diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt new file mode 100644 index 0000000000000000000000000000000000000000..888d51137fbe61e0dc04546b36a46486a9d9a555 --- /dev/null +++ b/tools/perf/Documentation/perf-mem.txt @@ -0,0 +1,48 @@ +perf-mem(1) +=========== + +NAME +---- +perf-mem - Profile memory accesses + +SYNOPSIS +-------- +[verse] +'perf mem' [] (record [] | report) + +DESCRIPTION +----------- +"perf mem -t record" runs a command and gathers memory operation data +from it, into perf.data. Perf record options are accepted and are passed through. + +"perf mem -t report" displays the result. It invokes perf report with the +right set of options to display a memory access profile. + +OPTIONS +------- +...:: + Any command you can specify in a shell. + +-t:: +--type=:: + Select the memory operation type: load or store (default: load) + +-D:: +--dump-raw-samples=:: + Dump the raw decoded samples on the screen in a format that is easy to parse with + one sample per line. + +-x:: +--field-separator:: + Specify the field separator used when dump raw samples (-D option). By default, + The separator is the space character. + +-C:: +--cpu-list:: + Restrict dump of raw samples to those provided via this option. Note that the same + option can be passed in record mode. It will be interpreted the same way as perf + record. + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 0230b75ed7f976d2f8a6e1182bb57bdad642a9a7..07feae773dc1e51c537f52dcd0b11216702dc51b 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -547,6 +547,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-lock.o BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o BUILTIN_OBJS += $(OUTPUT)builtin-inject.o BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o +BUILTIN_OBJS += $(OUTPUT)builtin-mem.o PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c new file mode 100644 index 0000000000000000000000000000000000000000..a8ff6d264e502bb576db15bb175f1f67ffe743c4 --- /dev/null +++ b/tools/perf/builtin-mem.c @@ -0,0 +1,242 @@ +#include "builtin.h" +#include "perf.h" + +#include "util/parse-options.h" +#include "util/trace-event.h" +#include "util/tool.h" +#include "util/session.h" + +#define MEM_OPERATION_LOAD "load" +#define MEM_OPERATION_STORE "store" + +static const char *mem_operation = MEM_OPERATION_LOAD; + +struct perf_mem { + struct perf_tool tool; + char const *input_name; + symbol_filter_t annotate_init; + bool hide_unresolved; + bool dump_raw; + const char *cpu_list; + DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +}; + +static const char * const mem_usage[] = { + "perf mem [] {record |report}", + NULL +}; + +static int __cmd_record(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + char event[64]; + int ret; + + rec_argc = argc + 4; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + if (!rec_argv) + return -1; + + rec_argv[i++] = strdup("record"); + if (!strcmp(mem_operation, MEM_OPERATION_LOAD)) + rec_argv[i++] = strdup("-W"); + rec_argv[i++] = strdup("-d"); + rec_argv[i++] = strdup("-e"); + + if (strcmp(mem_operation, MEM_OPERATION_LOAD)) + sprintf(event, "cpu/mem-stores/pp"); + else + sprintf(event, "cpu/mem-loads/pp"); + + rec_argv[i++] = strdup(event); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + ret = cmd_record(i, rec_argv, NULL); + free(rec_argv); + return ret; +} + +static int +dump_raw_samples(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine) +{ + struct perf_mem *mem = container_of(tool, struct perf_mem, tool); + struct addr_location al; + const char *fmt; + + if (perf_event__preprocess_sample(event, machine, &al, sample, + mem->annotate_init) < 0) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (al.filtered || (mem->hide_unresolved && al.sym == NULL)) + return 0; + + if (al.map != NULL) + al.map->dso->hit = 1; + + if (symbol_conf.field_sep) { + fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64 + "%s0x%"PRIx64"%s%s:%s\n"; + } else { + fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 + "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; + symbol_conf.field_sep = " "; + } + + printf(fmt, + sample->pid, + symbol_conf.field_sep, + sample->tid, + symbol_conf.field_sep, + event->ip.ip, + symbol_conf.field_sep, + sample->addr, + symbol_conf.field_sep, + sample->weight, + symbol_conf.field_sep, + sample->data_src, + symbol_conf.field_sep, + al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + al.sym ? al.sym->name : "???"); + + return 0; +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + return dump_raw_samples(tool, event, sample, evsel, machine); +} + +static int report_raw_events(struct perf_mem *mem) +{ + int err = -EINVAL; + int ret; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, + 0, false, &mem->tool); + + if (session == NULL) + return -ENOMEM; + + if (mem->cpu_list) { + ret = perf_session__cpu_bitmap(session, mem->cpu_list, + mem->cpu_bitmap); + if (ret) + goto out_delete; + } + + if (symbol__init() < 0) + return -1; + + printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); + + err = perf_session__process_events(session, &mem->tool); + if (err) + return err; + + return 0; + +out_delete: + perf_session__delete(session); + return err; +} + +static int report_events(int argc, const char **argv, struct perf_mem *mem) +{ + const char **rep_argv; + int ret, i = 0, j, rep_argc; + + if (mem->dump_raw) + return report_raw_events(mem); + + rep_argc = argc + 3; + rep_argv = calloc(rep_argc + 1, sizeof(char *)); + if (!rep_argv) + return -1; + + rep_argv[i++] = strdup("report"); + rep_argv[i++] = strdup("--mem-mode"); + rep_argv[i++] = strdup("-n"); /* display number of samples */ + + /* + * there is no weight (cost) associated with stores, so don't print + * the column + */ + if (strcmp(mem_operation, MEM_OPERATION_LOAD)) + rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"); + + for (j = 1; j < argc; j++, i++) + rep_argv[i] = argv[j]; + + ret = cmd_report(i, rep_argv, NULL); + free(rep_argv); + return ret; +} + +int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) +{ + struct stat st; + struct perf_mem mem = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_fork, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + }, + .input_name = "perf.data", + }; + const struct option mem_options[] = { + OPT_STRING('t', "type", &mem_operation, + "type", "memory operations(load/store)"), + OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw, + "dump raw samples in ASCII"), + OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved, + "Only display entries resolved to a symbol"), + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", + "list of cpus to profile"), + OPT_STRING('x', "field-separator", &symbol_conf.field_sep, + "separator", + "separator for columns, no spaces will be added" + " between columns '.' is reserved."), + OPT_END() + }; + + argc = parse_options(argc, argv, mem_options, mem_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation)) + usage_with_options(mem_usage, mem_options); + + if (!mem.input_name || !strlen(mem.input_name)) { + if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) + mem.input_name = "-"; + else + mem.input_name = "perf.data"; + } + + if (!strncmp(argv[0], "rec", 3)) + return __cmd_record(argc, argv); + else if (!strncmp(argv[0], "rep", 3)) + return report_events(argc, argv, &mem); + else + usage_with_options(mem_usage, mem_options); + + return 0; +} diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 08143bd854c7db8b09369ee9e108d9dd09714518..b210d62907e4d87853ce25bdfd86d3eee74c3e09 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -36,6 +36,7 @@ extern int cmd_kvm(int argc, const char **argv, const char *prefix); extern int cmd_test(int argc, const char **argv, const char *prefix); extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_inject(int argc, const char **argv, const char *prefix); +extern int cmd_mem(int argc, const char **argv, const char *prefix); extern int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index a28e31be6cb4d4c55127fb202e6f7fc7793075a4..0906fc401c520aa2c49f38f4e54447cd788ee425 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -14,6 +14,7 @@ perf-kmem mainporcelain common perf-kvm mainporcelain common perf-list mainporcelain common perf-lock mainporcelain common +perf-mem mainporcelain common perf-probe mainporcelain full perf-record mainporcelain common perf-report mainporcelain common diff --git a/tools/perf/perf.c b/tools/perf/perf.c index f6ba7b73f40e18c15f35a13245eb18cac8115ed1..31c9380cfa64dfdea747140d52bebdad6455966b 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -60,6 +60,7 @@ static struct cmd_struct commands[] = { { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, + { "mem", cmd_mem, 0 }, }; struct pager_config { diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 99cc719ce736945c03dca844266d1b51b59e454d..6b32721f829a487cfda9ecb60c411fa216ab96aa 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -520,6 +520,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__free(struct hist_entry *he) { free(he->branch_info); + free(he->mem_info); free(he); }