Fix following sparse warnings: tools/testing/selftests/resctrl/resctrl_val.c:47:6: warning: symbol 'membw_initialize_perf_event_attr' was not declared. Should it be static? tools/testing/selftests/resctrl/resctrl_val.c:64:6: warning: symbol 'membw_ioctl_perf_event_ioc_reset_enable' was not declared. Should it be static? tools/testing/selftests/resctrl/resctrl_val.c:70:6: warning: symbol 'membw_ioctl_perf_event_ioc_disable' was not declared. Should it be static? tools/testing/selftests/resctrl/resctrl_val.c:81:6: warning: symbol 'get_event_and_umask' was not declared. Should it be static?

Signed-off-by: Reinette Chatre reinette.chatre@intel.com Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com --- Changes since v1: - Add Ilpo's Reviewed-by tag. - Let subject describe the change, not the tool that found it. (checkpatch.pl) --- tools/testing/selftests/resctrl/resctrl_val.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 8c275f6b4dd7..70e8e31f5d1a 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -44,7 +44,7 @@ static int imcs; static struct imc_counter_config imc_counters_config[MAX_IMCS][2]; static const struct resctrl_test *current_test;

-void membw_initialize_perf_event_attr(int i, int j) +static void membw_initialize_perf_event_attr(int i, int j) { memset(&imc_counters_config[i][j].pe, 0, sizeof(struct perf_event_attr)); @@ -61,13 +61,13 @@ void membw_initialize_perf_event_attr(int i, int j) PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; }

-void membw_ioctl_perf_event_ioc_reset_enable(int i, int j) +static 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) +static void membw_ioctl_perf_event_ioc_disable(int i, int j) { ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0); } @@ -78,7 +78,7 @@ void membw_ioctl_perf_event_ioc_disable(int i, int j) * @count: iMC number * @op: Operation (read/write) */ -void get_event_and_umask(char *cas_count_cfg, int count, bool op) +static void get_event_and_umask(char *cas_count_cfg, int count, bool op) { char *token[MAX_TOKENS]; int i = 0;

alloc_buffer() allocates and initializes (with random data) a buffer of requested size. The initialization starts from the beginning of the allocated buffer and incrementally assigns sizeof(uint64_t) random data to each cache line. The initialization uses the size of the buffer to control the initialization flow, decrementing the amount of buffer needing to be initialized after each iteration.

The size of the buffer is stored in an unsigned (size_t) variable s64 and the test "s64 > 0" is used to decide if initialization is complete. The problem is that decrementing the buffer size may wrap around if the buffer size is not divisible by "CL_SIZE / sizeof(uint64_t)" resulting in the "s64 > 0" test being true and memory beyond the buffer "initialized".

Use a signed value for the buffer size to support all buffer sizes.

Fixes: a2561b12fe39 ("selftests/resctrl: Add built in benchmark") Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - New patch. --- tools/testing/selftests/resctrl/fill_buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index ae120f1735c0..34e5df721430 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -127,7 +127,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush) { void *buf = NULL; uint64_t *p64; - size_t s64; + ssize_t s64; int ret;

ret = posix_memalign(&buf, PAGE_SIZE, buf_size);

The MBM and MBA tests need to discover the event and umask with which to configure the performance event used to measure read memory bandwidth. This is done by parsing the /sys/bus/event_source/devices/uncore_imc_<imc instance>/events/cas_count_read file for each iMC instance that contains the formatted output: "event=<event>,umask=<umask>"

Parsing of cas_count_read contents is done by initializing an array of MAX_TOKENS elements with tokens (deliminated by "=,") from this file. Start by removing the unnecessary append of a delimiter to the string needing to be parsed. Per the strtok() man page: "delimiter bytes at the start or end of the string are ignored". This has no impact on the token placement within the array.

After initialization, the actual event and umask is determined by parsing the tokens directly following the "event" and "umask" tokens respectively.

Iterating through the array up to index "i < MAX_TOKENS" but then accessing index "i + 1" risks array overrun during the final iteration. Avoid array overrun by ensuring that the index used within for loop will always be valid.

Fixes: 1d3f08687d76 ("selftests/resctrl: Read memory bandwidth from perf IMC counter and from resctrl file system") Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - New patch. --- tools/testing/selftests/resctrl/resctrl_val.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 70e8e31f5d1a..e88d5ca30517 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -83,13 +83,12 @@ static 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++) { + for (i = 0; i < MAX_TOKENS - 1; i++) { if (!token[i]) break; if (strcmp(token[i], "event") == 0) {

The CMT, MBM, and MBA tests rely on a benchmark that runs while the test makes changes to needed configuration (for example memory bandwidth allocation) and takes needed measurements. By default the "fill_buf" benchmark is used and by default (via its "once = false" setting) "fill_buf" is configured to run until terminated after the test completes.

An unintended consequence of enabling the user to override the benchmark also enables the user to change parameters to the "fill_buf" benchmark. This enables the user to set "fill_buf" to only cycle through the buffer once (by setting "once = true") and thus breaking the CMT, MBA, and MBM tests that expect workload/interference to be reflected by their measurements.

Prevent user space from changing the "once" parameter and ensure that it is always false for the CMT, MBA, and MBM tests.

Suggested-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - New patch --- tools/testing/selftests/resctrl/fill_buf.c | 7 ++++--- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_tests.c | 8 +++++++- tools/testing/selftests/resctrl/resctrl_val.c | 11 +---------- 4 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 34e5df721430..854f0108d8e6 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -151,7 +151,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush) return buf; }

-int run_fill_buf(size_t buf_size, int memflush, int op, bool once) +int run_fill_buf(size_t buf_size, int memflush, int op) { unsigned char *buf;

@@ -160,9 +160,10 @@ int run_fill_buf(size_t buf_size, int memflush, int op, bool once) return -1;

if (op == 0) - fill_cache_read(buf, buf_size, once); + fill_cache_read(buf, buf_size, false); else - fill_cache_write(buf, buf_size, once); + fill_cache_write(buf, buf_size, false); + free(buf);

return 0; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 2dda56084588..51f5f4b25e06 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -142,7 +142,7 @@ int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, unsigned char *alloc_buffer(size_t buf_size, int memflush); void mem_flush(unsigned char *buf, size_t buf_size); void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); -int run_fill_buf(size_t buf_size, int memflush, int op, bool once); +int run_fill_buf(size_t buf_size, int memflush, int op); int initialize_mem_bw_imc(void); int measure_mem_bw(const struct user_params *uparams, struct resctrl_val_param *param, pid_t bm_pid, diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index ecbb7605a981..bee4123a5a9b 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -266,7 +266,13 @@ int main(int argc, char **argv) uparams.benchmark_cmd[1] = span_str; uparams.benchmark_cmd[2] = "1"; uparams.benchmark_cmd[3] = "0"; - uparams.benchmark_cmd[4] = "false"; + /* + * Fourth parameter was previously used to indicate + * how long "fill_buf" should run for, with "false" + * ("fill_buf" will keep running until terminated) + * the only option that works. + */ + uparams.benchmark_cmd[4] = NULL; uparams.benchmark_cmd[5] = NULL; }

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index e88d5ca30517..5331354aaf64 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -625,7 +625,6 @@ static 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; @@ -645,16 +644,8 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) 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 { - ksft_print_msg("Invalid once parameter\n"); - parent_exit(ppid); - }

- if (run_fill_buf(span, memflush, operation, once)) + if (run_fill_buf(span, memflush, operation)) fprintf(stderr, "Error in running fill buffer\n"); } else { /* Execute specified benchmark */

The MBM and MBA resctrl selftests run a benchmark during which it takes measurements of read memory bandwidth via perf. Code exists to support measurements of write memory bandwidth but there exists no path with which this code can execute.

While code exists for write memory bandwidth measurement there has not yet been a use case for it. Remove this unused code. Rename relevant functions to include "read" so that it is clear that it relates only to memory bandwidth reads, while renaming the functions also add consistency by changing the "membw" instances to more prevalent "mem_bw".

Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - New patch. --- tools/testing/selftests/resctrl/mba_test.c | 4 +- tools/testing/selftests/resctrl/mbm_test.c | 4 +- tools/testing/selftests/resctrl/resctrl.h | 8 +- tools/testing/selftests/resctrl/resctrl_val.c | 234 ++++++------------ tools/testing/selftests/resctrl/resctrlfs.c | 17 -- 5 files changed, 85 insertions(+), 182 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index da40a8ed4413..be0ead73e55d 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -21,7 +21,7 @@ static int mba_init(const struct resctrl_val_param *param, int domain_id) { int ret;

- ret = initialize_mem_bw_imc(); + ret = initialize_read_mem_bw_imc(); if (ret) return ret;

@@ -68,7 +68,7 @@ static int mba_setup(const struct resctrl_test *test, static int mba_measure(const struct user_params *uparams, struct resctrl_val_param *param, pid_t bm_pid) { - return measure_mem_bw(uparams, param, bm_pid, "reads"); + return measure_read_mem_bw(uparams, param, bm_pid); }

static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 80c7a1bc13b8..9744bf1ac16f 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -91,7 +91,7 @@ static int mbm_init(const struct resctrl_val_param *param, int domain_id) { int ret;

- ret = initialize_mem_bw_imc(); + ret = initialize_read_mem_bw_imc(); if (ret) return ret;

@@ -122,7 +122,7 @@ static int mbm_setup(const struct resctrl_test *test, static int mbm_measure(const struct user_params *uparams, struct resctrl_val_param *param, pid_t bm_pid) { - return measure_mem_bw(uparams, param, bm_pid, "reads"); + return measure_read_mem_bw(uparams, param, bm_pid); }

static void mbm_test_cleanup(void) diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index ba1ce1b35699..82801245e4c1 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -126,7 +126,6 @@ int filter_dmesg(void); int get_domain_id(const char *resource, int cpu_no, int *domain_id); int mount_resctrlfs(void); int umount_resctrlfs(void); -const char *get_bw_report_type(const char *bw_report); bool resctrl_resource_exists(const char *resource); bool resctrl_mon_feature_exists(const char *resource, const char *feature); bool resource_info_file_exists(const char *resource, const char *file); @@ -143,10 +142,9 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush); void mem_flush(unsigned char *buf, size_t buf_size); void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); int run_fill_buf(size_t buf_size, int memflush); -int initialize_mem_bw_imc(void); -int measure_mem_bw(const struct user_params *uparams, - struct resctrl_val_param *param, pid_t bm_pid, - const char *bw_report); +int initialize_read_mem_bw_imc(void); +int measure_read_mem_bw(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid); void initialize_mem_bw_resctrl(const struct resctrl_val_param *param, int domain_id); int resctrl_val(const struct resctrl_test *test, diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 8b5973c5e934..a1e097dc8e05 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -12,13 +12,10 @@

#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_MBM_LOCAL_BYTES_PATH \ "%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes" @@ -41,44 +38,43 @@ struct imc_counter_config {

static char mbm_total_path[1024]; static int imcs; -static struct imc_counter_config imc_counters_config[MAX_IMCS][2]; +static struct imc_counter_config imc_counters_config[MAX_IMCS]; static const struct resctrl_test *current_test;

-static void membw_initialize_perf_event_attr(int i, int j) +static void read_mem_bw_initialize_perf_event_attr(int i) { - memset(&imc_counters_config[i][j].pe, 0, + memset(&imc_counters_config[i].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 = + imc_counters_config[i].pe.type = imc_counters_config[i].type; + imc_counters_config[i].pe.size = sizeof(struct perf_event_attr); + imc_counters_config[i].pe.disabled = 1; + imc_counters_config[i].pe.inherit = 1; + imc_counters_config[i].pe.exclude_guest = 0; + imc_counters_config[i].pe.config = + imc_counters_config[i].umask << 8 | + imc_counters_config[i].event; + imc_counters_config[i].pe.sample_type = PERF_SAMPLE_IDENTIFIER; + imc_counters_config[i].pe.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; }

-static void membw_ioctl_perf_event_ioc_reset_enable(int i, int j) +static void read_mem_bw_ioctl_perf_event_ioc_reset_enable(int i) { - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0); - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_RESET, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_ENABLE, 0); }

-static void membw_ioctl_perf_event_ioc_disable(int i, int j) +static void read_mem_bw_ioctl_perf_event_ioc_disable(int i) { - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_DISABLE, 0); }

/* - * get_event_and_umask: Parse config into event and umask + * get_read_event_and_umask: Parse config into event and umask * @cas_count_cfg: Config * @count: iMC number - * @op: Operation (read/write) */ -static void get_event_and_umask(char *cas_count_cfg, int count, bool op) +static void get_read_event_and_umask(char *cas_count_cfg, int count) { char *token[MAX_TOKENS]; int i = 0; @@ -91,34 +87,22 @@ static void get_event_and_umask(char *cas_count_cfg, int count, bool op) for (i = 0; i < MAX_TOKENS - 1; 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); - } + if (strcmp(token[i], "event") == 0) + imc_counters_config[count].event = strtol(token[i + 1], NULL, 16); + if (strcmp(token[i], "umask") == 0) + imc_counters_config[count].umask = strtol(token[i + 1], NULL, 16); } }

-static int open_perf_event(int i, int cpu_no, int j) +static int open_perf_read_event(int i, int cpu_no) { - imc_counters_config[i][j].fd = - perf_event_open(&imc_counters_config[i][j].pe, -1, cpu_no, -1, + imc_counters_config[i].fd = + perf_event_open(&imc_counters_config[i].pe, -1, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);

- if (imc_counters_config[i][j].fd == -1) { + if (imc_counters_config[i].fd == -1) { fprintf(stderr, "Error opening leader %llx\n", - imc_counters_config[i][j].pe.config); + imc_counters_config[i].pe.config);

return -1; } @@ -126,7 +110,7 @@ static int open_perf_event(int i, int cpu_no, int j) return 0; }

-/* Get type and config (read and write) of an iMC counter */ +/* Get type and config of an iMC counter's read event. */ static int read_from_imc_dir(char *imc_dir, int count) { char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024]; @@ -140,7 +124,7 @@ static int read_from_imc_dir(char *imc_dir, int count)

return -1; } - if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) { + if (fscanf(fp, "%u", &imc_counters_config[count].type) <= 0) { ksft_perror("Could not get iMC type"); fclose(fp);

@@ -148,9 +132,6 @@ static int read_from_imc_dir(char *imc_dir, int count) } 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"); @@ -167,34 +148,19 @@ static int read_from_imc_dir(char *imc_dir, int count) } 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) { - ksft_perror("Failed to open iMC config file"); - - return -1; - } - if (fscanf(fp, "%s", cas_count_cfg) <= 0) { - ksft_perror("Could not get iMC cas count write"); - fclose(fp); - - return -1; - } - fclose(fp); - - get_event_and_umask(cas_count_cfg, count, WRITE); + get_read_event_and_umask(cas_count_cfg, count);

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. + * counters, get that 'n'. Discover the properties of the available + * counters in support of needed performance measurement via perf. + * For each iMC counter get it's type and config. Also obtain each + * counter's event and umask for the memory read events that will be + * measured. + * * Enumerate all these details into an array of structures. * * Return: >= 0 on success. < 0 on failure. @@ -255,55 +221,46 @@ static int num_of_imcs(void) return count; }

-int initialize_mem_bw_imc(void) +int initialize_read_mem_bw_imc(void) { - int imc, j; + int imc;

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); - } + for (imc = 0; imc < imcs; imc++) + read_mem_bw_initialize_perf_event_attr(imc);

return 0; }

-static void perf_close_imc_mem_bw(void) +static void perf_close_imc_read_mem_bw(void) { int mc;

for (mc = 0; mc < imcs; mc++) { - if (imc_counters_config[mc][READ].fd != -1) - close(imc_counters_config[mc][READ].fd); - if (imc_counters_config[mc][WRITE].fd != -1) - close(imc_counters_config[mc][WRITE].fd); + if (imc_counters_config[mc].fd != -1) + close(imc_counters_config[mc].fd); } }

/* - * perf_open_imc_mem_bw - Open perf fds for IMCs + * perf_open_imc_read_mem_bw - Open perf fds for IMCs * @cpu_no: CPU number that the benchmark PID is bound to * * Return: = 0 on success. < 0 on failure. */ -static int perf_open_imc_mem_bw(int cpu_no) +static int perf_open_imc_read_mem_bw(int cpu_no) { int imc, ret;

- for (imc = 0; imc < imcs; imc++) { - imc_counters_config[imc][READ].fd = -1; - imc_counters_config[imc][WRITE].fd = -1; - } + for (imc = 0; imc < imcs; imc++) + imc_counters_config[imc].fd = -1;

for (imc = 0; imc < imcs; imc++) { - ret = open_perf_event(imc, cpu_no, READ); - if (ret) - goto close_fds; - ret = open_perf_event(imc, cpu_no, WRITE); + ret = open_perf_read_event(imc, cpu_no); if (ret) goto close_fds; } @@ -311,60 +268,52 @@ static int perf_open_imc_mem_bw(int cpu_no) return 0;

close_fds: - perf_close_imc_mem_bw(); + perf_close_imc_read_mem_bw(); return -1; }

/* - * do_mem_bw_test - Perform memory bandwidth test + * do_imc_read_mem_bw_test - Perform memory bandwidth test * * Runs memory bandwidth test over one second period. Also, handles starting * and stopping of the IMC perf counters around the test. */ -static void do_imc_mem_bw_test(void) +static void do_imc_read_mem_bw_test(void) { int imc;

- for (imc = 0; imc < imcs; imc++) { - membw_ioctl_perf_event_ioc_reset_enable(imc, READ); - membw_ioctl_perf_event_ioc_reset_enable(imc, WRITE); - } + for (imc = 0; imc < imcs; imc++) + read_mem_bw_ioctl_perf_event_ioc_reset_enable(imc);

sleep(1);

- /* Stop counters after a second to get results (both read and write) */ - for (imc = 0; imc < imcs; imc++) { - membw_ioctl_perf_event_ioc_disable(imc, READ); - membw_ioctl_perf_event_ioc_disable(imc, WRITE); - } + /* Stop counters after a second to get results. */ + for (imc = 0; imc < imcs; imc++) + read_mem_bw_ioctl_perf_event_ioc_disable(imc); }

/* - * get_mem_bw_imc - Memory bandwidth as reported by iMC counters - * @bw_report: Bandwidth report type (reads, writes) + * get_read_mem_bw_imc - Memory read bandwidth as reported by iMC counters * - * Memory bandwidth utilized by a process on a socket can be calculated - * using iMC counters. Perf events are used to read these counters. + * Memory read bandwidth utilized by a process on a socket can be calculated + * using iMC counters' read events. Perf events are used to read these + * counters. * * Return: = 0 on success. < 0 on failure. */ -static int get_mem_bw_imc(const char *bw_report, float *bw_imc) +static int get_read_mem_bw_imc(float *bw_imc) { - float reads, writes, of_mul_read, of_mul_write; + float reads = 0, of_mul_read = 1; int imc;

- /* Start all iMC counters to log values (both read and write) */ - reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1; - /* - * Get results which are stored in struct type imc_counter_config + * Log read event values from all iMC counters into + * struct imc_counter_config. * Take overflow into consideration before calculating total bandwidth. */ 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]; + &imc_counters_config[imc];

if (read(r->fd, &r->return_value, sizeof(struct membw_read_format)) == -1) { @@ -372,12 +321,6 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc) return -1; }

- if (read(w->fd, &w->return_value, - sizeof(struct membw_read_format)) == -1) { - ksft_perror("Couldn't get write bandwidth through iMC"); - return -1; - } - __u64 r_time_enabled = r->return_value.time_enabled; __u64 r_time_running = r->return_value.time_running;

@@ -385,27 +328,10 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc) 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; }

- 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; + *bw_imc = reads; return 0; }

@@ -551,35 +477,31 @@ static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc, }

/* - * measure_mem_bw - Measures memory bandwidth numbers while benchmark runs + * measure_read_mem_bw - Measures read memory bandwidth numbers while benchmark runs * @uparams: User supplied parameters * @param: Parameters passed to resctrl_val() * @bm_pid: PID that runs the benchmark - * @bw_report: Bandwidth report type (reads, writes) * * 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 * 1 sec to measure the data. + * resctrl does not distinguish between read and write operations so + * its data includes all memory operations. */ -int measure_mem_bw(const struct user_params *uparams, - struct resctrl_val_param *param, pid_t bm_pid, - const char *bw_report) +int measure_read_mem_bw(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid) { unsigned long bw_resc, bw_resc_start, bw_resc_end; FILE *mem_bw_fp; float bw_imc; int ret;

- bw_report = get_bw_report_type(bw_report); - if (!bw_report) - return -1; - mem_bw_fp = open_mem_bw_resctrl(mbm_total_path); if (!mem_bw_fp) return -1;

- ret = perf_open_imc_mem_bw(uparams->cpu); + ret = perf_open_imc_read_mem_bw(uparams->cpu); if (ret < 0) goto close_fp;

@@ -589,17 +511,17 @@ int measure_mem_bw(const struct user_params *uparams,

rewind(mem_bw_fp);

- do_imc_mem_bw_test(); + do_imc_read_mem_bw_test();

ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_end); if (ret < 0) goto close_imc;

- ret = get_mem_bw_imc(bw_report, &bw_imc); + ret = get_read_mem_bw_imc(&bw_imc); if (ret < 0) goto close_imc;

- perf_close_imc_mem_bw(); + perf_close_imc_read_mem_bw(); fclose(mem_bw_fp);

bw_resc = (bw_resc_end - bw_resc_start) / MB; @@ -607,7 +529,7 @@ int measure_mem_bw(const struct user_params *uparams, return print_results_bw(param->filename, bm_pid, bw_imc, bw_resc);

close_imc: - perf_close_imc_mem_bw(); + perf_close_imc_read_mem_bw(); close_fp: fclose(mem_bw_fp); return ret; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 250c320349a7..eabdf0c20566 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -831,23 +831,6 @@ int filter_dmesg(void) return 0; }

-const char *get_bw_report_type(const char *bw_report) -{ - if (strcmp(bw_report, "reads") == 0) - return bw_report; - if (strcmp(bw_report, "writes") == 0) - return bw_report; - if (strcmp(bw_report, "nt-writes") == 0) { - return "writes"; - } - if (strcmp(bw_report, "total") == 0) - return bw_report; - - fprintf(stderr, "Requested iMC bandwidth report type unavailable\n"); - - return NULL; -} - int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags) {

The benchmark used during the CMT, MBM, and MBA tests can be provided by the user via (-b) parameter, if not provided the default "fill_buf" benchmark is used. The user is additionally able to override any of the "fill_buf" default parameters when running the tests with "-b fill_buf <fill_buf parameters>".

The "fill_buf" parameters are managed as an array of strings. Using an array of strings is complex because it requires transformations to/from strings at every producer and consumer. This is made worse for the individual tests where the default benchmark parameters values may not be appropriate and additional data wrangling is required. For example, the CMT test duplicates the entire array of strings in order to replace one of the parameters.

More issues appear when combining the usage of an array of strings with the use case of user overriding default parameters by specifying "-b fill_buf <parameters>". This use case is fragile with opportunities to trigger a SIGSEGV because of opportunities for NULL pointers to exist in the array of strings. For example, by running below (thus by specifying "fill_buf" should be used but all parameters are NULL): $ sudo resctrl_tests -t mbm -b fill_buf

Replace the "array of strings" parameters used for "fill_buf" with new struct fill_buf_param that contains the "fill_buf" parameters that can be used directly without transformations to/from strings. Two instances of struct fill_buf_param may exist at any point in time: * If the user provides new parameters to "fill_buf", the user parameter structure (struct user_params) will point to a fully initialized and immutable struct fill_buf_param containing the user provided parameters. * If "fill_buf" is the benchmark that should be used by a test, then the test parameter structure (struct resctrl_val_param) will point to a fully initialized struct fill_buf_param. The latter may contain (a) the user provided parameters verbatim, (b) user provided parameters adjusted to be appropriate for the test, or (c) the default parameters for "fill_buf" that is appropriate for the test if the user did not provide "fill_buf" parameters nor an alternate benchmark.

The existing behavior of CMT test is to use test defined value for the buffer size even if the user provides another value via command line. This behavior is maintained since the test requires that the buffer size matches the size of the cache allocated, and the amount of cache allocated can instead be changed by the user with the "-n" command line parameter.

Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - Maintain original behavior where user can override "fill_buf" parameters via command line ... but only those that can actually be changed. (Ilpo) - Fix parsing issues associated with original behavior to ensure any parameter is valid before any attempt to use it. - Move patch earlier in series to highlight that this fixes existing issues. - Make struct fill_buf_param dynamic to support user provided parameters as well as test specific parameters. - Rewrite changelog. --- tools/testing/selftests/resctrl/cmt_test.c | 32 ++---- tools/testing/selftests/resctrl/mba_test.c | 13 ++- tools/testing/selftests/resctrl/mbm_test.c | 22 ++-- tools/testing/selftests/resctrl/resctrl.h | 54 ++++++--- .../testing/selftests/resctrl/resctrl_tests.c | 104 +++++++++++++----- tools/testing/selftests/resctrl/resctrl_val.c | 43 ++++---- 6 files changed, 176 insertions(+), 92 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 0c045080d808..a7effe76b419 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -116,15 +116,13 @@ static void cmt_test_cleanup(void)

static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams) { - const char * const *cmd = uparams->benchmark_cmd; - const char *new_cmd[BENCHMARK_ARGS]; + struct fill_buf_param fill_buf = {0}; unsigned long cache_total_size = 0; int n = uparams->bits ? : 5; unsigned long long_mask; - char *span_str = NULL; int count_of_bits; size_t span; - int ret, i; + int ret;

ret = get_full_cbm("L3", &long_mask); if (ret) @@ -155,32 +153,26 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param

span = cache_portion_size(cache_total_size, param.mask, long_mask);

- if (strcmp(cmd[0], "fill_buf") == 0) { - /* Duplicate the command to be able to replace span in it */ - for (i = 0; uparams->benchmark_cmd[i]; i++) - new_cmd[i] = uparams->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; + if (uparams->fill_buf) { + fill_buf.buf_size = span; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + fill_buf.buf_size = span; + fill_buf.memflush = 1; + param.fill_buf = &fill_buf; }

remove(RESULT_FILE_NAME);

- ret = resctrl_val(test, uparams, cmd, &param); + ret = resctrl_val(test, uparams, &param); if (ret) - goto out; + return ret;

ret = check_results(&param, span, n); if (ret && (get_vendor() == ARCH_INTEL)) ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");

-out: - free(span_str); - return ret; }

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index be0ead73e55d..7e43056c8737 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -172,11 +172,22 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param .setup = mba_setup, .measure = mba_measure, }; + struct fill_buf_param fill_buf = {0}; int ret;

remove(RESULT_FILE_NAME);

- ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param); + if (uparams->fill_buf) { + fill_buf.buf_size = uparams->fill_buf->buf_size; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + fill_buf.buf_size = DEFAULT_SPAN; + fill_buf.memflush = 1; + param.fill_buf = &fill_buf; + } + + ret = resctrl_val(test, uparams, &param); if (ret) return ret;

diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 9744bf1ac16f..b1f03a73333f 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -139,26 +139,26 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param .setup = mbm_setup, .measure = mbm_measure, }; - char *endptr = NULL; - size_t span = 0; + struct fill_buf_param fill_buf = {0}; int ret;

remove(RESULT_FILE_NAME);

- if (uparams->benchmark_cmd[0] && strcmp(uparams->benchmark_cmd[0], "fill_buf") == 0) { - if (uparams->benchmark_cmd[1]) { - errno = 0; - span = strtoul(uparams->benchmark_cmd[1], &endptr, 10); - if (errno || uparams->benchmark_cmd[1] == endptr) - return -errno; - } + if (uparams->fill_buf) { + fill_buf.buf_size = uparams->fill_buf->buf_size; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + fill_buf.buf_size = DEFAULT_SPAN; + fill_buf.memflush = 1; + param.fill_buf = &fill_buf; }

- ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param); + ret = resctrl_val(test, uparams, &param); if (ret) return ret;

- ret = check_results(span); + ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0); if (ret && (get_vendor() == ARCH_INTEL)) ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 82801245e4c1..98462752cb46 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -43,16 +43,35 @@

#define DEFAULT_SPAN (250 * MB)

+/* + * fill_buf_param: "fill_buf" benchmark parameters + * @buf_size: Size (in bytes) of buffer used in benchmark. + * "fill_buf" allocates and initializes buffer of + * @buf_size. User can change value via command line. + * @memflush: If 0 then the buffer will not be flushed after + * allocation and initialization, otherwise the + * buffer will be flushed. User can change value via + * command line. + */ +struct fill_buf_param { + size_t buf_size; + int memflush; +}; + /* * user_params: User supplied parameters * @cpu: CPU number to which the benchmark will be bound to * @bits: Number of bits used for cache allocation size * @benchmark_cmd: Benchmark command to run during (some of the) tests + * @fill_buf: Pointer to user provided parameters for "fill_buf", + * NULL if user did not provide parameters and test + * specific defaults should be used. */ struct user_params { int cpu; int bits; const char *benchmark_cmd[BENCHMARK_ARGS]; + const struct fill_buf_param *fill_buf; };

/* @@ -87,21 +106,29 @@ struct resctrl_test { * @init: Callback function to initialize test environment * @setup: Callback function to setup per test run environment * @measure: Callback that performs the measurement (a single test) + * @fill_buf: Parameters for default "fill_buf" benchmark. + * Initialized with user provided parameters, possibly + * adapted to be relevant to the test. If user does + * not provide parameters for "fill_buf" nor a + * replacement benchmark then initialized with defaults + * appropriate for test. NULL if user provided + * benchmark. */ struct resctrl_val_param { - const char *ctrlgrp; - const char *mongrp; - char filename[64]; - unsigned long mask; - int num_of_runs; - int (*init)(const struct resctrl_val_param *param, - int domain_id); - int (*setup)(const struct resctrl_test *test, - const struct user_params *uparams, - struct resctrl_val_param *param); - int (*measure)(const struct user_params *uparams, - struct resctrl_val_param *param, - pid_t bm_pid); + const char *ctrlgrp; + const char *mongrp; + char filename[64]; + unsigned long mask; + int num_of_runs; + int (*init)(const struct resctrl_val_param *param, + int domain_id); + int (*setup)(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param); + int (*measure)(const struct user_params *uparams, + struct resctrl_val_param *param, + pid_t bm_pid); + struct fill_buf_param *fill_buf; };

struct perf_event_read { @@ -149,7 +176,6 @@ void initialize_mem_bw_resctrl(const struct resctrl_val_param *param, int domain_id); int resctrl_val(const struct resctrl_test *test, const struct user_params *uparams, - const char * const *benchmark_cmd, struct resctrl_val_param *param); unsigned long create_bit_mask(unsigned int start, unsigned int len); unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 60627dbae20a..121079363208 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -148,6 +148,78 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p test_cleanup(test); }

+/* + * Allocate and initialize a struct fill_buf_param with user provided + * (via "-b fill_buf <fill_buf parameters>") parameters. + * + * Use defaults (that may not be appropriate for all tests) for any + * fill_buf parameters omitted by the user. + * + * Historically it may have been possible for user space to provide + * additional parameters, "operation" ("read" vs "write") in + * benchmark_cmd[3] and "once" (run "once" or until terminated) in + * benchmark_cmd[4]. Changing these parameters have never been + * supported with the default of "read" operation and running until + * terminated built into the tests. Any unsupported values for + * (original) "fill_buf" parameters are treated as failure. + * + * Return: On failure, forcibly exits the test on any parsing failure, + * returns NULL if no parsing needed (user did not actually provide + * "-b fill_buf"). + * On success, returns pointer to newly allocated and fully + * initialized struct fill_buf_param that caller must free. + */ +static struct fill_buf_param *alloc_fill_buf_param(struct user_params *uparams) +{ + struct fill_buf_param *fill_param = NULL; + char *endptr = NULL; + + if (!uparams->benchmark_cmd[0] || strcmp(uparams->benchmark_cmd[0], "fill_buf")) + return NULL; + + fill_param = malloc(sizeof(*fill_param)); + if (!fill_param) + ksft_exit_skip("Unable to allocate memory for fill_buf parameters.\n"); + + if (uparams->benchmark_cmd[1]) { + errno = 0; + fill_param->buf_size = strtoul(uparams->benchmark_cmd[1], &endptr, 10); + if (errno || uparams->benchmark_cmd[1] == endptr) { + free(fill_param); + ksft_exit_skip("Unable to parse benchmark buffer size.\n"); + } + } else { + fill_param->buf_size = DEFAULT_SPAN; + } + + if (uparams->benchmark_cmd[2]) { + errno = 0; + fill_param->memflush = strtol(uparams->benchmark_cmd[2], &endptr, 10); + if (errno || uparams->benchmark_cmd[2] == endptr) { + free(fill_param); + ksft_exit_skip("Unable to parse benchmark memflush parameter.\n"); + } + } else { + fill_param->memflush = 1; + } + + if (uparams->benchmark_cmd[3]) { + if (strcmp(uparams->benchmark_cmd[3], "0")) { + free(fill_param); + ksft_exit_skip("Only read operations supported.\n"); + } + } + + if (uparams->benchmark_cmd[4]) { + if (strcmp(uparams->benchmark_cmd[4], "false")) { + free(fill_param); + ksft_exit_skip("fill_buf is required to run until termination.\n"); + } + } + + return fill_param; +} + static void init_user_params(struct user_params *uparams) { memset(uparams, 0, sizeof(*uparams)); @@ -158,11 +230,11 @@ static void init_user_params(struct user_params *uparams)

int main(int argc, char **argv) { + struct fill_buf_param *fill_param = NULL; int tests = ARRAY_SIZE(resctrl_tests); bool test_param_seen = false; struct user_params uparams; - char *span_str = NULL; - int ret, c, i; + int c, i;

init_user_params(&uparams);

@@ -239,6 +311,10 @@ int main(int argc, char **argv) } last_arg:

+ fill_param = alloc_fill_buf_param(&uparams); + if (fill_param) + uparams.fill_buf = fill_param; + ksft_print_header();

/* @@ -257,33 +333,11 @@ int main(int argc, char **argv)

filter_dmesg();

- if (!uparams.benchmark_cmd[0]) { - /* If no benchmark is given by "-b" argument, use fill_buf. */ - uparams.benchmark_cmd[0] = "fill_buf"; - ret = asprintf(&span_str, "%u", DEFAULT_SPAN); - if (ret < 0) - ksft_exit_fail_msg("Out of memory!\n"); - uparams.benchmark_cmd[1] = span_str; - uparams.benchmark_cmd[2] = "1"; - /* - * Third parameter was previously used for "operation" - * (read/write) of which only (now default) "read"/"0" - * works. - * Fourth parameter was previously used to indicate - * how long "fill_buf" should run for, with "false" - * ("fill_buf" will keep running until terminated) - * the only option that works. - */ - uparams.benchmark_cmd[3] = NULL; - uparams.benchmark_cmd[4] = NULL; - uparams.benchmark_cmd[5] = NULL; - } - ksft_set_plan(tests);

for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) run_single_test(resctrl_tests[i], &uparams);

- free(span_str); + free(fill_param); ksft_finished(); } diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index a1e097dc8e05..380c3f218d01 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -535,6 +535,11 @@ int measure_read_mem_bw(const struct user_params *uparams, return ret; }

+struct benchmark_info { + const struct user_params *uparams; + struct resctrl_val_param *param; +}; + /* * run_benchmark - Run a specified benchmark or fill_buf (default benchmark) * in specified signal. Direct benchmark stdio to /dev/null. @@ -544,12 +549,15 @@ int measure_read_mem_bw(const struct user_params *uparams, */ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) { - char **benchmark_cmd; - int ret, memflush; - size_t span; + struct benchmark_info *benchmark_info; + const struct user_params *uparams; + struct resctrl_val_param *param; FILE *fp; + int ret;

- benchmark_cmd = info->si_ptr; + benchmark_info = info->si_ptr; + uparams = benchmark_info->uparams; + param = benchmark_info->param;

/* * Direct stdio of child to /dev/null, so that only parent writes to @@ -561,16 +569,13 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) parent_exit(ppid); }

- 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]); - - if (run_fill_buf(span, memflush)) + if (param->fill_buf) { + if (run_fill_buf(param->fill_buf->buf_size, + param->fill_buf->memflush)) fprintf(stderr, "Error in running fill buffer\n"); - } else { + } else if (uparams->benchmark_cmd[0]) { /* Execute specified benchmark */ - ret = execvp(benchmark_cmd[0], benchmark_cmd); + ret = execvp(uparams->benchmark_cmd[0], (char **)uparams->benchmark_cmd); if (ret) ksft_perror("execvp"); } @@ -585,16 +590,15 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) * the benchmark * @test: test information structure * @uparams: user supplied parameters - * @benchmark_cmd: benchmark command and its arguments * @param: parameters passed to resctrl_val() * * Return: 0 when the test was run, < 0 on error. */ int resctrl_val(const struct resctrl_test *test, const struct user_params *uparams, - const char * const *benchmark_cmd, struct resctrl_val_param *param) { + struct benchmark_info benchmark_info; struct sigaction sigact; int ret = 0, pipefd[2]; char pipe_message = 0; @@ -610,6 +614,9 @@ int resctrl_val(const struct resctrl_test *test, return ret; }

+ benchmark_info.uparams = uparams; + benchmark_info.param = param; + /* * If benchmark wasn't successfully started by child, then child should * kill parent, so save parent's pid @@ -671,13 +678,7 @@ int resctrl_val(const struct resctrl_test *test,

ksft_print_msg("Benchmark PID: %d\n", (int)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; + value.sival_ptr = (void *)&benchmark_info;

/* Taskset benchmark to specified cpu */ ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);

The MBA test incrementally throttles memory bandwidth, each time followed by a comparison between the memory bandwidth observed by the performance counters and resctrl respectively.

While a comparison between performance counters and resctrl is generally appropriate, they do not have an identical view of memory bandwidth. For example RAS features or memory performance features that generate memory traffic may drive accesses that are counted differently by performance counters and MBM respectively, for instance generating "overhead" traffic which is not counted against any specific RMID. As a ratio, this different view of memory bandwidth becomes more apparent at low memory bandwidths.

It is not practical to enable/disable the various features that may generate memory bandwidth to give performance counters and resctrl an identical view. Instead, do not compare performance counters and resctrl view of memory bandwidth when the memory bandwidth is low.

Bandwidth throttling behaves differently across platforms so it is not appropriate to drop measurement data simply based on the throttling level. Instead, use a threshold of 750MiB that has been observed to support adequate comparison between performance counters and resctrl.

Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - Fix code alignment and spacing. - Modify flow to use "continue" instead of "break" now that earlier changes decreases throttling. - Expand comment of define to elaborate causes of discrepancy between performance counters and MBM. --- tools/testing/selftests/resctrl/mba_test.c | 7 +++++++ tools/testing/selftests/resctrl/resctrl.h | 10 ++++++++++ 2 files changed, 17 insertions(+)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index d8d9637c1951..5c6063d0a77c 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -98,6 +98,13 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)

avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1); avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1); + if (avg_bw_imc < THROTTLE_THRESHOLD || avg_bw_resc < THROTTLE_THRESHOLD) { + ksft_print_msg("Bandwidth below threshold (%d MiB). Dropping results from MBA schemata %u.\n", + THROTTLE_THRESHOLD, + ALLOCATION_MIN + ALLOCATION_STEP * allocation); + continue; + } + avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; avg_diff_per = (int)(avg_diff * 100);

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index dc01dc75cba5..eb151ac74938 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -43,6 +43,16 @@

#define DEFAULT_SPAN (250 * MB)

+/* + * Memory bandwidth (in MiB) below which the bandwidth comparisons + * between iMC and resctrl are considered unreliable. For example RAS + * features or memory performance features that generate memory traffic + * may drive accesses that are counted differently by performance counters + * and MBM respectively, for instance generating "overhead" traffic which + * is not counted against any specific RMID. + */ +#define THROTTLE_THRESHOLD 750 + /* * fill_buf_param: "fill_buf" benchmark parameters * @buf_size: Size (in bytes) of buffer used in benchmark.

The resctrl selftests drop the results from every first test run to avoid (per comment) "inaccurate due to monitoring setup transition phase" data. Previously inaccurate data resulted from workloads needing some time to "settle" and also the measurements themselves to account for earlier measurements to measure across needed timeframe.

commit da50de0a92f3 ("selftests/resctrl: Calculate resctrl FS derived mem bw over sleep(1) only")

ensured that measurements accurately measure just the time frame of interest. The default "fill_buf" benchmark since separated the buffer prepare phase from the benchmark run phase reducing the need for the tests themselves to accommodate the benchmark's "settle" time.

With these enhancements there are no remaining portions needing to "settle" and the first test run can contribute to measurements.

Signed-off-by: Reinette Chatre reinette.chatre@intel.com --- Changes since V1: - Remove comment about needing results from first run removed. - Fix existing incorrect spacing while changing line. --- tools/testing/selftests/resctrl/cmt_test.c | 5 ++--- tools/testing/selftests/resctrl/mba_test.c | 10 +++------- tools/testing/selftests/resctrl/mbm_test.c | 10 +++------- 3 files changed, 8 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index a7effe76b419..d4b85d144985 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -99,14 +99,13 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of }

/* Field 3 is llc occ resc value */ - if (runs > 0) - sum_llc_occu_resc += strtoul(token_array[3], NULL, 0); + sum_llc_occu_resc += strtoul(token_array[3], NULL, 0); runs++; } fclose(fp);

return show_results_info(sum_llc_occu_resc, no_of_bits, span, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true); + MAX_DIFF, MAX_DIFF_PERCENT, runs, true); }

static void cmt_test_cleanup(void) diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 5c6063d0a77c..89c2446b9f80 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -86,18 +86,14 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) 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; + for (runs = NUM_OF_RUNS * allocation; 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_bw_imc = sum_bw_imc / NUM_OF_RUNS; + avg_bw_resc = sum_bw_resc / NUM_OF_RUNS; if (avg_bw_imc < THROTTLE_THRESHOLD || avg_bw_resc < THROTTLE_THRESHOLD) { ksft_print_msg("Bandwidth below threshold (%d MiB). Dropping results from MBA schemata %u.\n", THROTTLE_THRESHOLD, diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 7635ee6b9339..8c818e292dce 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -22,17 +22,13 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) 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++) { + for (runs = 0; 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_bw_imc = sum_bw_imc / NUM_OF_RUNS; + avg_bw_resc = sum_bw_resc / NUM_OF_RUNS; avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; avg_diff_per = (int)(avg_diff * 100);