diff options
Diffstat (limited to 'tools/perf')
38 files changed, 1216 insertions, 692 deletions
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 44b0ce3..eac4d852e 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -8,16 +8,16 @@ perf-kmem - Tool to trace/measure kernel memory(slab) properties SYNOPSIS -------- [verse] -'perf kmem' {record} [<options>] +'perf kmem' {record|stat} [<options>] DESCRIPTION ----------- -There's two variants of perf kmem: +There are two variants of perf kmem: 'perf kmem record <command>' to record the kmem events of an arbitrary workload. - 'perf kmem' to report kernel memory statistics. + 'perf kmem stat' to report kernel memory statistics. OPTIONS ------- @@ -25,8 +25,11 @@ OPTIONS --input=<file>:: Select the input file (default: perf.data) ---stat=<caller|alloc>:: - Select per callsite or per allocation statistics +--caller:: + Show per-callsite statistics + +--alloc:: + Show per-allocation statistics -s <key[,key2...]>:: --sort=<key[,key2...]>:: diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 9270594..8fa6bf9 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -8,10 +8,13 @@ perf-probe - Define new dynamic tracepoints SYNOPSIS -------- [verse] -'perf probe' [options] --add 'PROBE' [--add 'PROBE' ...] +'perf probe' [options] --add='PROBE' [...] or -'perf probe' [options] 'PROBE' ['PROBE' ...] - +'perf probe' [options] PROBE +or +'perf probe' [options] --del='[GROUP:]EVENT' [...] +or +'perf probe' --list DESCRIPTION ----------- @@ -31,8 +34,16 @@ OPTIONS Be more verbose (show parsed arguments, etc). -a:: ---add:: - Define a probe point (see PROBE SYNTAX for detail) +--add=:: + Define a probe event (see PROBE SYNTAX for detail). + +-d:: +--del=:: + Delete a probe event. + +-l:: +--list:: + List up current probe events. PROBE SYNTAX ------------ diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 23ec6609..4069996 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -237,8 +237,8 @@ lib = lib export prefix bindir sharedir sysconfdir -CC = gcc -AR = ar +CC = $(CROSS_COMPILE)gcc +AR = $(CROSS_COMPILE)ar RM = rm -f TAR = tar FIND = find @@ -356,7 +356,9 @@ LIB_H += util/parse-options.h LIB_H += util/parse-events.h LIB_H += util/quote.h LIB_H += util/util.h +LIB_H += util/header.h LIB_H += util/help.h +LIB_H += util/session.h LIB_H += util/strbuf.h LIB_H += util/string.h LIB_H += util/strlist.h @@ -405,6 +407,7 @@ LIB_OBJS += util/callchain.o LIB_OBJS += util/values.o LIB_OBJS += util/debug.o LIB_OBJS += util/map.o +LIB_OBJS += util/session.o LIB_OBJS += util/thread.o LIB_OBJS += util/trace-event-parse.o LIB_OBJS += util/trace-event-read.o @@ -492,8 +495,10 @@ else LIB_OBJS += util/probe-finder.o endif +ifndef NO_LIBPERL PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null` PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +endif ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o /dev/null $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) BASIC_CFLAGS += -DNO_LIBPERL diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index 605a2a9..81cee78 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -1,6 +1,6 @@ /* * - * builtin-bench-messaging.c + * sched-messaging.c * * messaging: Benchmark for scheduler and IPC mechanisms * @@ -320,10 +320,12 @@ int bench_sched_messaging(int argc, const char **argv, num_groups, num_groups * 2 * num_fds, thread_mode ? "threads" : "processes"); printf(" %14s: %lu.%03lu [sec]\n", "Total time", - diff.tv_sec, diff.tv_usec/1000); + diff.tv_sec, + (unsigned long) (diff.tv_usec/1000)); break; case BENCH_FORMAT_SIMPLE: - printf("%lu.%03lu\n", diff.tv_sec, diff.tv_usec/1000); + printf("%lu.%03lu\n", diff.tv_sec, + (unsigned long) (diff.tv_usec/1000)); break; default: /* reaching here is something disaster */ diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 238185f..4f77c7c 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -1,6 +1,6 @@ /* * - * builtin-bench-pipe.c + * sched-pipe.c * * pipe: Benchmark for pipe() * @@ -87,7 +87,8 @@ int bench_sched_pipe(int argc, const char **argv, if (pid) { retpid = waitpid(pid, &wait_stat, 0); assert((retpid == pid) && WIFEXITED(wait_stat)); - return 0; + } else { + exit(0); } switch (bench_format) { @@ -99,7 +100,8 @@ int bench_sched_pipe(int argc, const char **argv, result_usec += diff.tv_usec; printf(" %14s: %lu.%03lu [sec]\n\n", "Total time", - diff.tv_sec, diff.tv_usec/1000); + diff.tv_sec, + (unsigned long) (diff.tv_usec/1000)); printf(" %14lf usecs/op\n", (double)result_usec / (double)loops); @@ -110,7 +112,8 @@ int bench_sched_pipe(int argc, const char **argv, case BENCH_FORMAT_SIMPLE: printf("%lu.%03lu\n", - diff.tv_sec, diff.tv_usec / 1000); + diff.tv_sec, + (unsigned long) (diff.tv_usec / 1000)); break; default: diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 0bf2e8f9..21a78d3 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -25,6 +25,7 @@ #include "util/thread.h" #include "util/sort.h" #include "util/hist.h" +#include "util/session.h" #include "util/data_map.h" static char const *input_name = "perf.data"; @@ -462,21 +463,23 @@ static struct perf_file_handler file_handler = { static int __cmd_annotate(void) { - struct perf_header *header; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, force); struct thread *idle; int ret; + if (session == NULL) + return -ENOMEM; + idle = register_idle_thread(); register_perf_file_handler(&file_handler); - ret = mmap_dispatch_perf_file(&header, input_name, 0, 0, - &event__cwdlen, &event__cwd); + ret = perf_session__process_events(session, 0, &event__cwdlen, &event__cwd); if (ret) - return ret; + goto out_delete; if (dump_trace) { event__print_totals(); - return 0; + goto out_delete; } if (verbose > 3) @@ -489,6 +492,8 @@ static int __cmd_annotate(void) output__resort(event__total[0]); find_annotations(); +out_delete: + perf_session__delete(session); return ret; } diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index e043eb8..4699677 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -31,6 +31,9 @@ struct bench_suite { const char *summary; int (*fn)(int, const char **, const char *); }; + \ +/* sentinel: easy for help */ +#define suite_all { "all", "test all suite (pseudo suite)", NULL } static struct bench_suite sched_suites[] = { { "messaging", @@ -39,6 +42,7 @@ static struct bench_suite sched_suites[] = { { "pipe", "Flood of communication over pipe() between two processes", bench_sched_pipe }, + suite_all, { NULL, NULL, NULL } @@ -48,6 +52,7 @@ static struct bench_suite mem_suites[] = { { "memcpy", "Simple memory copy in various ways", bench_mem_memcpy }, + suite_all, { NULL, NULL, NULL } @@ -66,6 +71,9 @@ static struct bench_subsys subsystems[] = { { "mem", "memory access performance", mem_suites }, + { "all", /* sentinel: easy for help */ + "test all subsystem (pseudo subsystem)", + NULL }, { NULL, NULL, NULL } @@ -75,11 +83,11 @@ static void dump_suites(int subsys_index) { int i; - printf("List of available suites for %s...\n\n", + printf("# List of available suites for %s...\n\n", subsystems[subsys_index].name); for (i = 0; subsystems[subsys_index].suites[i].name; i++) - printf("\t%s: %s\n", + printf("%14s: %s\n", subsystems[subsys_index].suites[i].name, subsystems[subsys_index].suites[i].summary); @@ -110,10 +118,10 @@ static void print_usage(void) printf("\t%s\n", bench_usage[i]); printf("\n"); - printf("List of available subsystems...\n\n"); + printf("# List of available subsystems...\n\n"); for (i = 0; subsystems[i].name; i++) - printf("\t%s: %s\n", + printf("%14s: %s\n", subsystems[i].name, subsystems[i].summary); printf("\n"); } @@ -131,6 +139,37 @@ static int bench_str2int(char *str) return BENCH_FORMAT_UNKNOWN; } +static void all_suite(struct bench_subsys *subsys) /* FROM HERE */ +{ + int i; + const char *argv[2]; + struct bench_suite *suites = subsys->suites; + + argv[1] = NULL; + /* + * TODO: + * preparing preset parameters for + * embedded, ordinary PC, HPC, etc... + * will be helpful + */ + for (i = 0; suites[i].fn; i++) { + printf("# Running %s/%s benchmark...\n", + subsys->name, + suites[i].name); + + argv[1] = suites[i].name; + suites[i].fn(1, argv, NULL); + printf("\n"); + } +} + +static void all_subsystem(void) +{ + int i; + for (i = 0; subsystems[i].suites; i++) + all_suite(&subsystems[i]); +} + int cmd_bench(int argc, const char **argv, const char *prefix __used) { int i, j, status = 0; @@ -155,6 +194,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used) goto end; } + if (!strcmp(argv[0], "all")) { + all_subsystem(); + goto end; + } + for (i = 0; subsystems[i].name; i++) { if (strcmp(subsystems[i].name, argv[0])) continue; @@ -165,6 +209,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used) goto end; } + if (!strcmp(argv[1], "all")) { + all_suite(&subsystems[i]); + goto end; + } + for (j = 0; subsystems[i].suites[j].name; j++) { if (strcmp(subsystems[i].suites[j].name, argv[1])) continue; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 7dee9d19..bfd16a1 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -11,15 +11,15 @@ #include "util/cache.h" #include "util/data_map.h" #include "util/debug.h" -#include "util/header.h" #include "util/parse-options.h" +#include "util/session.h" #include "util/symbol.h" static char const *input_name = "perf.data"; static int force; static const char *const buildid_list_usage[] = { - "perf report [<options>]", + "perf buildid-list [<options>]", NULL }; @@ -55,56 +55,17 @@ static int perf_file_section__process_buildids(struct perf_file_section *self, static int __cmd_buildid_list(void) { int err = -1; - struct perf_header *header; - struct perf_file_header f_header; - struct stat input_stat; - int input = open(input_name, O_RDONLY); + struct perf_session *session = perf_session__new(input_name, O_RDONLY, force); - if (input < 0) { - pr_err("failed to open file: %s", input_name); - if (!strcmp(input_name, "perf.data")) - pr_err(" (try 'perf record' first)"); - pr_err("\n"); - goto out; - } - - err = fstat(input, &input_stat); - if (err < 0) { - perror("failed to stat file"); - goto out_close; - } - - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", - input_name); - goto out_close; - } - - if (!input_stat.st_size) { - pr_info("zero-sized file, nothing to do!\n"); - goto out_close; - } - - err = -1; - header = perf_header__new(); - if (header == NULL) - goto out_close; - - if (perf_file_header__read(&f_header, header, input) < 0) { - pr_warning("incompatible file format"); - goto out_close; - } + if (session == NULL) + return -1; - err = perf_header__process_sections(header, input, + err = perf_header__process_sections(&session->header, session->fd, perf_file_section__process_buildids); + if (err >= 0) + dsos__fprintf_buildid(stdout); - if (err < 0) - goto out_close; - - dsos__fprintf_buildid(stdout); -out_close: - close(input); -out: + perf_session__delete(session); return err; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 047fef7..2071d24 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -6,6 +6,7 @@ #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" +#include "util/session.h" #include "util/parse-options.h" #include "util/trace-event.h" @@ -20,7 +21,6 @@ typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); static char const *input_name = "perf.data"; -static struct perf_header *header; static u64 sample_type; static int alloc_flag; @@ -57,11 +57,6 @@ static struct rb_root root_caller_sorted; static unsigned long total_requested, total_allocated; static unsigned long nr_allocs, nr_cross_allocs; -struct raw_event_sample { - u32 size; - char data[0]; -}; - #define PATH_SYS_NODE "/sys/devices/system/node" static void init_cpunode_map(void) @@ -201,7 +196,7 @@ static void insert_caller_stat(unsigned long call_site, } } -static void process_alloc_event(struct raw_event_sample *raw, +static void process_alloc_event(void *data, struct event *event, int cpu, u64 timestamp __used, @@ -214,10 +209,10 @@ static void process_alloc_event(struct raw_event_sample *raw, int bytes_alloc; int node1, node2; - ptr = raw_field_value(event, "ptr", raw->data); - call_site = raw_field_value(event, "call_site", raw->data); - bytes_req = raw_field_value(event, "bytes_req", raw->data); - bytes_alloc = raw_field_value(event, "bytes_alloc", raw->data); + ptr = raw_field_value(event, "ptr", data); + call_site = raw_field_value(event, "call_site", data); + bytes_req = raw_field_value(event, "bytes_req", data); + bytes_alloc = raw_field_value(event, "bytes_alloc", data); insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu); insert_caller_stat(call_site, bytes_req, bytes_alloc); @@ -227,7 +222,7 @@ static void process_alloc_event(struct raw_event_sample *raw, if (node) { node1 = cpunode_map[cpu]; - node2 = raw_field_value(event, "node", raw->data); + node2 = raw_field_value(event, "node", data); if (node1 != node2) nr_cross_allocs++; } @@ -262,7 +257,7 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr, return NULL; } -static void process_free_event(struct raw_event_sample *raw, +static void process_free_event(void *data, struct event *event, int cpu, u64 timestamp __used, @@ -271,7 +266,7 @@ static void process_free_event(struct raw_event_sample *raw, unsigned long ptr; struct alloc_stat *s_alloc, *s_caller; - ptr = raw_field_value(event, "ptr", raw->data); + ptr = raw_field_value(event, "ptr", data); s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp); if (!s_alloc) @@ -289,66 +284,53 @@ static void process_free_event(struct raw_event_sample *raw, } static void -process_raw_event(event_t *raw_event __used, void *more_data, +process_raw_event(event_t *raw_event __used, void *data, int cpu, u64 timestamp, struct thread *thread) { - struct raw_event_sample *raw = more_data; struct event *event; int type; - type = trace_parse_common_type(raw->data); + type = trace_parse_common_type(data); event = trace_find_event(type); if (!strcmp(event->name, "kmalloc") || !strcmp(event->name, "kmem_cache_alloc")) { - process_alloc_event(raw, event, cpu, timestamp, thread, 0); + process_alloc_event(data, event, cpu, timestamp, thread, 0); return; } if (!strcmp(event->name, "kmalloc_node") || !strcmp(event->name, "kmem_cache_alloc_node")) { - process_alloc_event(raw, event, cpu, timestamp, thread, 1); + process_alloc_event(data, event, cpu, timestamp, thread, 1); return; } if (!strcmp(event->name, "kfree") || !strcmp(event->name, "kmem_cache_free")) { - process_free_event(raw, event, cpu, timestamp, thread); + process_free_event(data, event, cpu, timestamp, thread); return; } } static int process_sample_event(event_t *event) { - u64 ip = event->ip.ip; - u64 timestamp = -1; - u32 cpu = -1; - u64 period = 1; - void *more_data = event->ip.__more_data; - struct thread *thread = threads__findnew(event->ip.pid); - - if (sample_type & PERF_SAMPLE_TIME) { - timestamp = *(u64 *)more_data; - more_data += sizeof(u64); - } + struct sample_data data; + struct thread *thread; - if (sample_type & PERF_SAMPLE_CPU) { - cpu = *(u32 *)more_data; - more_data += sizeof(u32); - more_data += sizeof(u32); /* reserved */ - } + memset(&data, 0, sizeof(data)); + data.time = -1; + data.cpu = -1; + data.period = 1; - if (sample_type & PERF_SAMPLE_PERIOD) { - period = *(u64 *)more_data; - more_data += sizeof(u64); - } + event__parse_sample(event, sample_type, &data); dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, - event->ip.pid, event->ip.tid, - (void *)(long)ip, - (long long)period); + data.pid, data.tid, + (void *)(long)data.ip, + (long long)data.period); + thread = threads__findnew(event->ip.pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); @@ -357,7 +339,8 @@ static int process_sample_event(event_t *event) dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - process_raw_event(event, more_data, cpu, timestamp, thread); + process_raw_event(event, data.raw_data, data.cpu, + data.time, thread); return 0; } @@ -384,11 +367,18 @@ static struct perf_file_handler file_handler = { static int read_events(void) { + int err; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); + + if (session == NULL) + return -ENOMEM; + register_idle_thread(); register_perf_file_handler(&file_handler); - return mmap_dispatch_perf_file(&header, input_name, 0, 0, - &event__cwdlen, &event__cwd); + err = perf_session__process_events(session, 0, &event__cwdlen, &event__cwd); + perf_session__delete(session); + return err; } static double fragmentation(unsigned long n_req, unsigned long n_alloc) @@ -420,7 +410,7 @@ static void __print_result(struct rb_root *root, int n_lines, int is_caller) if (is_caller) { addr = data->call_site; if (!raw_ip) - sym = thread__find_function(kthread, addr, NULL); + sym = map_groups__find_function(kmaps, addr, NULL); } else addr = data->ptr; @@ -543,7 +533,7 @@ static int __cmd_kmem(void) } static const char * const kmem_usage[] = { - "perf kmem [<options>] {record}", + "perf kmem [<options>] {record|stat}", NULL }; @@ -703,18 +693,17 @@ static int parse_sort_opt(const struct option *opt __used, return 0; } -static int parse_stat_opt(const struct option *opt __used, - const char *arg, int unset __used) +static int parse_caller_opt(const struct option *opt __used, + const char *arg __used, int unset __used) { - if (!arg) - return -1; + caller_flag = (alloc_flag + 1); + return 0; +} - if (strcmp(arg, "alloc") == 0) - alloc_flag = (caller_flag + 1); - else if (strcmp(arg, "caller") == 0) - caller_flag = (alloc_flag + 1); - else - return -1; +static int parse_alloc_opt(const struct option *opt __used, + const char *arg __used, int unset __used) +{ + alloc_flag = (caller_flag + 1); return 0; } @@ -739,14 +728,17 @@ static int parse_line_opt(const struct option *opt __used, static const struct option kmem_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_CALLBACK(0, "stat", NULL, "<alloc>|<caller>", - "stat selector, Pass 'alloc' or 'caller'.", - parse_stat_opt), + OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL, + "show per-callsite statistics", + parse_caller_opt), + OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL, + "show per-allocation statistics", + parse_alloc_opt), OPT_CALLBACK('s', "sort", NULL, "key[,key2...]", "sort by keys: ptr, call_site, bytes, hit, pingpong, frag", parse_sort_opt), OPT_CALLBACK('l', "line", NULL, "num", - "show n lins", + "show n lines", parse_line_opt), OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), OPT_END() @@ -790,18 +782,22 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, kmem_options, kmem_usage, 0); - if (argc && !strncmp(argv[0], "rec", 3)) - return __cmd_record(argc, argv); - else if (argc) + if (!argc) usage_with_options(kmem_usage, kmem_options); - if (list_empty(&caller_sort)) - setup_sorting(&caller_sort, default_sort_order); - if (list_empty(&alloc_sort)) - setup_sorting(&alloc_sort, default_sort_order); + if (!strncmp(argv[0], "rec", 3)) { + return __cmd_record(argc, argv); + } else if (!strcmp(argv[0], "stat")) { + setup_cpunode_map(); - setup_cpunode_map(); + if (list_empty(&caller_sort)) + setup_sorting(&caller_sort, default_sort_order); + if (list_empty(&alloc_sort)) + setup_sorting(&alloc_sort, default_sort_order); - return __cmd_kmem(); + return __cmd_kmem(); + } + + return 0; } diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index a58e11b..5a47c1e 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -35,6 +35,7 @@ #include "perf.h" #include "builtin.h" #include "util/util.h" +#include "util/strlist.h" #include "util/event.h" #include "util/debug.h" #include "util/parse-options.h" @@ -43,11 +44,12 @@ #include "util/probe-event.h" /* Default vmlinux search paths */ -#define NR_SEARCH_PATH 3 +#define NR_SEARCH_PATH 4 const char *default_search_path[NR_SEARCH_PATH] = { "/lib/modules/%s/build/vmlinux", /* Custom build kernel */ "/usr/lib/debug/lib/modules/%s/vmlinux", /* Red Hat debuginfo */ "/boot/vmlinux-debug-%s", /* Ubuntu */ +"./vmlinux", /* CWD */ }; #define MAX_PATH_LEN 256 @@ -60,6 +62,7 @@ static struct { int need_dwarf; int nr_probe; struct probe_point probes[MAX_PROBES]; + struct strlist *dellist; } session; static bool listing; @@ -79,6 +82,25 @@ static void parse_probe_event(const char *str) pr_debug("%d arguments\n", pp->nr_args); } +static void parse_probe_event_argv(int argc, const char **argv) +{ + int i, len; + char *buf; + + /* Bind up rest arguments */ + len = 0; + for (i = 0; i < argc; i++) + len += strlen(argv[i]) + 1; + buf = zalloc(len + 1); + if (!buf) + die("Failed to allocate memory for binding arguments."); + len = 0; + for (i = 0; i < argc; i++) + len += sprintf(&buf[len], "%s ", argv[i]); + parse_probe_event(buf); + free(buf); +} + static int opt_add_probe_event(const struct option *opt __used, const char *str, int unset __used) { @@ -87,6 +109,17 @@ static int opt_add_probe_event(const struct option *opt __used, return 0; } +static int opt_del_probe_event(const struct option *opt __used, + const char *str, int unset __used) +{ + if (str) { + if (!session.dellist) + session.dellist = strlist__new(true, NULL); + strlist__add(session.dellist, str); + } + return 0; +} + #ifndef NO_LIBDWARF static int open_default_vmlinux(void) { @@ -121,6 +154,7 @@ static int open_default_vmlinux(void) static const char * const probe_usage[] = { "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", + "perf probe [<options>] --del '[GROUP:]EVENT' ...", "perf probe --list", NULL }; @@ -132,7 +166,9 @@ static const struct option options[] = { OPT_STRING('k', "vmlinux", &session.vmlinux, "file", "vmlinux/module pathname"), #endif - OPT_BOOLEAN('l', "list", &listing, "list up current probes"), + OPT_BOOLEAN('l', "list", &listing, "list up current probe events"), + OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.", + opt_del_probe_event), OPT_CALLBACK('a', "add", NULL, #ifdef NO_LIBDWARF "FUNC[+OFFS|%return] [ARG ...]", @@ -160,7 +196,7 @@ static const struct option options[] = { int cmd_probe(int argc, const char **argv, const char *prefix __used) { - int i, j, ret; + int i, ret; #ifndef NO_LIBDWARF int fd; #endif @@ -168,40 +204,52 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, options, probe_usage, PARSE_OPT_STOP_AT_NON_OPTION); - for (i = 0; i < argc; i++) - parse_probe_event(argv[i]); + if (argc > 0) + parse_probe_event_argv(argc, argv); - if ((session.nr_probe == 0 && !listing) || - (session.nr_probe != 0 && listing)) + if ((session.nr_probe == 0 && !session.dellist && !listing)) usage_with_options(probe_usage, options); if (listing) { + if (session.nr_probe != 0 || session.dellist) { + pr_warning(" Error: Don't use --list with" + " --add/--del.\n"); + usage_with_options(probe_usage, options); + } show_perf_probe_events(); return 0; } + if (session.dellist) { + del_trace_kprobe_events(session.dellist); + strlist__delete(session.dellist); + if (session.nr_probe == 0) + return 0; + } + if (session.need_dwarf) #ifdef NO_LIBDWARF die("Debuginfo-analysis is not supported"); #else /* !NO_LIBDWARF */ pr_debug("Some probes require debuginfo.\n"); - if (session.vmlinux) + if (session.vmlinux) { + pr_debug("Try to open %s.", session.vmlinux); fd = open(session.vmlinux, O_RDONLY); - else + } else fd = open_default_vmlinux(); if (fd < 0) { if (session.need_dwarf) - die("Could not open vmlinux/module file."); + die("Could not open debuginfo file."); - pr_warning("Could not open vmlinux/module file." - " Try to use symbols.\n"); + pr_debug("Could not open vmlinux/module file." + " Try to use symbols.\n"); goto end_dwarf; } /* Searching probe points */ - for (j = 0; j < session.nr_probe; j++) { - pp = &session.probes[j]; + for (i = 0; i < session.nr_probe; i++) { + pp = &session.probes[i]; if (pp->found) continue; @@ -223,8 +271,8 @@ end_dwarf: #endif /* !NO_LIBDWARF */ /* Synthesize probes without dwarf */ - for (j = 0; j < session.nr_probe; j++) { - pp = &session.probes[j]; + for (i = 0; i < session.nr_probe; i++) { + pp = &session.probes[i]; if (pp->found) /* This probe is already found. */ continue; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0e519c6..4decbd1 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -17,6 +17,7 @@ #include "util/header.h" #include "util/event.h" #include "util/debug.h" +#include "util/session.h" #include "util/symbol.h" #include <unistd.h> @@ -62,7 +63,7 @@ static int nr_cpu = 0; static int file_new = 1; -struct perf_header *header = NULL; +static struct perf_session *session; struct mmap_data { int counter; @@ -216,12 +217,12 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n { struct perf_header_attr *h_attr; - if (nr < header->attrs) { - h_attr = header->attr[nr]; + if (nr < session->header.attrs) { + h_attr = session->header.attr[nr]; } else { h_attr = perf_header_attr__new(a); if (h_attr != NULL) - if (perf_header__add_attr(header, h_attr) < 0) { + if (perf_header__add_attr(&session->header, h_attr) < 0) { perf_header_attr__delete(h_attr); h_attr = NULL; } @@ -395,9 +396,9 @@ static void open_counters(int cpu, pid_t pid) static void atexit_header(void) { - header->data_size += bytes_written; + session->header.data_size += bytes_written; - perf_header__write(header, output, true); + perf_header__write(&session->header, output, true); } static int __cmd_record(int argc, const char **argv) @@ -440,24 +441,24 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - header = perf_header__new(); - if (header == NULL) { + session = perf_session__new(output_name, O_WRONLY, force); + if (session == NULL) { pr_err("Not enough memory for reading perf file header\n"); return -1; } if (!file_new) { - err = perf_header__read(header, output); + err = perf_header__read(&session->header, output); if (err < 0) return err; } if (raw_samples) { - perf_header__set_feat(header, HEADER_TRACE_INFO); + perf_header__set_feat(&session->header, HEADER_TRACE_INFO); } else { for (i = 0; i < nr_counters; i++) { if (attrs[i].sample_type & PERF_SAMPLE_RAW) { - perf_header__set_feat(header, HEADER_TRACE_INFO); + perf_header__set_feat(&session->header, HEADER_TRACE_INFO); break; } } @@ -481,7 +482,7 @@ static int __cmd_record(int argc, const char **argv) } if (file_new) { - err = perf_header__write(header, output, false); + err = perf_header__write(&session->header, output, false); if (err < 0) return err; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 383c4ab..e2ec49a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -22,6 +22,7 @@ #include "perf.h" #include "util/debug.h" #include "util/header.h" +#include "util/session.h" #include "util/parse-options.h" #include "util/parse-events.h" @@ -52,7 +53,7 @@ static int exclude_other = 1; static char callchain_default_opt[] = "fractal,0.5"; -static struct perf_header *header; +static struct perf_session *session; static u64 sample_type; @@ -605,44 +606,41 @@ static int validate_chain(struct ip_callchain *chain, event_t *event) static int process_sample_event(event_t *event) { - u64 ip = event->ip.ip; - u64 period = 1; - void *more_data = event->ip.__more_data; - struct ip_callchain *chain = NULL; + struct sample_data data; int cpumode; struct addr_location al; - struct thread *thread = threads__findnew(event->ip.pid); + struct thread *thread; - if (sample_type & PERF_SAMPLE_PERIOD) { - period = *(u64 *)more_data; - more_data += sizeof(u64); - } + memset(&data, 0, sizeof(data)); + data.period = 1; + + event__parse_sample(event, sample_type, &data); dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, - event->ip.pid, event->ip.tid, - (void *)(long)ip, - (long long)period); + data.pid, data.tid, + (void *)(long)data.ip, + (long long)data.period); if (sample_type & PERF_SAMPLE_CALLCHAIN) { unsigned int i; - chain = (void *)more_data; + dump_printf("... chain: nr:%Lu\n", data.callchain->nr); - dump_printf("... chain: nr:%Lu\n", chain->nr); - - if (validate_chain(chain, event) < 0) { + if (validate_chain(data.callchain, event) < 0) { pr_debug("call-chain problem with event, " "skipping it.\n"); return 0; } if (dump_trace) { - for (i = 0; i < chain->nr; i++) - dump_printf("..... %2d: %016Lx\n", i, chain->ips[i]); + for (i = 0; i < data.callchain->nr; i++) + dump_printf("..... %2d: %016Lx\n", + i, data.callchain->ips[i]); } } + thread = threads__findnew(data.pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); @@ -657,7 +655,7 @@ static int process_sample_event(event_t *event) cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; thread__find_addr_location(thread, cpumode, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, data.ip, &al, NULL); /* * We have to do this here as we may have a dso with no symbol hit that * has a name longer than the ones with symbols sampled. @@ -675,12 +673,12 @@ static int process_sample_event(event_t *event) if (sym_list && al.sym && !strlist__has_entry(sym_list, al.sym->name)) return 0; - if (hist_entry__add(&al, chain, period)) { + if (hist_entry__add(&al, data.callchain, data.period)) { pr_debug("problem incrementing symbol count, skipping event\n"); return -1; } - event__stats.total += period; + event__stats.total += data.period; return 0; } @@ -704,7 +702,7 @@ static int process_read_event(event_t *event) { struct perf_event_attr *attr; - attr = perf_header__find_attr(event->read.id, header); + attr = perf_header__find_attr(event->read.id, &session->header); if (show_threads) { const char *name = attr ? __event_name(attr->type, attr->config) @@ -769,6 +767,10 @@ static int __cmd_report(void) struct thread *idle; int ret; + session = perf_session__new(input_name, O_RDONLY, force); + if (session == NULL) + return -ENOMEM; + idle = register_idle_thread(); thread__comm_adjust(idle); @@ -777,14 +779,14 @@ static int __cmd_report(void) register_perf_file_handler(&file_handler); - ret = mmap_dispatch_perf_file(&header, input_name, force, - full_paths, &event__cwdlen, &event__cwd); + ret = perf_session__process_events(session, full_paths, + &event__cwdlen, &event__cwd); if (ret) - return ret; + goto out_delete; if (dump_trace) { event__print_totals(); - return 0; + goto out_delete; } if (verbose > 3) @@ -799,7 +801,8 @@ static int __cmd_report(void) if (show_threads) perf_read_values_destroy(&show_threads_values); - +out_delete: + perf_session__delete(session); return ret; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 26b782f..65021fe 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -6,6 +6,7 @@ #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" +#include "util/session.h" #include "util/parse-options.h" #include "util/trace-event.h" @@ -13,7 +14,6 @@ #include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h> @@ -22,7 +22,6 @@ static char const *input_name = "perf.data"; -static struct perf_header *header; static u64 sample_type; static char default_sort_order[] = "avg, max, switch, runtime"; @@ -141,6 +140,7 @@ struct work_atoms { struct thread *thread; struct rb_node node; u64 max_lat; + u64 max_lat_at; u64 total_lat; u64 nb_atoms; u64 total_runtime; @@ -414,34 +414,33 @@ static u64 get_cpu_usage_nsec_parent(void) return sum; } -static u64 get_cpu_usage_nsec_self(void) +static int self_open_counters(void) { - char filename [] = "/proc/1234567890/sched"; - unsigned long msecs, nsecs; - char *line = NULL; - u64 total = 0; - size_t len = 0; - ssize_t chars; - FILE *file; - int ret; + struct perf_event_attr attr; + int fd; - sprintf(filename, "/proc/%d/sched", getpid()); - file = fopen(filename, "r"); - BUG_ON(!file); + memset(&attr, 0, sizeof(attr)); - while ((chars = getline(&line, &len, file)) != -1) { - ret = sscanf(line, "se.sum_exec_runtime : %ld.%06ld\n", - &msecs, &nsecs); - if (ret == 2) { - total = msecs*1e6 + nsecs; - break; - } - } - if (line) - free(line); - fclose(file); + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_TASK_CLOCK; + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - return total; + if (fd < 0) + die("Error: sys_perf_event_open() syscall returned" + "with %d (%s)\n", fd, strerror(errno)); + return fd; +} + +static u64 get_cpu_usage_nsec_self(int fd) +{ + u64 runtime; + int ret; + + ret = read(fd, &runtime, sizeof(runtime)); + BUG_ON(ret != sizeof(runtime)); + + return runtime; } static void *thread_func(void *ctx) @@ -450,9 +449,11 @@ static void *thread_func(void *ctx) u64 cpu_usage_0, cpu_usage_1; unsigned long i, ret; char comm2[22]; + int fd; sprintf(comm2, ":%s", this_task->comm); prctl(PR_SET_NAME, comm2); + fd = self_open_counters(); again: ret = sem_post(&this_task->ready_for_work); @@ -462,16 +463,15 @@ again: ret = pthread_mutex_unlock(&start_work_mutex); BUG_ON(ret); - cpu_usage_0 = get_cpu_usage_nsec_self(); + cpu_usage_0 = get_cpu_usage_nsec_self(fd); for (i = 0; i < this_task->nr_events; i++) { this_task->curr_event = i; process_sched_event(this_task, this_task->atoms[i]); } - cpu_usage_1 = get_cpu_usage_nsec_self(); + cpu_usage_1 = get_cpu_usage_nsec_self(fd); this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret = sem_post(&this_task->work_done_sem); BUG_ON(ret); @@ -628,11 +628,6 @@ static void test_calibrations(void) printf("the sleep test took %Ld nsecs\n", T1-T0); } -struct raw_event_sample { - u32 size; - char data[0]; -}; - #define FILL_FIELD(ptr, field, event, data) \ ptr.field = (typeof(ptr.field)) raw_field_value(event, #field, data) @@ -1019,8 +1014,10 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) delta = atom->sched_in_time - atom->wake_up_time; atoms->total_lat += delta; - if (delta > atoms->max_lat) + if (delta > atoms->max_lat) { atoms->max_lat = delta; + atoms->max_lat_at = timestamp; + } atoms->nb_atoms++; } @@ -1216,10 +1213,11 @@ static void output_lat_thread(struct work_atoms *work_list) avg = work_list->total_lat / work_list->nb_atoms; - printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms |\n", + printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", (double)work_list->total_runtime / 1e6, work_list->nb_atoms, (double)avg / 1e6, - (double)work_list->max_lat / 1e6); + (double)work_list->max_lat / 1e6, + (double)work_list->max_lat_at / 1e9); } static int pid_cmp(struct work_atoms *l, struct work_atoms *r) @@ -1356,7 +1354,7 @@ static void sort_lat(void) static struct trace_sched_handler *trace_handler; static void -process_sched_wakeup_event(struct raw_event_sample *raw, +process_sched_wakeup_event(void *data, struct event *event, int cpu __used, u64 timestamp __used, @@ -1364,13 +1362,13 @@ process_sched_wakeup_event(struct raw_event_sample *raw, { struct trace_wakeup_event wakeup_event; - FILL_COMMON_FIELDS(wakeup_event, event, raw->data); + FILL_COMMON_FIELDS(wakeup_event, event, data); - FILL_ARRAY(wakeup_event, comm, event, raw->data); - FILL_FIELD(wakeup_event, pid, event, raw->data); - FILL_FIELD(wakeup_event, prio, event, raw->data); - FILL_FIELD(wakeup_event, success, event, raw->data); - FILL_FIELD(wakeup_event, cpu, event, raw->data); + FILL_ARRAY(wakeup_event, comm, event, data); + FILL_FIELD(wakeup_event, pid, event, data); + FILL_FIELD(wakeup_event, prio, event, data); + FILL_FIELD(wakeup_event, success, event, data); + FILL_FIELD(wakeup_event, cpu, event, data); if (trace_handler->wakeup_event) trace_handler->wakeup_event(&wakeup_event, event, cpu, timestamp, thread); @@ -1469,7 +1467,7 @@ map_switch_event(struct trace_switch_event *switch_event, static void -process_sched_switch_event(struct raw_event_sample *raw, +process_sched_switch_event(void *data, struct event *event, int this_cpu, u64 timestamp __used, @@ -1477,15 +1475,15 @@ process_sched_switch_event(struct raw_event_sample *raw, { struct trace_switch_event switch_event; - FILL_COMMON_FIELDS(switch_event, event, raw->data); + FILL_COMMON_FIELDS(switch_event, event, data); - FILL_ARRAY(switch_event, prev_comm, event, raw->data); - FILL_FIELD(switch_event, prev_pid, event, raw->data); - FILL_FIELD(switch_event, prev_prio, event, raw->data); - FILL_FIELD(switch_event, prev_state, event, raw->data); - FILL_ARRAY(switch_event, next_comm, event, raw->data); - FILL_FIELD(switch_event, next_pid, event, raw->data); - FILL_FIELD(switch_event, next_prio, event, raw->data); + FILL_ARRAY(switch_event, prev_comm, event, data); + FILL_FIELD(switch_event, prev_pid, event, data); + FILL_FIELD(switch_event, prev_prio, event, data); + FILL_FIELD(switch_event, prev_state, event, data); + FILL_ARRAY(switch_event, next_comm, event, data); + FILL_FIELD(switch_event, next_pid, event, data); + FILL_FIELD(switch_event, next_prio, event, data); if (curr_pid[this_cpu] != (u32)-1) { /* @@ -1502,7 +1500,7 @@ process_sched_switch_event(struct raw_event_sample *raw, } static void -process_sched_runtime_event(struct raw_event_sample *raw, +process_sched_runtime_event(void *data, struct event *event, int cpu __used, u64 timestamp __used, @@ -1510,17 +1508,17 @@ process_sched_runtime_event(struct raw_event_sample *raw, { struct trace_runtime_event runtime_event; - FILL_ARRAY(runtime_event, comm, event, raw->data); - FILL_FIELD(runtime_event, pid, event, raw->data); - FILL_FIELD(runtime_event, runtime, event, raw->data); - FILL_FIELD(runtime_event, vruntime, event, raw->data); + FILL_ARRAY(runtime_event, comm, event, data); + FILL_FIELD(runtime_event, pid, event, data); + FILL_FIELD(runtime_event, runtime, event, data); + FILL_FIELD(runtime_event, vruntime, event, data); if (trace_handler->runtime_event) trace_handler->runtime_event(&runtime_event, event, cpu, timestamp, thread); } static void -process_sched_fork_event(struct raw_event_sample *raw, +process_sched_fork_event(void *data, struct event *event, int cpu __used, u64 timestamp __used, @@ -1528,12 +1526,12 @@ process_sched_fork_event(struct raw_event_sample *raw, { struct trace_fork_event fork_event; - FILL_COMMON_FIELDS(fork_event, event, raw->data); + FILL_COMMON_FIELDS(fork_event, event, data); - FILL_ARRAY(fork_event, parent_comm, event, raw->data); - FILL_FIELD(fork_event, parent_pid, event, raw->data); - FILL_ARRAY(fork_event, child_comm, event, raw->data); - FILL_FIELD(fork_event, child_pid, event, raw->data); + FILL_ARRAY(fork_event, parent_comm, event, data); + FILL_FIELD(fork_event, parent_pid, event, data); + FILL_ARRAY(fork_event, child_comm, event, data); + FILL_FIELD(fork_event, child_pid, event, data); if (trace_handler->fork_event) trace_handler->fork_event(&fork_event, event, cpu, timestamp, thread); @@ -1550,7 +1548,7 @@ process_sched_exit_event(struct event *event, } static void -process_sched_migrate_task_event(struct raw_event_sample *raw, +process_sched_migrate_task_event(void *data, struct event *event, int cpu __used, u64 timestamp __used, @@ -1558,80 +1556,66 @@ process_sched_migrate_task_event(struct raw_event_sample *raw, { struct trace_migrate_task_event migrate_task_event; - FILL_COMMON_FIELDS(migrate_task_event, event, raw->data); + FILL_COMMON_FIELDS(migrate_task_event, event, data); - FILL_ARRAY(migrate_task_event, comm, event, raw->data); - FILL_FIELD(migrate_task_event, pid, event, raw->data); - FILL_FIELD(migrate_task_event, prio, event, raw->data); - FILL_FIELD(migrate_task_event, cpu, event, raw->data); + FILL_ARRAY(migrate_task_event, comm, event, data); + FILL_FIELD(migrate_task_event, pid, event, data); + FILL_FIELD(migrate_task_event, prio, event, data); + FILL_FIELD(migrate_task_event, cpu, event, data); if (trace_handler->migrate_task_event) trace_handler->migrate_task_event(&migrate_task_event, event, cpu, timestamp, thread); } static void -process_raw_event(event_t *raw_event __used, void *more_data, +process_raw_event(event_t *raw_event __used, void *data, int cpu, u64 timestamp, struct thread *thread) { - struct raw_event_sample *raw = more_data; struct event *event; int type; - type = trace_parse_common_type(raw->data); + + type = trace_parse_common_type(data); event = trace_find_event(type); if (!strcmp(event->name, "sched_switch")) - process_sched_switch_event(raw, event, cpu, timestamp, thread); + process_sched_switch_event(data, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_stat_runtime")) - process_sched_runtime_event(raw, event, cpu, timestamp, thread); + process_sched_runtime_event(data, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_wakeup")) - process_sched_wakeup_event(raw, event, cpu, timestamp, thread); + process_sched_wakeup_event(data, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_wakeup_new")) - process_sched_wakeup_event(raw, event, cpu, timestamp, thread); + process_sched_wakeup_event(data, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_process_fork")) - process_sched_fork_event(raw, event, cpu, timestamp, thread); + process_sched_fork_event(data, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_process_exit")) process_sched_exit_event(event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_migrate_task")) - process_sched_migrate_task_event(raw, event, cpu, timestamp, thread); + process_sched_migrate_task_event(data, event, cpu, timestamp, thread); } static int process_sample_event(event_t *event) { + struct sample_data data; struct thread *thread; - u64 ip = event->ip.ip; - u64 timestamp = -1; - u32 cpu = -1; - u64 period = 1; - void *more_data = event->ip.__more_data; if (!(sample_type & PERF_SAMPLE_RAW)) return 0; - thread = threads__findnew(event->ip.pid); + memset(&data, 0, sizeof(data)); + data.time = -1; + data.cpu = -1; + data.period = -1; - if (sample_type & PERF_SAMPLE_TIME) { - timestamp = *(u64 *)more_data; - more_data += sizeof(u64); - } - - if (sample_type & PERF_SAMPLE_CPU) { - cpu = *(u32 *)more_data; - more_data += sizeof(u32); - more_data += sizeof(u32); /* reserved */ - } - - if (sample_type & PERF_SAMPLE_PERIOD) { - period = *(u64 *)more_data; - more_data += sizeof(u64); - } + event__parse_sample(event, sample_type, &data); dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, - event->ip.pid, event->ip.tid, - (void *)(long)ip, - (long long)period); + data.pid, data.tid, + (void *)(long)data.ip, + (long long)data.period); + thread = threads__findnew(data.pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); @@ -1640,10 +1624,10 @@ static int process_sample_event(event_t *event) dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - if (profile_cpu != -1 && profile_cpu != (int) cpu) + if (profile_cpu != -1 && profile_cpu != (int)data.cpu) return 0; - process_raw_event(event, more_data, cpu, timestamp, thread); + process_raw_event(event, data.raw_data, data.cpu, data.time, thread); return 0; } @@ -1679,11 +1663,18 @@ static struct perf_file_handler file_handler = { static int read_events(void) { + int err; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); + + if (session == NULL) + return -ENOMEM; + register_idle_thread(); register_perf_file_handler(&file_handler); - return mmap_dispatch_perf_file(&header, input_name, 0, 0, - &event__cwdlen, &event__cwd); + err = perf_session__process_events(session, 0, &event__cwdlen, &event__cwd); + perf_session__delete(session); + return err; } static void print_bad_events(void) @@ -1724,9 +1715,9 @@ static void __cmd_lat(void) read_events(); sort_lat(); - printf("\n -----------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms |\n"); - printf(" -----------------------------------------------------------------------------------------\n"); + printf("\n ---------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); + printf(" ---------------------------------------------------------------------------------------------------------------\n"); next = rb_first(&sorted_atom_root); @@ -1902,13 +1893,18 @@ static int __cmd_record(int argc, const char **argv) int cmd_sched(int argc, const char **argv, const char *prefix __used) { - symbol__init(0); - argc = parse_options(argc, argv, sched_options, sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(sched_usage, sched_options); + /* + * Aliased to 'perf trace' for now: + */ + if (!strcmp(argv[0], "trace")) + return cmd_trace(argc, argv, prefix); + + symbol__init(0); if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strncmp(argv[0], "lat", 3)) { @@ -1932,11 +1928,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __used) usage_with_options(replay_usage, replay_options); } __cmd_replay(); - } else if (!strcmp(argv[0], "trace")) { - /* - * Aliased to 'perf trace' for now: - */ - return cmd_trace(argc, argv, prefix); } else { usage_with_options(sched_usage, sched_options); } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index cb58b66..759dd2b 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -302,12 +302,11 @@ process_exit_event(event_t *event) } struct trace_entry { - u32 size; unsigned short type; unsigned char flags; unsigned char preempt_count; int pid; - int tgid; + int lock_depth; }; struct power_entry { @@ -484,43 +483,22 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te) static int process_sample_event(event_t *event) { - int cursor = 0; - u64 addr = 0; - u64 stamp = 0; - u32 cpu = 0; - u32 pid = 0; + struct sample_data data; struct trace_entry *te; - if (sample_type & PERF_SAMPLE_IP) - cursor++; + memset(&data, 0, sizeof(data)); - if (sample_type & PERF_SAMPLE_TID) { - pid = event->sample.array[cursor]>>32; - cursor++; - } - if (sample_type & PERF_SAMPLE_TIME) { - stamp = event->sample.array[cursor++]; - - if (!first_time || first_time > stamp) - first_time = stamp; - if (last_time < stamp) - last_time = stamp; + event__parse_sample(event, sample_type, &data); + if (sample_type & PERF_SAMPLE_TIME) { + if (!first_time || first_time > data.time) + first_time = data.time; + if (last_time < data.time) + last_time = data.time; } - if (sample_type & PERF_SAMPLE_ADDR) - addr = event->sample.array[cursor++]; - if (sample_type & PERF_SAMPLE_ID) - cursor++; - if (sample_type & PERF_SAMPLE_STREAM_ID) - cursor++; - if (sample_type & PERF_SAMPLE_CPU) - cpu = event->sample.array[cursor++] & 0xFFFFFFFF; - if (sample_type & PERF_SAMPLE_PERIOD) - cursor++; - te = (void *)&event->sample.array[cursor]; - - if (sample_type & PERF_SAMPLE_RAW && te->size > 0) { + te = (void *)data.raw_data; + if (sample_type & PERF_SAMPLE_RAW && data.raw_size > 0) { char *event_str; struct power_entry *pe; @@ -532,19 +510,19 @@ process_sample_event(event_t *event) return 0; if (strcmp(event_str, "power:power_start") == 0) - c_state_start(cpu, stamp, pe->value); + c_state_start(data.cpu, data.time, pe->value); if (strcmp(event_str, "power:power_end") == 0) - c_state_end(cpu, stamp); + c_state_end(data.cpu, data.time); if (strcmp(event_str, "power:power_frequency") == 0) - p_state_change(cpu, stamp, pe->value); + p_state_change(data.cpu, data.time, pe->value); if (strcmp(event_str, "sched:sched_wakeup") == 0) - sched_wakeup(cpu, stamp, pid, te); + sched_wakeup(data.cpu, data.time, data.pid, te); if (strcmp(event_str, "sched:sched_switch") == 0) - sched_switch(cpu, stamp, te); + sched_switch(data.cpu, data.time, te); } return 0; } @@ -1081,15 +1059,17 @@ static struct perf_file_handler file_handler = { static int __cmd_timechart(void) { - struct perf_header *header; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); int ret; + if (session == NULL) + return -ENOMEM; + register_perf_file_handler(&file_handler); - ret = mmap_dispatch_perf_file(&header, input_name, 0, 0, - &event__cwdlen, &event__cwd); + ret = perf_session__process_events(session, 0, &event__cwdlen, &event__cwd); if (ret) - return EXIT_FAILURE; + goto out_delete; process_samples(); @@ -1101,8 +1081,9 @@ static int __cmd_timechart(void) pr_info("Written %2.1f seconds of trace to %s.\n", (last_time - first_time) / 1000000000.0, output_name); - - return EXIT_SUCCESS; +out_delete: + perf_session__delete(session); + return ret; } static const char * const timechart_usage[] = { diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index abb914a..0756664 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -7,6 +7,7 @@ #include "util/header.h" #include "util/exec_cmd.h" #include "util/trace-event.h" +#include "util/session.h" static char const *script_name; static char const *generate_script_lang; @@ -61,63 +62,45 @@ static int cleanup_scripting(void) static char const *input_name = "perf.data"; -static struct perf_header *header; +static struct perf_session *session; static u64 sample_type; static int process_sample_event(event_t *event) { - u64 ip = event->ip.ip; - u64 timestamp = -1; - u32 cpu = -1; - u64 period = 1; - void *more_data = event->ip.__more_data; - struct thread *thread = threads__findnew(event->ip.pid); - - if (sample_type & PERF_SAMPLE_TIME) { - timestamp = *(u64 *)more_data; - more_data += sizeof(u64); - } + struct sample_data data; + struct thread *thread; - if (sample_type & PERF_SAMPLE_CPU) { - cpu = *(u32 *)more_data; - more_data += sizeof(u32); - more_data += sizeof(u32); /* reserved */ - } + memset(&data, 0, sizeof(data)); + data.time = -1; + data.cpu = -1; + data.period = 1; - if (sample_type & PERF_SAMPLE_PERIOD) { - period = *(u64 *)more_data; - more_data += sizeof(u64); - } + event__parse_sample(event, sample_type, &data); dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, - event->ip.pid, event->ip.tid, - (void *)(long)ip, - (long long)period); + data.pid, data.tid, + (void *)(long)data.ip, + (long long)data.period); + thread = threads__findnew(event->ip.pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); return -1; } - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - if (sample_type & PERF_SAMPLE_RAW) { - struct { - u32 size; - char data[0]; - } *raw = more_data; - /* * FIXME: better resolve from pid from the struct trace_entry * field, although it should be the same than this perf * event pid */ - scripting_ops->process_event(cpu, raw->data, raw->size, - timestamp, thread->comm); + scripting_ops->process_event(data.cpu, data.raw_data, + data.raw_size, + data.time, thread->comm); } - event__stats.total += period; + event__stats.total += data.period; return 0; } @@ -144,11 +127,18 @@ static struct perf_file_handler file_handler = { static int __cmd_trace(void) { + int err; + + session = perf_session__new(input_name, O_RDONLY, 0); + if (session == NULL) + return -ENOMEM; + register_idle_thread(); register_perf_file_handler(&file_handler); - return mmap_dispatch_perf_file(&header, input_name, - 0, 0, &event__cwdlen, &event__cwd); + err = perf_session__process_events(session, 0, &event__cwdlen, &event__cwd); + perf_session__delete(session); + return err; } struct script_spec { @@ -366,11 +356,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used) return -1; } - header = perf_header__new(); - if (header == NULL) - return -1; - - perf_header__read(header, input); + perf_header__read(&session->header, input); err = scripting_ops->generate_script("perf-trace"); goto out; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 454d5d5..75f941b 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -59,6 +59,18 @@ #define cpu_relax() asm volatile ("hint @pause" ::: "memory") #endif +#ifdef __arm__ +#include "../../arch/arm/include/asm/unistd.h" +/* + * Use the __kuser_memory_barrier helper in the CPU helper page. See + * arch/arm/kernel/entry-armv.S in the kernel source for details. + */ +#define rmb() asm volatile("mov r0, #0xffff0fff; mov lr, pc;" \ + "sub pc, r0, #95" ::: "r0", "lr", "cc", \ + "memory") +#define cpu_relax() asm volatile("":::"memory") +#endif + #include <time.h> #include <unistd.h> #include <sys/types.h> diff --git a/tools/perf/util/data_map.c b/tools/perf/util/data_map.c index ca0bedf..6d46dda 100644 --- a/tools/perf/util/data_map.c +++ b/tools/perf/util/data_map.c @@ -100,11 +100,11 @@ process_event(event_t *event, unsigned long offset, unsigned long head) } } -int perf_header__read_build_ids(int input, off_t offset, off_t size) +int perf_header__read_build_ids(int input, u64 offset, u64 size) { struct build_id_event bev; char filename[PATH_MAX]; - off_t limit = offset + size; + u64 limit = offset + size; int err = -1; while (offset < limit) { @@ -129,23 +129,16 @@ out: return err; } -int mmap_dispatch_perf_file(struct perf_header **pheader, - const char *input_name, - int force, - int full_paths, - int *cwdlen, - char **cwd) +int perf_session__process_events(struct perf_session *self, + int full_paths, int *cwdlen, char **cwd) { int err; - struct perf_header *header; unsigned long head, shift; unsigned long offset = 0; - struct stat input_stat; size_t page_size; u64 sample_type; event_t *event; uint32_t size; - int input; char *buf; if (curr_handler == NULL) { @@ -155,56 +148,19 @@ int mmap_dispatch_perf_file(struct perf_header **pheader, page_size = getpagesize(); - input = open(input_name, O_RDONLY); - if (input < 0) { - pr_err("Failed to open file: %s", input_name); - if (!strcmp(input_name, "perf.data")) - pr_err(" (try 'perf record' first)"); - pr_err("\n"); - return -errno; - } - - if (fstat(input, &input_stat) < 0) { - pr_err("failed to stat file"); - err = -errno; - goto out_close; - } - - err = -EACCES; - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - pr_err("file: %s not owned by current user or root\n", - input_name); - goto out_close; - } - - if (input_stat.st_size == 0) { - pr_info("zero-sized file, nothing to do!\n"); - goto done; - } - - err = -ENOMEM; - header = perf_header__new(); - if (header == NULL) - goto out_close; - - err = perf_header__read(header, input); - if (err < 0) - goto out_delete; - *pheader = header; - head = header->data_offset; - - sample_type = perf_header__sample_type(header); + head = self->header.data_offset; + sample_type = perf_header__sample_type(&self->header); err = -EINVAL; if (curr_handler->sample_type_check && curr_handler->sample_type_check(sample_type) < 0) - goto out_delete; + goto out_err; if (!full_paths) { if (getcwd(__cwd, sizeof(__cwd)) == NULL) { pr_err("failed to get the current directory\n"); err = -errno; - goto out_delete; + goto out_err; } *cwd = __cwd; *cwdlen = strlen(*cwd); @@ -219,11 +175,11 @@ int mmap_dispatch_perf_file(struct perf_header **pheader, remap: buf = mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); + MAP_SHARED, self->fd, offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); err = -errno; - goto out_delete; + goto out_err; } more: @@ -273,19 +229,14 @@ more: head += size; - if (offset + head >= header->data_offset + header->data_size) + if (offset + head >= self->header.data_offset + self->header.data_size) goto done; - if (offset + head < (unsigned long)input_stat.st_size) + if (offset + head < self->size) goto more; done: err = 0; -out_close: - close(input); - +out_err: return err; -out_delete: - perf_header__delete(header); - goto out_close; } diff --git a/tools/perf/util/data_map.h b/tools/perf/util/data_map.h index 3180ff7..98c5b82 100644 --- a/tools/perf/util/data_map.h +++ b/tools/perf/util/data_map.h @@ -3,6 +3,7 @@ #include "event.h" #include "header.h" +#include "session.h" typedef int (*event_type_handler_t)(event_t *); @@ -21,12 +22,8 @@ struct perf_file_handler { }; void register_perf_file_handler(struct perf_file_handler *handler); -int mmap_dispatch_perf_file(struct perf_header **pheader, - const char *input_name, - int force, - int full_paths, - int *cwdlen, - char **cwd); -int perf_header__read_build_ids(int input, off_t offset, off_t file_size); +int perf_session__process_events(struct perf_session *self, + int full_paths, int *cwdlen, char **cwd); +int perf_header__read_build_ids(int input, u64 offset, u64 file_size); #endif diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 414b89d..ba0de90 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -254,13 +254,14 @@ void thread__find_addr_location(struct thread *self, u8 cpumode, struct addr_location *al, symbol_filter_t filter) { - struct thread *thread = al->thread = self; + struct map_groups *mg = &self->mg; + al->thread = self; al->addr = addr; if (cpumode & PERF_RECORD_MISC_KERNEL) { al->level = 'k'; - thread = kthread; + mg = kmaps; } else if (cpumode & PERF_RECORD_MISC_USER) al->level = '.'; else { @@ -270,7 +271,7 @@ void thread__find_addr_location(struct thread *self, u8 cpumode, return; } try_again: - al->map = thread__find_map(thread, type, al->addr); + al->map = map_groups__find(mg, type, al->addr); if (al->map == NULL) { /* * If this is outside of all known maps, and is a negative @@ -281,8 +282,8 @@ try_again: * "[vdso]" dso, but for now lets use the old trick of looking * in the whole kernel symbol list. */ - if ((long long)al->addr < 0 && thread != kthread) { - thread = kthread; + if ((long long)al->addr < 0 && mg != kmaps) { + mg = kmaps; goto try_again; } al->sym = NULL; @@ -310,3 +311,70 @@ int event__preprocess_sample(const event_t *self, struct addr_location *al, al->level == 'H' ? "[hypervisor]" : "<not found>"); return 0; } + +int event__parse_sample(event_t *event, u64 type, struct sample_data *data) +{ + u64 *array = event->sample.array; + + if (type & PERF_SAMPLE_IP) { + data->ip = event->ip.ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u32 *p = (u32 *)array; + data->pid = p[0]; + data->tid = p[1]; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + data->time = *array; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + data->addr = *array; + array++; + } + + if (type & PERF_SAMPLE_ID) { + data->id = *array; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + data->stream_id = *array; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u32 *p = (u32 *)array; + data->cpu = *p; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + data->period = *array; + array++; + } + + if (type & PERF_SAMPLE_READ) { + pr_debug("PERF_SAMPLE_READ is unsuported for now\n"); + return -1; + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + data->callchain = (struct ip_callchain *)array; + array += 1 + data->callchain->nr; + } + + if (type & PERF_SAMPLE_RAW) { + u32 *p = (u32 *)array; + data->raw_size = *p; + p++; + data->raw_data = p; + } + + return 0; +} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index a4cc810..51a96c2 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -56,11 +56,25 @@ struct read_event { u64 id; }; -struct sample_event{ +struct sample_event { struct perf_event_header header; u64 array[]; }; +struct sample_data { + u64 ip; + u32 pid, tid; + u64 time; + u64 addr; + u64 id; + u64 stream_id; + u32 cpu; + u64 period; + struct ip_callchain *callchain; + u32 raw_size; + void *raw_data; +}; + #define BUILD_ID_SIZE 20 struct build_id_event { @@ -89,10 +103,11 @@ void event__print_totals(void); enum map_type { MAP__FUNCTION = 0, - - MAP__NR_TYPES, + MAP__VARIABLE, }; +#define MAP__NR_TYPES (MAP__VARIABLE + 1) + struct map { union { struct rb_node rb_node; @@ -136,6 +151,8 @@ int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *self, FILE *fp); struct symbol *map__find_symbol(struct map *self, u64 addr, symbol_filter_t filter); +struct symbol *map__find_symbol_by_name(struct map *self, const char *name, + symbol_filter_t filter); void map__fixup_start(struct map *self); void map__fixup_end(struct map *self); @@ -155,5 +172,6 @@ int event__process_task(event_t *self); struct addr_location; int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter); +int event__parse_sample(event_t *event, u64 type, struct sample_data *data); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 4805e6d..f2e8d87 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -58,35 +58,19 @@ int perf_header_attr__add_id(struct perf_header_attr *self, u64 id) return 0; } -/* - * Create new perf.data header: - */ -struct perf_header *perf_header__new(void) +int perf_header__init(struct perf_header *self) { - struct perf_header *self = zalloc(sizeof(*self)); - - if (self != NULL) { - self->size = 1; - self->attr = malloc(sizeof(void *)); - - if (self->attr == NULL) { - free(self); - self = NULL; - } - } - - return self; + self->size = 1; + self->attr = malloc(sizeof(void *)); + return self->attr == NULL ? -ENOMEM : 0; } -void perf_header__delete(struct perf_header *self) +void perf_header__exit(struct perf_header *self) { int i; - for (i = 0; i < self->attrs; ++i) - perf_header_attr__delete(self->attr[i]); - + perf_header_attr__delete(self->attr[i]); free(self->attr); - free(self); } int perf_header__add_attr(struct perf_header *self, @@ -187,7 +171,9 @@ static int do_write(int fd, const void *buf, size_t size) static int __dsos__write_buildid_table(struct list_head *head, int fd) { +#define NAME_ALIGN 64 struct dso *pos; + static const char zero_buf[NAME_ALIGN]; list_for_each_entry(pos, head, node) { int err; @@ -197,14 +183,17 @@ static int __dsos__write_buildid_table(struct list_head *head, int fd) if (!pos->has_build_id) continue; len = pos->long_name_len + 1; - len = ALIGN(len, 64); + len = ALIGN(len, NAME_ALIGN); memset(&b, 0, sizeof(b)); memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); if (err < 0) return err; - err = do_write(fd, pos->long_name, len); + err = do_write(fd, pos->long_name, pos->long_name_len + 1); + if (err < 0) + return err; + err = do_write(fd, zero_buf, len - pos->long_name_len - 1); if (err < 0) return err; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d1dbe2b..d118d05 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -55,8 +55,8 @@ struct perf_header { DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; -struct perf_header *perf_header__new(void); -void perf_header__delete(struct perf_header *self); +int perf_header__init(struct perf_header *self); +void perf_header__exit(struct perf_header *self); int perf_header__read(struct perf_header *self, int fd); int perf_header__write(struct perf_header *self, int fd, bool at_exit); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 69f94fe..76bdca6 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -104,43 +104,64 @@ void map__fixup_end(struct map *self) #define DSO__DELETED "(deleted)" -struct symbol *map__find_symbol(struct map *self, u64 addr, - symbol_filter_t filter) +static int map__load(struct map *self, symbol_filter_t filter) { - if (!dso__loaded(self->dso, self->type)) { - int nr = dso__load(self->dso, self, filter); - - if (nr < 0) { - if (self->dso->has_build_id) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - build_id__sprintf(self->dso->build_id, - sizeof(self->dso->build_id), - sbuild_id); - pr_warning("%s with build id %s not found", - self->dso->long_name, sbuild_id); - } else - pr_warning("Failed to open %s", - self->dso->long_name); - pr_warning(", continuing without symbols\n"); - return NULL; - } else if (nr == 0) { - const char *name = self->dso->long_name; - const size_t len = strlen(name); - const size_t real_len = len - sizeof(DSO__DELETED); - - if (len > sizeof(DSO__DELETED) && - strcmp(name + real_len + 1, DSO__DELETED) == 0) { - pr_warning("%.*s was updated, restart the long running apps that use it!\n", - (int)real_len, name); - } else { - pr_warning("no symbols found in %s, maybe install a debug package?\n", name); - } - return NULL; + const char *name = self->dso->long_name; + int nr = dso__load(self->dso, self, filter); + + if (nr < 0) { + if (self->dso->has_build_id) { + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(self->dso->build_id, + sizeof(self->dso->build_id), + sbuild_id); + pr_warning("%s with build id %s not found", + name, sbuild_id); + } else + pr_warning("Failed to open %s", name); + + pr_warning(", continuing without symbols\n"); + return -1; + } else if (nr == 0) { + const size_t len = strlen(name); + const size_t real_len = len - sizeof(DSO__DELETED); + + if (len > sizeof(DSO__DELETED) && + strcmp(name + real_len + 1, DSO__DELETED) == 0) { + pr_warning("%.*s was updated, restart the long " + "running apps that use it!\n", + (int)real_len, name); + } else { + pr_warning("no symbols found in %s, maybe install " + "a debug package?\n", name); } + + return -1; } - return self->dso->find_symbol(self->dso, self->type, addr); + return 0; +} + +struct symbol *map__find_symbol(struct map *self, u64 addr, + symbol_filter_t filter) +{ + if (!dso__loaded(self->dso, self->type) && map__load(self, filter) < 0) + return NULL; + + return dso__find_symbol(self->dso, self->type, addr); +} + +struct symbol *map__find_symbol_by_name(struct map *self, const char *name, + symbol_filter_t filter) +{ + if (!dso__loaded(self->dso, self->type) && map__load(self, filter) < 0) + return NULL; + + if (!dso__sorted_by_name(self->dso, self->type)) + dso__sort_by_name(self->dso, self->type); + + return dso__find_symbol_by_name(self->dso, self->type, name); } struct map *map__clone(struct map *self) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9e5dbd6..e5bc0fb 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -197,7 +197,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) if (id == config) { closedir(evt_dir); closedir(sys_dir); - path = zalloc(sizeof(path)); + path = zalloc(sizeof(*path)); path->system = malloc(MAX_EVENT_LENGTH); if (!path->system) { free(path); @@ -467,7 +467,6 @@ parse_subsystem_tracepoint_event(char *sys_name, char *flags) while ((evt_ent = readdir(evt_dir))) { char event_opt[MAX_EVOPT_LEN + 1]; int len; - unsigned int rem = MAX_EVOPT_LEN; if (!strcmp(evt_ent->d_name, ".") || !strcmp(evt_ent->d_name, "..") @@ -475,20 +474,12 @@ parse_subsystem_tracepoint_event(char *sys_name, char *flags) || !strcmp(evt_ent->d_name, "filter")) continue; - len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s", sys_name, - evt_ent->d_name); + len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name, + evt_ent->d_name, flags ? ":" : "", + flags ?: ""); if (len < 0) return EVT_FAILED; - rem -= len; - if (flags) { - if (rem < strlen(flags) + 1) - return EVT_FAILED; - - strcat(event_opt, ":"); - strcat(event_opt, flags); - } - if (parse_events(NULL, event_opt, 0)) return EVT_FAILED; } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 6d8af48..efebd5b 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -430,6 +430,9 @@ int usage_with_options_internal(const char * const *usagestr, pos = fprintf(stderr, " "); if (opts->short_name) pos += fprintf(stderr, "-%c", opts->short_name); + else + pos += fprintf(stderr, " "); + if (opts->long_name && opts->short_name) pos += fprintf(stderr, ", "); if (opts->long_name) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index cd7fbda..d14a458 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -48,6 +48,9 @@ /* If there is no space to write, returns -E2BIG. */ static int e_snprintf(char *str, size_t size, const char *format, ...) + __attribute__((format(printf, 3, 4))); + +static int e_snprintf(char *str, size_t size, const char *format, ...) { int ret; va_list ap; @@ -258,7 +261,7 @@ int synthesize_perf_probe_event(struct probe_point *pp) ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function, offs, pp->retprobe ? "%return" : "", line); else - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->file, line); + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", pp->file, line); if (ret <= 0) goto error; len = ret; @@ -373,14 +376,32 @@ static void clear_probe_point(struct probe_point *pp) free(pp->args); for (i = 0; i < pp->found; i++) free(pp->probes[i]); - memset(pp, 0, sizeof(pp)); + memset(pp, 0, sizeof(*pp)); +} + +/* Show an event */ +static void show_perf_probe_event(const char *group, const char *event, + const char *place, struct probe_point *pp) +{ + int i; + char buf[128]; + + e_snprintf(buf, 128, "%s:%s", group, event); + printf(" %-40s (on %s", buf, place); + + if (pp->nr_args > 0) { + printf(" with"); + for (i = 0; i < pp->nr_args; i++) + printf(" %s", pp->args[i]); + } + printf(")\n"); } /* List up current perf-probe events */ void show_perf_probe_events(void) { unsigned int i; - int fd; + int fd, nr; char *group, *event; struct probe_point pp; struct strlist *rawlist; @@ -393,8 +414,13 @@ void show_perf_probe_events(void) for (i = 0; i < strlist__nr_entries(rawlist); i++) { ent = strlist__entry(rawlist, i); parse_trace_kprobe_event(ent->s, &group, &event, &pp); + /* Synthesize only event probe point */ + nr = pp.nr_args; + pp.nr_args = 0; synthesize_perf_probe_event(&pp); - printf("[%s:%s]\t%s\n", group, event, pp.probes[0]); + pp.nr_args = nr; + /* Show an event */ + show_perf_probe_event(group, event, pp.probes[0], &pp); free(group); free(event); clear_probe_point(&pp); @@ -404,21 +430,28 @@ void show_perf_probe_events(void) } /* Get current perf-probe event names */ -static struct strlist *get_perf_event_names(int fd) +static struct strlist *get_perf_event_names(int fd, bool include_group) { unsigned int i; char *group, *event; + char buf[128]; struct strlist *sl, *rawlist; struct str_node *ent; rawlist = get_trace_kprobe_event_rawlist(fd); - sl = strlist__new(false, NULL); + sl = strlist__new(true, NULL); for (i = 0; i < strlist__nr_entries(rawlist); i++) { ent = strlist__entry(rawlist, i); parse_trace_kprobe_event(ent->s, &group, &event, NULL); - strlist__add(sl, event); + if (include_group) { + if (e_snprintf(buf, 128, "%s:%s", group, event) < 0) + die("Failed to copy group:event name."); + strlist__add(sl, buf); + } else + strlist__add(sl, event); free(group); + free(event); } strlist__delete(rawlist); @@ -426,24 +459,30 @@ static struct strlist *get_perf_event_names(int fd) return sl; } -static int write_trace_kprobe_event(int fd, const char *buf) +static void write_trace_kprobe_event(int fd, const char *buf) { int ret; + pr_debug("Writing event: %s\n", buf); ret = write(fd, buf, strlen(buf)); if (ret <= 0) - die("Failed to create event."); - else - printf("Added new event: %s\n", buf); - - return ret; + die("Failed to write event: %s", strerror(errno)); } static void get_new_event_name(char *buf, size_t len, const char *base, struct strlist *namelist) { int i, ret; - for (i = 0; i < MAX_EVENT_INDEX; i++) { + + /* Try no suffix */ + ret = e_snprintf(buf, len, "%s", base); + if (ret < 0) + die("snprintf() failed: %s", strerror(-ret)); + if (!strlist__has_entry(namelist, buf)) + return; + + /* Try to add suffix */ + for (i = 1; i < MAX_EVENT_INDEX; i++) { ret = e_snprintf(buf, len, "%s_%d", base, i); if (ret < 0) die("snprintf() failed: %s", strerror(-ret)); @@ -464,7 +503,7 @@ void add_trace_kprobe_events(struct probe_point *probes, int nr_probes) fd = open_kprobe_events(O_RDWR, O_APPEND); /* Get current event names */ - namelist = get_perf_event_names(fd); + namelist = get_perf_event_names(fd, false); for (j = 0; j < nr_probes; j++) { pp = probes + j; @@ -476,9 +515,73 @@ void add_trace_kprobe_events(struct probe_point *probes, int nr_probes) PERFPROBE_GROUP, event, pp->probes[i]); write_trace_kprobe_event(fd, buf); + printf("Added new event:\n"); + /* Get the first parameter (probe-point) */ + sscanf(pp->probes[i], "%s", buf); + show_perf_probe_event(PERFPROBE_GROUP, event, + buf, pp); /* Add added event name to namelist */ strlist__add(namelist, event); } } + /* Show how to use the event. */ + printf("\nYou can now use it on all perf tools, such as:\n\n"); + printf("\tperf record -e %s:%s -a sleep 1\n\n", PERFPROBE_GROUP, event); + + strlist__delete(namelist); + close(fd); +} + +static void del_trace_kprobe_event(int fd, const char *group, + const char *event, struct strlist *namelist) +{ + char buf[128]; + + if (e_snprintf(buf, 128, "%s:%s", group, event) < 0) + die("Failed to copy event."); + if (!strlist__has_entry(namelist, buf)) { + pr_warning("Warning: event \"%s\" is not found.\n", buf); + return; + } + /* Convert from perf-probe event to trace-kprobe event */ + if (e_snprintf(buf, 128, "-:%s/%s", group, event) < 0) + die("Failed to copy event."); + + write_trace_kprobe_event(fd, buf); + printf("Remove event: %s:%s\n", group, event); +} + +void del_trace_kprobe_events(struct strlist *dellist) +{ + int fd; + unsigned int i; + const char *group, *event; + char *p, *str; + struct str_node *ent; + struct strlist *namelist; + + fd = open_kprobe_events(O_RDWR, O_APPEND); + /* Get current event names */ + namelist = get_perf_event_names(fd, true); + + for (i = 0; i < strlist__nr_entries(dellist); i++) { + ent = strlist__entry(dellist, i); + str = strdup(ent->s); + if (!str) + die("Failed to copy event."); + p = strchr(str, ':'); + if (p) { + group = str; + *p = '\0'; + event = p + 1; + } else { + group = PERFPROBE_GROUP; + event = str; + } + del_trace_kprobe_event(fd, group, event, namelist); + free(str); + } + strlist__delete(namelist); close(fd); } + diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 0c6fe56..f752159 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -10,6 +10,7 @@ extern void parse_trace_kprobe_event(const char *str, char **group, char **event, struct probe_point *pp); extern int synthesize_trace_kprobe_event(struct probe_point *pp); extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes); +extern void del_trace_kprobe_events(struct strlist *dellist); extern void show_perf_probe_events(void); /* Maximum index number of event-name postfix */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 293cdfc..4585f1d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -106,7 +106,7 @@ static int strtailcmp(const char *s1, const char *s2) { int i1 = strlen(s1); int i2 = strlen(s2); - while (--i1 > 0 && --i2 > 0) { + while (--i1 >= 0 && --i2 >= 0) { if (s1[i1] != s2[i2]) return s1[i1] - s2[i2]; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c new file mode 100644 index 0000000..707ce1c --- /dev/null +++ b/tools/perf/util/session.c @@ -0,0 +1,80 @@ +#include <linux/kernel.h> + +#include <unistd.h> +#include <sys/types.h> + +#include "session.h" +#include "util.h" + +static int perf_session__open(struct perf_session *self, bool force) +{ + struct stat input_stat; + + self->fd = open(self->filename, O_RDONLY); + if (self->fd < 0) { + pr_err("failed to open file: %s", self->filename); + if (!strcmp(self->filename, "perf.data")) + pr_err(" (try 'perf record' first)"); + pr_err("\n"); + return -errno; + } + + if (fstat(self->fd, &input_stat) < 0) + goto out_close; + + if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { + pr_err("file %s not owned by current user or root\n", + self->filename); + goto out_close; + } + + if (!input_stat.st_size) { + pr_info("zero-sized file (%s), nothing to do!\n", + self->filename); + goto out_close; + } + + if (perf_header__read(&self->header, self->fd) < 0) { + pr_err("incompatible file format"); + goto out_close; + } + + self->size = input_stat.st_size; + return 0; + +out_close: + close(self->fd); + self->fd = -1; + return -1; +} + +struct perf_session *perf_session__new(const char *filename, int mode, bool force) +{ + size_t len = strlen(filename) + 1; + struct perf_session *self = zalloc(sizeof(*self) + len); + + if (self == NULL) + goto out; + + if (perf_header__init(&self->header) < 0) + goto out_delete; + + memcpy(self->filename, filename, len); + + if (mode == O_RDONLY && perf_session__open(self, force) < 0) { + perf_session__delete(self); + self = NULL; + } +out: + return self; +out_delete: + free(self); + return NULL; +} + +void perf_session__delete(struct perf_session *self) +{ + perf_header__exit(&self->header); + close(self->fd); + free(self); +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h new file mode 100644 index 0000000..f3699c8 --- /dev/null +++ b/tools/perf/util/session.h @@ -0,0 +1,16 @@ +#ifndef __PERF_SESSION_H +#define __PERF_SESSION_H + +#include "header.h" + +struct perf_session { + struct perf_header header; + unsigned long size; + int fd; + char filename[0]; +}; + +struct perf_session *perf_session__new(const char *filename, int mode, bool force); +void perf_session__delete(struct perf_session *self); + +#endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index fffcb93..d3d9fed 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -29,11 +29,9 @@ enum dso_origin { }; static void dsos__add(struct list_head *head, struct dso *dso); -static struct map *thread__find_map_by_name(struct thread *self, char *name); static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); -struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); static int dso__load_kernel_sym(struct dso *self, struct map *map, - struct thread *thread, symbol_filter_t filter); + struct map_groups *mg, symbol_filter_t filter); unsigned int symbol__priv_size; static int vmlinux_path__nr_entries; static char **vmlinux_path; @@ -43,19 +41,41 @@ static struct symbol_conf symbol_conf__defaults = { .try_vmlinux_path = true, }; -static struct thread kthread_mem; -struct thread *kthread = &kthread_mem; +static struct map_groups kmaps_mem; +struct map_groups *kmaps = &kmaps_mem; bool dso__loaded(const struct dso *self, enum map_type type) { return self->loaded & (1 << type); } +bool dso__sorted_by_name(const struct dso *self, enum map_type type) +{ + return self->sorted_by_name & (1 << type); +} + static void dso__set_loaded(struct dso *self, enum map_type type) { self->loaded |= (1 << type); } +static void dso__set_sorted_by_name(struct dso *self, enum map_type type) +{ + self->sorted_by_name |= (1 << type); +} + +static bool symbol_type__is_a(char symbol_type, enum map_type map_type) +{ + switch (map_type) { + case MAP__FUNCTION: + return symbol_type == 'T' || symbol_type == 'W'; + case MAP__VARIABLE: + return symbol_type == 'D' || symbol_type == 'd'; + default: + return false; + } +} + static void symbols__fixup_end(struct rb_root *self) { struct rb_node *nd, *prevnd = rb_first(self); @@ -79,7 +99,7 @@ static void symbols__fixup_end(struct rb_root *self) curr->end = roundup(curr->start, 4096); } -static void __thread__fixup_maps_end(struct thread *self, enum map_type type) +static void __map_groups__fixup_end(struct map_groups *self, enum map_type type) { struct map *prev, *curr; struct rb_node *nd, *prevnd = rb_first(&self->maps[type]); @@ -102,11 +122,11 @@ static void __thread__fixup_maps_end(struct thread *self, enum map_type type) curr->end = ~0UL; } -static void thread__fixup_maps_end(struct thread *self) +static void map_groups__fixup_end(struct map_groups *self) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) - __thread__fixup_maps_end(self, i); + __map_groups__fixup_end(self, i); } static struct symbol *symbol__new(u64 start, u64 len, const char *name) @@ -164,11 +184,11 @@ struct dso *dso__new(const char *name) dso__set_long_name(self, self->name); self->short_name = self->name; for (i = 0; i < MAP__NR_TYPES; ++i) - self->symbols[i] = RB_ROOT; - self->find_symbol = dso__find_symbol; + self->symbols[i] = self->symbol_names[i] = RB_ROOT; self->slen_calculated = 0; self->origin = DSO__ORIG_NOT_FOUND; self->loaded = 0; + self->sorted_by_name = 0; self->has_build_id = 0; } @@ -246,11 +266,85 @@ static struct symbol *symbols__find(struct rb_root *self, u64 ip) return NULL; } -struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr) +struct symbol_name_rb_node { + struct rb_node rb_node; + struct symbol sym; +}; + +static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym) +{ + struct rb_node **p = &self->rb_node; + struct rb_node *parent = NULL; + struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s; + + while (*p != NULL) { + parent = *p; + s = rb_entry(parent, struct symbol_name_rb_node, rb_node); + if (strcmp(sym->name, s->sym.name) < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&symn->rb_node, parent, p); + rb_insert_color(&symn->rb_node, self); +} + +static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source) +{ + struct rb_node *nd; + + for (nd = rb_first(source); nd; nd = rb_next(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + symbols__insert_by_name(self, pos); + } +} + +static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name) +{ + struct rb_node *n; + + if (self == NULL) + return NULL; + + n = self->rb_node; + + while (n) { + struct symbol_name_rb_node *s; + int cmp; + + s = rb_entry(n, struct symbol_name_rb_node, rb_node); + cmp = strcmp(name, s->sym.name); + + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return &s->sym; + } + + return NULL; +} + +struct symbol *dso__find_symbol(struct dso *self, + enum map_type type, u64 addr) { return symbols__find(&self->symbols[type], addr); } +struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, + const char *name) +{ + return symbols__find_by_name(&self->symbol_names[type], name); +} + +void dso__sort_by_name(struct dso *self, enum map_type type) +{ + dso__set_sorted_by_name(self, type); + return symbols__sort_by_name(&self->symbol_names[type], + &self->symbols[type]); +} + int build_id__sprintf(u8 *self, int len, char *bf) { char *bid = bf; @@ -327,10 +421,7 @@ static int dso__load_all_kallsyms(struct dso *self, struct map *map) continue; symbol_type = toupper(line[len]); - /* - * We're interested only in code ('T'ext) - */ - if (symbol_type != 'T' && symbol_type != 'W') + if (!symbol_type__is_a(symbol_type, map->type)) continue; symbol_name = line + len + 2; @@ -364,8 +455,8 @@ out_failure: * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *self, struct map *map, struct thread *thread, - symbol_filter_t filter) +static int dso__split_kallsyms(struct dso *self, struct map *map, + struct map_groups *mg, symbol_filter_t filter) { struct map *curr_map = map; struct symbol *pos; @@ -382,13 +473,13 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, struct thread module = strchr(pos->name, '\t'); if (module) { - if (!thread->use_modules) + if (!mg->use_modules) goto discard_symbol; *module++ = '\0'; if (strcmp(self->name, module)) { - curr_map = thread__find_map_by_name(thread, module); + curr_map = map_groups__find_by_name(mg, map->type, module); if (curr_map == NULL) { pr_debug("/proc/{kallsyms,modules} " "inconsistency!\n"); @@ -419,7 +510,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, struct thread } curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; - __thread__insert_map(thread, curr_map); + map_groups__insert(mg, curr_map); ++kernel_range; } @@ -440,7 +531,7 @@ discard_symbol: rb_erase(&pos->rb_node, root); static int dso__load_kallsyms(struct dso *self, struct map *map, - struct thread *thread, symbol_filter_t filter) + struct map_groups *mg, symbol_filter_t filter) { if (dso__load_all_kallsyms(self, map) < 0) return -1; @@ -448,13 +539,13 @@ static int dso__load_kallsyms(struct dso *self, struct map *map, symbols__fixup_end(&self->symbols[map->type]); self->origin = DSO__ORIG_KERNEL; - return dso__split_kallsyms(self, map, thread, filter); + return dso__split_kallsyms(self, map, mg, filter); } size_t kernel_maps__fprintf(FILE *fp) { size_t printed = fprintf(fp, "Kernel maps:\n"); - printed += thread__fprintf_maps(kthread, fp); + printed += map_groups__fprintf_maps(kmaps, fp); return printed + fprintf(fp, "END kernel maps\n"); } @@ -544,6 +635,13 @@ static inline int elf_sym__is_function(const GElf_Sym *sym) sym->st_shndx != SHN_UNDEF; } +static inline bool elf_sym__is_object(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_OBJECT && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF; +} + static inline int elf_sym__is_label(const GElf_Sym *sym) { return elf_sym__type(sym) == STT_NOTYPE && @@ -564,6 +662,12 @@ static inline int elf_sec__is_text(const GElf_Shdr *shdr, return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; } +static inline bool elf_sec__is_data(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; +} + static inline const char *elf_sym__name(const GElf_Sym *sym, const Elf_Data *symstrs) { @@ -744,8 +848,32 @@ out: return 0; } +static bool elf_sym__is_a(GElf_Sym *self, enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sym__is_function(self); + case MAP__VARIABLE: + return elf_sym__is_object(self); + default: + return false; + } +} + +static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sec__is_text(self, secstrs); + case MAP__VARIABLE: + return elf_sec__is_data(self, secstrs); + default: + return false; + } +} + static int dso__load_sym(struct dso *self, struct map *map, - struct thread *thread, const char *name, int fd, + struct map_groups *mg, const char *name, int fd, symbol_filter_t filter, int kernel, int kmodule) { struct map *curr_map = map; @@ -818,7 +946,7 @@ static int dso__load_sym(struct dso *self, struct map *map, int is_label = elf_sym__is_label(&sym); const char *section_name; - if (!is_label && !elf_sym__is_function(&sym)) + if (!is_label && !elf_sym__is_a(&sym, map->type)) continue; sec = elf_getscn(elf, sym.st_shndx); @@ -827,7 +955,7 @@ static int dso__load_sym(struct dso *self, struct map *map, gelf_getshdr(sec, &shdr); - if (is_label && !elf_sec__is_text(&shdr, secstrs)) + if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) continue; elf_name = elf_sym__name(&sym, symstrs); @@ -849,7 +977,7 @@ static int dso__load_sym(struct dso *self, struct map *map, snprintf(dso_name, sizeof(dso_name), "%s%s", self->short_name, section_name); - curr_map = thread__find_map_by_name(thread, dso_name); + curr_map = map_groups__find_by_name(mg, map->type, dso_name); if (curr_map == NULL) { u64 start = sym.st_value; @@ -868,7 +996,7 @@ static int dso__load_sym(struct dso *self, struct map *map, curr_map->map_ip = identity__map_ip; curr_map->unmap_ip = identity__map_ip; curr_dso->origin = DSO__ORIG_KERNEL; - __thread__insert_map(kthread, curr_map); + map_groups__insert(kmaps, curr_map); dsos__add(&dsos__kernel, curr_dso); } else curr_dso = curr_map->dso; @@ -938,8 +1066,9 @@ static bool __dsos__read_build_ids(struct list_head *head) bool dsos__read_build_ids(void) { - return __dsos__read_build_ids(&dsos__kernel) || - __dsos__read_build_ids(&dsos__user); + bool kbuildids = __dsos__read_build_ids(&dsos__kernel), + ubuildids = __dsos__read_build_ids(&dsos__user); + return kbuildids || ubuildids; } /* @@ -1093,7 +1222,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) dso__set_loaded(self, map->type); if (self->kernel) - return dso__load_kernel_sym(self, map, kthread, filter); + return dso__load_kernel_sym(self, map, kmaps, filter); name = malloc(size); if (!name) @@ -1179,11 +1308,12 @@ out: return ret; } -static struct map *thread__find_map_by_name(struct thread *self, char *name) +struct map *map_groups__find_by_name(struct map_groups *self, + enum map_type type, const char *name) { struct rb_node *nd; - for (nd = rb_first(&self->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { struct map *map = rb_entry(nd, struct map, rb_node); if (map->dso && strcmp(map->dso->name, name) == 0) @@ -1227,7 +1357,7 @@ static int dsos__set_modules_path_dir(char *dirname) (int)(dot - dent->d_name), dent->d_name); strxfrchar(dso_name, '-', '_'); - map = thread__find_map_by_name(kthread, dso_name); + map = map_groups__find_by_name(kmaps, MAP__FUNCTION, dso_name); if (map == NULL) continue; @@ -1280,7 +1410,7 @@ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) return self; } -static int thread__create_module_maps(struct thread *self) +static int map_groups__create_module_maps(struct map_groups *self) { char *line = NULL; size_t n; @@ -1337,7 +1467,7 @@ static int thread__create_module_maps(struct thread *self) dso->has_build_id = true; dso->origin = DSO__ORIG_KMODULE; - __thread__insert_map(self, map); + map_groups__insert(self, map); dsos__add(&dsos__kernel, dso); } @@ -1352,7 +1482,8 @@ out_failure: return -1; } -static int dso__load_vmlinux(struct dso *self, struct map *map, struct thread *thread, +static int dso__load_vmlinux(struct dso *self, struct map *map, + struct map_groups *mg, const char *vmlinux, symbol_filter_t filter) { int err = -1, fd; @@ -1386,14 +1517,14 @@ static int dso__load_vmlinux(struct dso *self, struct map *map, struct thread *t return -1; dso__set_loaded(self, map->type); - err = dso__load_sym(self, map, thread, self->long_name, fd, filter, 1, 0); + err = dso__load_sym(self, map, mg, self->long_name, fd, filter, 1, 0); close(fd); return err; } static int dso__load_kernel_sym(struct dso *self, struct map *map, - struct thread *thread, symbol_filter_t filter) + struct map_groups *mg, symbol_filter_t filter) { int err; bool is_kallsyms; @@ -1403,7 +1534,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map, pr_debug("Looking at the vmlinux_path (%d entries long)\n", vmlinux_path__nr_entries); for (i = 0; i < vmlinux_path__nr_entries; ++i) { - err = dso__load_vmlinux(self, map, thread, + err = dso__load_vmlinux(self, map, mg, vmlinux_path[i], filter); if (err > 0) { pr_debug("Using %s for symbols\n", @@ -1419,12 +1550,12 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map, if (is_kallsyms) goto do_kallsyms; - err = dso__load_vmlinux(self, map, thread, self->long_name, filter); + err = dso__load_vmlinux(self, map, mg, self->long_name, filter); if (err <= 0) { pr_info("The file %s cannot be used, " "trying to use /proc/kallsyms...", self->long_name); do_kallsyms: - err = dso__load_kallsyms(self, map, thread, filter); + err = dso__load_kallsyms(self, map, mg, filter); if (err > 0 && !is_kallsyms) dso__set_long_name(self, strdup("[kernel.kallsyms]")); } @@ -1507,42 +1638,59 @@ size_t dsos__fprintf_buildid(FILE *fp) __dsos__fprintf_buildid(&dsos__user, fp)); } -static int thread__create_kernel_map(struct thread *self, const char *vmlinux) +static struct dso *dsos__create_kernel( const char *vmlinux) { - struct map *kmap; struct dso *kernel = dso__new(vmlinux ?: "[kernel.kallsyms]"); if (kernel == NULL) - return -1; - - kmap = map__new2(0, kernel, MAP__FUNCTION); - if (kmap == NULL) - goto out_delete_kernel_dso; + return NULL; - kmap->map_ip = kmap->unmap_ip = identity__map_ip; kernel->short_name = "[kernel]"; kernel->kernel = 1; vdso = dso__new("[vdso]"); if (vdso == NULL) - goto out_delete_kernel_map; + goto out_delete_kernel_dso; dso__set_loaded(vdso, MAP__FUNCTION); if (sysfs__read_build_id("/sys/kernel/notes", kernel->build_id, sizeof(kernel->build_id)) == 0) kernel->has_build_id = true; - __thread__insert_map(self, kmap); dsos__add(&dsos__kernel, kernel); dsos__add(&dsos__user, vdso); - return 0; + return kernel; -out_delete_kernel_map: - map__delete(kmap); out_delete_kernel_dso: dso__delete(kernel); - return -1; + return NULL; +} + +static int map_groups__create_kernel_maps(struct map_groups *self, const char *vmlinux) +{ + struct map *functions, *variables; + struct dso *kernel = dsos__create_kernel(vmlinux); + + if (kernel == NULL) + return -1; + + functions = map__new2(0, kernel, MAP__FUNCTION); + if (functions == NULL) + return -1; + + variables = map__new2(0, kernel, MAP__VARIABLE); + if (variables == NULL) { + map__delete(functions); + return -1; + } + + functions->map_ip = functions->unmap_ip = + variables->map_ip = variables->unmap_ip = identity__map_ip; + map_groups__insert(self, functions); + map_groups__insert(self, variables); + + return 0; } static void vmlinux_path__exit(void) @@ -1606,23 +1754,26 @@ int symbol__init(struct symbol_conf *conf) elf_version(EV_CURRENT); symbol__priv_size = pconf->priv_size; - thread__init(kthread, 0); + if (pconf->sort_by_name) + symbol__priv_size += (sizeof(struct symbol_name_rb_node) - + sizeof(struct symbol)); + map_groups__init(kmaps); if (pconf->try_vmlinux_path && vmlinux_path__init() < 0) return -1; - if (thread__create_kernel_map(kthread, pconf->vmlinux_name) < 0) { + if (map_groups__create_kernel_maps(kmaps, pconf->vmlinux_name) < 0) { vmlinux_path__exit(); return -1; } - kthread->use_modules = pconf->use_modules; - if (pconf->use_modules && thread__create_module_maps(kthread) < 0) + kmaps->use_modules = pconf->use_modules; + if (pconf->use_modules && map_groups__create_module_maps(kmaps) < 0) pr_debug("Failed to load list of modules in use, " "continuing...\n"); /* * Now that we have all the maps created, just set the ->end of them: */ - thread__fixup_maps_end(kthread); + map_groups__fixup_end(kmaps); return 0; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 17003ef..cf99f88 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -52,7 +52,8 @@ struct symbol { struct symbol_conf { unsigned short priv_size; bool try_vmlinux_path, - use_modules; + use_modules, + sort_by_name; const char *vmlinux_name; }; @@ -74,13 +75,13 @@ struct addr_location { struct dso { struct list_head node; struct rb_root symbols[MAP__NR_TYPES]; - struct symbol *(*find_symbol)(struct dso *self, - enum map_type type, u64 addr); + struct rb_root symbol_names[MAP__NR_TYPES]; u8 adjust_symbols:1; u8 slen_calculated:1; u8 has_build_id:1; u8 kernel:1; unsigned char origin; + u8 sorted_by_name; u8 loaded; u8 build_id[BUILD_ID_SIZE]; u16 long_name_len; @@ -93,6 +94,9 @@ struct dso *dso__new(const char *name); void dso__delete(struct dso *self); bool dso__loaded(const struct dso *self, enum map_type type); +bool dso__sorted_by_name(const struct dso *self, enum map_type type); + +void dso__sort_by_name(struct dso *self, enum map_type type); struct dso *dsos__findnew(const char *name); int dso__load(struct dso *self, struct map *map, symbol_filter_t filter); @@ -103,6 +107,9 @@ size_t dso__fprintf_buildid(struct dso *self, FILE *fp); size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp); char dso__symtab_origin(const struct dso *self); void dso__set_build_id(struct dso *self, void *build_id); +struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); +struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, + const char *name); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); @@ -113,8 +120,8 @@ size_t kernel_maps__fprintf(FILE *fp); int symbol__init(struct symbol_conf *conf); -struct thread; -struct thread *kthread; +struct map_groups; +struct map_groups *kmaps; extern struct list_head dsos__user, dsos__kernel; extern struct dso *vdso; #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 603f561..b68a00e 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -9,11 +9,9 @@ static struct rb_root threads; static struct thread *last_match; -void thread__init(struct thread *self, pid_t pid) +void map_groups__init(struct map_groups *self) { int i; - self->pid = pid; - self->comm = NULL; for (i = 0; i < MAP__NR_TYPES; ++i) { self->maps[i] = RB_ROOT; INIT_LIST_HEAD(&self->removed_maps[i]); @@ -25,7 +23,8 @@ static struct thread *thread__new(pid_t pid) struct thread *self = zalloc(sizeof(*self)); if (self != NULL) { - thread__init(self, pid); + map_groups__init(&self->mg); + self->pid = pid; self->comm = malloc(32); if (self->comm) snprintf(self->comm, 32, ":%d", self->pid); @@ -55,10 +54,11 @@ int thread__comm_len(struct thread *self) static const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", + [MAP__VARIABLE] = "Variables", }; -static size_t __thread__fprintf_maps(struct thread *self, - enum map_type type, FILE *fp) +static size_t __map_groups__fprintf_maps(struct map_groups *self, + enum map_type type, FILE *fp) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; @@ -76,16 +76,16 @@ static size_t __thread__fprintf_maps(struct thread *self, return printed; } -size_t thread__fprintf_maps(struct thread *self, FILE *fp) +size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __thread__fprintf_maps(self, i, fp); + printed += __map_groups__fprintf_maps(self, i, fp); return printed; } -static size_t __thread__fprintf_removed_maps(struct thread *self, - enum map_type type, FILE *fp) +static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, + enum map_type type, FILE *fp) { struct map *pos; size_t printed = 0; @@ -101,20 +101,25 @@ static size_t __thread__fprintf_removed_maps(struct thread *self, return printed; } -static size_t thread__fprintf_removed_maps(struct thread *self, FILE *fp) +static size_t map_groups__fprintf_removed_maps(struct map_groups *self, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __thread__fprintf_removed_maps(self, i, fp); + printed += __map_groups__fprintf_removed_maps(self, i, fp); return printed; } -static size_t thread__fprintf(struct thread *self, FILE *fp) +static size_t map_groups__fprintf(struct map_groups *self, FILE *fp) { - size_t printed = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); - printed += thread__fprintf_removed_maps(self, fp); + size_t printed = map_groups__fprintf_maps(self, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + thread__fprintf_removed_maps(self, fp); + return printed + map_groups__fprintf_removed_maps(self, fp); +} + +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) + + map_groups__fprintf(&self->mg, fp); } struct thread *threads__findnew(pid_t pid) @@ -168,7 +173,8 @@ struct thread *register_idle_thread(void) return thread; } -static void thread__remove_overlappings(struct thread *self, struct map *map) +static void map_groups__remove_overlappings(struct map_groups *self, + struct map *map) { struct rb_root *root = &self->maps[map->type]; struct rb_node *next = rb_first(root); @@ -238,12 +244,15 @@ struct map *maps__find(struct rb_root *maps, u64 ip) void thread__insert_map(struct thread *self, struct map *map) { - thread__remove_overlappings(self, map); - maps__insert(&self->maps[map->type], map); + map_groups__remove_overlappings(&self->mg, map); + map_groups__insert(&self->mg, map); } -static int thread__clone_maps(struct thread *self, struct thread *parent, - enum map_type type) +/* + * XXX This should not really _copy_ te maps, but refcount them. + */ +static int map_groups__clone(struct map_groups *self, + struct map_groups *parent, enum map_type type) { struct rb_node *nd; for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) { @@ -251,7 +260,7 @@ static int thread__clone_maps(struct thread *self, struct thread *parent, struct map *new = map__clone(map); if (new == NULL) return -ENOMEM; - thread__insert_map(self, new); + map_groups__insert(self, new); } return 0; } @@ -267,7 +276,7 @@ int thread__fork(struct thread *self, struct thread *parent) return -ENOMEM; for (i = 0; i < MAP__NR_TYPES; ++i) - if (thread__clone_maps(self, parent, i) < 0) + if (map_groups__clone(&self->mg, &parent->mg, i) < 0) return -ENOMEM; return 0; } @@ -286,11 +295,11 @@ size_t threads__fprintf(FILE *fp) return ret; } -struct symbol *thread__find_symbol(struct thread *self, - enum map_type type, u64 addr, - symbol_filter_t filter) +struct symbol *map_groups__find_symbol(struct map_groups *self, + enum map_type type, u64 addr, + symbol_filter_t filter) { - struct map *map = thread__find_map(self, type, addr); + struct map *map = map_groups__find(self, type, addr); if (map != NULL) return map__find_symbol(map, map->map_ip(map, addr), filter); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 686d6e9..1751802 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -5,52 +5,66 @@ #include <unistd.h> #include "symbol.h" -struct thread { - struct rb_node rb_node; +struct map_groups { struct rb_root maps[MAP__NR_TYPES]; struct list_head removed_maps[MAP__NR_TYPES]; - pid_t pid; bool use_modules; +}; + +struct thread { + struct rb_node rb_node; + struct map_groups mg; + pid_t pid; char shortname[3]; char *comm; int comm_len; }; -void thread__init(struct thread *self, pid_t pid); +void map_groups__init(struct map_groups *self); int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); struct thread *threads__findnew(pid_t pid); struct thread *register_idle_thread(void); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); -size_t thread__fprintf_maps(struct thread *self, FILE *fp); +size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp); size_t threads__fprintf(FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); -static inline struct map *thread__find_map(struct thread *self, +static inline void map_groups__insert(struct map_groups *self, struct map *map) +{ + maps__insert(&self->maps[map->type], map); +} + +static inline struct map *map_groups__find(struct map_groups *self, enum map_type type, u64 addr) { - return self ? maps__find(&self->maps[type], addr) : NULL; + return maps__find(&self->maps[type], addr); } -static inline void __thread__insert_map(struct thread *self, struct map *map) +static inline struct map *thread__find_map(struct thread *self, + enum map_type type, u64 addr) { - maps__insert(&self->maps[map->type], map); + return self ? map_groups__find(&self->mg, type, addr) : NULL; } void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter); -struct symbol *thread__find_symbol(struct thread *self, - enum map_type type, u64 addr, - symbol_filter_t filter); +struct symbol *map_groups__find_symbol(struct map_groups *self, + enum map_type type, u64 addr, + symbol_filter_t filter); static inline struct symbol * -thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) +map_groups__find_function(struct map_groups *self, u64 addr, + symbol_filter_t filter) { - return thread__find_symbol(self, MAP__FUNCTION, addr, filter); + return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter); } + +struct map *map_groups__find_by_name(struct map_groups *self, + enum map_type type, const char *name); #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 0302405..c5c32be 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -177,7 +177,7 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused) func_count++; } - func_list = malloc_or_die(sizeof(*func_list) * func_count + 1); + func_list = malloc_or_die(sizeof(*func_list) * (func_count + 1)); i = 0; while (list) { @@ -1477,7 +1477,7 @@ process_fields(struct event *event, struct print_flag_sym **list, char **tok) goto out_free; field = malloc_or_die(sizeof(*field)); - memset(field, 0, sizeof(field)); + memset(field, 0, sizeof(*field)); value = arg_eval(arg); field->value = strdup(value); diff --git a/tools/perf/util/trace-event-perl.c b/tools/perf/util/trace-event-perl.c index 51e833f..a5ffe60 100644 --- a/tools/perf/util/trace-event-perl.c +++ b/tools/perf/util/trace-event-perl.c @@ -32,9 +32,6 @@ void xs_init(pTHX); -void boot_Perf__Trace__Context(pTHX_ CV *cv); -void boot_DynaLoader(pTHX_ CV *cv); - void xs_init(pTHX) { const char *file = __FILE__; @@ -573,26 +570,72 @@ struct scripting_ops perl_scripting_ops = { .generate_script = perl_generate_script, }; -#ifdef NO_LIBPERL -void setup_perl_scripting(void) +static void print_unsupported_msg(void) { fprintf(stderr, "Perl scripting not supported." - " Install libperl and rebuild perf to enable it. e.g. " - "apt-get install libperl-dev (ubuntu), yum install " - "perl-ExtUtils-Embed (Fedora), etc.\n"); + " Install libperl and rebuild perf to enable it.\n" + "For example:\n # apt-get install libperl-dev (ubuntu)" + "\n # yum install perl-ExtUtils-Embed (Fedora)" + "\n etc.\n"); } -#else -void setup_perl_scripting(void) + +static int perl_start_script_unsupported(const char *script __unused) +{ + print_unsupported_msg(); + + return -1; +} + +static int perl_stop_script_unsupported(void) +{ + return 0; +} + +static void perl_process_event_unsupported(int cpu __unused, + void *data __unused, + int size __unused, + unsigned long long nsecs __unused, + char *comm __unused) +{ +} + +static int perl_generate_script_unsupported(const char *outfile __unused) +{ + print_unsupported_msg(); + + return -1; +} + +struct scripting_ops perl_scripting_unsupported_ops = { + .name = "Perl", + .start_script = perl_start_script_unsupported, + .stop_script = perl_stop_script_unsupported, + .process_event = perl_process_event_unsupported, + .generate_script = perl_generate_script_unsupported, +}; + +static void register_perl_scripting(struct scripting_ops *scripting_ops) { int err; - err = script_spec_register("Perl", &perl_scripting_ops); + err = script_spec_register("Perl", scripting_ops); if (err) die("error registering Perl script extension"); - err = script_spec_register("pl", &perl_scripting_ops); + err = script_spec_register("pl", scripting_ops); if (err) die("error registering pl script extension"); scripting_context = malloc(sizeof(struct scripting_context)); } + +#ifdef NO_LIBPERL +void setup_perl_scripting(void) +{ + register_perl_scripting(&perl_scripting_unsupported_ops); +} +#else +void setup_perl_scripting(void) +{ + register_perl_scripting(&perl_scripting_ops); +} #endif diff --git a/tools/perf/util/trace-event-perl.h b/tools/perf/util/trace-event-perl.h index 8fe0d86..e88fb26 100644 --- a/tools/perf/util/trace-event-perl.h +++ b/tools/perf/util/trace-event-perl.h @@ -34,9 +34,13 @@ typedef int INTERP; #define dXSUB_SYS #define pTHX_ static inline void newXS(const char *a, void *b, const char *c) {} +static void boot_Perf__Trace__Context(pTHX_ CV *cv) {} +static void boot_DynaLoader(pTHX_ CV *cv) {} #else #include <EXTERN.h> #include <perl.h> +void boot_Perf__Trace__Context(pTHX_ CV *cv); +void boot_DynaLoader(pTHX_ CV *cv); typedef PerlInterpreter * INTERP; #endif diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 342dfdd..1744422 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -145,8 +145,9 @@ static void read_proc_kallsyms(void) if (!size) return; - buf = malloc_or_die(size); + buf = malloc_or_die(size + 1); read_or_die(buf, size); + buf[size] = '\0'; parse_proc_kallsyms(buf, size); |
