diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /tools/testing/selftests/resctrl | |
parent | Initial commit. (diff) | |
download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/testing/selftests/resctrl')
-rw-r--r-- | tools/testing/selftests/resctrl/.gitignore | 2 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/Makefile | 10 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/README | 78 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/cache.c | 308 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/cat_test.c | 211 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/cmt_test.c | 141 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/config | 2 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/fill_buf.c | 179 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/mba_test.c | 169 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/mbm_test.c | 137 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/resctrl.h | 121 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/resctrl_tests.c | 324 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/resctrl_val.c | 793 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/resctrlfs.c | 732 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/settings | 3 |
15 files changed, 3210 insertions, 0 deletions
diff --git a/tools/testing/selftests/resctrl/.gitignore b/tools/testing/selftests/resctrl/.gitignore new file mode 100644 index 0000000000..ab68442b6b --- /dev/null +++ b/tools/testing/selftests/resctrl/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +resctrl_tests diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile new file mode 100644 index 0000000000..2deac2031d --- /dev/null +++ b/tools/testing/selftests/resctrl/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS = -g -Wall -O2 -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE +CFLAGS += $(KHDR_INCLUDES) + +TEST_GEN_PROGS := resctrl_tests + +include ../lib.mk + +$(OUTPUT)/resctrl_tests: $(wildcard *.[ch]) diff --git a/tools/testing/selftests/resctrl/README b/tools/testing/selftests/resctrl/README new file mode 100644 index 0000000000..8d11ce7c2e --- /dev/null +++ b/tools/testing/selftests/resctrl/README @@ -0,0 +1,78 @@ +resctrl_tests - resctrl file system test suit + +Authors: + Fenghua Yu <fenghua.yu@intel.com> + Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + +resctrl_tests tests various resctrl functionalities and interfaces including +both software and hardware. + +Currently it supports Memory Bandwidth Monitoring test and Memory Bandwidth +Allocation test on Intel RDT hardware. More tests will be added in the future. +And the test suit can be extended to cover AMD QoS and ARM MPAM hardware +as well. + +resctrl_tests can be run with or without kselftest framework. + +WITH KSELFTEST FRAMEWORK +======================= + +BUILD +----- + +Build executable file "resctrl_tests" from top level directory of the kernel source: + $ make -C tools/testing/selftests TARGETS=resctrl + +RUN +--- + +Run resctrl_tests as sudo or root since the test needs to mount resctrl file +system and change contents in the file system. +Using kselftest framework will run all supported tests within resctrl_tests: + + $ sudo make -C tools/testing/selftests TARGETS=resctrl run_tests + +More details about kselftest framework can be found in +Documentation/dev-tools/kselftest.rst. + +WITHOUT KSELFTEST FRAMEWORK +=========================== + +BUILD +----- + +Build executable file "resctrl_tests" from this directory(tools/testing/selftests/resctrl/): + $ make + +RUN +--- + +Run resctrl_tests as sudo or root since the test needs to mount resctrl file +system and change contents in the file system. +Executing the test without any parameter will run all supported tests: + + $ sudo ./resctrl_tests + +OVERVIEW OF EXECUTION +===================== + +A test case has four stages: + + - setup: mount resctrl file system, create group, setup schemata, move test + process pids to tasks, start benchmark. + - execute: let benchmark run + - verify: get resctrl data and verify the data with another source, e.g. + perf event. + - teardown: umount resctrl and clear temporary files. + +ARGUMENTS +========= + +Parameter '-h' shows usage information. + +usage: resctrl_tests [-h] [-b "benchmark_cmd [options]"] [-t test list] [-n no_of_bits] + -b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT default benchmark is builtin fill_buf + -t test list: run tests specified in the test list, e.g. -t mbm,mba,cmt,cat + -n no_of_bits: run cache tests using specified no of bits in cache bit mask + -p cpu_no: specify CPU number to run the test. 1 is default + -h: help diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c new file mode 100644 index 0000000000..a0318bd3a6 --- /dev/null +++ b/tools/testing/selftests/resctrl/cache.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdint.h> +#include "resctrl.h" + +struct read_format { + __u64 nr; /* The number of events */ + struct { + __u64 value; /* The value of the event */ + } values[2]; +}; + +static struct perf_event_attr pea_llc_miss; +static struct read_format rf_cqm; +static int fd_lm; +char llc_occup_path[1024]; + +static void initialize_perf_event_attr(void) +{ + pea_llc_miss.type = PERF_TYPE_HARDWARE; + pea_llc_miss.size = sizeof(struct perf_event_attr); + pea_llc_miss.read_format = PERF_FORMAT_GROUP; + pea_llc_miss.exclude_kernel = 1; + pea_llc_miss.exclude_hv = 1; + pea_llc_miss.exclude_idle = 1; + pea_llc_miss.exclude_callchain_kernel = 1; + pea_llc_miss.inherit = 1; + pea_llc_miss.exclude_guest = 1; + pea_llc_miss.disabled = 1; +} + +static void ioctl_perf_event_ioc_reset_enable(void) +{ + ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0); + ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0); +} + +static int perf_event_open_llc_miss(pid_t pid, int cpu_no) +{ + fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, + PERF_FLAG_FD_CLOEXEC); + if (fd_lm == -1) { + perror("Error opening leader"); + ctrlc_handler(0, NULL, NULL); + return -1; + } + + return 0; +} + +static void initialize_llc_perf(void) +{ + memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); + memset(&rf_cqm, 0, sizeof(struct read_format)); + + /* Initialize perf_event_attr structures for HW_CACHE_MISSES */ + initialize_perf_event_attr(); + + pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES; + + rf_cqm.nr = 1; +} + +static int reset_enable_llc_perf(pid_t pid, int cpu_no) +{ + int ret = 0; + + ret = perf_event_open_llc_miss(pid, cpu_no); + if (ret < 0) + return ret; + + /* Start counters to log values */ + ioctl_perf_event_ioc_reset_enable(); + + return 0; +} + +/* + * get_llc_perf: llc cache miss through perf events + * @llc_perf_miss: LLC miss counter that is filled on success + * + * Perf events like HW_CACHE_MISSES could be used to validate number of + * cache lines allocated. + * + * Return: =0 on success. <0 on failure. + */ +static int get_llc_perf(unsigned long *llc_perf_miss) +{ + __u64 total_misses; + int ret; + + /* Stop counters after one span to get miss rate */ + + ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); + + ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); + if (ret == -1) { + perror("Could not get llc misses through perf"); + return -1; + } + + total_misses = rf_cqm.values[0].value; + *llc_perf_miss = total_misses; + + return 0; +} + +/* + * Get LLC Occupancy as reported by RESCTRL FS + * For CMT, + * 1. If con_mon grp and mon grp given, then read from mon grp in + * con_mon grp + * 2. If only con_mon grp given, then read from con_mon grp + * 3. If both not given, then read from root con_mon grp + * For CAT, + * 1. If con_mon grp given, then read from it + * 2. If con_mon grp not given, then read from root con_mon grp + * + * Return: =0 on success. <0 on failure. + */ +static int get_llc_occu_resctrl(unsigned long *llc_occupancy) +{ + FILE *fp; + + fp = fopen(llc_occup_path, "r"); + if (!fp) { + perror("Failed to open results file"); + + return errno; + } + if (fscanf(fp, "%lu", llc_occupancy) <= 0) { + perror("Could not get llc occupancy"); + fclose(fp); + + return -1; + } + fclose(fp); + + return 0; +} + +/* + * print_results_cache: the cache results are stored in a file + * @filename: file that stores the results + * @bm_pid: child pid that runs benchmark + * @llc_value: perf miss value / + * llc occupancy value reported by resctrl FS + * + * Return: 0 on success. non-zero on failure. + */ +static int print_results_cache(char *filename, int bm_pid, + unsigned long llc_value) +{ + FILE *fp; + + if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) { + printf("Pid: %d \t LLC_value: %lu\n", bm_pid, + llc_value); + } else { + fp = fopen(filename, "a"); + if (!fp) { + perror("Cannot open results file"); + + return errno; + } + fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value); + fclose(fp); + } + + return 0; +} + +int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) +{ + unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0; + int ret; + + /* + * Measure cache miss from perf. + */ + if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) { + ret = get_llc_perf(&llc_perf_miss); + if (ret < 0) + return ret; + llc_value = llc_perf_miss; + } + + /* + * Measure llc occupancy from resctrl. + */ + if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) { + ret = get_llc_occu_resctrl(&llc_occu_resc); + if (ret < 0) + return ret; + llc_value = llc_occu_resc; + } + ret = print_results_cache(param->filename, bm_pid, llc_value); + if (ret) + return ret; + + return 0; +} + +/* + * cache_val: execute benchmark and measure LLC occupancy resctrl + * and perf cache miss for the benchmark + * @param: parameters passed to cache_val() + * @span: buffer size for the benchmark + * + * Return: 0 on success. non-zero on failure. + */ +int cat_val(struct resctrl_val_param *param, size_t span) +{ + int memflush = 1, operation = 0, ret = 0; + char *resctrl_val = param->resctrl_val; + pid_t bm_pid; + + if (strcmp(param->filename, "") == 0) + sprintf(param->filename, "stdio"); + + bm_pid = getpid(); + + /* Taskset benchmark to specified cpu */ + ret = taskset_benchmark(bm_pid, param->cpu_no); + if (ret) + return ret; + + /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/ + ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, + resctrl_val); + if (ret) + return ret; + + initialize_llc_perf(); + + /* Test runs until the callback setup() tells the test to stop. */ + while (1) { + ret = param->setup(param); + if (ret == END_OF_TESTS) { + ret = 0; + break; + } + if (ret < 0) + break; + ret = reset_enable_llc_perf(bm_pid, param->cpu_no); + if (ret) + break; + + if (run_fill_buf(span, memflush, operation, true)) { + fprintf(stderr, "Error-running fill buffer\n"); + ret = -1; + goto pe_close; + } + + sleep(1); + ret = measure_cache_vals(param, bm_pid); + if (ret) + goto pe_close; + } + + return ret; + +pe_close: + close(fd_lm); + return ret; +} + +/* + * show_cache_info: show cache test result information + * @sum_llc_val: sum of LLC cache result data + * @no_of_bits: number of bits + * @cache_span: cache span in bytes for CMT or in lines for CAT + * @max_diff: max difference + * @max_diff_percent: max difference percentage + * @num_of_runs: number of runs + * @platform: show test information on this platform + * @cmt: CMT test or CAT test + * + * Return: 0 on success. non-zero on failure. + */ +int show_cache_info(unsigned long sum_llc_val, int no_of_bits, + size_t cache_span, unsigned long max_diff, + unsigned long max_diff_percent, unsigned long num_of_runs, + bool platform, bool cmt) +{ + unsigned long avg_llc_val = 0; + float diff_percent; + long avg_diff = 0; + int ret; + + avg_llc_val = sum_llc_val / num_of_runs; + avg_diff = (long)abs(cache_span - avg_llc_val); + diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; + + ret = platform && abs((int)diff_percent) > max_diff_percent && + (cmt ? (abs(avg_diff) > max_diff) : true); + + ksft_print_msg("%s Check cache miss rate within %d%%\n", + ret ? "Fail:" : "Pass:", max_diff_percent); + + ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); + ksft_print_msg("Number of bits: %d\n", no_of_bits); + ksft_print_msg("Average LLC val: %lu\n", avg_llc_val); + ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines", + cache_span); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c new file mode 100644 index 0000000000..224ba8544d --- /dev/null +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cache Allocation Technology (CAT) test + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" +#include <unistd.h> + +#define RESULT_FILE_NAME1 "result_cat1" +#define RESULT_FILE_NAME2 "result_cat2" +#define NUM_OF_RUNS 5 +#define MAX_DIFF_PERCENT 4 +#define MAX_DIFF 1000000 + +/* + * Change schemata. Write schemata to specified + * con_mon grp, mon_grp in resctrl FS. + * Run 5 times in order to get average values. + */ +static int cat_setup(struct resctrl_val_param *p) +{ + char schemata[64]; + int ret = 0; + + /* Run NUM_OF_RUNS times */ + if (p->num_of_runs >= NUM_OF_RUNS) + return END_OF_TESTS; + + if (p->num_of_runs == 0) { + sprintf(schemata, "%lx", p->mask); + ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no, + p->resctrl_val); + } + p->num_of_runs++; + + return ret; +} + +static int check_results(struct resctrl_val_param *param, size_t span) +{ + char *token_array[8], temp[512]; + unsigned long sum_llc_perf_miss = 0; + int runs = 0, no_of_bits = 0; + FILE *fp; + + ksft_print_msg("Checking for pass/fail\n"); + fp = fopen(param->filename, "r"); + if (!fp) { + perror("# Cannot open file"); + + return errno; + } + + while (fgets(temp, sizeof(temp), fp)) { + char *token = strtok(temp, ":\t"); + int fields = 0; + + while (token) { + token_array[fields++] = token; + token = strtok(NULL, ":\t"); + } + /* + * Discard the first value which is inaccurate due to monitoring + * setup transition phase. + */ + if (runs > 0) + sum_llc_perf_miss += strtoul(token_array[3], NULL, 0); + runs++; + } + + fclose(fp); + no_of_bits = count_bits(param->mask); + + return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, + get_vendor() == ARCH_INTEL, false); +} + +void cat_test_cleanup(void) +{ + remove(RESULT_FILE_NAME1); + remove(RESULT_FILE_NAME2); +} + +int cat_perf_miss_val(int cpu_no, int n, char *cache_type) +{ + unsigned long l_mask, l_mask_1; + int ret, pipefd[2], sibling_cpu_no; + unsigned long cache_size = 0; + unsigned long long_mask; + char cbm_mask[256]; + int count_of_bits; + char pipe_message; + size_t span; + + /* Get default cbm mask for L3/L2 cache */ + ret = get_cbm_mask(cache_type, cbm_mask); + if (ret) + return ret; + + long_mask = strtoul(cbm_mask, NULL, 16); + + /* Get L3/L2 cache size */ + ret = get_cache_size(cpu_no, cache_type, &cache_size); + if (ret) + return ret; + ksft_print_msg("Cache size :%lu\n", cache_size); + + /* Get max number of bits from default-cabm mask */ + count_of_bits = count_bits(long_mask); + + if (!n) + n = count_of_bits / 2; + + if (n > count_of_bits - 1) { + ksft_print_msg("Invalid input value for no_of_bits n!\n"); + ksft_print_msg("Please enter value in range 1 to %d\n", + count_of_bits - 1); + return -1; + } + + /* Get core id from same socket for running another thread */ + sibling_cpu_no = get_core_sibling(cpu_no); + if (sibling_cpu_no < 0) + return -1; + + struct resctrl_val_param param = { + .resctrl_val = CAT_STR, + .cpu_no = cpu_no, + .setup = cat_setup, + }; + + l_mask = long_mask >> n; + l_mask_1 = ~l_mask & long_mask; + + /* Set param values for parent thread which will be allocated bitmask + * with (max_bits - n) bits + */ + span = cache_size * (count_of_bits - n) / count_of_bits; + strcpy(param.ctrlgrp, "c2"); + strcpy(param.mongrp, "m2"); + strcpy(param.filename, RESULT_FILE_NAME2); + param.mask = l_mask; + param.num_of_runs = 0; + + if (pipe(pipefd)) { + perror("# Unable to create pipe"); + return errno; + } + + fflush(stdout); + bm_pid = fork(); + + /* Set param values for child thread which will be allocated bitmask + * with n bits + */ + if (bm_pid == 0) { + param.mask = l_mask_1; + strcpy(param.ctrlgrp, "c1"); + strcpy(param.mongrp, "m1"); + span = cache_size * n / count_of_bits; + strcpy(param.filename, RESULT_FILE_NAME1); + param.num_of_runs = 0; + param.cpu_no = sibling_cpu_no; + } + + remove(param.filename); + + ret = cat_val(¶m, span); + if (ret == 0) + ret = check_results(¶m, span); + + if (bm_pid == 0) { + /* Tell parent that child is ready */ + close(pipefd[0]); + pipe_message = 1; + if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < + sizeof(pipe_message)) + /* + * Just print the error message. + * Let while(1) run and wait for itself to be killed. + */ + perror("# failed signaling parent process"); + + close(pipefd[1]); + while (1) + ; + } else { + /* Parent waits for child to be ready. */ + close(pipefd[1]); + pipe_message = 0; + while (pipe_message != 1) { + if (read(pipefd[0], &pipe_message, + sizeof(pipe_message)) < sizeof(pipe_message)) { + perror("# failed reading from child process"); + break; + } + } + close(pipefd[0]); + kill(bm_pid, SIGKILL); + } + + cat_test_cleanup(); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c new file mode 100644 index 0000000000..50bdbce9fb --- /dev/null +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cache Monitoring Technology (CMT) test + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" +#include <unistd.h> + +#define RESULT_FILE_NAME "result_cmt" +#define NUM_OF_RUNS 5 +#define MAX_DIFF 2000000 +#define MAX_DIFF_PERCENT 15 + +static int cmt_setup(struct resctrl_val_param *p) +{ + /* Run NUM_OF_RUNS times */ + if (p->num_of_runs >= NUM_OF_RUNS) + return END_OF_TESTS; + + p->num_of_runs++; + + return 0; +} + +static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits) +{ + char *token_array[8], temp[512]; + unsigned long sum_llc_occu_resc = 0; + int runs = 0; + FILE *fp; + + ksft_print_msg("Checking for pass/fail\n"); + fp = fopen(param->filename, "r"); + if (!fp) { + perror("# Error in opening file\n"); + + return errno; + } + + while (fgets(temp, sizeof(temp), fp)) { + char *token = strtok(temp, ":\t"); + int fields = 0; + + while (token) { + token_array[fields++] = token; + token = strtok(NULL, ":\t"); + } + + /* Field 3 is llc occ resc value */ + if (runs > 0) + sum_llc_occu_resc += strtoul(token_array[3], NULL, 0); + runs++; + } + fclose(fp); + + return show_cache_info(sum_llc_occu_resc, no_of_bits, span, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, + true, true); +} + +void cmt_test_cleanup(void) +{ + remove(RESULT_FILE_NAME); +} + +int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) +{ + const char * const *cmd = benchmark_cmd; + const char *new_cmd[BENCHMARK_ARGS]; + unsigned long cache_size = 0; + unsigned long long_mask; + char *span_str = NULL; + char cbm_mask[256]; + int count_of_bits; + size_t span; + int ret, i; + + ret = get_cbm_mask("L3", cbm_mask); + if (ret) + return ret; + + long_mask = strtoul(cbm_mask, NULL, 16); + + ret = get_cache_size(cpu_no, "L3", &cache_size); + if (ret) + return ret; + ksft_print_msg("Cache size :%lu\n", cache_size); + + count_of_bits = count_bits(long_mask); + + if (n < 1 || n > count_of_bits) { + ksft_print_msg("Invalid input value for numbr_of_bits n!\n"); + ksft_print_msg("Please enter value in range 1 to %d\n", count_of_bits); + return -1; + } + + struct resctrl_val_param param = { + .resctrl_val = CMT_STR, + .ctrlgrp = "c1", + .mongrp = "m1", + .cpu_no = cpu_no, + .filename = RESULT_FILE_NAME, + .mask = ~(long_mask << n) & long_mask, + .num_of_runs = 0, + .setup = cmt_setup, + }; + + span = cache_size * n / count_of_bits; + + if (strcmp(cmd[0], "fill_buf") == 0) { + /* Duplicate the command to be able to replace span in it */ + for (i = 0; benchmark_cmd[i]; i++) + new_cmd[i] = benchmark_cmd[i]; + new_cmd[i] = NULL; + + ret = asprintf(&span_str, "%zu", span); + if (ret < 0) + return -1; + new_cmd[1] = span_str; + cmd = new_cmd; + } + + remove(RESULT_FILE_NAME); + + ret = resctrl_val(cmd, ¶m); + if (ret) + goto out; + + ret = check_results(¶m, span, n); + +out: + cmt_test_cleanup(); + free(span_str); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/config b/tools/testing/selftests/resctrl/config new file mode 100644 index 0000000000..8d9f2deb56 --- /dev/null +++ b/tools/testing/selftests/resctrl/config @@ -0,0 +1,2 @@ +CONFIG_X86_CPU_RESCTRL=y +CONFIG_PROC_CPU_RESCTRL=y diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c new file mode 100644 index 0000000000..0d425f2658 --- /dev/null +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fill_buf benchmark + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <inttypes.h> +#include <string.h> + +#include "resctrl.h" + +#define CL_SIZE (64) +#define PAGE_SIZE (4 * 1024) +#define MB (1024 * 1024) + +static void sb(void) +{ +#if defined(__i386) || defined(__x86_64) + asm volatile("sfence\n\t" + : : : "memory"); +#endif +} + +static void cl_flush(void *p) +{ +#if defined(__i386) || defined(__x86_64) + asm volatile("clflush (%0)\n\t" + : : "r"(p) : "memory"); +#endif +} + +static void mem_flush(unsigned char *buf, size_t buf_size) +{ + unsigned char *cp = buf; + size_t i = 0; + + buf_size = buf_size / CL_SIZE; /* mem size in cache lines */ + + for (i = 0; i < buf_size; i++) + cl_flush(&cp[i * CL_SIZE]); + + sb(); +} + +static void *malloc_and_init_memory(size_t buf_size) +{ + void *p = NULL; + uint64_t *p64; + size_t s64; + int ret; + + ret = posix_memalign(&p, PAGE_SIZE, buf_size); + if (ret < 0) + return NULL; + + p64 = (uint64_t *)p; + s64 = buf_size / sizeof(uint64_t); + + while (s64 > 0) { + *p64 = (uint64_t)rand(); + p64 += (CL_SIZE / sizeof(uint64_t)); + s64 -= (CL_SIZE / sizeof(uint64_t)); + } + + return p; +} + +static int fill_one_span_read(unsigned char *buf, size_t buf_size) +{ + unsigned char *end_ptr = buf + buf_size; + unsigned char sum, *p; + + sum = 0; + p = buf; + while (p < end_ptr) { + sum += *p; + p += (CL_SIZE / 2); + } + + return sum; +} + +static void fill_one_span_write(unsigned char *buf, size_t buf_size) +{ + unsigned char *end_ptr = buf + buf_size; + unsigned char *p; + + p = buf; + while (p < end_ptr) { + *p = '1'; + p += (CL_SIZE / 2); + } +} + +static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) +{ + int ret = 0; + FILE *fp; + + while (1) { + ret = fill_one_span_read(buf, buf_size); + if (once) + break; + } + + /* Consume read result so that reading memory is not optimized out. */ + fp = fopen("/dev/null", "w"); + if (!fp) { + perror("Unable to write to /dev/null"); + return -1; + } + fprintf(fp, "Sum: %d ", ret); + fclose(fp); + + return 0; +} + +static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) +{ + while (1) { + fill_one_span_write(buf, buf_size); + if (once) + break; + } + + return 0; +} + +static int fill_cache(size_t buf_size, int memflush, int op, bool once) +{ + unsigned char *buf; + int ret; + + buf = malloc_and_init_memory(buf_size); + if (!buf) + return -1; + + /* Flush the memory before using to avoid "cache hot pages" effect */ + if (memflush) + mem_flush(buf, buf_size); + + if (op == 0) + ret = fill_cache_read(buf, buf_size, once); + else + ret = fill_cache_write(buf, buf_size, once); + + free(buf); + + if (ret) { + printf("\n Error in fill cache read/write...\n"); + return -1; + } + + + return 0; +} + +int run_fill_buf(size_t span, int memflush, int op, bool once) +{ + size_t cache_size = span; + int ret; + + ret = fill_cache(cache_size, memflush, op, once); + if (ret) { + printf("\n Error in fill cache\n"); + return -1; + } + + return 0; +} diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c new file mode 100644 index 0000000000..d3bf436834 --- /dev/null +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory Bandwidth Allocation (MBA) test + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" + +#define RESULT_FILE_NAME "result_mba" +#define NUM_OF_RUNS 5 +#define MAX_DIFF_PERCENT 8 +#define ALLOCATION_MAX 100 +#define ALLOCATION_MIN 10 +#define ALLOCATION_STEP 10 + +/* + * Change schemata percentage from 100 to 10%. Write schemata to specified + * con_mon grp, mon_grp in resctrl FS. + * For each allocation, run 5 times in order to get average values. + */ +static int mba_setup(struct resctrl_val_param *p) +{ + static int runs_per_allocation, allocation = 100; + char allocation_str[64]; + int ret; + + if (runs_per_allocation >= NUM_OF_RUNS) + runs_per_allocation = 0; + + /* Only set up schemata once every NUM_OF_RUNS of allocations */ + if (runs_per_allocation++ != 0) + return 0; + + if (allocation < ALLOCATION_MIN || allocation > ALLOCATION_MAX) + return END_OF_TESTS; + + sprintf(allocation_str, "%d", allocation); + + ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, + p->resctrl_val); + if (ret < 0) + return ret; + + allocation -= ALLOCATION_STEP; + + return 0; +} + +static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) +{ + int allocation, runs; + bool ret = false; + + ksft_print_msg("Results are displayed in (MB)\n"); + /* Memory bandwidth from 100% down to 10% */ + for (allocation = 0; allocation < ALLOCATION_MAX / ALLOCATION_STEP; + allocation++) { + unsigned long avg_bw_imc, avg_bw_resc; + unsigned long sum_bw_imc = 0, sum_bw_resc = 0; + int avg_diff_per; + float avg_diff; + + /* + * The first run is discarded due to inaccurate value from + * phase transition. + */ + for (runs = NUM_OF_RUNS * allocation + 1; + runs < NUM_OF_RUNS * allocation + NUM_OF_RUNS ; runs++) { + sum_bw_imc += bw_imc[runs]; + sum_bw_resc += bw_resc[runs]; + } + + avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1); + avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1); + avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; + avg_diff_per = (int)(avg_diff * 100); + + ksft_print_msg("%s Check MBA diff within %d%% for schemata %u\n", + avg_diff_per > MAX_DIFF_PERCENT ? + "Fail:" : "Pass:", + MAX_DIFF_PERCENT, + ALLOCATION_MAX - ALLOCATION_STEP * allocation); + + ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); + ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); + ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); + if (avg_diff_per > MAX_DIFF_PERCENT) + ret = true; + } + + ksft_print_msg("%s Check schemata change using MBA\n", + ret ? "Fail:" : "Pass:"); + if (ret) + ksft_print_msg("At least one test failed\n"); + + return ret; +} + +static int check_results(void) +{ + char *token_array[8], output[] = RESULT_FILE_NAME, temp[512]; + unsigned long bw_imc[1024], bw_resc[1024]; + int runs; + FILE *fp; + + fp = fopen(output, "r"); + if (!fp) { + perror(output); + + return errno; + } + + runs = 0; + while (fgets(temp, sizeof(temp), fp)) { + char *token = strtok(temp, ":\t"); + int fields = 0; + + while (token) { + token_array[fields++] = token; + token = strtok(NULL, ":\t"); + } + + /* Field 3 is perf imc value */ + bw_imc[runs] = strtoul(token_array[3], NULL, 0); + /* Field 5 is resctrl value */ + bw_resc[runs] = strtoul(token_array[5], NULL, 0); + runs++; + } + + fclose(fp); + + return show_mba_info(bw_imc, bw_resc); +} + +void mba_test_cleanup(void) +{ + remove(RESULT_FILE_NAME); +} + +int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd) +{ + struct resctrl_val_param param = { + .resctrl_val = MBA_STR, + .ctrlgrp = "c1", + .mongrp = "m1", + .cpu_no = cpu_no, + .filename = RESULT_FILE_NAME, + .bw_report = "reads", + .setup = mba_setup + }; + int ret; + + remove(RESULT_FILE_NAME); + + ret = resctrl_val(benchmark_cmd, ¶m); + if (ret) + goto out; + + ret = check_results(); + +out: + mba_test_cleanup(); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c new file mode 100644 index 0000000000..d3c0d30c67 --- /dev/null +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory Bandwidth Monitoring (MBM) test + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" + +#define RESULT_FILE_NAME "result_mbm" +#define MAX_DIFF_PERCENT 8 +#define NUM_OF_RUNS 5 + +static int +show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) +{ + unsigned long avg_bw_imc = 0, avg_bw_resc = 0; + unsigned long sum_bw_imc = 0, sum_bw_resc = 0; + int runs, ret, avg_diff_per; + float avg_diff = 0; + + /* + * Discard the first value which is inaccurate due to monitoring setup + * transition phase. + */ + for (runs = 1; runs < NUM_OF_RUNS ; runs++) { + sum_bw_imc += bw_imc[runs]; + sum_bw_resc += bw_resc[runs]; + } + + avg_bw_imc = sum_bw_imc / 4; + avg_bw_resc = sum_bw_resc / 4; + avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; + avg_diff_per = (int)(avg_diff * 100); + + ret = avg_diff_per > MAX_DIFF_PERCENT; + ksft_print_msg("%s Check MBM diff within %d%%\n", + ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT); + ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); + ksft_print_msg("Span (MB): %zu\n", span / MB); + ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); + ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); + + return ret; +} + +static int check_results(size_t span) +{ + unsigned long bw_imc[NUM_OF_RUNS], bw_resc[NUM_OF_RUNS]; + char temp[1024], *token_array[8]; + char output[] = RESULT_FILE_NAME; + int runs, ret; + FILE *fp; + + ksft_print_msg("Checking for pass/fail\n"); + + fp = fopen(output, "r"); + if (!fp) { + perror(output); + + return errno; + } + + runs = 0; + while (fgets(temp, sizeof(temp), fp)) { + char *token = strtok(temp, ":\t"); + int i = 0; + + while (token) { + token_array[i++] = token; + token = strtok(NULL, ":\t"); + } + + bw_resc[runs] = strtoul(token_array[5], NULL, 0); + bw_imc[runs] = strtoul(token_array[3], NULL, 0); + runs++; + } + + ret = show_bw_info(bw_imc, bw_resc, span); + + fclose(fp); + + return ret; +} + +static int mbm_setup(struct resctrl_val_param *p) +{ + int ret = 0; + + /* Run NUM_OF_RUNS times */ + if (p->num_of_runs >= NUM_OF_RUNS) + return END_OF_TESTS; + + /* Set up shemata with 100% allocation on the first run. */ + if (p->num_of_runs == 0) + ret = write_schemata(p->ctrlgrp, "100", p->cpu_no, + p->resctrl_val); + + p->num_of_runs++; + + return ret; +} + +void mbm_test_cleanup(void) +{ + remove(RESULT_FILE_NAME); +} + +int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd) +{ + struct resctrl_val_param param = { + .resctrl_val = MBM_STR, + .ctrlgrp = "c1", + .mongrp = "m1", + .cpu_no = cpu_no, + .filename = RESULT_FILE_NAME, + .bw_report = "reads", + .setup = mbm_setup + }; + int ret; + + remove(RESULT_FILE_NAME); + + ret = resctrl_val(benchmark_cmd, ¶m); + if (ret) + goto out; + + ret = check_results(DEFAULT_SPAN); + +out: + mbm_test_cleanup(); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h new file mode 100644 index 0000000000..8578a8b4e1 --- /dev/null +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef RESCTRL_H +#define RESCTRL_H +#include <stdio.h> +#include <math.h> +#include <errno.h> +#include <sched.h> +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <signal.h> +#include <dirent.h> +#include <stdbool.h> +#include <sys/stat.h> +#include <sys/ioctl.h> +#include <sys/mount.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/select.h> +#include <sys/time.h> +#include <sys/eventfd.h> +#include <asm/unistd.h> +#include <linux/perf_event.h> +#include "../kselftest.h" + +#define MB (1024 * 1024) +#define RESCTRL_PATH "/sys/fs/resctrl" +#define PHYS_ID_PATH "/sys/devices/system/cpu/cpu" +#define INFO_PATH "/sys/fs/resctrl/info" + +#define ARCH_INTEL 1 +#define ARCH_AMD 2 + +#define END_OF_TESTS 1 + +#define BENCHMARK_ARGS 64 + +#define DEFAULT_SPAN (250 * MB) + +#define PARENT_EXIT(err_msg) \ + do { \ + perror(err_msg); \ + kill(ppid, SIGKILL); \ + umount_resctrlfs(); \ + exit(EXIT_FAILURE); \ + } while (0) + +/* + * resctrl_val_param: resctrl test parameters + * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * @ctrlgrp: Name of the control monitor group (con_mon grp) + * @mongrp: Name of the monitor group (mon grp) + * @cpu_no: CPU number to which the benchmark would be binded + * @filename: Name of file to which the o/p should be written + * @bw_report: Bandwidth report type (reads vs writes) + * @setup: Call back function to setup test environment + */ +struct resctrl_val_param { + char *resctrl_val; + char ctrlgrp[64]; + char mongrp[64]; + int cpu_no; + char filename[64]; + char *bw_report; + unsigned long mask; + int num_of_runs; + int (*setup)(struct resctrl_val_param *param); +}; + +#define MBM_STR "mbm" +#define MBA_STR "mba" +#define CMT_STR "cmt" +#define CAT_STR "cat" + +extern pid_t bm_pid, ppid; + +extern char llc_occup_path[1024]; + +int get_vendor(void); +bool check_resctrlfs_support(void); +int filter_dmesg(void); +int get_resource_id(int cpu_no, int *resource_id); +int mount_resctrlfs(void); +int umount_resctrlfs(void); +int validate_bw_report_request(char *bw_report); +bool validate_resctrl_feature_request(const char *resource, const char *feature); +char *fgrep(FILE *inf, const char *str); +int taskset_benchmark(pid_t bm_pid, int cpu_no); +void run_benchmark(int signum, siginfo_t *info, void *ucontext); +int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, + char *resctrl_val); +int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, + char *resctrl_val); +int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, + int group_fd, unsigned long flags); +int run_fill_buf(size_t span, int memflush, int op, bool once); +int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); +int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); +void tests_cleanup(void); +void mbm_test_cleanup(void); +int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); +void mba_test_cleanup(void); +int get_cbm_mask(char *cache_type, char *cbm_mask); +int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); +void ctrlc_handler(int signum, siginfo_t *info, void *ptr); +int signal_handler_register(void); +void signal_handler_unregister(void); +int cat_val(struct resctrl_val_param *param, size_t span); +void cat_test_cleanup(void); +int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); +int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); +unsigned int count_bits(unsigned long n); +void cmt_test_cleanup(void); +int get_core_sibling(int cpu_no); +int measure_cache_vals(struct resctrl_val_param *param, int bm_pid); +int show_cache_info(unsigned long sum_llc_val, int no_of_bits, + size_t cache_span, unsigned long max_diff, + unsigned long max_diff_percent, unsigned long num_of_runs, + bool platform, bool cmt); + +#endif /* RESCTRL_H */ diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c new file mode 100644 index 0000000000..31373b69e6 --- /dev/null +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resctrl tests + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" + +static int detect_vendor(void) +{ + FILE *inf = fopen("/proc/cpuinfo", "r"); + int vendor_id = 0; + char *s = NULL; + char *res; + + if (!inf) + return vendor_id; + + res = fgrep(inf, "vendor_id"); + + if (res) + s = strchr(res, ':'); + + if (s && !strcmp(s, ": GenuineIntel\n")) + vendor_id = ARCH_INTEL; + else if (s && !strcmp(s, ": AuthenticAMD\n")) + vendor_id = ARCH_AMD; + + fclose(inf); + free(res); + return vendor_id; +} + +int get_vendor(void) +{ + static int vendor = -1; + + if (vendor == -1) + vendor = detect_vendor(); + if (vendor == 0) + ksft_print_msg("Can not get vendor info...\n"); + + return vendor; +} + +static void cmd_help(void) +{ + printf("usage: resctrl_tests [-h] [-b \"benchmark_cmd [options]\"] [-t test list] [-n no_of_bits]\n"); + printf("\t-b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT\n"); + printf("\t default benchmark is builtin fill_buf\n"); + printf("\t-t test list: run tests specified in the test list, "); + printf("e.g. -t mbm,mba,cmt,cat\n"); + printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n"); + printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n"); + printf("\t-h: help\n"); +} + +void tests_cleanup(void) +{ + mbm_test_cleanup(); + mba_test_cleanup(); + cmt_test_cleanup(); + cat_test_cleanup(); +} + +static int test_prepare(void) +{ + int res; + + res = signal_handler_register(); + if (res) { + ksft_print_msg("Failed to register signal handler\n"); + return res; + } + + res = mount_resctrlfs(); + if (res) { + signal_handler_unregister(); + ksft_print_msg("Failed to mount resctrl FS\n"); + return res; + } + return 0; +} + +static void test_cleanup(void) +{ + umount_resctrlfs(); + signal_handler_unregister(); +} + +static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no) +{ + int res; + + ksft_print_msg("Starting MBM BW change ...\n"); + + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + return; + } + + if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") || + !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || + (get_vendor() != ARCH_INTEL)) { + ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); + goto cleanup; + } + + res = mbm_bw_change(cpu_no, benchmark_cmd); + ksft_test_result(!res, "MBM: bw change\n"); + if ((get_vendor() == ARCH_INTEL) && res) + ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + +cleanup: + test_cleanup(); +} + +static void run_mba_test(const char * const *benchmark_cmd, int cpu_no) +{ + int res; + + ksft_print_msg("Starting MBA Schemata change ...\n"); + + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + return; + } + + if (!validate_resctrl_feature_request("MB", NULL) || + !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || + (get_vendor() != ARCH_INTEL)) { + ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); + goto cleanup; + } + + res = mba_schemata_change(cpu_no, benchmark_cmd); + ksft_test_result(!res, "MBA: schemata change\n"); + +cleanup: + test_cleanup(); +} + +static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no) +{ + int res; + + ksft_print_msg("Starting CMT test ...\n"); + + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + return; + } + + if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") || + !validate_resctrl_feature_request("L3", NULL)) { + ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n"); + goto cleanup; + } + + res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd); + ksft_test_result(!res, "CMT: test\n"); + if ((get_vendor() == ARCH_INTEL) && res) + ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + +cleanup: + test_cleanup(); +} + +static void run_cat_test(int cpu_no, int no_of_bits) +{ + int res; + + ksft_print_msg("Starting CAT test ...\n"); + + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + return; + } + + if (!validate_resctrl_feature_request("L3", NULL)) { + ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n"); + goto cleanup; + } + + res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); + ksft_test_result(!res, "CAT: test\n"); + +cleanup: + test_cleanup(); +} + +int main(int argc, char **argv) +{ + bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true; + int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0; + const char *benchmark_cmd[BENCHMARK_ARGS]; + int ben_ind, ben_count, tests = 0; + char *span_str = NULL; + bool cat_test = true; + int ret; + + for (i = 0; i < argc; i++) { + if (strcmp(argv[i], "-b") == 0) { + ben_ind = i + 1; + ben_count = argc - ben_ind; + argc_new = ben_ind - 1; + has_ben = true; + break; + } + } + + while ((c = getopt(argc_new, argv, "ht:b:n:p:")) != -1) { + char *token; + + switch (c) { + case 't': + token = strtok(optarg, ","); + + mbm_test = false; + mba_test = false; + cmt_test = false; + cat_test = false; + while (token) { + if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) { + mbm_test = true; + tests++; + } else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) { + mba_test = true; + tests++; + } else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) { + cmt_test = true; + tests++; + } else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) { + cat_test = true; + tests++; + } else { + printf("invalid argument\n"); + + return -1; + } + token = strtok(NULL, ","); + } + break; + case 'p': + cpu_no = atoi(optarg); + break; + case 'n': + no_of_bits = atoi(optarg); + if (no_of_bits <= 0) { + printf("Bail out! invalid argument for no_of_bits\n"); + return -1; + } + break; + case 'h': + cmd_help(); + + return 0; + default: + printf("invalid argument\n"); + + return -1; + } + } + + ksft_print_header(); + + /* + * Typically we need root privileges, because: + * 1. We write to resctrl FS + * 2. We execute perf commands + */ + if (geteuid() != 0) + return ksft_exit_skip("Not running as root. Skipping...\n"); + + if (has_ben) { + if (argc - ben_ind >= BENCHMARK_ARGS) + ksft_exit_fail_msg("Too long benchmark command.\n"); + + /* Extract benchmark command from command line. */ + for (i = 0; i < argc - ben_ind; i++) + benchmark_cmd[i] = argv[i + ben_ind]; + benchmark_cmd[ben_count] = NULL; + } else { + /* If no benchmark is given by "-b" argument, use fill_buf. */ + benchmark_cmd[0] = "fill_buf"; + ret = asprintf(&span_str, "%u", DEFAULT_SPAN); + if (ret < 0) + ksft_exit_fail_msg("Out of memory!\n"); + benchmark_cmd[1] = span_str; + benchmark_cmd[2] = "1"; + benchmark_cmd[3] = "0"; + benchmark_cmd[4] = "false"; + benchmark_cmd[5] = NULL; + } + + if (!check_resctrlfs_support()) + return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n"); + + if (umount_resctrlfs()) + return ksft_exit_skip("resctrl FS unmount failed.\n"); + + filter_dmesg(); + + ksft_set_plan(tests ? : 4); + + if (mbm_test) + run_mbm_test(benchmark_cmd, cpu_no); + + if (mba_test) + run_mba_test(benchmark_cmd, cpu_no); + + if (cmt_test) + run_cmt_test(benchmark_cmd, cpu_no); + + if (cat_test) + run_cat_test(cpu_no, no_of_bits); + + free(span_str); + ksft_finished(); +} diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c new file mode 100644 index 0000000000..b8ca6fa40b --- /dev/null +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -0,0 +1,793 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory bandwidth monitoring and allocation library + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include "resctrl.h" + +#define UNCORE_IMC "uncore_imc" +#define READ_FILE_NAME "events/cas_count_read" +#define WRITE_FILE_NAME "events/cas_count_write" +#define DYN_PMU_PATH "/sys/bus/event_source/devices" +#define SCALE 0.00006103515625 +#define MAX_IMCS 20 +#define MAX_TOKENS 5 +#define READ 0 +#define WRITE 1 +#define CON_MON_MBM_LOCAL_BYTES_PATH \ + "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes" + +#define CON_MBM_LOCAL_BYTES_PATH \ + "%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes" + +#define MON_MBM_LOCAL_BYTES_PATH \ + "%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes" + +#define MBM_LOCAL_BYTES_PATH \ + "%s/mon_data/mon_L3_%02d/mbm_local_bytes" + +#define CON_MON_LCC_OCCUP_PATH \ + "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy" + +#define CON_LCC_OCCUP_PATH \ + "%s/%s/mon_data/mon_L3_%02d/llc_occupancy" + +#define MON_LCC_OCCUP_PATH \ + "%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy" + +#define LCC_OCCUP_PATH \ + "%s/mon_data/mon_L3_%02d/llc_occupancy" + +struct membw_read_format { + __u64 value; /* The value of the event */ + __u64 time_enabled; /* if PERF_FORMAT_TOTAL_TIME_ENABLED */ + __u64 time_running; /* if PERF_FORMAT_TOTAL_TIME_RUNNING */ + __u64 id; /* if PERF_FORMAT_ID */ +}; + +struct imc_counter_config { + __u32 type; + __u64 event; + __u64 umask; + struct perf_event_attr pe; + struct membw_read_format return_value; + int fd; +}; + +static char mbm_total_path[1024]; +static int imcs; +static struct imc_counter_config imc_counters_config[MAX_IMCS][2]; + +void membw_initialize_perf_event_attr(int i, int j) +{ + memset(&imc_counters_config[i][j].pe, 0, + sizeof(struct perf_event_attr)); + imc_counters_config[i][j].pe.type = imc_counters_config[i][j].type; + imc_counters_config[i][j].pe.size = sizeof(struct perf_event_attr); + imc_counters_config[i][j].pe.disabled = 1; + imc_counters_config[i][j].pe.inherit = 1; + imc_counters_config[i][j].pe.exclude_guest = 0; + imc_counters_config[i][j].pe.config = + imc_counters_config[i][j].umask << 8 | + imc_counters_config[i][j].event; + imc_counters_config[i][j].pe.sample_type = PERF_SAMPLE_IDENTIFIER; + imc_counters_config[i][j].pe.read_format = + PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; +} + +void membw_ioctl_perf_event_ioc_reset_enable(int i, int j) +{ + ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0); + ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0); +} + +void membw_ioctl_perf_event_ioc_disable(int i, int j) +{ + ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0); +} + +/* + * get_event_and_umask: Parse config into event and umask + * @cas_count_cfg: Config + * @count: iMC number + * @op: Operation (read/write) + */ +void get_event_and_umask(char *cas_count_cfg, int count, bool op) +{ + char *token[MAX_TOKENS]; + int i = 0; + + strcat(cas_count_cfg, ","); + token[0] = strtok(cas_count_cfg, "=,"); + + for (i = 1; i < MAX_TOKENS; i++) + token[i] = strtok(NULL, "=,"); + + for (i = 0; i < MAX_TOKENS; i++) { + if (!token[i]) + break; + if (strcmp(token[i], "event") == 0) { + if (op == READ) + imc_counters_config[count][READ].event = + strtol(token[i + 1], NULL, 16); + else + imc_counters_config[count][WRITE].event = + strtol(token[i + 1], NULL, 16); + } + if (strcmp(token[i], "umask") == 0) { + if (op == READ) + imc_counters_config[count][READ].umask = + strtol(token[i + 1], NULL, 16); + else + imc_counters_config[count][WRITE].umask = + strtol(token[i + 1], NULL, 16); + } + } +} + +static int open_perf_event(int i, int cpu_no, int j) +{ + imc_counters_config[i][j].fd = + perf_event_open(&imc_counters_config[i][j].pe, -1, cpu_no, -1, + PERF_FLAG_FD_CLOEXEC); + + if (imc_counters_config[i][j].fd == -1) { + fprintf(stderr, "Error opening leader %llx\n", + imc_counters_config[i][j].pe.config); + + return -1; + } + + return 0; +} + +/* Get type and config (read and write) of an iMC counter */ +static int read_from_imc_dir(char *imc_dir, int count) +{ + char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024]; + FILE *fp; + + /* Get type of iMC counter */ + sprintf(imc_counter_type, "%s%s", imc_dir, "type"); + fp = fopen(imc_counter_type, "r"); + if (!fp) { + perror("Failed to open imc counter type file"); + + return -1; + } + if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) { + perror("Could not get imc type"); + fclose(fp); + + return -1; + } + fclose(fp); + + imc_counters_config[count][WRITE].type = + imc_counters_config[count][READ].type; + + /* Get read config */ + sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME); + fp = fopen(imc_counter_cfg, "r"); + if (!fp) { + perror("Failed to open imc config file"); + + return -1; + } + if (fscanf(fp, "%s", cas_count_cfg) <= 0) { + perror("Could not get imc cas count read"); + fclose(fp); + + return -1; + } + fclose(fp); + + get_event_and_umask(cas_count_cfg, count, READ); + + /* Get write config */ + sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME); + fp = fopen(imc_counter_cfg, "r"); + if (!fp) { + perror("Failed to open imc config file"); + + return -1; + } + if (fscanf(fp, "%s", cas_count_cfg) <= 0) { + perror("Could not get imc cas count write"); + fclose(fp); + + return -1; + } + fclose(fp); + + get_event_and_umask(cas_count_cfg, count, WRITE); + + return 0; +} + +/* + * A system can have 'n' number of iMC (Integrated Memory Controller) + * counters, get that 'n'. For each iMC counter get it's type and config. + * Also, each counter has two configs, one for read and the other for write. + * A config again has two parts, event and umask. + * Enumerate all these details into an array of structures. + * + * Return: >= 0 on success. < 0 on failure. + */ +static int num_of_imcs(void) +{ + char imc_dir[512], *temp; + unsigned int count = 0; + struct dirent *ep; + int ret; + DIR *dp; + + dp = opendir(DYN_PMU_PATH); + if (dp) { + while ((ep = readdir(dp))) { + temp = strstr(ep->d_name, UNCORE_IMC); + if (!temp) + continue; + + /* + * imc counters are named as "uncore_imc_<n>", hence + * increment the pointer to point to <n>. Note that + * sizeof(UNCORE_IMC) would count for null character as + * well and hence the last underscore character in + * uncore_imc'_' need not be counted. + */ + temp = temp + sizeof(UNCORE_IMC); + + /* + * Some directories under "DYN_PMU_PATH" could have + * names like "uncore_imc_free_running", hence, check if + * first character is a numerical digit or not. + */ + if (temp[0] >= '0' && temp[0] <= '9') { + sprintf(imc_dir, "%s/%s/", DYN_PMU_PATH, + ep->d_name); + ret = read_from_imc_dir(imc_dir, count); + if (ret) { + closedir(dp); + + return ret; + } + count++; + } + } + closedir(dp); + if (count == 0) { + perror("Unable find iMC counters!\n"); + + return -1; + } + } else { + perror("Unable to open PMU directory!\n"); + + return -1; + } + + return count; +} + +static int initialize_mem_bw_imc(void) +{ + int imc, j; + + imcs = num_of_imcs(); + if (imcs <= 0) + return imcs; + + /* Initialize perf_event_attr structures for all iMC's */ + for (imc = 0; imc < imcs; imc++) { + for (j = 0; j < 2; j++) + membw_initialize_perf_event_attr(imc, j); + } + + return 0; +} + +/* + * get_mem_bw_imc: Memory band width as reported by iMC counters + * @cpu_no: CPU number that the benchmark PID is binded to + * @bw_report: Bandwidth report type (reads, writes) + * + * Memory B/W utilized by a process on a socket can be calculated using + * iMC counters. Perf events are used to read these counters. + * + * Return: = 0 on success. < 0 on failure. + */ +static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc) +{ + float reads, writes, of_mul_read, of_mul_write; + int imc, j, ret; + + /* Start all iMC counters to log values (both read and write) */ + reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1; + for (imc = 0; imc < imcs; imc++) { + for (j = 0; j < 2; j++) { + ret = open_perf_event(imc, cpu_no, j); + if (ret) + return -1; + } + for (j = 0; j < 2; j++) + membw_ioctl_perf_event_ioc_reset_enable(imc, j); + } + + sleep(1); + + /* Stop counters after a second to get results (both read and write) */ + for (imc = 0; imc < imcs; imc++) { + for (j = 0; j < 2; j++) + membw_ioctl_perf_event_ioc_disable(imc, j); + } + + /* + * Get results which are stored in struct type imc_counter_config + * Take over flow into consideration before calculating total b/w + */ + for (imc = 0; imc < imcs; imc++) { + struct imc_counter_config *r = + &imc_counters_config[imc][READ]; + struct imc_counter_config *w = + &imc_counters_config[imc][WRITE]; + + if (read(r->fd, &r->return_value, + sizeof(struct membw_read_format)) == -1) { + perror("Couldn't get read b/w through iMC"); + + return -1; + } + + if (read(w->fd, &w->return_value, + sizeof(struct membw_read_format)) == -1) { + perror("Couldn't get write bw through iMC"); + + return -1; + } + + __u64 r_time_enabled = r->return_value.time_enabled; + __u64 r_time_running = r->return_value.time_running; + + if (r_time_enabled != r_time_running) + of_mul_read = (float)r_time_enabled / + (float)r_time_running; + + __u64 w_time_enabled = w->return_value.time_enabled; + __u64 w_time_running = w->return_value.time_running; + + if (w_time_enabled != w_time_running) + of_mul_write = (float)w_time_enabled / + (float)w_time_running; + reads += r->return_value.value * of_mul_read * SCALE; + writes += w->return_value.value * of_mul_write * SCALE; + } + + for (imc = 0; imc < imcs; imc++) { + close(imc_counters_config[imc][READ].fd); + close(imc_counters_config[imc][WRITE].fd); + } + + if (strcmp(bw_report, "reads") == 0) { + *bw_imc = reads; + return 0; + } + + if (strcmp(bw_report, "writes") == 0) { + *bw_imc = writes; + return 0; + } + + *bw_imc = reads + writes; + return 0; +} + +void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id) +{ + if (ctrlgrp && mongrp) + sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH, + RESCTRL_PATH, ctrlgrp, mongrp, resource_id); + else if (!ctrlgrp && mongrp) + sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, + mongrp, resource_id); + else if (ctrlgrp && !mongrp) + sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, + ctrlgrp, resource_id); + else if (!ctrlgrp && !mongrp) + sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, + resource_id); +} + +/* + * initialize_mem_bw_resctrl: Appropriately populate "mbm_total_path" + * @ctrlgrp: Name of the control monitor group (con_mon grp) + * @mongrp: Name of the monitor group (mon grp) + * @cpu_no: CPU number that the benchmark PID is binded to + * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + */ +static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp, + int cpu_no, char *resctrl_val) +{ + int resource_id; + + if (get_resource_id(cpu_no, &resource_id) < 0) { + perror("Could not get resource_id"); + return; + } + + if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) + set_mbm_path(ctrlgrp, mongrp, resource_id); + + if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { + if (ctrlgrp) + sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, + RESCTRL_PATH, ctrlgrp, resource_id); + else + sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, + RESCTRL_PATH, resource_id); + } +} + +/* + * Get MBM Local bytes as reported by resctrl FS + * For MBM, + * 1. If con_mon grp and mon grp are given, then read from con_mon grp's mon grp + * 2. If only con_mon grp is given, then read from con_mon grp + * 3. If both are not given, then read from root con_mon grp + * For MBA, + * 1. If con_mon grp is given, then read from it + * 2. If con_mon grp is not given, then read from root con_mon grp + */ +static int get_mem_bw_resctrl(unsigned long *mbm_total) +{ + FILE *fp; + + fp = fopen(mbm_total_path, "r"); + if (!fp) { + perror("Failed to open total bw file"); + + return -1; + } + if (fscanf(fp, "%lu", mbm_total) <= 0) { + perror("Could not get mbm local bytes"); + fclose(fp); + + return -1; + } + fclose(fp); + + return 0; +} + +pid_t bm_pid, ppid; + +void ctrlc_handler(int signum, siginfo_t *info, void *ptr) +{ + /* Only kill child after bm_pid is set after fork() */ + if (bm_pid) + kill(bm_pid, SIGKILL); + umount_resctrlfs(); + tests_cleanup(); + ksft_print_msg("Ending\n\n"); + + exit(EXIT_SUCCESS); +} + +/* + * Register CTRL-C handler for parent, as it has to kill + * child process before exiting. + */ +int signal_handler_register(void) +{ + struct sigaction sigact = {}; + int ret = 0; + + bm_pid = 0; + + sigact.sa_sigaction = ctrlc_handler; + sigemptyset(&sigact.sa_mask); + sigact.sa_flags = SA_SIGINFO; + if (sigaction(SIGINT, &sigact, NULL) || + sigaction(SIGTERM, &sigact, NULL) || + sigaction(SIGHUP, &sigact, NULL)) { + perror("# sigaction"); + ret = -1; + } + return ret; +} + +/* + * Reset signal handler to SIG_DFL. + * Non-Value return because the caller should keep + * the error code of other path even if sigaction fails. + */ +void signal_handler_unregister(void) +{ + struct sigaction sigact = {}; + + sigact.sa_handler = SIG_DFL; + sigemptyset(&sigact.sa_mask); + if (sigaction(SIGINT, &sigact, NULL) || + sigaction(SIGTERM, &sigact, NULL) || + sigaction(SIGHUP, &sigact, NULL)) { + perror("# sigaction"); + } +} + +/* + * print_results_bw: the memory bandwidth results are stored in a file + * @filename: file that stores the results + * @bm_pid: child pid that runs benchmark + * @bw_imc: perf imc counter value + * @bw_resc: memory bandwidth value + * + * Return: 0 on success. non-zero on failure. + */ +static int print_results_bw(char *filename, int bm_pid, float bw_imc, + unsigned long bw_resc) +{ + unsigned long diff = fabs(bw_imc - bw_resc); + FILE *fp; + + if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) { + printf("Pid: %d \t Mem_BW_iMC: %f \t ", bm_pid, bw_imc); + printf("Mem_BW_resc: %lu \t Difference: %lu\n", bw_resc, diff); + } else { + fp = fopen(filename, "a"); + if (!fp) { + perror("Cannot open results file"); + + return errno; + } + if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n", + bm_pid, bw_imc, bw_resc, diff) <= 0) { + fclose(fp); + perror("Could not log results."); + + return errno; + } + fclose(fp); + } + + return 0; +} + +static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num) +{ + if (strlen(ctrlgrp) && strlen(mongrp)) + sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH, + ctrlgrp, mongrp, sock_num); + else if (!strlen(ctrlgrp) && strlen(mongrp)) + sprintf(llc_occup_path, MON_LCC_OCCUP_PATH, RESCTRL_PATH, + mongrp, sock_num); + else if (strlen(ctrlgrp) && !strlen(mongrp)) + sprintf(llc_occup_path, CON_LCC_OCCUP_PATH, RESCTRL_PATH, + ctrlgrp, sock_num); + else if (!strlen(ctrlgrp) && !strlen(mongrp)) + sprintf(llc_occup_path, LCC_OCCUP_PATH, RESCTRL_PATH, sock_num); +} + +/* + * initialize_llc_occu_resctrl: Appropriately populate "llc_occup_path" + * @ctrlgrp: Name of the control monitor group (con_mon grp) + * @mongrp: Name of the monitor group (mon grp) + * @cpu_no: CPU number that the benchmark PID is binded to + * @resctrl_val: Resctrl feature (Eg: cat, cmt.. etc) + */ +static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, + int cpu_no, char *resctrl_val) +{ + int resource_id; + + if (get_resource_id(cpu_no, &resource_id) < 0) { + perror("# Unable to resource_id"); + return; + } + + if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) + set_cmt_path(ctrlgrp, mongrp, resource_id); +} + +static int +measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start) +{ + unsigned long bw_resc, bw_resc_end; + float bw_imc; + int ret; + + /* + * Measure memory bandwidth from resctrl and from + * another source which is perf imc value or could + * be something else if perf imc event is not available. + * Compare the two values to validate resctrl value. + * It takes 1sec to measure the data. + */ + ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc); + if (ret < 0) + return ret; + + ret = get_mem_bw_resctrl(&bw_resc_end); + if (ret < 0) + return ret; + + bw_resc = (bw_resc_end - *bw_resc_start) / MB; + ret = print_results_bw(param->filename, bm_pid, bw_imc, bw_resc); + if (ret) + return ret; + + *bw_resc_start = bw_resc_end; + + return 0; +} + +/* + * resctrl_val: execute benchmark and measure memory bandwidth on + * the benchmark + * @benchmark_cmd: benchmark command and its arguments + * @param: parameters passed to resctrl_val() + * + * Return: 0 on success. non-zero on failure. + */ +int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param) +{ + char *resctrl_val = param->resctrl_val; + unsigned long bw_resc_start = 0; + struct sigaction sigact; + int ret = 0, pipefd[2]; + char pipe_message = 0; + union sigval value; + + if (strcmp(param->filename, "") == 0) + sprintf(param->filename, "stdio"); + + if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || + !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) { + ret = validate_bw_report_request(param->bw_report); + if (ret) + return ret; + } + + /* + * If benchmark wasn't successfully started by child, then child should + * kill parent, so save parent's pid + */ + ppid = getpid(); + + if (pipe(pipefd)) { + perror("# Unable to create pipe"); + + return -1; + } + + /* + * Fork to start benchmark, save child's pid so that it can be killed + * when needed + */ + fflush(stdout); + bm_pid = fork(); + if (bm_pid == -1) { + perror("# Unable to fork"); + + return -1; + } + + if (bm_pid == 0) { + /* + * Mask all signals except SIGUSR1, parent uses SIGUSR1 to + * start benchmark + */ + sigfillset(&sigact.sa_mask); + sigdelset(&sigact.sa_mask, SIGUSR1); + + sigact.sa_sigaction = run_benchmark; + sigact.sa_flags = SA_SIGINFO; + + /* Register for "SIGUSR1" signal from parent */ + if (sigaction(SIGUSR1, &sigact, NULL)) + PARENT_EXIT("Can't register child for signal"); + + /* Tell parent that child is ready */ + close(pipefd[0]); + pipe_message = 1; + if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < + sizeof(pipe_message)) { + perror("# failed signaling parent process"); + close(pipefd[1]); + return -1; + } + close(pipefd[1]); + + /* Suspend child until delivery of "SIGUSR1" from parent */ + sigsuspend(&sigact.sa_mask); + + PARENT_EXIT("Child is done"); + } + + ksft_print_msg("Benchmark PID: %d\n", bm_pid); + + /* + * The cast removes constness but nothing mutates benchmark_cmd within + * the context of this process. At the receiving process, it becomes + * argv, which is mutable, on exec() but that's after fork() so it + * doesn't matter for the process running the tests. + */ + value.sival_ptr = (void *)benchmark_cmd; + + /* Taskset benchmark to specified cpu */ + ret = taskset_benchmark(bm_pid, param->cpu_no); + if (ret) + goto out; + + /* Write benchmark to specified control&monitoring grp in resctrl FS */ + ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, + resctrl_val); + if (ret) + goto out; + + if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || + !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { + ret = initialize_mem_bw_imc(); + if (ret) + goto out; + + initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp, + param->cpu_no, resctrl_val); + } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) + initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp, + param->cpu_no, resctrl_val); + + /* Parent waits for child to be ready. */ + close(pipefd[1]); + while (pipe_message != 1) { + if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) < + sizeof(pipe_message)) { + perror("# failed reading message from child process"); + close(pipefd[0]); + goto out; + } + } + close(pipefd[0]); + + /* Signal child to start benchmark */ + if (sigqueue(bm_pid, SIGUSR1, value) == -1) { + perror("# sigqueue SIGUSR1 to child"); + ret = errno; + goto out; + } + + /* Give benchmark enough time to fully run */ + sleep(1); + + /* Test runs until the callback setup() tells the test to stop. */ + while (1) { + ret = param->setup(param); + if (ret == END_OF_TESTS) { + ret = 0; + break; + } + if (ret < 0) + break; + + if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || + !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { + ret = measure_vals(param, &bw_resc_start); + if (ret) + break; + } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { + sleep(1); + ret = measure_cache_vals(param, bm_pid); + if (ret) + break; + } + } + +out: + kill(bm_pid, SIGKILL); + + return ret; +} diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c new file mode 100644 index 0000000000..3a8111362d --- /dev/null +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -0,0 +1,732 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic resctrl file system operations + * + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>, + * Fenghua Yu <fenghua.yu@intel.com> + */ +#include <limits.h> + +#include "resctrl.h" + +static int find_resctrl_mount(char *buffer) +{ + FILE *mounts; + char line[256], *fs, *mntpoint; + + mounts = fopen("/proc/mounts", "r"); + if (!mounts) { + perror("/proc/mounts"); + return -ENXIO; + } + while (!feof(mounts)) { + if (!fgets(line, 256, mounts)) + break; + fs = strtok(line, " \t"); + if (!fs) + continue; + mntpoint = strtok(NULL, " \t"); + if (!mntpoint) + continue; + fs = strtok(NULL, " \t"); + if (!fs) + continue; + if (strcmp(fs, "resctrl")) + continue; + + fclose(mounts); + if (buffer) + strncpy(buffer, mntpoint, 256); + + return 0; + } + + fclose(mounts); + + return -ENOENT; +} + +/* + * mount_resctrlfs - Mount resctrl FS at /sys/fs/resctrl + * + * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid + * pre-existing settings interfering with the test results. + * + * Return: 0 on success, non-zero on failure + */ +int mount_resctrlfs(void) +{ + int ret; + + ret = find_resctrl_mount(NULL); + if (ret != -ENOENT) + return -1; + + ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH); + ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL); + if (ret) + perror("# mount"); + + return ret; +} + +int umount_resctrlfs(void) +{ + char mountpoint[256]; + int ret; + + ret = find_resctrl_mount(mountpoint); + if (ret == -ENOENT) + return 0; + if (ret) + return ret; + + if (umount(mountpoint)) { + perror("# Unable to umount resctrl"); + + return errno; + } + + return 0; +} + +/* + * get_resource_id - Get socket number/l3 id for a specified CPU + * @cpu_no: CPU number + * @resource_id: Socket number or l3_id + * + * Return: >= 0 on success, < 0 on failure. + */ +int get_resource_id(int cpu_no, int *resource_id) +{ + char phys_pkg_path[1024]; + FILE *fp; + + if (get_vendor() == ARCH_AMD) + sprintf(phys_pkg_path, "%s%d/cache/index3/id", + PHYS_ID_PATH, cpu_no); + else + sprintf(phys_pkg_path, "%s%d/topology/physical_package_id", + PHYS_ID_PATH, cpu_no); + + fp = fopen(phys_pkg_path, "r"); + if (!fp) { + perror("Failed to open physical_package_id"); + + return -1; + } + if (fscanf(fp, "%d", resource_id) <= 0) { + perror("Could not get socket number or l3 id"); + fclose(fp); + + return -1; + } + fclose(fp); + + return 0; +} + +/* + * get_cache_size - Get cache size for a specified CPU + * @cpu_no: CPU number + * @cache_type: Cache level L2/L3 + * @cache_size: pointer to cache_size + * + * Return: = 0 on success, < 0 on failure. + */ +int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) +{ + char cache_path[1024], cache_str[64]; + int length, i, cache_num; + FILE *fp; + + if (!strcmp(cache_type, "L3")) { + cache_num = 3; + } else if (!strcmp(cache_type, "L2")) { + cache_num = 2; + } else { + perror("Invalid cache level"); + return -1; + } + + sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size", + cpu_no, cache_num); + fp = fopen(cache_path, "r"); + if (!fp) { + perror("Failed to open cache size"); + + return -1; + } + if (fscanf(fp, "%s", cache_str) <= 0) { + perror("Could not get cache_size"); + fclose(fp); + + return -1; + } + fclose(fp); + + length = (int)strlen(cache_str); + + *cache_size = 0; + + for (i = 0; i < length; i++) { + if ((cache_str[i] >= '0') && (cache_str[i] <= '9')) + + *cache_size = *cache_size * 10 + (cache_str[i] - '0'); + + else if (cache_str[i] == 'K') + + *cache_size = *cache_size * 1024; + + else if (cache_str[i] == 'M') + + *cache_size = *cache_size * 1024 * 1024; + + else + break; + } + + return 0; +} + +#define CORE_SIBLINGS_PATH "/sys/bus/cpu/devices/cpu" + +/* + * get_cbm_mask - Get cbm mask for given cache + * @cache_type: Cache level L2/L3 + * @cbm_mask: cbm_mask returned as a string + * + * Return: = 0 on success, < 0 on failure. + */ +int get_cbm_mask(char *cache_type, char *cbm_mask) +{ + char cbm_mask_path[1024]; + FILE *fp; + + if (!cbm_mask) + return -1; + + sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type); + + fp = fopen(cbm_mask_path, "r"); + if (!fp) { + perror("Failed to open cache level"); + + return -1; + } + if (fscanf(fp, "%s", cbm_mask) <= 0) { + perror("Could not get max cbm_mask"); + fclose(fp); + + return -1; + } + fclose(fp); + + return 0; +} + +/* + * get_core_sibling - Get sibling core id from the same socket for given CPU + * @cpu_no: CPU number + * + * Return: > 0 on success, < 0 on failure. + */ +int get_core_sibling(int cpu_no) +{ + char core_siblings_path[1024], cpu_list_str[64]; + int sibling_cpu_no = -1; + FILE *fp; + + sprintf(core_siblings_path, "%s%d/topology/core_siblings_list", + CORE_SIBLINGS_PATH, cpu_no); + + fp = fopen(core_siblings_path, "r"); + if (!fp) { + perror("Failed to open core siblings path"); + + return -1; + } + if (fscanf(fp, "%s", cpu_list_str) <= 0) { + perror("Could not get core_siblings list"); + fclose(fp); + + return -1; + } + fclose(fp); + + char *token = strtok(cpu_list_str, "-,"); + + while (token) { + sibling_cpu_no = atoi(token); + /* Skipping core 0 as we don't want to run test on core 0 */ + if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no) + break; + token = strtok(NULL, "-,"); + } + + return sibling_cpu_no; +} + +/* + * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu + * @bm_pid: PID that should be binded + * @cpu_no: CPU number at which the PID would be binded + * + * Return: 0 on success, non-zero on failure + */ +int taskset_benchmark(pid_t bm_pid, int cpu_no) +{ + cpu_set_t my_set; + + CPU_ZERO(&my_set); + CPU_SET(cpu_no, &my_set); + + if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) { + perror("Unable to taskset benchmark"); + + return -1; + } + + return 0; +} + +/* + * run_benchmark - Run a specified benchmark or fill_buf (default benchmark) + * in specified signal. Direct benchmark stdio to /dev/null. + * @signum: signal number + * @info: signal info + * @ucontext: user context in signal handling + * + * Return: void + */ +void run_benchmark(int signum, siginfo_t *info, void *ucontext) +{ + int operation, ret, memflush; + char **benchmark_cmd; + size_t span; + bool once; + FILE *fp; + + benchmark_cmd = info->si_ptr; + + /* + * Direct stdio of child to /dev/null, so that only parent writes to + * stdio (console) + */ + fp = freopen("/dev/null", "w", stdout); + if (!fp) + PARENT_EXIT("Unable to direct benchmark status to /dev/null"); + + if (strcmp(benchmark_cmd[0], "fill_buf") == 0) { + /* Execute default fill_buf benchmark */ + span = strtoul(benchmark_cmd[1], NULL, 10); + memflush = atoi(benchmark_cmd[2]); + operation = atoi(benchmark_cmd[3]); + if (!strcmp(benchmark_cmd[4], "true")) + once = true; + else if (!strcmp(benchmark_cmd[4], "false")) + once = false; + else + PARENT_EXIT("Invalid once parameter"); + + if (run_fill_buf(span, memflush, operation, once)) + fprintf(stderr, "Error in running fill buffer\n"); + } else { + /* Execute specified benchmark */ + ret = execvp(benchmark_cmd[0], benchmark_cmd); + if (ret) + perror("wrong\n"); + } + + fclose(stdout); + PARENT_EXIT("Unable to run specified benchmark"); +} + +/* + * create_grp - Create a group only if one doesn't exist + * @grp_name: Name of the group + * @grp: Full path and name of the group + * @parent_grp: Full path and name of the parent group + * + * Return: 0 on success, non-zero on failure + */ +static int create_grp(const char *grp_name, char *grp, const char *parent_grp) +{ + int found_grp = 0; + struct dirent *ep; + DIR *dp; + + /* + * At this point, we are guaranteed to have resctrl FS mounted and if + * length of grp_name == 0, it means, user wants to use root con_mon + * grp, so do nothing + */ + if (strlen(grp_name) == 0) + return 0; + + /* Check if requested grp exists or not */ + dp = opendir(parent_grp); + if (dp) { + while ((ep = readdir(dp)) != NULL) { + if (strcmp(ep->d_name, grp_name) == 0) + found_grp = 1; + } + closedir(dp); + } else { + perror("Unable to open resctrl for group"); + + return -1; + } + + /* Requested grp doesn't exist, hence create it */ + if (found_grp == 0) { + if (mkdir(grp, 0) == -1) { + perror("Unable to create group"); + + return -1; + } + } + + return 0; +} + +static int write_pid_to_tasks(char *tasks, pid_t pid) +{ + FILE *fp; + + fp = fopen(tasks, "w"); + if (!fp) { + perror("Failed to open tasks file"); + + return -1; + } + if (fprintf(fp, "%d\n", pid) < 0) { + perror("Failed to wr pid to tasks file"); + fclose(fp); + + return -1; + } + fclose(fp); + + return 0; +} + +/* + * write_bm_pid_to_resctrl - Write a PID (i.e. benchmark) to resctrl FS + * @bm_pid: PID that should be written + * @ctrlgrp: Name of the control monitor group (con_mon grp) + * @mongrp: Name of the monitor group (mon grp) + * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * + * If a con_mon grp is requested, create it and write pid to it, otherwise + * write pid to root con_mon grp. + * If a mon grp is requested, create it and write pid to it, otherwise + * pid is not written, this means that pid is in con_mon grp and hence + * should consult con_mon grp's mon_data directory for results. + * + * Return: 0 on success, non-zero on failure + */ +int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, + char *resctrl_val) +{ + char controlgroup[128], monitorgroup[512], monitorgroup_p[256]; + char tasks[1024]; + int ret = 0; + + if (strlen(ctrlgrp)) + sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp); + else + sprintf(controlgroup, "%s", RESCTRL_PATH); + + /* Create control and monitoring group and write pid into it */ + ret = create_grp(ctrlgrp, controlgroup, RESCTRL_PATH); + if (ret) + goto out; + sprintf(tasks, "%s/tasks", controlgroup); + ret = write_pid_to_tasks(tasks, bm_pid); + if (ret) + goto out; + + /* Create mon grp and write pid into it for "mbm" and "cmt" test */ + if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) || + !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) { + if (strlen(mongrp)) { + sprintf(monitorgroup_p, "%s/mon_groups", controlgroup); + sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp); + ret = create_grp(mongrp, monitorgroup, monitorgroup_p); + if (ret) + goto out; + + sprintf(tasks, "%s/mon_groups/%s/tasks", + controlgroup, mongrp); + ret = write_pid_to_tasks(tasks, bm_pid); + if (ret) + goto out; + } + } + +out: + ksft_print_msg("Writing benchmark parameters to resctrl FS\n"); + if (ret) + perror("# writing to resctrlfs"); + + return ret; +} + +/* + * write_schemata - Update schemata of a con_mon grp + * @ctrlgrp: Name of the con_mon grp + * @schemata: Schemata that should be updated to + * @cpu_no: CPU number that the benchmark PID is binded to + * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * + * Update schemata of a con_mon grp *only* if requested resctrl feature is + * allocation type + * + * Return: 0 on success, non-zero on failure + */ +int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) +{ + char controlgroup[1024], schema[1024], reason[64]; + int resource_id, ret = 0; + FILE *fp; + + if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) && + strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) && + strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) && + strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) + return -ENOENT; + + if (!schemata) { + ksft_print_msg("Skipping empty schemata update\n"); + + return -1; + } + + if (get_resource_id(cpu_no, &resource_id) < 0) { + sprintf(reason, "Failed to get resource id"); + ret = -1; + + goto out; + } + + if (strlen(ctrlgrp) != 0) + sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp); + else + sprintf(controlgroup, "%s/schemata", RESCTRL_PATH); + + if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) || + !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) + sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata); + if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || + !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) + sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata); + + fp = fopen(controlgroup, "w"); + if (!fp) { + sprintf(reason, "Failed to open control group"); + ret = -1; + + goto out; + } + + if (fprintf(fp, "%s\n", schema) < 0) { + sprintf(reason, "Failed to write schemata in control group"); + fclose(fp); + ret = -1; + + goto out; + } + fclose(fp); + +out: + ksft_print_msg("Write schema \"%s\" to resctrl FS%s%s\n", + schema, ret ? " # " : "", + ret ? reason : ""); + + return ret; +} + +bool check_resctrlfs_support(void) +{ + FILE *inf = fopen("/proc/filesystems", "r"); + DIR *dp; + char *res; + bool ret = false; + + if (!inf) + return false; + + res = fgrep(inf, "nodev\tresctrl\n"); + + if (res) { + ret = true; + free(res); + } + + fclose(inf); + + ksft_print_msg("%s Check kernel supports resctrl filesystem\n", + ret ? "Pass:" : "Fail:"); + + if (!ret) + return ret; + + dp = opendir(RESCTRL_PATH); + ksft_print_msg("%s Check resctrl mountpoint \"%s\" exists\n", + dp ? "Pass:" : "Fail:", RESCTRL_PATH); + if (dp) + closedir(dp); + + ksft_print_msg("resctrl filesystem %s mounted\n", + find_resctrl_mount(NULL) ? "not" : "is"); + + return ret; +} + +char *fgrep(FILE *inf, const char *str) +{ + char line[256]; + int slen = strlen(str); + + while (!feof(inf)) { + if (!fgets(line, 256, inf)) + break; + if (strncmp(line, str, slen)) + continue; + + return strdup(line); + } + + return NULL; +} + +/* + * validate_resctrl_feature_request - Check if requested feature is valid. + * @resource: Required resource (e.g., MB, L3, L2, L3_MON, etc.) + * @feature: Required monitor feature (in mon_features file). Can only be + * set for L3_MON. Must be NULL for all other resources. + * + * Return: True if the resource/feature is supported, else false. False is + * also returned if resctrl FS is not mounted. + */ +bool validate_resctrl_feature_request(const char *resource, const char *feature) +{ + char res_path[PATH_MAX]; + struct stat statbuf; + char *res; + FILE *inf; + int ret; + + if (!resource) + return false; + + ret = find_resctrl_mount(NULL); + if (ret) + return false; + + snprintf(res_path, sizeof(res_path), "%s/%s", INFO_PATH, resource); + + if (stat(res_path, &statbuf)) + return false; + + if (!feature) + return true; + + snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource); + inf = fopen(res_path, "r"); + if (!inf) + return false; + + res = fgrep(inf, feature); + free(res); + fclose(inf); + + return !!res; +} + +int filter_dmesg(void) +{ + char line[1024]; + FILE *fp; + int pipefds[2]; + pid_t pid; + int ret; + + ret = pipe(pipefds); + if (ret) { + perror("pipe"); + return ret; + } + fflush(stdout); + pid = fork(); + if (pid == 0) { + close(pipefds[0]); + dup2(pipefds[1], STDOUT_FILENO); + execlp("dmesg", "dmesg", NULL); + perror("executing dmesg"); + exit(1); + } + close(pipefds[1]); + fp = fdopen(pipefds[0], "r"); + if (!fp) { + perror("fdopen(pipe)"); + kill(pid, SIGTERM); + + return -1; + } + + while (fgets(line, 1024, fp)) { + if (strstr(line, "intel_rdt:")) + ksft_print_msg("dmesg: %s", line); + if (strstr(line, "resctrl:")) + ksft_print_msg("dmesg: %s", line); + } + fclose(fp); + waitpid(pid, NULL, 0); + + return 0; +} + +int validate_bw_report_request(char *bw_report) +{ + if (strcmp(bw_report, "reads") == 0) + return 0; + if (strcmp(bw_report, "writes") == 0) + return 0; + if (strcmp(bw_report, "nt-writes") == 0) { + strcpy(bw_report, "writes"); + return 0; + } + if (strcmp(bw_report, "total") == 0) + return 0; + + fprintf(stderr, "Requested iMC B/W report type unavailable\n"); + + return -1; +} + +int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, + int group_fd, unsigned long flags) +{ + int ret; + + ret = syscall(__NR_perf_event_open, hw_event, pid, cpu, + group_fd, flags); + return ret; +} + +unsigned int count_bits(unsigned long n) +{ + unsigned int count = 0; + + while (n) { + count += n & 1; + n >>= 1; + } + + return count; +} diff --git a/tools/testing/selftests/resctrl/settings b/tools/testing/selftests/resctrl/settings new file mode 100644 index 0000000000..a383f3d456 --- /dev/null +++ b/tools/testing/selftests/resctrl/settings @@ -0,0 +1,3 @@ +# If running time is longer than 120 seconds when new tests are added in +# the future, increase timeout here. +timeout=120 |