diff options
Diffstat (limited to 'tools/perf')
29 files changed, 1944 insertions, 856 deletions
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 34202b1be0bb..0f944b3be9e9 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -57,6 +57,11 @@ OPTIONS --force:: Forcibly add events with existing name. +-n:: +--dry-run:: + Dry run. With this option, --add and --del doesn't execute actual + adding and removal operations. + PROBE SYNTAX ------------ Probe points are defined by following syntax. diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 8a8f52db7e38..0abd25ee595f 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -513,6 +513,14 @@ else LIB_OBJS += util/probe-finder.o endif +ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) + msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); + BASIC_CFLAGS += -DNO_NEWT_SUPPORT +else + EXTLIBS += -lnewt + LIB_OBJS += util/newt.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` diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 6ad7148451c5..45d14660d53d 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -452,6 +452,16 @@ static void annotate_sym(struct hist_entry *he) if (!filename) return; + if (dso->origin == DSO__ORIG_KERNEL) { + if (dso->annotate_warned) + return; + dso->annotate_warned = 1; + pr_err("Can't annotate %s: No vmlinux file was found in the " + "path:\n", sym->name); + vmlinux_path__fprintf(stderr); + return; + } + pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__, filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index c30a33592340..e0dafd9dfeb5 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -36,47 +36,41 @@ #include "builtin.h" #include "util/util.h" #include "util/strlist.h" -#include "util/event.h" +#include "util/symbol.h" #include "util/debug.h" #include "util/debugfs.h" -#include "util/symbol.h" -#include "util/thread.h" #include "util/parse-options.h" #include "util/parse-events.h" /* For debugfs_path */ #include "util/probe-finder.h" #include "util/probe-event.h" #define MAX_PATH_LEN 256 -#define MAX_PROBES 128 /* Session management structure */ static struct { - bool need_dwarf; bool list_events; bool force_add; bool show_lines; - int nr_probe; - struct probe_point probes[MAX_PROBES]; + int nevents; + struct perf_probe_event events[MAX_PROBES]; struct strlist *dellist; - struct map_groups kmap_groups; - struct map *kmaps[MAP__NR_TYPES]; struct line_range line_range; -} session; +} params; /* Parse an event definition. Note that any error must die. */ static void parse_probe_event(const char *str) { - struct probe_point *pp = &session.probes[session.nr_probe]; + struct perf_probe_event *pev = ¶ms.events[params.nevents]; - pr_debug("probe-definition(%d): %s\n", session.nr_probe, str); - if (++session.nr_probe == MAX_PROBES) + pr_debug("probe-definition(%d): %s\n", params.nevents, str); + if (++params.nevents == MAX_PROBES) die("Too many probes (> %d) are specified.", MAX_PROBES); - /* Parse perf-probe event into probe_point */ - parse_perf_probe_event(str, pp, &session.need_dwarf); + /* Parse a perf-probe command into event */ + parse_perf_probe_command(str, pev); - pr_debug("%d arguments\n", pp->nr_args); + pr_debug("%d arguments\n", pev->nargs); } static void parse_probe_event_argv(int argc, const char **argv) @@ -88,9 +82,7 @@ static void parse_probe_event_argv(int argc, const char **argv) 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."); + buf = xzalloc(len + 1); len = 0; for (i = 0; i < argc; i++) len += sprintf(&buf[len], "%s ", argv[i]); @@ -110,43 +102,21 @@ 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); + if (!params.dellist) + params.dellist = strlist__new(true, NULL); + strlist__add(params.dellist, str); } return 0; } -/* Currently just checking function name from symbol map */ -static void evaluate_probe_point(struct probe_point *pp) -{ - struct symbol *sym; - sym = map__find_symbol_by_name(session.kmaps[MAP__FUNCTION], - pp->function, NULL); - if (!sym) - die("Kernel symbol \'%s\' not found - probe not added.", - pp->function); -} - #ifndef NO_DWARF_SUPPORT -static int open_vmlinux(void) -{ - if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) { - pr_debug("Failed to load kernel map.\n"); - return -EINVAL; - } - pr_debug("Try to open %s\n", - session.kmaps[MAP__FUNCTION]->dso->long_name); - return open(session.kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY); -} - static int opt_show_lines(const struct option *opt __used, const char *str, int unset __used) { if (str) - parse_line_range_desc(str, &session.line_range); - INIT_LIST_HEAD(&session.line_range.line_list); - session.show_lines = true; + parse_line_range_desc(str, ¶ms.line_range); + INIT_LIST_HEAD(¶ms.line_range.line_list); + params.show_lines = true; return 0; } #endif @@ -169,7 +139,7 @@ static const struct option options[] = { OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), #endif - OPT_BOOLEAN('l', "list", &session.list_events, + OPT_BOOLEAN('l', "list", ¶ms.list_events, "list up current probe events"), OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.", opt_del_probe_event), @@ -197,41 +167,19 @@ static const struct option options[] = { #endif "\t\t\tkprobe-tracer argument format.)\n", opt_add_probe_event), - OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events" + OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events" " with existing name"), #ifndef NO_DWARF_SUPPORT OPT_CALLBACK('L', "line", NULL, "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]", "Show source code lines.", opt_show_lines), #endif + OPT__DRY_RUN(&probe_event_dry_run), OPT_END() }; -/* Initialize symbol maps for vmlinux */ -static void init_vmlinux(void) -{ - symbol_conf.sort_by_name = true; - if (symbol_conf.vmlinux_name == NULL) - symbol_conf.try_vmlinux_path = true; - else - pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); - if (symbol__init() < 0) - die("Failed to init symbol map."); - - map_groups__init(&session.kmap_groups); - if (map_groups__create_kernel_maps(&session.kmap_groups, - session.kmaps) < 0) - die("Failed to create kernel maps."); -} - int cmd_probe(int argc, const char **argv, const char *prefix __used) { - int i, ret; -#ifndef NO_DWARF_SUPPORT - int fd; -#endif - struct probe_point *pp; - argc = parse_options(argc, argv, options, probe_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (argc > 0) { @@ -242,20 +190,20 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) parse_probe_event_argv(argc, argv); } - if ((!session.nr_probe && !session.dellist && !session.list_events && - !session.show_lines)) + if ((!params.nevents && !params.dellist && !params.list_events && + !params.show_lines)) usage_with_options(probe_usage, options); if (debugfs_valid_mountpoint(debugfs_path) < 0) die("Failed to find debugfs path."); - if (session.list_events) { - if (session.nr_probe != 0 || session.dellist) { + if (params.list_events) { + if (params.nevents != 0 || params.dellist) { pr_warning(" Error: Don't use --list with" " --add/--del.\n"); usage_with_options(probe_usage, options); } - if (session.show_lines) { + if (params.show_lines) { pr_warning(" Error: Don't use --list with --line.\n"); usage_with_options(probe_usage, options); } @@ -264,98 +212,26 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) } #ifndef NO_DWARF_SUPPORT - if (session.show_lines) { - if (session.nr_probe != 0 || session.dellist) { + if (params.show_lines) { + if (params.nevents != 0 || params.dellist) { pr_warning(" Error: Don't use --line with" " --add/--del.\n"); usage_with_options(probe_usage, options); } - init_vmlinux(); - fd = open_vmlinux(); - if (fd < 0) - die("Could not open debuginfo file."); - ret = find_line_range(fd, &session.line_range); - if (ret <= 0) - die("Source line is not found.\n"); - close(fd); - show_line_range(&session.line_range); + + show_line_range(¶ms.line_range); return 0; } #endif - if (session.dellist) { - del_trace_kprobe_events(session.dellist); - strlist__delete(session.dellist); - if (session.nr_probe == 0) + if (params.dellist) { + del_perf_probe_events(params.dellist); + strlist__delete(params.dellist); + if (params.nevents == 0) return 0; } - /* Add probes */ - init_vmlinux(); - - if (session.need_dwarf) -#ifdef NO_DWARF_SUPPORT - die("Debuginfo-analysis is not supported"); -#else /* !NO_DWARF_SUPPORT */ - pr_debug("Some probes require debuginfo.\n"); - - fd = open_vmlinux(); - if (fd < 0) { - if (session.need_dwarf) - die("Could not open debuginfo file."); - - pr_debug("Could not open vmlinux/module file." - " Try to use symbols.\n"); - goto end_dwarf; - } - - /* Searching probe points */ - for (i = 0; i < session.nr_probe; i++) { - pp = &session.probes[i]; - if (pp->found) - continue; - - lseek(fd, SEEK_SET, 0); - ret = find_probe_point(fd, pp); - if (ret > 0) - continue; - if (ret == 0) { /* No error but failed to find probe point. */ - synthesize_perf_probe_point(pp); - die("Probe point '%s' not found. - probe not added.", - pp->probes[0]); - } - /* Error path */ - if (session.need_dwarf) { - if (ret == -ENOENT) - pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO=y.\n"); - die("Could not analyze debuginfo."); - } - pr_debug("An error occurred in debuginfo analysis." - " Try to use symbols.\n"); - break; - } - close(fd); - -end_dwarf: -#endif /* !NO_DWARF_SUPPORT */ - - /* Synthesize probes without dwarf */ - for (i = 0; i < session.nr_probe; i++) { - pp = &session.probes[i]; - if (pp->found) /* This probe is already found. */ - continue; - - evaluate_probe_point(pp); - ret = synthesize_trace_kprobe_event(pp); - if (ret == -E2BIG) - die("probe point definition becomes too long."); - else if (ret < 0) - die("Failed to synthesize a probe point."); - } - - /* Settng up probe points */ - add_trace_kprobe_events(session.probes, session.nr_probe, - session.force_add); + add_perf_probe_events(params.events, params.nevents, params.force_add); return 0; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3b8b6387c47c..bb5b23db4239 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -27,7 +27,7 @@ #include <unistd.h> #include <sched.h> -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; static long default_interval = 0; @@ -43,6 +43,9 @@ static int raw_samples = 0; static int system_wide = 0; static int profile_cpu = -1; static pid_t target_pid = -1; +static pid_t target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; static pid_t child_pid = -1; static int inherit = 1; static int force = 0; @@ -60,7 +63,7 @@ static struct timeval this_read; static u64 bytes_written = 0; -static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; +static struct pollfd *event_array; static int nr_poll = 0; static int nr_cpu = 0; @@ -77,7 +80,7 @@ struct mmap_data { unsigned int prev; }; -static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; +static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; static unsigned long mmap_read_head(struct mmap_data *md) { @@ -225,12 +228,13 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n return h_attr; } -static void create_counter(int counter, int cpu, pid_t pid) +static void create_counter(int counter, int cpu) { char *filter = filters[counter]; struct perf_event_attr *attr = attrs + counter; struct perf_header_attr *h_attr; int track = !counter; /* only the first counter needs these */ + int thread_index; int ret; struct { u64 count; @@ -275,118 +279,129 @@ static void create_counter(int counter, int cpu, pid_t pid) attr->mmap = track; attr->comm = track; attr->inherit = inherit; - attr->disabled = 1; + if (target_pid == -1 && !system_wide) { + attr->disabled = 1; + attr->enable_on_exec = 1; + } + for (thread_index = 0; thread_index < thread_num; thread_index++) { try_again: - fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0); - - if (fd[nr_cpu][counter] < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) - die("Permission error - are you root?\n"); - else if (err == ENODEV && profile_cpu != -1) - die("No such device - did you specify an out-of-range profile CPU?\n"); + fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr, + all_tids[thread_index], cpu, group_fd, 0); + + if (fd[nr_cpu][counter][thread_index] < 0) { + int err = errno; + + if (err == EPERM || err == EACCES) + die("Permission error - are you root?\n" + "\t Consider tweaking" + " /proc/sys/kernel/perf_event_paranoid.\n"); + else if (err == ENODEV && profile_cpu != -1) { + die("No such device - did you specify" + " an out-of-range profile CPU?\n"); + } - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: - */ - if (attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - - if (verbose) - warning(" ... trying to fall back to cpu-clock-ticks\n"); - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - goto try_again; - } - printf("\n"); - error("perfcounter syscall returned with %d (%s)\n", - fd[nr_cpu][counter], strerror(err)); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[nr_cpu][counter][thread_index], strerror(err)); #if defined(__i386__) || defined(__x86_64__) - if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) - die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n"); + if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) + die("No hardware sampling interrupt available." + " No APIC? If so then you can boot the kernel" + " with the \"lapic\" boot parameter to" + " force-enable it.\n"); #endif - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - exit(-1); - } + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + exit(-1); + } - h_attr = get_header_attr(attr, counter); - if (h_attr == NULL) - die("nomem\n"); + h_attr = get_header_attr(attr, counter); + if (h_attr == NULL) + die("nomem\n"); - if (!file_new) { - if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { - fprintf(stderr, "incompatible append\n"); - exit(-1); + if (!file_new) { + if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { + fprintf(stderr, "incompatible append\n"); + exit(-1); + } } - } - if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) { - perror("Unable to read perf file descriptor\n"); - exit(-1); - } + if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) { + perror("Unable to read perf file descriptor\n"); + exit(-1); + } - if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { - pr_warning("Not enough memory to add id\n"); - exit(-1); - } + if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { + pr_warning("Not enough memory to add id\n"); + exit(-1); + } - assert(fd[nr_cpu][counter] >= 0); - fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); + assert(fd[nr_cpu][counter][thread_index] >= 0); + fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK); - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = fd[nr_cpu][counter]; - if (multiplex && multiplex_fd == -1) - multiplex_fd = fd[nr_cpu][counter]; + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[nr_cpu][counter][thread_index]; + if (multiplex && multiplex_fd == -1) + multiplex_fd = fd[nr_cpu][counter][thread_index]; - if (multiplex && fd[nr_cpu][counter] != multiplex_fd) { + if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) { - ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd); - assert(ret != -1); - } else { - event_array[nr_poll].fd = fd[nr_cpu][counter]; - event_array[nr_poll].events = POLLIN; - nr_poll++; - - mmap_array[nr_cpu][counter].counter = counter; - mmap_array[nr_cpu][counter].prev = 0; - mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1; - mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0); - if (mmap_array[nr_cpu][counter].base == MAP_FAILED) { - error("failed to mmap with %d (%s)\n", errno, strerror(errno)); - exit(-1); + ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd); + assert(ret != -1); + } else { + event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[nr_cpu][counter][thread_index].counter = counter; + mmap_array[nr_cpu][counter][thread_index].prev = 0; + mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1; + mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0); + if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) { + error("failed to mmap with %d (%s)\n", errno, strerror(errno)); + exit(-1); + } } - } - if (filter != NULL) { - ret = ioctl(fd[nr_cpu][counter], - PERF_EVENT_IOC_SET_FILTER, filter); - if (ret) { - error("failed to set filter with %d (%s)\n", errno, - strerror(errno)); - exit(-1); + if (filter != NULL) { + ret = ioctl(fd[nr_cpu][counter][thread_index], + PERF_EVENT_IOC_SET_FILTER, filter); + if (ret) { + error("failed to set filter with %d (%s)\n", errno, + strerror(errno)); + exit(-1); + } } } - - ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE); } -static void open_counters(int cpu, pid_t pid) +static void open_counters(int cpu) { int counter; group_fd = -1; for (counter = 0; counter < nr_counters; counter++) - create_counter(counter, cpu, pid); + create_counter(counter, cpu); nr_cpu++; } @@ -421,7 +436,7 @@ static int __cmd_record(int argc, const char **argv) int err; unsigned long waking = 0; int child_ready_pipe[2], go_pipe[2]; - const bool forks = target_pid == -1 && argc > 0; + const bool forks = argc > 0; char buf; page_size = sysconf(_SC_PAGE_SIZE); @@ -492,13 +507,13 @@ static int __cmd_record(int argc, const char **argv) atexit(atexit_header); if (forks) { - pid = fork(); + child_pid = fork(); if (pid < 0) { perror("failed to fork"); exit(-1); } - if (!pid) { + if (!child_pid) { close(child_ready_pipe[0]); close(go_pipe[1]); fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); @@ -527,10 +542,8 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - child_pid = pid; - - if (!system_wide) - target_pid = pid; + if (!system_wide && target_tid == -1 && target_pid == -1) + all_tids[0] = child_pid; close(child_ready_pipe[1]); close(go_pipe[0]); @@ -544,13 +557,12 @@ static int __cmd_record(int argc, const char **argv) close(child_ready_pipe[0]); } - if ((!system_wide && !inherit) || profile_cpu != -1) { - open_counters(profile_cpu, target_pid); + open_counters(profile_cpu); } else { nr_cpus = read_cpu_map(); for (i = 0; i < nr_cpus; i++) - open_counters(cpumap[i], target_pid); + open_counters(cpumap[i]); } if (file_new) { @@ -575,7 +587,7 @@ static int __cmd_record(int argc, const char **argv) } if (!system_wide && profile_cpu == -1) - event__synthesize_thread(target_pid, process_synthesized_event, + event__synthesize_thread(target_tid, process_synthesized_event, session); else event__synthesize_threads(process_synthesized_event, session); @@ -598,11 +610,16 @@ static int __cmd_record(int argc, const char **argv) for (;;) { int hits = samples; + int thread; for (i = 0; i < nr_cpu; i++) { for (counter = 0; counter < nr_counters; counter++) { - if (mmap_array[i][counter].base) - mmap_read(&mmap_array[i][counter]); + for (thread = 0; + thread < thread_num; thread++) { + if (mmap_array[i][counter][thread].base) + mmap_read(&mmap_array[i][counter][thread]); + } + } } @@ -615,8 +632,15 @@ static int __cmd_record(int argc, const char **argv) if (done) { for (i = 0; i < nr_cpu; i++) { - for (counter = 0; counter < nr_counters; counter++) - ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE); + for (counter = 0; + counter < nr_counters; + counter++) { + for (thread = 0; + thread < thread_num; + thread++) + ioctl(fd[i][counter][thread], + PERF_EVENT_IOC_DISABLE); + } } } } @@ -648,7 +672,9 @@ static const struct option options[] = { OPT_CALLBACK(0, "filter", NULL, "filter", "event filter", parse_filter), OPT_INTEGER('p', "pid", &target_pid, - "record events on existing pid"), + "record events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "record events on existing thread id"), OPT_INTEGER('r', "realtime", &realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_BOOLEAN('R', "raw-samples", &raw_samples, @@ -689,10 +715,12 @@ static const struct option options[] = { int cmd_record(int argc, const char **argv, const char *prefix __used) { int counter; + int i,j; argc = parse_options(argc, argv, options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1) + if (!argc && target_pid == -1 && target_tid == -1 && + !system_wide && profile_cpu == -1) usage_with_options(record_usage, options); symbol__init(); @@ -703,6 +731,37 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) attrs[0].config = PERF_COUNT_HW_CPU_CYCLES; } + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(record_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + mmap_array[i][j] = malloc( + sizeof(struct mmap_data)*thread_num); + if (!fd[i][j] || !mmap_array[i][j]) + return -ENOMEM; + } + } + event_array = malloc( + sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num); + if (!event_array) + return -ENOMEM; + /* * User specified count overrides default frequency. */ diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f815de25d0fc..1f9f8695f055 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -267,6 +267,7 @@ static int __cmd_report(void) int ret = -EINVAL; struct perf_session *session; struct rb_node *next; + const char *help = "For a higher level overview, try: perf report --sort comm,dso"; session = perf_session__new(input_name, O_RDONLY, force); if (session == NULL) @@ -301,30 +302,38 @@ static int __cmd_report(void) stats = rb_entry(next, struct event_stat_id, rb_node); perf_session__collapse_resort(&stats->hists); perf_session__output_resort(&stats->hists, stats->stats.total); - if (rb_first(&session->stats_by_id) == - rb_last(&session->stats_by_id)) - fprintf(stdout, "# Samples: %Ld\n#\n", - stats->stats.total); - else - fprintf(stdout, "# Samples: %Ld %s\n#\n", - stats->stats.total, - __event_name(stats->type, stats->config)); - perf_session__fprintf_hists(&stats->hists, NULL, false, stdout, + if (use_browser) + perf_session__browse_hists(&stats->hists, + stats->stats.total, help); + else { + if (rb_first(&session->stats_by_id) == + rb_last(&session->stats_by_id)) + fprintf(stdout, "# Samples: %Ld\n#\n", + stats->stats.total); + else + fprintf(stdout, "# Samples: %Ld %s\n#\n", + stats->stats.total, + __event_name(stats->type, stats->config)); + + perf_session__fprintf_hists(&stats->hists, NULL, false, stdout, stats->stats.total); - fprintf(stdout, "\n\n"); + fprintf(stdout, "\n\n"); + } + next = rb_next(&stats->rb_node); } - if (sort_order == default_sort_order && - parent_pattern == default_parent_pattern) - fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n"); + if (!use_browser && sort_order == default_sort_order && + parent_pattern == default_parent_pattern) { + fprintf(stdout, "#\n# (%s)\n#\n", help); - if (show_threads) { - bool raw_printing_style = !strcmp(pretty_printing_style, "raw"); - perf_read_values_display(stdout, &show_threads_values, - raw_printing_style); - perf_read_values_destroy(&show_threads_values); + if (show_threads) { + bool style = !strcmp(pretty_printing_style, "raw"); + perf_read_values_display(stdout, &show_threads_values, + style); + perf_read_values_destroy(&show_threads_values); + } } out_delete: perf_session__delete(session); @@ -447,7 +456,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) { argc = parse_options(argc, argv, options, report_usage, 0); - setup_pager(); + setup_browser(); if (symbol__init() < 0) return -1; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 95db31cff6fd..c92f90ff5a9f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -46,6 +46,7 @@ #include "util/debug.h" #include "util/header.h" #include "util/cpumap.h" +#include "util/thread.h" #include <sys/prctl.h> #include <math.h> @@ -74,10 +75,13 @@ static int run_count = 1; static int inherit = 1; static int scale = 1; static pid_t target_pid = -1; +static pid_t target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; static pid_t child_pid = -1; static int null_run = 0; -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; static int event_scaled[MAX_COUNTERS]; @@ -140,9 +144,10 @@ struct stats runtime_branches_stats; #define ERR_PERF_OPEN \ "Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n" -static void create_perf_stat_counter(int counter, int pid) +static void create_perf_stat_counter(int counter) { struct perf_event_attr *attr = attrs + counter; + int thread; if (scale) attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | @@ -152,20 +157,26 @@ static void create_perf_stat_counter(int counter, int pid) unsigned int cpu; for (cpu = 0; cpu < nr_cpus; cpu++) { - fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0); - if (fd[cpu][counter] < 0 && verbose) + fd[cpu][counter][0] = sys_perf_event_open(attr, + -1, cpumap[cpu], -1, 0); + if (fd[cpu][counter][0] < 0 && verbose) fprintf(stderr, ERR_PERF_OPEN, counter, - fd[cpu][counter], strerror(errno)); + fd[cpu][counter][0], strerror(errno)); } } else { attr->inherit = inherit; - attr->disabled = 1; - attr->enable_on_exec = 1; - - fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0); - if (fd[0][counter] < 0 && verbose) - fprintf(stderr, ERR_PERF_OPEN, counter, - fd[0][counter], strerror(errno)); + if (target_pid == -1) { + attr->disabled = 1; + attr->enable_on_exec = 1; + } + for (thread = 0; thread < thread_num; thread++) { + fd[0][counter][thread] = sys_perf_event_open(attr, + all_tids[thread], -1, -1, 0); + if (fd[0][counter][thread] < 0 && verbose) + fprintf(stderr, ERR_PERF_OPEN, counter, + fd[0][counter][thread], + strerror(errno)); + } } } @@ -190,25 +201,28 @@ static void read_counter(int counter) unsigned int cpu; size_t res, nv; int scaled; - int i; + int i, thread; count[0] = count[1] = count[2] = 0; nv = scale ? 3 : 1; for (cpu = 0; cpu < nr_cpus; cpu++) { - if (fd[cpu][counter] < 0) - continue; - - res = read(fd[cpu][counter], single_count, nv * sizeof(u64)); - assert(res == nv * sizeof(u64)); - - close(fd[cpu][counter]); - fd[cpu][counter] = -1; - - count[0] += single_count[0]; - if (scale) { - count[1] += single_count[1]; - count[2] += single_count[2]; + for (thread = 0; thread < thread_num; thread++) { + if (fd[cpu][counter][thread] < 0) + continue; + + res = read(fd[cpu][counter][thread], + single_count, nv * sizeof(u64)); + assert(res == nv * sizeof(u64)); + + close(fd[cpu][counter][thread]); + fd[cpu][counter][thread] = -1; + + count[0] += single_count[0]; + if (scale) { + count[1] += single_count[1]; + count[2] += single_count[2]; + } } } @@ -251,9 +265,8 @@ static int run_perf_stat(int argc __used, const char **argv) unsigned long long t0, t1; int status = 0; int counter; - int pid = target_pid; int child_ready_pipe[2], go_pipe[2]; - const bool forks = (target_pid == -1 && argc > 0); + const bool forks = (argc > 0); char buf; if (!system_wide) @@ -265,10 +278,10 @@ static int run_perf_stat(int argc __used, const char **argv) } if (forks) { - if ((pid = fork()) < 0) + if ((child_pid = fork()) < 0) perror("failed to fork"); - if (!pid) { + if (!child_pid) { close(child_ready_pipe[0]); close(go_pipe[1]); fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); @@ -297,7 +310,8 @@ static int run_perf_stat(int argc __used, const char **argv) exit(-1); } - child_pid = pid; + if (target_tid == -1 && target_pid == -1 && !system_wide) + all_tids[0] = child_pid; /* * Wait for the child to be ready to exec. @@ -310,7 +324,7 @@ static int run_perf_stat(int argc __used, const char **argv) } for (counter = 0; counter < nr_counters; counter++) - create_perf_stat_counter(counter, pid); + create_perf_stat_counter(counter); /* * Enable counters and exec the command: @@ -321,7 +335,7 @@ static int run_perf_stat(int argc __used, const char **argv) close(go_pipe[1]); wait(&status); } else { - while(!done); + while(!done) sleep(1); } t1 = rdclock(); @@ -429,12 +443,14 @@ static void print_stat(int argc, const char **argv) fprintf(stderr, "\n"); fprintf(stderr, " Performance counter stats for "); - if(target_pid == -1) { + if(target_pid == -1 && target_tid == -1) { fprintf(stderr, "\'%s", argv[0]); for (i = 1; i < argc; i++) fprintf(stderr, " %s", argv[i]); - }else - fprintf(stderr, "task pid \'%d", target_pid); + } else if (target_pid != -1) + fprintf(stderr, "process id \'%d", target_pid); + else + fprintf(stderr, "thread id \'%d", target_tid); fprintf(stderr, "\'"); if (run_count > 1) @@ -459,7 +475,7 @@ static volatile int signr = -1; static void skip_signal(int signo) { - if(target_pid != -1) + if(child_pid == -1) done = 1; signr = signo; @@ -489,7 +505,9 @@ static const struct option options[] = { OPT_BOOLEAN('i', "inherit", &inherit, "child tasks inherit counters"), OPT_INTEGER('p', "pid", &target_pid, - "stat events on existing pid"), + "stat events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "stat events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('c', "scale", &scale, @@ -506,10 +524,11 @@ static const struct option options[] = { int cmd_stat(int argc, const char **argv, const char *prefix __used) { int status; + int i,j; argc = parse_options(argc, argv, options, stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target_pid == -1) + if (!argc && target_pid == -1 && target_tid == -1) usage_with_options(stat_usage, options); if (run_count <= 0) usage_with_options(stat_usage, options); @@ -525,6 +544,31 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) else nr_cpus = 1; + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(stat_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + if (!fd[i][j]) + return -ENOMEM; + } + } + /* * We dont want to block the signals - that would cause * child tasks to inherit that and Ctrl-C would not work. diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 0b719e3dde05..5f3ac9ff354d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -55,7 +55,7 @@ #include <linux/unistd.h> #include <linux/types.h> -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; static int system_wide = 0; @@ -65,6 +65,9 @@ static int count_filter = 5; static int print_entries; static int target_pid = -1; +static int target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; static int inherit = 0; static int profile_cpu = -1; static int nr_cpus = 0; @@ -133,7 +136,7 @@ static inline struct symbol *sym_entry__symbol(struct sym_entry *self) return ((void *)self) + symbol_conf.priv_size; } -static void get_term_dimensions(struct winsize *ws) +void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); @@ -169,7 +172,7 @@ static void sig_winch_handler(int sig __used) update_print_entries(&winsize); } -static void parse_source(struct sym_entry *syme) +static int parse_source(struct sym_entry *syme) { struct symbol *sym; struct sym_entry_source *source; @@ -180,12 +183,21 @@ static void parse_source(struct sym_entry *syme) u64 len; if (!syme) - return; + return -1; + + sym = sym_entry__symbol(syme); + map = syme->map; + + /* + * We can't annotate with just /proc/kallsyms + */ + if (map->dso->origin == DSO__ORIG_KERNEL) + return -1; if (syme->src == NULL) { syme->src = zalloc(sizeof(*source)); if (syme->src == NULL) - return; + return -1; pthread_mutex_init(&syme->src->lock, NULL); } @@ -195,9 +207,6 @@ static void parse_source(struct sym_entry *syme) pthread_mutex_lock(&source->lock); goto out_assign; } - - sym = sym_entry__symbol(syme); - map = syme->map; path = map->dso->long_name; len = sym->end - sym->start; @@ -209,7 +218,7 @@ static void parse_source(struct sym_entry *syme) file = popen(command, "r"); if (!file) - return; + return -1; pthread_mutex_lock(&source->lock); source->lines_tail = &source->lines; @@ -245,6 +254,7 @@ static void parse_source(struct sym_entry *syme) out_assign: sym_filter_entry = syme; pthread_mutex_unlock(&source->lock); + return 0; } static void __zero_source_counters(struct sym_entry *syme) @@ -411,6 +421,7 @@ static double sym_weight(const struct sym_entry *sym) static long samples; static long userspace_samples; +static long exact_samples; static const char CONSOLE_CLEAR[] = "[H[2J"; static void __list_insert_active_sym(struct sym_entry *syme) @@ -451,14 +462,15 @@ static void print_sym_table(void) int counter, snap = !display_weighted ? sym_counter : 0; float samples_per_sec = samples/delay_secs; float ksamples_per_sec = (samples-userspace_samples)/delay_secs; + float esamples_percent = (100.0*exact_samples)/samples; float sum_ksamples = 0.0; struct sym_entry *syme, *n; struct rb_root tmp = RB_ROOT; struct rb_node *nd; - int sym_width = 0, dso_width = 0, max_dso_width; + int sym_width = 0, dso_width = 0, dso_short_width = 0; const int win_width = winsize.ws_col - 1; - samples = userspace_samples = 0; + samples = userspace_samples = exact_samples = 0; /* Sort the active symbols */ pthread_mutex_lock(&active_symbols_lock); @@ -489,9 +501,10 @@ static void print_sym_table(void) puts(CONSOLE_CLEAR); printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [", + printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% exact: %4.1f%% [", samples_per_sec, - 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); + 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)), + esamples_percent); if (nr_counters == 1 || !display_weighted) { printf("%Ld", (u64)attrs[0].sample_period); @@ -514,13 +527,15 @@ static void print_sym_table(void) if (target_pid != -1) printf(" (target_pid: %d", target_pid); + else if (target_tid != -1) + printf(" (target_tid: %d", target_tid); else printf(" (all"); if (profile_cpu != -1) printf(", cpu: %d)\n", profile_cpu); else { - if (target_pid != -1) + if (target_tid != -1) printf(")\n"); else printf(", %d CPUs)\n", nr_cpus); @@ -545,15 +560,20 @@ static void print_sym_table(void) if (syme->map->dso->long_name_len > dso_width) dso_width = syme->map->dso->long_name_len; + if (syme->map->dso->short_name_len > dso_short_width) + dso_short_width = syme->map->dso->short_name_len; + if (syme->name_len > sym_width) sym_width = syme->name_len; } printed = 0; - max_dso_width = winsize.ws_col - sym_width - 29; - if (dso_width > max_dso_width) - dso_width = max_dso_width; + if (sym_width + dso_width > winsize.ws_col - 29) { + dso_width = dso_short_width; + if (sym_width + dso_width > winsize.ws_col - 29) + sym_width = winsize.ws_col - dso_width - 29; + } putchar('\n'); if (nr_counters == 1) printf(" samples pcnt"); @@ -955,6 +975,9 @@ static void event__process_sample(const event_t *self, return; } + if (self->header.misc & PERF_RECORD_MISC_EXACT) + exact_samples++; + if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 || al.filtered) return; @@ -985,7 +1008,17 @@ static void event__process_sample(const event_t *self, if (sym_filter_entry_sched) { sym_filter_entry = sym_filter_entry_sched; sym_filter_entry_sched = NULL; - parse_source(sym_filter_entry); + if (parse_source(sym_filter_entry) < 0) { + struct symbol *sym = sym_entry__symbol(sym_filter_entry); + + pr_err("Can't annotate %s", sym->name); + if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) { + pr_err(": No vmlinux file was found in the path:\n"); + vmlinux_path__fprintf(stderr); + } else + pr_err(".\n"); + exit(1); + } } syme = symbol__priv(al.sym); @@ -1101,16 +1134,21 @@ static void perf_session__mmap_read_counter(struct perf_session *self, md->prev = old; } -static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; -static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; +static struct pollfd *event_array; +static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; static void perf_session__mmap_read(struct perf_session *self) { - int i, counter; + int i, counter, thread_index; for (i = 0; i < nr_cpus; i++) { for (counter = 0; counter < nr_counters; counter++) - perf_session__mmap_read_counter(self, &mmap_array[i][counter]); + for (thread_index = 0; + thread_index < thread_num; + thread_index++) { + perf_session__mmap_read_counter(self, + &mmap_array[i][counter][thread_index]); + } } } @@ -1121,9 +1159,10 @@ static void start_counter(int i, int counter) { struct perf_event_attr *attr; int cpu; + int thread_index; cpu = profile_cpu; - if (target_pid == -1 && profile_cpu == -1) + if (target_tid == -1 && profile_cpu == -1) cpu = cpumap[i]; attr = attrs + counter; @@ -1139,55 +1178,58 @@ static void start_counter(int i, int counter) attr->inherit = (cpu < 0) && inherit; attr->mmap = 1; + for (thread_index = 0; thread_index < thread_num; thread_index++) { try_again: - fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0); - - if (fd[i][counter] < 0) { - int err = errno; + fd[i][counter][thread_index] = sys_perf_event_open(attr, + all_tids[thread_index], cpu, group_fd, 0); + + if (fd[i][counter][thread_index] < 0) { + int err = errno; + + if (err == EPERM || err == EACCES) + die("No permission - are you root?\n"); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[i][counter][thread_index], strerror(err)); + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + exit(-1); + } + assert(fd[i][counter][thread_index] >= 0); + fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK); - if (err == EPERM || err == EACCES) - die("No permission - are you root?\n"); /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: + * First counter acts as the group leader: */ - if (attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - - if (verbose) - warning(" ... trying to fall back to cpu-clock-ticks\n"); - - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - goto try_again; - } - printf("\n"); - error("perfcounter syscall returned with %d (%s)\n", - fd[i][counter], strerror(err)); - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - exit(-1); + if (group && group_fd == -1) + group_fd = fd[i][counter][thread_index]; + + event_array[nr_poll].fd = fd[i][counter][thread_index]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[i][counter][thread_index].counter = counter; + mmap_array[i][counter][thread_index].prev = 0; + mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1; + mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0); + if (mmap_array[i][counter][thread_index].base == MAP_FAILED) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } - assert(fd[i][counter] >= 0); - fcntl(fd[i][counter], F_SETFL, O_NONBLOCK); - - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = fd[i][counter]; - - event_array[nr_poll].fd = fd[i][counter]; - event_array[nr_poll].events = POLLIN; - nr_poll++; - - mmap_array[i][counter].counter = counter; - mmap_array[i][counter].prev = 0; - mmap_array[i][counter].mask = mmap_pages*page_size - 1; - mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ, MAP_SHARED, fd[i][counter], 0); - if (mmap_array[i][counter].base == MAP_FAILED) - die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } static int __cmd_top(void) @@ -1203,8 +1245,8 @@ static int __cmd_top(void) if (session == NULL) return -ENOMEM; - if (target_pid != -1) - event__synthesize_thread(target_pid, event__process, session); + if (target_tid != -1) + event__synthesize_thread(target_tid, event__process, session); else event__synthesize_threads(event__process, session); @@ -1215,7 +1257,7 @@ static int __cmd_top(void) } /* Wait for a minimal set of events before starting the snapshot */ - poll(event_array, nr_poll, 100); + poll(&event_array[0], nr_poll, 100); perf_session__mmap_read(session); @@ -1258,7 +1300,9 @@ static const struct option options[] = { OPT_INTEGER('c', "count", &default_interval, "event period to sample"), OPT_INTEGER('p', "pid", &target_pid, - "profile events on existing pid"), + "profile events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "profile events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_INTEGER('C', "CPU", &profile_cpu, @@ -1299,6 +1343,7 @@ static const struct option options[] = { int cmd_top(int argc, const char **argv, const char *prefix __used) { int counter; + int i,j; page_size = sysconf(_SC_PAGE_SIZE); @@ -1306,8 +1351,39 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) if (argc) usage_with_options(top_usage, options); + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(top_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + mmap_array[i][j] = malloc( + sizeof(struct mmap_data)*thread_num); + if (!fd[i][j] || !mmap_array[i][j]) + return -ENOMEM; + } + } + event_array = malloc( + sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num); + if (!event_array) + return -ENOMEM; + /* CPU and PID are mutually exclusive */ - if (target_pid != -1 && profile_cpu != -1) { + if (target_tid > 0 && profile_cpu != -1) { printf("WARNING: PID switch overriding CPU\n"); sleep(1); profile_cpu = -1; @@ -1348,7 +1424,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) attrs[counter].sample_period = default_interval; } - if (target_pid != -1 || profile_cpu != -1) + if (target_tid != -1 || profile_cpu != -1) nr_cpus = 1; else nr_cpus = read_cpu_map(); diff --git a/tools/perf/perf.c b/tools/perf/perf.c index cd32c200cdb3..d2de8393a33c 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -16,6 +16,8 @@ #include "util/string.h" #include "util/debugfs.h" +bool use_browser; + const char perf_usage_string[] = "perf [--version] [--help] COMMAND [ARGS]"; @@ -265,6 +267,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) if (status) return status & 0xff; + exit_browser(); + /* Somebody closed stdout? */ if (fstat(fileno(stdout), &st)) return 0; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 6fb379bc1d1f..aa786158b668 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,6 +1,10 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H +struct winsize; + +void get_term_dimensions(struct winsize *ws); + #if defined(__i386__) #include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 918eb376abe3..47b12a3d11bf 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -1,6 +1,7 @@ #ifndef __PERF_CACHE_H #define __PERF_CACHE_H +#include <stdbool.h> #include "util.h" #include "strbuf.h" #include "../perf.h" @@ -69,6 +70,19 @@ extern const char *pager_program; extern int pager_in_use(void); extern int pager_use_color; +extern bool use_browser; + +#ifdef NO_NEWT_SUPPORT +static inline void setup_browser(void) +{ + setup_pager(); +} +static inline void exit_browser(void) {} +#else +void setup_browser(void); +void exit_browser(void); +#endif + extern const char *editor_program; extern const char *excludes_file; diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e88bca55a599..9da01914e0af 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -203,7 +203,10 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) int r; va_start(args, fmt); - r = color_vfprintf(fp, color, fmt, args); + if (use_browser) + r = vfprintf(fp, fmt, args); + else + r = color_vfprintf(fp, color, fmt, args); va_end(args); return r; } diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 0905600c3851..033d66db863a 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -6,6 +6,7 @@ #include <stdarg.h> #include <stdio.h> +#include "cache.h" #include "color.h" #include "event.h" #include "debug.h" @@ -21,7 +22,10 @@ int eprintf(int level, const char *fmt, ...) if (verbose >= level) { va_start(args, fmt); - ret = vfprintf(stderr, fmt, args); + if (use_browser) + ret = browser__show_help(fmt, args); + else + ret = vfprintf(stderr, fmt, args); va_end(args); } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index c6c24c522dea..0172edf3f153 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -7,9 +7,16 @@ extern int verbose; extern int dump_trace; -int eprintf(int level, - const char *fmt, ...) __attribute__((format(printf, 2, 3))); int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(event_t *event); +#ifdef NO_NEWT_SUPPORT +static inline int browser__show_help(const char *format __used, va_list ap __used) +{ + return 0; +} +#else +int browser__show_help(const char *format, va_list ap); +#endif + #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2be33c7dbf03..c37da8b88573 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -455,11 +455,11 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, return ret; } -static size_t hist_entry__fprintf(struct hist_entry *self, - struct perf_session *pair_session, - bool show_displacement, - long displacement, FILE *fp, - u64 session_total) +size_t hist_entry__fprintf(struct hist_entry *self, + struct perf_session *pair_session, + bool show_displacement, + long displacement, FILE *fp, + u64 session_total) { struct sort_entry *se; u64 count, total; @@ -485,9 +485,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self, if (symbol_conf.show_nr_samples) { if (sep) - fprintf(fp, "%c%lld", *sep, count); + ret += fprintf(fp, "%c%lld", *sep, count); else - fprintf(fp, "%11lld", count); + ret += fprintf(fp, "%11lld", count); } if (pair_session) { @@ -518,9 +518,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self, snprintf(bf, sizeof(bf), " "); if (sep) - fprintf(fp, "%c%s", *sep, bf); + ret += fprintf(fp, "%c%s", *sep, bf); else - fprintf(fp, "%6.6s", bf); + ret += fprintf(fp, "%6.6s", bf); } } @@ -528,27 +528,27 @@ static size_t hist_entry__fprintf(struct hist_entry *self, if (se->elide) continue; - fprintf(fp, "%s", sep ?: " "); + ret += fprintf(fp, "%s", sep ?: " "); ret += se->print(fp, self, se->width ? *se->width : 0); } - ret += fprintf(fp, "\n"); - - if (symbol_conf.use_callchain) { - int left_margin = 0; + return ret + fprintf(fp, "\n"); +} - if (sort__first_dimension == SORT_COMM) { - se = list_first_entry(&hist_entry__sort_list, typeof(*se), - list); - left_margin = se->width ? *se->width : 0; - left_margin -= thread__comm_len(self->thread); - } +static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp, + u64 session_total) +{ + int left_margin = 0; - hist_entry_callchain__fprintf(fp, self, session_total, - left_margin); + if (sort__first_dimension == SORT_COMM) { + struct sort_entry *se = list_first_entry(&hist_entry__sort_list, + typeof(*se), list); + left_margin = se->width ? *se->width : 0; + left_margin -= thread__comm_len(self->thread); } - return ret; + return hist_entry_callchain__fprintf(fp, self, session_total, + left_margin); } size_t perf_session__fprintf_hists(struct rb_root *hists, @@ -655,6 +655,10 @@ print_entries: } ret += hist_entry__fprintf(h, pair, show_displacement, displacement, fp, session_total); + + if (symbol_conf.use_callchain) + ret += hist_entry__fprintf_callchain(h, fp, session_total); + if (h->map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, MAP__FUNCTION, fp); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 16f360cce5bf..fe366ce5db45 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -18,6 +18,11 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, u64 count, bool *hit); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); +size_t hist_entry__fprintf(struct hist_entry *self, + struct perf_session *pair_session, + bool show_displacement, + long displacement, FILE *fp, + u64 session_total); void hist_entry__free(struct hist_entry *); void perf_session__output_resort(struct rb_root *hists, u64 total_samples); diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index f2611655ab51..388ab1bfd114 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -85,16 +85,19 @@ simple_strtoul(const char *nptr, char **endptr, int base) return strtoul(nptr, endptr, base); } +int eprintf(int level, + const char *fmt, ...) __attribute__((format(printf, 2, 3))); + #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif #define pr_err(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug(fmt, ...) \ eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debugN(n, fmt, ...) \ diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c new file mode 100644 index 000000000000..2d19e7a3e6e8 --- /dev/null +++ b/tools/perf/util/newt.c @@ -0,0 +1,207 @@ +#define _GNU_SOURCE +#include <stdio.h> +#undef _GNU_SOURCE + +#include <stdlib.h> +#include <newt.h> +#include <sys/ttydefaults.h> + +#include "cache.h" +#include "hist.h" +#include "session.h" +#include "sort.h" +#include "symbol.h" + +static void newt_form__set_exit_keys(newtComponent self) +{ + newtFormAddHotKey(self, NEWT_KEY_ESCAPE); + newtFormAddHotKey(self, 'Q'); + newtFormAddHotKey(self, 'q'); + newtFormAddHotKey(self, CTRL('c')); +} + +static newtComponent newt_form__new(void) +{ + newtComponent self = newtForm(NULL, NULL, 0); + if (self) + newt_form__set_exit_keys(self); + return self; +} + +static size_t hist_entry__append_browser(struct hist_entry *self, + newtComponent listbox, u64 total) +{ + char bf[1024]; + size_t len; + FILE *fp; + + if (symbol_conf.exclude_other && !self->parent) + return 0; + + fp = fmemopen(bf, sizeof(bf), "w"); + if (fp == NULL) + return 0; + + len = hist_entry__fprintf(self, NULL, false, 0, fp, total); + + fclose(fp); + newtListboxAppendEntry(listbox, bf, self); + return len; +} + +static void hist_entry__annotate_browser(struct hist_entry *self) +{ + FILE *fp; + int cols, rows; + newtComponent form, listbox; + struct newtExitStruct es; + char *str; + size_t line_len, max_line_len = 0; + size_t max_usable_width; + char *line = NULL; + + if (self->sym == NULL) + return; + + if (asprintf(&str, "perf annotate %s 2>&1 | expand", self->sym->name) < 0) + return; + + fp = popen(str, "r"); + if (fp == NULL) + goto out_free_str; + + newtPushHelpLine("Press ESC to exit"); + newtGetScreenSize(&cols, &rows); + listbox = newtListbox(0, 0, rows - 5, NEWT_FLAG_SCROLL); + + while (!feof(fp)) { + if (getline(&line, &line_len, fp) < 0 || !line_len) + break; + while (line_len != 0 && isspace(line[line_len - 1])) + line[--line_len] = '\0'; + + if (line_len > max_line_len) + max_line_len = line_len; + newtListboxAppendEntry(listbox, line, NULL); + } + fclose(fp); + free(line); + + max_usable_width = cols - 22; + if (max_line_len > max_usable_width) + max_line_len = max_usable_width; + + newtListboxSetWidth(listbox, max_line_len); + + newtCenteredWindow(max_line_len + 2, rows - 5, self->sym->name); + form = newt_form__new(); + newtFormAddComponents(form, listbox, NULL); + + newtFormRun(form, &es); + newtFormDestroy(form); + newtPopWindow(); + newtPopHelpLine(); +out_free_str: + free(str); +} + +void perf_session__browse_hists(struct rb_root *hists, u64 session_total, + const char *helpline) +{ + struct sort_entry *se; + struct rb_node *nd; + unsigned int width; + char *col_width = symbol_conf.col_width_list_str; + int rows; + size_t max_len = 0; + char str[1024]; + newtComponent form, listbox; + struct newtExitStruct es; + + snprintf(str, sizeof(str), "Samples: %Ld", session_total); + newtDrawRootText(0, 0, str); + newtPushHelpLine(helpline); + + newtGetScreenSize(NULL, &rows); + + form = newt_form__new(); + + listbox = newtListbox(1, 1, rows - 2, (NEWT_FLAG_SCROLL | + NEWT_FLAG_BORDER | + NEWT_FLAG_RETURNEXIT)); + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + width = strlen(se->header); + if (se->width) { + if (symbol_conf.col_width_list_str) { + if (col_width) { + *se->width = atoi(col_width); + col_width = strchr(col_width, ','); + if (col_width) + ++col_width; + } + } + *se->width = max(*se->width, width); + } + } + + for (nd = rb_first(hists); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + size_t len = hist_entry__append_browser(h, listbox, session_total); + if (len > max_len) + max_len = len; + } + + newtListboxSetWidth(listbox, max_len); + newtFormAddComponents(form, listbox, NULL); + + while (1) { + struct hist_entry *selection; + + newtFormRun(form, &es); + if (es.reason == NEWT_EXIT_HOTKEY) + break; + selection = newtListboxGetCurrent(listbox); + hist_entry__annotate_browser(selection); + } + + newtFormDestroy(form); +} + +int browser__show_help(const char *format, va_list ap) +{ + int ret; + static int backlog; + static char msg[1024]; + + ret = vsnprintf(msg + backlog, sizeof(msg) - backlog, format, ap); + backlog += ret; + + if (msg[backlog - 1] == '\n') { + newtPopHelpLine(); + newtPushHelpLine(msg); + newtRefresh(); + backlog = 0; + } + + return ret; +} + +void setup_browser(void) +{ + if (!isatty(1)) + return; + + use_browser = true; + newtInit(); + newtCls(); + newtPushHelpLine(" "); +} + +void exit_browser(void) +{ + if (use_browser) + newtFinished(); +} diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 05d0c5c2030c..a2014459125a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -656,6 +656,10 @@ parse_raw_event(const char **strp, struct perf_event_attr *attr) return EVT_FAILED; n = hex2u64(str + 1, &config); if (n > 0) { + if (str[n+1] == 'p') { + attr->precise = 1; + n++; + } *strp = str + n + 1; attr->type = PERF_TYPE_RAW; attr->config = config; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 53181dbfe4a8..c6603f3bb430 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -33,19 +33,25 @@ #include <limits.h> #undef _GNU_SOURCE +#include "util.h" #include "event.h" #include "string.h" #include "strlist.h" #include "debug.h" #include "cache.h" #include "color.h" +#include "symbol.h" +#include "thread.h" #include "parse-events.h" /* For debugfs_path */ #include "probe-event.h" +#include "probe-finder.h" #define MAX_CMDLEN 256 #define MAX_PROBE_ARGS 128 #define PERFPROBE_GROUP "probe" +bool probe_event_dry_run; /* Dry run flag */ + #define semantic_error(msg ...) die("Semantic error :" msg) /* If there is no space to write, returns -E2BIG. */ @@ -64,6 +70,37 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) return ret; } +static struct map_groups kmap_groups; +static struct map *kmaps[MAP__NR_TYPES]; + +/* Initialize symbol maps for vmlinux */ +static void init_vmlinux(void) +{ + symbol_conf.sort_by_name = true; + if (symbol_conf.vmlinux_name == NULL) + symbol_conf.try_vmlinux_path = true; + else + pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); + if (symbol__init() < 0) + die("Failed to init symbol map."); + + map_groups__init(&kmap_groups); + if (map_groups__create_kernel_maps(&kmap_groups, kmaps) < 0) + die("Failed to create kernel maps."); +} + +#ifndef NO_DWARF_SUPPORT +static int open_vmlinux(void) +{ + if (map__load(kmaps[MAP__FUNCTION], NULL) < 0) { + pr_debug("Failed to load kernel map.\n"); + return -EINVAL; + } + pr_debug("Try to open %s\n", kmaps[MAP__FUNCTION]->dso->long_name); + return open(kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY); +} +#endif + void parse_line_range_desc(const char *arg, struct line_range *lr) { const char *ptr; @@ -90,9 +127,9 @@ void parse_line_range_desc(const char *arg, struct line_range *lr) if (*tmp != '\0') semantic_error("Tailing with invalid character '%d'.", *tmp); - tmp = strndup(arg, (ptr - arg)); + tmp = xstrndup(arg, (ptr - arg)); } else - tmp = strdup(arg); + tmp = xstrdup(arg); if (strchr(tmp, '.')) lr->file = tmp; @@ -113,8 +150,9 @@ static bool check_event_name(const char *name) } /* Parse probepoint definition. */ -static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) +static void parse_perf_probe_point(char *arg, struct perf_probe_event *pev) { + struct perf_probe_point *pp = &pev->point; char *ptr, *tmp; char c, nc = 0; /* @@ -135,7 +173,8 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) if (!check_event_name(arg)) semantic_error("%s is bad for event name -it must " "follow C symbol-naming rule.", arg); - pp->event = strdup(arg); + pev->event = xstrdup(arg); + pev->group = NULL; arg = tmp; } @@ -147,17 +186,16 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) /* Check arg is function or file and copy it */ if (strchr(arg, '.')) /* File */ - pp->file = strdup(arg); + pp->file = xstrdup(arg); else /* Function */ - pp->function = strdup(arg); - DIE_IF(pp->file == NULL && pp->function == NULL); + pp->function = xstrdup(arg); /* Parse other options */ while (ptr) { arg = ptr; c = nc; if (c == ';') { /* Lazy pattern must be the last part */ - pp->lazy_line = strdup(arg); + pp->lazy_line = xstrdup(arg); break; } ptr = strpbrk(arg, ";:+@%"); @@ -181,8 +219,7 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) case '@': /* File name */ if (pp->file) semantic_error("SRC@SRC is not allowed."); - pp->file = strdup(arg); - DIE_IF(pp->file == NULL); + pp->file = xstrdup(arg); break; case '%': /* Probe places */ if (strcmp(arg, "return") == 0) { @@ -220,59 +257,108 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) semantic_error("Offset/Line/Lazy pattern can't be used with " "return probe."); - pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n", + pr_debug("symbol:%s file:%s line:%d offset:%lu return:%d lazy:%s\n", pp->function, pp->file, pp->line, pp->offset, pp->retprobe, pp->lazy_line); } -/* Parse perf-probe event definition */ -void parse_perf_probe_event(const char *str, struct probe_point *pp, - bool *need_dwarf) +/* Parse perf-probe event argument */ +static void parse_perf_probe_arg(const char *str, struct perf_probe_arg *arg) +{ + const char *tmp; + struct perf_probe_arg_field **fieldp; + + pr_debug("parsing arg: %s into ", str); + + tmp = strpbrk(str, "-."); + if (!is_c_varname(str) || !tmp) { + /* A variable, register, symbol or special value */ + arg->name = xstrdup(str); + pr_debug("%s\n", arg->name); + return; + } + + /* Structure fields */ + arg->name = xstrndup(str, tmp - str); + pr_debug("%s, ", arg->name); + fieldp = &arg->field; + + do { + *fieldp = xzalloc(sizeof(struct perf_probe_arg_field)); + if (*tmp == '.') { + str = tmp + 1; + (*fieldp)->ref = false; + } else if (tmp[1] == '>') { + str = tmp + 2; + (*fieldp)->ref = true; + } else + semantic_error("Argument parse error: %s", str); + + tmp = strpbrk(str, "-."); + if (tmp) { + (*fieldp)->name = xstrndup(str, tmp - str); + pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref); + fieldp = &(*fieldp)->next; + } + } while (tmp); + (*fieldp)->name = xstrdup(str); + pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref); +} + +/* Parse perf-probe event command */ +void parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev) { char **argv; int argc, i; - *need_dwarf = false; - - argv = argv_split(str, &argc); + argv = argv_split(cmd, &argc); if (!argv) die("argv_split failed."); if (argc > MAX_PROBE_ARGS + 1) semantic_error("Too many arguments"); /* Parse probe point */ - parse_perf_probe_probepoint(argv[0], pp); - if (pp->file || pp->line) - *need_dwarf = true; + parse_perf_probe_point(argv[0], pev); /* Copy arguments and ensure return probe has no C argument */ - pp->nr_args = argc - 1; - pp->args = zalloc(sizeof(char *) * pp->nr_args); - for (i = 0; i < pp->nr_args; i++) { - pp->args[i] = strdup(argv[i + 1]); - if (!pp->args[i]) - die("Failed to copy argument."); - if (is_c_varname(pp->args[i])) { - if (pp->retprobe) - semantic_error("You can't specify local" - " variable for kretprobe"); - *need_dwarf = true; - } + pev->nargs = argc - 1; + pev->args = xzalloc(sizeof(struct perf_probe_arg) * pev->nargs); + for (i = 0; i < pev->nargs; i++) { + parse_perf_probe_arg(argv[i + 1], &pev->args[i]); + if (is_c_varname(pev->args[i].name) && pev->point.retprobe) + semantic_error("You can't specify local variable for" + " kretprobe"); } argv_free(argv); } +/* Return true if this perf_probe_event requires debuginfo */ +bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) +{ + int i; + + if (pev->point.file || pev->point.line || pev->point.lazy_line) + return true; + + for (i = 0; i < pev->nargs; i++) + if (is_c_varname(pev->args[i].name)) + return true; + + return false; +} + /* Parse kprobe_events event into struct probe_point */ -void parse_trace_kprobe_event(const char *str, struct probe_point *pp) +void parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev) { + struct kprobe_trace_point *tp = &tev->point; char pr; char *p; int ret, i, argc; char **argv; - pr_debug("Parsing kprobe_events: %s\n", str); - argv = argv_split(str, &argc); + pr_debug("Parsing kprobe_events: %s\n", cmd); + argv = argv_split(cmd, &argc); if (!argv) die("argv_split failed."); if (argc < 2) @@ -280,132 +366,332 @@ void parse_trace_kprobe_event(const char *str, struct probe_point *pp) /* Scan event and group name. */ ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]", - &pr, (float *)(void *)&pp->group, - (float *)(void *)&pp->event); + &pr, (float *)(void *)&tev->group, + (float *)(void *)&tev->event); if (ret != 3) semantic_error("Failed to parse event name: %s", argv[0]); - pr_debug("Group:%s Event:%s probe:%c\n", pp->group, pp->event, pr); + pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr); - pp->retprobe = (pr == 'r'); + tp->retprobe = (pr == 'r'); /* Scan function name and offset */ - ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function, - &pp->offset); + ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol, + &tp->offset); if (ret == 1) - pp->offset = 0; + tp->offset = 0; - /* kprobe_events doesn't have this information */ - pp->line = 0; - pp->file = NULL; - - pp->nr_args = argc - 2; - pp->args = zalloc(sizeof(char *) * pp->nr_args); - for (i = 0; i < pp->nr_args; i++) { + tev->nargs = argc - 2; + tev->args = xzalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + for (i = 0; i < tev->nargs; i++) { p = strchr(argv[i + 2], '='); if (p) /* We don't need which register is assigned. */ - *p = '\0'; - pp->args[i] = strdup(argv[i + 2]); - if (!pp->args[i]) - die("Failed to copy argument."); + *p++ = '\0'; + else + p = argv[i + 2]; + tev->args[i].name = xstrdup(argv[i + 2]); + /* TODO: parse regs and offset */ + tev->args[i].value = xstrdup(p); } argv_free(argv); } -/* Synthesize only probe point (not argument) */ -int synthesize_perf_probe_point(struct probe_point *pp) +/* Compose only probe arg */ +int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) { - char *buf; - char offs[64] = "", line[64] = ""; + struct perf_probe_arg_field *field = pa->field; int ret; + char *tmp = buf; - pp->probes[0] = buf = zalloc(MAX_CMDLEN); - pp->found = 1; - if (!buf) - die("Failed to allocate memory by zalloc."); + ret = e_snprintf(tmp, len, "%s", pa->name); + if (ret <= 0) + goto error; + tmp += ret; + len -= ret; + + while (field) { + ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".", + field->name); + if (ret <= 0) + goto error; + tmp += ret; + len -= ret; + field = field->next; + } + return tmp - buf; +error: + die("Failed to synthesize perf probe argument: %s", strerror(-ret)); +} + +/* Compose only probe point (not argument) */ +static char *synthesize_perf_probe_point(struct perf_probe_point *pp) +{ + char *buf, *tmp; + char offs[32] = "", line[32] = "", file[32] = ""; + int ret, len; + + buf = xzalloc(MAX_CMDLEN); if (pp->offset) { - ret = e_snprintf(offs, 64, "+%d", pp->offset); + ret = e_snprintf(offs, 32, "+%lu", pp->offset); if (ret <= 0) goto error; } if (pp->line) { - ret = e_snprintf(line, 64, ":%d", pp->line); + ret = e_snprintf(line, 32, ":%d", pp->line); + if (ret <= 0) + goto error; + } + if (pp->file) { + len = strlen(pp->file) - 32; + if (len < 0) + len = 0; + tmp = strchr(pp->file + len, '/'); + if (!tmp) + tmp = pp->file + len - 1; + ret = e_snprintf(file, 32, "@%s", tmp + 1); if (ret <= 0) goto error; } if (pp->function) - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function, - offs, pp->retprobe ? "%return" : "", line); + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function, + offs, pp->retprobe ? "%return" : "", line, + file); else - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", pp->file, line); - if (ret <= 0) { + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line); + if (ret <= 0) + goto error; + + return buf; error: - free(pp->probes[0]); - pp->probes[0] = NULL; - pp->found = 0; - } - return ret; + die("Failed to synthesize perf probe point: %s", strerror(-ret)); } -int synthesize_perf_probe_event(struct probe_point *pp) +#if 0 +char *synthesize_perf_probe_command(struct perf_probe_event *pev) { char *buf; int i, len, ret; - len = synthesize_perf_probe_point(pp); - if (len < 0) - return 0; + buf = synthesize_perf_probe_point(&pev->point); + if (!buf) + return NULL; - buf = pp->probes[0]; - for (i = 0; i < pp->nr_args; i++) { + len = strlen(buf); + for (i = 0; i < pev->nargs; i++) { ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", - pp->args[i]); - if (ret <= 0) - goto error; + pev->args[i].name); + if (ret <= 0) { + free(buf); + return NULL; + } len += ret; } - pp->found = 1; - return pp->found; -error: - free(pp->probes[0]); - pp->probes[0] = NULL; + return buf; +} +#endif + +static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref, + char **buf, size_t *buflen, + int depth) +{ + int ret; + if (ref->next) { + depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf, + buflen, depth + 1); + if (depth < 0) + goto out; + } + + ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset); + if (ret < 0) + depth = ret; + else { + *buf += ret; + *buflen -= ret; + } +out: + return depth; - return ret; } -int synthesize_trace_kprobe_event(struct probe_point *pp) +static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg, + char *buf, size_t buflen) { + int ret, depth = 0; + char *tmp = buf; + + /* Argument name or separator */ + if (arg->name) + ret = e_snprintf(buf, buflen, " %s=", arg->name); + else + ret = e_snprintf(buf, buflen, " "); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + + /* Dereferencing arguments */ + if (arg->ref) { + depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf, + &buflen, 1); + if (depth < 0) + return depth; + } + + /* Print argument value */ + ret = e_snprintf(buf, buflen, "%s", arg->value); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + + /* Closing */ + while (depth--) { + ret = e_snprintf(buf, buflen, ")"); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + } + + return buf - tmp; +} + +char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev) +{ + struct kprobe_trace_point *tp = &tev->point; char *buf; int i, len, ret; - pp->probes[0] = buf = zalloc(MAX_CMDLEN); - if (!buf) - die("Failed to allocate memory by zalloc."); - ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset); - if (ret <= 0) + buf = xzalloc(MAX_CMDLEN); + len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu", + tp->retprobe ? 'r' : 'p', + tev->group, tev->event, + tp->symbol, tp->offset); + if (len <= 0) goto error; - len = ret; - for (i = 0; i < pp->nr_args; i++) { - ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", - pp->args[i]); + for (i = 0; i < tev->nargs; i++) { + ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len, + MAX_CMDLEN - len); if (ret <= 0) goto error; len += ret; } - pp->found = 1; - return pp->found; + return buf; error: - free(pp->probes[0]); - pp->probes[0] = NULL; + free(buf); + return NULL; +} - return ret; +void convert_to_perf_probe_event(struct kprobe_trace_event *tev, + struct perf_probe_event *pev) +{ + char buf[64]; + int i; +#ifndef NO_DWARF_SUPPORT + struct symbol *sym; + int fd, ret = 0; + + sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION], + tev->point.symbol, NULL); + if (sym) { + fd = open_vmlinux(); + ret = find_perf_probe_point(fd, sym->start + tev->point.offset, + &pev->point); + close(fd); + } + if (ret <= 0) { + pev->point.function = xstrdup(tev->point.symbol); + pev->point.offset = tev->point.offset; + } +#else + /* Convert trace_point to probe_point */ + pev->point.function = xstrdup(tev->point.symbol); + pev->point.offset = tev->point.offset; +#endif + pev->point.retprobe = tev->point.retprobe; + + pev->event = xstrdup(tev->event); + pev->group = xstrdup(tev->group); + + /* Convert trace_arg to probe_arg */ + pev->nargs = tev->nargs; + pev->args = xzalloc(sizeof(struct perf_probe_arg) * pev->nargs); + for (i = 0; i < tev->nargs; i++) + if (tev->args[i].name) + pev->args[i].name = xstrdup(tev->args[i].name); + else { + synthesize_kprobe_trace_arg(&tev->args[i], buf, 64); + pev->args[i].name = xstrdup(buf); + } +} + +void clear_perf_probe_event(struct perf_probe_event *pev) +{ + struct perf_probe_point *pp = &pev->point; + struct perf_probe_arg_field *field, *next; + int i; + + if (pev->event) + free(pev->event); + if (pev->group) + free(pev->group); + if (pp->file) + free(pp->file); + if (pp->function) + free(pp->function); + if (pp->lazy_line) + free(pp->lazy_line); + for (i = 0; i < pev->nargs; i++) { + if (pev->args[i].name) + free(pev->args[i].name); + field = pev->args[i].field; + while (field) { + next = field->next; + if (field->name) + free(field->name); + free(field); + field = next; + } + } + if (pev->args) + free(pev->args); + memset(pev, 0, sizeof(*pev)); } -static int open_kprobe_events(int flags, int mode) +void clear_kprobe_trace_event(struct kprobe_trace_event *tev) +{ + struct kprobe_trace_arg_ref *ref, *next; + int i; + + if (tev->event) + free(tev->event); + if (tev->group) + free(tev->group); + if (tev->point.symbol) + free(tev->point.symbol); + for (i = 0; i < tev->nargs; i++) { + if (tev->args[i].name) + free(tev->args[i].name); + if (tev->args[i].value) + free(tev->args[i].value); + ref = tev->args[i].ref; + while (ref) { + next = ref->next; + free(ref); + ref = next; + } + } + if (tev->args) + free(tev->args); + memset(tev, 0, sizeof(*tev)); +} + +static int open_kprobe_events(bool readwrite) { char buf[PATH_MAX]; int ret; @@ -414,7 +700,11 @@ static int open_kprobe_events(int flags, int mode) if (ret < 0) die("Failed to make kprobe_events path."); - ret = open(buf, flags, mode); + if (readwrite && !probe_event_dry_run) + ret = open(buf, O_RDWR, O_APPEND); + else + ret = open(buf, O_RDONLY, 0); + if (ret < 0) { if (errno == ENOENT) die("kprobe_events file does not exist -" @@ -427,7 +717,7 @@ static int open_kprobe_events(int flags, int mode) } /* Get raw string list of current kprobe_events */ -static struct strlist *get_trace_kprobe_event_rawlist(int fd) +static struct strlist *get_kprobe_trace_command_rawlist(int fd) { int ret, idx; FILE *fp; @@ -455,99 +745,85 @@ static struct strlist *get_trace_kprobe_event_rawlist(int fd) return sl; } -/* Free and zero clear probe_point */ -static void clear_probe_point(struct probe_point *pp) -{ - int i; - - if (pp->event) - free(pp->event); - if (pp->group) - free(pp->group); - if (pp->function) - free(pp->function); - if (pp->file) - free(pp->file); - if (pp->lazy_line) - free(pp->lazy_line); - for (i = 0; i < pp->nr_args; i++) - free(pp->args[i]); - if (pp->args) - free(pp->args); - for (i = 0; i < pp->found; i++) - free(pp->probes[i]); - memset(pp, 0, sizeof(*pp)); -} - /* Show an event */ -static void show_perf_probe_event(const char *event, const char *place, - struct probe_point *pp) +static void show_perf_probe_event(struct perf_probe_event *pev) { int i, ret; char buf[128]; + char *place; + + /* Synthesize only event probe point */ + place = synthesize_perf_probe_point(&pev->point); - ret = e_snprintf(buf, 128, "%s:%s", pp->group, event); + ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event); if (ret < 0) die("Failed to copy event: %s", strerror(-ret)); - printf(" %-40s (on %s", buf, place); + printf(" %-20s (on %s", buf, place); - if (pp->nr_args > 0) { + if (pev->nargs > 0) { printf(" with"); - for (i = 0; i < pp->nr_args; i++) - printf(" %s", pp->args[i]); + for (i = 0; i < pev->nargs; i++) { + synthesize_perf_probe_arg(&pev->args[i], buf, 128); + printf(" %s", buf); + } } printf(")\n"); + free(place); } /* List up current perf-probe events */ void show_perf_probe_events(void) { int fd; - struct probe_point pp; + struct kprobe_trace_event tev; + struct perf_probe_event pev; struct strlist *rawlist; struct str_node *ent; setup_pager(); - memset(&pp, 0, sizeof(pp)); + init_vmlinux(); + + memset(&tev, 0, sizeof(tev)); + memset(&pev, 0, sizeof(pev)); - fd = open_kprobe_events(O_RDONLY, 0); - rawlist = get_trace_kprobe_event_rawlist(fd); + fd = open_kprobe_events(false); + rawlist = get_kprobe_trace_command_rawlist(fd); close(fd); strlist__for_each(ent, rawlist) { - parse_trace_kprobe_event(ent->s, &pp); - /* Synthesize only event probe point */ - synthesize_perf_probe_point(&pp); + parse_kprobe_trace_command(ent->s, &tev); + convert_to_perf_probe_event(&tev, &pev); /* Show an event */ - show_perf_probe_event(pp.event, pp.probes[0], &pp); - clear_probe_point(&pp); + show_perf_probe_event(&pev); + clear_perf_probe_event(&pev); + clear_kprobe_trace_event(&tev); } strlist__delete(rawlist); } /* Get current perf-probe event names */ -static struct strlist *get_perf_event_names(int fd, bool include_group) +static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group) { char buf[128]; struct strlist *sl, *rawlist; struct str_node *ent; - struct probe_point pp; + struct kprobe_trace_event tev; - memset(&pp, 0, sizeof(pp)); - rawlist = get_trace_kprobe_event_rawlist(fd); + memset(&tev, 0, sizeof(tev)); + rawlist = get_kprobe_trace_command_rawlist(fd); sl = strlist__new(true, NULL); strlist__for_each(ent, rawlist) { - parse_trace_kprobe_event(ent->s, &pp); + parse_kprobe_trace_command(ent->s, &tev); if (include_group) { - if (e_snprintf(buf, 128, "%s:%s", pp.group, - pp.event) < 0) + if (e_snprintf(buf, 128, "%s:%s", tev.group, + tev.event) < 0) die("Failed to copy group:event name."); strlist__add(sl, buf); } else - strlist__add(sl, pp.event); - clear_probe_point(&pp); + strlist__add(sl, tev.event); + clear_kprobe_trace_event(&tev); } strlist__delete(rawlist); @@ -555,14 +831,18 @@ static struct strlist *get_perf_event_names(int fd, bool include_group) return sl; } -static void write_trace_kprobe_event(int fd, const char *buf) +static void write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev) { int ret; + char *buf = synthesize_kprobe_trace_command(tev); pr_debug("Writing event: %s\n", buf); - ret = write(fd, buf, strlen(buf)); - if (ret <= 0) - die("Failed to write event: %s", strerror(errno)); + if (!probe_event_dry_run) { + ret = write(fd, buf, strlen(buf)); + if (ret <= 0) + die("Failed to write event: %s", strerror(errno)); + } + free(buf); } static void get_new_event_name(char *buf, size_t len, const char *base, @@ -595,65 +875,187 @@ static void get_new_event_name(char *buf, size_t len, const char *base, die("Too many events are on the same function."); } -void add_trace_kprobe_events(struct probe_point *probes, int nr_probes, - bool force_add) +static void __add_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event *tevs, + int ntevs, bool allow_suffix) { - int i, j, fd; - struct probe_point *pp; - char buf[MAX_CMDLEN]; - char event[64]; + int i, fd; + struct kprobe_trace_event *tev = NULL; + char buf[64]; + const char *event, *group; struct strlist *namelist; - bool allow_suffix; - fd = open_kprobe_events(O_RDWR, O_APPEND); + fd = open_kprobe_events(true); /* Get current event names */ - namelist = get_perf_event_names(fd, false); - - for (j = 0; j < nr_probes; j++) { - pp = probes + j; - if (!pp->event) - pp->event = strdup(pp->function); - if (!pp->group) - pp->group = strdup(PERFPROBE_GROUP); - DIE_IF(!pp->event || !pp->group); - /* If force_add is true, suffix search is allowed */ - allow_suffix = force_add; - for (i = 0; i < pp->found; i++) { - /* Get an unused new event name */ - get_new_event_name(event, 64, pp->event, namelist, - allow_suffix); - snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n", - pp->retprobe ? 'r' : 'p', - pp->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(event, buf, pp); - /* Add added event name to namelist */ - strlist__add(namelist, event); - /* - * Probes after the first probe which comes from same - * user input are always allowed to add suffix, because - * there might be several addresses corresponding to - * one code line. - */ - allow_suffix = true; - } + namelist = get_kprobe_trace_event_names(fd, false); + + printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":"); + for (i = 0; i < ntevs; i++) { + tev = &tevs[i]; + if (pev->event) + event = pev->event; + else + if (pev->point.function) + event = pev->point.function; + else + event = tev->point.symbol; + if (pev->group) + group = pev->group; + else + group = PERFPROBE_GROUP; + + /* Get an unused new event name */ + get_new_event_name(buf, 64, event, namelist, allow_suffix); + event = buf; + + tev->event = xstrdup(event); + tev->group = xstrdup(group); + write_kprobe_trace_event(fd, tev); + /* Add added event name to namelist */ + strlist__add(namelist, event); + + /* Trick here - save current event/group */ + event = pev->event; + group = pev->group; + pev->event = tev->event; + pev->group = tev->group; + show_perf_probe_event(pev); + /* Trick here - restore current event/group */ + pev->event = (char *)event; + pev->group = (char *)group; + + /* + * Probes after the first probe which comes from same + * user input are always allowed to add suffix, because + * there might be several addresses corresponding to + * one code line. + */ + allow_suffix = true; } /* 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); + printf("\tperf record -e %s:%s -a sleep 1\n\n", tev->group, tev->event); strlist__delete(namelist); close(fd); } +static int convert_to_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event **tevs) +{ + struct symbol *sym; + bool need_dwarf; +#ifndef NO_DWARF_SUPPORT + int fd; +#endif + int ntevs = 0, i; + struct kprobe_trace_event *tev; + + need_dwarf = perf_probe_event_need_dwarf(pev); + + if (need_dwarf) +#ifdef NO_DWARF_SUPPORT + die("Debuginfo-analysis is not supported"); +#else /* !NO_DWARF_SUPPORT */ + pr_debug("Some probes require debuginfo.\n"); + + fd = open_vmlinux(); + if (fd < 0) { + if (need_dwarf) + die("Could not open debuginfo file."); + + pr_debug("Could not open vmlinux/module file." + " Try to use symbols.\n"); + goto end_dwarf; + } + + /* Searching probe points */ + ntevs = find_kprobe_trace_events(fd, pev, tevs); + + if (ntevs > 0) /* Found */ + goto found; + + if (ntevs == 0) /* No error but failed to find probe point. */ + die("Probe point '%s' not found. - probe not added.", + synthesize_perf_probe_point(&pev->point)); + + /* Error path */ + if (need_dwarf) { + if (ntevs == -ENOENT) + pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO=y.\n"); + die("Could not analyze debuginfo."); + } + pr_debug("An error occurred in debuginfo analysis." + " Try to use symbols.\n"); + +end_dwarf: +#endif /* !NO_DWARF_SUPPORT */ + + /* Allocate trace event buffer */ + ntevs = 1; + tev = *tevs = xzalloc(sizeof(struct kprobe_trace_event)); + + /* Copy parameters */ + tev->point.symbol = xstrdup(pev->point.function); + tev->point.offset = pev->point.offset; + tev->nargs = pev->nargs; + if (tev->nargs) { + tev->args = xzalloc(sizeof(struct kprobe_trace_arg) + * tev->nargs); + for (i = 0; i < tev->nargs; i++) + tev->args[i].value = xstrdup(pev->args[i].name); + } + + /* Currently just checking function name from symbol map */ + sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION], + tev->point.symbol, NULL); + if (!sym) + die("Kernel symbol \'%s\' not found - probe not added.", + tev->point.symbol); +#ifndef NO_DWARF_SUPPORT +found: + close(fd); +#endif + return ntevs; +} + +struct __event_package { + struct perf_probe_event *pev; + struct kprobe_trace_event *tevs; + int ntevs; +}; + +void add_perf_probe_events(struct perf_probe_event *pevs, int npevs, + bool force_add) +{ + int i; + struct __event_package *pkgs; + + pkgs = xzalloc(sizeof(struct __event_package) * npevs); + + /* Init vmlinux path */ + init_vmlinux(); + + /* Loop 1: convert all events */ + for (i = 0; i < npevs; i++) { + pkgs[i].pev = &pevs[i]; + /* Convert with or without debuginfo */ + pkgs[i].ntevs = convert_to_kprobe_trace_events(pkgs[i].pev, + &pkgs[i].tevs); + } + + /* Loop 2: add all events */ + for (i = 0; i < npevs; i++) + __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs, + pkgs[i].ntevs, force_add); + /* TODO: cleanup all trace events? */ +} + static void __del_trace_kprobe_event(int fd, struct str_node *ent) { char *p; char buf[128]; + int ret; /* Convert from perf-probe event to trace-kprobe event */ if (e_snprintf(buf, 128, "-:%s", ent->s) < 0) @@ -663,7 +1065,10 @@ static void __del_trace_kprobe_event(int fd, struct str_node *ent) die("Internal error: %s should have ':' but not.", ent->s); *p = '/'; - write_trace_kprobe_event(fd, buf); + pr_debug("Writing event: %s\n", buf); + ret = write(fd, buf, strlen(buf)); + if (ret <= 0) + die("Failed to write event: %s", strerror(errno)); printf("Remove event: %s\n", ent->s); } @@ -696,7 +1101,7 @@ static void del_trace_kprobe_event(int fd, const char *group, pr_info("Info: event \"%s\" does not exist, could not remove it.\n", buf); } -void del_trace_kprobe_events(struct strlist *dellist) +void del_perf_probe_events(struct strlist *dellist) { int fd; const char *group, *event; @@ -704,14 +1109,12 @@ void del_trace_kprobe_events(struct strlist *dellist) struct str_node *ent; struct strlist *namelist; - fd = open_kprobe_events(O_RDWR, O_APPEND); + fd = open_kprobe_events(true); /* Get current event names */ - namelist = get_perf_event_names(fd, true); + namelist = get_kprobe_trace_event_names(fd, true); strlist__for_each(ent, dellist) { - str = strdup(ent->s); - if (!str) - die("Failed to copy event."); + str = xstrdup(ent->s); pr_debug("Parsing: %s\n", str); p = strchr(str, ':'); if (p) { @@ -771,6 +1174,21 @@ void show_line_range(struct line_range *lr) unsigned int l = 1; struct line_node *ln; FILE *fp; +#ifndef NO_DWARF_SUPPORT + int fd, ret; +#endif + + /* Search a line range */ + init_vmlinux(); +#ifndef NO_DWARF_SUPPORT + fd = open_vmlinux(); + if (fd < 0) + die("Could not open debuginfo file."); + ret = find_line_range(fd, lr); + if (ret <= 0) + die("Source line is not found.\n"); + close(fd); +#endif setup_pager(); @@ -800,3 +1218,5 @@ void show_line_range(struct line_range *lr) fclose(fp); } + + diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 711287d4baea..cd308b0a4d96 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -2,22 +2,123 @@ #define _PROBE_EVENT_H #include <stdbool.h> -#include "probe-finder.h" #include "strlist.h" -extern void parse_line_range_desc(const char *arg, struct line_range *lr); -extern void parse_perf_probe_event(const char *str, struct probe_point *pp, - bool *need_dwarf); -extern int synthesize_perf_probe_point(struct probe_point *pp); -extern int synthesize_perf_probe_event(struct probe_point *pp); -extern void parse_trace_kprobe_event(const char *str, 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, - bool force_add); -extern void del_trace_kprobe_events(struct strlist *dellist); +extern bool probe_event_dry_run; + +/* kprobe-tracer tracing point */ +struct kprobe_trace_point { + char *symbol; /* Base symbol */ + unsigned long offset; /* Offset from symbol */ + bool retprobe; /* Return probe flag */ +}; + +/* kprobe-tracer tracing argument referencing offset */ +struct kprobe_trace_arg_ref { + struct kprobe_trace_arg_ref *next; /* Next reference */ + long offset; /* Offset value */ +}; + +/* kprobe-tracer tracing argument */ +struct kprobe_trace_arg { + char *name; /* Argument name */ + char *value; /* Base value */ + struct kprobe_trace_arg_ref *ref; /* Referencing offset */ +}; + +/* kprobe-tracer tracing event (point + arg) */ +struct kprobe_trace_event { + char *event; /* Event name */ + char *group; /* Group name */ + struct kprobe_trace_point point; /* Trace point */ + int nargs; /* Number of args */ + struct kprobe_trace_arg *args; /* Arguments */ +}; + +/* Perf probe probing point */ +struct perf_probe_point { + char *file; /* File path */ + char *function; /* Function name */ + int line; /* Line number */ + char *lazy_line; /* Lazy matching pattern */ + unsigned long offset; /* Offset from function entry */ + bool retprobe; /* Return probe flag */ +}; + +/* Perf probe probing argument field chain */ +struct perf_probe_arg_field { + struct perf_probe_arg_field *next; /* Next field */ + char *name; /* Name of the field */ + bool ref; /* Referencing flag */ +}; + +/* Perf probe probing argument */ +struct perf_probe_arg { + char *name; /* Argument name */ + struct perf_probe_arg_field *field; /* Structure fields */ +}; + +/* Perf probe probing event (point + arg) */ +struct perf_probe_event { + char *event; /* Event name */ + char *group; /* Group name */ + struct perf_probe_point point; /* Probe point */ + int nargs; /* Number of arguments */ + struct perf_probe_arg *args; /* Arguments */ +}; + + +/* Line number container */ +struct line_node { + struct list_head list; + unsigned int line; +}; + +/* Line range */ +struct line_range { + char *file; /* File name */ + char *function; /* Function name */ + unsigned int start; /* Start line number */ + unsigned int end; /* End line number */ + int offset; /* Start line offset */ + char *path; /* Real path name */ + struct list_head line_list; /* Visible lines */ +}; + +/* Command string to events */ +extern void parse_perf_probe_command(const char *cmd, + struct perf_probe_event *pev); +extern void parse_kprobe_trace_command(const char *cmd, + struct kprobe_trace_event *tev); + +/* Events to command string */ +extern char *synthesize_perf_probe_command(struct perf_probe_event *pev); +extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev); +extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, + size_t len); + +/* Check the perf_probe_event needs debuginfo */ +extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); + +/* Convert from kprobe_trace_event to perf_probe_event */ +extern void convert_to_perf_probe_event(struct kprobe_trace_event *tev, + struct perf_probe_event *pev); + +/* Release event contents */ +extern void clear_perf_probe_event(struct perf_probe_event *pev); +extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev); + +/* Command string to line-range */ +extern void parse_line_range_desc(const char *cmd, struct line_range *lr); + + +extern void add_perf_probe_events(struct perf_probe_event *pevs, int ntevs, + bool force_add); +extern void del_perf_probe_events(struct strlist *dellist); extern void show_perf_probe_events(void); extern void show_line_range(struct line_range *lr); + /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1e6c65ebbd80..db52ec2e84de 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -125,8 +125,7 @@ static void line_list__add_line(struct list_head *head, unsigned int line) p = head; found: pr_debug("line list: add a line %u\n", line); - ln = zalloc(sizeof(struct line_node)); - DIE_IF(ln == NULL); + ln = xzalloc(sizeof(struct line_node)); ln->line = line; INIT_LIST_HEAD(&ln->list); list_add(&ln->list, p); @@ -187,6 +186,84 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname) return src; } +/* Compare diename and tname */ +static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) +{ + const char *name; + name = dwarf_diename(dw_die); + DIE_IF(name == NULL); + return strcmp(tname, name); +} + +/* Get entry pc(or low pc, 1st entry of ranges) of the die */ +static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die) +{ + Dwarf_Addr epc; + int ret; + + ret = dwarf_entrypc(dw_die, &epc); + DIE_IF(ret == -1); + return epc; +} + +/* Get type die, but skip qualifiers and typedef */ +static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) +{ + Dwarf_Attribute attr; + int tag; + + do { + if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL || + dwarf_formref_die(&attr, die_mem) == NULL) + return NULL; + + tag = dwarf_tag(die_mem); + vr_die = die_mem; + } while (tag == DW_TAG_const_type || + tag == DW_TAG_restrict_type || + tag == DW_TAG_volatile_type || + tag == DW_TAG_shared_type || + tag == DW_TAG_typedef); + + return die_mem; +} + +/* Return values for die_find callbacks */ +enum { + DIE_FIND_CB_FOUND = 0, /* End of Search */ + DIE_FIND_CB_CHILD = 1, /* Search only children */ + DIE_FIND_CB_SIBLING = 2, /* Search only siblings */ + DIE_FIND_CB_CONTINUE = 3, /* Search children and siblings */ +}; + +/* Search a child die */ +static Dwarf_Die *die_find_child(Dwarf_Die *rt_die, + int (*callback)(Dwarf_Die *, void *), + void *data, Dwarf_Die *die_mem) +{ + Dwarf_Die child_die; + int ret; + + ret = dwarf_child(rt_die, die_mem); + if (ret != 0) + return NULL; + + do { + ret = callback(die_mem, data); + if (ret == DIE_FIND_CB_FOUND) + return die_mem; + + if ((ret & DIE_FIND_CB_CHILD) && + die_find_child(die_mem, callback, data, &child_die)) { + memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); + return die_mem; + } + } while ((ret & DIE_FIND_CB_SIBLING) && + dwarf_siblingof(die_mem, die_mem) == 0); + + return NULL; +} + struct __addr_die_search_param { Dwarf_Addr addr; Dwarf_Die *die_mem; @@ -205,8 +282,8 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) } /* Search a real subprogram including this line, */ -static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, - Dwarf_Die *die_mem) +static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) { struct __addr_die_search_param ad; ad.addr = addr; @@ -218,77 +295,64 @@ static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, return die_mem; } -/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */ -static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, - Dwarf_Die *die_mem) +/* die_find callback for inline function search */ +static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) { - Dwarf_Die child_die; - int ret; + Dwarf_Addr *addr = data; - ret = dwarf_child(sp_die, die_mem); - if (ret != 0) - return NULL; + if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && + dwarf_haspc(die_mem, *addr)) + return DIE_FIND_CB_FOUND; - do { - if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && - dwarf_haspc(die_mem, addr)) - return die_mem; - - if (die_get_inlinefunc(die_mem, addr, &child_die)) { - memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); - return die_mem; - } - } while (dwarf_siblingof(die_mem, die_mem) == 0); - - return NULL; + return DIE_FIND_CB_CONTINUE; } -/* Compare diename and tname */ -static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) +/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */ +static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) { - const char *name; - name = dwarf_diename(dw_die); - DIE_IF(name == NULL); - return strcmp(tname, name); + return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); } -/* Get entry pc(or low pc, 1st entry of ranges) of the die */ -static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die) +static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) { - Dwarf_Addr epc; - int ret; + const char *name = data; + int tag; - ret = dwarf_entrypc(dw_die, &epc); - DIE_IF(ret == -1); - return epc; + tag = dwarf_tag(die_mem); + if ((tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) && + (die_compare_name(die_mem, name) == 0)) + return DIE_FIND_CB_FOUND; + + return DIE_FIND_CB_CONTINUE; } -/* Get a variable die */ +/* Find a variable called 'name' */ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name, Dwarf_Die *die_mem) { - Dwarf_Die child_die; - int tag; - int ret; + return die_find_child(sp_die, __die_find_variable_cb, (void *)name, + die_mem); +} - ret = dwarf_child(sp_die, die_mem); - if (ret != 0) - return NULL; +static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) +{ + const char *name = data; - do { - tag = dwarf_tag(die_mem); - if ((tag == DW_TAG_formal_parameter || - tag == DW_TAG_variable) && - (die_compare_name(die_mem, name) == 0)) - return die_mem; + if ((dwarf_tag(die_mem) == DW_TAG_member) && + (die_compare_name(die_mem, name) == 0)) + return DIE_FIND_CB_FOUND; - if (die_find_variable(die_mem, name, &child_die)) { - memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); - return die_mem; - } - } while (dwarf_siblingof(die_mem, die_mem) == 0); + return DIE_FIND_CB_SIBLING; +} - return NULL; +/* Find a member called 'name' */ +static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, + Dwarf_Die *die_mem) +{ + return die_find_child(st_die, __die_find_member_cb, (void *)name, + die_mem); } /* @@ -296,19 +360,20 @@ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name, */ /* Show a location */ -static void show_location(Dwarf_Op *op, struct probe_finder *pf) +static void convert_location(Dwarf_Op *op, struct probe_finder *pf) { unsigned int regn; Dwarf_Word offs = 0; - int deref = 0, ret; + bool ref = false; const char *regs; + struct kprobe_trace_arg *tvar = pf->tvar; /* TODO: support CFA */ /* If this is based on frame buffer, set the offset */ if (op->atom == DW_OP_fbreg) { if (pf->fb_ops == NULL) die("The attribute of frame base is not supported.\n"); - deref = 1; + ref = true; offs = op->number; op = &pf->fb_ops[0]; } @@ -316,13 +381,13 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf) if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) { regn = op->atom - DW_OP_breg0; offs += op->number; - deref = 1; + ref = true; } else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) { regn = op->atom - DW_OP_reg0; } else if (op->atom == DW_OP_bregx) { regn = op->number; offs += op->number2; - deref = 1; + ref = true; } else if (op->atom == DW_OP_regx) { regn = op->number; } else @@ -332,17 +397,71 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf) if (!regs) die("%u exceeds max register number.", regn); - if (deref) - ret = snprintf(pf->buf, pf->len, " %s=+%ju(%s)", - pf->var, (uintmax_t)offs, regs); - else - ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs); - DIE_IF(ret < 0); - DIE_IF(ret >= pf->len); + tvar->value = xstrdup(regs); + if (ref) { + tvar->ref = xzalloc(sizeof(struct kprobe_trace_arg_ref)); + tvar->ref->offset = (long)offs; + } +} + +static void convert_variable_fields(Dwarf_Die *vr_die, const char *varname, + struct perf_probe_arg_field *field, + struct kprobe_trace_arg_ref **ref_ptr) +{ + struct kprobe_trace_arg_ref *ref = *ref_ptr; + Dwarf_Attribute attr; + Dwarf_Die member; + Dwarf_Die type; + Dwarf_Word offs; + + pr_debug("converting %s in %s\n", field->name, varname); + if (die_get_real_type(vr_die, &type) == NULL) + die("Failed to get a type information of %s.", varname); + + /* Check the pointer and dereference */ + if (dwarf_tag(&type) == DW_TAG_pointer_type) { + if (!field->ref) + die("Semantic error: %s must be referred by '->'", + field->name); + /* Get the type pointed by this pointer */ + if (die_get_real_type(&type, &type) == NULL) + die("Failed to get a type information of %s.", varname); + + ref = xzalloc(sizeof(struct kprobe_trace_arg_ref)); + if (*ref_ptr) + (*ref_ptr)->next = ref; + else + *ref_ptr = ref; + } else { + if (field->ref) + die("Semantic error: %s must be referred by '.'", + field->name); + if (!ref) + die("Structure on a register is not supported yet."); + } + + /* Verify it is a data structure */ + if (dwarf_tag(&type) != DW_TAG_structure_type) + die("%s is not a data structure.", varname); + + if (die_find_member(&type, field->name, &member) == NULL) + die("%s(tyep:%s) has no member %s.", varname, + dwarf_diename(&type), field->name); + + /* Get the offset of the field */ + if (dwarf_attr(&member, DW_AT_data_member_location, &attr) == NULL || + dwarf_formudata(&attr, &offs) != 0) + die("Failed to get the offset of %s.", field->name); + ref->offset += (long)offs; + + /* Converting next field */ + if (field->next) + convert_variable_fields(&member, field->name, field->next, + &ref); } /* Show a variables in kprobe event format */ -static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf) +static void convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) { Dwarf_Attribute attr; Dwarf_Op *expr; @@ -352,111 +471,100 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf) if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) goto error; /* TODO: handle more than 1 exprs */ - ret = dwarf_getlocation_addr(&attr, (pf->addr - pf->cu_base), - &expr, &nexpr, 1); + ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1); if (ret <= 0 || nexpr == 0) goto error; - show_location(expr, pf); + convert_location(expr, pf); + + if (pf->pvar->field) + convert_variable_fields(vr_die, pf->pvar->name, + pf->pvar->field, &pf->tvar->ref); /* *expr will be cached in libdw. Don't free it. */ return ; error: /* TODO: Support const_value */ die("Failed to find the location of %s at this address.\n" - " Perhaps, it has been optimized out.", pf->var); + " Perhaps, it has been optimized out.", pf->pvar->name); } /* Find a variable in a subprogram die */ static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) { - int ret; Dwarf_Die vr_die; + char buf[128]; /* TODO: Support struct members and arrays */ - if (!is_c_varname(pf->var)) { - /* Output raw parameters */ - ret = snprintf(pf->buf, pf->len, " %s", pf->var); - DIE_IF(ret < 0); - DIE_IF(ret >= pf->len); - return ; + if (!is_c_varname(pf->pvar->name)) { + /* Copy raw parameters */ + pf->tvar->value = xstrdup(pf->pvar->name); + } else { + synthesize_perf_probe_arg(pf->pvar, buf, 128); + pf->tvar->name = xstrdup(buf); + pr_debug("Searching '%s' variable in context.\n", + pf->pvar->name); + /* Search child die for local variables and parameters. */ + if (!die_find_variable(sp_die, pf->pvar->name, &vr_die)) + die("Failed to find '%s' in this function.", + pf->pvar->name); + convert_variable(&vr_die, pf); } - - pr_debug("Searching '%s' variable in context.\n", pf->var); - /* Search child die for local variables and parameters. */ - if (!die_find_variable(sp_die, pf->var, &vr_die)) - die("Failed to find '%s' in this function.", pf->var); - - show_variable(&vr_die, pf); } /* Show a probe point to output buffer */ -static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) +static void convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) { - struct probe_point *pp = pf->pp; + struct kprobe_trace_event *tev; Dwarf_Addr eaddr; Dwarf_Die die_mem; const char *name; - char tmp[MAX_PROBE_BUFFER]; - int ret, i, len; + int ret, i; Dwarf_Attribute fb_attr; size_t nops; + if (pf->ntevs == MAX_PROBES) + die("Too many( > %d) probe point found.\n", MAX_PROBES); + tev = &pf->tevs[pf->ntevs++]; + /* If no real subprogram, find a real one */ if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) { - sp_die = die_get_real_subprogram(&pf->cu_die, + sp_die = die_find_real_subprogram(&pf->cu_die, pf->addr, &die_mem); if (!sp_die) die("Probe point is not found in subprograms."); } - /* Output name of probe point */ + /* Copy the name of probe point */ name = dwarf_diename(sp_die); if (name) { dwarf_entrypc(sp_die, &eaddr); - ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name, - (unsigned long)(pf->addr - eaddr)); - /* Copy the function name if possible */ - if (!pp->function) { - pp->function = strdup(name); - pp->offset = (size_t)(pf->addr - eaddr); - } - } else { + tev->point.symbol = xstrdup(name); + tev->point.offset = (unsigned long)(pf->addr - eaddr); + } else /* This function has no name. */ - ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx", - (uintmax_t)pf->addr); - if (!pp->function) { - /* TODO: Use _stext */ - pp->function = strdup(""); - pp->offset = (size_t)pf->addr; - } - } - DIE_IF(ret < 0); - DIE_IF(ret >= MAX_PROBE_BUFFER); - len = ret; - pr_debug("Probe point found: %s\n", tmp); + tev->point.offset = (unsigned long)pf->addr; + + pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, + tev->point.offset); /* Get the frame base attribute/ops */ dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr); - ret = dwarf_getlocation_addr(&fb_attr, (pf->addr - pf->cu_base), - &pf->fb_ops, &nops, 1); + ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1); if (ret <= 0 || nops == 0) pf->fb_ops = NULL; /* Find each argument */ /* TODO: use dwarf_cfi_addrframe */ - for (i = 0; i < pp->nr_args; i++) { - pf->var = pp->args[i]; - pf->buf = &tmp[len]; - pf->len = MAX_PROBE_BUFFER - len; + tev->nargs = pf->pev->nargs; + tev->args = xzalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + for (i = 0; i < pf->pev->nargs; i++) { + pf->pvar = &pf->pev->args[i]; + pf->tvar = &tev->args[i]; find_variable(sp_die, pf); - len += strlen(pf->buf); } /* *pf->fb_ops will be cached in libdw. Don't free it. */ pf->fb_ops = NULL; - - pp->probes[pp->found] = strdup(tmp); - pp->found++; } /* Find probe point from its line number */ @@ -488,7 +596,7 @@ static void find_probe_point_by_line(struct probe_finder *pf) (int)i, lineno, (uintmax_t)addr); pf->addr = addr; - show_probe_point(NULL, pf); + convert_probe_point(NULL, pf); /* Continuing, because target line might be inlined. */ } } @@ -505,8 +613,7 @@ static int find_lazy_match_lines(struct list_head *head, if (fd < 0) die("failed to open %s", fname); DIE_IF(fstat(fd, &st) < 0); - fbuf = malloc(st.st_size + 2); - DIE_IF(fbuf == NULL); + fbuf = xmalloc(st.st_size + 2); DIE_IF(read(fd, fbuf, st.st_size) < 0); close(fd); fbuf[st.st_size] = '\n'; /* Dummy line */ @@ -540,7 +647,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) if (list_empty(&pf->lcache)) { /* Matching lazy line pattern */ ret = find_lazy_match_lines(&pf->lcache, pf->fname, - pf->pp->lazy_line); + pf->pev->point.lazy_line); if (ret <= 0) die("No matched lines found in %s.", pf->fname); } @@ -565,7 +672,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) if (!dwarf_haspc(sp_die, addr)) continue; /* Address filtering 2: No child include addr? */ - if (die_get_inlinefunc(sp_die, addr, &die_mem)) + if (die_find_inlinefunc(sp_die, addr, &die_mem)) continue; } @@ -573,7 +680,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) (int)i, lineno, (unsigned long long)addr); pf->addr = addr; - show_probe_point(sp_die, pf); + convert_probe_point(sp_die, pf); /* Continuing, because target line might be inlined. */ } /* TODO: deallocate lines, but how? */ @@ -582,7 +689,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) { struct probe_finder *pf = (struct probe_finder *)data; - struct probe_point *pp = pf->pp; + struct perf_probe_point *pp = &pf->pev->point; if (pp->lazy_line) find_probe_point_lazy(in_die, pf); @@ -593,7 +700,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) pr_debug("found inline addr: 0x%jx\n", (uintmax_t)pf->addr); - show_probe_point(in_die, pf); + convert_probe_point(in_die, pf); } return DWARF_CB_OK; @@ -603,7 +710,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) { struct probe_finder *pf = (struct probe_finder *)data; - struct probe_point *pp = pf->pp; + struct perf_probe_point *pp = &pf->pev->point; /* Check tag and diename */ if (dwarf_tag(sp_die) != DW_TAG_subprogram || @@ -623,7 +730,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) pf->addr = die_get_entrypc(sp_die); pf->addr += pp->offset; /* TODO: Check the address in this function */ - show_probe_point(sp_die, pf); + convert_probe_point(sp_die, pf); } } else /* Inlined function: search instances */ @@ -637,21 +744,25 @@ static void find_probe_point_by_func(struct probe_finder *pf) dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0); } -/* Find a probe point */ -int find_probe_point(int fd, struct probe_point *pp) +/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ +int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, + struct kprobe_trace_event **tevs) { - struct probe_finder pf = {.pp = pp}; - int ret; + struct probe_finder pf = {.pev = pev}; + struct perf_probe_point *pp = &pev->point; Dwarf_Off off, noff; size_t cuhl; Dwarf_Die *diep; Dwarf *dbg; + pf.tevs = xzalloc(sizeof(struct kprobe_trace_event) * MAX_PROBES); + *tevs = pf.tevs; + pf.ntevs = 0; + dbg = dwarf_begin(fd, DWARF_C_READ); if (!dbg) return -ENOENT; - pp->found = 0; off = 0; line_list__init(&pf.lcache); /* Loop on CUs (Compilation Unit) */ @@ -668,10 +779,6 @@ int find_probe_point(int fd, struct probe_point *pp) pf.fname = NULL; if (!pp->file || pf.fname) { - /* Save CU base address (for frame_base) */ - ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base); - if (ret != 0) - pf.cu_base = 0; if (pp->function) find_probe_point_by_func(&pf); else if (pp->lazy_line) @@ -686,9 +793,79 @@ int find_probe_point(int fd, struct probe_point *pp) line_list__free(&pf.lcache); dwarf_end(dbg); - return pp->found; + return pf.ntevs; } +/* Reverse search */ +int find_perf_probe_point(int fd, unsigned long addr, + struct perf_probe_point *ppt) +{ + Dwarf_Die cudie, spdie, indie; + Dwarf *dbg; + Dwarf_Line *line; + Dwarf_Addr laddr, eaddr; + const char *tmp; + int lineno, ret = 0; + + dbg = dwarf_begin(fd, DWARF_C_READ); + if (!dbg) + return -ENOENT; + + /* Find cu die */ + if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) + return -EINVAL; + + /* Find a corresponding line */ + line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr); + if (line) { + dwarf_lineaddr(line, &laddr); + if ((Dwarf_Addr)addr == laddr) { + dwarf_lineno(line, &lineno); + ppt->line = lineno; + + tmp = dwarf_linesrc(line, NULL, NULL); + DIE_IF(!tmp); + ppt->file = xstrdup(tmp); + ret = 1; + } + } + + /* Find a corresponding function */ + if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) { + tmp = dwarf_diename(&spdie); + if (!tmp) + goto end; + + dwarf_entrypc(&spdie, &eaddr); + if (!lineno) { + /* We don't have a line number, let's use offset */ + ppt->function = xstrdup(tmp); + ppt->offset = addr - (unsigned long)eaddr; + ret = 1; + goto end; + } + if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { + /* addr in an inline function */ + tmp = dwarf_diename(&indie); + if (!tmp) + goto end; + dwarf_decl_line(&indie, &lineno); + } else { + if (eaddr == addr) /* No offset: function entry */ + lineno = ppt->line; + else + dwarf_decl_line(&spdie, &lineno); + } + ppt->function = xstrdup(tmp); + ppt->line -= lineno; /* Make a relative line number */ + } + +end: + dwarf_end(dbg); + return ret; +} + + /* Find line range from its line number */ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) { @@ -720,7 +897,7 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) continue; /* Address filtering 2: No child include addr? */ - if (die_get_inlinefunc(sp_die, addr, &die_mem)) + if (die_find_inlinefunc(sp_die, addr, &die_mem)) continue; } @@ -731,7 +908,7 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) /* Copy real path */ if (!lf->lr->path) - lf->lr->path = strdup(src); + lf->lr->path = xstrdup(src); line_list__add_line(&lf->lr->line_list, (unsigned int)lineno); } /* Update status */ diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index d1a651793ba6..2f2307d4139f 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -3,6 +3,7 @@ #include <stdbool.h> #include "util.h" +#include "probe-event.h" #define MAX_PATH_LEN 256 #define MAX_PROBE_BUFFER 1024 @@ -14,68 +15,36 @@ static inline int is_c_varname(const char *name) return isalpha(name[0]) || name[0] == '_'; } -struct probe_point { - char *event; /* Event name */ - char *group; /* Event group */ - - /* Inputs */ - char *file; /* File name */ - int line; /* Line number */ - char *lazy_line; /* Lazy line pattern */ - - char *function; /* Function name */ - int offset; /* Offset bytes */ - - int nr_args; /* Number of arguments */ - char **args; /* Arguments */ - - int retprobe; /* Return probe */ - - /* Output */ - int found; /* Number of found probe points */ - char *probes[MAX_PROBES]; /* Output buffers (will be allocated)*/ -}; - -/* Line number container */ -struct line_node { - struct list_head list; - unsigned int line; -}; +#ifndef NO_DWARF_SUPPORT +/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ +extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, + struct kprobe_trace_event **tevs); -/* Line range */ -struct line_range { - char *file; /* File name */ - char *function; /* Function name */ - unsigned int start; /* Start line number */ - unsigned int end; /* End line number */ - int offset; /* Start line offset */ - char *path; /* Real path name */ - struct list_head line_list; /* Visible lines */ -}; +/* Find a perf_probe_point from debuginfo */ +extern int find_perf_probe_point(int fd, unsigned long addr, + struct perf_probe_point *ppt); -#ifndef NO_DWARF_SUPPORT -extern int find_probe_point(int fd, struct probe_point *pp); extern int find_line_range(int fd, struct line_range *lr); #include <dwarf.h> #include <libdw.h> struct probe_finder { - struct probe_point *pp; /* Target probe point */ + struct perf_probe_event *pev; /* Target probe event */ + int ntevs; /* number of trace events */ + struct kprobe_trace_event *tevs; /* Result trace events */ /* For function searching */ Dwarf_Addr addr; /* Address */ - const char *fname; /* File name */ + const char *fname; /* Real file name */ int lno; /* Line number */ Dwarf_Die cu_die; /* Current CU */ + struct list_head lcache; /* Line cache for lazy match */ /* For variable searching */ Dwarf_Op *fb_ops; /* Frame base attribute */ - Dwarf_Addr cu_base; /* Current CU base address */ - const char *var; /* Current variable name */ - char *buf; /* Current output buffer */ - int len; /* Length of output buffer */ - struct list_head lcache; /* Line cache for lazy match */ + struct perf_probe_arg *pvar; /* Current target variable */ + struct kprobe_trace_arg *tvar; /* Current result variable */ }; struct line_finder { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 5c33417eebb3..34d73395baac 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -86,4 +86,13 @@ static inline struct map * { return map_groups__new_module(&self->kmaps, start, filename); } + +#ifdef NO_NEWT_SUPPORT +static inline void perf_session__browse_hists(struct rb_root *hists __used, + u64 session_total __used, + const char *helpline __used) {} +#else +void perf_session__browse_hists(struct rb_root *hists, u64 session_total, + const char *helpline); +#endif #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 323c0aea0a91..3eb9de4baef3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -18,18 +18,6 @@ #define NT_GNU_BUILD_ID 3 #endif -enum dso_origin { - DSO__ORIG_KERNEL = 0, - DSO__ORIG_JAVA_JIT, - DSO__ORIG_BUILD_ID_CACHE, - DSO__ORIG_FEDORA, - DSO__ORIG_UBUNTU, - DSO__ORIG_BUILDID, - DSO__ORIG_DSO, - DSO__ORIG_KMODULE, - DSO__ORIG_NOT_FOUND, -}; - static void dsos__add(struct list_head *head, struct dso *dso); static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); static int dso__load_kernel_sym(struct dso *self, struct map *map, @@ -163,9 +151,17 @@ void dso__set_long_name(struct dso *self, char *name) self->long_name_len = strlen(name); } +static void dso__set_short_name(struct dso *self, const char *name) +{ + if (name == NULL) + return; + self->short_name = name; + self->short_name_len = strlen(name); +} + static void dso__set_basename(struct dso *self) { - self->short_name = basename(self->long_name); + dso__set_short_name(self, basename(self->long_name)); } struct dso *dso__new(const char *name) @@ -176,7 +172,7 @@ struct dso *dso__new(const char *name) int i; strcpy(self->name, name); dso__set_long_name(self, self->name); - self->short_name = self->name; + dso__set_short_name(self, self->name); for (i = 0; i < MAP__NR_TYPES; ++i) self->symbols[i] = self->symbol_names[i] = RB_ROOT; self->slen_calculated = 0; @@ -862,8 +858,8 @@ out_close: if (err == 0) return nr; out: - pr_warning("%s: problems reading %s PLT info.\n", - __func__, self->long_name); + pr_debug("%s: problems reading %s PLT info.\n", + __func__, self->long_name); return 0; } @@ -897,7 +893,6 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, struct kmap *kmap = self->kernel ? map__kmap(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = self; - size_t dso_name_len = strlen(self->short_name); Elf_Data *symstrs, *secstrs; uint32_t nr_syms; int err = -1; @@ -987,7 +982,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, char dso_name[PATH_MAX]; if (strcmp(section_name, - curr_dso->short_name + dso_name_len) == 0) + (curr_dso->short_name + + self->short_name_len)) == 0) goto new_symbol; if (strcmp(section_name, ".text") == 0) { @@ -1017,7 +1013,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, } curr_map->map_ip = identity__map_ip; curr_map->unmap_ip = identity__map_ip; - curr_dso->origin = DSO__ORIG_KERNEL; + curr_dso->origin = self->origin; map_groups__insert(kmap->kmaps, curr_map); dsos__add(&dsos__kernel, curr_dso); dso__set_loaded(curr_dso, map->type); @@ -1782,7 +1778,7 @@ struct dso *dso__new_kernel(const char *name) struct dso *self = dso__new(name ?: "[kernel.kallsyms]"); if (self != NULL) { - self->short_name = "[kernel]"; + dso__set_short_name(self, "[kernel]"); self->kernel = 1; } @@ -1887,6 +1883,17 @@ out_fail: return -1; } +size_t vmlinux_path__fprintf(FILE *fp) +{ + int i; + size_t printed = 0; + + for (i = 0; i < vmlinux_path__nr_entries; ++i) + printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]); + + return printed; +} + static int setup_list(struct strlist **list, const char *list_str, const char *list_name) { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 280dadd32a08..0da2455d5b90 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -106,13 +106,15 @@ struct dso { u8 has_build_id:1; u8 kernel:1; u8 hit:1; + u8 annotate_warned:1; unsigned char origin; u8 sorted_by_name; u8 loaded; u8 build_id[BUILD_ID_SIZE]; - u16 long_name_len; const char *short_name; char *long_name; + u16 long_name_len; + u16 short_name_len; char name[0]; }; @@ -149,6 +151,19 @@ size_t dsos__fprintf_buildid(FILE *fp, bool with_hits); size_t dso__fprintf_buildid(struct dso *self, FILE *fp); size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp); + +enum dso_origin { + DSO__ORIG_KERNEL = 0, + DSO__ORIG_JAVA_JIT, + DSO__ORIG_BUILD_ID_CACHE, + DSO__ORIG_FEDORA, + DSO__ORIG_UBUNTU, + DSO__ORIG_BUILDID, + DSO__ORIG_DSO, + DSO__ORIG_KMODULE, + DSO__ORIG_NOT_FOUND, +}; + char dso__symtab_origin(const struct dso *self); void dso__set_long_name(struct dso *self, char *name); void dso__set_build_id(struct dso *self, void *build_id); @@ -168,4 +183,6 @@ int kallsyms__parse(const char *filename, void *arg, int symbol__init(void); bool symbol_type__is_a(char symbol_type, enum map_type map_type); +size_t vmlinux_path__fprintf(FILE *fp); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index fa968312ee7d..ea6506234d57 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,6 +7,37 @@ #include "util.h" #include "debug.h" +int find_all_tid(int pid, pid_t ** all_tid) +{ + char name[256]; + int items; + struct dirent **namelist = NULL; + int ret = 0; + int i; + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + *all_tid = malloc(sizeof(pid_t) * items); + if (!*all_tid) { + ret = -ENOMEM; + goto failure; + } + + for (i = 0; i < items; i++) + (*all_tid)[i] = atoi(namelist[i]->d_name); + + ret = items; + +failure: + for (i=0; i<items; i++) + free(namelist[i]); + free(namelist); + + return ret; +} + void map_groups__init(struct map_groups *self) { int i; @@ -348,3 +379,4 @@ struct symbol *map_groups__find_symbol(struct map_groups *self, return NULL; } + diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index dcf70303e58e..a81426a891bf 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -23,6 +23,7 @@ struct thread { int comm_len; }; +int find_all_tid(int pid, pid_t ** all_tid); 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); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 0f5b2a6f1080..52701087ce04 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -295,6 +295,13 @@ extern void *xmemdupz(const void *data, size_t len); extern char *xstrndup(const char *str, size_t len); extern void *xrealloc(void *ptr, size_t size) __attribute__((weak)); +static inline void *xzalloc(size_t size) +{ + void *buf = xmalloc(size); + + return memset(buf, 0, size); +} + static inline void *zalloc(size_t size) { return calloc(1, size); @@ -309,6 +316,7 @@ static inline int has_extension(const char *filename, const char *ext) { size_t len = strlen(filename); size_t extlen = strlen(ext); + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); } @@ -322,6 +330,7 @@ static inline int has_extension(const char *filename, const char *ext) #undef isalnum #undef tolower #undef toupper + extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 |
