diff options
| -rw-r--r-- | tools/perf/Documentation/perf-stat.txt | 16 | ||||
| -rw-r--r-- | tools/perf/builtin-stat.c | 56 |
2 files changed, 72 insertions, 0 deletions
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 29bdcfa93f04..785f0e2bcfac 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -308,6 +308,14 @@ use --per-die in addition to -a. (system-wide). The output includes the die number and the number of online processors on that die. This is useful to gauge the amount of aggregation. +--per-cache:: +Aggregate counts per cache instance for system-wide mode measurements. By +default, the aggregation happens for the cache level at the highest index +in the system. To specify a particular level, mention the cache level +alongside the option in the format [Ll][1-9][0-9]*. For example: +Using option "--per-cache=l3" or "--per-cache=L3" will aggregate the +information at the boundary of the level 3 cache in the system. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. This is a useful mode to detect imbalance between physical cores. To enable this mode, @@ -379,6 +387,14 @@ Aggregate counts per processor socket for system-wide mode measurements. --per-die:: Aggregate counts per processor die for system-wide mode measurements. +--per-cache:: +Aggregate counts per cache instance for system-wide mode measurements. By +default, the aggregation happens for the cache level at the highest index +in the system. To specify a particular level, mention the cache level +alongside the option in the format [Ll][1-9][0-9]*. For example: Using +option "--per-cache=l3" or "--per-cache=L3" will aggregate the +information at the boundary of the level 3 cache in the system. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0528d1bc15d2..176deeb8ee66 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1113,6 +1113,55 @@ static int parse_cputype(const struct option *opt, return 0; } +static int parse_cache_level(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + int level; + u32 *aggr_mode = (u32 *)opt->value; + u32 *aggr_level = (u32 *)opt->data; + + /* + * If no string is specified, aggregate based on the topology of + * Last Level Cache (LLC). Since the LLC level can change from + * architecture to architecture, set level greater than + * MAX_CACHE_LVL which will be interpreted as LLC. + */ + if (str == NULL) { + level = MAX_CACHE_LVL + 1; + goto out; + } + + /* + * The format to specify cache level is LX or lX where X is the + * cache level. + */ + if (strlen(str) != 2 || (str[0] != 'l' && str[0] != 'L')) { + pr_err("Cache level must be of form L[1-%d], or l[1-%d]\n", + MAX_CACHE_LVL, + MAX_CACHE_LVL); + return -EINVAL; + } + + level = atoi(&str[1]); + if (level < 1) { + pr_err("Cache level must be of form L[1-%d], or l[1-%d]\n", + MAX_CACHE_LVL, + MAX_CACHE_LVL); + return -EINVAL; + } + + if (level > MAX_CACHE_LVL) { + pr_err("perf only supports max cache level of %d.\n" + "Consider increasing MAX_CACHE_LVL\n", MAX_CACHE_LVL); + return -EINVAL; + } +out: + *aggr_mode = AGGR_CACHE; + *aggr_level = level; + return 0; +} + static struct option stat_options[] = { OPT_BOOLEAN('T', "transaction", &transaction_run, "hardware transaction statistics"), @@ -1190,6 +1239,9 @@ static struct option stat_options[] = { "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode, "aggregate counts per processor die", AGGR_DIE), + OPT_CALLBACK_OPTARG(0, "per-cache", &stat_config.aggr_mode, &stat_config.aggr_level, + "cache level", "aggregate count at this cache level (Default: LLC)", + parse_cache_level), OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode, @@ -2346,6 +2398,10 @@ static int __cmd_report(int argc, const char **argv) "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode, "aggregate counts per processor die", AGGR_DIE), + OPT_CALLBACK_OPTARG(0, "per-cache", &perf_stat.aggr_mode, &perf_stat.aggr_level, + "cache level", + "aggregate count at this cache level (Default: LLC)", + parse_cache_level), OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), OPT_SET_UINT(0, "per-node", &perf_stat.aggr_mode, |