diff options
Diffstat (limited to 'tools')
78 files changed, 9334 insertions, 575 deletions
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 5a776a08f78c..2da3316bb559 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -373,9 +373,23 @@ struct kvm_debugregs { __u64 reserved[9]; }; -/* for KVM_CAP_XSAVE */ +/* for KVM_CAP_XSAVE and KVM_CAP_XSAVE2 */ struct kvm_xsave { + /* + * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many bytes + * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * respectively, when invoked on the vm file descriptor. + * + * The size value returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * will always be at least 4096. Currently, it is only greater + * than 4096 if a dynamic feature has been enabled with + * ``arch_prctl()``, but this may change in the future. + * + * The offsets of the state save areas in struct kvm_xsave follow + * the contents of CPUID leaf 0xD on the host. + */ __u32 region[1024]; + __u32 extra[0]; }; #define KVM_MAX_XCRS 16 diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 0076437f6e3f..b94a16ba5c6c 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -279,6 +279,7 @@ static void print_event(struct iio_event_data *event) printf(", direction: %s", iio_ev_dir_text[dir]); printf("\n"); + fflush(stdout); } /* Enable or disable events in sysfs if the knob is available */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 1daa45268de2..f066637ee206 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1131,6 +1131,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 +#define KVM_CAP_XSAVE2 207 #ifdef KVM_CAP_IRQ_ROUTING @@ -1551,6 +1552,8 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_XSAVE */ #define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave) #define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) /* Available with KVM_CAP_XCRS */ #define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) #define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index fe58843d047c..8e24c4c78c7f 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -1367,6 +1367,14 @@ static int field_is_dynamic(struct tep_format_field *field) return 0; } +static int field_is_relative_dynamic(struct tep_format_field *field) +{ + if (strncmp(field->type, "__rel_loc", 9) == 0) + return 1; + + return 0; +} + static int field_is_long(struct tep_format_field *field) { /* includes long long */ @@ -1622,6 +1630,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** field->flags |= TEP_FIELD_IS_STRING; if (field_is_dynamic(field)) field->flags |= TEP_FIELD_IS_DYNAMIC; + if (field_is_relative_dynamic(field)) + field->flags |= TEP_FIELD_IS_DYNAMIC | TEP_FIELD_IS_RELATIVE; if (field_is_long(field)) field->flags |= TEP_FIELD_IS_LONG; @@ -2928,7 +2938,7 @@ process_str(struct tep_event *event __maybe_unused, struct tep_print_arg *arg, arg->type = TEP_PRINT_STRING; arg->string.string = token; - arg->string.offset = -1; + arg->string.field = NULL; if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; @@ -2957,7 +2967,7 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar arg->type = TEP_PRINT_BITMASK; arg->bitmask.bitmask = token; - arg->bitmask.offset = -1; + arg->bitmask.field = NULL; if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; @@ -3123,19 +3133,23 @@ process_function(struct tep_event *event, struct tep_print_arg *arg, free_token(token); return process_int_array(event, arg, tok); } - if (strcmp(token, "__get_str") == 0) { + if (strcmp(token, "__get_str") == 0 || + strcmp(token, "__get_rel_str") == 0) { free_token(token); return process_str(event, arg, tok); } - if (strcmp(token, "__get_bitmask") == 0) { + if (strcmp(token, "__get_bitmask") == 0 || + strcmp(token, "__get_rel_bitmask") == 0) { free_token(token); return process_bitmask(event, arg, tok); } - if (strcmp(token, "__get_dynamic_array") == 0) { + if (strcmp(token, "__get_dynamic_array") == 0 || + strcmp(token, "__get_rel_dynamic_array") == 0) { free_token(token); return process_dynamic_array(event, arg, tok); } - if (strcmp(token, "__get_dynamic_array_len") == 0) { + if (strcmp(token, "__get_dynamic_array_len") == 0 || + strcmp(token, "__get_rel_dynamic_array_len") == 0) { free_token(token); return process_dynamic_array_len(event, arg, tok); } @@ -4163,14 +4177,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, case TEP_PRINT_STRING: { int str_offset; - if (arg->string.offset == -1) { - struct tep_format_field *f; + if (!arg->string.field) + arg->string.field = tep_find_any_field(event, arg->string.string); + if (!arg->string.field) + break; - f = tep_find_any_field(event, arg->string.string); - arg->string.offset = f->offset; - } - str_offset = data2host4(tep, *(unsigned int *)(data + arg->string.offset)); + str_offset = data2host4(tep, + *(unsigned int *)(data + arg->string.field->offset)); str_offset &= 0xffff; + if (arg->string.field->flags & TEP_FIELD_IS_RELATIVE) + str_offset += arg->string.field->offset + arg->string.field->size; print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset); break; } @@ -4181,15 +4197,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, int bitmask_offset; int bitmask_size; - if (arg->bitmask.offset == -1) { - struct tep_format_field *f; - - f = tep_find_any_field(event, arg->bitmask.bitmask); - arg->bitmask.offset = f->offset; - } - bitmask_offset = data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset)); + if (!arg->bitmask.field) + arg->bitmask.field = tep_find_any_field(event, arg->bitmask.bitmask); + if (!arg->bitmask.field) + break; + bitmask_offset = data2host4(tep, + *(unsigned int *)(data + arg->bitmask.field->offset)); bitmask_size = bitmask_offset >> 16; bitmask_offset &= 0xffff; + if (arg->bitmask.field->flags & TEP_FIELD_IS_RELATIVE) + bitmask_offset += arg->bitmask.field->offset + arg->bitmask.field->size; print_bitmask_to_seq(tep, s, format, len_arg, data + bitmask_offset, bitmask_size); break; @@ -5109,6 +5126,8 @@ void tep_print_field(struct trace_seq *s, void *data, offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { @@ -6987,6 +7006,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, data + offset, field->size); *len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } else *len = field->size; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index a67ad9a5b835..41d4f9f6a843 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -125,6 +125,7 @@ enum tep_format_flags { TEP_FIELD_IS_LONG = 32, TEP_FIELD_IS_FLAG = 64, TEP_FIELD_IS_SYMBOLIC = 128, + TEP_FIELD_IS_RELATIVE = 256, }; struct tep_format_field { @@ -153,12 +154,12 @@ struct tep_print_arg_atom { struct tep_print_arg_string { char *string; - int offset; + struct tep_format_field *field; }; struct tep_print_arg_bitmask { char *bitmask; - int offset; + struct tep_format_field *field; }; struct tep_print_arg_field { diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 368826bb5a57..5df177070d53 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1712,8 +1712,11 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record * if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) { addr = *(unsigned int *)val; - val = record->data + (addr & 0xffff); size = addr >> 16; + addr &= 0xffff; + if (arg->str.field->flags & TEP_FIELD_IS_RELATIVE) + addr += arg->str.field->offset + arg->str.field->size; + val = record->data + addr; } /* diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8c1931eab5f1..c2d2ab9a2861 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -168,14 +168,16 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", - "__module_put_and_exit", - "complete_and_exit", + "kthread_exit", + "make_task_dead", + "__module_put_and_kthread_exit", + "kthread_complete_and_exit", "__reiserfs_panic", "lbug_with_loc", "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_do_exit", + "rewind_stack_and_make_dead", "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 46bca1f9ab9e..32844d8a0ea5 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2726,6 +2726,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, offset = format_field__intval(field, sample, evsel->needs_swap); syscall_arg.len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } val = (uintptr_t)(sample->raw_data + offset); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 8f7705bbc2da..9e0aee276df8 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -318,6 +318,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, offset = tmp_val; len = offset >> 16; offset &= 0xffff; + if (flags & TEP_FIELD_IS_RELATIVE) + offset += fmtf->offset + fmtf->size; } if (flags & TEP_FIELD_IS_ARRAY) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 7660e0bf3b50..2f6b18af49e5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2688,6 +2688,8 @@ void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(sample->raw_data + field->offset); offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } return sample->raw_data + offset; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 95fb53899bcd..f3e5131f183c 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -428,6 +428,8 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 32a721b3e9a5..a5d945415bbc 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -392,6 +392,8 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(data + field->offset); offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } else offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index bd95d60018a9..f5ad0e62227a 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -944,6 +944,8 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index e417e47f51b9..cfba8c337783 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2381,6 +2381,8 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, tep_read_number_field(field, a->raw_data, &dyn); offset = dyn & 0xffff; size = (dyn >> 16) & 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; /* record max width for output */ if (size > hde->dynamic_len) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c852eb40c4f7..d08fe4cfe811 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -TARGETS = arm64 +TARGETS += alsa +TARGETS += arm64 TARGETS += bpf TARGETS += breakpoints TARGETS += capabilities diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore new file mode 100644 index 000000000000..3bb7c41266a8 --- /dev/null +++ b/tools/testing/selftests/alsa/.gitignore @@ -0,0 +1 @@ +mixer-test diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile new file mode 100644 index 000000000000..f64d9090426d --- /dev/null +++ b/tools/testing/selftests/alsa/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +# + +CFLAGS += $(shell pkg-config --cflags alsa) +LDLIBS += $(shell pkg-config --libs alsa) + +TEST_GEN_PROGS := mixer-test + +include ../lib.mk diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c new file mode 100644 index 000000000000..17f158d7a767 --- /dev/null +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -0,0 +1,705 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// kselftest for the ALSA mixer API +// +// Original author: Mark Brown <broonie@kernel.org> +// Copyright (c) 2021 Arm Limited + +// This test will iterate over all cards detected in the system, exercising +// every mixer control it can find. This may conflict with other system +// software if there is audio activity so is best run on a system with a +// minimal active userspace. + +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <getopt.h> +#include <stdarg.h> +#include <ctype.h> +#include <math.h> +#include <errno.h> +#include <assert.h> +#include <alsa/asoundlib.h> +#include <poll.h> +#include <stdint.h> + +#include "../kselftest.h" + +#define TESTS_PER_CONTROL 3 + +struct card_data { + snd_ctl_t *handle; + int card; + int num_ctls; + snd_ctl_elem_list_t *ctls; + struct card_data *next; +}; + +struct ctl_data { + const char *name; + snd_ctl_elem_id_t *id; + snd_ctl_elem_info_t *info; + snd_ctl_elem_value_t *def_val; + int elem; + struct card_data *card; + struct ctl_data *next; +}; + +static const char *alsa_config = +"ctl.hw {\n" +" @args [ CARD ]\n" +" @args.CARD.type string\n" +" type hw\n" +" card $CARD\n" +"}\n" +; + +int num_cards = 0; +int num_controls = 0; +struct card_data *card_list = NULL; +struct ctl_data *ctl_list = NULL; + +#ifdef SND_LIB_VER +#if SND_LIB_VERSION >= SND_LIB_VER(1, 2, 6) +#define LIB_HAS_LOAD_STRING +#endif +#endif + +#ifndef LIB_HAS_LOAD_STRING +int snd_config_load_string(snd_config_t **config, const char *s, size_t size) +{ + snd_input_t *input; + snd_config_t *dst; + int err; + + assert(config && s); + if (size == 0) + size = strlen(s); + err = snd_input_buffer_open(&input, s, size); + if (err < 0) + return err; + err = snd_config_top(&dst); + if (err < 0) { + snd_input_close(input); + return err; + } + err = snd_config_load(dst, input); + snd_input_close(input); + if (err < 0) { + snd_config_delete(dst); + return err; + } + *config = dst; + return 0; +} +#endif + +void find_controls(void) +{ + char name[32]; + int card, ctl, err; + struct card_data *card_data; + struct ctl_data *ctl_data; + snd_config_t *config; + + card = -1; + if (snd_card_next(&card) < 0 || card < 0) + return; + + err = snd_config_load_string(&config, alsa_config, strlen(alsa_config)); + if (err < 0) { + ksft_print_msg("Unable to parse custom alsa-lib configuration: %s\n", + snd_strerror(err)); + ksft_exit_fail(); + } + + while (card >= 0) { + sprintf(name, "hw:%d", card); + + card_data = malloc(sizeof(*card_data)); + if (!card_data) + ksft_exit_fail_msg("Out of memory\n"); + + err = snd_ctl_open_lconf(&card_data->handle, name, 0, config); + if (err < 0) { + ksft_print_msg("Failed to get hctl for card %d: %s\n", + card, snd_strerror(err)); + goto next_card; + } + + /* Count controls */ + snd_ctl_elem_list_malloc(&card_data->ctls); + snd_ctl_elem_list(card_data->handle, card_data->ctls); + card_data->num_ctls = snd_ctl_elem_list_get_count(card_data->ctls); + + /* Enumerate control information */ + snd_ctl_elem_list_alloc_space(card_data->ctls, card_data->num_ctls); + snd_ctl_elem_list(card_data->handle, card_data->ctls); + + card_data->card = num_cards++; + card_data->next = card_list; + card_list = card_data; + + num_controls += card_data->num_ctls; + + for (ctl = 0; ctl < card_data->num_ctls; ctl++) { + ctl_data = malloc(sizeof(*ctl_data)); + if (!ctl_data) + ksft_exit_fail_msg("Out of memory\n"); + + ctl_data->card = card_data; + ctl_data->elem = ctl; + ctl_data->name = snd_ctl_elem_list_get_name(card_data->ctls, + ctl); + + err = snd_ctl_elem_id_malloc(&ctl_data->id); + if (err < 0) + ksft_exit_fail_msg("Out of memory\n"); + + err = snd_ctl_elem_info_malloc(&ctl_data->info); + if (err < 0) + ksft_exit_fail_msg("Out of memory\n"); + + err = snd_ctl_elem_value_malloc(&ctl_data->def_val); + if (err < 0) + ksft_exit_fail_msg("Out of memory\n"); + + snd_ctl_elem_list_get_id(card_data->ctls, ctl, + ctl_data->id); + snd_ctl_elem_info_set_id(ctl_data->info, ctl_data->id); + err = snd_ctl_elem_info(card_data->handle, + ctl_data->info); + if (err < 0) { + ksft_print_msg("%s getting info for %d\n", + snd_strerror(err), + ctl_data->name); + } + + snd_ctl_elem_value_set_id(ctl_data->def_val, + ctl_data->id); + + ctl_data->next = ctl_list; + ctl_list = ctl_data; + } + + next_card: + if (snd_card_next(&card) < 0) { + ksft_print_msg("snd_card_next"); + break; + } + } + + snd_config_delete(config); +} + +bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val, + int index) +{ + long int_val; + long long int64_val; + + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_NONE: + ksft_print_msg("%s.%d Invalid control type NONE\n", + ctl->name, index); + return false; + + case SND_CTL_ELEM_TYPE_BOOLEAN: + int_val = snd_ctl_elem_value_get_boolean(val, index); + switch (int_val) { + case 0: + case 1: + break; + default: + ksft_print_msg("%s.%d Invalid boolean value %ld\n", + ctl->name, index, int_val); + return false; + } + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + int_val = snd_ctl_elem_value_get_integer(val, index); + + if (int_val < snd_ctl_elem_info_get_min(ctl->info)) { + ksft_print_msg("%s.%d value %ld less than minimum %ld\n", + ctl->name, index, int_val, + snd_ctl_elem_info_get_min(ctl->info)); + return false; + } + + if (int_val > snd_ctl_elem_info_get_max(ctl->info)) { + ksft_print_msg("%s.%d value %ld more than maximum %ld\n", + ctl->name, index, int_val, + snd_ctl_elem_info_get_max(ctl->info)); + return false; + } + + /* Only check step size if there is one and we're in bounds */ + if (snd_ctl_elem_info_get_step(ctl->info) && + (int_val - snd_ctl_elem_info_get_min(ctl->info) % + snd_ctl_elem_info_get_step(ctl->info))) { + ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n", + ctl->name, index, int_val, + snd_ctl_elem_info_get_step(ctl->info), + snd_ctl_elem_info_get_min(ctl->info)); + return false; + } + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + int64_val = snd_ctl_elem_value_get_integer64(val, index); + + if (int64_val < snd_ctl_elem_info_get_min64(ctl->info)) { + ksft_print_msg("%s.%d value %lld less than minimum %lld\n", + ctl->name, index, int64_val, + snd_ctl_elem_info_get_min64(ctl->info)); + return false; + } + + if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) { + ksft_print_msg("%s.%d value %lld more than maximum %lld\n", + ctl->name, index, int64_val, + snd_ctl_elem_info_get_max(ctl->info)); + return false; + } + + /* Only check step size if there is one and we're in bounds */ + if (snd_ctl_elem_info_get_step64(ctl->info) && + (int64_val - snd_ctl_elem_info_get_min64(ctl->info)) % + snd_ctl_elem_info_get_step64(ctl->info)) { + ksft_print_msg("%s.%d value %lld invalid for step %lld minimum %lld\n", + ctl->name, index, int64_val, + snd_ctl_elem_info_get_step64(ctl->info), + snd_ctl_elem_info_get_min64(ctl->info)); + return false; + } + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + int_val = snd_ctl_elem_value_get_enumerated(val, index); + + if (int_val < 0) { + ksft_print_msg("%s.%d negative value %ld for enumeration\n", + ctl->name, index, int_val); + return false; + } + + if (int_val >= snd_ctl_elem_info_get_items(ctl->info)) { + ksft_print_msg("%s.%d value %ld more than item count %ld\n", + ctl->name, index, int_val, + snd_ctl_elem_info_get_items(ctl->info)); + return false; + } + break; + + default: + /* No tests for other types */ + break; + } + + return true; +} + +/* + * Check that the provided value meets the constraints for the + * provided control. + */ +bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) +{ + int i; + bool valid = true; + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) + if (!ctl_value_index_valid(ctl, val, i)) + valid = false; + + return valid; +} + +/* + * Check that we can read the default value and it is valid. Write + * tests use the read value to restore the default. + */ +void test_ctl_get_value(struct ctl_data *ctl) +{ + int err; + + /* If the control is turned off let's be polite */ + if (snd_ctl_elem_info_is_inactive(ctl->info)) { + ksft_print_msg("%s is inactive\n", ctl->name); + ksft_test_result_skip("get_value.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + /* Can't test reading on an unreadable control */ + if (!snd_ctl_elem_info_is_readable(ctl->info)) { + ksft_print_msg("%s is not readable\n", ctl->name); + ksft_test_result_skip("get_value.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + err = snd_ctl_elem_read(ctl->card->handle, ctl->def_val); + if (err < 0) { + ksft_print_msg("snd_ctl_elem_read() failed: %s\n", + snd_strerror(err)); + goto out; + } + + if (!ctl_value_valid(ctl, ctl->def_val)) + err = -EINVAL; + +out: + ksft_test_result(err >= 0, "get_value.%d.%d\n", + ctl->card->card, ctl->elem); +} + +bool show_mismatch(struct ctl_data *ctl, int index, + snd_ctl_elem_value_t *read_val, + snd_ctl_elem_value_t *expected_val) +{ + long long expected_int, read_int; + + /* + * We factor out the code to compare values representable as + * integers, ensure that check doesn't log otherwise. + */ + expected_int = 0; + read_int = 0; + + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_BOOLEAN: + expected_int = snd_ctl_elem_value_get_boolean(expected_val, + index); + read_int = snd_ctl_elem_value_get_boolean(read_val, index); + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + expected_int = snd_ctl_elem_value_get_integer(expected_val, + index); + read_int = snd_ctl_elem_value_get_integer(read_val, index); + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + expected_int = snd_ctl_elem_value_get_integer64(expected_val, + index); + read_int = snd_ctl_elem_value_get_integer64(read_val, + index); + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + expected_int = snd_ctl_elem_value_get_enumerated(expected_val, + index); + read_int = snd_ctl_elem_value_get_enumerated(read_val, + index); + break; + + default: + break; + } + + if (expected_int != read_int) { + /* + * NOTE: The volatile attribute means that the hardware + * can voluntarily change the state of control element + * independent of any operation by software. + */ + bool is_volatile = snd_ctl_elem_info_is_volatile(ctl->info); + ksft_print_msg("%s.%d expected %lld but read %lld, is_volatile %d\n", + ctl->name, index, expected_int, read_int, is_volatile); + return !is_volatile; + } else { + return false; + } +} + +/* + * Write a value then if possible verify that we get the expected + * result. An optional expected value can be provided if we expect + * the write to fail, for verifying that invalid writes don't corrupt + * anything. + */ +int write_and_verify(struct ctl_data *ctl, + snd_ctl_elem_value_t *write_val, + snd_ctl_elem_value_t *expected_val) +{ + int err, i; + bool error_expected, mismatch_shown; + snd_ctl_elem_value_t *read_val, *w_val; + snd_ctl_elem_value_alloca(&read_val); + snd_ctl_elem_value_alloca(&w_val); + + /* + * We need to copy the write value since writing can modify + * the value which causes surprises, and allocate an expected + * value if we expect to read back what we wrote. + */ + snd_ctl_elem_value_copy(w_val, write_val); + if (expected_val) { + error_expected = true; + } else { + error_expected = false; + snd_ctl_elem_value_alloca(&expected_val); + snd_ctl_elem_value_copy(expected_val, write_val); + } + + /* + * Do the write, if we have an expected value ignore the error + * and carry on to validate the expected value. + */ + err = snd_ctl_elem_write(ctl->card->handle, w_val); + if (err < 0 && !error_expected) { + ksft_print_msg("snd_ctl_elem_write() failed: %s\n", + snd_strerror(err)); + return err; + } + + /* Can we do the verification part? */ + if (!snd_ctl_elem_info_is_readable(ctl->info)) + return err; + + snd_ctl_elem_value_set_id(read_val, ctl->id); + + err = snd_ctl_elem_read(ctl->card->handle, read_val); + if (err < 0) { + ksft_print_msg("snd_ctl_elem_read() failed: %s\n", + snd_strerror(err)); + return err; + } + + /* + * Use the libray to compare values, if there's a mismatch + * carry on and try to provide a more useful diagnostic than + * just "mismatch". + */ + if (!snd_ctl_elem_value_compare(expected_val, read_val)) + return 0; + + mismatch_shown = false; + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) + if (show_mismatch(ctl, i, read_val, expected_val)) + mismatch_shown = true; + + if (!mismatch_shown) + ksft_print_msg("%s read and written values differ\n", + ctl->name); + + return -1; +} + +/* + * Make sure we can write the default value back to the control, this + * should validate that at least some write works. + */ +void test_ctl_write_default(struct ctl_data *ctl) +{ + int err; + + /* If the control is turned off let's be polite */ + if (snd_ctl_elem_info_is_inactive(ctl->info)) { + ksft_print_msg("%s is inactive\n", ctl->name); + ksft_test_result_skip("write_default.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + if (!snd_ctl_elem_info_is_writable(ctl->info)) { + ksft_print_msg("%s is not writeable\n", ctl->name); + ksft_test_result_skip("write_default.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + /* No idea what the default was for unreadable controls */ + if (!snd_ctl_elem_info_is_readable(ctl->info)) { + ksft_print_msg("%s couldn't read default\n", ctl->name); + ksft_test_result_skip("write_default.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + err = write_and_verify(ctl, ctl->def_val, NULL); + + ksft_test_result(err >= 0, "write_default.%d.%d\n", + ctl->card->card, ctl->elem); +} + +bool test_ctl_write_valid_boolean(struct ctl_data *ctl) +{ + int err, i, j; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + for (j = 0; j < 2; j++) { + snd_ctl_elem_value_set_boolean(val, i, j); + err = write_and_verify(ctl, val, NULL); + if (err != 0) + fail = true; + } + } + + return !fail; +} + +bool test_ctl_write_valid_integer(struct ctl_data *ctl) +{ + int err; + int i; + long j, step; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + step = snd_ctl_elem_info_get_step(ctl->info); + if (!step) + step = 1; + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + for (j = snd_ctl_elem_info_get_min(ctl->info); + j <= snd_ctl_elem_info_get_max(ctl->info); j += step) { + + snd_ctl_elem_value_set_integer(val, i, j); + err = write_and_verify(ctl, val, NULL); + if (err != 0) + fail = true; + } + } + + + return !fail; +} + +bool test_ctl_write_valid_integer64(struct ctl_data *ctl) +{ + int err, i; + long long j, step; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + step = snd_ctl_elem_info_get_step64(ctl->info); + if (!step) + step = 1; + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + for (j = snd_ctl_elem_info_get_min64(ctl->info); + j <= snd_ctl_elem_info_get_max64(ctl->info); j += step) { + + snd_ctl_elem_value_set_integer64(val, i, j); + err = write_and_verify(ctl, val, NULL); + if (err != 0) + fail = true; + } + } + + return !fail; +} + +bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) +{ + int err, i, j; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + for (j = 0; j < snd_ctl_elem_info_get_items(ctl->info); j++) { + snd_ctl_elem_value_set_enumerated(val, i, j); + err = write_and_verify(ctl, val, NULL); + if (err != 0) + fail = true; + } + } + + return !fail; +} + +void test_ctl_write_valid(struct ctl_data *ctl) +{ + bool pass; + int err; + + /* If the control is turned off let's be polite */ + if (snd_ctl_elem_info_is_inactive(ctl->info)) { + ksft_print_msg("%s is inactive\n", ctl->name); + ksft_test_result_skip("write_valid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + if (!snd_ctl_elem_info_is_writable(ctl->info)) { + ksft_print_msg("%s is not writeable\n", ctl->name); + ksft_test_result_skip("write_valid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_BOOLEAN: + pass = test_ctl_write_valid_boolean(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + pass = test_ctl_write_valid_integer(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + pass = test_ctl_write_valid_integer64(ctl); + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + pass = test_ctl_write_valid_enumerated(ctl); + break; + + default: + /* No tests for this yet */ + ksft_test_result_skip("write_valid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + /* Restore the default value to minimise disruption */ + err = write_and_verify(ctl, ctl->def_val, NULL); + if (err < 0) + pass = false; + + ksft_test_result(pass, "write_valid.%d.%d\n", + ctl->card->card, ctl->elem); +} + +int main(void) +{ + struct ctl_data *ctl; + + ksft_print_header(); + + find_controls(); + + ksft_set_plan(num_controls * TESTS_PER_CONTROL); + + for (ctl = ctl_list; ctl != NULL; ctl = ctl->next) { + /* + * Must test get_value() before we write anything, the + * test stores the default value for later cleanup. + */ + test_ctl_get_value(ctl); + test_ctl_write_default(ctl); + test_ctl_write_valid(ctl); + } + + ksft_exit_pass(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 3cb5ac5da087..8c129961accf 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -4,6 +4,7 @@ /aarch64/get-reg-list /aarch64/psci_cpu_on_test /aarch64/vgic_init +/aarch64/vgic_irq /s390x/memop /s390x/resets /s390x/sync_regs_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 17342b575e85..ee8cf2149824 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -32,11 +32,16 @@ endif ifeq ($(ARCH),s390) UNAME_M := s390x endif +# Set UNAME_M riscv compile/install to work +ifeq ($(ARCH),riscv) + UNAME_M := riscv +endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c +LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features @@ -77,6 +82,7 @@ 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/vmx_pi_mmio_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 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test @@ -96,6 +102,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test TEST_GEN_PROGS_aarch64 += aarch64/vgic_init +TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -119,6 +126,13 @@ TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += demand_paging_test +TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += kvm_create_max_vcpus +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_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) @@ -133,7 +147,7 @@ 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/$(UNAME_M) -I.. + -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index bf6a45b0b8dc..9ad38bd360a4 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -382,7 +382,7 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - vgic_v3_setup(vm, nr_vcpus, GICD_BASE_GPA, GICR_BASE_GPA); + vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index cc898181faab..f769fc6cd927 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -1014,6 +1014,22 @@ static __u64 sve_rejects_set[] = { KVM_REG_ARM64_SVE_VLS, }; +static __u64 pauth_addr_regs[] = { + ARM64_SYS_REG(3, 0, 2, 1, 0), /* APIAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 1), /* APIAKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 2), /* APIBKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 3), /* APIBKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 0), /* APDAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 1), /* APDAKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 2), /* APDBKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 3) /* APDBKEYHI_EL1 */ +}; + +static __u64 pauth_generic_regs[] = { + ARM64_SYS_REG(3, 0, 2, 3, 0), /* APGAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 3, 1), /* APGAKEYHI_EL1 */ +}; + #define BASE_SUBLIST \ { "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), } #define VREGS_SUBLIST \ @@ -1025,6 +1041,21 @@ static __u64 sve_rejects_set[] = { { "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \ .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \ .rejects_set = sve_rejects_set, .rejects_set_n = ARRAY_SIZE(sve_rejects_set), } +#define PAUTH_SUBLIST \ + { \ + .name = "pauth_address", \ + .capability = KVM_CAP_ARM_PTRAUTH_ADDRESS, \ + .feature = KVM_ARM_VCPU_PTRAUTH_ADDRESS, \ + .regs = pauth_addr_regs, \ + .regs_n = ARRAY_SIZE(pauth_addr_regs), \ + }, \ + { \ + .name = "pauth_generic", \ + .capability = KVM_CAP_ARM_PTRAUTH_GENERIC, \ + .feature = KVM_ARM_VCPU_PTRAUTH_GENERIC, \ + .regs = pauth_generic_regs, \ + .regs_n = ARRAY_SIZE(pauth_generic_regs), \ + } static struct vcpu_config vregs_config = { .sublists = { @@ -1056,11 +1087,30 @@ static struct vcpu_config sve_pmu_config = { {0}, }, }; +static struct vcpu_config pauth_config = { + .sublists = { + BASE_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + {0}, + }, +}; +static struct vcpu_config pauth_pmu_config = { + .sublists = { + BASE_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + PMU_SUBLIST, + {0}, + }, +}; static struct vcpu_config *vcpu_configs[] = { &vregs_config, &vregs_pmu_config, &sve_config, &sve_pmu_config, + &pauth_config, + &pauth_pmu_config, }; static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c new file mode 100644 index 000000000000..e6c7d7f8fbd1 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -0,0 +1,853 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * vgic_irq.c - Test userspace injection of IRQs + * + * This test validates the injection of IRQs from userspace using various + * methods (e.g., KVM_IRQ_LINE) and modes (e.g., EOI). The guest "asks" the + * host to inject a specific intid via a GUEST_SYNC call, and then checks that + * it received it. + */ + +#include <asm/kvm.h> +#include <asm/kvm_para.h> +#include <sys/eventfd.h> +#include <linux/sizes.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "gic.h" +#include "gic_v3.h" +#include "vgic.h" + +#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 + * function. + */ +struct test_args { + uint32_t nr_irqs; /* number of KVM supported IRQs. */ + bool eoi_split; /* 1 is eoir+dir, 0 is eoir only */ + bool level_sensitive; /* 1 is level, 0 is edge */ + int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */ + bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */ +}; + +/* + * KVM implements 32 priority levels: + * 0x00 (highest priority) - 0xF8 (lowest priority), in steps of 8 + * + * Note that these macros will still be correct in the case that KVM implements + * more priority levels. Also note that 32 is the minimum for GICv3 and GICv2. + */ +#define KVM_NUM_PRIOS 32 +#define KVM_PRIO_SHIFT 3 /* steps of 8 = 1 << 3 */ +#define KVM_PRIO_STEPS (1 << KVM_PRIO_SHIFT) /* 8 */ +#define LOWEST_PRIO (KVM_NUM_PRIOS - 1) +#define CPU_PRIO_MASK (LOWEST_PRIO << KVM_PRIO_SHIFT) /* 0xf8 */ +#define IRQ_DEFAULT_PRIO (LOWEST_PRIO - 1) +#define IRQ_DEFAULT_PRIO_REG (IRQ_DEFAULT_PRIO << KVM_PRIO_SHIFT) /* 0xf0 */ + +static void *dist = (void *)GICD_BASE_GPA; +static void *redist = (void *)GICR_BASE_GPA; + +/* + * The kvm_inject_* utilities are used by the guest to ask the host to inject + * interrupts (e.g., using the KVM_IRQ_LINE ioctl). + */ + +typedef enum { + KVM_INJECT_EDGE_IRQ_LINE = 1, + KVM_SET_IRQ_LINE, + KVM_SET_IRQ_LINE_HIGH, + KVM_SET_LEVEL_INFO_HIGH, + KVM_INJECT_IRQFD, + KVM_WRITE_ISPENDR, + KVM_WRITE_ISACTIVER, +} kvm_inject_cmd; + +struct kvm_inject_args { + kvm_inject_cmd cmd; + uint32_t first_intid; + uint32_t num; + int level; + bool expect_failure; +}; + +/* Used on the guest side to perform the hypercall. */ +static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, + uint32_t num, int level, bool expect_failure); + +/* Used on the host side to get the hypercall info. */ +static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, + struct kvm_inject_args *args); + +#define _KVM_INJECT_MULTI(cmd, intid, num, expect_failure) \ + kvm_inject_call(cmd, intid, num, -1 /* not used */, expect_failure) + +#define KVM_INJECT_MULTI(cmd, intid, num) \ + _KVM_INJECT_MULTI(cmd, intid, num, false) + +#define _KVM_INJECT(cmd, intid, expect_failure) \ + _KVM_INJECT_MULTI(cmd, intid, 1, expect_failure) + +#define KVM_INJECT(cmd, intid) \ + _KVM_INJECT_MULTI(cmd, intid, 1, false) + +#define KVM_ACTIVATE(cmd, intid) \ + kvm_inject_call(cmd, intid, 1, 1, false); + +struct kvm_inject_desc { + kvm_inject_cmd cmd; + /* can inject PPIs, PPIs, and/or SPIs. */ + bool sgi, ppi, spi; +}; + +static struct kvm_inject_desc inject_edge_fns[] = { + /* sgi ppi spi */ + { KVM_INJECT_EDGE_IRQ_LINE, false, false, true }, + { KVM_INJECT_IRQFD, false, false, true }, + { KVM_WRITE_ISPENDR, true, false, true }, + { 0, }, +}; + +static struct kvm_inject_desc inject_level_fns[] = { + /* sgi ppi spi */ + { KVM_SET_IRQ_LINE_HIGH, false, true, true }, + { KVM_SET_LEVEL_INFO_HIGH, false, true, true }, + { KVM_INJECT_IRQFD, false, false, true }, + { KVM_WRITE_ISPENDR, false, true, true }, + { 0, }, +}; + +static struct kvm_inject_desc set_active_fns[] = { + /* sgi ppi spi */ + { KVM_WRITE_ISACTIVER, true, true, true }, + { 0, }, +}; + +#define for_each_inject_fn(t, f) \ + for ((f) = (t); (f)->cmd; (f)++) + +#define for_each_supported_inject_fn(args, t, f) \ + for_each_inject_fn(t, f) \ + if ((args)->kvm_supports_irqfd || (f)->cmd != KVM_INJECT_IRQFD) + +#define for_each_supported_activate_fn(args, t, f) \ + for_each_supported_inject_fn((args), (t), (f)) + +/* Shared between the guest main thread and the IRQ handlers. */ +volatile uint64_t irq_handled; +volatile uint32_t irqnr_received[MAX_SPI + 1]; + +static void reset_stats(void) +{ + int i; + + irq_handled = 0; + for (i = 0; i <= MAX_SPI; i++) + irqnr_received[i] = 0; +} + +static uint64_t gic_read_ap1r0(void) +{ + uint64_t reg = read_sysreg_s(SYS_ICV_AP1R0_EL1); + + dsb(sy); + return reg; +} + +static void gic_write_ap1r0(uint64_t val) +{ + write_sysreg_s(val, SYS_ICV_AP1R0_EL1); + isb(); +} + +static void guest_set_irq_line(uint32_t intid, uint32_t level); + +static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive) +{ + uint32_t intid = gic_get_and_ack_irq(); + + if (intid == IAR_SPURIOUS) + return; + + GUEST_ASSERT(gic_irq_get_active(intid)); + + if (!level_sensitive) + GUEST_ASSERT(!gic_irq_get_pending(intid)); + + if (level_sensitive) + guest_set_irq_line(intid, 0); + + GUEST_ASSERT(intid < MAX_SPI); + irqnr_received[intid] += 1; + irq_handled += 1; + + gic_set_eoi(intid); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + if (eoi_split) + gic_set_dir(intid); + + GUEST_ASSERT(!gic_irq_get_active(intid)); + GUEST_ASSERT(!gic_irq_get_pending(intid)); +} + +static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, + uint32_t num, int level, bool expect_failure) +{ + struct kvm_inject_args args = { + .cmd = cmd, + .first_intid = first_intid, + .num = num, + .level = level, + .expect_failure = expect_failure, + }; + GUEST_SYNC(&args); +} + +#define GUEST_ASSERT_IAR_EMPTY() \ +do { \ + uint32_t _intid; \ + _intid = gic_get_and_ack_irq(); \ + GUEST_ASSERT(_intid == 0 || _intid == IAR_SPURIOUS); \ +} while (0) + +#define CAT_HELPER(a, b) a ## b +#define CAT(a, b) CAT_HELPER(a, b) +#define PREFIX guest_irq_handler_ +#define GUEST_IRQ_HANDLER_NAME(split, lev) CAT(PREFIX, CAT(split, lev)) +#define GENERATE_GUEST_IRQ_HANDLER(split, lev) \ +static void CAT(PREFIX, CAT(split, lev))(struct ex_regs *regs) \ +{ \ + guest_irq_generic_handler(split, lev); \ +} + +GENERATE_GUEST_IRQ_HANDLER(0, 0); +GENERATE_GUEST_IRQ_HANDLER(0, 1); +GENERATE_GUEST_IRQ_HANDLER(1, 0); +GENERATE_GUEST_IRQ_HANDLER(1, 1); + +static void (*guest_irq_handlers[2][2])(struct ex_regs *) = { + {GUEST_IRQ_HANDLER_NAME(0, 0), GUEST_IRQ_HANDLER_NAME(0, 1),}, + {GUEST_IRQ_HANDLER_NAME(1, 0), GUEST_IRQ_HANDLER_NAME(1, 1),}, +}; + +static void reset_priorities(struct test_args *args) +{ + int i; + + for (i = 0; i < args->nr_irqs; i++) + gic_set_priority(i, IRQ_DEFAULT_PRIO_REG); +} + +static void guest_set_irq_line(uint32_t intid, uint32_t level) +{ + kvm_inject_call(KVM_SET_IRQ_LINE, intid, 1, level, false); +} + +static void test_inject_fail(struct test_args *args, + uint32_t intid, kvm_inject_cmd cmd) +{ + reset_stats(); + + _KVM_INJECT(cmd, intid, true); + /* no IRQ to handle on entry */ + + GUEST_ASSERT_EQ(irq_handled, 0); + GUEST_ASSERT_IAR_EMPTY(); +} + +static void guest_inject(struct test_args *args, + uint32_t first_intid, uint32_t num, + kvm_inject_cmd cmd) +{ + uint32_t i; + + reset_stats(); + + /* Cycle over all priorities to make things more interesting. */ + for (i = first_intid; i < num + first_intid; i++) + gic_set_priority(i, (i % (KVM_NUM_PRIOS - 1)) << 3); + + asm volatile("msr daifset, #2" : : : "memory"); + KVM_INJECT_MULTI(cmd, first_intid, num); + + while (irq_handled < num) { + asm volatile("wfi\n" + "msr daifclr, #2\n" + /* handle IRQ */ + "msr daifset, #2\n" + : : : "memory"); + } + asm volatile("msr daifclr, #2" : : : "memory"); + + GUEST_ASSERT_EQ(irq_handled, num); + for (i = first_intid; i < num + first_intid; i++) + GUEST_ASSERT_EQ(irqnr_received[i], 1); + GUEST_ASSERT_IAR_EMPTY(); + + reset_priorities(args); +} + +/* + * Restore the active state of multiple concurrent IRQs (given by + * concurrent_irqs). This does what a live-migration would do on the + * destination side assuming there are some active IRQs that were not + * deactivated yet. + */ +static void guest_restore_active(struct test_args *args, + uint32_t first_intid, uint32_t num, + kvm_inject_cmd cmd) +{ + uint32_t prio, intid, ap1r; + int i; + + /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs + * in descending order, so intid+1 can preempt intid. + */ + for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) { + GUEST_ASSERT(prio >= 0); + intid = i + first_intid; + gic_set_priority(intid, prio); + } + + /* In a real migration, KVM would restore all GIC state before running + * guest code. + */ + for (i = 0; i < num; i++) { + intid = i + first_intid; + KVM_ACTIVATE(cmd, intid); + ap1r = gic_read_ap1r0(); + ap1r |= 1U << i; + gic_write_ap1r0(ap1r); + } + + /* This is where the "migration" would occur. */ + + /* finish handling the IRQs starting with the highest priority one. */ + for (i = 0; i < num; i++) { + intid = num - i - 1 + first_intid; + gic_set_eoi(intid); + if (args->eoi_split) + gic_set_dir(intid); + } + + for (i = 0; i < num; i++) + GUEST_ASSERT(!gic_irq_get_active(i + first_intid)); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + GUEST_ASSERT_IAR_EMPTY(); +} + +/* + * Polls the IAR until it's not a spurious interrupt. + * + * This function should only be used in test_inject_preemption (with IRQs + * masked). + */ +static uint32_t wait_for_and_activate_irq(void) +{ + uint32_t intid; + + do { + asm volatile("wfi" : : : "memory"); + intid = gic_get_and_ack_irq(); + } while (intid == IAR_SPURIOUS); + + return intid; +} + +/* + * Inject multiple concurrent IRQs (num IRQs starting at first_intid) and + * handle them without handling the actual exceptions. This is done by masking + * interrupts for the whole test. + */ +static void test_inject_preemption(struct test_args *args, + uint32_t first_intid, int num, + kvm_inject_cmd cmd) +{ + uint32_t intid, prio, step = KVM_PRIO_STEPS; + int i; + + /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs + * in descending order, so intid+1 can preempt intid. + */ + for (i = 0, prio = (num - 1) * step; i < num; i++, prio -= step) { + GUEST_ASSERT(prio >= 0); + intid = i + first_intid; + gic_set_priority(intid, prio); + } + + local_irq_disable(); + + for (i = 0; i < num; i++) { + uint32_t tmp; + intid = i + first_intid; + KVM_INJECT(cmd, intid); + /* Each successive IRQ will preempt the previous one. */ + tmp = wait_for_and_activate_irq(); + GUEST_ASSERT_EQ(tmp, intid); + if (args->level_sensitive) + guest_set_irq_line(intid, 0); + } + + /* finish handling the IRQs starting with the highest priority one. */ + for (i = 0; i < num; i++) { + intid = num - i - 1 + first_intid; + gic_set_eoi(intid); + if (args->eoi_split) + gic_set_dir(intid); + } + + local_irq_enable(); + + for (i = 0; i < num; i++) + GUEST_ASSERT(!gic_irq_get_active(i + first_intid)); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + GUEST_ASSERT_IAR_EMPTY(); + + reset_priorities(args); +} + +static void test_injection(struct test_args *args, struct kvm_inject_desc *f) +{ + uint32_t nr_irqs = args->nr_irqs; + + if (f->sgi) { + guest_inject(args, MIN_SGI, 1, f->cmd); + guest_inject(args, 0, 16, f->cmd); + } + + if (f->ppi) + guest_inject(args, MIN_PPI, 1, f->cmd); + + if (f->spi) { + guest_inject(args, MIN_SPI, 1, f->cmd); + guest_inject(args, nr_irqs - 1, 1, f->cmd); + guest_inject(args, MIN_SPI, nr_irqs - MIN_SPI, f->cmd); + } +} + +static void test_injection_failure(struct test_args *args, + struct kvm_inject_desc *f) +{ + uint32_t bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, }; + int i; + + for (i = 0; i < ARRAY_SIZE(bad_intid); i++) + test_inject_fail(args, bad_intid[i], f->cmd); +} + +static void test_preemption(struct test_args *args, struct kvm_inject_desc *f) +{ + /* + * Test up to 4 levels of preemption. The reason is that KVM doesn't + * currently implement the ability to have more than the number-of-LRs + * number of concurrently active IRQs. The number of LRs implemented is + * IMPLEMENTATION DEFINED, however, it seems that most implement 4. + */ + if (f->sgi) + test_inject_preemption(args, MIN_SGI, 4, f->cmd); + + if (f->ppi) + test_inject_preemption(args, MIN_PPI, 4, f->cmd); + + if (f->spi) + test_inject_preemption(args, MIN_SPI, 4, f->cmd); +} + +static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f) +{ + /* Test up to 4 active IRQs. Same reason as in test_preemption. */ + if (f->sgi) + guest_restore_active(args, MIN_SGI, 4, f->cmd); + + if (f->ppi) + guest_restore_active(args, MIN_PPI, 4, f->cmd); + + if (f->spi) + guest_restore_active(args, MIN_SPI, 4, f->cmd); +} + +static void guest_code(struct test_args args) +{ + uint32_t i, nr_irqs = args.nr_irqs; + bool level_sensitive = args.level_sensitive; + struct kvm_inject_desc *f, *inject_fns; + + gic_init(GIC_V3, 1, dist, redist); + + for (i = 0; i < nr_irqs; i++) + gic_irq_enable(i); + + for (i = MIN_SPI; i < nr_irqs; i++) + gic_irq_set_config(i, !args.level_sensitive); + + gic_set_eoi_split(args.eoi_split); + + reset_priorities(&args); + gic_set_priority_mask(CPU_PRIO_MASK); + + inject_fns = level_sensitive ? inject_level_fns + : inject_edge_fns; + + local_irq_enable(); + + /* Start the tests. */ + for_each_supported_inject_fn(&args, inject_fns, f) { + test_injection(&args, f); + test_preemption(&args, f); + test_injection_failure(&args, f); + } + + /* Restore the active state of IRQs. This would happen when live + * migrating IRQs in the middle of being handled. + */ + for_each_supported_activate_fn(&args, set_active_fns, f) + test_restore_active(&args, f); + + GUEST_DONE(); +} + +static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level, + struct test_args *test_args, bool expect_failure) +{ + int ret; + + if (!expect_failure) { + kvm_arm_irq_line(vm, intid, level); + } else { + /* The interface doesn't allow larger intid's. */ + if (intid > KVM_ARM_IRQ_NUM_MASK) + return; + + ret = _kvm_arm_irq_line(vm, intid, level); + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %i did not cause KVM_IRQ_LINE " + "error: rc: %i errno: %i", intid, ret, errno); + } +} + +void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level, + bool expect_failure) +{ + if (!expect_failure) { + kvm_irq_set_level_info(gic_fd, intid, level); + } else { + int ret = _kvm_irq_set_level_info(gic_fd, intid, level); + /* + * The kernel silently fails for invalid SPIs and SGIs (which + * are not level-sensitive). It only checks for intid to not + * spill over 1U << 10 (the max reserved SPI). Also, callers + * are supposed to mask the intid with 0x3ff (1023). + */ + if (intid > VGIC_MAX_RESERVED) + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %i did not cause VGIC_GRP_LEVEL_INFO " + "error: rc: %i errno: %i", intid, ret, errno); + else + TEST_ASSERT(!ret, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO " + "for intid %i failed, rc: %i errno: %i", + intid, ret, errno); + } +} + +static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, + uint32_t intid, uint32_t num, uint32_t kvm_max_routes, + bool expect_failure) +{ + struct kvm_irq_routing *routing; + int ret; + uint64_t i; + + assert(num <= kvm_max_routes && kvm_max_routes <= KVM_MAX_IRQ_ROUTES); + + routing = kvm_gsi_routing_create(); + for (i = intid; i < (uint64_t)intid + num; i++) + kvm_gsi_routing_irqchip_add(routing, i - MIN_SPI, i - MIN_SPI); + + if (!expect_failure) { + kvm_gsi_routing_write(vm, routing); + } else { + ret = _kvm_gsi_routing_write(vm, routing); + /* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */ + if (intid >= KVM_IRQCHIP_NUM_PINS) + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %u did not cause KVM_SET_GSI_ROUTING " + "error: rc: %i errno: %i", intid, ret, errno); + else + TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING " + "for intid %i failed, rc: %i errno: %i", + intid, ret, errno); + } +} + +static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid, + uint32_t vcpu, bool expect_failure) +{ + /* + * Ignore this when expecting failure as invalid intids will lead to + * either trying to inject SGIs when we configured the test to be + * level_sensitive (or the reverse), or inject large intids which + * will lead to writing above the ISPENDR register space (and we + * don't want to do that either). + */ + if (!expect_failure) + kvm_irq_write_ispendr(gic_fd, intid, vcpu); +} + +static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, + uint32_t intid, uint32_t num, uint32_t kvm_max_routes, + bool expect_failure) +{ + int fd[MAX_SPI]; + uint64_t val; + int ret, f; + uint64_t i; + + /* + * There is no way to try injecting an SGI or PPI as the interface + * starts counting from the first SPI (above the private ones), so just + * exit. + */ + if (INTID_IS_SGI(intid) || INTID_IS_PPI(intid)) + return; + + kvm_set_gsi_routing_irqchip_check(vm, intid, num, + kvm_max_routes, expect_failure); + + /* + * If expect_failure, then just to inject anyway. These + * will silently fail. And in any case, the guest will check + * that no actual interrupt was injected for those cases. + */ + + 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); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + struct kvm_irqfd irqfd = { + .fd = fd[f], + .gsi = i - MIN_SPI, + }; + assert(i <= (uint64_t)UINT_MAX); + vm_ioctl(vm, KVM_IRQFD, &irqfd); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + 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); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + close(fd[f]); +} + +/* handles the valid case: intid=0xffffffff num=1 */ +#define for_each_intid(first, num, tmp, i) \ + for ((tmp) = (i) = (first); \ + (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) +{ + 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; + uint64_t tmp; + uint32_t i; + + /* handles the valid case: intid=0xffffffff num=1 */ + assert(intid < UINT_MAX - num || num == 1); + + switch (cmd) { + case KVM_INJECT_EDGE_IRQ_LINE: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 1, test_args, + expect_failure); + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 0, test_args, + expect_failure); + break; + case KVM_SET_IRQ_LINE: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, level, test_args, + expect_failure); + break; + case KVM_SET_IRQ_LINE_HIGH: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 1, test_args, + expect_failure); + break; + case KVM_SET_LEVEL_INFO_HIGH: + for_each_intid(intid, num, tmp, i) + kvm_irq_set_level_info_check(gic_fd, i, 1, + expect_failure); + break; + case KVM_INJECT_IRQFD: + kvm_routing_and_irqfd_check(vm, intid, num, + test_args->kvm_max_routes, + expect_failure); + break; + case KVM_WRITE_ISPENDR: + for (i = intid; i < intid + num; i++) + kvm_irq_write_ispendr_check(gic_fd, i, + VCPU_ID, expect_failure); + break; + case KVM_WRITE_ISACTIVER: + for (i = intid; i < intid + num; i++) + kvm_irq_write_isactiver(gic_fd, i, VCPU_ID); + break; + default: + break; + } +} + +static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, + struct kvm_inject_args *args) +{ + struct kvm_inject_args *kvm_args_hva; + vm_vaddr_t kvm_args_gva; + + kvm_args_gva = uc->args[1]; + kvm_args_hva = (struct kvm_inject_args *)addr_gva2hva(vm, kvm_args_gva); + memcpy(args, kvm_args_hva, sizeof(struct kvm_inject_args)); +} + +static void print_args(struct test_args *args) +{ + printf("nr-irqs=%d level-sensitive=%d eoi-split=%d\n", + args->nr_irqs, args->level_sensitive, + args->eoi_split); +} + +static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) +{ + struct ucall uc; + int gic_fd; + struct kvm_vm *vm; + struct kvm_inject_args inject_args; + + struct test_args args = { + .nr_irqs = nr_irqs, + .level_sensitive = level_sensitive, + .eoi_split = eoi_split, + .kvm_max_routes = kvm_check_cap(KVM_CAP_IRQ_ROUTING), + .kvm_supports_irqfd = kvm_check_cap(KVM_CAP_IRQFD), + }; + + print_args(&args); + + vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + /* Setup the guest args page (so it gets the args). */ + vcpu_args_set(vm, 0, 1, args); + + gic_fd = vgic_v3_setup(vm, 1, nr_irqs, + GICD_BASE_GPA, GICR_BASE_GPA); + + vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, + guest_irq_handlers[args.eoi_split][args.level_sensitive]); + + while (1) { + vcpu_run(vm, VCPU_ID); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + kvm_inject_get_call(vm, &uc, &inject_args); + run_guest_cmd(vm, 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]); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + close(gic_fd); + kvm_vm_free(vm); +} + +static void help(const char *name) +{ + printf( + "\n" + "usage: %s [-n num_irqs] [-e eoi_split] [-l level_sensitive]\n", name); + printf(" -n: specify number of IRQs to setup the vgic with. " + "It has to be a multiple of 32 and between 64 and 1024.\n"); + printf(" -e: if 1 then EOI is split into a write to DIR on top " + "of writing EOI.\n"); + printf(" -l: specify whether the IRQs are level-sensitive (1) or not (0)."); + puts(""); + exit(1); +} + +int main(int argc, char **argv) +{ + uint32_t nr_irqs = 64; + bool default_args = true; + bool level_sensitive = false; + int opt; + bool eoi_split = false; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) { + switch (opt) { + case 'n': + nr_irqs = atoi(optarg); + if (nr_irqs > 1024 || nr_irqs % 32) + help(argv[0]); + break; + case 'e': + eoi_split = (bool)atoi(optarg); + default_args = false; + break; + case 'l': + level_sensitive = (bool)atoi(optarg); + default_args = false; + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + /* If the user just specified nr_irqs and/or gic_version, then run all + * combinations. + */ + if (default_args) { + test_vgic(nr_irqs, false /* level */, false /* eoi_split */); + test_vgic(nr_irqs, false /* level */, true /* eoi_split */); + test_vgic(nr_irqs, true /* level */, false /* eoi_split */); + test_vgic(nr_irqs, true /* level */, true /* eoi_split */); + } else { + test_vgic(nr_irqs, level_sensitive, eoi_split); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h index 85dd1e53048e..b217ea17cac5 100644 --- a/tools/testing/selftests/kvm/include/aarch64/gic.h +++ b/tools/testing/selftests/kvm/include/aarch64/gic.h @@ -11,11 +11,37 @@ enum gic_type { GIC_TYPE_MAX, }; +#define MIN_SGI 0 +#define MIN_PPI 16 +#define MIN_SPI 32 +#define MAX_SPI 1019 +#define IAR_SPURIOUS 1023 + +#define INTID_IS_SGI(intid) (0 <= (intid) && (intid) < MIN_PPI) +#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI) +#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI) + void gic_init(enum gic_type type, unsigned int nr_cpus, void *dist_base, void *redist_base); void gic_irq_enable(unsigned int intid); void gic_irq_disable(unsigned int intid); unsigned int gic_get_and_ack_irq(void); void gic_set_eoi(unsigned int intid); +void gic_set_dir(unsigned int intid); + +/* + * Sets the EOI mode. When split is false, EOI just drops the priority. When + * split is true, EOI drops the priority and deactivates the interrupt. + */ +void gic_set_eoi_split(bool split); +void gic_set_priority_mask(uint64_t mask); +void gic_set_priority(uint32_t intid, uint32_t prio); +void gic_irq_set_active(unsigned int intid); +void gic_irq_clear_active(unsigned int intid); +bool gic_irq_get_active(unsigned int intid); +void gic_irq_set_pending(unsigned int intid); +void gic_irq_clear_pending(unsigned int intid); +bool gic_irq_get_pending(unsigned int intid); +void gic_irq_set_config(unsigned int intid, bool is_edge); #endif /* SELFTEST_KVM_GIC_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h index b51536d469a6..ba0886e8a2bb 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h +++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h @@ -16,8 +16,12 @@ #define GICD_IGROUPR 0x0080 #define GICD_ISENABLER 0x0100 #define GICD_ICENABLER 0x0180 +#define GICD_ISPENDR 0x0200 +#define GICD_ICPENDR 0x0280 #define GICD_ICACTIVER 0x0380 +#define GICD_ISACTIVER 0x0300 #define GICD_IPRIORITYR 0x0400 +#define GICD_ICFGR 0x0C00 /* * The assumption is that the guest runs in a non-secure mode. @@ -49,16 +53,24 @@ #define GICR_IGROUPR0 GICD_IGROUPR #define GICR_ISENABLER0 GICD_ISENABLER #define GICR_ICENABLER0 GICD_ICENABLER +#define GICR_ISPENDR0 GICD_ISPENDR +#define GICR_ISACTIVER0 GICD_ISACTIVER #define GICR_ICACTIVER0 GICD_ICACTIVER +#define GICR_ICENABLER GICD_ICENABLER +#define GICR_ICACTIVER GICD_ICACTIVER #define GICR_IPRIORITYR0 GICD_IPRIORITYR /* CPU interface registers */ #define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) #define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0) #define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1) +#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1) +#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4) #define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5) #define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) +#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0) + #define ICC_PMR_DEF_PRIO 0xf0 #define ICC_SRE_EL1_SRE (1U << 0) diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 27d8e1bb5b36..8f9f46979a00 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -113,6 +113,9 @@ enum { #define ESR_EC_WP_CURRENT 0x35 #define ESR_EC_BRK_INS 0x3c +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); diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h index 0ecfb253893c..4442081221a0 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h @@ -14,7 +14,21 @@ ((uint64_t)(flags) << 12) | \ index) -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, uint64_t gicd_base_gpa, uint64_t gicr_base_gpa); -#endif /* SELFTEST_KVM_VGIC_H */ +#define VGIC_MAX_RESERVED 1023 + +void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); +int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); + +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); + +#define KVM_IRQCHIP_NUM_PINS (1020 - 32) + +#endif // SELFTEST_KVM_VGIC_H diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 2d62edc49d67..c9286811a4cb 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -7,412 +7,7 @@ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H -#include "test_util.h" - -#include "asm/kvm.h" -#include "linux/list.h" -#include "linux/kvm.h" -#include <sys/ioctl.h> - -#include "sparsebit.h" - -#define KVM_DEV_PATH "/dev/kvm" -#define KVM_MAX_VCPUS 512 - -#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 */ - -/* 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 - -enum vm_guest_mode { - VM_MODE_P52V48_4K, - VM_MODE_P52V48_64K, - VM_MODE_P48V48_4K, - VM_MODE_P48V48_64K, - VM_MODE_P40V48_4K, - VM_MODE_P40V48_64K, - VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ - VM_MODE_P47V64_4K, - VM_MODE_P44V64_4K, - NUM_VM_MODES, -}; - -#if defined(__aarch64__) - -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__x86_64__) - -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__s390x__) - -#define VM_MODE_DEFAULT VM_MODE_P44V64_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 16) - -#endif - -#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) -#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) - -struct vm_guest_mode_params { - unsigned int pa_bits; - unsigned int va_bits; - unsigned int page_size; - unsigned int page_shift; -}; -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_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); -int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, - struct kvm_enable_cap *cap); -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); -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_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); - -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); - -void vm_create_irqchip(struct kvm_vm *vm); - -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - 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); -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); - -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages); -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); -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); - -/* - * VM VCPU Args Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * num - number of arguments - * ... - arguments, each of type uint64_t - * - * Output Args: None - * - * 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. - */ -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); - -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); - -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, - vm_paddr_t paddr_min, uint32_t memslot); -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. - */ -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code); - -/* 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[]); - -/* 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[]); - -/* - * 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 - */ -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); - -bool vm_is_unrestricted_guest(struct kvm_vm *vm); - -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); - -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); -static inline unsigned int -vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) -{ - unsigned int n; - n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); -#ifdef __s390x__ - /* s390 requires 1M aligned guest sizes */ - n = (n + 255) & ~255; -#endif - return n; -} - -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)); \ -}) - -#define sync_global_from_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - memcpy(&(g), _p, sizeof(g)); \ -}) - -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); - -/* Common ucalls */ -enum { - UCALL_NONE, - UCALL_SYNC, - UCALL_ABORT, - UCALL_DONE, - UCALL_UNHANDLED, -}; - -#define UCALL_MAX_ARGS 6 - -struct ucall { - uint64_t cmd; - uint64_t args[UCALL_MAX_ARGS]; -}; - -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); - -#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); \ -} while (0) - -#define GUEST_ASSERT(_condition) \ - __GUEST_ASSERT(_condition, #_condition, 0, 0) - -#define GUEST_ASSERT_1(_condition, arg1) \ - __GUEST_ASSERT(_condition, #_condition, 1, (arg1)) - -#define GUEST_ASSERT_2(_condition, arg1, arg2) \ - __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2)) - -#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \ - __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3)) - -#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ - __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4)) - -#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) - -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); +#include "kvm_util_base.h" +#include "ucall_common.h" #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h new file mode 100644 index 000000000000..66775de26952 --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -0,0 +1,399 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/kvm_util_base.h + * + * Copyright (C) 2018, Google LLC. + */ +#ifndef SELFTEST_KVM_UTIL_BASE_H +#define SELFTEST_KVM_UTIL_BASE_H + +#include "test_util.h" + +#include "asm/kvm.h" +#include "linux/list.h" +#include "linux/kvm.h" +#include <sys/ioctl.h> + +#include "sparsebit.h" + +#define KVM_DEV_PATH "/dev/kvm" +#define KVM_MAX_VCPUS 512 + +#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 */ + +/* 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 + +enum vm_guest_mode { + VM_MODE_P52V48_4K, + VM_MODE_P52V48_64K, + VM_MODE_P48V48_4K, + VM_MODE_P48V48_16K, + VM_MODE_P48V48_64K, + VM_MODE_P40V48_4K, + VM_MODE_P40V48_16K, + VM_MODE_P40V48_64K, + VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, + VM_MODE_P36V48_4K, + VM_MODE_P36V48_16K, + VM_MODE_P36V48_64K, + VM_MODE_P36V47_16K, + NUM_VM_MODES, +}; + +#if defined(__aarch64__) + +extern enum vm_guest_mode vm_mode_default; + +#define VM_MODE_DEFAULT vm_mode_default +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__x86_64__) + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + +#elif defined(__riscv) + +#if __riscv_xlen == 32 +#error "RISC-V 32-bit kvm selftests not supported" +#endif + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#endif + +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + +struct vm_guest_mode_params { + unsigned int pa_bits; + unsigned int va_bits; + unsigned int page_size; + unsigned int page_shift; +}; +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); +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_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); + +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); + +void vm_create_irqchip(struct kvm_vm *vm); + +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + 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); +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); + +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages); +void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); +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); + +/* + * VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * 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. + */ +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 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); +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin); +int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); +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, + vm_paddr_t paddr_min, uint32_t memslot); +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. + */ +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code); + +/* 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[]); + +/* 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[]); + +/* + * 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 + */ +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); +void vm_xsave_req_perm(void); + +bool vm_is_unrestricted_guest(struct kvm_vm *vm); + +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); + +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); +static inline unsigned int +vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + unsigned int n; + n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); +#ifdef __s390x__ + /* s390 requires 1M aligned guest sizes */ + n = (n + 255) & ~255; +#endif + return n; +} + +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)); \ +}) + +#define sync_global_from_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(&(g), _p, sizeof(g)); \ +}) + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + +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); + +#endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h new file mode 100644 index 000000000000..dc284c6bdbc3 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RISC-V processor specific defines + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +#include "kvm_util.h" +#include <linux/stringify.h> + +static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, + uint64_t size) +{ + return KVM_REG_RISCV | type | idx | size; +} + +#if __riscv_xlen == 64 +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64 +#else +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32 +#endif + +#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \ + KVM_REG_RISCV_CONFIG_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \ + KVM_REG_RISCV_CORE_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \ + KVM_REG_RISCV_CSR_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \ + 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 +#define PGTBL_L3_BLOCK_SHIFT 39 +#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL +#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1)) +/* L2 index Bit[38:30] */ +#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL +#define PGTBL_L2_INDEX_SHIFT 30 +#define PGTBL_L2_BLOCK_SHIFT 30 +#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL +#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1)) +/* L1 index Bit[29:21] */ +#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL +#define PGTBL_L1_INDEX_SHIFT 21 +#define PGTBL_L1_BLOCK_SHIFT 21 +#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL +#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1)) +/* L0 index Bit[20:12] */ +#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL +#define PGTBL_L0_INDEX_SHIFT 12 +#define PGTBL_L0_BLOCK_SHIFT 12 +#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL +#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1)) + +#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL +#define PGTBL_PTE_ADDR_SHIFT 10 +#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL +#define PGTBL_PTE_RSW_SHIFT 8 +#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL +#define PGTBL_PTE_DIRTY_SHIFT 7 +#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL +#define PGTBL_PTE_ACCESSED_SHIFT 6 +#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL +#define PGTBL_PTE_GLOBAL_SHIFT 5 +#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL +#define PGTBL_PTE_USER_SHIFT 4 +#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL +#define PGTBL_PTE_EXECUTE_SHIFT 3 +#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL +#define PGTBL_PTE_WRITE_SHIFT 2 +#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL +#define PGTBL_PTE_READ_SHIFT 1 +#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \ + PGTBL_PTE_WRITE_MASK | \ + PGTBL_PTE_READ_MASK) +#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL +#define PGTBL_PTE_VALID_SHIFT 0 + +#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE +#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT + +#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define SATP_MODE_39 _AC(0x8000000000000000, UL) +#define SATP_MODE_48 _AC(0x9000000000000000, UL) +#define SATP_ASID_BITS 16 +#define SATP_ASID_SHIFT 44 +#define SATP_ASID_MASK _AC(0xFFFF, UL) + +#define SBI_EXT_EXPERIMENTAL_START 0x08000000 +#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF + +#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END + +struct sbiret { + long error; + long value; +}; + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5); + +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h new file mode 100644 index 000000000000..9eecc9d40b79 --- /dev/null +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/kvm_util.h + * + * Copyright (C) 2018, Google LLC. + */ +#ifndef SELFTEST_KVM_UCALL_COMMON_H +#define SELFTEST_KVM_UCALL_COMMON_H + +/* Common ucalls */ +enum { + UCALL_NONE, + UCALL_SYNC, + UCALL_ABORT, + UCALL_DONE, + UCALL_UNHANDLED, +}; + +#define UCALL_MAX_ARGS 6 + +struct ucall { + uint64_t cmd; + uint64_t args[UCALL_MAX_ARGS]; +}; + +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); + +#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); \ +} while (0) + +#define GUEST_ASSERT(_condition) \ + __GUEST_ASSERT(_condition, #_condition, 0, 0) + +#define GUEST_ASSERT_1(_condition, arg1) \ + __GUEST_ASSERT(_condition, #_condition, 1, (arg1)) + +#define GUEST_ASSERT_2(_condition, arg1, arg2) \ + __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2)) + +#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \ + __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3)) + +#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ + __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4)) + +#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) + +#endif /* SELFTEST_KVM_UCALL_COMMON_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 05e65ca1c30c..e94ba0fc67d8 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -10,8 +10,10 @@ #include <assert.h> #include <stdint.h> +#include <syscall.h> #include <asm/msr-index.h> +#include <asm/prctl.h> #include "../kvm_util.h" @@ -92,6 +94,21 @@ struct desc_ptr { uint64_t address; } __attribute__((packed)); +struct kvm_x86_state { + struct kvm_xsave *xsave; + struct kvm_vcpu_events events; + struct kvm_mp_state mp_state; + struct kvm_regs regs; + struct kvm_xcrs xcrs; + struct kvm_sregs sregs; + struct kvm_debugregs debugregs; + union { + struct kvm_nested_state nested; + char nested_[16384]; + }; + struct kvm_msrs msrs; +}; + static inline uint64_t get_desc64_base(const struct desc64 *desc) { return ((uint64_t)desc->base3 << 32) | @@ -348,10 +365,10 @@ static inline unsigned long get_xmm(int n) bool is_intel_cpu(void); -struct kvm_x86_state; 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); +void kvm_x86_state_cleanup(struct kvm_x86_state *state); struct kvm_msr_list *kvm_get_msr_index_list(void); uint64_t kvm_get_feature_msr(uint64_t msr_index); @@ -443,4 +460,11 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, /* VMX_EPT_VPID_CAP bits */ #define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) +#define XSTATE_XTILE_CFG_BIT 17 +#define XSTATE_XTILE_DATA_BIT 18 + +#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT) +#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT) +#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \ + XSTATE_XTILE_DATA_MASK) #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c index fff4fc27504d..55668631d546 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c @@ -93,3 +93,69 @@ void gic_set_eoi(unsigned int intid) GUEST_ASSERT(gic_common_ops); gic_common_ops->gic_write_eoir(intid); } + +void gic_set_dir(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_write_dir(intid); +} + +void gic_set_eoi_split(bool split) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_eoi_split(split); +} + +void gic_set_priority_mask(uint64_t pmr) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_priority_mask(pmr); +} + +void gic_set_priority(unsigned int intid, unsigned int prio) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_priority(intid, prio); +} + +void gic_irq_set_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_active(intid); +} + +void gic_irq_clear_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_clear_active(intid); +} + +bool gic_irq_get_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + return gic_common_ops->gic_irq_get_active(intid); +} + +void gic_irq_set_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_pending(intid); +} + +void gic_irq_clear_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_clear_pending(intid); +} + +bool gic_irq_get_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + return gic_common_ops->gic_irq_get_pending(intid); +} + +void gic_irq_set_config(unsigned int intid, bool is_edge) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_config(intid, is_edge); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h index d81d739433dc..75d07313c893 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h +++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h @@ -14,6 +14,17 @@ struct gic_common_ops { void (*gic_irq_disable)(unsigned int intid); uint64_t (*gic_read_iar)(void); void (*gic_write_eoir)(uint32_t irq); + void (*gic_write_dir)(uint32_t irq); + void (*gic_set_eoi_split)(bool split); + void (*gic_set_priority_mask)(uint64_t mask); + void (*gic_set_priority)(uint32_t intid, uint32_t prio); + void (*gic_irq_set_active)(uint32_t intid); + void (*gic_irq_clear_active)(uint32_t intid); + bool (*gic_irq_get_active)(uint32_t intid); + void (*gic_irq_set_pending)(uint32_t intid); + void (*gic_irq_clear_pending)(uint32_t intid); + bool (*gic_irq_get_pending)(uint32_t intid); + void (*gic_irq_set_config)(uint32_t intid, bool is_edge); }; extern const struct gic_common_ops gicv3_ops; diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c index 2dbf3339b62e..00f613c0583c 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c +++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c @@ -19,7 +19,8 @@ struct gicv3_data { unsigned int nr_spis; }; -#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) +#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) +#define DIST_BIT (1U << 31) enum gicv3_intid_range { SGI_RANGE, @@ -50,6 +51,14 @@ static void gicv3_gicr_wait_for_rwp(void *redist_base) } } +static void gicv3_wait_for_rwp(uint32_t cpu_or_dist) +{ + if (cpu_or_dist & DIST_BIT) + gicv3_gicd_wait_for_rwp(); + else + gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]); +} + static enum gicv3_intid_range get_intid_range(unsigned int intid) { switch (intid) { @@ -81,39 +90,175 @@ static void gicv3_write_eoir(uint32_t irq) isb(); } -static void -gicv3_config_irq(unsigned int intid, unsigned int offset) +static void gicv3_write_dir(uint32_t irq) +{ + write_sysreg_s(irq, SYS_ICC_DIR_EL1); + isb(); +} + +static void gicv3_set_priority_mask(uint64_t mask) +{ + write_sysreg_s(mask, SYS_ICC_PMR_EL1); +} + +static void gicv3_set_eoi_split(bool split) +{ + uint32_t val; + + /* All other fields are read-only, so no need to read CTLR first. In + * fact, the kernel does the same. + */ + val = split ? (1U << 1) : 0; + write_sysreg_s(val, SYS_ICC_CTLR_EL1); + isb(); +} + +uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset) +{ + void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base + : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]); + return readl(base + offset); +} + +void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val) +{ + void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base + : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]); + writel(reg_val, base + offset); +} + +uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask) +{ + return gicv3_reg_readl(cpu_or_dist, offset) & mask; +} + +void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset, + uint32_t mask, uint32_t reg_val) +{ + uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask; + + tmp |= (reg_val & mask); + gicv3_reg_writel(cpu_or_dist, offset, tmp); +} + +/* + * We use a single offset for the distributor and redistributor maps as they + * have the same value in both. The only exceptions are registers that only + * exist in one and not the other, like GICR_WAKER that doesn't exist in the + * distributor map. Such registers are conveniently marked as reserved in the + * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being + * marked as "Reserved" in the Distributor map. + */ +static void gicv3_access_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field, + bool write, uint32_t *val) { uint32_t cpu = guest_get_vcpuid(); - uint32_t mask = 1 << (intid % 32); enum gicv3_intid_range intid_range = get_intid_range(intid); - void *reg; - - /* We care about 'cpu' only for SGIs or PPIs */ - if (intid_range == SGI_RANGE || intid_range == PPI_RANGE) { - GUEST_ASSERT(cpu < gicv3_data.nr_cpus); - - reg = sgi_base_from_redist(gicv3_data.redist_base[cpu]) + - offset; - writel(mask, reg); - gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu]); - } else if (intid_range == SPI_RANGE) { - reg = gicv3_data.dist_base + offset + (intid / 32) * 4; - writel(mask, reg); - gicv3_gicd_wait_for_rwp(); - } else { - GUEST_ASSERT(0); - } + uint32_t fields_per_reg, index, mask, shift; + uint32_t cpu_or_dist; + + GUEST_ASSERT(bits_per_field <= reg_bits); + GUEST_ASSERT(*val < (1U << bits_per_field)); + /* Some registers like IROUTER are 64 bit long. Those are currently not + * supported by readl nor writel, so just asserting here until then. + */ + GUEST_ASSERT(reg_bits == 32); + + fields_per_reg = reg_bits / bits_per_field; + index = intid % fields_per_reg; + shift = index * bits_per_field; + mask = ((1U << bits_per_field) - 1) << shift; + + /* Set offset to the actual register holding intid's config. */ + offset += (intid / fields_per_reg) * (reg_bits / 8); + + cpu_or_dist = (intid_range == SPI_RANGE) ? DIST_BIT : cpu; + + if (write) + gicv3_setl_fields(cpu_or_dist, offset, mask, *val << shift); + *val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift; +} + +static void gicv3_write_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field, uint32_t val) +{ + gicv3_access_reg(intid, offset, reg_bits, + bits_per_field, true, &val); +} + +static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field) +{ + uint32_t val; + + gicv3_access_reg(intid, offset, reg_bits, + bits_per_field, false, &val); + return val; +} + +static void gicv3_set_priority(uint32_t intid, uint32_t prio) +{ + gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio); +} + +/* Sets the intid to be level-sensitive or edge-triggered. */ +static void gicv3_irq_set_config(uint32_t intid, bool is_edge) +{ + uint32_t val; + + /* N/A for private interrupts. */ + GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE); + val = is_edge ? 2 : 0; + gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val); +} + +static void gicv3_irq_enable(uint32_t intid) +{ + bool is_spi = get_intid_range(intid) == SPI_RANGE; + uint32_t cpu = guest_get_vcpuid(); + + gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1); + gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); +} + +static void gicv3_irq_disable(uint32_t intid) +{ + bool is_spi = get_intid_range(intid) == SPI_RANGE; + uint32_t cpu = guest_get_vcpuid(); + + gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1); + gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); +} + +static void gicv3_irq_set_active(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1); +} + +static void gicv3_irq_clear_active(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1); +} + +static bool gicv3_irq_get_active(uint32_t intid) +{ + return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1); +} + +static void gicv3_irq_set_pending(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1); } -static void gicv3_irq_enable(unsigned int intid) +static void gicv3_irq_clear_pending(uint32_t intid) { - gicv3_config_irq(intid, GICD_ISENABLER); + gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1); } -static void gicv3_irq_disable(unsigned int intid) +static bool gicv3_irq_get_pending(uint32_t intid) { - gicv3_config_irq(intid, GICD_ICENABLER); + return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1); } static void gicv3_enable_redist(void *redist_base) @@ -237,4 +382,15 @@ const struct gic_common_ops gicv3_ops = { .gic_irq_disable = gicv3_irq_disable, .gic_read_iar = gicv3_read_iar, .gic_write_eoir = gicv3_write_eoir, + .gic_write_dir = gicv3_write_dir, + .gic_set_priority_mask = gicv3_set_priority_mask, + .gic_set_eoi_split = gicv3_set_eoi_split, + .gic_set_priority = gicv3_set_priority, + .gic_irq_set_active = gicv3_irq_set_active, + .gic_irq_clear_active = gicv3_irq_clear_active, + .gic_irq_get_active = gicv3_irq_get_active, + .gic_irq_set_pending = gicv3_irq_set_pending, + .gic_irq_clear_pending = gicv3_irq_clear_pending, + .gic_irq_get_pending = gicv3_irq_get_pending, + .gic_irq_set_config = gicv3_irq_set_config, }; diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index b4eeeafd2a70..9343d82519b4 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <assert.h> +#include "guest_modes.h" #include "kvm_util.h" #include "../kvm_util_internal.h" #include "processor.h" @@ -237,6 +238,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init 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); + /* Configure base granule size */ switch (vm->mode) { case VM_MODE_P52V48_4K: TEST_FAIL("AArch64 does not support 4K sized pages " @@ -245,25 +247,47 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init TEST_FAIL("AArch64 does not support 4K sized pages " "with ANY-bit physical address ranges"); case VM_MODE_P52V48_64K: + case VM_MODE_P48V48_64K: + case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ - tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 2ul << 14; /* TG0 = 16KB */ break; case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + /* Configure output size */ + switch (vm->mode) { + case VM_MODE_P52V48_64K: + tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_4K: + case VM_MODE_P48V48_16K: case VM_MODE_P48V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; case VM_MODE_P40V48_4K: - tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ - break; + case VM_MODE_P40V48_16K: case VM_MODE_P40V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ break; + case VM_MODE_P36V48_4K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V48_64K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 1ul << 32; /* IPS = 36 bits */ + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } @@ -432,3 +456,47 @@ uint32_t guest_get_vcpuid(void) { return read_sysreg(tpidr_el1); } + +void aarch64_get_supported_page_sizes(uint32_t ipa, + bool *ps4k, bool *ps16k, bool *ps64k) +{ + struct kvm_vcpu_init preferred_init; + int kvm_fd, vm_fd, vcpu_fd, err; + uint64_t val; + struct kvm_one_reg reg = { + .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1), + .addr = (uint64_t)&val, + }; + + 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"); + + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu"); + + err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init); + TEST_ASSERT(err == 0, "Can't get target"); + err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init); + TEST_ASSERT(err == 0, "Can't get init vcpu"); + + err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); + TEST_ASSERT(err == 0, "Can't get MMFR0"); + + *ps4k = ((val >> 28) & 0xf) != 0xf; + *ps64k = ((val >> 24) & 0xf) == 0; + *ps16k = ((val >> 20) & 0xf) != 0; + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* + * arm64 doesn't have a true default mode, so start by computing the + * available IPA space and page sizes early. + */ +void __attribute__((constructor)) init_guest_modes(void) +{ + guest_modes_append_default(); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c index b9b271ff520d..b3a0fca0d780 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -5,11 +5,14 @@ #include <linux/kvm.h> #include <linux/sizes.h> +#include <asm/kvm_para.h> #include <asm/kvm.h> #include "kvm_util.h" #include "../kvm_util_internal.h" #include "vgic.h" +#include "gic.h" +#include "gic_v3.h" /* * vGIC-v3 default host setup @@ -28,7 +31,7 @@ * redistributor regions of the guest. Since it depends on the number of * vCPUs for the VM, it must be called after all the vCPUs have been created. */ -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, uint64_t gicd_base_gpa, uint64_t gicr_base_gpa) { int gic_fd; @@ -50,6 +53,13 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, /* Distributor setup */ gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, + 0, &nr_irqs, true); + + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true); nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE); @@ -68,3 +78,94 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, return gic_fd; } + +/* should only work for level sensitive interrupts */ +int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) +{ + uint64_t attr = 32 * (intid / 32); + uint64_t index = intid % 32; + uint64_t val; + int ret; + + ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val, false); + if (ret != 0) + return ret; + + val |= 1U << index; + ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val, true); + return ret; +} + +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); +} + +int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) +{ + uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK; + + TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself " + "doesn't allow injecting SGIs. There's no mask for it."); + + if (INTID_IS_PPI(intid)) + irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT; + else + irq |= KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT; + + return _kvm_irq_line(vm, irq, level); +} + +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); +} + +static void vgic_poke_irq(int gic_fd, uint32_t intid, + uint32_t vcpu, uint64_t reg_off) +{ + uint64_t reg = intid / 32; + uint64_t index = intid % 32; + uint64_t attr = reg_off + reg * 4; + uint64_t val; + bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid); + + /* Check that the addr part of the attr is within 32 bits. */ + assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK); + + uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS + : KVM_DEV_ARM_VGIC_GRP_DIST_REGS; + + if (intid_is_private) { + /* TODO: only vcpu 0 implemented for now. */ + assert(vcpu == 0); + attr += SZ_64K; + } + + /* All calls will succeed, even with invalid intid's, as long as the + * addr part of the attr is within 32 bits (checked above). An invalid + * 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); + val |= 1ULL << index; + kvm_device_access(gic_fd, group, attr, &val, true); +} + +void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu) +{ + vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR); +} + +void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu) +{ + vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER); +} diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index c330f414ef96..8784013b747c 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -4,22 +4,59 @@ */ #include "guest_modes.h" +#ifdef __aarch64__ +#include "processor.h" +enum vm_guest_mode vm_mode_default; +#endif + struct guest_mode guest_modes[NUM_VM_MODES]; void guest_modes_append_default(void) { +#ifndef __aarch64__ guest_mode_append(VM_MODE_DEFAULT, true, true); - -#ifdef __aarch64__ - guest_mode_append(VM_MODE_P40V48_64K, true, true); +#else { unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + bool ps4k, ps16k, ps64k; + int i; + + aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k); + + vm_mode_default = NUM_VM_MODES; + if (limit >= 52) - guest_mode_append(VM_MODE_P52V48_64K, true, true); + guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k); if (limit >= 48) { - guest_mode_append(VM_MODE_P48V48_4K, true, true); - guest_mode_append(VM_MODE_P48V48_64K, true, true); + guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k); + } + if (limit >= 40) { + guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k); + if (ps4k) + vm_mode_default = VM_MODE_P40V48_4K; } + if (limit >= 36) { + guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k); + guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k); + } + + /* + * Pick the first supported IPA size if the default + * isn't available. + */ + for (i = 0; vm_mode_default == NUM_VM_MODES && i < NUM_VM_MODES; i++) { + if (guest_modes[i].supported && guest_modes[i].enabled) + vm_mode_default = i; + } + + TEST_ASSERT(vm_mode_default != NUM_VM_MODES, + "No supported mode!"); } #endif #ifdef __s390x__ @@ -38,6 +75,16 @@ void guest_modes_append_default(void) guest_mode_append(VM_MODE_P47V64_4K, true, true); } #endif +#ifdef __riscv + { + unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS); + + if (sz >= 52) + guest_mode_append(VM_MODE_P52V48_4K, true, true); + if (sz >= 48) + guest_mode_append(VM_MODE_P48V48_4K, true, true); + } +#endif } void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 53d2b5d04b82..4a645dc77f34 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -85,6 +85,33 @@ int kvm_check_cap(long cap) 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: @@ -166,12 +193,18 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", [VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages", [VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages", + [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages", [VM_MODE_P48V48_64K] = "PA-bits:48, VA-bits:48, 64K pages", [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", + [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", + [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages", + [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages", + [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages", + [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -185,12 +218,18 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, + [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 }, [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 }, [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, + [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 }, [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, + [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 }, + [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 }, + [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 }, + [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -252,9 +291,19 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->pgtable_levels = 3; break; case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: vm->pgtable_levels = 4; break; case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: + vm->pgtable_levels = 3; + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + vm->pgtable_levels = 4; + break; + case VM_MODE_P36V47_16K: vm->pgtable_levels = 3; break; case VM_MODE_PXXV48_4K: @@ -344,6 +393,11 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, struct kvm_vm *vm; int i; + /* + * Permission needs to be requested before KVM_SET_CPUID2. + */ + vm_xsave_req_perm(); + /* 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; @@ -2087,6 +2141,78 @@ int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, } /* + * IRQ related functions. + */ + +int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) +{ + struct kvm_irq_level irq_level = { + .irq = irq, + .level = 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); +} + +struct kvm_irq_routing *kvm_gsi_routing_create(void) +{ + struct kvm_irq_routing *routing; + size_t size; + + size = sizeof(struct kvm_irq_routing); + /* Allocate space for the max number of entries: this wastes 196 KBs. */ + size += KVM_MAX_IRQ_ROUTES * sizeof(struct kvm_irq_routing_entry); + routing = calloc(1, size); + assert(routing); + + return routing; +} + +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin) +{ + int i; + + assert(routing); + assert(routing->nr < KVM_MAX_IRQ_ROUTES); + + i = routing->nr; + routing->entries[i].gsi = gsi; + routing->entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; + routing->entries[i].flags = 0; + routing->entries[i].u.irqchip.irqchip = 0; + routing->entries[i].u.irqchip.pin = pin; + routing->nr++; +} + +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); + free(routing); + + return ret; +} + +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); +} + +/* * VM Dump * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c new file mode 100644 index 000000000000..d377f2603d98 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V code + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include <linux/compiler.h> +#include <assert.h> + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 + +static uint64_t page_align(struct kvm_vm *vm, uint64_t v) +{ + return (v + vm->page_size) & ~(vm->page_size - 1); +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +{ + return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) << + PGTBL_PAGE_SIZE_SHIFT; +} + +static uint64_t ptrs_per_pte(struct kvm_vm *vm) +{ + return PGTBL_PAGE_SIZE / sizeof(uint64_t); +} + +static uint64_t pte_index_mask[] = { + PGTBL_L0_INDEX_MASK, + PGTBL_L1_INDEX_MASK, + PGTBL_L2_INDEX_MASK, + PGTBL_L3_INDEX_MASK, +}; + +static uint32_t pte_index_shift[] = { + PGTBL_L0_INDEX_SHIFT, + PGTBL_L1_INDEX_SHIFT, + PGTBL_L2_INDEX_SHIFT, + PGTBL_L3_INDEX_SHIFT, +}; + +static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) +{ + TEST_ASSERT(level > -1, + "Negative page table level (%d) not possible", level); + TEST_ASSERT(level < vm->pgtable_levels, + "Invalid page table level (%d)", level); + + return (gva & pte_index_mask[level]) >> pte_index_shift[level]; +} + +void virt_pgd_alloc(struct kvm_vm *vm) +{ + if (!vm->pgd_created) { + vm_paddr_t paddr = vm_phy_pages_alloc(vm, + page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); + vm->pgd = paddr; + vm->pgd_created = true; + } +} + +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + uint64_t *ptep, next_ppn; + int level = vm->pgtable_levels - 1; + + TEST_ASSERT((vaddr % vm->page_size) == 0, + "Virtual address not on page boundary,\n" + " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, + (vaddr >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", vaddr); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, vaddr, level) * 8; + if (!*ptep) { + next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, vaddr, level) * 8; + if (!*ptep && level > 0) { + next_ppn = vm_alloc_page_table(vm) >> + PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + } + + paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK; +} + +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + uint64_t *ptep; + int level = vm->pgtable_levels - 1; + + if (!vm->pgd_created) + goto unmapped_gva; + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + } + + return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); + +unmapped_gva: + TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d", + gva, level); + exit(1); +} + +static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, + uint64_t page, int level) +{ +#ifdef DEBUG + static const char *const type[] = { "pte", "pmd", "pud", "p4d"}; + uint64_t pte, *ptep; + + if (level < 0) + return; + + for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) { + ptep = addr_gpa2hva(vm, pte); + if (!*ptep) + continue; + fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", + type[level], pte, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +#endif +} + +void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + int level = vm->pgtable_levels - 1; + uint64_t pgd, *ptep; + + if (!vm->pgd_created) + return; + + for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) { + ptep = addr_gpa2hva(vm, pgd); + if (!*ptep) + continue; + fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", + pgd, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +} + +void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid) +{ + unsigned long satp; + + /* + * The RISC-V Sv48 MMU mode supports 56-bit physical address + * for 48-bit virtual address with 4KB last level page size. + */ + switch (vm->mode) { + case VM_MODE_P52V48_4K: + case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN; + satp |= SATP_MODE_48; + + set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp); +} + +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, 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); + + fprintf(stream, + " MODE: 0x%lx\n", core.mode); + fprintf(stream, + " PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n", + core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp); + fprintf(stream, + " TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n", + core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2); + fprintf(stream, + " S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n", + core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1); + fprintf(stream, + " A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n", + core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5); + fprintf(stream, + " A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n", + core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3); + fprintf(stream, + " S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n", + core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7); + fprintf(stream, + " S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n", + core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11); + fprintf(stream, + " T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n", + core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6); +} + +static void guest_hang(void) +{ + while (1) + ; +} + +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + int r; + size_t stack_size = vm->page_size == 4096 ? + DEFAULT_STACK_PGS * vm->page_size : + vm->page_size; + unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_RISCV_GUEST_STACK_VADDR_MIN); + unsigned long current_gp = 0; + struct kvm_mp_state mps; + + vm_vcpu_add(vm, vcpuid); + riscv_vcpu_mmu_setup(vm, vcpuid); + + /* + * With SBI HSM support in KVM RISC-V, all secondary VCPUs are + * powered-off by default so we ensure that all secondary VCPUs + * 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); + 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); + + /* 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); + + /* Setup default exception vector of guest */ + set_reg(vm, vcpuid, RISCV_CSR_REG(stvec), + (unsigned long)guest_hang); +} + +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + uint64_t id = RISCV_CORE_REG(regs.a0); + int i; + + TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n" + " num: %u\n", num); + + va_start(ap, num); + + for (i = 0; i < num; i++) { + switch (i) { + case 0: + id = RISCV_CORE_REG(regs.a0); + break; + case 1: + id = RISCV_CORE_REG(regs.a1); + break; + case 2: + id = RISCV_CORE_REG(regs.a2); + break; + case 3: + id = RISCV_CORE_REG(regs.a3); + break; + case 4: + id = RISCV_CORE_REG(regs.a4); + break; + case 5: + id = RISCV_CORE_REG(regs.a5); + break; + case 6: + id = RISCV_CORE_REG(regs.a6); + break; + case 7: + id = RISCV_CORE_REG(regs.a7); + break; + }; + set_reg(vm, vcpuid, id, va_arg(ap, uint64_t)); + } + + va_end(ap); +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c new file mode 100644 index 000000000000..9e42d8248fa6 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#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) +{ +} + +void ucall_uninit(struct kvm_vm *vm) +{ +} + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + struct sbiret ret; + + asm volatile ( + "ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + return ret; +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + uc.args[i] = va_arg(va, uint64_t); + va_end(va); + + sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc, + 0, 0, 0, 0, 0); +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct ucall ucall = {}; + + if (uc) + memset(uc, 0, sizeof(*uc)); + + if (run->exit_reason == KVM_EXIT_RISCV_SBI && + run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT && + run->riscv_sbi.function_id == 0) { + memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]), + sizeof(ucall)); + + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); + } + + return ucall.cmd; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index eef7b34756d5..babb0f28575c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -650,6 +650,45 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid) vcpu_sregs_set(vm, vcpuid, &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(void) +{ + unsigned long bitmask; + long rc; + + if (!is_xfd_supported()) + return; + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, + XSTATE_XTILE_DATA_BIT); + /* + * The older kernel version(<5.15) can't support + * ARCH_REQ_XCOMP_GUEST_PERM and directly return. + */ + if (rc) + return; + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); + TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); + TEST_ASSERT(bitmask & XFEATURE_XTILE_MASK, + "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", + bitmask); +} + void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { struct kvm_mp_state mp_state; @@ -1017,21 +1056,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) sregs_dump(stream, &sregs, indent + 4); } -struct kvm_x86_state { - struct kvm_vcpu_events events; - struct kvm_mp_state mp_state; - struct kvm_regs regs; - struct kvm_xsave xsave; - struct kvm_xcrs xcrs; - struct kvm_sregs sregs; - struct kvm_debugregs debugregs; - union { - struct kvm_nested_state nested; - char nested_[16384]; - }; - struct kvm_msrs msrs; -}; - static int kvm_get_num_msrs_fd(int kvm_fd) { struct kvm_msr_list nmsrs; @@ -1069,6 +1093,22 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) return list; } +static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu, + struct kvm_x86_state *state) +{ + int size; + + size = vm_check_cap(vm, KVM_CAP_XSAVE2); + if (!size) + size = sizeof(struct kvm_xsave); + + 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); +} + struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); @@ -1112,7 +1152,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i", r); - r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave); + r = vcpu_save_xsave_state(vm, vcpu, state); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", r); @@ -1157,24 +1197,25 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s struct vcpu *vcpu = vcpu_find(vm, vcpuid); int r; - r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", + 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_SREGS, &state->sregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", + 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_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); - r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i", r); @@ -1198,6 +1239,12 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s } } +void kvm_x86_state_cleanup(struct kvm_x86_state *state) +{ + free(state->xsave); + free(state); +} + bool is_intel_cpu(void) { int eax, ebx, ecx, edx; diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c new file mode 100644 index 000000000000..523c1e99ed64 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -0,0 +1,448 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * amx tests + * + * Copyright (C) 2021, Intel, Inc. + * + * Tests for amx #NM exception and save/restore. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#ifndef __x86_64__ +# 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 PAGE_SIZE (1 << 12) +#define NUM_TILES 8 +#define TILE_SIZE 1024 +#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) + +/* Tile configuration associated: */ +#define MAX_TILES 16 +#define RESERVED_BYTES 14 + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define TILE_CPUID 0x1d +#define XSTATE_CPUID 0xd +#define TILE_PALETTE_CPUID_SUBLEAVE 0x1 +#define XSTATE_USER_STATE_SUBLEAVE 0x0 + +#define XSAVE_HDR_OFFSET 512 + +struct xsave_data { + u8 area[XSAVE_SIZE]; +} __aligned(64); + +struct tile_config { + u8 palette_id; + u8 start_row; + u8 reserved[RESERVED_BYTES]; + u16 colsb[MAX_TILES]; + u8 rows[MAX_TILES]; +}; + +struct tile_data { + u8 data[NUM_TILES * TILE_SIZE]; +}; + +struct xtile_info { + u16 bytes_per_tile; + u16 bytes_per_row; + u16 max_names; + u16 max_rows; + u32 xsave_offset; + u32 xsave_size; +}; + +static struct xtile_info xtile; + +static inline u64 __xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void __xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +static inline void __ldtilecfg(void *cfg) +{ + asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00" + : : "a"(cfg)); +} + +static inline void __tileloadd(void *tile) +{ + asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10" + : : "a"(tile), "d"(0)); +} + +static inline void __tilerelease(void) +{ + asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); +} + +static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsavec (%%rdi)" + : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +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!"); +} + +static bool check_xsave_supports_xtile(void) +{ + return __xgetbv(0) & XFEATURE_MASK_XTILE; +} + +static bool enum_xtile_config(void) +{ + u32 eax, ebx, ecx, edx; + + eax = TILE_CPUID; + ecx = TILE_PALETTE_CPUID_SUBLEAVE; + + cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx || !ecx) + return false; + + xtile.max_names = ebx >> 16; + if (xtile.max_names < NUM_TILES) + return false; + + xtile.bytes_per_tile = eax >> 16; + if (xtile.bytes_per_tile < TILE_SIZE) + return false; + + xtile.bytes_per_row = ebx; + xtile.max_rows = ecx; + + return true; +} + +static bool enum_xsave_tile(void) +{ + u32 eax, ebx, ecx, edx; + + eax = XSTATE_CPUID; + ecx = XFEATURE_XTILEDATA; + + cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx) + return false; + + xtile.xsave_offset = ebx; + xtile.xsave_size = eax; + + return true; +} + +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); + if (ebx && ebx <= XSAVE_SIZE) + valid = true; + + return valid; +} + +static bool check_xtile_info(void) +{ + bool ret = false; + + if (!check_xsave_size()) + return ret; + + if (!enum_xsave_tile()) + return ret; + + if (!enum_xtile_config()) + return ret; + + if (sizeof(struct tile_data) >= xtile.xsave_size) + ret = true; + + return ret; +} + +static void set_tilecfg(struct tile_config *cfg) +{ + int i; + + /* Only palette id 1 */ + cfg->palette_id = 1; + for (i = 0; i < xtile.max_names; i++) { + cfg->colsb[i] = xtile.bytes_per_row; + cfg->rows[i] = xtile.max_rows; + } +} + +static void set_xstatebv(void *data, uint64_t bv) +{ + *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv; +} + +static u64 get_xstatebv(void *data) +{ + return *(u64 *)(data + XSAVE_HDR_OFFSET); +} + +static void init_regs(void) +{ + uint64_t cr4, xcr0; + + /* turn on CR4.OSXSAVE */ + cr4 = get_cr4(); + cr4 |= X86_CR4_OSXSAVE; + set_cr4(cr4); + + xcr0 = __xgetbv(0); + xcr0 |= XFEATURE_MASK_XTILE; + __xsetbv(0x0, xcr0); +} + +static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, + struct tile_data *tiledata, + struct xsave_data *xsave_data) +{ + init_regs(); + check_cpuid_xsave(); + GUEST_ASSERT(check_xsave_supports_xtile()); + GUEST_ASSERT(check_xtile_info()); + + /* check xtile configs */ + GUEST_ASSERT(xtile.xsave_offset == 2816); + GUEST_ASSERT(xtile.xsave_size == 8192); + GUEST_ASSERT(xtile.max_names == 8); + GUEST_ASSERT(xtile.bytes_per_tile == 1024); + GUEST_ASSERT(xtile.bytes_per_row == 64); + GUEST_ASSERT(xtile.max_rows == 16); + GUEST_SYNC(1); + + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(2); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + GUEST_SYNC(3); + /* Check save/restore when trap to userspace */ + __tileloadd(tiledata); + GUEST_SYNC(4); + __tilerelease(); + GUEST_SYNC(5); + /* bit 18 not in the XCOMP_BV after xsavec() */ + set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA); + __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(6); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + /* Trigger #NM exception */ + __tileloadd(tiledata); + GUEST_SYNC(10); + + GUEST_DONE(); +} + +void guest_nm_handler(struct ex_regs *regs) +{ + /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ + GUEST_SYNC(7); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(8); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + /* Clear xfd_err */ + wrmsr(MSR_IA32_XFD_ERR, 0); + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(9); +} + +int main(int argc, char *argv[]) +{ + struct kvm_cpuid_entry2 *entry; + struct kvm_regs regs1, regs2; + bool amx_supported = false; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int xsave_restore_size = 0; + vm_vaddr_t amx_cfg, tiledata, xsavedata; + struct ucall uc; + u32 amx_offset; + int stage, ret; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + entry = kvm_get_supported_cpuid_entry(1); + if (!(entry->ecx & X86_FEATURE_XSAVE)) { + print_skip("XSAVE feature not supported"); + exit(KSFT_SKIP); + } + + 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; + } + + run = vcpu_state(vm, VCPU_ID); + vcpu_regs_get(vm, VCPU_ID, ®s1); + + /* Register #NM handler */ + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); + + /* amx cfg for guest_code */ + amx_cfg = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); + + /* amx tiledata for guest_code */ + tiledata = vm_vaddr_alloc_pages(vm, 2); + memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); + + /* 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); + + for (stage = 1; ; stage++) { + _vcpu_run(vm, VCPU_ID); + 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)) { + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + switch (uc.args[1]) { + case 1: + case 2: + case 3: + case 5: + case 6: + case 7: + case 8: + fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); + break; + case 4: + case 10: + fprintf(stderr, + "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + + /* Compacted mode, get amx offset by xsave area + * size subtract 8K amx size. + */ + amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + state = vcpu_save_state(vm, VCPU_ID); + void *amx_start = (void *)state->xsave + amx_offset; + void *tiles_data = (void *)addr_gva2hva(vm, tiledata); + /* Only check TMM0 register, 1 tile */ + ret = memcmp(amx_start, tiles_data, TILE_SIZE); + TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret); + kvm_x86_state_cleanup(state); + break; + case 9: + fprintf(stderr, + "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); + break; + } + break; + case UCALL_DONE: + fprintf(stderr, "UCALL_DONE\n"); + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®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); + kvm_x86_state_cleanup(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®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); + } +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 2b46dcca86a8..4c7841dfd481 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -129,7 +129,7 @@ static void save_restore_vm(struct kvm_vm *vm) vcpu_set_hv_cpuid(vm, VCPU_ID); vcpu_enable_evmcs(vm, VCPU_ID); vcpu_load_state(vm, VCPU_ID, state); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); 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 29b18d565cf4..80056bbbb003 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -21,7 +21,7 @@ #define NR_LOCK_TESTING_THREADS 3 #define NR_LOCK_TESTING_ITERATIONS 10000 -static void sev_ioctl(int vm_fd, int cmd_id, void *data) +static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error) { struct kvm_sev_cmd cmd = { .id = cmd_id, @@ -31,9 +31,19 @@ static void sev_ioctl(int vm_fd, int cmd_id, void *data) int ret; ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); - TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS), + *fw_error = cmd.error; + return ret; +} + +static void sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + int ret; + __u32 fw_error; + + ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error); + TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS, "%d failed: return code: %d, errno: %d, fw error: %d", - cmd_id, ret, errno, cmd.error); + cmd_id, ret, errno, fw_error); } static struct kvm_vm *sev_vm_create(bool es) @@ -225,12 +235,45 @@ static void sev_mirror_create(int dst_fd, int src_fd) TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); } +static void verify_mirror_allowed_cmds(int vm_fd) +{ + struct kvm_sev_guest_status status; + + for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) { + int ret; + __u32 fw_error; + + /* + * These commands are allowed for mirror VMs, all others are + * not. + */ + switch (cmd_id) { + case KVM_SEV_LAUNCH_UPDATE_VMSA: + case KVM_SEV_GUEST_STATUS: + case KVM_SEV_DBG_DECRYPT: + case KVM_SEV_DBG_ENCRYPT: + continue; + default: + break; + } + + /* + * These commands should be disallowed before the data + * parameter is examined so NULL is OK here. + */ + ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able call command: %d. ret: %d, errno: %d\n", + cmd_id, ret, errno); + } + + sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status); +} + static void test_sev_mirror(bool es) { struct kvm_vm *src_vm, *dst_vm; - struct kvm_sev_launch_start start = { - .policy = es ? SEV_POLICY_ES : 0 - }; int i; src_vm = sev_vm_create(es); @@ -241,10 +284,12 @@ static void test_sev_mirror(bool es) /* 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); - sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + verify_mirror_allowed_cmds(dst_vm->fd); + kvm_vm_free(src_vm); kvm_vm_free(dst_vm); } diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index d0fe2fdce58c..2da8eb8e2d96 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -212,7 +212,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); } done: diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 32854c1462ad..2e0a92da8ff5 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -218,7 +218,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); 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 a07480aed397..ff92e25b6f1e 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 @@ -244,7 +244,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); 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 a0699f00b3d6..478e0ae8b93e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,6 +14,9 @@ #include <stdint.h> #include <time.h> #include <sched.h> +#include <signal.h> + +#include <sys/eventfd.h> #define VCPU_ID 5 @@ -22,10 +25,15 @@ #define SHINFO_REGION_SLOT 10 #define PAGE_SIZE 4096 +#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT 11 + +#define SHINFO_ADDR (SHINFO_REGION_GPA) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) +#define SHINFO_VADDR (SHINFO_REGION_GVA) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) #define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) @@ -73,15 +81,37 @@ struct vcpu_info { struct pvclock_vcpu_time_info time; }; /* 64 bytes (x86) */ +struct shared_info { + struct vcpu_info vcpu_info[32]; + unsigned long evtchn_pending[64]; + unsigned long evtchn_mask[64]; + struct pvclock_wall_clock wc; + uint32_t wc_sec_hi; + /* arch_shared_info here */ +}; + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static const char *runstate_names[] = { + "running", + "runnable", + "blocked", + "offline" +}; + +struct { + struct kvm_irq_routing info; + struct kvm_irq_routing_entry entries[2]; +} irq_routes; + static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; vi->evtchn_upcall_pending = 0; + vi->evtchn_pending_sel = 0; GUEST_SYNC(0x20); } @@ -127,7 +157,25 @@ static void guest_code(void) GUEST_SYNC(6); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); - GUEST_DONE(); + /* Attempt to deliver a *masked* interrupt */ + GUEST_SYNC(7); + + /* Wait until we see the bit set */ + struct shared_info *si = (void *)SHINFO_VADDR; + while (!si->evtchn_pending[0]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Now deliver an *unmasked* interrupt */ + GUEST_SYNC(8); + + while (!si->evtchn_pending[1]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Change memslots and deliver an interrupt */ + GUEST_SYNC(9); + + for (;;) + __asm__ __volatile__ ("rep nop" : : : "memory"); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static void handle_alrm(int sig) +{ + TEST_FAIL("IRQ delivery timed out"); +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + 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) ) { @@ -155,6 +212,7 @@ int main(int argc, char *argv[]) } bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); clock_gettime(CLOCK_REALTIME, &min_ts); @@ -166,6 +224,11 @@ int main(int argc, char *argv[]) SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); + struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + + int zero_fd = open("/dev/zero", O_RDONLY); + TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); + struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, .msr = XEN_HYPERCALL_MSR, @@ -184,6 +247,16 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + /* + * Test what happens when the HVA of the shinfo page is remapped after + * the kernel has a reference to it. But make sure we copy the clock + * info over since that's only set at setup time, and we test it later. + */ + struct pvclock_wall_clock wc_copy = shinfo->wc; + void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0); + TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info"); + shinfo->wc = wc_copy; + struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, @@ -214,6 +287,49 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + int irq_fd[2] = { -1, -1 }; + + if (do_eventfd_tests) { + irq_fd[0] = eventfd(0, 0); + irq_fd[1] = eventfd(0, 0); + + /* Unexpected, but not a KVM failure */ + if (irq_fd[0] == -1 || irq_fd[1] == -1) + do_eventfd_tests = false; + } + + if (do_eventfd_tests) { + irq_routes.info.nr = 2; + + irq_routes.entries[0].gsi = 32; + irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[0].u.xen_evtchn.port = 15; + 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 = 66; + 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); + + struct kvm_irqfd ifd = { }; + + ifd.fd = irq_fd[0]; + ifd.gsi = 32; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + ifd.fd = irq_fd[1]; + ifd.gsi = 33; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + struct sigaction sa = { }; + sa.sa_handler = handle_alrm; + sigaction(SIGALRM, &sa, NULL); + } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; @@ -248,6 +364,8 @@ int main(int argc, char *argv[]) switch (uc.args[1]) { case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; @@ -256,11 +374,16 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; + if (verbose) + 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); break; + case 4: + if (verbose) + printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = (uint64_t)-1; @@ -274,6 +397,8 @@ int main(int argc, char *argv[]) break; case 5: + if (verbose) + printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = RUNSTATE_running; @@ -282,16 +407,54 @@ int main(int argc, char *argv[]) rst.u.runstate.time_offline = 0x5a; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 6: + if (verbose) + printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ rundelay = get_run_delay() + MIN_STEAL_TIME; do { sched_yield(); } while (get_run_delay() < rundelay); break; + + case 7: + if (!do_eventfd_tests) + goto done; + if (verbose) + printf("Testing masked event channel\n"); + shinfo->evtchn_mask[0] = 0x8000; + eventfd_write(irq_fd[0], 1UL); + alarm(1); + break; + + case 8: + if (verbose) + printf("Testing unmasked event channel\n"); + /* Unmask that, but deliver the other one */ + shinfo->evtchn_pending[0] = 0; + shinfo->evtchn_mask[0] = 0; + eventfd_write(irq_fd[1], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 9: + if (verbose) + printf("Testing event channel after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0); + eventfd_write(irq_fd[0], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + case 0x20: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; + if (shinfo->evtchn_pending[1] && + shinfo->evtchn_pending[0]) + goto done; break; } break; @@ -318,6 +481,16 @@ int main(int argc, char *argv[]) ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); ti2 = addr_gpa2hva(vm, PVTIME_ADDR); + if (verbose) { + printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec); + printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul, + ti->tsc_shift, ti->flags); + printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul, + ti2->tsc_shift, ti2->flags); + } + vm_ts.tv_sec = wc->sec; vm_ts.tv_nsec = wc->nsec; TEST_ASSERT(wc->version && !(wc->version & 1), @@ -341,6 +514,15 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + if (verbose) { + printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", + rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown", + rs->state, rs->state_entry_time); + for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) { + printf("State %s: %" PRIu64 " ns\n", + runstate_names[i], rs->time[i]); + } + } TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, "State entry time mismatch"); diff --git a/tools/testing/selftests/lkdtm/stack-entropy.sh b/tools/testing/selftests/lkdtm/stack-entropy.sh index 1b4d95d575f8..14fedeef762e 100755 --- a/tools/testing/selftests/lkdtm/stack-entropy.sh +++ b/tools/testing/selftests/lkdtm/stack-entropy.sh @@ -4,13 +4,27 @@ # Measure kernel stack entropy by sampling via LKDTM's REPORT_STACK test. set -e samples="${1:-1000}" +TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT +KSELFTEST_SKIP_TEST=4 + +# Verify we have LKDTM available in the kernel. +if [ ! -r $TRIGGER ] ; then + /sbin/modprobe -q lkdtm || true + if [ ! -r $TRIGGER ] ; then + echo "Cannot find $TRIGGER (missing CONFIG_LKDTM?)" + else + echo "Cannot write $TRIGGER (need to run as root?)" + fi + # Skip this test + exit $KSELFTEST_SKIP_TEST +fi # Capture dmesg continuously since it may fill up depending on sample size. log=$(mktemp -t stack-entropy-XXXXXX) dmesg --follow >"$log" & pid=$! report=-1 for i in $(seq 1 $samples); do - echo "REPORT_STACK" >/sys/kernel/debug/provoke-crash/DIRECT + echo "REPORT_STACK" > $TRIGGER if [ -t 1 ]; then percent=$(( 100 * $i / $samples )) if [ "$percent" -ne "$report" ]; then diff --git a/tools/testing/selftests/powerpc/security/mitigation-patching.sh b/tools/testing/selftests/powerpc/security/mitigation-patching.sh index b0b20e0b4e30..f43aa4b77fba 100755 --- a/tools/testing/selftests/powerpc/security/mitigation-patching.sh +++ b/tools/testing/selftests/powerpc/security/mitigation-patching.sh @@ -44,7 +44,10 @@ mitigations="barrier_nospec stf_barrier count_cache_flush rfi_flush entry_flush for m in $mitigations do - do_one "$m" & + if [[ -f /sys/kernel/debug/powerpc/$m ]] + then + do_one "$m" & + fi done echo "Spawned threads enabling/disabling mitigations ..." diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c index adc2b7294e5f..83647b8277e7 100644 --- a/tools/testing/selftests/powerpc/security/spectre_v2.c +++ b/tools/testing/selftests/powerpc/security/spectre_v2.c @@ -193,7 +193,7 @@ int spectre_v2_test(void) * We are not vulnerable and reporting otherwise, so * missing such a mismatch is safe. */ - if (state == VULNERABLE) + if (miss_percent > 95) return 4; return 1; diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore index ce3375cd8e73..9d0915777fed 100644 --- a/tools/testing/selftests/powerpc/signal/.gitignore +++ b/tools/testing/selftests/powerpc/signal/.gitignore @@ -4,3 +4,5 @@ signal_tm sigfuz sigreturn_vdso sig_sc_double_restart +sigreturn_kernel +sigreturn_unaligned diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile index d6ae54663aed..f679d260afc8 100644 --- a/tools/testing/selftests/powerpc/signal/Makefile +++ b/tools/testing/selftests/powerpc/signal/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso sig_sc_double_restart +TEST_GEN_PROGS += sigreturn_kernel +TEST_GEN_PROGS += sigreturn_unaligned CFLAGS += -maltivec $(OUTPUT)/signal_tm: CFLAGS += -mhtm diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c new file mode 100644 index 000000000000..0a1b6e591eee --- /dev/null +++ b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test that we can't sigreturn to kernel addresses, or to kernel mode. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <signal.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "utils.h" + +#define MSR_PR (1ul << 14) + +static volatile unsigned long long sigreturn_addr; +static volatile unsigned long long sigreturn_msr_mask; + +static void sigusr1_handler(int signo, siginfo_t *si, void *uc_ptr) +{ + ucontext_t *uc = (ucontext_t *)uc_ptr; + + if (sigreturn_addr) + UCONTEXT_NIA(uc) = sigreturn_addr; + + if (sigreturn_msr_mask) + UCONTEXT_MSR(uc) &= sigreturn_msr_mask; +} + +static pid_t fork_child(void) +{ + pid_t pid; + + pid = fork(); + if (pid == 0) { + raise(SIGUSR1); + exit(0); + } + + return pid; +} + +static int expect_segv(pid_t pid) +{ + int child_ret; + + waitpid(pid, &child_ret, 0); + FAIL_IF(WIFEXITED(child_ret)); + FAIL_IF(!WIFSIGNALED(child_ret)); + FAIL_IF(WTERMSIG(child_ret) != 11); + + return 0; +} + +int test_sigreturn_kernel(void) +{ + struct sigaction act; + int child_ret, i; + pid_t pid; + + act.sa_sigaction = sigusr1_handler; + act.sa_flags = SA_SIGINFO; + sigemptyset(&act.sa_mask); + + FAIL_IF(sigaction(SIGUSR1, &act, NULL)); + + for (i = 0; i < 2; i++) { + // Return to kernel + sigreturn_addr = 0xcull << 60; + pid = fork_child(); + expect_segv(pid); + + // Return to kernel virtual + sigreturn_addr = 0xc008ull << 48; + pid = fork_child(); + expect_segv(pid); + + // Return out of range + sigreturn_addr = 0xc010ull << 48; + pid = fork_child(); + expect_segv(pid); + + // Return to no-man's land, just below PAGE_OFFSET + sigreturn_addr = (0xcull << 60) - (64 * 1024); + pid = fork_child(); + expect_segv(pid); + + // Return to no-man's land, above TASK_SIZE_4PB + sigreturn_addr = 0x1ull << 52; + pid = fork_child(); + expect_segv(pid); + + // Return to 0xd space + sigreturn_addr = 0xdull << 60; + pid = fork_child(); + expect_segv(pid); + + // Return to 0xe space + sigreturn_addr = 0xeull << 60; + pid = fork_child(); + expect_segv(pid); + + // Return to 0xf space + sigreturn_addr = 0xfull << 60; + pid = fork_child(); + expect_segv(pid); + + // Attempt to set PR=0 for 2nd loop (should be blocked by kernel) + sigreturn_msr_mask = ~MSR_PR; + } + + printf("All children killed as expected\n"); + + // Don't change address, just MSR, should return to user as normal + sigreturn_addr = 0; + sigreturn_msr_mask = ~MSR_PR; + pid = fork_child(); + waitpid(pid, &child_ret, 0); + FAIL_IF(!WIFEXITED(child_ret)); + FAIL_IF(WIFSIGNALED(child_ret)); + FAIL_IF(WEXITSTATUS(child_ret) != 0); + + return 0; +} + +int main(void) +{ + return test_harness(test_sigreturn_kernel, "sigreturn_kernel"); +} diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c new file mode 100644 index 000000000000..6e58ee4f0fdf --- /dev/null +++ b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test sigreturn to an unaligned address, ie. low 2 bits set. + * Nothing bad should happen. + * This was able to trigger warnings with CONFIG_PPC_RFI_SRR_DEBUG=y. + */ + +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <ucontext.h> +#include <unistd.h> + +#include "utils.h" + + +static void sigusr1_handler(int signo, siginfo_t *info, void *ptr) +{ + ucontext_t *uc = ptr; + + UCONTEXT_NIA(uc) |= 3; +} + +static int test_sigreturn_unaligned(void) +{ + struct sigaction action; + + memset(&action, 0, sizeof(action)); + action.sa_sigaction = sigusr1_handler; + action.sa_flags = SA_SIGINFO; + + FAIL_IF(sigaction(SIGUSR1, &action, NULL) == -1); + + raise(SIGUSR1); + + return 0; +} + +int main(void) +{ + return test_harness(test_sigreturn_unaligned, "sigreturn_unaligned"); +} diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh index fe8fcfb334e0..a5cb4b09a46c 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -24,19 +24,23 @@ if [[ "$1" == "-cgroup-v2" ]]; then reservation_usage_file=rsvd.current fi -cgroup_path=/dev/cgroup/memory -if [[ ! -e $cgroup_path ]]; then - mkdir -p $cgroup_path - if [[ $cgroup2 ]]; then +if [[ $cgroup2 ]]; then + cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + if [[ -z "$cgroup_path" ]]; then + cgroup_path=/dev/cgroup/memory mount -t cgroup2 none $cgroup_path - else + do_umount=1 + fi + echo "+hugetlb" >$cgroup_path/cgroup.subtree_control +else + cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + if [[ -z "$cgroup_path" ]]; then + cgroup_path=/dev/cgroup/memory mount -t cgroup memory,hugetlb $cgroup_path + do_umount=1 fi fi - -if [[ $cgroup2 ]]; then - echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control -fi +export cgroup_path function cleanup() { if [[ $cgroup2 ]]; then @@ -108,7 +112,7 @@ function setup_cgroup() { function wait_for_hugetlb_memory_to_get_depleted() { local cgroup="$1" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" # Wait for hugetlbfs memory to get depleted. while [ $(cat $path) != 0 ]; do echo Waiting for hugetlb memory to get depleted. @@ -121,7 +125,7 @@ function wait_for_hugetlb_memory_to_get_reserved() { local cgroup="$1" local size="$2" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" # Wait for hugetlbfs memory to get written. while [ $(cat $path) != $size ]; do echo Waiting for hugetlb memory reservation to reach size $size. @@ -134,7 +138,7 @@ function wait_for_hugetlb_memory_to_get_written() { local cgroup="$1" local size="$2" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file" # Wait for hugetlbfs memory to get written. while [ $(cat $path) != $size ]; do echo Waiting for hugetlb memory to reach size $size. @@ -574,5 +578,7 @@ for populate in "" "-o"; do done # populate done # method -umount $cgroup_path -rmdir $cgroup_path +if [[ $do_umount ]]; then + umount $cgroup_path + rmdir $cgroup_path +fi diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 864f126ffd78..203323967b50 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1251,6 +1251,48 @@ TEST_F(hmm, anon_teardown) /* * Test memory snapshot without faulting in pages accessed by the device. */ +TEST_F(hmm, mixedmap) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned char *m; + int ret; + + npages = 1; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(npages); + ASSERT_NE(buffer->mirror, NULL); + + + /* Reserve a range of addresses. */ + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + self->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ); + + hmm_buffer_free(buffer); +} + +/* + * Test memory snapshot without faulting in pages accessed by the device. + */ TEST_F(hmm2, snapshot) { struct hmm_buffer *buffer; diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 257df94697a5..2a7c33631a29 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -4,7 +4,11 @@ * * Example of remapping huge page memory in a user application using the * mremap system call. Code assumes a hugetlbfs filesystem is mounted - * at './huge'. The code will use 10MB worth of huge pages. + * at './huge'. The amount of memory used by this test is decided by a command + * line argument in MBs. If missing, the default amount is 10MB. + * + * To make sure the test triggers pmd sharing and goes through the 'unshare' + * path in the mremap code use 1GB (1024) or more. */ #define _GNU_SOURCE @@ -18,8 +22,10 @@ #include <linux/userfaultfd.h> #include <sys/ioctl.h> -#define LENGTH (1UL * 1024 * 1024 * 1024) +#define DEFAULT_LENGTH_MB 10UL +#define MB_TO_BYTES(x) (x * 1024 * 1024) +#define FILE_NAME "huge/hugepagefile" #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) #define FLAGS (MAP_SHARED | MAP_ANONYMOUS) @@ -28,20 +34,20 @@ static void check_bytes(char *addr) printf("First hex is %x\n", *((unsigned int *)addr)); } -static void write_bytes(char *addr) +static void write_bytes(char *addr, size_t len) { unsigned long i; - for (i = 0; i < LENGTH; i++) + for (i = 0; i < len; i++) *(addr + i) = (char)i; } -static int read_bytes(char *addr) +static int read_bytes(char *addr, size_t len) { unsigned long i; check_bytes(addr); - for (i = 0; i < LENGTH; i++) + for (i = 0; i < len; i++) if (*(addr + i) != (char)i) { printf("Mismatch at %lu\n", i); return 1; @@ -99,11 +105,19 @@ static void register_region_with_uffd(char *addr, size_t len) } } -int main(void) +int main(int argc, char *argv[]) { + /* Read memory length as the first arg if valid, otherwise fallback to + * the default length. Any additional args are ignored. + */ + size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL; + + length = length > 0 ? length : DEFAULT_LENGTH_MB; + length = MB_TO_BYTES(length); + int ret = 0; - int fd = open("/huge/test", O_CREAT | O_RDWR, 0755); + int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); if (fd < 0) { perror("Open failed"); @@ -112,7 +126,7 @@ int main(void) /* mmap to a PUD aligned address to hopefully trigger pmd sharing. */ unsigned long suggested_addr = 0x7eaa40000000; - void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + void *haddr = mmap((void *)suggested_addr, length, PROTECTION, MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); printf("Map haddr: Returned address is %p\n", haddr); if (haddr == MAP_FAILED) { @@ -122,7 +136,7 @@ int main(void) /* mmap again to a dummy address to hopefully trigger pmd sharing. */ suggested_addr = 0x7daa40000000; - void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + void *daddr = mmap((void *)suggested_addr, length, PROTECTION, MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); printf("Map daddr: Returned address is %p\n", daddr); if (daddr == MAP_FAILED) { @@ -132,16 +146,16 @@ int main(void) suggested_addr = 0x7faa40000000; void *vaddr = - mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0); + mmap((void *)suggested_addr, length, PROTECTION, FLAGS, -1, 0); printf("Map vaddr: Returned address is %p\n", vaddr); if (vaddr == MAP_FAILED) { perror("mmap2"); exit(1); } - register_region_with_uffd(haddr, LENGTH); + register_region_with_uffd(haddr, length); - void *addr = mremap(haddr, LENGTH, LENGTH, + void *addr = mremap(haddr, length, length, MREMAP_MAYMOVE | MREMAP_FIXED, vaddr); if (addr == MAP_FAILED) { perror("mremap"); @@ -150,10 +164,10 @@ int main(void) printf("Mremap: Returned address is %p\n", addr); check_bytes(addr); - write_bytes(addr); - ret = read_bytes(addr); + write_bytes(addr, length); + ret = read_bytes(addr, length); - munmap(addr, LENGTH); + munmap(addr, length); return ret; } diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh index 4a9a3afe9fd4..bf2d2a684edf 100644 --- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh @@ -18,19 +18,24 @@ if [[ "$1" == "-cgroup-v2" ]]; then usage_file=current fi -CGROUP_ROOT='/dev/cgroup/memory' -MNT='/mnt/huge/' -if [[ ! -e $CGROUP_ROOT ]]; then - mkdir -p $CGROUP_ROOT - if [[ $cgroup2 ]]; then +if [[ $cgroup2 ]]; then + CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + if [[ -z "$CGROUP_ROOT" ]]; then + CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup2 none $CGROUP_ROOT - sleep 1 - echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control - else + do_umount=1 + fi + echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control +else + CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + if [[ -z "$CGROUP_ROOT" ]]; then + CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup memory,hugetlb $CGROUP_ROOT + do_umount=1 fi fi +MNT='/mnt/huge/' function get_machine_hugepage_size() { hpz=$(grep -i hugepagesize /proc/meminfo) diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index a24d30af3094..75d401741394 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -111,7 +111,7 @@ fi echo "-----------------------" echo "running hugepage-mremap" echo "-----------------------" -./hugepage-mremap +./hugepage-mremap 256 if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 9354a5e0321c..d3fd24f9fae8 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -87,7 +87,7 @@ static bool test_uffdio_minor = false; static bool map_shared; static int shm_fd; -static int huge_fd = -1; /* only used for hugetlb_shared test */ +static int huge_fd; static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd = -1; @@ -223,9 +223,6 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) static void hugetlb_release_pages(char *rel_area) { - if (huge_fd == -1) - return; - if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, rel_area == huge_fd_off0 ? 0 : nr_pages * page_size, nr_pages * page_size)) @@ -238,17 +235,17 @@ static void hugetlb_allocate_area(void **alloc_area) char **alloc_area_alias; *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - map_shared ? MAP_SHARED : - MAP_PRIVATE | MAP_HUGETLB | + (map_shared ? MAP_SHARED : MAP_PRIVATE) | + MAP_HUGETLB | (*alloc_area == area_src ? 0 : MAP_NORESERVE), - huge_fd, - *alloc_area == area_src ? 0 : nr_pages * page_size); + huge_fd, *alloc_area == area_src ? 0 : + nr_pages * page_size); if (*alloc_area == MAP_FAILED) err("mmap of hugetlbfs file failed"); if (map_shared) { area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED, + MAP_SHARED | MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) @@ -648,7 +645,7 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg) if (ret != sizeof(*msg)) { if (ret < 0) { - if (errno == EAGAIN) + if (errno == EAGAIN || errno == EINTR) return 1; err("blocking read error"); } else { @@ -724,8 +721,11 @@ static void *uffd_poll_thread(void *arg) for (;;) { ret = poll(pollfd, 2, -1); - if (ret <= 0) + if (ret <= 0) { + if (errno == EINTR || errno == EAGAIN) + continue; err("poll error: %d", ret); + } if (pollfd[1].revents & POLLIN) { if (read(pollfd[1].fd, &tmp_chr, 1) != 1) err("read pipefd error"); @@ -1417,7 +1417,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; - char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1528,13 +1527,9 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - tmp_area = area_src; - area_src = area_dst; - area_dst = tmp_area; + swap(area_src, area_dst); - tmp_area = area_src_alias; - area_src_alias = area_dst_alias; - area_dst_alias = tmp_area; + swap(area_src_alias, area_dst_alias); uffd_stats_report(uffd_stats, nr_cpus); } diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh index d3d0d108924d..70a02301f4c2 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -14,7 +14,7 @@ want_sleep=$8 reserve=$9 echo "Putting task in cgroup '$cgroup'" -echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs +echo $$ > ${cgroup_path:-/dev/cgroup/memory}/"$cgroup"/cgroup.procs echo "Method is $method" diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile new file mode 100644 index 000000000000..2d52ff0bff7d --- /dev/null +++ b/tools/tracing/rtla/Makefile @@ -0,0 +1,102 @@ +NAME := rtla +VERSION := 0.5 + +# From libtracefs: +# Makefiles suck: This macro sets a default value of $(2) for the +# variable named by $(1), unless the variable has been set by +# environment or command line. This is necessary for CC and AR +# because make sets default values, so the simpler ?= approach +# won't work as expected. +define allow-override + $(if $(or $(findstring environment,$(origin $(1))),\ + $(findstring command line,$(origin $(1)))),,\ + $(eval $(1) = $(2))) +endef + +# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix. +$(call allow-override,CC,$(CROSS_COMPILE)gcc) +$(call allow-override,AR,$(CROSS_COMPILE)ar) +$(call allow-override,STRIP,$(CROSS_COMPILE)strip) +$(call allow-override,PKG_CONFIG,pkg-config) +$(call allow-override,LD_SO_CONF_PATH,/etc/ld.so.conf.d/) +$(call allow-override,LDCONFIG,ldconfig) + +INSTALL = install +FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ + -fasynchronous-unwind-tables -fstack-clash-protection +WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized + +TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) + +CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) +LDFLAGS := -ggdb +LIBS := $$($(PKG_CONFIG) --libs libtracefs) -lprocps + +SRC := $(wildcard src/*.c) +HDR := $(wildcard src/*.h) +OBJ := $(SRC:.c=.o) +DIRS := src +FILES := Makefile README.txt +CEXT := bz2 +TARBALL := $(NAME)-$(VERSION).tar.$(CEXT) +TAROPTS := -cvjf $(TARBALL) +BINDIR := /usr/bin +DATADIR := /usr/share +DOCDIR := $(DATADIR)/doc +MANDIR := $(DATADIR)/man +LICDIR := $(DATADIR)/licenses +SRCTREE := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)) + +# If running from the tarball, man pages are stored in the Documentation +# dir. If running from the kernel source, man pages are stored in +# Documentation/tools/rtla/. +ifneq ($(wildcard Documentation/.*),) +DOCSRC = Documentation/ +else +DOCSRC = $(SRCTREE)/../../../Documentation/tools/rtla/ +endif + +.PHONY: all +all: rtla + +rtla: $(OBJ) doc + $(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS) + +static: $(OBJ) + $(CC) -o rtla-static $(LDFLAGS) --static $(OBJ) $(LIBS) -lpthread -ldl + +.PHONY: install +install: doc_install + $(INSTALL) -d -m 755 $(DESTDIR)$(BINDIR) + $(INSTALL) rtla -m 755 $(DESTDIR)$(BINDIR) + $(STRIP) $(DESTDIR)$(BINDIR)/rtla + @test ! -f $(DESTDIR)$(BINDIR)/osnoise || rm $(DESTDIR)$(BINDIR)/osnoise + ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/osnoise + @test ! -f $(DESTDIR)$(BINDIR)/timerlat || rm $(DESTDIR)$(BINDIR)/timerlat + ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/timerlat + +.PHONY: clean tarball +clean: doc_clean + @test ! -f rtla || rm rtla + @test ! -f rtla-static || rm rtla-static + @test ! -f src/rtla.o || rm src/rtla.o + @test ! -f $(TARBALL) || rm -f $(TARBALL) + @rm -rf *~ $(OBJ) *.tar.$(CEXT) + +tarball: clean + rm -rf $(NAME)-$(VERSION) && mkdir $(NAME)-$(VERSION) + cp -r $(DIRS) $(FILES) $(NAME)-$(VERSION) + mkdir $(NAME)-$(VERSION)/Documentation/ + cp -rp $(SRCTREE)/../../../Documentation/tools/rtla/* $(NAME)-$(VERSION)/Documentation/ + tar $(TAROPTS) --exclude='*~' $(NAME)-$(VERSION) + rm -rf $(NAME)-$(VERSION) + +.PHONY: doc doc_clean doc_install +doc: + $(MAKE) -C $(DOCSRC) + +doc_clean: + $(MAKE) -C $(DOCSRC) clean + +doc_install: + $(MAKE) -C $(DOCSRC) install diff --git a/tools/tracing/rtla/README.txt b/tools/tracing/rtla/README.txt new file mode 100644 index 000000000000..6c88446f7e74 --- /dev/null +++ b/tools/tracing/rtla/README.txt @@ -0,0 +1,36 @@ +RTLA: Real-Time Linux Analysis tools + +The rtla is a meta-tool that includes a set of commands that +aims to analyze the real-time properties of Linux. But, instead of +testing Linux as a black box, rtla leverages kernel tracing +capabilities to provide precise information about the properties +and root causes of unexpected results. + +Installing RTLA + +RTLA depends on some libraries and tools. More precisely, it depends on the +following libraries: + + - libtracefs + - libtraceevent + - procps + +It also depends on python3-docutils to compile man pages. + +For development, we suggest the following steps for compiling rtla: + + $ git clone git://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git + $ cd libtraceevent/ + $ make + $ sudo make install + $ cd .. + $ git clone git://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git + $ cd libtracefs/ + $ make + $ sudo make install + $ cd .. + $ cd $rtla_src + $ make + $ sudo make install + +For further information, please refer to the rtla man page. diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c new file mode 100644 index 000000000000..7b73d1eccd0e --- /dev/null +++ b/tools/tracing/rtla/src/osnoise.c @@ -0,0 +1,875 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <sys/types.h> +#include <sys/stat.h> +#include <pthread.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> + +#include "osnoise.h" +#include "utils.h" + +/* + * osnoise_get_cpus - return the original "osnoise/cpus" content + * + * It also saves the value to be restored. + */ +char *osnoise_get_cpus(struct osnoise_context *context) +{ + if (context->curr_cpus) + return context->curr_cpus; + + if (context->orig_cpus) + return context->orig_cpus; + + context->orig_cpus = tracefs_instance_file_read(NULL, "osnoise/cpus", NULL); + + /* + * The error value (NULL) is the same for tracefs_instance_file_read() + * and this functions, so: + */ + return context->orig_cpus; +} + +/* + * osnoise_set_cpus - configure osnoise to run on *cpus + * + * "osnoise/cpus" file is used to set the cpus in which osnoise/timerlat + * will run. This function opens this file, saves the current value, + * and set the cpus passed as argument. + */ +int osnoise_set_cpus(struct osnoise_context *context, char *cpus) +{ + char *orig_cpus = osnoise_get_cpus(context); + char buffer[1024]; + int retval; + + if (!orig_cpus) + return -1; + + context->curr_cpus = strdup(cpus); + if (!context->curr_cpus) + return -1; + + snprintf(buffer, 1024, "%s\n", cpus); + + debug_msg("setting cpus to %s from %s", cpus, context->orig_cpus); + + retval = tracefs_instance_file_write(NULL, "osnoise/cpus", buffer); + if (retval < 0) { + free(context->curr_cpus); + context->curr_cpus = NULL; + return -1; + } + + return 0; +} + +/* + * osnoise_restore_cpus - restore the original "osnoise/cpus" + * + * osnoise_set_cpus() saves the original data for the "osnoise/cpus" + * file. This function restore the original config it was previously + * modified. + */ +void osnoise_restore_cpus(struct osnoise_context *context) +{ + int retval; + + if (!context->orig_cpus) + return; + + if (!context->curr_cpus) + return; + + /* nothing to do? */ + if (!strcmp(context->orig_cpus, context->curr_cpus)) + goto out_done; + + debug_msg("restoring cpus to %s", context->orig_cpus); + + retval = tracefs_instance_file_write(NULL, "osnoise/cpus", context->orig_cpus); + if (retval < 0) + err_msg("could not restore original osnoise cpus\n"); + +out_done: + free(context->curr_cpus); + context->curr_cpus = NULL; +} + +/* + * osnoise_put_cpus - restore cpus config and cleanup data + */ +void osnoise_put_cpus(struct osnoise_context *context) +{ + osnoise_restore_cpus(context); + + if (!context->orig_cpus) + return; + + free(context->orig_cpus); + context->orig_cpus = NULL; +} + +/* + * osnoise_read_ll_config - read a long long value from a config + * + * returns -1 on error. + */ +static long long osnoise_read_ll_config(char *rel_path) +{ + long long retval; + char *buffer; + + buffer = tracefs_instance_file_read(NULL, rel_path, NULL); + if (!buffer) + return -1; + + /* get_llong_from_str returns -1 on error */ + retval = get_llong_from_str(buffer); + + debug_msg("reading %s returned %lld\n", rel_path, retval); + + free(buffer); + + return retval; +} + +/* + * osnoise_write_ll_config - write a long long value to a config in rel_path + * + * returns -1 on error. + */ +static long long osnoise_write_ll_config(char *rel_path, long long value) +{ + char buffer[BUFF_U64_STR_SIZE]; + long long retval; + + snprintf(buffer, sizeof(buffer), "%lld\n", value); + + debug_msg("setting %s to %lld\n", rel_path, value); + + retval = tracefs_instance_file_write(NULL, rel_path, buffer); + return retval; +} + +/* + * osnoise_get_runtime - return the original "osnoise/runtime_us" value + * + * It also saves the value to be restored. + */ +unsigned long long osnoise_get_runtime(struct osnoise_context *context) +{ + long long runtime_us; + + if (context->runtime_us != OSNOISE_TIME_INIT_VAL) + return context->runtime_us; + + if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL) + return context->orig_runtime_us; + + runtime_us = osnoise_read_ll_config("osnoise/runtime_us"); + if (runtime_us < 0) + goto out_err; + + context->orig_runtime_us = runtime_us; + return runtime_us; + +out_err: + return OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_get_period - return the original "osnoise/period_us" value + * + * It also saves the value to be restored. + */ +unsigned long long osnoise_get_period(struct osnoise_context *context) +{ + long long period_us; + + if (context->period_us != OSNOISE_TIME_INIT_VAL) + return context->period_us; + + if (context->orig_period_us != OSNOISE_TIME_INIT_VAL) + return context->orig_period_us; + + period_us = osnoise_read_ll_config("osnoise/period_us"); + if (period_us < 0) + goto out_err; + + context->orig_period_us = period_us; + return period_us; + +out_err: + return OSNOISE_TIME_INIT_VAL; +} + +static int __osnoise_write_runtime(struct osnoise_context *context, + unsigned long long runtime) +{ + int retval; + + if (context->orig_runtime_us == OSNOISE_TIME_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/runtime_us", runtime); + if (retval < 0) + return -1; + + context->runtime_us = runtime; + return 0; +} + +static int __osnoise_write_period(struct osnoise_context *context, + unsigned long long period) +{ + int retval; + + if (context->orig_period_us == OSNOISE_TIME_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/period_us", period); + if (retval < 0) + return -1; + + context->period_us = period; + return 0; +} + +/* + * osnoise_set_runtime_period - set osnoise runtime and period + * + * Osnoise's runtime and period are related as runtime <= period. + * Thus, this function saves the original values, and then tries + * to set the runtime and period if they are != 0. + */ +int osnoise_set_runtime_period(struct osnoise_context *context, + unsigned long long runtime, + unsigned long long period) +{ + unsigned long long curr_runtime_us; + unsigned long long curr_period_us; + int retval; + + if (!period && !runtime) + return 0; + + curr_runtime_us = osnoise_get_runtime(context); + curr_period_us = osnoise_get_period(context); + + /* error getting any value? */ + if (curr_period_us == OSNOISE_TIME_INIT_VAL || curr_runtime_us == OSNOISE_TIME_INIT_VAL) + return -1; + + if (!period) { + if (runtime > curr_period_us) + return -1; + return __osnoise_write_runtime(context, runtime); + } else if (!runtime) { + if (period < curr_runtime_us) + return -1; + return __osnoise_write_period(context, period); + } + + if (runtime > curr_period_us) { + retval = __osnoise_write_period(context, period); + if (retval) + return -1; + retval = __osnoise_write_runtime(context, runtime); + if (retval) + return -1; + } else { + retval = __osnoise_write_runtime(context, runtime); + if (retval) + return -1; + retval = __osnoise_write_period(context, period); + if (retval) + return -1; + } + + return 0; +} + +/* + * osnoise_restore_runtime_period - restore the original runtime and period + */ +void osnoise_restore_runtime_period(struct osnoise_context *context) +{ + unsigned long long orig_runtime = context->orig_runtime_us; + unsigned long long orig_period = context->orig_period_us; + unsigned long long curr_runtime = context->runtime_us; + unsigned long long curr_period = context->period_us; + int retval; + + if ((orig_runtime == OSNOISE_TIME_INIT_VAL) && (orig_period == OSNOISE_TIME_INIT_VAL)) + return; + + if ((orig_period == curr_period) && (orig_runtime == curr_runtime)) + goto out_done; + + retval = osnoise_set_runtime_period(context, orig_runtime, orig_period); + if (retval) + err_msg("Could not restore original osnoise runtime/period\n"); + +out_done: + context->runtime_us = OSNOISE_TIME_INIT_VAL; + context->period_us = OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_put_runtime_period - restore original values and cleanup data + */ +void osnoise_put_runtime_period(struct osnoise_context *context) +{ + osnoise_restore_runtime_period(context); + + if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL) + context->orig_runtime_us = OSNOISE_TIME_INIT_VAL; + + if (context->orig_period_us != OSNOISE_TIME_INIT_VAL) + context->orig_period_us = OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_get_timerlat_period_us - read and save the original "timerlat_period_us" + */ +static long long +osnoise_get_timerlat_period_us(struct osnoise_context *context) +{ + long long timerlat_period_us; + + if (context->timerlat_period_us != OSNOISE_TIME_INIT_VAL) + return context->timerlat_period_us; + + if (context->orig_timerlat_period_us != OSNOISE_TIME_INIT_VAL) + return context->orig_timerlat_period_us; + + timerlat_period_us = osnoise_read_ll_config("osnoise/timerlat_period_us"); + if (timerlat_period_us < 0) + goto out_err; + + context->orig_timerlat_period_us = timerlat_period_us; + return timerlat_period_us; + +out_err: + return OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_set_timerlat_period_us - set "timerlat_period_us" + */ +int osnoise_set_timerlat_period_us(struct osnoise_context *context, long long timerlat_period_us) +{ + long long curr_timerlat_period_us = osnoise_get_timerlat_period_us(context); + int retval; + + if (curr_timerlat_period_us == OSNOISE_TIME_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/timerlat_period_us", timerlat_period_us); + if (retval < 0) + return -1; + + context->timerlat_period_us = timerlat_period_us; + + return 0; +} + +/* + * osnoise_restore_timerlat_period_us - restore "timerlat_period_us" + */ +void osnoise_restore_timerlat_period_us(struct osnoise_context *context) +{ + int retval; + + if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL) + return; + + if (context->orig_timerlat_period_us == context->timerlat_period_us) + goto out_done; + + retval = osnoise_write_ll_config("osnoise/timerlat_period_us", context->orig_timerlat_period_us); + if (retval < 0) + err_msg("Could not restore original osnoise timerlat_period_us\n"); + +out_done: + context->timerlat_period_us = OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_put_timerlat_period_us - restore original values and cleanup data + */ +void osnoise_put_timerlat_period_us(struct osnoise_context *context) +{ + osnoise_restore_timerlat_period_us(context); + + if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL) + return; + + context->orig_timerlat_period_us = OSNOISE_TIME_INIT_VAL; +} + +/* + * osnoise_get_stop_us - read and save the original "stop_tracing_us" + */ +static long long +osnoise_get_stop_us(struct osnoise_context *context) +{ + long long stop_us; + + if (context->stop_us != OSNOISE_OPTION_INIT_VAL) + return context->stop_us; + + if (context->orig_stop_us != OSNOISE_OPTION_INIT_VAL) + return context->orig_stop_us; + + stop_us = osnoise_read_ll_config("osnoise/stop_tracing_us"); + if (stop_us < 0) + goto out_err; + + context->orig_stop_us = stop_us; + return stop_us; + +out_err: + return OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_set_stop_us - set "stop_tracing_us" + */ +int osnoise_set_stop_us(struct osnoise_context *context, long long stop_us) +{ + long long curr_stop_us = osnoise_get_stop_us(context); + int retval; + + if (curr_stop_us == OSNOISE_OPTION_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/stop_tracing_us", stop_us); + if (retval < 0) + return -1; + + context->stop_us = stop_us; + + return 0; +} + +/* + * osnoise_restore_stop_us - restore the original "stop_tracing_us" + */ +void osnoise_restore_stop_us(struct osnoise_context *context) +{ + int retval; + + if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL) + return; + + if (context->orig_stop_us == context->stop_us) + goto out_done; + + retval = osnoise_write_ll_config("osnoise/stop_tracing_us", context->orig_stop_us); + if (retval < 0) + err_msg("Could not restore original osnoise stop_us\n"); + +out_done: + context->stop_us = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_put_stop_us - restore original values and cleanup data + */ +void osnoise_put_stop_us(struct osnoise_context *context) +{ + osnoise_restore_stop_us(context); + + if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL) + return; + + context->orig_stop_us = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_get_stop_total_us - read and save the original "stop_tracing_total_us" + */ +static long long +osnoise_get_stop_total_us(struct osnoise_context *context) +{ + long long stop_total_us; + + if (context->stop_total_us != OSNOISE_OPTION_INIT_VAL) + return context->stop_total_us; + + if (context->orig_stop_total_us != OSNOISE_OPTION_INIT_VAL) + return context->orig_stop_total_us; + + stop_total_us = osnoise_read_ll_config("osnoise/stop_tracing_total_us"); + if (stop_total_us < 0) + goto out_err; + + context->orig_stop_total_us = stop_total_us; + return stop_total_us; + +out_err: + return OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_set_stop_total_us - set "stop_tracing_total_us" + */ +int osnoise_set_stop_total_us(struct osnoise_context *context, long long stop_total_us) +{ + long long curr_stop_total_us = osnoise_get_stop_total_us(context); + int retval; + + if (curr_stop_total_us == OSNOISE_OPTION_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us", stop_total_us); + if (retval < 0) + return -1; + + context->stop_total_us = stop_total_us; + + return 0; +} + +/* + * osnoise_restore_stop_total_us - restore the original "stop_tracing_total_us" + */ +void osnoise_restore_stop_total_us(struct osnoise_context *context) +{ + int retval; + + if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL) + return; + + if (context->orig_stop_total_us == context->stop_total_us) + goto out_done; + + retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us", + context->orig_stop_total_us); + if (retval < 0) + err_msg("Could not restore original osnoise stop_total_us\n"); + +out_done: + context->stop_total_us = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_put_stop_total_us - restore original values and cleanup data + */ +void osnoise_put_stop_total_us(struct osnoise_context *context) +{ + osnoise_restore_stop_total_us(context); + + if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL) + return; + + context->orig_stop_total_us = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_get_print_stack - read and save the original "print_stack" + */ +static long long +osnoise_get_print_stack(struct osnoise_context *context) +{ + long long print_stack; + + if (context->print_stack != OSNOISE_OPTION_INIT_VAL) + return context->print_stack; + + if (context->orig_print_stack != OSNOISE_OPTION_INIT_VAL) + return context->orig_print_stack; + + print_stack = osnoise_read_ll_config("osnoise/print_stack"); + if (print_stack < 0) + goto out_err; + + context->orig_print_stack = print_stack; + return print_stack; + +out_err: + return OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_set_print_stack - set "print_stack" + */ +int osnoise_set_print_stack(struct osnoise_context *context, long long print_stack) +{ + long long curr_print_stack = osnoise_get_print_stack(context); + int retval; + + if (curr_print_stack == OSNOISE_OPTION_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("osnoise/print_stack", print_stack); + if (retval < 0) + return -1; + + context->print_stack = print_stack; + + return 0; +} + +/* + * osnoise_restore_print_stack - restore the original "print_stack" + */ +void osnoise_restore_print_stack(struct osnoise_context *context) +{ + int retval; + + if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL) + return; + + if (context->orig_print_stack == context->print_stack) + goto out_done; + + retval = osnoise_write_ll_config("osnoise/print_stack", context->orig_print_stack); + if (retval < 0) + err_msg("Could not restore original osnoise print_stack\n"); + +out_done: + context->print_stack = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_put_print_stack - restore original values and cleanup data + */ +void osnoise_put_print_stack(struct osnoise_context *context) +{ + osnoise_restore_print_stack(context); + + if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL) + return; + + context->orig_print_stack = OSNOISE_OPTION_INIT_VAL; +} + +/* + * enable_osnoise - enable osnoise tracer in the trace_instance + */ +int enable_osnoise(struct trace_instance *trace) +{ + return enable_tracer_by_name(trace->inst, "osnoise"); +} + +/* + * enable_timerlat - enable timerlat tracer in the trace_instance + */ +int enable_timerlat(struct trace_instance *trace) +{ + return enable_tracer_by_name(trace->inst, "timerlat"); +} + +enum { + FLAG_CONTEXT_NEWLY_CREATED = (1 << 0), + FLAG_CONTEXT_DELETED = (1 << 1), +}; + +/* + * osnoise_get_context - increase the usage of a context and return it + */ +int osnoise_get_context(struct osnoise_context *context) +{ + int ret; + + if (context->flags & FLAG_CONTEXT_DELETED) { + ret = -1; + } else { + context->ref++; + ret = 0; + } + + return ret; +} + +/* + * osnoise_context_alloc - alloc an osnoise_context + * + * The osnoise context contains the information of the "osnoise/" configs. + * It is used to set and restore the config. + */ +struct osnoise_context *osnoise_context_alloc(void) +{ + struct osnoise_context *context; + + context = calloc(1, sizeof(*context)); + if (!context) + return NULL; + + context->orig_stop_us = OSNOISE_OPTION_INIT_VAL; + context->stop_us = OSNOISE_OPTION_INIT_VAL; + + context->orig_stop_total_us = OSNOISE_OPTION_INIT_VAL; + context->stop_total_us = OSNOISE_OPTION_INIT_VAL; + + context->orig_print_stack = OSNOISE_OPTION_INIT_VAL; + context->print_stack = OSNOISE_OPTION_INIT_VAL; + + osnoise_get_context(context); + + return context; +} + +/* + * osnoise_put_context - put the osnoise_put_context + * + * If there is no other user for the context, the original data + * is restored. + */ +void osnoise_put_context(struct osnoise_context *context) +{ + if (--context->ref < 1) + context->flags |= FLAG_CONTEXT_DELETED; + + if (!(context->flags & FLAG_CONTEXT_DELETED)) + return; + + osnoise_put_cpus(context); + osnoise_put_runtime_period(context); + osnoise_put_stop_us(context); + osnoise_put_stop_total_us(context); + osnoise_put_timerlat_period_us(context); + osnoise_put_print_stack(context); + + free(context); +} + +/* + * osnoise_destroy_tool - disable trace, restore configs and free data + */ +void osnoise_destroy_tool(struct osnoise_tool *top) +{ + trace_instance_destroy(&top->trace); + + if (top->context) + osnoise_put_context(top->context); + + free(top); +} + +/* + * osnoise_init_tool - init an osnoise tool + * + * It allocs data, create a context to store data and + * creates a new trace instance for the tool. + */ +struct osnoise_tool *osnoise_init_tool(char *tool_name) +{ + struct osnoise_tool *top; + int retval; + + top = calloc(1, sizeof(*top)); + if (!top) + return NULL; + + top->context = osnoise_context_alloc(); + if (!top->context) + goto out_err; + + retval = trace_instance_init(&top->trace, tool_name); + if (retval) + goto out_err; + + return top; +out_err: + osnoise_destroy_tool(top); + return NULL; +} + +/* + * osnoise_init_trace_tool - init a tracer instance to trace osnoise events + */ +struct osnoise_tool *osnoise_init_trace_tool(char *tracer) +{ + struct osnoise_tool *trace; + int retval; + + trace = osnoise_init_tool("osnoise_trace"); + if (!trace) + return NULL; + + retval = tracefs_event_enable(trace->trace.inst, "osnoise", NULL); + if (retval < 0 && !errno) { + err_msg("Could not find osnoise events\n"); + goto out_err; + } + + retval = enable_tracer_by_name(trace->trace.inst, tracer); + if (retval) { + err_msg("Could not enable osnoiser tracer for tracing\n"); + goto out_err; + } + + return trace; +out_err: + osnoise_destroy_tool(trace); + return NULL; +} + +static void osnoise_usage(void) +{ + int i; + + static const char *msg[] = { + "", + "osnoise version " VERSION, + "", + " usage: [rtla] osnoise [MODE] ...", + "", + " modes:", + " top - prints the summary from osnoise tracer", + " hist - prints a histogram of osnoise samples", + "", + "if no MODE is given, the top mode is called, passing the arguments", + NULL, + }; + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +int osnoise_main(int argc, char *argv[]) +{ + if (argc == 0) + goto usage; + + /* + * if osnoise was called without any argument, run the + * default cmdline. + */ + if (argc == 1) { + osnoise_top_main(argc, argv); + exit(0); + } + + if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) { + osnoise_usage(); + exit(0); + } else if (strncmp(argv[1], "-", 1) == 0) { + /* the user skipped the tool, call the default one */ + osnoise_top_main(argc, argv); + exit(0); + } else if (strcmp(argv[1], "top") == 0) { + osnoise_top_main(argc-1, &argv[1]); + exit(0); + } else if (strcmp(argv[1], "hist") == 0) { + osnoise_hist_main(argc-1, &argv[1]); + exit(0); + } + +usage: + osnoise_usage(); + exit(1); +} diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h new file mode 100644 index 000000000000..9e4b2e2a4559 --- /dev/null +++ b/tools/tracing/rtla/src/osnoise.h @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "trace.h" + +/* + * osnoise_context - read, store, write, restore osnoise configs. + */ +struct osnoise_context { + int flags; + int ref; + + char *curr_cpus; + char *orig_cpus; + + /* 0 as init value */ + unsigned long long orig_runtime_us; + unsigned long long runtime_us; + + /* 0 as init value */ + unsigned long long orig_period_us; + unsigned long long period_us; + + /* 0 as init value */ + long long orig_timerlat_period_us; + long long timerlat_period_us; + + /* -1 as init value because 0 is disabled */ + long long orig_stop_us; + long long stop_us; + + /* -1 as init value because 0 is disabled */ + long long orig_stop_total_us; + long long stop_total_us; + + /* -1 as init value because 0 is disabled */ + long long orig_print_stack; + long long print_stack; +}; + +/* + * *_INIT_VALs are also invalid values, they are used to + * communicate errors. + */ +#define OSNOISE_OPTION_INIT_VAL (-1) +#define OSNOISE_TIME_INIT_VAL (0) + +struct osnoise_context *osnoise_context_alloc(void); +int osnoise_get_context(struct osnoise_context *context); +void osnoise_put_context(struct osnoise_context *context); + +int osnoise_set_cpus(struct osnoise_context *context, char *cpus); +void osnoise_restore_cpus(struct osnoise_context *context); + +int osnoise_set_runtime_period(struct osnoise_context *context, + unsigned long long runtime, + unsigned long long period); +void osnoise_restore_runtime_period(struct osnoise_context *context); + +int osnoise_set_stop_us(struct osnoise_context *context, + long long stop_us); +void osnoise_restore_stop_us(struct osnoise_context *context); + +int osnoise_set_stop_total_us(struct osnoise_context *context, + long long stop_total_us); +void osnoise_restore_stop_total_us(struct osnoise_context *context); + +int osnoise_set_timerlat_period_us(struct osnoise_context *context, + long long timerlat_period_us); +void osnoise_restore_timerlat_period_us(struct osnoise_context *context); + +void osnoise_restore_print_stack(struct osnoise_context *context); +int osnoise_set_print_stack(struct osnoise_context *context, + long long print_stack); + +/* + * osnoise_tool - osnoise based tool definition. + */ +struct osnoise_tool { + struct trace_instance trace; + struct osnoise_context *context; + void *data; + void *params; + time_t start_time; +}; + +void osnoise_destroy_tool(struct osnoise_tool *top); +struct osnoise_tool *osnoise_init_tool(char *tool_name); +struct osnoise_tool *osnoise_init_trace_tool(char *tracer); + +int osnoise_hist_main(int argc, char *argv[]); +int osnoise_top_main(int argc, char **argv); +int osnoise_main(int argc, char **argv); diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c new file mode 100644 index 000000000000..180fcbe423cd --- /dev/null +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -0,0 +1,801 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> +#include <time.h> + +#include "utils.h" +#include "osnoise.h" + +struct osnoise_hist_params { + char *cpus; + char *monitored_cpus; + char *trace_output; + unsigned long long runtime; + unsigned long long period; + long long stop_us; + long long stop_total_us; + int sleep_time; + int duration; + int set_sched; + int output_divisor; + struct sched_attr sched_param; + + char no_header; + char no_summary; + char no_index; + char with_zeros; + int bucket_size; + int entries; +}; + +struct osnoise_hist_cpu { + int *samples; + int count; + + unsigned long long min_sample; + unsigned long long sum_sample; + unsigned long long max_sample; + +}; + +struct osnoise_hist_data { + struct tracefs_hist *trace_hist; + struct osnoise_hist_cpu *hist; + int entries; + int bucket_size; + int nr_cpus; +}; + +/* + * osnoise_free_histogram - free runtime data + */ +static void +osnoise_free_histogram(struct osnoise_hist_data *data) +{ + int cpu; + + /* one histogram for IRQ and one for thread, per CPU */ + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (data->hist[cpu].samples) + free(data->hist[cpu].samples); + } + + /* one set of histograms per CPU */ + if (data->hist) + free(data->hist); + + free(data); +} + +/* + * osnoise_alloc_histogram - alloc runtime data + */ +static struct osnoise_hist_data +*osnoise_alloc_histogram(int nr_cpus, int entries, int bucket_size) +{ + struct osnoise_hist_data *data; + int cpu; + + data = calloc(1, sizeof(*data)); + if (!data) + return NULL; + + data->entries = entries; + data->bucket_size = bucket_size; + data->nr_cpus = nr_cpus; + + data->hist = calloc(1, sizeof(*data->hist) * nr_cpus); + if (!data->hist) + goto cleanup; + + for (cpu = 0; cpu < nr_cpus; cpu++) { + data->hist[cpu].samples = calloc(1, sizeof(*data->hist->samples) * (entries + 1)); + if (!data->hist[cpu].samples) + goto cleanup; + } + + /* set the min to max */ + for (cpu = 0; cpu < nr_cpus; cpu++) + data->hist[cpu].min_sample = ~0; + + return data; + +cleanup: + osnoise_free_histogram(data); + return NULL; +} + +static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, + unsigned long long duration, int count) +{ + struct osnoise_hist_params *params = tool->params; + struct osnoise_hist_data *data = tool->data; + int entries = data->entries; + int bucket; + int *hist; + + if (params->output_divisor) + duration = duration / params->output_divisor; + + if (data->bucket_size) + bucket = duration / data->bucket_size; + + hist = data->hist[cpu].samples; + data->hist[cpu].count += count; + update_min(&data->hist[cpu].min_sample, &duration); + update_sum(&data->hist[cpu].sum_sample, &duration); + update_max(&data->hist[cpu].max_sample, &duration); + + if (bucket < entries) + hist[bucket] += count; + else + hist[entries] += count; +} + +/* + * osnoise_destroy_trace_hist - disable events used to collect histogram + */ +static void osnoise_destroy_trace_hist(struct osnoise_tool *tool) +{ + struct osnoise_hist_data *data = tool->data; + + tracefs_hist_pause(tool->trace.inst, data->trace_hist); + tracefs_hist_destroy(tool->trace.inst, data->trace_hist); +} + +/* + * osnoise_init_trace_hist - enable events used to collect histogram + */ +static int osnoise_init_trace_hist(struct osnoise_tool *tool) +{ + struct osnoise_hist_params *params = tool->params; + struct osnoise_hist_data *data = tool->data; + int bucket_size; + char buff[128]; + int retval = 0; + + /* + * Set the size of the bucket. + */ + bucket_size = params->output_divisor * params->bucket_size; + snprintf(buff, sizeof(buff), "duration.buckets=%d", bucket_size); + + data->trace_hist = tracefs_hist_alloc(tool->trace.tep, "osnoise", "sample_threshold", + buff, TRACEFS_HIST_KEY_NORMAL); + if (!data->trace_hist) + return 1; + + retval = tracefs_hist_add_key(data->trace_hist, "cpu", 0); + if (retval) + goto out_err; + + retval = tracefs_hist_start(tool->trace.inst, data->trace_hist); + if (retval) + goto out_err; + + return 0; + +out_err: + osnoise_destroy_trace_hist(tool); + return 1; +} + +/* + * osnoise_read_trace_hist - parse histogram file and file osnoise histogram + */ +static void osnoise_read_trace_hist(struct osnoise_tool *tool) +{ + struct osnoise_hist_data *data = tool->data; + long long cpu, counter, duration; + char *content, *position; + + tracefs_hist_pause(tool->trace.inst, data->trace_hist); + + content = tracefs_event_file_read(tool->trace.inst, "osnoise", + "sample_threshold", + "hist", NULL); + if (!content) + return; + + position = content; + while (true) { + position = strstr(position, "duration: ~"); + if (!position) + break; + position += strlen("duration: ~"); + duration = get_llong_from_str(position); + if (duration == -1) + err_msg("error reading duration from histogram\n"); + + position = strstr(position, "cpu:"); + if (!position) + break; + position += strlen("cpu: "); + cpu = get_llong_from_str(position); + if (cpu == -1) + err_msg("error reading cpu from histogram\n"); + + position = strstr(position, "hitcount:"); + if (!position) + break; + position += strlen("hitcount: "); + counter = get_llong_from_str(position); + if (counter == -1) + err_msg("error reading counter from histogram\n"); + + osnoise_hist_update_multiple(tool, cpu, duration, counter); + } + free(content); +} + +/* + * osnoise_hist_header - print the header of the tracer to the output + */ +static void osnoise_hist_header(struct osnoise_tool *tool) +{ + struct osnoise_hist_params *params = tool->params; + struct osnoise_hist_data *data = tool->data; + struct trace_seq *s = tool->trace.seq; + char duration[26]; + int cpu; + + if (params->no_header) + return; + + get_duration(tool->start_time, duration, sizeof(duration)); + trace_seq_printf(s, "# RTLA osnoise histogram\n"); + trace_seq_printf(s, "# Time unit is %s (%s)\n", + params->output_divisor == 1 ? "nanoseconds" : "microseconds", + params->output_divisor == 1 ? "ns" : "us"); + + trace_seq_printf(s, "# Duration: %s\n", duration); + + if (!params->no_index) + trace_seq_printf(s, "Index"); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + trace_seq_printf(s, " CPU-%03d", cpu); + } + trace_seq_printf(s, "\n"); + + trace_seq_do_printf(s); + trace_seq_reset(s); +} + +/* + * osnoise_print_summary - print the summary of the hist data to the output + */ +static void +osnoise_print_summary(struct osnoise_hist_params *params, + struct trace_instance *trace, + struct osnoise_hist_data *data) +{ + int cpu; + + if (params->no_summary) + return; + + if (!params->no_index) + trace_seq_printf(trace->seq, "count:"); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].count); + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "min: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + trace_seq_printf(trace->seq, "%9llu ", data->hist[cpu].min_sample); + + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "avg: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + if (data->hist[cpu].count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].sum_sample / data->hist[cpu].count); + else + trace_seq_printf(trace->seq, " - "); + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "max: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + trace_seq_printf(trace->seq, "%9llu ", data->hist[cpu].max_sample); + + } + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); +} + +/* + * osnoise_print_stats - print data for all CPUs + */ +static void +osnoise_print_stats(struct osnoise_hist_params *params, struct osnoise_tool *tool) +{ + struct osnoise_hist_data *data = tool->data; + struct trace_instance *trace = &tool->trace; + int bucket, cpu; + int total; + + osnoise_hist_header(tool); + + for (bucket = 0; bucket < data->entries; bucket++) { + total = 0; + + if (!params->no_index) + trace_seq_printf(trace->seq, "%-6d", + bucket * data->bucket_size); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + total += data->hist[cpu].samples[bucket]; + trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].samples[bucket]); + } + + if (total == 0 && !params->with_zeros) { + trace_seq_reset(trace->seq); + continue; + } + + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); + } + + if (!params->no_index) + trace_seq_printf(trace->seq, "over: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].count) + continue; + + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].samples[data->entries]); + } + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); + + osnoise_print_summary(params, trace, data); +} + +/* + * osnoise_hist_usage - prints osnoise hist usage message + */ +static void osnoise_hist_usage(char *usage) +{ + int i; + + static const char * const msg[] = { + "", + " usage: rtla osnoise hist [-h] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\", + " [-c cpu-list] [-P priority] [-b N] [-e N] [--no-header] [--no-summary] \\", + " [--no-index] [--with-zeros]", + "", + " -h/--help: print this menu", + " -p/--period us: osnoise period in us", + " -r/--runtime us: osnoise runtime in us", + " -s/--stop us: stop trace if a single sample is higher than the argument in us", + " -S/--stop-total us: stop trace if the total sample is higher than the argument in us", + " -c/--cpus cpu-list: list of cpus to run osnoise threads", + " -d/--duration time[s|m|h|d]: duration of the session", + " -D/--debug: print debug info", + " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]", + " -b/--bucket-size N: set the histogram bucket size (default 1)", + " -e/--entries N: set the number of entries of the histogram (default 256)", + " --no-header: do not print header", + " --no-summary: do not print summary", + " --no-index: do not print index", + " --with-zeros: print zero only entries", + " -P/--priority o:prio|r:prio|f:prio|d:runtime:period: set scheduling parameters", + " o:prio - use SCHED_OTHER with prio", + " r:prio - use SCHED_RR with prio", + " f:prio - use SCHED_FIFO with prio", + " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period", + " in nanoseconds", + NULL, + }; + + if (usage) + fprintf(stderr, "%s\n", usage); + + fprintf(stderr, "rtla osnoise hist: a per-cpu histogram of the OS noise (version %s)\n", + VERSION); + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +/* + * osnoise_hist_parse_args - allocs, parse and fill the cmd line parameters + */ +static struct osnoise_hist_params +*osnoise_hist_parse_args(int argc, char *argv[]) +{ + struct osnoise_hist_params *params; + int retval; + int c; + + params = calloc(1, sizeof(*params)); + if (!params) + exit(1); + + /* display data in microseconds */ + params->output_divisor = 1000; + params->bucket_size = 1; + params->entries = 256; + + while (1) { + static struct option long_options[] = { + {"bucket-size", required_argument, 0, 'b'}, + {"entries", required_argument, 0, 'e'}, + {"cpus", required_argument, 0, 'c'}, + {"debug", no_argument, 0, 'D'}, + {"duration", required_argument, 0, 'd'}, + {"help", no_argument, 0, 'h'}, + {"period", required_argument, 0, 'p'}, + {"priority", required_argument, 0, 'P'}, + {"runtime", required_argument, 0, 'r'}, + {"stop", required_argument, 0, 's'}, + {"stop-total", required_argument, 0, 'S'}, + {"trace", optional_argument, 0, 't'}, + {"no-header", no_argument, 0, '0'}, + {"no-summary", no_argument, 0, '1'}, + {"no-index", no_argument, 0, '2'}, + {"with-zeros", no_argument, 0, '3'}, + {0, 0, 0, 0} + }; + + /* getopt_long stores the option index here. */ + int option_index = 0; + + c = getopt_long(argc, argv, "c:b:d:e:Dhp:P:r:s:S:t::0123", + long_options, &option_index); + + /* detect the end of the options. */ + if (c == -1) + break; + + switch (c) { + case 'b': + params->bucket_size = get_llong_from_str(optarg); + if ((params->bucket_size == 0) || (params->bucket_size >= 1000000)) + osnoise_hist_usage("Bucket size needs to be > 0 and <= 1000000\n"); + break; + case 'c': + retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); + if (retval) + osnoise_hist_usage("\nInvalid -c cpu list\n"); + params->cpus = optarg; + break; + case 'D': + config_debug = 1; + break; + case 'd': + params->duration = parse_seconds_duration(optarg); + if (!params->duration) + osnoise_hist_usage("Invalid -D duration\n"); + break; + case 'e': + params->entries = get_llong_from_str(optarg); + if ((params->entries < 10) || (params->entries > 9999999)) + osnoise_hist_usage("Entries must be > 10 and < 9999999\n"); + break; + case 'h': + case '?': + osnoise_hist_usage(NULL); + break; + case 'p': + params->period = get_llong_from_str(optarg); + if (params->period > 10000000) + osnoise_hist_usage("Period longer than 10 s\n"); + break; + case 'P': + retval = parse_prio(optarg, ¶ms->sched_param); + if (retval == -1) + osnoise_hist_usage("Invalid -P priority"); + params->set_sched = 1; + break; + case 'r': + params->runtime = get_llong_from_str(optarg); + if (params->runtime < 100) + osnoise_hist_usage("Runtime shorter than 100 us\n"); + break; + case 's': + params->stop_us = get_llong_from_str(optarg); + break; + case 'S': + params->stop_total_us = get_llong_from_str(optarg); + break; + case 't': + if (optarg) + /* skip = */ + params->trace_output = &optarg[1]; + else + params->trace_output = "osnoise_trace.txt"; + break; + case '0': /* no header */ + params->no_header = 1; + break; + case '1': /* no summary */ + params->no_summary = 1; + break; + case '2': /* no index */ + params->no_index = 1; + break; + case '3': /* with zeros */ + params->with_zeros = 1; + break; + default: + osnoise_hist_usage("Invalid option"); + } + } + + if (geteuid()) { + err_msg("rtla needs root permission\n"); + exit(EXIT_FAILURE); + } + + if (params->no_index && !params->with_zeros) + osnoise_hist_usage("no-index set and with-zeros not set - it does not make sense"); + + return params; +} + +/* + * osnoise_hist_apply_config - apply the hist configs to the initialized tool + */ +static int +osnoise_hist_apply_config(struct osnoise_tool *tool, struct osnoise_hist_params *params) +{ + int retval; + + if (!params->sleep_time) + params->sleep_time = 1; + + if (params->cpus) { + retval = osnoise_set_cpus(tool->context, params->cpus); + if (retval) { + err_msg("Failed to apply CPUs config\n"); + goto out_err; + } + } + + if (params->runtime || params->period) { + retval = osnoise_set_runtime_period(tool->context, + params->runtime, + params->period); + if (retval) { + err_msg("Failed to set runtime and/or period\n"); + goto out_err; + } + } + + if (params->stop_us) { + retval = osnoise_set_stop_us(tool->context, params->stop_us); + if (retval) { + err_msg("Failed to set stop us\n"); + goto out_err; + } + } + + if (params->stop_total_us) { + retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us); + if (retval) { + err_msg("Failed to set stop total us\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -1; +} + +/* + * osnoise_init_hist - initialize a osnoise hist tool with parameters + */ +static struct osnoise_tool +*osnoise_init_hist(struct osnoise_hist_params *params) +{ + struct osnoise_tool *tool; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + tool = osnoise_init_tool("osnoise_hist"); + if (!tool) + return NULL; + + tool->data = osnoise_alloc_histogram(nr_cpus, params->entries, params->bucket_size); + if (!tool->data) + goto out_err; + + tool->params = params; + + return tool; + +out_err: + osnoise_destroy_tool(tool); + return NULL; +} + +static int stop_tracing; +static void stop_hist(int sig) +{ + stop_tracing = 1; +} + +/* + * osnoise_hist_set_signals - handles the signal to stop the tool + */ +static void +osnoise_hist_set_signals(struct osnoise_hist_params *params) +{ + signal(SIGINT, stop_hist); + if (params->duration) { + signal(SIGALRM, stop_hist); + alarm(params->duration); + } +} + +int osnoise_hist_main(int argc, char *argv[]) +{ + struct osnoise_hist_params *params; + struct trace_instance *trace; + struct osnoise_tool *record; + struct osnoise_tool *tool; + int return_value = 1; + int retval; + + params = osnoise_hist_parse_args(argc, argv); + if (!params) + exit(1); + + tool = osnoise_init_hist(params); + if (!tool) { + err_msg("Could not init osnoise hist\n"); + goto out_exit; + } + + retval = osnoise_hist_apply_config(tool, params); + if (retval) { + err_msg("Could not apply config\n"); + goto out_destroy; + } + + trace = &tool->trace; + + retval = enable_osnoise(trace); + if (retval) { + err_msg("Failed to enable osnoise tracer\n"); + goto out_destroy; + } + + retval = osnoise_init_trace_hist(tool); + if (retval) + goto out_destroy; + + if (params->set_sched) { + retval = set_comm_sched_attr("osnoise/", ¶ms->sched_param); + if (retval) { + err_msg("Failed to set sched parameters\n"); + goto out_hist; + } + } + + trace_instance_start(trace); + + if (params->trace_output) { + record = osnoise_init_trace_tool("osnoise"); + if (!record) { + err_msg("Failed to enable the trace instance\n"); + goto out_hist; + } + trace_instance_start(&record->trace); + } + + tool->start_time = time(NULL); + osnoise_hist_set_signals(params); + + while (!stop_tracing) { + sleep(params->sleep_time); + + retval = tracefs_iterate_raw_events(trace->tep, + trace->inst, + NULL, + 0, + collect_registered_events, + trace); + if (retval < 0) { + err_msg("Error iterating on events\n"); + goto out_hist; + } + + if (!tracefs_trace_is_on(trace->inst)) + break; + }; + + osnoise_read_trace_hist(tool); + + osnoise_print_stats(params, tool); + + return_value = 0; + + if (!tracefs_trace_is_on(trace->inst)) { + printf("rtla timelat hit stop tracing\n"); + if (params->trace_output) { + printf(" Saving trace to %s\n", params->trace_output); + save_trace_to_file(record->trace.inst, params->trace_output); + } + } + +out_hist: + osnoise_free_histogram(tool->data); +out_destroy: + osnoise_destroy_tool(tool); + if (params->trace_output) + osnoise_destroy_tool(record); + free(params); +out_exit: + exit(return_value); +} diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c new file mode 100644 index 000000000000..332b2ac205fc --- /dev/null +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -0,0 +1,579 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#include <stdio.h> +#include <time.h> + +#include "osnoise.h" +#include "utils.h" + +/* + * osnoise top parameters + */ +struct osnoise_top_params { + char *cpus; + char *monitored_cpus; + char *trace_output; + unsigned long long runtime; + unsigned long long period; + long long stop_us; + long long stop_total_us; + int sleep_time; + int duration; + int quiet; + int set_sched; + struct sched_attr sched_param; +}; + +struct osnoise_top_cpu { + unsigned long long sum_runtime; + unsigned long long sum_noise; + unsigned long long max_noise; + unsigned long long max_sample; + + unsigned long long hw_count; + unsigned long long nmi_count; + unsigned long long irq_count; + unsigned long long softirq_count; + unsigned long long thread_count; + + int sum_cycles; +}; + +struct osnoise_top_data { + struct osnoise_top_cpu *cpu_data; + int nr_cpus; +}; + +/* + * osnoise_free_top - free runtime data + */ +static void +osnoise_free_top(struct osnoise_top_data *data) +{ + free(data->cpu_data); + free(data); +} + +/* + * osnoise_alloc_histogram - alloc runtime data + */ +static struct osnoise_top_data *osnoise_alloc_top(int nr_cpus) +{ + struct osnoise_top_data *data; + + data = calloc(1, sizeof(*data)); + if (!data) + return NULL; + + data->nr_cpus = nr_cpus; + + /* one set of histograms per CPU */ + data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus); + if (!data->cpu_data) + goto cleanup; + + return data; + +cleanup: + osnoise_free_top(data); + return NULL; +} + +/* + * osnoise_top_handler - this is the handler for osnoise tracer events + */ +static int +osnoise_top_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct trace_instance *trace = context; + struct osnoise_tool *tool; + unsigned long long val; + struct osnoise_top_cpu *cpu_data; + struct osnoise_top_data *data; + int cpu = record->cpu; + + tool = container_of(trace, struct osnoise_tool, trace); + + data = tool->data; + cpu_data = &data->cpu_data[cpu]; + + cpu_data->sum_cycles++; + + tep_get_field_val(s, event, "runtime", record, &val, 1); + update_sum(&cpu_data->sum_runtime, &val); + + tep_get_field_val(s, event, "noise", record, &val, 1); + update_max(&cpu_data->max_noise, &val); + update_sum(&cpu_data->sum_noise, &val); + + tep_get_field_val(s, event, "max_sample", record, &val, 1); + update_max(&cpu_data->max_sample, &val); + + tep_get_field_val(s, event, "hw_count", record, &val, 1); + update_sum(&cpu_data->hw_count, &val); + + tep_get_field_val(s, event, "nmi_count", record, &val, 1); + update_sum(&cpu_data->nmi_count, &val); + + tep_get_field_val(s, event, "irq_count", record, &val, 1); + update_sum(&cpu_data->irq_count, &val); + + tep_get_field_val(s, event, "softirq_count", record, &val, 1); + update_sum(&cpu_data->softirq_count, &val); + + tep_get_field_val(s, event, "thread_count", record, &val, 1); + update_sum(&cpu_data->thread_count, &val); + + return 0; +} + +/* + * osnoise_top_header - print the header of the tool output + */ +static void osnoise_top_header(struct osnoise_tool *top) +{ + struct trace_seq *s = top->trace.seq; + char duration[26]; + + get_duration(top->start_time, duration, sizeof(duration)); + + trace_seq_printf(s, "\033[2;37;40m"); + trace_seq_printf(s, " Operating System Noise"); + trace_seq_printf(s, " "); + trace_seq_printf(s, " "); + trace_seq_printf(s, "\033[0;0;0m"); + trace_seq_printf(s, "\n"); + + trace_seq_printf(s, "duration: %9s | time is in us\n", duration); + + trace_seq_printf(s, "\033[2;30;47m"); + trace_seq_printf(s, "CPU Period Runtime "); + trace_seq_printf(s, " Noise "); + trace_seq_printf(s, " %% CPU Aval "); + trace_seq_printf(s, " Max Noise Max Single "); + trace_seq_printf(s, " HW NMI IRQ Softirq Thread"); + trace_seq_printf(s, "\033[0;0;0m"); + trace_seq_printf(s, "\n"); +} + +/* + * clear_terminal - clears the output terminal + */ +static void clear_terminal(struct trace_seq *seq) +{ + if (!config_debug) + trace_seq_printf(seq, "\033c"); +} + +/* + * osnoise_top_print - prints the output of a given CPU + */ +static void osnoise_top_print(struct osnoise_tool *tool, int cpu) +{ + struct trace_seq *s = tool->trace.seq; + struct osnoise_top_cpu *cpu_data; + struct osnoise_top_data *data; + int percentage; + int decimal; + + data = tool->data; + cpu_data = &data->cpu_data[cpu]; + + if (!cpu_data->sum_runtime) + return; + + percentage = ((cpu_data->sum_runtime - cpu_data->sum_noise) * 10000000) + / cpu_data->sum_runtime; + decimal = percentage % 100000; + percentage = percentage / 100000; + + trace_seq_printf(s, "%3d #%-6d %12llu ", cpu, cpu_data->sum_cycles, cpu_data->sum_runtime); + trace_seq_printf(s, "%12llu ", cpu_data->sum_noise); + trace_seq_printf(s, " %3d.%05d", percentage, decimal); + trace_seq_printf(s, "%12llu %12llu", cpu_data->max_noise, cpu_data->max_sample); + + trace_seq_printf(s, "%12llu ", cpu_data->hw_count); + trace_seq_printf(s, "%12llu ", cpu_data->nmi_count); + trace_seq_printf(s, "%12llu ", cpu_data->irq_count); + trace_seq_printf(s, "%12llu ", cpu_data->softirq_count); + trace_seq_printf(s, "%12llu\n", cpu_data->thread_count); +} + +/* + * osnoise_print_stats - print data for all cpus + */ +static void +osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top) +{ + struct trace_instance *trace = &top->trace; + static int nr_cpus = -1; + int i; + + if (nr_cpus == -1) + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + if (!params->quiet) + clear_terminal(trace->seq); + + osnoise_top_header(top); + + for (i = 0; i < nr_cpus; i++) { + if (params->cpus && !params->monitored_cpus[i]) + continue; + osnoise_top_print(top, i); + } + + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); +} + +/* + * osnoise_top_usage - prints osnoise top usage message + */ +void osnoise_top_usage(char *usage) +{ + int i; + + static const char * const msg[] = { + " usage: rtla osnoise [top] [-h] [-q] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\", + " [-c cpu-list] [-P priority]", + "", + " -h/--help: print this menu", + " -p/--period us: osnoise period in us", + " -r/--runtime us: osnoise runtime in us", + " -s/--stop us: stop trace if a single sample is higher than the argument in us", + " -S/--stop-total us: stop trace if the total sample is higher than the argument in us", + " -c/--cpus cpu-list: list of cpus to run osnoise threads", + " -d/--duration time[s|m|h|d]: duration of the session", + " -D/--debug: print debug info", + " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]", + " -q/--quiet print only a summary at the end", + " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", + " o:prio - use SCHED_OTHER with prio", + " r:prio - use SCHED_RR with prio", + " f:prio - use SCHED_FIFO with prio", + " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period", + " in nanoseconds", + NULL, + }; + + if (usage) + fprintf(stderr, "%s\n", usage); + + fprintf(stderr, "rtla osnoise top: a per-cpu summary of the OS noise (version %s)\n", + VERSION); + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +/* + * osnoise_top_parse_args - allocs, parse and fill the cmd line parameters + */ +struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) +{ + struct osnoise_top_params *params; + int retval; + int c; + + params = calloc(1, sizeof(*params)); + if (!params) + exit(1); + + while (1) { + static struct option long_options[] = { + {"cpus", required_argument, 0, 'c'}, + {"debug", no_argument, 0, 'D'}, + {"duration", required_argument, 0, 'd'}, + {"help", no_argument, 0, 'h'}, + {"period", required_argument, 0, 'p'}, + {"priority", required_argument, 0, 'P'}, + {"quiet", no_argument, 0, 'q'}, + {"runtime", required_argument, 0, 'r'}, + {"stop", required_argument, 0, 's'}, + {"stop-total", required_argument, 0, 'S'}, + {"trace", optional_argument, 0, 't'}, + {0, 0, 0, 0} + }; + + /* getopt_long stores the option index here. */ + int option_index = 0; + + c = getopt_long(argc, argv, "c:d:Dhp:P:qr:s:S:t::", + long_options, &option_index); + + /* Detect the end of the options. */ + if (c == -1) + break; + + switch (c) { + case 'c': + retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); + if (retval) + osnoise_top_usage("\nInvalid -c cpu list\n"); + params->cpus = optarg; + break; + case 'D': + config_debug = 1; + break; + case 'd': + params->duration = parse_seconds_duration(optarg); + if (!params->duration) + osnoise_top_usage("Invalid -D duration\n"); + break; + case 'h': + case '?': + osnoise_top_usage(NULL); + break; + case 'p': + params->period = get_llong_from_str(optarg); + if (params->period > 10000000) + osnoise_top_usage("Period longer than 10 s\n"); + break; + case 'P': + retval = parse_prio(optarg, ¶ms->sched_param); + if (retval == -1) + osnoise_top_usage("Invalid -P priority"); + params->set_sched = 1; + break; + case 'q': + params->quiet = 1; + break; + case 'r': + params->runtime = get_llong_from_str(optarg); + if (params->runtime < 100) + osnoise_top_usage("Runtime shorter than 100 us\n"); + break; + case 's': + params->stop_us = get_llong_from_str(optarg); + break; + case 'S': + params->stop_total_us = get_llong_from_str(optarg); + break; + case 't': + if (optarg) + /* skip = */ + params->trace_output = &optarg[1]; + else + params->trace_output = "osnoise_trace.txt"; + break; + default: + osnoise_top_usage("Invalid option"); + } + } + + if (geteuid()) { + err_msg("osnoise needs root permission\n"); + exit(EXIT_FAILURE); + } + + return params; +} + +/* + * osnoise_top_apply_config - apply the top configs to the initialized tool + */ +static int +osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_top_params *params) +{ + int retval; + + if (!params->sleep_time) + params->sleep_time = 1; + + if (params->cpus) { + retval = osnoise_set_cpus(tool->context, params->cpus); + if (retval) { + err_msg("Failed to apply CPUs config\n"); + goto out_err; + } + } + + if (params->runtime || params->period) { + retval = osnoise_set_runtime_period(tool->context, + params->runtime, + params->period); + if (retval) { + err_msg("Failed to set runtime and/or period\n"); + goto out_err; + } + } + + if (params->stop_us) { + retval = osnoise_set_stop_us(tool->context, params->stop_us); + if (retval) { + err_msg("Failed to set stop us\n"); + goto out_err; + } + } + + if (params->stop_total_us) { + retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us); + if (retval) { + err_msg("Failed to set stop total us\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -1; +} + +/* + * osnoise_init_top - initialize a osnoise top tool with parameters + */ +struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) +{ + struct osnoise_tool *tool; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + tool = osnoise_init_tool("osnoise_top"); + if (!tool) + return NULL; + + tool->data = osnoise_alloc_top(nr_cpus); + if (!tool->data) + goto out_err; + + tool->params = params; + + tep_register_event_handler(tool->trace.tep, -1, "ftrace", "osnoise", + osnoise_top_handler, NULL); + + return tool; + +out_err: + osnoise_free_top(tool->data); + osnoise_destroy_tool(tool); + return NULL; +} + +static int stop_tracing; +static void stop_top(int sig) +{ + stop_tracing = 1; +} + +/* + * osnoise_top_set_signals - handles the signal to stop the tool + */ +static void osnoise_top_set_signals(struct osnoise_top_params *params) +{ + signal(SIGINT, stop_top); + if (params->duration) { + signal(SIGALRM, stop_top); + alarm(params->duration); + } +} + +int osnoise_top_main(int argc, char **argv) +{ + struct osnoise_top_params *params; + struct trace_instance *trace; + struct osnoise_tool *record; + struct osnoise_tool *tool; + int return_value = 1; + int retval; + + params = osnoise_top_parse_args(argc, argv); + if (!params) + exit(1); + + tool = osnoise_init_top(params); + if (!tool) { + err_msg("Could not init osnoise top\n"); + goto out_exit; + } + + retval = osnoise_top_apply_config(tool, params); + if (retval) { + err_msg("Could not apply config\n"); + goto out_top; + } + + trace = &tool->trace; + + retval = enable_osnoise(trace); + if (retval) { + err_msg("Failed to enable osnoise tracer\n"); + goto out_top; + } + + if (params->set_sched) { + retval = set_comm_sched_attr("osnoise/", ¶ms->sched_param); + if (retval) { + err_msg("Failed to set sched parameters\n"); + goto out_top; + } + } + + trace_instance_start(trace); + + if (params->trace_output) { + record = osnoise_init_trace_tool("osnoise"); + if (!record) { + err_msg("Failed to enable the trace instance\n"); + goto out_top; + } + trace_instance_start(&record->trace); + } + + tool->start_time = time(NULL); + osnoise_top_set_signals(params); + + do { + sleep(params->sleep_time); + + retval = tracefs_iterate_raw_events(trace->tep, + trace->inst, + NULL, + 0, + collect_registered_events, + trace); + if (retval < 0) { + err_msg("Error iterating on events\n"); + goto out_top; + } + + if (!params->quiet) + osnoise_print_stats(params, tool); + + if (!tracefs_trace_is_on(trace->inst)) + break; + + } while (!stop_tracing); + + osnoise_print_stats(params, tool); + + return_value = 0; + + if (!tracefs_trace_is_on(trace->inst)) { + printf("osnoise hit stop tracing\n"); + if (params->trace_output) { + printf(" Saving trace to %s\n", params->trace_output); + save_trace_to_file(record->trace.inst, params->trace_output); + } + } + +out_top: + osnoise_free_top(tool->data); + osnoise_destroy_tool(tool); + if (params->trace_output) + osnoise_destroy_tool(record); +out_exit: + exit(return_value); +} diff --git a/tools/tracing/rtla/src/rtla.c b/tools/tracing/rtla/src/rtla.c new file mode 100644 index 000000000000..09bd21b8af81 --- /dev/null +++ b/tools/tracing/rtla/src/rtla.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> + +#include "osnoise.h" +#include "timerlat.h" + +/* + * rtla_usage - print rtla usage + */ +static void rtla_usage(void) +{ + int i; + + static const char *msg[] = { + "", + "rtla version " VERSION, + "", + " usage: rtla COMMAND ...", + "", + " commands:", + " osnoise - gives information about the operating system noise (osnoise)", + " timerlat - measures the timer irq and thread latency", + "", + NULL, + }; + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +/* + * run_command - try to run a rtla tool command + * + * It returns 0 if it fails. The tool's main will generally not + * return as they should call exit(). + */ +int run_command(int argc, char **argv, int start_position) +{ + if (strcmp(argv[start_position], "osnoise") == 0) { + osnoise_main(argc-start_position, &argv[start_position]); + goto ran; + } else if (strcmp(argv[start_position], "timerlat") == 0) { + timerlat_main(argc-start_position, &argv[start_position]); + goto ran; + } + + return 0; +ran: + return 1; +} + +int main(int argc, char *argv[]) +{ + int retval; + + /* is it an alias? */ + retval = run_command(argc, argv, 0); + if (retval) + exit(0); + + if (argc < 2) + goto usage; + + if (strcmp(argv[1], "-h") == 0) { + rtla_usage(); + exit(0); + } else if (strcmp(argv[1], "--help") == 0) { + rtla_usage(); + exit(0); + } + + retval = run_command(argc, argv, 1); + if (retval) + exit(0); + +usage: + rtla_usage(); + exit(1); +} diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c new file mode 100644 index 000000000000..97abbf494fee --- /dev/null +++ b/tools/tracing/rtla/src/timerlat.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ +#include <sys/types.h> +#include <sys/stat.h> +#include <pthread.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> + +#include "timerlat.h" + +static void timerlat_usage(void) +{ + int i; + + static const char * const msg[] = { + "", + "timerlat version " VERSION, + "", + " usage: [rtla] timerlat [MODE] ...", + "", + " modes:", + " top - prints the summary from timerlat tracer", + " hist - prints a histogram of timer latencies", + "", + "if no MODE is given, the top mode is called, passing the arguments", + NULL, + }; + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +int timerlat_main(int argc, char *argv[]) +{ + if (argc == 0) + goto usage; + + /* + * if timerlat was called without any argument, run the + * default cmdline. + */ + if (argc == 1) { + timerlat_top_main(argc, argv); + exit(0); + } + + if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) { + timerlat_usage(); + exit(0); + } else if (strncmp(argv[1], "-", 1) == 0) { + /* the user skipped the tool, call the default one */ + timerlat_top_main(argc, argv); + exit(0); + } else if (strcmp(argv[1], "top") == 0) { + timerlat_top_main(argc-1, &argv[1]); + exit(0); + } else if (strcmp(argv[1], "hist") == 0) { + timerlat_hist_main(argc-1, &argv[1]); + exit(0); + } + +usage: + timerlat_usage(); + exit(1); +} diff --git a/tools/tracing/rtla/src/timerlat.h b/tools/tracing/rtla/src/timerlat.h new file mode 100644 index 000000000000..88561bfd14f3 --- /dev/null +++ b/tools/tracing/rtla/src/timerlat.h @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +int timerlat_hist_main(int argc, char *argv[]); +int timerlat_top_main(int argc, char *argv[]); +int timerlat_main(int argc, char *argv[]); diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c new file mode 100644 index 000000000000..235f9620ef3d --- /dev/null +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -0,0 +1,822 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#include <stdio.h> +#include <time.h> + +#include "utils.h" +#include "osnoise.h" +#include "timerlat.h" + +struct timerlat_hist_params { + char *cpus; + char *monitored_cpus; + char *trace_output; + unsigned long long runtime; + long long stop_us; + long long stop_total_us; + long long timerlat_period_us; + long long print_stack; + int sleep_time; + int output_divisor; + int duration; + int set_sched; + struct sched_attr sched_param; + + char no_irq; + char no_thread; + char no_header; + char no_summary; + char no_index; + char with_zeros; + int bucket_size; + int entries; +}; + +struct timerlat_hist_cpu { + int *irq; + int *thread; + + int irq_count; + int thread_count; + + unsigned long long min_irq; + unsigned long long sum_irq; + unsigned long long max_irq; + + unsigned long long min_thread; + unsigned long long sum_thread; + unsigned long long max_thread; +}; + +struct timerlat_hist_data { + struct timerlat_hist_cpu *hist; + int entries; + int bucket_size; + int nr_cpus; +}; + +/* + * timerlat_free_histogram - free runtime data + */ +static void +timerlat_free_histogram(struct timerlat_hist_data *data) +{ + int cpu; + + /* one histogram for IRQ and one for thread, per CPU */ + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (data->hist[cpu].irq) + free(data->hist[cpu].irq); + + if (data->hist[cpu].thread) + free(data->hist[cpu].thread); + } + + /* one set of histograms per CPU */ + if (data->hist) + free(data->hist); + + free(data); +} + +/* + * timerlat_alloc_histogram - alloc runtime data + */ +static struct timerlat_hist_data +*timerlat_alloc_histogram(int nr_cpus, int entries, int bucket_size) +{ + struct timerlat_hist_data *data; + int cpu; + + data = calloc(1, sizeof(*data)); + if (!data) + return NULL; + + data->entries = entries; + data->bucket_size = bucket_size; + data->nr_cpus = nr_cpus; + + /* one set of histograms per CPU */ + data->hist = calloc(1, sizeof(*data->hist) * nr_cpus); + if (!data->hist) + goto cleanup; + + /* one histogram for IRQ and one for thread, per cpu */ + for (cpu = 0; cpu < nr_cpus; cpu++) { + data->hist[cpu].irq = calloc(1, sizeof(*data->hist->irq) * (entries + 1)); + if (!data->hist[cpu].irq) + goto cleanup; + data->hist[cpu].thread = calloc(1, sizeof(*data->hist->thread) * (entries + 1)); + if (!data->hist[cpu].thread) + goto cleanup; + } + + /* set the min to max */ + for (cpu = 0; cpu < nr_cpus; cpu++) { + data->hist[cpu].min_irq = ~0; + data->hist[cpu].min_thread = ~0; + } + + return data; + +cleanup: + timerlat_free_histogram(data); + return NULL; +} + +/* + * timerlat_hist_update - record a new timerlat occurent on cpu, updating data + */ +static void +timerlat_hist_update(struct osnoise_tool *tool, int cpu, + unsigned long long thread, + unsigned long long latency) +{ + struct timerlat_hist_params *params = tool->params; + struct timerlat_hist_data *data = tool->data; + int entries = data->entries; + int bucket; + int *hist; + + if (params->output_divisor) + latency = latency / params->output_divisor; + + if (data->bucket_size) + bucket = latency / data->bucket_size; + + if (!thread) { + hist = data->hist[cpu].irq; + data->hist[cpu].irq_count++; + update_min(&data->hist[cpu].min_irq, &latency); + update_sum(&data->hist[cpu].sum_irq, &latency); + update_max(&data->hist[cpu].max_irq, &latency); + } else { + hist = data->hist[cpu].thread; + data->hist[cpu].thread_count++; + update_min(&data->hist[cpu].min_thread, &latency); + update_sum(&data->hist[cpu].sum_thread, &latency); + update_max(&data->hist[cpu].max_thread, &latency); + } + + if (bucket < entries) + hist[bucket]++; + else + hist[entries]++; +} + +/* + * timerlat_hist_handler - this is the handler for timerlat tracer events + */ +static int +timerlat_hist_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *data) +{ + struct trace_instance *trace = data; + unsigned long long thread, latency; + struct osnoise_tool *tool; + int cpu = record->cpu; + + tool = container_of(trace, struct osnoise_tool, trace); + + tep_get_field_val(s, event, "context", record, &thread, 1); + tep_get_field_val(s, event, "timer_latency", record, &latency, 1); + + timerlat_hist_update(tool, cpu, thread, latency); + + return 0; +} + +/* + * timerlat_hist_header - print the header of the tracer to the output + */ +static void timerlat_hist_header(struct osnoise_tool *tool) +{ + struct timerlat_hist_params *params = tool->params; + struct timerlat_hist_data *data = tool->data; + struct trace_seq *s = tool->trace.seq; + char duration[26]; + int cpu; + + if (params->no_header) + return; + + get_duration(tool->start_time, duration, sizeof(duration)); + trace_seq_printf(s, "# RTLA timerlat histogram\n"); + trace_seq_printf(s, "# Time unit is %s (%s)\n", + params->output_divisor == 1 ? "nanoseconds" : "microseconds", + params->output_divisor == 1 ? "ns" : "us"); + + trace_seq_printf(s, "# Duration: %s\n", duration); + + if (!params->no_index) + trace_seq_printf(s, "Index"); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) + trace_seq_printf(s, " IRQ-%03d", cpu); + + if (!params->no_thread) + trace_seq_printf(s, " Thr-%03d", cpu); + } + trace_seq_printf(s, "\n"); + + + trace_seq_do_printf(s); + trace_seq_reset(s); +} + +/* + * timerlat_print_summary - print the summary of the hist data to the output + */ +static void +timerlat_print_summary(struct timerlat_hist_params *params, + struct trace_instance *trace, + struct timerlat_hist_data *data) +{ + int cpu; + + if (params->no_summary) + return; + + if (!params->no_index) + trace_seq_printf(trace->seq, "count:"); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].irq_count); + + if (!params->no_thread) + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].thread_count); + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "min: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].min_irq); + + if (!params->no_thread) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].min_thread); + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "avg: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) { + if (data->hist[cpu].irq_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].sum_irq / data->hist[cpu].irq_count); + else + trace_seq_printf(trace->seq, " - "); + } + + if (!params->no_thread) { + if (data->hist[cpu].thread_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].sum_thread / data->hist[cpu].thread_count); + else + trace_seq_printf(trace->seq, " - "); + } + } + trace_seq_printf(trace->seq, "\n"); + + if (!params->no_index) + trace_seq_printf(trace->seq, "max: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].max_irq); + + if (!params->no_thread) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].max_thread); + } + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); +} + +/* + * timerlat_print_stats - print data for all CPUs + */ +static void +timerlat_print_stats(struct timerlat_hist_params *params, struct osnoise_tool *tool) +{ + struct timerlat_hist_data *data = tool->data; + struct trace_instance *trace = &tool->trace; + int bucket, cpu; + int total; + + timerlat_hist_header(tool); + + for (bucket = 0; bucket < data->entries; bucket++) { + total = 0; + + if (!params->no_index) + trace_seq_printf(trace->seq, "%-6d", + bucket * data->bucket_size); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) { + total += data->hist[cpu].irq[bucket]; + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].irq[bucket]); + } + + if (!params->no_thread) { + total += data->hist[cpu].thread[bucket]; + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].thread[bucket]); + } + + } + + if (total == 0 && !params->with_zeros) { + trace_seq_reset(trace->seq); + continue; + } + + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); + } + + if (!params->no_index) + trace_seq_printf(trace->seq, "over: "); + + for (cpu = 0; cpu < data->nr_cpus; cpu++) { + if (params->cpus && !params->monitored_cpus[cpu]) + continue; + + if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) + continue; + + if (!params->no_irq) + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].irq[data->entries]); + + if (!params->no_thread) + trace_seq_printf(trace->seq, "%9d ", + data->hist[cpu].thread[data->entries]); + } + trace_seq_printf(trace->seq, "\n"); + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); + + timerlat_print_summary(params, trace, data); +} + +/* + * timerlat_hist_usage - prints timerlat top usage message + */ +static void timerlat_hist_usage(char *usage) +{ + int i; + + char *msg[] = { + "", + " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\", + " [-c cpu-list] [-P priority] [-e N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", + " [--no-index] [--with-zeros]", + "", + " -h/--help: print this menu", + " -p/--period us: timerlat period in us", + " -i/--irq us: stop trace if the irq latency is higher than the argument in us", + " -T/--thread us: stop trace if the thread latency is higher than the argument in us", + " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us", + " -c/--cpus cpus: run the tracer only on the given cpus", + " -d/--duration time[m|h|d]: duration of the session in seconds", + " -D/--debug: print debug info", + " -T/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", + " -n/--nano: display data in nanoseconds", + " -b/--bucket-size N: set the histogram bucket size (default 1)", + " -e/--entries N: set the number of entries of the histogram (default 256)", + " --no-irq: ignore IRQ latencies", + " --no-thread: ignore thread latencies", + " --no-header: do not print header", + " --no-summary: do not print summary", + " --no-index: do not print index", + " --with-zeros: print zero only entries", + " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", + " o:prio - use SCHED_OTHER with prio", + " r:prio - use SCHED_RR with prio", + " f:prio - use SCHED_FIFO with prio", + " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period", + " in nanoseconds", + NULL, + }; + + if (usage) + fprintf(stderr, "%s\n", usage); + + fprintf(stderr, "rtla timerlat hist: a per-cpu histogram of the timer latency (version %s)\n", + VERSION); + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +/* + * timerlat_hist_parse_args - allocs, parse and fill the cmd line parameters + */ +static struct timerlat_hist_params +*timerlat_hist_parse_args(int argc, char *argv[]) +{ + struct timerlat_hist_params *params; + int retval; + int c; + + params = calloc(1, sizeof(*params)); + if (!params) + exit(1); + + /* display data in microseconds */ + params->output_divisor = 1000; + params->bucket_size = 1; + params->entries = 256; + + while (1) { + static struct option long_options[] = { + {"cpus", required_argument, 0, 'c'}, + {"bucket-size", required_argument, 0, 'b'}, + {"debug", no_argument, 0, 'D'}, + {"entries", required_argument, 0, 'e'}, + {"duration", required_argument, 0, 'd'}, + {"help", no_argument, 0, 'h'}, + {"irq", required_argument, 0, 'i'}, + {"nano", no_argument, 0, 'n'}, + {"period", required_argument, 0, 'p'}, + {"priority", required_argument, 0, 'P'}, + {"stack", required_argument, 0, 's'}, + {"thread", required_argument, 0, 'T'}, + {"trace", optional_argument, 0, 't'}, + {"no-irq", no_argument, 0, '0'}, + {"no-thread", no_argument, 0, '1'}, + {"no-header", no_argument, 0, '2'}, + {"no-summary", no_argument, 0, '3'}, + {"no-index", no_argument, 0, '4'}, + {"with-zeros", no_argument, 0, '5'}, + {0, 0, 0, 0} + }; + + /* getopt_long stores the option index here. */ + int option_index = 0; + + c = getopt_long(argc, argv, "c:b:d:e:Dhi:np:P:s:t::T:012345", + long_options, &option_index); + + /* detect the end of the options. */ + if (c == -1) + break; + + switch (c) { + case 'c': + retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); + if (retval) + timerlat_hist_usage("\nInvalid -c cpu list\n"); + params->cpus = optarg; + break; + case 'b': + params->bucket_size = get_llong_from_str(optarg); + if ((params->bucket_size == 0) || (params->bucket_size >= 1000000)) + timerlat_hist_usage("Bucket size needs to be > 0 and <= 1000000\n"); + break; + case 'D': + config_debug = 1; + break; + case 'd': + params->duration = parse_seconds_duration(optarg); + if (!params->duration) + timerlat_hist_usage("Invalid -D duration\n"); + break; + case 'e': + params->entries = get_llong_from_str(optarg); + if ((params->entries < 10) || (params->entries > 9999999)) + timerlat_hist_usage("Entries must be > 10 and < 9999999\n"); + break; + case 'h': + case '?': + timerlat_hist_usage(NULL); + break; + case 'i': + params->stop_us = get_llong_from_str(optarg); + break; + case 'n': + params->output_divisor = 1; + break; + case 'p': + params->timerlat_period_us = get_llong_from_str(optarg); + if (params->timerlat_period_us > 1000000) + timerlat_hist_usage("Period longer than 1 s\n"); + break; + case 'P': + retval = parse_prio(optarg, ¶ms->sched_param); + if (retval == -1) + timerlat_hist_usage("Invalid -P priority"); + params->set_sched = 1; + break; + case 's': + params->print_stack = get_llong_from_str(optarg); + break; + case 'T': + params->stop_total_us = get_llong_from_str(optarg); + break; + case 't': + if (optarg) + /* skip = */ + params->trace_output = &optarg[1]; + else + params->trace_output = "timerlat_trace.txt"; + break; + case '0': /* no irq */ + params->no_irq = 1; + break; + case '1': /* no thread */ + params->no_thread = 1; + break; + case '2': /* no header */ + params->no_header = 1; + break; + case '3': /* no summary */ + params->no_summary = 1; + break; + case '4': /* no index */ + params->no_index = 1; + break; + case '5': /* with zeros */ + params->with_zeros = 1; + break; + default: + timerlat_hist_usage("Invalid option"); + } + } + + if (geteuid()) { + err_msg("rtla needs root permission\n"); + exit(EXIT_FAILURE); + } + + if (params->no_irq && params->no_thread) + timerlat_hist_usage("no-irq and no-thread set, there is nothing to do here"); + + if (params->no_index && !params->with_zeros) + timerlat_hist_usage("no-index set with with-zeros is not set - it does not make sense"); + + return params; +} + +/* + * timerlat_hist_apply_config - apply the hist configs to the initialized tool + */ +static int +timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_params *params) +{ + int retval; + + if (!params->sleep_time) + params->sleep_time = 1; + + if (params->cpus) { + retval = osnoise_set_cpus(tool->context, params->cpus); + if (retval) { + err_msg("Failed to apply CPUs config\n"); + goto out_err; + } + } + + if (params->stop_us) { + retval = osnoise_set_stop_us(tool->context, params->stop_us); + if (retval) { + err_msg("Failed to set stop us\n"); + goto out_err; + } + } + + if (params->stop_total_us) { + retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us); + if (retval) { + err_msg("Failed to set stop total us\n"); + goto out_err; + } + } + + if (params->timerlat_period_us) { + retval = osnoise_set_timerlat_period_us(tool->context, params->timerlat_period_us); + if (retval) { + err_msg("Failed to set timerlat period\n"); + goto out_err; + } + } + + if (params->print_stack) { + retval = osnoise_set_print_stack(tool->context, params->print_stack); + if (retval) { + err_msg("Failed to set print stack\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -1; +} + +/* + * timerlat_init_hist - initialize a timerlat hist tool with parameters + */ +static struct osnoise_tool +*timerlat_init_hist(struct timerlat_hist_params *params) +{ + struct osnoise_tool *tool; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + tool = osnoise_init_tool("timerlat_hist"); + if (!tool) + return NULL; + + tool->data = timerlat_alloc_histogram(nr_cpus, params->entries, params->bucket_size); + if (!tool->data) + goto out_err; + + tool->params = params; + + tep_register_event_handler(tool->trace.tep, -1, "ftrace", "timerlat", + timerlat_hist_handler, tool); + + return tool; + +out_err: + osnoise_destroy_tool(tool); + return NULL; +} + +static int stop_tracing; +static void stop_hist(int sig) +{ + stop_tracing = 1; +} + +/* + * timerlat_hist_set_signals - handles the signal to stop the tool + */ +static void +timerlat_hist_set_signals(struct timerlat_hist_params *params) +{ + signal(SIGINT, stop_hist); + if (params->duration) { + signal(SIGALRM, stop_hist); + alarm(params->duration); + } +} + +int timerlat_hist_main(int argc, char *argv[]) +{ + struct timerlat_hist_params *params; + struct trace_instance *trace; + struct osnoise_tool *record; + struct osnoise_tool *tool; + int return_value = 1; + int retval; + + params = timerlat_hist_parse_args(argc, argv); + if (!params) + exit(1); + + tool = timerlat_init_hist(params); + if (!tool) { + err_msg("Could not init osnoise hist\n"); + goto out_exit; + } + + retval = timerlat_hist_apply_config(tool, params); + if (retval) { + err_msg("Could not apply config\n"); + goto out_hist; + } + + trace = &tool->trace; + + retval = enable_timerlat(trace); + if (retval) { + err_msg("Failed to enable timerlat tracer\n"); + goto out_hist; + } + + if (params->set_sched) { + retval = set_comm_sched_attr("timerlat/", ¶ms->sched_param); + if (retval) { + err_msg("Failed to set sched parameters\n"); + goto out_hist; + } + } + + trace_instance_start(trace); + + if (params->trace_output) { + record = osnoise_init_trace_tool("timerlat"); + if (!record) { + err_msg("Failed to enable the trace instance\n"); + goto out_hist; + } + trace_instance_start(&record->trace); + } + + tool->start_time = time(NULL); + timerlat_hist_set_signals(params); + + while (!stop_tracing) { + sleep(params->sleep_time); + + retval = tracefs_iterate_raw_events(trace->tep, + trace->inst, + NULL, + 0, + collect_registered_events, + trace); + if (retval < 0) { + err_msg("Error iterating on events\n"); + goto out_hist; + } + + if (!tracefs_trace_is_on(trace->inst)) + break; + }; + + timerlat_print_stats(params, tool); + + return_value = 0; + + if (!tracefs_trace_is_on(trace->inst)) { + printf("rtla timelat hit stop tracing\n"); + if (params->trace_output) { + printf(" Saving trace to %s\n", params->trace_output); + save_trace_to_file(record->trace.inst, params->trace_output); + } + } + +out_hist: + timerlat_free_histogram(tool->data); + osnoise_destroy_tool(tool); + if (params->trace_output) + osnoise_destroy_tool(record); + free(params); +out_exit: + exit(return_value); +} diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c new file mode 100644 index 000000000000..1ebd5291539c --- /dev/null +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -0,0 +1,618 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#include <stdio.h> +#include <time.h> + +#include "utils.h" +#include "osnoise.h" +#include "timerlat.h" + +struct timerlat_top_params { + char *cpus; + char *monitored_cpus; + char *trace_output; + unsigned long long runtime; + long long stop_us; + long long stop_total_us; + long long timerlat_period_us; + long long print_stack; + int sleep_time; + int output_divisor; + int duration; + int quiet; + int set_sched; + struct sched_attr sched_param; +}; + +struct timerlat_top_cpu { + int irq_count; + int thread_count; + + unsigned long long cur_irq; + unsigned long long min_irq; + unsigned long long sum_irq; + unsigned long long max_irq; + + unsigned long long cur_thread; + unsigned long long min_thread; + unsigned long long sum_thread; + unsigned long long max_thread; +}; + +struct timerlat_top_data { + struct timerlat_top_cpu *cpu_data; + int nr_cpus; +}; + +/* + * timerlat_free_top - free runtime data + */ +static void +timerlat_free_top(struct timerlat_top_data *data) +{ + free(data->cpu_data); + free(data); +} + +/* + * timerlat_alloc_histogram - alloc runtime data + */ +static struct timerlat_top_data *timerlat_alloc_top(int nr_cpus) +{ + struct timerlat_top_data *data; + int cpu; + + data = calloc(1, sizeof(*data)); + if (!data) + return NULL; + + data->nr_cpus = nr_cpus; + + /* one set of histograms per CPU */ + data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus); + if (!data->cpu_data) + goto cleanup; + + /* set the min to max */ + for (cpu = 0; cpu < nr_cpus; cpu++) { + data->cpu_data[cpu].min_irq = ~0; + data->cpu_data[cpu].min_thread = ~0; + } + + return data; + +cleanup: + timerlat_free_top(data); + return NULL; +} + +/* + * timerlat_hist_update - record a new timerlat occurent on cpu, updating data + */ +static void +timerlat_top_update(struct osnoise_tool *tool, int cpu, + unsigned long long thread, + unsigned long long latency) +{ + struct timerlat_top_data *data = tool->data; + struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu]; + + if (!thread) { + cpu_data->irq_count++; + cpu_data->cur_irq = latency; + update_min(&cpu_data->min_irq, &latency); + update_sum(&cpu_data->sum_irq, &latency); + update_max(&cpu_data->max_irq, &latency); + } else { + cpu_data->thread_count++; + cpu_data->cur_thread = latency; + update_min(&cpu_data->min_thread, &latency); + update_sum(&cpu_data->sum_thread, &latency); + update_max(&cpu_data->max_thread, &latency); + } +} + +/* + * timerlat_top_handler - this is the handler for timerlat tracer events + */ +static int +timerlat_top_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct trace_instance *trace = context; + unsigned long long latency, thread; + struct osnoise_tool *top; + int cpu = record->cpu; + + top = container_of(trace, struct osnoise_tool, trace); + + tep_get_field_val(s, event, "context", record, &thread, 1); + tep_get_field_val(s, event, "timer_latency", record, &latency, 1); + + timerlat_top_update(top, cpu, thread, latency); + + return 0; +} + +/* + * timerlat_top_header - print the header of the tool output + */ +static void timerlat_top_header(struct osnoise_tool *top) +{ + struct timerlat_top_params *params = top->params; + struct trace_seq *s = top->trace.seq; + char duration[26]; + + get_duration(top->start_time, duration, sizeof(duration)); + + trace_seq_printf(s, "\033[2;37;40m"); + trace_seq_printf(s, " Timer Latency "); + trace_seq_printf(s, "\033[0;0;0m"); + trace_seq_printf(s, "\n"); + + trace_seq_printf(s, "%-6s | IRQ Timer Latency (%s) | Thread Timer Latency (%s)\n", duration, + params->output_divisor == 1 ? "ns" : "us", + params->output_divisor == 1 ? "ns" : "us"); + + trace_seq_printf(s, "\033[2;30;47m"); + trace_seq_printf(s, "CPU COUNT | cur min avg max | cur min avg max"); + trace_seq_printf(s, "\033[0;0;0m"); + trace_seq_printf(s, "\n"); +} + +/* + * timerlat_top_print - prints the output of a given CPU + */ +static void timerlat_top_print(struct osnoise_tool *top, int cpu) +{ + + struct timerlat_top_params *params = top->params; + struct timerlat_top_data *data = top->data; + struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu]; + int divisor = params->output_divisor; + struct trace_seq *s = top->trace.seq; + + if (divisor == 0) + return; + + /* + * Skip if no data is available: is this cpu offline? + */ + if (!cpu_data->irq_count && !cpu_data->thread_count) + return; + + /* + * Unless trace is being lost, IRQ counter is always the max. + */ + trace_seq_printf(s, "%3d #%-9d |", cpu, cpu_data->irq_count); + + if (!cpu_data->irq_count) { + trace_seq_printf(s, " - "); + trace_seq_printf(s, " - "); + trace_seq_printf(s, " - "); + trace_seq_printf(s, " - |"); + } else { + trace_seq_printf(s, "%9llu ", cpu_data->cur_irq / params->output_divisor); + trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor); + trace_seq_printf(s, "%9llu ", (cpu_data->sum_irq / cpu_data->irq_count) / divisor); + trace_seq_printf(s, "%9llu |", cpu_data->max_irq / divisor); + } + + if (!cpu_data->thread_count) { + trace_seq_printf(s, " - "); + trace_seq_printf(s, " - "); + trace_seq_printf(s, " - "); + trace_seq_printf(s, " -\n"); + } else { + trace_seq_printf(s, "%9llu ", cpu_data->cur_thread / divisor); + trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor); + trace_seq_printf(s, "%9llu ", + (cpu_data->sum_thread / cpu_data->thread_count) / divisor); + trace_seq_printf(s, "%9llu\n", cpu_data->max_thread / divisor); + } +} + +/* + * clear_terminal - clears the output terminal + */ +static void clear_terminal(struct trace_seq *seq) +{ + if (!config_debug) + trace_seq_printf(seq, "\033c"); +} + +/* + * timerlat_print_stats - print data for all cpus + */ +static void +timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *top) +{ + struct trace_instance *trace = &top->trace; + static int nr_cpus = -1; + int i; + + if (nr_cpus == -1) + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + if (!params->quiet) + clear_terminal(trace->seq); + + timerlat_top_header(top); + + for (i = 0; i < nr_cpus; i++) { + if (params->cpus && !params->monitored_cpus[i]) + continue; + timerlat_top_print(top, i); + } + + trace_seq_do_printf(trace->seq); + trace_seq_reset(trace->seq); +} + +/* + * timerlat_top_usage - prints timerlat top usage message + */ +static void timerlat_top_usage(char *usage) +{ + int i; + + static const char *const msg[] = { + "", + " usage: rtla timerlat [top] [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\", + " [-c cpu-list] [-P priority]", + "", + " -h/--help: print this menu", + " -p/--period us: timerlat period in us", + " -i/--irq us: stop trace if the irq latency is higher than the argument in us", + " -T/--thread us: stop trace if the thread latency is higher than the argument in us", + " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us", + " -c/--cpus cpus: run the tracer only on the given cpus", + " -d/--duration time[m|h|d]: duration of the session in seconds", + " -D/--debug: print debug info", + " -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", + " -n/--nano: display data in nanoseconds", + " -q/--quiet print only a summary at the end", + " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", + " o:prio - use SCHED_OTHER with prio", + " r:prio - use SCHED_RR with prio", + " f:prio - use SCHED_FIFO with prio", + " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period", + " in nanoseconds", + NULL, + }; + + if (usage) + fprintf(stderr, "%s\n", usage); + + fprintf(stderr, "rtla timerlat top: a per-cpu summary of the timer latency (version %s)\n", + VERSION); + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); + exit(1); +} + +/* + * timerlat_top_parse_args - allocs, parse and fill the cmd line parameters + */ +static struct timerlat_top_params +*timerlat_top_parse_args(int argc, char **argv) +{ + struct timerlat_top_params *params; + int retval; + int c; + + params = calloc(1, sizeof(*params)); + if (!params) + exit(1); + + /* display data in microseconds */ + params->output_divisor = 1000; + + while (1) { + static struct option long_options[] = { + {"cpus", required_argument, 0, 'c'}, + {"debug", no_argument, 0, 'D'}, + {"duration", required_argument, 0, 'd'}, + {"help", no_argument, 0, 'h'}, + {"irq", required_argument, 0, 'i'}, + {"nano", no_argument, 0, 'n'}, + {"period", required_argument, 0, 'p'}, + {"priority", required_argument, 0, 'P'}, + {"quiet", no_argument, 0, 'q'}, + {"stack", required_argument, 0, 's'}, + {"thread", required_argument, 0, 'T'}, + {"trace", optional_argument, 0, 't'}, + {0, 0, 0, 0} + }; + + /* getopt_long stores the option index here. */ + int option_index = 0; + + c = getopt_long(argc, argv, "c:d:Dhi:np:P:qs:t::T:", + long_options, &option_index); + + /* detect the end of the options. */ + if (c == -1) + break; + + switch (c) { + case 'c': + retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); + if (retval) + timerlat_top_usage("\nInvalid -c cpu list\n"); + params->cpus = optarg; + break; + case 'D': + config_debug = 1; + break; + case 'd': + params->duration = parse_seconds_duration(optarg); + if (!params->duration) + timerlat_top_usage("Invalid -D duration\n"); + break; + case 'h': + case '?': + timerlat_top_usage(NULL); + break; + case 'i': + params->stop_us = get_llong_from_str(optarg); + break; + case 'n': + params->output_divisor = 1; + break; + case 'p': + params->timerlat_period_us = get_llong_from_str(optarg); + if (params->timerlat_period_us > 1000000) + timerlat_top_usage("Period longer than 1 s\n"); + break; + case 'P': + retval = parse_prio(optarg, ¶ms->sched_param); + if (retval == -1) + timerlat_top_usage("Invalid -P priority"); + params->set_sched = 1; + break; + case 'q': + params->quiet = 1; + break; + case 's': + params->print_stack = get_llong_from_str(optarg); + break; + case 'T': + params->stop_total_us = get_llong_from_str(optarg); + break; + case 't': + if (optarg) + /* skip = */ + params->trace_output = &optarg[1]; + else + params->trace_output = "timerlat_trace.txt"; + break; + default: + timerlat_top_usage("Invalid option"); + } + } + + if (geteuid()) { + err_msg("rtla needs root permission\n"); + exit(EXIT_FAILURE); + } + + return params; +} + +/* + * timerlat_top_apply_config - apply the top configs to the initialized tool + */ +static int +timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params *params) +{ + int retval; + + if (!params->sleep_time) + params->sleep_time = 1; + + if (params->cpus) { + retval = osnoise_set_cpus(top->context, params->cpus); + if (retval) { + err_msg("Failed to apply CPUs config\n"); + goto out_err; + } + } + + if (params->stop_us) { + retval = osnoise_set_stop_us(top->context, params->stop_us); + if (retval) { + err_msg("Failed to set stop us\n"); + goto out_err; + } + } + + if (params->stop_total_us) { + retval = osnoise_set_stop_total_us(top->context, params->stop_total_us); + if (retval) { + err_msg("Failed to set stop total us\n"); + goto out_err; + } + } + + + if (params->timerlat_period_us) { + retval = osnoise_set_timerlat_period_us(top->context, params->timerlat_period_us); + if (retval) { + err_msg("Failed to set timerlat period\n"); + goto out_err; + } + } + + + if (params->print_stack) { + retval = osnoise_set_print_stack(top->context, params->print_stack); + if (retval) { + err_msg("Failed to set print stack\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -1; +} + +/* + * timerlat_init_top - initialize a timerlat top tool with parameters + */ +static struct osnoise_tool +*timerlat_init_top(struct timerlat_top_params *params) +{ + struct osnoise_tool *top; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + top = osnoise_init_tool("timerlat_top"); + if (!top) + return NULL; + + top->data = timerlat_alloc_top(nr_cpus); + if (!top->data) + goto out_err; + + top->params = params; + + tep_register_event_handler(top->trace.tep, -1, "ftrace", "timerlat", + timerlat_top_handler, top); + + return top; + +out_err: + osnoise_destroy_tool(top); + return NULL; +} + +static int stop_tracing; +static void stop_top(int sig) +{ + stop_tracing = 1; +} + +/* + * timerlat_top_set_signals - handles the signal to stop the tool + */ +static void +timerlat_top_set_signals(struct timerlat_top_params *params) +{ + signal(SIGINT, stop_top); + if (params->duration) { + signal(SIGALRM, stop_top); + alarm(params->duration); + } +} + +int timerlat_top_main(int argc, char *argv[]) +{ + struct timerlat_top_params *params; + struct trace_instance *trace; + struct osnoise_tool *record; + struct osnoise_tool *top; + int return_value = 1; + int retval; + + params = timerlat_top_parse_args(argc, argv); + if (!params) + exit(1); + + top = timerlat_init_top(params); + if (!top) { + err_msg("Could not init osnoise top\n"); + goto out_exit; + } + + retval = timerlat_top_apply_config(top, params); + if (retval) { + err_msg("Could not apply config\n"); + goto out_top; + } + + trace = &top->trace; + + retval = enable_timerlat(trace); + if (retval) { + err_msg("Failed to enable timerlat tracer\n"); + goto out_top; + } + + if (params->set_sched) { + retval = set_comm_sched_attr("timerlat/", ¶ms->sched_param); + if (retval) { + err_msg("Failed to set sched parameters\n"); + goto out_top; + } + } + + trace_instance_start(trace); + + if (params->trace_output) { + record = osnoise_init_trace_tool("timerlat"); + if (!record) { + err_msg("Failed to enable the trace instance\n"); + goto out_top; + } + trace_instance_start(&record->trace); + } + + top->start_time = time(NULL); + timerlat_top_set_signals(params); + + while (!stop_tracing) { + sleep(params->sleep_time); + + retval = tracefs_iterate_raw_events(trace->tep, + trace->inst, + NULL, + 0, + collect_registered_events, + trace); + if (retval < 0) { + err_msg("Error iterating on events\n"); + goto out_top; + } + + if (!params->quiet) + timerlat_print_stats(params, top); + + if (!tracefs_trace_is_on(trace->inst)) + break; + + }; + + timerlat_print_stats(params, top); + + return_value = 0; + + if (!tracefs_trace_is_on(trace->inst)) { + printf("rtla timelat hit stop tracing\n"); + if (params->trace_output) { + printf(" Saving trace to %s\n", params->trace_output); + save_trace_to_file(record->trace.inst, params->trace_output); + } + } + +out_top: + timerlat_free_top(top->data); + osnoise_destroy_tool(top); + if (params->trace_output) + osnoise_destroy_tool(record); + free(params); +out_exit: + exit(return_value); +} diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c new file mode 100644 index 000000000000..107a0c6387f7 --- /dev/null +++ b/tools/tracing/rtla/src/trace.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/sendfile.h> +#include <tracefs.h> +#include <signal.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> + +#include "trace.h" +#include "utils.h" + +/* + * enable_tracer_by_name - enable a tracer on the given instance + */ +int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name) +{ + enum tracefs_tracers tracer; + int retval; + + tracer = TRACEFS_TRACER_CUSTOM; + + debug_msg("enabling %s tracer\n", tracer_name); + + retval = tracefs_tracer_set(inst, tracer, tracer_name); + if (retval < 0) { + if (errno == ENODEV) + err_msg("tracer %s not found!\n", tracer_name); + + err_msg("failed to enable the tracer %s\n", tracer_name); + return -1; + } + + return 0; +} + +/* + * disable_tracer - set nop tracer to the insta + */ +void disable_tracer(struct tracefs_instance *inst) +{ + enum tracefs_tracers t = TRACEFS_TRACER_NOP; + int retval; + + retval = tracefs_tracer_set(inst, t); + if (retval < 0) + err_msg("oops, error disabling tracer\n"); +} + +/* + * create_instance - create a trace instance with *instance_name + */ +struct tracefs_instance *create_instance(char *instance_name) +{ + return tracefs_instance_create(instance_name); +} + +/* + * destroy_instance - remove a trace instance and free the data + */ +void destroy_instance(struct tracefs_instance *inst) +{ + tracefs_instance_destroy(inst); + tracefs_instance_free(inst); +} + +/* + * save_trace_to_file - save the trace output of the instance to the file + */ +int save_trace_to_file(struct tracefs_instance *inst, const char *filename) +{ + const char *file = "trace"; + mode_t mode = 0644; + char buffer[4096]; + int out_fd, in_fd; + int retval = -1; + + in_fd = tracefs_instance_file_open(inst, file, O_RDONLY); + if (in_fd < 0) { + err_msg("Failed to open trace file\n"); + return -1; + } + + out_fd = creat(filename, mode); + if (out_fd < 0) { + err_msg("Failed to create output file %s\n", filename); + goto out_close_in; + } + + do { + retval = read(in_fd, buffer, sizeof(buffer)); + if (retval <= 0) + goto out_close; + + retval = write(out_fd, buffer, retval); + if (retval < 0) + goto out_close; + } while (retval > 0); + + retval = 0; +out_close: + close(out_fd); +out_close_in: + close(in_fd); + return retval; +} + +/* + * collect_registered_events - call the existing callback function for the event + * + * If an event has a registered callback function, call it. + * Otherwise, ignore the event. + */ +int +collect_registered_events(struct tep_event *event, struct tep_record *record, + int cpu, void *context) +{ + struct trace_instance *trace = context; + struct trace_seq *s = trace->seq; + + if (!event->handler) + return 0; + + event->handler(s, record, event, context); + + return 0; +} + +/* + * trace_instance_destroy - destroy and free a rtla trace instance + */ +void trace_instance_destroy(struct trace_instance *trace) +{ + if (trace->inst) { + disable_tracer(trace->inst); + destroy_instance(trace->inst); + } + + if (trace->seq) + free(trace->seq); + + if (trace->tep) + tep_free(trace->tep); +} + +/* + * trace_instance_init - create an rtla trace instance + * + * It is more than the tracefs instance, as it contains other + * things required for the tracing, such as the local events and + * a seq file. + * + * Note that the trace instance is returned disabled. This allows + * the tool to apply some other configs, like setting priority + * to the kernel threads, before starting generating trace entries. + */ +int trace_instance_init(struct trace_instance *trace, char *tool_name) +{ + trace->seq = calloc(1, sizeof(*trace->seq)); + if (!trace->seq) + goto out_err; + + trace_seq_init(trace->seq); + + trace->inst = create_instance(tool_name); + if (!trace->inst) + goto out_err; + + trace->tep = tracefs_local_events(NULL); + if (!trace->tep) + goto out_err; + + /* + * Let the main enable the record after setting some other + * things such as the priority of the tracer's threads. + */ + tracefs_trace_off(trace->inst); + + return 0; + +out_err: + trace_instance_destroy(trace); + return 1; +} + +/* + * trace_instance_start - start tracing a given rtla instance + */ +int trace_instance_start(struct trace_instance *trace) +{ + return tracefs_trace_on(trace->inst); +} diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h new file mode 100644 index 000000000000..0ea1df0ad9a7 --- /dev/null +++ b/tools/tracing/rtla/src/trace.h @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <tracefs.h> +#include <stddef.h> + +struct trace_instance { + struct tracefs_instance *inst; + struct tep_handle *tep; + struct trace_seq *seq; +}; + +int trace_instance_init(struct trace_instance *trace, char *tool_name); +int trace_instance_start(struct trace_instance *trace); +void trace_instance_destroy(struct trace_instance *trace); + +struct trace_seq *get_trace_seq(void); +int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name); +void disable_tracer(struct tracefs_instance *inst); + +int enable_osnoise(struct trace_instance *trace); +int enable_timerlat(struct trace_instance *trace); + +struct tracefs_instance *create_instance(char *instance_name); +void destroy_instance(struct tracefs_instance *inst); + +int save_trace_to_file(struct tracefs_instance *inst, const char *filename); +int collect_registered_events(struct tep_event *tep, struct tep_record *record, + int cpu, void *context); diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c new file mode 100644 index 000000000000..1c9f0eea6166 --- /dev/null +++ b/tools/tracing/rtla/src/utils.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <proc/readproc.h> +#include <stdarg.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <ctype.h> +#include <errno.h> +#include <sched.h> +#include <stdio.h> + +#include "utils.h" + +#define MAX_MSG_LENGTH 1024 +int config_debug; + +/* + * err_msg - print an error message to the stderr + */ +void err_msg(const char *fmt, ...) +{ + char message[MAX_MSG_LENGTH]; + va_list ap; + + va_start(ap, fmt); + vsnprintf(message, sizeof(message), fmt, ap); + va_end(ap); + + fprintf(stderr, "%s", message); +} + +/* + * debug_msg - print a debug message to stderr if debug is set + */ +void debug_msg(const char *fmt, ...) +{ + char message[MAX_MSG_LENGTH]; + va_list ap; + + if (!config_debug) + return; + + va_start(ap, fmt); + vsnprintf(message, sizeof(message), fmt, ap); + va_end(ap); + + fprintf(stderr, "%s", message); +} + +/* + * get_llong_from_str - get a long long int from a string + */ +long long get_llong_from_str(char *start) +{ + long long value; + char *end; + + errno = 0; + value = strtoll(start, &end, 10); + if (errno || start == end) + return -1; + + return value; +} + +/* + * get_duration - fill output with a human readable duration since start_time + */ +void get_duration(time_t start_time, char *output, int output_size) +{ + time_t now = time(NULL); + struct tm *tm_info; + time_t duration; + + duration = difftime(now, start_time); + tm_info = localtime(&duration); + + snprintf(output, output_size, "%3d %02d:%02d:%02d", + tm_info->tm_yday, + tm_info->tm_hour - 1, + tm_info->tm_min, + tm_info->tm_sec); +} + +/* + * parse_cpu_list - parse a cpu_list filling a char vector with cpus set + * + * Receives a cpu list, like 1-3,5 (cpus 1, 2, 3, 5), and then set the char + * in the monitored_cpus. + * + * XXX: convert to a bitmask. + */ +int parse_cpu_list(char *cpu_list, char **monitored_cpus) +{ + char *mon_cpus; + const char *p; + int end_cpu; + int nr_cpus; + int cpu; + int i; + + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + + mon_cpus = malloc(nr_cpus * sizeof(char)); + memset(mon_cpus, 0, (nr_cpus * sizeof(char))); + + for (p = cpu_list; *p; ) { + cpu = atoi(p); + if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus) + goto err; + + while (isdigit(*p)) + p++; + if (*p == '-') { + p++; + end_cpu = atoi(p); + if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus) + goto err; + while (isdigit(*p)) + p++; + } else + end_cpu = cpu; + + if (cpu == end_cpu) { + debug_msg("cpu_list: adding cpu %d\n", cpu); + mon_cpus[cpu] = 1; + } else { + for (i = cpu; i <= end_cpu; i++) { + debug_msg("cpu_list: adding cpu %d\n", i); + mon_cpus[i] = 1; + } + } + + if (*p == ',') + p++; + } + + *monitored_cpus = mon_cpus; + + return 0; + +err: + debug_msg("Error parsing the cpu list %s", cpu_list); + return 1; +} + +/* + * parse_duration - parse duration with s/m/h/d suffix converting it to seconds + */ +long parse_seconds_duration(char *val) +{ + char *end; + long t; + + t = strtol(val, &end, 10); + + if (end) { + switch (*end) { + case 's': + case 'S': + break; + case 'm': + case 'M': + t *= 60; + break; + case 'h': + case 'H': + t *= 60 * 60; + break; + + case 'd': + case 'D': + t *= 24 * 60 * 60; + break; + } + } + + return t; +} + +/* + * parse_ns_duration - parse duration with ns/us/ms/s converting it to nanoseconds + */ +long parse_ns_duration(char *val) +{ + char *end; + long t; + + t = strtol(val, &end, 10); + + if (end) { + if (!strncmp(end, "ns", 2)) { + return t; + } else if (!strncmp(end, "us", 2)) { + t *= 1000; + return t; + } else if (!strncmp(end, "ms", 2)) { + t *= 1000 * 1000; + return t; + } else if (!strncmp(end, "s", 1)) { + t *= 1000 * 1000 * 1000; + return t; + } + return -1; + } + + return t; +} + +/* + * This is a set of helper functions to use SCHED_DEADLINE. + */ +#ifdef __x86_64__ +# define __NR_sched_setattr 314 +# define __NR_sched_getattr 315 +#elif __i386__ +# define __NR_sched_setattr 351 +# define __NR_sched_getattr 352 +#elif __arm__ +# define __NR_sched_setattr 380 +# define __NR_sched_getattr 381 +#elif __aarch64__ +# define __NR_sched_setattr 274 +# define __NR_sched_getattr 275 +#elif __powerpc__ +# define __NR_sched_setattr 355 +# define __NR_sched_getattr 356 +#elif __s390x__ +# define __NR_sched_setattr 345 +# define __NR_sched_getattr 346 +#endif + +#define SCHED_DEADLINE 6 + +static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, + unsigned int flags) { + return syscall(__NR_sched_setattr, pid, attr, flags); +} + +static inline int sched_getattr(pid_t pid, struct sched_attr *attr, + unsigned int size, unsigned int flags) +{ + return syscall(__NR_sched_getattr, pid, attr, size, flags); +} + +int __set_sched_attr(int pid, struct sched_attr *attr) +{ + int flags = 0; + int retval; + + retval = sched_setattr(pid, attr, flags); + if (retval < 0) { + err_msg("boost_with_deadline failed to boost pid %d: %s\n", + pid, strerror(errno)); + return 1; + } + + return 0; +} +/* + * set_comm_sched_attr - set sched params to threads starting with char *comm + * + * This function uses procps to list the currently running threads and then + * set the sched_attr *attr to the threads that start with char *comm. It is + * mainly used to set the priority to the kernel threads created by the + * tracers. + */ +int set_comm_sched_attr(const char *comm, struct sched_attr *attr) +{ + int flags = PROC_FILLCOM | PROC_FILLSTAT; + PROCTAB *ptp; + proc_t task; + int retval; + + ptp = openproc(flags); + if (!ptp) { + err_msg("error openproc()\n"); + return -ENOENT; + } + + memset(&task, 0, sizeof(task)); + + while (readproc(ptp, &task)) { + retval = strncmp(comm, task.cmd, strlen(comm)); + if (retval) + continue; + retval = __set_sched_attr(task.tid, attr); + if (retval) + goto out_err; + } + + closeproc(ptp); + return 0; + +out_err: + closeproc(ptp); + return 1; +} + +#define INVALID_VAL (~0L) +static long get_long_ns_after_colon(char *start) +{ + long val = INVALID_VAL; + + /* find the ":" */ + start = strstr(start, ":"); + if (!start) + return -1; + + /* skip ":" */ + start++; + val = parse_ns_duration(start); + + return val; +} + +static long get_long_after_colon(char *start) +{ + long val = INVALID_VAL; + + /* find the ":" */ + start = strstr(start, ":"); + if (!start) + return -1; + + /* skip ":" */ + start++; + val = get_llong_from_str(start); + + return val; +} + +/* + * parse priority in the format: + * SCHED_OTHER: + * o:<prio> + * O:<prio> + * SCHED_RR: + * r:<prio> + * R:<prio> + * SCHED_FIFO: + * f:<prio> + * F:<prio> + * SCHED_DEADLINE: + * d:runtime:period + * D:runtime:period + */ +int parse_prio(char *arg, struct sched_attr *sched_param) +{ + long prio; + long runtime; + long period; + + memset(sched_param, 0, sizeof(*sched_param)); + sched_param->size = sizeof(*sched_param); + + switch (arg[0]) { + case 'd': + case 'D': + /* d:runtime:period */ + if (strlen(arg) < 4) + return -1; + + runtime = get_long_ns_after_colon(arg); + if (runtime == INVALID_VAL) + return -1; + + period = get_long_ns_after_colon(&arg[2]); + if (period == INVALID_VAL) + return -1; + + if (runtime > period) + return -1; + + sched_param->sched_policy = SCHED_DEADLINE; + sched_param->sched_runtime = runtime; + sched_param->sched_deadline = period; + sched_param->sched_period = period; + break; + case 'f': + case 'F': + /* f:prio */ + prio = get_long_after_colon(arg); + if (prio == INVALID_VAL) + return -1; + + if (prio < sched_get_priority_min(SCHED_FIFO)) + return -1; + if (prio > sched_get_priority_max(SCHED_FIFO)) + return -1; + + sched_param->sched_policy = SCHED_FIFO; + sched_param->sched_priority = prio; + break; + case 'r': + case 'R': + /* r:prio */ + prio = get_long_after_colon(arg); + if (prio == INVALID_VAL) + return -1; + + if (prio < sched_get_priority_min(SCHED_RR)) + return -1; + if (prio > sched_get_priority_max(SCHED_RR)) + return -1; + + sched_param->sched_policy = SCHED_RR; + sched_param->sched_priority = prio; + break; + case 'o': + case 'O': + /* o:prio */ + prio = get_long_after_colon(arg); + if (prio == INVALID_VAL) + return -1; + + if (prio < sched_get_priority_min(SCHED_OTHER)) + return -1; + if (prio > sched_get_priority_max(SCHED_OTHER)) + return -1; + + sched_param->sched_policy = SCHED_OTHER; + sched_param->sched_priority = prio; + break; + default: + return -1; + } + return 0; +} diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h new file mode 100644 index 000000000000..9aa962319ca2 --- /dev/null +++ b/tools/tracing/rtla/src/utils.h @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdint.h> +#include <time.h> + +/* + * '18446744073709551615\0' + */ +#define BUFF_U64_STR_SIZE 24 + +#define container_of(ptr, type, member)({ \ + const typeof(((type *)0)->member) *__mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)) ; }) + +extern int config_debug; +void debug_msg(const char *fmt, ...); +void err_msg(const char *fmt, ...); + +long parse_seconds_duration(char *val); +void get_duration(time_t start_time, char *output, int output_size); + +int parse_cpu_list(char *cpu_list, char **monitored_cpus); +long long get_llong_from_str(char *start); + +static inline void +update_min(unsigned long long *a, unsigned long long *b) +{ + if (*a > *b) + *a = *b; +} + +static inline void +update_max(unsigned long long *a, unsigned long long *b) +{ + if (*a < *b) + *a = *b; +} + +static inline void +update_sum(unsigned long long *a, unsigned long long *b) +{ + *a += *b; +} + +struct sched_attr { + uint32_t size; + uint32_t sched_policy; + uint64_t sched_flags; + int32_t sched_nice; + uint32_t sched_priority; + uint64_t sched_runtime; + uint64_t sched_deadline; + uint64_t sched_period; +}; + +int parse_prio(char *arg, struct sched_attr *sched_param); +int set_comm_sched_attr(const char *comm, struct sched_attr *attr); |