE; + modt_ioc.page_type = SGX_PAGE_TYPE_TRIM; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(modt_ioc.result, 0); + EXPECT_EQ(modt_ioc.count, 3 * PAGE_SIZE); + + /* + * Enter enclave via TCS #1 and approve page removal by sending + * EACCEPT for each of three removed pages. + */ + self->run.tcs = self->encl.encl_base; + + eaccept_op.epc_addr = (unsigned long)stack_end; + eaccept_op.flags = SGX_SECINFO_TRIM | SGX_SECINFO_MODIFIED; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + eaccept_op.epc_addr = (unsigned long)tcs; + eaccept_op.ret = 0; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + eaccept_op.epc_addr = (unsigned long)ssa; + eaccept_op.ret = 0; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* Send final ioctl() to complete page removal. */ + memset(&remove_ioc, 0, sizeof(remove_ioc)); + + remove_ioc.offset = total_size; + remove_ioc.length = 3 * PAGE_SIZE; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_REMOVE_PAGES, &remove_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(remove_ioc.count, 3 * PAGE_SIZE); + + /* + * Enter enclave via TCS #1 and access location where TCS #3 was to + * trigger dynamic add of regular page at that location. + */ + eaccept_op.epc_addr = (unsigned long)tcs; + eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_REG | SGX_SECINFO_PENDING; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* + * New page should be accessible from within enclave - write to it. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = (unsigned long)tcs; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory from newly added page that was just written to, + * confirming that data previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = (unsigned long)tcs; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + munmap(addr, 3 * PAGE_SIZE); +} + +/* + * Ensure sane behavior if user requests page removal, does not run + * EACCEPT from within enclave but still attempts to finalize page removal + * with the SGX_IOC_ENCLAVE_REMOVE_PAGES ioctl(). The latter should fail + * because the removal was not EACCEPTed from within the enclave. + */ +TEST_F(enclave, remove_added_page_no_eaccept) +{ + struct sgx_enclave_remove_pages remove_ioc; + struct encl_op_get_from_addr get_addr_op; + struct sgx_enclave_modify_types modt_ioc; + struct encl_op_put_to_addr put_addr_op; + unsigned long data_start; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* + * Page that will be removed is the second data page in the .data + * segment. This forms part of the local encl_buffer within the + * enclave. + */ + data_start = self->encl.encl_base + + encl_get_data_offset(&self->encl) + PAGE_SIZE; + + /* + * Sanity check that page at @data_start is writable before + * removing it. + * + * Start by writing MAGIC to test page. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = data_start; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory that was just written to, confirming that data + * previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = data_start; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* Start page removal by requesting change of page type to PT_TRIM */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + + modt_ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + modt_ioc.length = PAGE_SIZE; + modt_ioc.page_type = SGX_PAGE_TYPE_TRIM; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(modt_ioc.result, 0); + EXPECT_EQ(modt_ioc.count, 4096); + + /* Skip EACCEPT */ + + /* Send final ioctl() to complete page removal */ + memset(&remove_ioc, 0, sizeof(remove_ioc)); + + remove_ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + remove_ioc.length = PAGE_SIZE; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_REMOVE_PAGES, &remove_ioc); + errno_save = ret == -1 ? errno : 0; + + /* Operation not permitted since EACCEPT was omitted. */ + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno_save, EPERM); + EXPECT_EQ(remove_ioc.count, 0); +} + +/* + * Request enclave page removal but instead of correctly following with + * EACCEPT a read attempt to page is made from within the enclave. + */ +TEST_F(enclave, remove_added_page_invalid_access) +{ + struct encl_op_get_from_addr get_addr_op; + struct encl_op_put_to_addr put_addr_op; + struct sgx_enclave_modify_types ioc; + unsigned long data_start; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&ioc, 0, sizeof(ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* + * Page that will be removed is the second data page in the .data + * segment. This forms part of the local encl_buffer within the + * enclave. + */ + data_start = self->encl.encl_base + + encl_get_data_offset(&self->encl) + PAGE_SIZE; + + /* + * Sanity check that page at @data_start is writable before + * removing it. + * + * Start by writing MAGIC to test page. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = data_start; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory that was just written to, confirming that data + * previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = data_start; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* Start page removal by requesting change of page type to PT_TRIM. */ + memset(&ioc, 0, sizeof(ioc)); + + ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + ioc.length = PAGE_SIZE; + ioc.page_type = SGX_PAGE_TYPE_TRIM; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(ioc.result, 0); + EXPECT_EQ(ioc.count, 4096); + + /* + * Read from page that was just removed. + */ + get_addr_op.value = 0; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + /* + * From kernel perspective the page is present but according to SGX the + * page should not be accessible so a #PF with SGX bit set is + * expected. + */ + + EXPECT_EQ(self->run.function, ERESUME); + EXPECT_EQ(self->run.exception_vector, 14); + EXPECT_EQ(self->run.exception_error_code, 0x8005); + EXPECT_EQ(self->run.exception_addr, data_start); +} + +/* + * Request enclave page removal and correctly follow with + * EACCEPT but do not follow with removal ioctl() but instead a read attempt + * to removed page is made from within the enclave. + */ +TEST_F(enclave, remove_added_page_invalid_access_after_eaccept) +{ + struct encl_op_get_from_addr get_addr_op; + struct encl_op_put_to_addr put_addr_op; + struct sgx_enclave_modify_types ioc; + struct encl_op_eaccept eaccept_op; + unsigned long data_start; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&ioc, 0, sizeof(ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* + * Page that will be removed is the second data page in the .data + * segment. This forms part of the local encl_buffer within the + * enclave. + */ + data_start = self->encl.encl_base + + encl_get_data_offset(&self->encl) + PAGE_SIZE; + + /* + * Sanity check that page at @data_start is writable before + * removing it. + * + * Start by writing MAGIC to test page. + */ + put_addr_op.value = MAGIC; + put_addr_op.addr = data_start; + put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* + * Read memory that was just written to, confirming that data + * previously written (MAGIC) is present. + */ + get_addr_op.value = 0; + get_addr_op.addr = data_start; + get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + EXPECT_EQ(get_addr_op.value, MAGIC); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + + /* Start page removal by requesting change of page type to PT_TRIM. */ + memset(&ioc, 0, sizeof(ioc)); + + ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + ioc.length = PAGE_SIZE; + ioc.page_type = SGX_PAGE_TYPE_TRIM; + + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(ioc.result, 0); + EXPECT_EQ(ioc.count, 4096); + + eaccept_op.epc_addr = (unsigned long)data_start; + eaccept_op.ret = 0; + eaccept_op.flags = SGX_SECINFO_TRIM | SGX_SECINFO_MODIFIED; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + /* Skip ioctl() to remove page. */ + + /* + * Read from page that was just removed. + */ + get_addr_op.value = 0; + + EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0); + + /* + * From kernel perspective the page is present but according to SGX the + * page should not be accessible so a #PF with SGX bit set is + * expected. + */ + + EXPECT_EQ(self->run.function, ERESUME); + EXPECT_EQ(self->run.exception_vector, 14); + EXPECT_EQ(self->run.exception_error_code, 0x8005); + EXPECT_EQ(self->run.exception_addr, data_start); +} + +TEST_F(enclave, remove_untouched_page) +{ + struct sgx_enclave_remove_pages remove_ioc; + struct sgx_enclave_modify_types modt_ioc; + struct encl_op_eaccept eaccept_op; + unsigned long data_start; + int ret, errno_save; + + ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata)); + + /* + * Hardware (SGX2) and kernel support is needed for this test. Start + * with check that test has a chance of succeeding. + */ + memset(&modt_ioc, 0, sizeof(modt_ioc)); + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + + if (ret == -1) { + if (errno == ENOTTY) + SKIP(return, + "Kernel does not support SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()"); + else if (errno == ENODEV) + SKIP(return, "System does not support SGX2"); + } + + /* + * Invalid parameters were provided during sanity check, + * expect command to fail. + */ + EXPECT_EQ(ret, -1); + + /* SGX2 is supported by kernel and hardware, test can proceed. */ + memset(&self->run, 0, sizeof(self->run)); + self->run.tcs = self->encl.encl_base; + + data_start = self->encl.encl_base + + encl_get_data_offset(&self->encl) + PAGE_SIZE; + + memset(&modt_ioc, 0, sizeof(modt_ioc)); + + modt_ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + modt_ioc.length = PAGE_SIZE; + modt_ioc.page_type = SGX_PAGE_TYPE_TRIM; + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_MODIFY_TYPES, &modt_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(modt_ioc.result, 0); + EXPECT_EQ(modt_ioc.count, 4096); + + /* + * Enter enclave via TCS #1 and approve page removal by sending + * EACCEPT for removed page. + */ + + eaccept_op.epc_addr = data_start; + eaccept_op.flags = SGX_SECINFO_TRIM | SGX_SECINFO_MODIFIED; + eaccept_op.ret = 0; + eaccept_op.header.type = ENCL_OP_EACCEPT; + + EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0); + EXPECT_EEXIT(&self->run); + EXPECT_EQ(self->run.exception_vector, 0); + EXPECT_EQ(self->run.exception_error_code, 0); + EXPECT_EQ(self->run.exception_addr, 0); + EXPECT_EQ(eaccept_op.ret, 0); + + memset(&remove_ioc, 0, sizeof(remove_ioc)); + + remove_ioc.offset = encl_get_data_offset(&self->encl) + PAGE_SIZE; + remove_ioc.length = PAGE_SIZE; + ret = ioctl(self->encl.fd, SGX_IOC_ENCLAVE_REMOVE_PAGES, &remove_ioc); + errno_save = ret == -1 ? errno : 0; + + EXPECT_EQ(ret, 0); + EXPECT_EQ(errno_save, 0); + EXPECT_EQ(remove_ioc.count, 4096); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h index b45c52ec7ab3..fc585be97e2f 100644 --- a/tools/testing/selftests/sgx/main.h +++ b/tools/testing/selftests/sgx/main.h @@ -38,6 +38,7 @@ void encl_delete(struct encl *ctx); bool encl_load(const char *path, struct encl *encl, unsigned long heap_size); bool encl_measure(struct encl *encl); bool encl_build(struct encl *encl); +uint64_t encl_get_entry(struct encl *encl, const char *symbol); int sgx_enter_enclave(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, struct sgx_enclave_run *run); diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c index 4fca01cfd898..c0d6397295e3 100644 --- a/tools/testing/selftests/sgx/test_encl.c +++ b/tools/testing/selftests/sgx/test_encl.c @@ -11,6 +11,42 @@ */ static uint8_t encl_buffer[8192] = { 1 }; +enum sgx_enclu_function { + EACCEPT = 0x5, + EMODPE = 0x6, +}; + +static void do_encl_emodpe(void *_op) +{ + struct sgx_secinfo secinfo __aligned(sizeof(struct sgx_secinfo)) = {0}; + struct encl_op_emodpe *op = _op; + + secinfo.flags = op->flags; + + asm volatile(".byte 0x0f, 0x01, 0xd7" + : + : "a" (EMODPE), + "b" (&secinfo), + "c" (op->epc_addr)); +} + +static void do_encl_eaccept(void *_op) +{ + struct sgx_secinfo secinfo __aligned(sizeof(struct sgx_secinfo)) = {0}; + struct encl_op_eaccept *op = _op; + int rax; + + secinfo.flags = op->flags; + + asm volatile(".byte 0x0f, 0x01, 0xd7" + : "=a" (rax) + : "a" (EACCEPT), + "b" (&secinfo), + "c" (op->epc_addr)); + + op->ret = rax; +} + static void *memcpy(void *dest, const void *src, size_t n) { size_t i; @@ -21,6 +57,35 @@ static void *memcpy(void *dest, const void *src, size_t n) return dest; } +static void *memset(void *dest, int c, size_t n) +{ + size_t i; + + for (i = 0; i < n; i++) + ((char *)dest)[i] = c; + + return dest; +} + +static void do_encl_init_tcs_page(void *_op) +{ + struct encl_op_init_tcs_page *op = _op; + void *tcs = (void *)op->tcs_page; + uint32_t val_32; + + memset(tcs, 0, 16); /* STATE and FLAGS */ + memcpy(tcs + 16, &op->ssa, 8); /* OSSA */ + memset(tcs + 24, 0, 4); /* CSSA */ + val_32 = 1; + memcpy(tcs + 28, &val_32, 4); /* NSSA */ + memcpy(tcs + 32, &op->entry, 8); /* OENTRY */ + memset(tcs + 40, 0, 24); /* AEP, OFSBASE, OGSBASE */ + val_32 = 0xFFFFFFFF; + memcpy(tcs + 64, &val_32, 4); /* FSLIMIT */ + memcpy(tcs + 68, &val_32, 4); /* GSLIMIT */ + memset(tcs + 72, 0, 4024); /* Reserved */ +} + static void do_encl_op_put_to_buf(void *op) { struct encl_op_put_to_buf *op2 = op; @@ -62,6 +127,9 @@ void encl_body(void *rdi, void *rsi) do_encl_op_put_to_addr, do_encl_op_get_from_addr, do_encl_op_nop, + do_encl_eaccept, + do_encl_emodpe, + do_encl_init_tcs_page, }; struct encl_op_header *op = (struct encl_op_header *)rdi; diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S index 82fb0dfcbd23..03ae0f57e29d 100644 --- a/tools/testing/selftests/sgx/test_encl_bootstrap.S +++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S @@ -45,6 +45,12 @@ encl_entry: # TCS #2. By adding the value of encl_stack to it, we get # the absolute address for the stack. lea (encl_stack)(%rbx), %rax + jmp encl_entry_core +encl_dyn_entry: + # Entry point for dynamically created TCS page expected to follow + # its stack directly. + lea -1(%rbx), %rax +encl_entry_core: xchg %rsp, %rax push %rax diff --git a/tools/testing/selftests/sync/config b/tools/testing/selftests/sync/config index 47ff5afc3727..64c60f38b446 100644 --- a/tools/testing/selftests/sync/config +++ b/tools/testing/selftests/sync/config @@ -1,3 +1,2 @@ CONFIG_STAGING=y -CONFIG_ANDROID=y CONFIG_SW_SYNC=y diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 108587cb327a..d9fa6a9ea584 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -93,6 +93,7 @@ TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh +TEST_FILES += va_128TBswitch.sh include ../lib.mk diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 203323967b50..529f53b40296 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -36,6 +36,7 @@ * in the usual include/uapi/... directory. */ #include "../../../../lib/test_hmm_uapi.h" +#include "../../../../mm/gup_test.h" struct hmm_buffer { void *ptr; @@ -46,12 +47,22 @@ struct hmm_buffer { uint64_t faults; }; +enum { + HMM_PRIVATE_DEVICE_ONE, + HMM_PRIVATE_DEVICE_TWO, + HMM_COHERENCE_DEVICE_ONE, + HMM_COHERENCE_DEVICE_TWO, +}; + #define TWOMEG (1 << 21) #define HMM_BUFFER_SIZE (1024 << 12) #define HMM_PATH_MAX 64 #define NTIMES 10 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) +/* Just the flags we need, copied from mm.h: */ +#define FOLL_WRITE 0x01 /* check pte is writable */ +#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite */ FIXTURE(hmm) { @@ -60,6 +71,21 @@ FIXTURE(hmm) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm) +{ + int device_number; +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_private) +{ + .device_number = HMM_PRIVATE_DEVICE_ONE, +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_coherent) +{ + .device_number = HMM_COHERENCE_DEVICE_ONE, +}; + FIXTURE(hmm2) { int fd0; @@ -68,6 +94,24 @@ FIXTURE(hmm2) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm2) +{ + int device_number0; + int device_number1; +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_private) +{ + .device_number0 = HMM_PRIVATE_DEVICE_ONE, + .device_number1 = HMM_PRIVATE_DEVICE_TWO, +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_coherent) +{ + .device_number0 = HMM_COHERENCE_DEVICE_ONE, + .device_number1 = HMM_COHERENCE_DEVICE_TWO, +}; + static int hmm_open(int unit) { char pathname[HMM_PATH_MAX]; @@ -81,12 +125,19 @@ static int hmm_open(int unit) return fd; } +static bool hmm_is_coherent_type(int dev_num) +{ + return (dev_num >= HMM_COHERENCE_DEVICE_ONE); +} + FIXTURE_SETUP(hmm) { self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd = hmm_open(0); + self->fd = hmm_open(variant->device_number); + if (self->fd < 0 && hmm_is_coherent_type(variant->device_number)) + SKIP(exit(0), "DEVICE_COHERENT not available"); ASSERT_GE(self->fd, 0); } @@ -95,9 +146,11 @@ FIXTURE_SETUP(hmm2) self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd0 = hmm_open(0); + self->fd0 = hmm_open(variant->device_number0); + if (self->fd0 < 0 && hmm_is_coherent_type(variant->device_number0)) + SKIP(exit(0), "DEVICE_COHERENT not available"); ASSERT_GE(self->fd0, 0); - self->fd1 = hmm_open(1); + self->fd1 = hmm_open(variant->device_number1); ASSERT_GE(self->fd1, 0); } @@ -211,6 +264,20 @@ static void hmm_nanosleep(unsigned int n) nanosleep(&t, NULL); } +static int hmm_migrate_sys_to_dev(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_DEV, buffer, npages); +} + +static int hmm_migrate_dev_to_sys(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_SYS, buffer, npages); +} + /* * Simple NULL test of device open/close. */ @@ -875,7 +942,7 @@ TEST_F(hmm, migrate) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -923,7 +990,7 @@ TEST_F(hmm, migrate_fault) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -936,7 +1003,7 @@ TEST_F(hmm, migrate_fault) ASSERT_EQ(ptr[i], i); /* Migrate memory to the device again. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -976,7 +1043,7 @@ TEST_F(hmm, migrate_shared) ASSERT_NE(buffer->ptr, MAP_FAILED); /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, -ENOENT); hmm_buffer_free(buffer); @@ -1015,7 +1082,7 @@ TEST_F(hmm2, migrate_mixed) p = buffer->ptr; /* Migrating a protected area should be an error. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); ASSERT_EQ(ret, -EINVAL); /* Punch a hole after the first page address. */ @@ -1023,7 +1090,7 @@ TEST_F(hmm2, migrate_mixed) ASSERT_EQ(ret, 0); /* We expect an error if the vma doesn't cover the range. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 3); ASSERT_EQ(ret, -EINVAL); /* Page 2 will be a read-only zero page. */ @@ -1055,13 +1122,13 @@ TEST_F(hmm2, migrate_mixed) /* Now try to migrate pages 2-5 to device 1. */ buffer->ptr = p + 2 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 4); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 4); /* Page 5 won't be migrated to device 0 because it's on device 1. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, -ENOENT); buffer->ptr = p; @@ -1070,8 +1137,12 @@ TEST_F(hmm2, migrate_mixed) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory multiple times. + * Migrate anonymous memory to device memory and back to system memory + * multiple times. In case of private zone configuration, this is done + * through fault pages accessed by CPU. In case of coherent zone configuration, + * the pages from the device should be explicitly migrated back to system memory. + * The reason is Coherent device zone has coherent access by CPU, therefore + * it will not generate any page fault. */ TEST_F(hmm, migrate_multiple) { @@ -1107,8 +1178,7 @@ TEST_F(hmm, migrate_multiple) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, - npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -1116,7 +1186,13 @@ TEST_F(hmm, migrate_multiple) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Fault pages back to system memory and check them. */ + /* Migrate back to system memory and check them. */ + if (hmm_is_coherent_type(variant->device_number)) { + ret = hmm_migrate_dev_to_sys(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + } + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); @@ -1354,13 +1430,13 @@ TEST_F(hmm2, snapshot) /* Page 5 will be migrated to device 0. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); /* Page 6 will be migrated to device 1. */ buffer->ptr = p + 6 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); @@ -1377,9 +1453,16 @@ TEST_F(hmm2, snapshot) ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | - HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + if (!hmm_is_coherent_type(variant->device_number0)) { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + } else { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE | + HMM_DMIRROR_PROT_WRITE); + } hmm_buffer_free(buffer); } @@ -1520,9 +1603,19 @@ TEST_F(hmm2, double_map) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Punch a hole after the first page address. */ - ret = munmap(buffer->ptr + self->page_size, self->page_size); + /* Migrate pages to device 1 and try to read from device 0. */ + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_READ, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + ASSERT_EQ(buffer->faults, 1); + + /* Check what device 0 read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); } @@ -1685,4 +1778,190 @@ TEST_F(hmm, exclusive_cow) hmm_buffer_free(buffer); } +static int gup_test_exec(int gup_fd, unsigned long addr, int cmd, + int npages, int size, int flags) +{ + struct gup_test gup = { + .nr_pages_per_call = npages, + .addr = addr, + .gup_flags = FOLL_WRITE | flags, + .size = size, + }; + + if (ioctl(gup_fd, cmd, &gup)) { + perror("ioctl on error\n"); + return errno; + } + + return 0; +} + +/* + * Test get user device pages through gup_test. Setting PIN_LONGTERM flag. + * This should trigger a migration back to system memory for both, private + * and coherent type pages. + * This test makes use of gup_test module. Make sure GUP_TEST_CONFIG is added + * to your configuration before you run it. + */ +TEST_F(hmm, hmm_gup_test) +{ + struct hmm_buffer *buffer; + int gup_fd; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (gup_fd == -1) + SKIP(return, "Skipping test, could not find gup_test driver"); + + npages = 4; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr, + GUP_BASIC_TEST, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 1 * self->page_size, + GUP_FAST_BENCHMARK, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 2 * self->page_size, + PIN_FAST_BENCHMARK, 1, self->page_size, FOLL_LONGTERM), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 3 * self->page_size, + PIN_LONGTERM_BENCHMARK, 1, self->page_size, 0), 0); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + if (hmm_is_coherent_type(variant->device_number)) { + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[1]); + } else { + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[1]); + } + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[2]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[3]); + /* + * Check again the content on the pages. Make sure there's no + * corrupted data. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + close(gup_fd); + hmm_buffer_free(buffer); +} + +/* + * Test copy-on-write in device pages. + * In case of writing to COW private page(s), a page fault will migrate pages + * back to system memory first. Then, these pages will be duplicated. In case + * of COW device coherent type, pages are duplicated directly from device + * memory. + */ +TEST_F(hmm, hmm_cow_in_device) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + pid_t pid; + int status; + + npages = 4; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + pid = fork(); + if (pid == -1) + ASSERT_EQ(pid, 0); + if (!pid) { + /* Child process waitd for SIGTERM from the parent. */ + while (1) { + } + perror("Should not reach this\n"); + exit(0); + } + /* Parent process writes to COW pages(s) and gets a + * new copy in system. In case of device private pages, + * this write causes a migration to system mem first. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Terminate child and wait */ + EXPECT_EQ(0, kill(pid, SIGTERM)); + EXPECT_EQ(pid, waitpid(pid, &status, 0)); + EXPECT_NE(0, WIFSIGNALED(status)); + EXPECT_EQ(SIGTERM, WTERMSIG(status)); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + for (i = 0; i < npages; i++) + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[i]); + + hmm_buffer_free(buffer); +} TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 585978f181ed..e63a0214f639 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -107,7 +107,7 @@ static void register_region_with_uffd(char *addr, size_t len) int main(int argc, char *argv[]) { - size_t length; + size_t length = 0; if (argc != 2 && argc != 3) { printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c index 6c6af40f5747..3c9943131881 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -89,10 +89,11 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - unsigned long i, tmp; + unsigned long dummy = 0; + unsigned long i; for (i = 0; i < nr_pages; i++) - tmp += *((unsigned long *)(addr + (i * huge_page_size))); + dummy += *((unsigned long *)(addr + (i * huge_page_size))); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/vm/mrelease_test.c index 96671c2f7d48..6c62966ab5db 100644 --- a/tools/testing/selftests/vm/mrelease_test.c +++ b/tools/testing/selftests/vm/mrelease_test.c @@ -62,19 +62,22 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) /* The process_mrelease calls in this test are expected to fail */ static void run_negative_tests(int pidfd) { + int res; /* Test invalid flags. Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || errno != EINVAL) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease with wrong flags"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } /* * Test reaping while process is alive with no pending SIGKILL. * Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease on a live process"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } } @@ -100,8 +103,9 @@ int main(void) /* Test a wrong pidfd */ if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease with wrong pidfd"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } /* Start the test with 1MB child memory allocation */ @@ -156,8 +160,9 @@ retry: run_negative_tests(pidfd); if (kill(pid, SIGKILL)) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("kill"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); @@ -172,9 +177,10 @@ retry: if (errno == ESRCH) { retry = (size <= MAX_SIZE_MB); } else { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease"); waitpid(pid, NULL, 0); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } } diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 41fce8bea929..de86983b8a0f 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -151,7 +151,7 @@ if [ $VADDR64 -ne 0 ]; then run_test ./virtual_address_range # virtual address 128TB switch test - run_test ./va_128TBswitch + run_test ./va_128TBswitch.sh fi # VADDR64 # vmalloc stability smoke test @@ -179,4 +179,17 @@ run_test ./ksm_tests -N -m 1 # KSM test with 2 NUMA nodes and merge_across_nodes = 0 run_test ./ksm_tests -N -m 0 +# protection_keys tests +if [ -x ./protection_keys_32 ] +then + run_test ./protection_keys_32 +fi + +if [ -x ./protection_keys_64 ] +then + run_test ./protection_keys_64 +fi + +run_test ./soft-dirty + exit $exitcode diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/vm/soft-dirty.c index 08ab62a4a9d0..e3a43f5d4fa2 100644 --- a/tools/testing/selftests/vm/soft-dirty.c +++ b/tools/testing/selftests/vm/soft-dirty.c @@ -121,13 +121,76 @@ static void test_hugepage(int pagemap_fd, int pagesize) free(map); } +static void test_mprotect(int pagemap_fd, int pagesize, bool anon) +{ + const char *type[] = {"file", "anon"}; + const char *fname = "./soft-dirty-test-file"; + int test_fd; + char *map; + + if (anon) { + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + if (!map) + ksft_exit_fail_msg("anon mmap failed\n"); + } else { + test_fd = open(fname, O_RDWR | O_CREAT); + if (test_fd < 0) { + ksft_test_result_skip("Test %s open() file failed\n", __func__); + return; + } + unlink(fname); + ftruncate(test_fd, pagesize); + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_SHARED, test_fd, 0); + if (!map) + ksft_exit_fail_msg("file mmap failed\n"); + } + + *map = 1; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s dirty bit of new written page\n", + __func__, type[anon]); + clear_softdirty(); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after clear_refs\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RO\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ|PROT_WRITE); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RW\n", + __func__, type[anon]); + *map = 2; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s soft-dirty after rewritten\n", + __func__, type[anon]); + + munmap(map, pagesize); + + if (!anon) + close(test_fd); +} + +static void test_mprotect_anon(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, true); +} + +static void test_mprotect_file(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, false); +} + int main(int argc, char **argv) { int pagemap_fd; int pagesize; ksft_print_header(); - ksft_set_plan(5); + ksft_set_plan(15); pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY); if (pagemap_fd < 0) @@ -138,6 +201,8 @@ int main(int argc, char **argv) test_simple(pagemap_fd, pagesize); test_vma_reuse(pagemap_fd, pagesize); test_hugepage(pagemap_fd, pagesize); + test_mprotect_anon(pagemap_fd, pagesize); + test_mprotect_file(pagemap_fd, pagesize); close(pagemap_fd); diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh index 0647b525a625..539c9371e592 100755 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/vm/test_hmm.sh @@ -40,11 +40,26 @@ check_test_requirements() load_driver() { - modprobe $DRIVER > /dev/null 2>&1 + if [ $# -eq 0 ]; then + modprobe $DRIVER > /dev/null 2>&1 + else + if [ $# -eq 2 ]; then + modprobe $DRIVER spm_addr_dev0=$1 spm_addr_dev1=$2 + > /dev/null 2>&1 + else + echo "Missing module parameters. Make sure pass"\ + "spm_addr_dev0 and spm_addr_dev1" + usage + fi + fi if [ $? == 0 ]; then major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices) mknod /dev/hmm_dmirror0 c $major 0 mknod /dev/hmm_dmirror1 c $major 1 + if [ $# -eq 2 ]; then + mknod /dev/hmm_dmirror2 c $major 2 + mknod /dev/hmm_dmirror3 c $major 3 + fi fi } @@ -58,7 +73,7 @@ run_smoke() { echo "Running smoke test. Note, this test provides basic coverage." - load_driver + load_driver $1 $2 $(dirname "${BASH_SOURCE[0]}")/hmm-tests unload_driver } @@ -75,6 +90,9 @@ usage() echo "# Smoke testing" echo "./${TEST_NAME}.sh smoke" echo + echo "# Smoke testing with SPM enabled" + echo "./${TEST_NAME}.sh smoke <spm_addr_dev0> <spm_addr_dev1>" + echo exit 0 } @@ -84,7 +102,7 @@ function run_test() usage else if [ "$1" = "smoke" ]; then - run_smoke + run_smoke $2 $3 else usage fi diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 4bc24581760d..7c3f1b0ab468 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -931,7 +931,7 @@ static int faulting_process(int signal_test) unsigned long split_nr_pages; unsigned long lastnr; struct sigaction act; - unsigned long signalled = 0; + volatile unsigned long signalled = 0; split_nr_pages = (nr_pages + 1) / 2; @@ -946,7 +946,7 @@ static int faulting_process(int signal_test) } for (nr = 0; nr < split_nr_pages; nr++) { - int steps = 1; + volatile int steps = 1; unsigned long offset = nr * page_size; if (signal_test) { diff --git a/tools/testing/selftests/vm/va_128TBswitch.c b/tools/testing/selftests/vm/va_128TBswitch.c index da6ec3b53ea8..1d2068989883 100644 --- a/tools/testing/selftests/vm/va_128TBswitch.c +++ b/tools/testing/selftests/vm/va_128TBswitch.c @@ -231,7 +231,7 @@ static struct testcase hugetlb_testcases[] = { static int run_test(struct testcase *test, int count) { void *p; - int i, ret = 0; + int i, ret = KSFT_PASS; for (i = 0; i < count; i++) { struct testcase *t = test + i; @@ -242,13 +242,13 @@ static int run_test(struct testcase *test, int count) if (p == MAP_FAILED) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; continue; } if (t->low_addr_required && p >= (void *)(ADDR_SWITCH_HINT)) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; } else { /* * Do a dereference of the address returned so that we catch @@ -280,7 +280,7 @@ int main(int argc, char **argv) int ret; if (!supported_arch()) - return 0; + return KSFT_SKIP; ret = run_test(testcases, ARRAY_SIZE(testcases)); if (argc == 2 && !strcmp(argv[1], "--run-hugetlb")) diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh new file mode 100755 index 000000000000..41580751dc51 --- /dev/null +++ b/tools/testing/selftests/vm/va_128TBswitch.sh @@ -0,0 +1,54 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2022 Adam Sindelar (Meta) <adam@wowsignal.io> +# +# This is a test for mmap behavior with 5-level paging. This script wraps the +# real test to check that the kernel is configured to support at least 5 +# pagetable levels. + +# 1 means the test failed +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +fail() +{ + echo "$1" + exit $exitcode +} + +check_supported_x86_64() +{ + local config="/proc/config.gz" + [[ -f "${config}" ]] || config="/boot/config-$(uname -r)" + [[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot" + + # gzip -dcfq automatically handles both compressed and plaintext input. + # See man 1 gzip under '-f'. + local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + + if [[ "${pg_table_levels}" -lt 5 ]]; then + echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" + exit $ksft_skip + fi +} + +check_test_requirements() +{ + # The test supports x86_64 and powerpc64. We currently have no useful + # eligibility check for powerpc64, and the test itself will reject other + # architectures. + case `uname -m` in + "x86_64") + check_supported_x86_64 + ;; + *) + return 0 + ;; + esac +} + +check_test_requirements +./va_128TBswitch |