From c05556421742eb47f80301767653a4bcb19de9de Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Tue, 13 Apr 2010 18:37:33 +1000 Subject: perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie Acked-by: David S. Miller Cc: # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list Cc: Ian Munsie Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: KOSAKI Motohiro Cc: Hitoshi Mitake Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Eric B Munson Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong Cc: Thiago Farina Cc: Masami Hiramatsu Cc: Xiao Guangrong Cc: Jaswinder Singh Rajput Cc: Arjan van de Ven Cc: OGAWA Hirofumi Cc: Mike Galbraith Cc: Tom Zanussi Cc: Anton Blanchard Cc: John Kacur Cc: Li Zefan Cc: Steven Rostedt LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-diff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1ea15d8aeed1..3a1d94d75dce 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -19,7 +19,7 @@ static char const *input_old = "perf.data.old", *input_new = "perf.data"; static char diff__default_sort_order[] = "dso,symbol"; -static int force; +static bool force; static bool show_displacement; static int perf_session__add_hist_entry(struct perf_session *self, @@ -188,7 +188,7 @@ static const char * const diff_usage[] = { }; static const struct option options[] = { - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('m', "displacement", &show_displacement, "Show position displacement relative to baseline"), -- cgit v1.2.3 From a1645ce12adb6c9cc9e19d7695466204e3f017fe Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Mon, 19 Apr 2010 13:32:50 +0800 Subject: perf: 'perf kvm' tool for monitoring guest performance from host Here is the patch of userspace perf tool. Signed-off-by: Zhang Yanmin Signed-off-by: Avi Kivity --- tools/perf/Documentation/perf-kvm.txt | 67 ++++++ tools/perf/Makefile | 1 + tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-buildid-list.c | 2 +- tools/perf/builtin-diff.c | 6 +- tools/perf/builtin-kmem.c | 11 +- tools/perf/builtin-kvm.c | 144 +++++++++++++ tools/perf/builtin-record.c | 63 +++++- tools/perf/builtin-report.c | 6 +- tools/perf/builtin-top.c | 75 +++++-- tools/perf/builtin.h | 1 + tools/perf/command-list.txt | 1 + tools/perf/perf.c | 1 + tools/perf/perf.h | 2 + tools/perf/util/build-id.c | 2 +- tools/perf/util/event.c | 280 ++++++++++++++++++------- tools/perf/util/event.h | 10 +- tools/perf/util/header.c | 213 +++++++++++++++---- tools/perf/util/header.h | 1 + tools/perf/util/hist.c | 72 ++++++- tools/perf/util/hist.h | 3 + tools/perf/util/map.c | 139 ++++++++++++- tools/perf/util/map.h | 75 +++++-- tools/perf/util/probe-event.c | 7 +- tools/perf/util/session.c | 77 +++---- tools/perf/util/session.h | 28 +-- tools/perf/util/sort.h | 5 + tools/perf/util/symbol.c | 382 ++++++++++++++++++++++++++++------ tools/perf/util/symbol.h | 43 ++-- tools/perf/util/thread.h | 4 +- 30 files changed, 1407 insertions(+), 316 deletions(-) create mode 100644 tools/perf/Documentation/perf-kvm.txt create mode 100644 tools/perf/builtin-kvm.c (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt new file mode 100644 index 000000000000..93400a0f17f0 --- /dev/null +++ b/tools/perf/Documentation/perf-kvm.txt @@ -0,0 +1,67 @@ +perf-kvm(1) +============== + +NAME +---- +perf-kvm - Tool to trace/measure kvm guest os + +SYNOPSIS +-------- +[verse] +'perf kvm' [--host] [--guest] [--guestmount= + [--guestkallsyms= --guestmodules= | --guestvmlinux=]] + {top|record|report|diff|buildid-list} +'perf kvm' [--host] [--guest] [--guestkallsyms= --guestmodules= + | --guestvmlinux=] {top|record|report|diff|buildid-list} + +DESCRIPTION +----------- +There are a couple of variants of perf kvm: + + 'perf kvm [options] top ' to generates and displays + a performance counter profile of guest os in realtime + of an arbitrary workload. + + 'perf kvm record ' to record the performance couinter profile + of an arbitrary workload and save it into a perf data file. If both + --host and --guest are input, the perf data file name is perf.data.kvm. + If there is no --host but --guest, the file name is perf.data.guest. + If there is no --guest but --host, the file name is perf.data.host. + + 'perf kvm report' to display the performance counter profile information + recorded via perf kvm record. + + 'perf kvm diff' to displays the performance difference amongst two perf.data + files captured via perf record. + + 'perf kvm buildid-list' to display the buildids found in a perf data file, + so that other tools can be used to fetch packages with matching symbol tables + for use by perf report. + +OPTIONS +------- +--host=:: + Collect host side perforamnce profile. +--guest=:: + Collect guest side perforamnce profile. +--guestmount=:: + Guest os root file system mount directory. Users mounts guest os + root directories under by a specific filesystem access method, + typically, sshfs. For example, start 2 guest os. The one's pid is 8888 + and the other's is 9999. + #mkdir ~/guestmount; cd ~/guestmount + #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/ + #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/ + #perf kvm --host --guest --guestmount=~/guestmount top +--guestkallsyms=:: + Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest + kernel symbols. Users copy it out from guest os. +--guestmodules=:: + Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest + kernel module information. Users copy it out from guest os. +--guestvmlinux=:: + Guest os kernel vmlinux. + +SEE ALSO +-------- +linkperf:perf-top[1] perf-record[1] perf-report[1] perf-diff[1] perf-buildid-list[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 57b3569716dd..3cb3449a9645 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -472,6 +472,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-trace.o BUILTIN_OBJS += $(OUTPUT)builtin-probe.o BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o BUILTIN_OBJS += $(OUTPUT)builtin-lock.o +BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o PERFLIBS = $(LIB_FILE) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 06eaebe10d04..f924b4332be6 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -571,7 +571,7 @@ static int __cmd_annotate(void) perf_session__fprintf(session, stdout); if (verbose > 2) - dsos__fprintf(stdout); + dsos__fprintf(&session->kerninfo_root, stdout); perf_session__collapse_resort(&session->hists); perf_session__output_resort(&session->hists, session->event_total[0]); diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index af2ad8b92f76..623afe3fdcb8 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -46,7 +46,7 @@ static int __cmd_buildid_list(void) if (with_hits) perf_session__process_events(session, &build_id__mark_dso_hit_ops); - dsos__fprintf_buildid(stdout, with_hits); + dsos__fprintf_buildid(&session->kerninfo_root, stdout, with_hits); perf_session__delete(session); return err; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 3a1d94d75dce..207e860591e2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -33,7 +33,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return -ENOMEM; if (hit) - he->count += count; + __perf_session__add_count(he, al, count); return 0; } @@ -225,6 +225,10 @@ int cmd_diff(int argc, const char **argv, const char *prefix __used) input_new = argv[1]; } else input_new = argv[0]; + } else if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_kallsyms) { + input_old = "perf.data.host"; + input_new = "perf.data.guest"; } symbol_conf.exclude_other = false; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 513aa8a55db6..db474bbf3322 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -351,6 +351,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session, int n_lines, int is_caller) { struct rb_node *next; + struct kernel_info *kerninfo; printf("%.102s\n", graph_dotted_line); printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); @@ -359,10 +360,16 @@ static void __print_result(struct rb_root *root, struct perf_session *session, next = rb_first(root); + kerninfo = kerninfo__findhost(&session->kerninfo_root); + if (!kerninfo) { + pr_err("__print_result: couldn't find kernel information\n"); + return; + } while (next && n_lines--) { struct alloc_stat *data = rb_entry(next, struct alloc_stat, node); struct symbol *sym = NULL; + struct map_groups *kmaps = &kerninfo->kmaps; struct map *map; char buf[BUFSIZ]; u64 addr; @@ -370,8 +377,8 @@ static void __print_result(struct rb_root *root, struct perf_session *session, if (is_caller) { addr = data->call_site; if (!raw_ip) - sym = map_groups__find_function(&session->kmaps, - addr, &map, NULL); + sym = map_groups__find_function(kmaps, addr, + &map, NULL); } else addr = data->ptr; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c new file mode 100644 index 000000000000..a4c7cae45024 --- /dev/null +++ b/tools/perf/builtin-kvm.c @@ -0,0 +1,144 @@ +#include "builtin.h" +#include "perf.h" + +#include "util/util.h" +#include "util/cache.h" +#include "util/symbol.h" +#include "util/thread.h" +#include "util/header.h" +#include "util/session.h" + +#include "util/parse-options.h" +#include "util/trace-event.h" + +#include "util/debug.h" + +#include + +#include +#include +#include + +static char *file_name; +static char name_buffer[256]; + +int perf_host = 1; +int perf_guest; + +static const char * const kvm_usage[] = { + "perf kvm [] {top|record|report|diff|buildid-list}", + NULL +}; + +static const struct option kvm_options[] = { + OPT_STRING('i', "input", &file_name, "file", + "Input file name"), + OPT_STRING('o', "output", &file_name, "file", + "Output file name"), + OPT_BOOLEAN(0, "guest", &perf_guest, + "Collect guest os data"), + OPT_BOOLEAN(0, "host", &perf_host, + "Collect guest os data"), + OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", + "guest mount directory under which every guest os" + " instance has a subdir"), + OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, + "file", "file saving guest os vmlinux"), + OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, + "file", "file saving guest os /proc/kallsyms"), + OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, + "file", "file saving guest os /proc/modules"), + OPT_END() +}; + +static int __cmd_record(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("record"); + rec_argv[i++] = strdup("-o"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_record(i, rec_argv, NULL); +} + +static int __cmd_report(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("report"); + rec_argv[i++] = strdup("-i"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_report(i, rec_argv, NULL); +} + +static int __cmd_buildid_list(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("buildid-list"); + rec_argv[i++] = strdup("-i"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_buildid_list(i, rec_argv, NULL); +} + +int cmd_kvm(int argc, const char **argv, const char *prefix __used) +{ + perf_host = perf_guest = 0; + + argc = parse_options(argc, argv, kvm_options, kvm_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (!argc) + usage_with_options(kvm_usage, kvm_options); + + if (!perf_host) + perf_guest = 1; + + if (!file_name) { + if (perf_host && !perf_guest) + sprintf(name_buffer, "perf.data.host"); + else if (!perf_host && perf_guest) + sprintf(name_buffer, "perf.data.guest"); + else + sprintf(name_buffer, "perf.data.kvm"); + file_name = name_buffer; + } + + if (!strncmp(argv[0], "rec", 3)) + return __cmd_record(argc, argv); + else if (!strncmp(argv[0], "rep", 3)) + return __cmd_report(argc, argv); + else if (!strncmp(argv[0], "diff", 4)) + return cmd_diff(argc, argv, NULL); + else if (!strncmp(argv[0], "top", 3)) + return cmd_top(argc, argv, NULL); + else if (!strncmp(argv[0], "buildid-list", 12)) + return __cmd_buildid_list(argc, argv); + else + usage_with_options(kvm_usage, kvm_options); + + return 0; +} diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a1b99eeac3c0..27f992aca8b5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -456,6 +456,52 @@ static void atexit_header(void) } } +static void event__synthesize_guest_os(struct kernel_info *kerninfo, + void *data __attribute__((unused))) +{ + int err; + char *guest_kallsyms; + char path[PATH_MAX]; + + if (is_host_kernel(kerninfo)) + return; + + /* + *As for guest kernel when processing subcommand record&report, + *we arrange module mmap prior to guest kernel mmap and trigger + *a preload dso because default guest module symbols are loaded + *from guest kallsyms instead of /lib/modules/XXX/XXX. This + *method is used to avoid symbol missing when the first addr is + *in module instead of in guest kernel. + */ + err = event__synthesize_modules(process_synthesized_event, + session, + kerninfo); + if (err < 0) + pr_err("Couldn't record guest kernel [%d]'s reference" + " relocation symbol.\n", kerninfo->pid); + + if (is_default_guest(kerninfo)) + guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + guest_kallsyms = path; + } + + /* + * We use _stext for guest kernel because guest kernel's /proc/kallsyms + * have no _text sometimes. + */ + err = event__synthesize_kernel_mmap(process_synthesized_event, + session, kerninfo, "_text"); + if (err < 0) + err = event__synthesize_kernel_mmap(process_synthesized_event, + session, kerninfo, "_stext"); + if (err < 0) + pr_err("Couldn't record guest kernel [%d]'s reference" + " relocation symbol.\n", kerninfo->pid); +} + static int __cmd_record(int argc, const char **argv) { int i, counter; @@ -467,6 +513,7 @@ static int __cmd_record(int argc, const char **argv) int child_ready_pipe[2], go_pipe[2]; const bool forks = argc > 0; char buf; + struct kernel_info *kerninfo; page_size = sysconf(_SC_PAGE_SIZE); @@ -635,21 +682,31 @@ static int __cmd_record(int argc, const char **argv) advance_output(err); } + kerninfo = kerninfo__findhost(&session->kerninfo_root); + if (!kerninfo) { + pr_err("Couldn't find native kernel information.\n"); + return -1; + } + err = event__synthesize_kernel_mmap(process_synthesized_event, - session, "_text"); + session, kerninfo, "_text"); if (err < 0) err = event__synthesize_kernel_mmap(process_synthesized_event, - session, "_stext"); + session, kerninfo, "_stext"); if (err < 0) { pr_err("Couldn't record kernel reference relocation symbol.\n"); return err; } - err = event__synthesize_modules(process_synthesized_event, session); + err = event__synthesize_modules(process_synthesized_event, + session, kerninfo); if (err < 0) { pr_err("Couldn't record kernel reference relocation symbol.\n"); return err; } + if (perf_guest) + kerninfo__process_allkernels(&session->kerninfo_root, + event__synthesize_guest_os, session); if (!system_wide && profile_cpu == -1) event__synthesize_thread(target_tid, process_synthesized_event, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 7da5fb365264..816edae7c5b2 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -108,7 +108,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return -ENOMEM; if (hit) - he->count += data->period; + __perf_session__add_count(he, al, data->period); if (symbol_conf.use_callchain) { if (!hit) @@ -313,7 +313,7 @@ static int __cmd_report(void) perf_session__fprintf(session, stdout); if (verbose > 2) - dsos__fprintf(stdout); + dsos__fprintf(&session->kerninfo_root, stdout); next = rb_first(&session->stats_by_id); while (next) { @@ -450,6 +450,8 @@ static const struct option options[] = { "sort by key(s): pid, comm, dso, symbol, parent"), OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths, "Don't shorten the pathnames taking into account the cwd"), + OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, + "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 40f24dd46ef4..dfd7ea7dabdd 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -420,8 +420,9 @@ static double sym_weight(const struct sym_entry *sym) } static long samples; -static long userspace_samples; +static long kernel_samples, us_samples; static long exact_samples; +static long guest_us_samples, guest_kernel_samples; static const char CONSOLE_CLEAR[] = ""; static void __list_insert_active_sym(struct sym_entry *syme) @@ -461,7 +462,10 @@ static void print_sym_table(void) int printed = 0, j; 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 ksamples_per_sec = kernel_samples/delay_secs; + float us_samples_per_sec = (us_samples)/delay_secs; + float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs; + float guest_us_samples_per_sec = (guest_us_samples)/delay_secs; float esamples_percent = (100.0*exact_samples)/samples; float sum_ksamples = 0.0; struct sym_entry *syme, *n; @@ -470,7 +474,8 @@ static void print_sym_table(void) int sym_width = 0, dso_width = 0, dso_short_width = 0; const int win_width = winsize.ws_col - 1; - samples = userspace_samples = exact_samples = 0; + samples = us_samples = kernel_samples = exact_samples = 0; + guest_kernel_samples = guest_us_samples = 0; /* Sort the active symbols */ pthread_mutex_lock(&active_symbols_lock); @@ -501,10 +506,30 @@ 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%% exact: %4.1f%% [", - samples_per_sec, - 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)), - esamples_percent); + if (!perf_guest) { + 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)), + esamples_percent); + } else { + printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%" + " guest kernel:%4.1f%% guest us:%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-us_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_kernel_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_us_samples_per_sec) / + samples_per_sec)), + esamples_percent); + } if (nr_counters == 1 || !display_weighted) { printf("%Ld", (u64)attrs[0].sample_period); @@ -597,7 +622,6 @@ static void print_sym_table(void) syme = rb_entry(nd, struct sym_entry, rb_node); sym = sym_entry__symbol(syme); - if (++printed > print_entries || (int)syme->snap_count < count_filter) continue; @@ -761,7 +785,7 @@ static int key_mapped(int c) return 0; } -static void handle_keypress(int c) +static void handle_keypress(struct perf_session *session, int c) { if (!key_mapped(c)) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; @@ -830,7 +854,7 @@ static void handle_keypress(int c) case 'Q': printf("exiting.\n"); if (dump_symtab) - dsos__fprintf(stderr); + dsos__fprintf(&session->kerninfo_root, stderr); exit(0); case 's': prompt_symbol(&sym_filter_entry, "Enter details symbol"); @@ -866,6 +890,7 @@ static void *display_thread(void *arg __used) struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; struct termios tc, save; int delay_msecs, c; + struct perf_session *session = (struct perf_session *) arg; tcgetattr(0, &save); tc = save; @@ -886,7 +911,7 @@ repeat: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); - handle_keypress(c); + handle_keypress(session, c); goto repeat; return NULL; @@ -957,24 +982,46 @@ static void event__process_sample(const event_t *self, u64 ip = self->ip.ip; struct sym_entry *syme; struct addr_location al; + struct kernel_info *kerninfo; u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; ++samples; switch (origin) { case PERF_RECORD_MISC_USER: - ++userspace_samples; + ++us_samples; if (hide_user_symbols) return; + kerninfo = kerninfo__findhost(&session->kerninfo_root); break; case PERF_RECORD_MISC_KERNEL: + ++kernel_samples; if (hide_kernel_symbols) return; + kerninfo = kerninfo__findhost(&session->kerninfo_root); break; + case PERF_RECORD_MISC_GUEST_KERNEL: + ++guest_kernel_samples; + kerninfo = kerninfo__find(&session->kerninfo_root, + self->ip.pid); + break; + case PERF_RECORD_MISC_GUEST_USER: + ++guest_us_samples; + /* + * TODO: we don't process guest user from host side + * except simple counting. + */ + return; default: return; } + if (!kerninfo && perf_guest) { + pr_err("Can't find guest [%d]'s kernel information\n", + self->ip.pid); + return; + } + if (self->header.misc & PERF_RECORD_MISC_EXACT) exact_samples++; @@ -994,7 +1041,7 @@ static void event__process_sample(const event_t *self, * --hide-kernel-symbols, even if the user specifies an * invalid --vmlinux ;-) */ - if (al.map == session->vmlinux_maps[MAP__FUNCTION] && + if (al.map == kerninfo->vmlinux_maps[MAP__FUNCTION] && RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { pr_err("The %s file can't be used\n", symbol_conf.vmlinux_name); @@ -1261,7 +1308,7 @@ static int __cmd_top(void) perf_session__mmap_read(session); - if (pthread_create(&thread, NULL, display_thread, NULL)) { + if (pthread_create(&thread, NULL, display_thread, session)) { printf("Could not create display thread.\n"); exit(-1); } diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 10fe49e7048a..ab28bca92e52 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -32,5 +32,6 @@ extern int cmd_version(int argc, const char **argv, const char *prefix); extern int cmd_probe(int argc, const char **argv, const char *prefix); extern int cmd_kmem(int argc, const char **argv, const char *prefix); extern int cmd_lock(int argc, const char **argv, const char *prefix); +extern int cmd_kvm(int argc, const char **argv, const char *prefix); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index db6ee94d4a8e..2a1162d413a8 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -19,3 +19,4 @@ perf-trace mainporcelain common perf-probe mainporcelain common perf-kmem mainporcelain common perf-lock mainporcelain common +perf-kvm mainporcelain common diff --git a/tools/perf/perf.c b/tools/perf/perf.c index d4be55b6cd34..985cdb4bd005 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -307,6 +307,7 @@ static void handle_internal_command(int argc, const char **argv) { "probe", cmd_probe, 0 }, { "kmem", cmd_kmem, 0 }, { "lock", cmd_lock, 0 }, + { "kvm", cmd_kvm, 0 }, }; unsigned int i; static const char ext[] = STRIP_EXTENSION; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index ec212748d651..02821febb704 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -131,4 +131,6 @@ struct ip_callchain { u64 ips[0]; }; +extern int perf_host, perf_guest; + #endif diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 04904b35ba81..0f60a3906808 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -24,7 +24,7 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) } thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + event->ip.pid, event->ip.ip, &al); if (al.map != NULL) al.map->dso->hit = 1; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 571fb25f7eb9..e3fa8d3d11b4 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -112,7 +112,11 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, event_t ev = { .header = { .type = PERF_RECORD_MMAP, - .misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */ + /* + * Just like the kernel, see __perf_event_mmap + * in kernel/perf_event.c + */ + .misc = PERF_RECORD_MISC_USER, }, }; int n; @@ -167,11 +171,23 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, } int event__synthesize_modules(event__handler_t process, - struct perf_session *session) + struct perf_session *session, + struct kernel_info *kerninfo) { struct rb_node *nd; + struct map_groups *kmaps = &kerninfo->kmaps; + u16 misc; - for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]); + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (is_host_kernel(kerninfo)) + misc = PERF_RECORD_MISC_KERNEL; + else + misc = PERF_RECORD_MISC_GUEST_KERNEL; + + for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { event_t ev; size_t size; @@ -182,12 +198,13 @@ int event__synthesize_modules(event__handler_t process, size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); memset(&ev, 0, sizeof(ev)); - ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */ + ev.mmap.header.misc = misc; ev.mmap.header.type = PERF_RECORD_MMAP; ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size)); ev.mmap.start = pos->start; ev.mmap.len = pos->end - pos->start; + ev.mmap.pid = kerninfo->pid; memcpy(ev.mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); @@ -250,13 +267,18 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start) int event__synthesize_kernel_mmap(event__handler_t process, struct perf_session *session, + struct kernel_info *kerninfo, const char *symbol_name) { size_t size; + const char *filename, *mmap_name; + char path[PATH_MAX]; + char name_buff[PATH_MAX]; + struct map *map; + event_t ev = { .header = { .type = PERF_RECORD_MMAP, - .misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */ }, }; /* @@ -266,16 +288,37 @@ int event__synthesize_kernel_mmap(event__handler_t process, */ struct process_symbol_args args = { .name = symbol_name, }; - if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0) + mmap_name = kern_mmap_name(kerninfo, name_buff); + if (is_host_kernel(kerninfo)) { + /* + * kernel uses PERF_RECORD_MISC_USER for user space maps, + * see kernel/perf_event.c __perf_event_mmap + */ + ev.header.misc = PERF_RECORD_MISC_KERNEL; + filename = "/proc/kallsyms"; + } else { + ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + if (is_default_guest(kerninfo)) + filename = (char *) symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + filename = path; + } + } + + if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) return -ENOENT; + map = kerninfo->vmlinux_maps[MAP__FUNCTION]; size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename), - "[kernel.kallsyms.%s]", symbol_name) + 1; + "%s%s", mmap_name, symbol_name) + 1; size = ALIGN(size, sizeof(u64)); - ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size)); + ev.mmap.header.size = (sizeof(ev.mmap) - + (sizeof(ev.mmap.filename) - size)); ev.mmap.pgoff = args.start; - ev.mmap.start = session->vmlinux_maps[MAP__FUNCTION]->start; - ev.mmap.len = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ; + ev.mmap.start = map->start; + ev.mmap.len = map->end - ev.mmap.start; + ev.mmap.pid = kerninfo->pid; return process(&ev, session); } @@ -329,22 +372,50 @@ int event__process_lost(event_t *self, struct perf_session *session) return 0; } -int event__process_mmap(event_t *self, struct perf_session *session) +static void event_set_kernel_mmap_len(struct map **maps, event_t *self) +{ + maps[MAP__FUNCTION]->start = self->mmap.start; + maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (maps[MAP__FUNCTION]->end == 0) + maps[MAP__FUNCTION]->end = ~0UL; +} + +static int event__process_kernel_mmap(event_t *self, + struct perf_session *session) { - struct thread *thread; struct map *map; + char kmmap_prefix[PATH_MAX]; + struct kernel_info *kerninfo; + enum dso_kernel_type kernel_type; + bool is_kernel_mmap; + + kerninfo = kerninfo__findnew(&session->kerninfo_root, self->mmap.pid); + if (!kerninfo) { + pr_err("Can't find id %d's kerninfo\n", self->mmap.pid); + goto out_problem; + } - dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", - self->mmap.pid, self->mmap.tid, self->mmap.start, - self->mmap.len, self->mmap.pgoff, self->mmap.filename); + kern_mmap_name(kerninfo, kmmap_prefix); + if (is_host_kernel(kerninfo)) + kernel_type = DSO_TYPE_KERNEL; + else + kernel_type = DSO_TYPE_GUEST_KERNEL; - if (self->mmap.pid == 0) { - static const char kmmap_prefix[] = "[kernel.kallsyms."; + is_kernel_mmap = memcmp(self->mmap.filename, + kmmap_prefix, + strlen(kmmap_prefix)) == 0; + if (self->mmap.filename[0] == '/' || + (!is_kernel_mmap && self->mmap.filename[0] == '[')) { - if (self->mmap.filename[0] == '/') { - char short_module_name[1024]; - char *name = strrchr(self->mmap.filename, '/'), *dot; + char short_module_name[1024]; + char *name, *dot; + if (self->mmap.filename[0] == '/') { + name = strrchr(self->mmap.filename, '/'); if (name == NULL) goto out_problem; @@ -352,59 +423,86 @@ int event__process_mmap(event_t *self, struct perf_session *session) dot = strrchr(name, '.'); if (dot == NULL) goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); + "[%.*s]", (int)(dot - name), name); strxfrchar(short_module_name, '-', '_'); - - map = perf_session__new_module_map(session, - self->mmap.start, - self->mmap.filename); - if (map == NULL) - goto out_problem; - - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - map->dso->short_name = name; - map->end = map->start + self->mmap.len; - } else if (memcmp(self->mmap.filename, kmmap_prefix, - sizeof(kmmap_prefix) - 1) == 0) { - const char *symbol_name = (self->mmap.filename + - sizeof(kmmap_prefix) - 1); + } else + strcpy(short_module_name, self->mmap.filename); + + map = map_groups__new_module(&kerninfo->kmaps, + self->mmap.start, + self->mmap.filename, + kerninfo); + if (map == NULL) + goto out_problem; + + name = strdup(short_module_name); + if (name == NULL) + goto out_problem; + + map->dso->short_name = name; + map->end = map->start + self->mmap.len; + } else if (is_kernel_mmap) { + const char *symbol_name = (self->mmap.filename + + strlen(kmmap_prefix)); + /* + * Should be there already, from the build-id table in + * the header. + */ + struct dso *kernel = __dsos__findnew(&kerninfo->dsos__kernel, + kmmap_prefix); + if (kernel == NULL) + goto out_problem; + + kernel->kernel = kernel_type; + if (__map_groups__create_kernel_maps(&kerninfo->kmaps, + kerninfo->vmlinux_maps, kernel) < 0) + goto out_problem; + + event_set_kernel_mmap_len(kerninfo->vmlinux_maps, self); + perf_session__set_kallsyms_ref_reloc_sym(kerninfo->vmlinux_maps, + symbol_name, + self->mmap.pgoff); + if (is_default_guest(kerninfo)) { /* - * Should be there already, from the build-id table in - * the header. + * preload dso of guest kernel and modules */ - struct dso *kernel = __dsos__findnew(&dsos__kernel, - "[kernel.kallsyms]"); - if (kernel == NULL) - goto out_problem; - - kernel->kernel = 1; - if (__perf_session__create_kernel_maps(session, kernel) < 0) - goto out_problem; + dso__load(kernel, + kerninfo->vmlinux_maps[MAP__FUNCTION], + NULL); + } + } + return 0; +out_problem: + return -1; +} - session->vmlinux_maps[MAP__FUNCTION]->start = self->mmap.start; - session->vmlinux_maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (session->vmlinux_maps[MAP__FUNCTION]->end == 0) - session->vmlinux_maps[MAP__FUNCTION]->end = ~0UL; +int event__process_mmap(event_t *self, struct perf_session *session) +{ + struct kernel_info *kerninfo; + struct thread *thread; + struct map *map; + u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + int ret = 0; - perf_session__set_kallsyms_ref_reloc_sym(session, symbol_name, - self->mmap.pgoff); - } + dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", + self->mmap.pid, self->mmap.tid, self->mmap.start, + self->mmap.len, self->mmap.pgoff, self->mmap.filename); + + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = event__process_kernel_mmap(self, session); + if (ret < 0) + goto out_problem; return 0; } thread = perf_session__findnew(session, self->mmap.pid); - map = map__new(self->mmap.start, self->mmap.len, self->mmap.pgoff, - self->mmap.pid, self->mmap.filename, MAP__FUNCTION, - session->cwd, session->cwdlen); + kerninfo = kerninfo__findhost(&session->kerninfo_root); + map = map__new(&kerninfo->dsos__user, self->mmap.start, + self->mmap.len, self->mmap.pgoff, + self->mmap.pid, self->mmap.filename, + MAP__FUNCTION, session->cwd, session->cwdlen); if (thread == NULL || map == NULL) goto out_problem; @@ -444,22 +542,52 @@ int event__process_task(event_t *self, struct perf_session *session) void thread__find_addr_map(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al) { struct map_groups *mg = &self->mg; + struct kernel_info *kerninfo = NULL; al->thread = self; al->addr = addr; + al->cpumode = cpumode; + al->filtered = false; - if (cpumode == PERF_RECORD_MISC_KERNEL) { + if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - mg = &session->kmaps; - } else if (cpumode == PERF_RECORD_MISC_USER) + kerninfo = kerninfo__findhost(&session->kerninfo_root); + mg = &kerninfo->kmaps; + } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; - else { - al->level = 'H'; + kerninfo = kerninfo__findhost(&session->kerninfo_root); + } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { + al->level = 'g'; + kerninfo = kerninfo__find(&session->kerninfo_root, pid); + if (!kerninfo) { + al->map = NULL; + return; + } + mg = &kerninfo->kmaps; + } else { + /* + * 'u' means guest os user space. + * TODO: We don't support guest user space. Might support late. + */ + if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) + al->level = 'u'; + else + al->level = 'H'; al->map = NULL; + + if ((cpumode == PERF_RECORD_MISC_GUEST_USER || + cpumode == PERF_RECORD_MISC_GUEST_KERNEL) && + !perf_guest) + al->filtered = true; + if ((cpumode == PERF_RECORD_MISC_USER || + cpumode == PERF_RECORD_MISC_KERNEL) && + !perf_host) + al->filtered = true; + return; } try_again: @@ -474,8 +602,11 @@ try_again: * "[vdso]" dso, but for now lets use the old trick of looking * in the whole kernel symbol list. */ - if ((long long)al->addr < 0 && mg != &session->kmaps) { - mg = &session->kmaps; + if ((long long)al->addr < 0 && + cpumode == PERF_RECORD_MISC_KERNEL && + kerninfo && + mg != &kerninfo->kmaps) { + mg = &kerninfo->kmaps; goto try_again; } } else @@ -484,11 +615,11 @@ try_again: void thread__find_addr_location(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al, symbol_filter_t filter) { - thread__find_addr_map(self, session, cpumode, type, addr, al); + thread__find_addr_map(self, session, cpumode, type, pid, addr, al); if (al->map != NULL) al->sym = map__find_symbol(al->map, al->addr, filter); else @@ -524,7 +655,7 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - self->ip.ip, al); + self->ip.pid, self->ip.ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : ""); @@ -554,7 +685,6 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, !strlist__has_entry(symbol_conf.sym_list, al->sym->name)) goto out_filtered; - al->filtered = false; return 0; out_filtered: diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index e5740ea140ab..4af2ed5d48ad 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -79,6 +79,7 @@ struct sample_data { struct build_id_event { struct perf_event_header header; + pid_t pid; u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[]; }; @@ -154,10 +155,13 @@ int event__synthesize_thread(pid_t pid, event__handler_t process, void event__synthesize_threads(event__handler_t process, struct perf_session *session); int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - const char *symbol_name); + struct perf_session *session, + struct kernel_info *kerninfo, + const char *symbol_name); + int event__synthesize_modules(event__handler_t process, - struct perf_session *session); + struct perf_session *session, + struct kernel_info *kerninfo); int event__process_comm(event_t *self, struct perf_session *session); int event__process_lost(event_t *self, struct perf_session *session); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 628173ba689e..75d016768021 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -190,7 +190,8 @@ static int write_padded(int fd, const void *bf, size_t count, continue; \ else -static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, + u16 misc, int fd) { struct dso *pos; @@ -205,6 +206,7 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) len = ALIGN(len, NAME_ALIGN); memset(&b, 0, sizeof(b)); memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); + b.pid = pid; b.header.misc = misc; b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); @@ -219,13 +221,33 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) return 0; } -static int dsos__write_buildid_table(int fd) +static int dsos__write_buildid_table(struct perf_header *header, int fd) { - int err = __dsos__write_buildid_table(&dsos__kernel, - PERF_RECORD_MISC_KERNEL, fd); - if (err == 0) - err = __dsos__write_buildid_table(&dsos__user, - PERF_RECORD_MISC_USER, fd); + struct perf_session *session = container_of(header, + struct perf_session, header); + struct rb_node *nd; + int err = 0; + u16 kmisc, umisc; + + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + if (is_host_kernel(pos)) { + kmisc = PERF_RECORD_MISC_KERNEL; + umisc = PERF_RECORD_MISC_USER; + } else { + kmisc = PERF_RECORD_MISC_GUEST_KERNEL; + umisc = PERF_RECORD_MISC_GUEST_USER; + } + + err = __dsos__write_buildid_table(&pos->dsos__kernel, pos->pid, + kmisc, fd); + if (err == 0) + err = __dsos__write_buildid_table(&pos->dsos__user, + pos->pid, umisc, fd); + if (err) + break; + } return err; } @@ -342,9 +364,12 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) return err; } -static int dsos__cache_build_ids(void) +static int dsos__cache_build_ids(struct perf_header *self) { - int err_kernel, err_user; + struct perf_session *session = container_of(self, + struct perf_session, header); + struct rb_node *nd; + int ret = 0; char debugdir[PATH_MAX]; snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"), @@ -353,9 +378,30 @@ static int dsos__cache_build_ids(void) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir); - err_user = __dsos__cache_build_ids(&dsos__user, debugdir); - return err_kernel || err_user ? -1 : 0; + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret |= __dsos__cache_build_ids(&pos->dsos__kernel, debugdir); + ret |= __dsos__cache_build_ids(&pos->dsos__user, debugdir); + } + return ret ? -1 : 0; +} + +static bool dsos__read_build_ids(struct perf_header *self, bool with_hits) +{ + bool ret = false; + struct perf_session *session = container_of(self, + struct perf_session, header); + struct rb_node *nd; + + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret |= __dsos__read_build_ids(&pos->dsos__kernel, with_hits); + ret |= __dsos__read_build_ids(&pos->dsos__user, with_hits); + } + + return ret; } static int perf_header__adds_write(struct perf_header *self, int fd) @@ -366,7 +412,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd) u64 sec_start; int idx = 0, err; - if (dsos__read_build_ids(true)) + if (dsos__read_build_ids(self, true)) perf_header__set_feat(self, HEADER_BUILD_ID); nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); @@ -401,14 +447,14 @@ static int perf_header__adds_write(struct perf_header *self, int fd) /* Write build-ids */ buildid_sec->offset = lseek(fd, 0, SEEK_CUR); - err = dsos__write_buildid_table(fd); + err = dsos__write_buildid_table(self, fd); if (err < 0) { pr_debug("failed to write buildid table\n"); goto out_free; } buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset; - dsos__cache_build_ids(); + dsos__cache_build_ids(self); } lseek(fd, sec_start, SEEK_SET); @@ -633,6 +679,85 @@ int perf_file_header__read(struct perf_file_header *self, return 0; } +static int __event_process_build_id(struct build_id_event *bev, + char *filename, + struct perf_session *session) +{ + int err = -1; + struct list_head *head; + struct kernel_info *kerninfo; + u16 misc; + struct dso *dso; + enum dso_kernel_type dso_type; + + kerninfo = kerninfo__findnew(&session->kerninfo_root, bev->pid); + if (!kerninfo) + goto out; + + misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + switch (misc) { + case PERF_RECORD_MISC_KERNEL: + dso_type = DSO_TYPE_KERNEL; + head = &kerninfo->dsos__kernel; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + dso_type = DSO_TYPE_GUEST_KERNEL; + head = &kerninfo->dsos__kernel; + break; + case PERF_RECORD_MISC_USER: + case PERF_RECORD_MISC_GUEST_USER: + dso_type = DSO_TYPE_USER; + head = &kerninfo->dsos__user; + break; + default: + goto out; + } + + dso = __dsos__findnew(head, filename); + if (dso != NULL) { + dso__set_build_id(dso, &bev->build_id); + if (filename[0] == '[') + dso->kernel = dso_type; + } + + err = 0; +out: + return err; +} + +static int perf_header__read_build_ids(struct perf_header *self, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(self, + struct perf_session, header); + struct build_id_event bev; + char filename[PATH_MAX]; + u64 limit = offset + size; + int err = -1; + + while (offset < limit) { + ssize_t len; + + if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + goto out; + + if (self->needs_swap) + perf_event_header__bswap(&bev.header); + + len = bev.header.size - sizeof(bev); + if (read(input, filename, len) != len) + goto out; + + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + err = 0; +out: + return err; +} + static int perf_file_section__process(struct perf_file_section *self, struct perf_header *ph, int feat, int fd) @@ -989,6 +1114,7 @@ int event__process_tracing_data(event_t *self, int event__synthesize_build_id(struct dso *pos, u16 misc, event__handler_t process, + struct kernel_info *kerninfo, struct perf_session *session) { event_t ev; @@ -1005,6 +1131,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc, memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc; + ev.build_id.pid = kerninfo->pid; ev.build_id.header.size = sizeof(ev.build_id) + len; memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); @@ -1015,6 +1142,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc, static int __event_synthesize_build_ids(struct list_head *head, u16 misc, event__handler_t process, + struct kernel_info *kerninfo, struct perf_session *session) { struct dso *pos; @@ -1024,7 +1152,8 @@ static int __event_synthesize_build_ids(struct list_head *head, u16 misc, if (!pos->hit) continue; - err = event__synthesize_build_id(pos, misc, process, session); + err = event__synthesize_build_id(pos, misc, process, + kerninfo, session); if (err < 0) return err; } @@ -1035,44 +1164,48 @@ static int __event_synthesize_build_ids(struct list_head *head, u16 misc, int event__synthesize_build_ids(event__handler_t process, struct perf_session *session) { - int err; + int err = 0; + u16 kmisc, umisc; + struct kernel_info *pos; + struct rb_node *nd; - if (!dsos__read_build_ids(true)) + if (!dsos__read_build_ids(&session->header, true)) return 0; - err = __event_synthesize_build_ids(&dsos__kernel, - PERF_RECORD_MISC_KERNEL, - process, session); - if (err == 0) - err = __event_synthesize_build_ids(&dsos__user, - PERF_RECORD_MISC_USER, - process, session); + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct kernel_info, rb_node); + if (is_host_kernel(pos)) { + kmisc = PERF_RECORD_MISC_KERNEL; + umisc = PERF_RECORD_MISC_USER; + } else { + kmisc = PERF_RECORD_MISC_GUEST_KERNEL; + umisc = PERF_RECORD_MISC_GUEST_USER; + } + + err = __event_synthesize_build_ids(&pos->dsos__kernel, + kmisc, process, pos, session); + if (err == 0) + err = __event_synthesize_build_ids(&pos->dsos__user, + umisc, process, pos, session); + if (err) + break; + } if (err < 0) { pr_debug("failed to synthesize build ids\n"); return err; } - dsos__cache_build_ids(); + dsos__cache_build_ids(&session->header); return 0; } int event__process_build_id(event_t *self, - struct perf_session *session __unused) + struct perf_session *session) { - struct list_head *head = &dsos__user; - struct dso *dso; - - if (self->build_id.header.misc & PERF_RECORD_MISC_KERNEL) - head = &dsos__kernel; - - dso = __dsos__findnew(head, self->build_id.filename); - if (dso != NULL) { - dso__set_build_id(dso, &self->build_id.build_id); - if (head == &dsos__kernel && self->build_id.filename[0] == '[') - dso->kernel = 1; - } - + __event_process_build_id(&self->build_id, + self->build_id.filename, + session); return 0; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 4214e2375650..275915458148 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -120,6 +120,7 @@ int event__process_tracing_data(event_t *self, int event__synthesize_build_id(struct dso *pos, u16 misc, event__handler_t process, + struct kernel_info *kerninfo, struct perf_session *session); int event__synthesize_build_ids(event__handler_t process, struct perf_session *session); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 9c2b8743cef6..ad6b22dde27f 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -8,6 +8,30 @@ struct callchain_param callchain_param = { .min_percent = 0.5 }; +void __perf_session__add_count(struct hist_entry *he, + struct addr_location *al, + u64 count) +{ + he->count += count; + + switch (al->cpumode) { + case PERF_RECORD_MISC_KERNEL: + he->count_sys += count; + break; + case PERF_RECORD_MISC_USER: + he->count_us += count; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + he->count_guest_sys += count; + break; + case PERF_RECORD_MISC_GUEST_USER: + he->count_guest_us += count; + break; + default: + break; + } +} + /* * histogram, sorted on item, collects counts */ @@ -464,7 +488,7 @@ int hist_entry__snprintf(struct hist_entry *self, u64 session_total) { struct sort_entry *se; - u64 count, total; + u64 count, total, count_sys, count_us, count_guest_sys, count_guest_us; const char *sep = symbol_conf.field_sep; int ret; @@ -474,9 +498,17 @@ int hist_entry__snprintf(struct hist_entry *self, if (pair_session) { count = self->pair ? self->pair->count : 0; total = pair_session->events_stats.total; + count_sys = self->pair ? self->pair->count_sys : 0; + count_us = self->pair ? self->pair->count_us : 0; + count_guest_sys = self->pair ? self->pair->count_guest_sys : 0; + count_guest_us = self->pair ? self->pair->count_guest_us : 0; } else { count = self->count; total = session_total; + count_sys = self->count_sys; + count_us = self->count_us; + count_guest_sys = self->count_guest_sys; + count_guest_us = self->count_guest_us; } if (total) { @@ -487,6 +519,26 @@ int hist_entry__snprintf(struct hist_entry *self, else ret = snprintf(s, size, sep ? "%.2f" : " %6.2f%%", (count * 100.0) / total); + if (symbol_conf.show_cpu_utilization) { + ret += percent_color_snprintf(s + ret, size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_sys * 100.0) / total); + ret += percent_color_snprintf(s + ret, size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_us * 100.0) / total); + if (perf_guest) { + ret += percent_color_snprintf(s + ret, + size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_guest_sys * 100.0) / + total); + ret += percent_color_snprintf(s + ret, + size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_guest_us * 100.0) / + total); + } + } } else ret = snprintf(s, size, sep ? "%lld" : "%12lld ", count); @@ -597,6 +649,24 @@ size_t perf_session__fprintf_hists(struct rb_root *hists, fputs(" Samples ", fp); } + if (symbol_conf.show_cpu_utilization) { + if (sep) { + ret += fprintf(fp, "%csys", *sep); + ret += fprintf(fp, "%cus", *sep); + if (perf_guest) { + ret += fprintf(fp, "%cguest sys", *sep); + ret += fprintf(fp, "%cguest us", *sep); + } + } else { + ret += fprintf(fp, " sys "); + ret += fprintf(fp, " us "); + if (perf_guest) { + ret += fprintf(fp, " guest sys "); + ret += fprintf(fp, " guest us "); + } + } + } + if (pair) { if (sep) ret += fprintf(fp, "%cDelta", *sep); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index ad17f0ad798b..9df1c340ec92 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -12,6 +12,9 @@ struct addr_location; struct symbol; struct rb_root; +void __perf_session__add_count(struct hist_entry *he, + struct addr_location *al, + u64 count); struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, struct addr_location *al, struct symbol *parent, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 37913b241bdf..7facd016ec97 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "map.h" const char *map_type__name[MAP__NR_TYPES] = { @@ -37,9 +38,11 @@ void map__init(struct map *self, enum map_type type, self->map_ip = map__map_ip; self->unmap_ip = map__unmap_ip; RB_CLEAR_NODE(&self->rb_node); + self->groups = NULL; } -struct map *map__new(u64 start, u64 len, u64 pgoff, u32 pid, char *filename, +struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, + u64 pgoff, u32 pid, char *filename, enum map_type type, char *cwd, int cwdlen) { struct map *self = malloc(sizeof(*self)); @@ -66,7 +69,7 @@ struct map *map__new(u64 start, u64 len, u64 pgoff, u32 pid, char *filename, filename = newfilename; } - dso = dsos__findnew(filename); + dso = __dsos__findnew(dsos__list, filename); if (dso == NULL) goto out_delete; @@ -242,6 +245,7 @@ void map_groups__init(struct map_groups *self) self->maps[i] = RB_ROOT; INIT_LIST_HEAD(&self->removed_maps[i]); } + self->this_kerninfo = NULL; } void map_groups__flush(struct map_groups *self) @@ -508,3 +512,134 @@ struct map *maps__find(struct rb_root *maps, u64 ip) return NULL; } + +struct kernel_info *add_new_kernel_info(struct rb_root *kerninfo_root, + pid_t pid, const char *root_dir) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo, *pos; + + kerninfo = malloc(sizeof(struct kernel_info)); + if (!kerninfo) + return NULL; + + kerninfo->pid = pid; + map_groups__init(&kerninfo->kmaps); + kerninfo->root_dir = strdup(root_dir); + RB_CLEAR_NODE(&kerninfo->rb_node); + INIT_LIST_HEAD(&kerninfo->dsos__user); + INIT_LIST_HEAD(&kerninfo->dsos__kernel); + kerninfo->kmaps.this_kerninfo = kerninfo; + + while (*p != NULL) { + parent = *p; + pos = rb_entry(parent, struct kernel_info, rb_node); + if (pid < pos->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&kerninfo->rb_node, parent, p); + rb_insert_color(&kerninfo->rb_node, kerninfo_root); + + return kerninfo; +} + +struct kernel_info *kerninfo__find(struct rb_root *kerninfo_root, pid_t pid) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo; + struct kernel_info *default_kerninfo = NULL; + + while (*p != NULL) { + parent = *p; + kerninfo = rb_entry(parent, struct kernel_info, rb_node); + if (pid < kerninfo->pid) + p = &(*p)->rb_left; + else if (pid > kerninfo->pid) + p = &(*p)->rb_right; + else + return kerninfo; + if (!kerninfo->pid) + default_kerninfo = kerninfo; + } + + return default_kerninfo; +} + +struct kernel_info *kerninfo__findhost(struct rb_root *kerninfo_root) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo; + pid_t pid = HOST_KERNEL_ID; + + while (*p != NULL) { + parent = *p; + kerninfo = rb_entry(parent, struct kernel_info, rb_node); + if (pid < kerninfo->pid) + p = &(*p)->rb_left; + else if (pid > kerninfo->pid) + p = &(*p)->rb_right; + else + return kerninfo; + } + + return NULL; +} + +struct kernel_info *kerninfo__findnew(struct rb_root *kerninfo_root, pid_t pid) +{ + char path[PATH_MAX]; + const char *root_dir; + int ret; + struct kernel_info *kerninfo = kerninfo__find(kerninfo_root, pid); + + if (!kerninfo || kerninfo->pid != pid) { + if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID) + root_dir = ""; + else { + if (!symbol_conf.guestmount) + goto out; + sprintf(path, "%s/%d", symbol_conf.guestmount, pid); + ret = access(path, R_OK); + if (ret) { + pr_err("Can't access file %s\n", path); + goto out; + } + root_dir = path; + } + kerninfo = add_new_kernel_info(kerninfo_root, pid, root_dir); + } + +out: + return kerninfo; +} + +void kerninfo__process_allkernels(struct rb_root *kerninfo_root, + process_kernel_info process, + void *data) +{ + struct rb_node *nd; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + process(pos, data); + } +} + +char *kern_mmap_name(struct kernel_info *kerninfo, char *buff) +{ + if (is_host_kernel(kerninfo)) + sprintf(buff, "[%s]", "kernel.kallsyms"); + else if (is_default_guest(kerninfo)) + sprintf(buff, "[%s]", "guest.kernel.kallsyms"); + else + sprintf(buff, "[%s.%d]", "guest.kernel.kallsyms", kerninfo->pid); + + return buff; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 2031278cc06a..30d38d634e09 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -19,6 +19,7 @@ extern const char *map_type__name[MAP__NR_TYPES]; struct dso; struct ref_reloc_sym; struct map_groups; +struct kernel_info; struct map { union { @@ -36,6 +37,7 @@ struct map { u64 (*unmap_ip)(struct map *, u64); struct dso *dso; + struct map_groups *groups; }; struct kmap { @@ -43,6 +45,26 @@ struct kmap { struct map_groups *kmaps; }; +struct map_groups { + struct rb_root maps[MAP__NR_TYPES]; + struct list_head removed_maps[MAP__NR_TYPES]; + struct kernel_info *this_kerninfo; +}; + +/* Native host kernel uses -1 as pid index in kernel_info */ +#define HOST_KERNEL_ID (-1) +#define DEFAULT_GUEST_KERNEL_ID (0) + +struct kernel_info { + struct rb_node rb_node; + pid_t pid; + char *root_dir; + struct list_head dsos__user; + struct list_head dsos__kernel; + struct map_groups kmaps; + struct map *vmlinux_maps[MAP__NR_TYPES]; +}; + static inline struct kmap *map__kmap(struct map *self) { return (struct kmap *)(self + 1); @@ -74,7 +96,8 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *self, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); -struct map *map__new(u64 start, u64 len, u64 pgoff, u32 pid, char *filename, +struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, + u64 pgoff, u32 pid, char *filename, enum map_type type, char *cwd, int cwdlen); void map__delete(struct map *self); struct map *map__clone(struct map *self); @@ -91,11 +114,6 @@ void map__fixup_end(struct map *self); void map__reloc_vmlinux(struct map *self); -struct map_groups { - struct rb_root maps[MAP__NR_TYPES]; - struct list_head removed_maps[MAP__NR_TYPES]; -}; - size_t __map_groups__fprintf_maps(struct map_groups *self, enum map_type type, int verbose, FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); @@ -106,9 +124,40 @@ int map_groups__clone(struct map_groups *self, size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp); size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp); +struct kernel_info *add_new_kernel_info(struct rb_root *kerninfo_root, + pid_t pid, const char *root_dir); +struct kernel_info *kerninfo__find(struct rb_root *kerninfo_root, pid_t pid); +struct kernel_info *kerninfo__findnew(struct rb_root *kerninfo_root, pid_t pid); +struct kernel_info *kerninfo__findhost(struct rb_root *kerninfo_root); +char *kern_mmap_name(struct kernel_info *kerninfo, char *buff); + +/* + * Default guest kernel is defined by parameter --guestkallsyms + * and --guestmodules + */ +static inline int is_default_guest(struct kernel_info *kerninfo) +{ + if (!kerninfo) + return 0; + return kerninfo->pid == DEFAULT_GUEST_KERNEL_ID; +} + +static inline int is_host_kernel(struct kernel_info *kerninfo) +{ + if (!kerninfo) + return 0; + return kerninfo->pid == HOST_KERNEL_ID; +} + +typedef void (*process_kernel_info)(struct kernel_info *kerninfo, void *data); +void kerninfo__process_allkernels(struct rb_root *kerninfo_root, + process_kernel_info process, + void *data); + static inline void map_groups__insert(struct map_groups *self, struct map *map) { - maps__insert(&self->maps[map->type], map); + maps__insert(&self->maps[map->type], map); + map->groups = self; } static inline struct map *map_groups__find(struct map_groups *self, @@ -148,13 +197,11 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, struct map *map_groups__find_by_name(struct map_groups *self, enum map_type type, const char *name); -int __map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES], - struct dso *kernel); -int map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES]); -struct map *map_groups__new_module(struct map_groups *self, u64 start, - const char *filename); +struct map *map_groups__new_module(struct map_groups *self, + u64 start, + const char *filename, + struct kernel_info *kerninfo); + void map_groups__flush(struct map_groups *self); #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 5bf8ab034466..3967f8f63d0d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -78,6 +78,7 @@ static struct map *kmaps[MAP__NR_TYPES]; /* Initialize symbol maps and path of vmlinux */ static int init_vmlinux(void) { + struct dso *kernel; int ret; symbol_conf.sort_by_name = true; @@ -91,8 +92,12 @@ static int init_vmlinux(void) goto out; } + kernel = dso__new_kernel(symbol_conf.vmlinux_name); + if (kernel == NULL) + die("Failed to create kernel dso."); + map_groups__init(&kmap_groups); - ret = map_groups__create_kernel_maps(&kmap_groups, kmaps); + ret = __map_groups__create_kernel_maps(&kmap_groups, kmaps, kernel); if (ret < 0) pr_debug("Failed to create kernel maps.\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0fdf3ebef1e9..7d88ae5c270f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -67,6 +67,17 @@ void perf_session__update_sample_type(struct perf_session *self) self->sample_type = perf_header__sample_type(&self->header); } +int perf_session__create_kernel_maps(struct perf_session *self) +{ + int ret; + struct rb_root *root = &self->kerninfo_root; + + ret = map_groups__create_kernel_maps(root, HOST_KERNEL_ID); + if (ret >= 0) + ret = map_groups__create_guest_kernel_maps(root); + return ret; +} + struct perf_session *perf_session__new(const char *filename, int mode, bool force) { size_t len = filename ? strlen(filename) + 1 : 0; @@ -86,7 +97,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc self->cwd = NULL; self->cwdlen = 0; self->unknown_events = 0; - map_groups__init(&self->kmaps); + self->kerninfo_root = RB_ROOT; if (mode == O_RDONLY) { if (perf_session__open(self, force) < 0) @@ -157,8 +168,9 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, continue; } + al.filtered = false; thread__find_addr_location(thread, self, cpumode, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, thread->pid, ip, &al, NULL); if (al.sym != NULL) { if (sort__has_parent && !*parent && symbol__match_parent_regex(al.sym)) @@ -399,46 +411,6 @@ void perf_event_header__bswap(struct perf_event_header *self) self->size = bswap_16(self->size); } -int perf_header__read_build_ids(struct perf_header *self, - int input, u64 offset, u64 size) -{ - struct build_id_event bev; - char filename[PATH_MAX]; - u64 limit = offset + size; - int err = -1; - - while (offset < limit) { - struct dso *dso; - ssize_t len; - struct list_head *head = &dsos__user; - - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) - goto out; - - if (self->needs_swap) - perf_event_header__bswap(&bev.header); - - len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) - goto out; - - if (bev.header.misc & PERF_RECORD_MISC_KERNEL) - head = &dsos__kernel; - - dso = __dsos__findnew(head, filename); - if (dso != NULL) { - dso__set_build_id(dso, &bev.build_id); - if (head == &dsos__kernel && filename[0] == '[') - dso->kernel = 1; - } - - offset += bev.header.size; - } - err = 0; -out: - return err; -} - static struct thread *perf_session__register_idle_thread(struct perf_session *self) { struct thread *thread = perf_session__findnew(self, 0); @@ -690,26 +662,33 @@ bool perf_session__has_traces(struct perf_session *self, const char *msg) return true; } -int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self, +int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr) { char *bracket; enum map_type i; + struct ref_reloc_sym *ref; + + ref = zalloc(sizeof(struct ref_reloc_sym)); + if (ref == NULL) + return -ENOMEM; - self->ref_reloc_sym.name = strdup(symbol_name); - if (self->ref_reloc_sym.name == NULL) + ref->name = strdup(symbol_name); + if (ref->name == NULL) { + free(ref); return -ENOMEM; + } - bracket = strchr(self->ref_reloc_sym.name, ']'); + bracket = strchr(ref->name, ']'); if (bracket) *bracket = '\0'; - self->ref_reloc_sym.addr = addr; + ref->addr = addr; for (i = 0; i < MAP__NR_TYPES; ++i) { - struct kmap *kmap = map__kmap(self->vmlinux_maps[i]); - kmap->ref_reloc_sym = &self->ref_reloc_sym; + struct kmap *kmap = map__kmap(maps[i]); + kmap->ref_reloc_sym = ref; } return 0; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 0ac14d42dc28..5e47c87b9266 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -15,17 +15,15 @@ struct perf_session { struct perf_header header; unsigned long size; unsigned long mmap_window; - struct map_groups kmaps; struct rb_root threads; struct thread *last_match; - struct map *vmlinux_maps[MAP__NR_TYPES]; + struct rb_root kerninfo_root; struct events_stats events_stats; struct rb_root stats_by_id; unsigned long event_total[PERF_RECORD_MAX]; unsigned long unknown_events; struct rb_root hists; u64 sample_type; - struct ref_reloc_sym ref_reloc_sym; int fd; bool fd_pipe; int cwdlen; @@ -69,33 +67,13 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, bool perf_session__has_traces(struct perf_session *self, const char *msg); -int perf_header__read_build_ids(struct perf_header *self, int input, - u64 offset, u64 file_size); - -int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self, +int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); void mem_bswap_64(void *src, int byte_size); -static inline int __perf_session__create_kernel_maps(struct perf_session *self, - struct dso *kernel) -{ - return __map_groups__create_kernel_maps(&self->kmaps, - self->vmlinux_maps, kernel); -} - -static inline int perf_session__create_kernel_maps(struct perf_session *self) -{ - return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps); -} - -static inline struct map * - perf_session__new_module_map(struct perf_session *self, - u64 start, const char *filename) -{ - return map_groups__new_module(&self->kmaps, start, filename); -} +int perf_session__create_kernel_maps(struct perf_session *self); int do_read(int fd, void *buf, size_t size); void perf_session__update_sample_type(struct perf_session *self); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 1d857aa2c01f..b7c54eeed9c9 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -44,6 +44,11 @@ extern enum sort_type sort__first_dimension; struct hist_entry { struct rb_node rb_node; u64 count; + u64 count_sys; + u64 count_us; + u64 count_guest_sys; + u64 count_guest_us; + /* * XXX WARNING! * thread _has_ to come after ms, see diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index f3d4151e46a1..e782e7db16c5 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -28,6 +28,8 @@ 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, symbol_filter_t filter); +static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, + symbol_filter_t filter); static int vmlinux_path__nr_entries; static char **vmlinux_path; @@ -186,6 +188,7 @@ struct dso *dso__new(const char *name) self->loaded = 0; self->sorted_by_name = 0; self->has_build_id = 0; + self->kernel = DSO_TYPE_USER; } return self; @@ -402,12 +405,9 @@ int kallsyms__parse(const char *filename, void *arg, char *symbol_name; line_len = getline(&line, &n, file); - if (line_len < 0) + if (line_len < 0 || !line) break; - if (!line) - goto out_failure; - line[--line_len] = '\0'; /* \n */ len = hex2u64(line, &start); @@ -459,6 +459,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * map__split_kallsyms, when we have split the maps per module */ symbols__insert(root, sym); + return 0; } @@ -483,6 +484,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, symbol_filter_t filter) { struct map_groups *kmaps = map__kmap(map)->kmaps; + struct kernel_info *kerninfo = kmaps->this_kerninfo; struct map *curr_map = map; struct symbol *pos; int count = 0; @@ -504,15 +506,33 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, *module++ = '\0'; if (strcmp(curr_map->dso->short_name, module)) { - curr_map = map_groups__find_by_name(kmaps, map->type, module); + if (curr_map != map && + self->kernel == DSO_TYPE_GUEST_KERNEL && + is_default_guest(kerninfo)) { + /* + * We assume all symbols of a module are + * continuous in * kallsyms, so curr_map + * points to a module and all its + * symbols are in its kmap. Mark it as + * loaded. + */ + dso__set_loaded(curr_map->dso, + curr_map->type); + } + + curr_map = map_groups__find_by_name(kmaps, + map->type, module); if (curr_map == NULL) { - pr_debug("/proc/{kallsyms,modules} " + pr_err("%s/proc/{kallsyms,modules} " "inconsistency while looking " - "for \"%s\" module!\n", module); - return -1; + "for \"%s\" module!\n", + kerninfo->root_dir, module); + curr_map = map; + goto discard_symbol; } - if (curr_map->dso->loaded) + if (curr_map->dso->loaded && + !is_default_guest(kmaps->this_kerninfo)) goto discard_symbol; } /* @@ -525,13 +545,21 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, char dso_name[PATH_MAX]; struct dso *dso; - snprintf(dso_name, sizeof(dso_name), "[kernel].%d", - kernel_range++); + if (self->kernel == DSO_TYPE_GUEST_KERNEL) + snprintf(dso_name, sizeof(dso_name), + "[guest.kernel].%d", + kernel_range++); + else + snprintf(dso_name, sizeof(dso_name), + "[kernel].%d", + kernel_range++); dso = dso__new(dso_name); if (dso == NULL) return -1; + dso->kernel = self->kernel; + curr_map = map__new2(pos->start, dso, map->type); if (curr_map == NULL) { dso__delete(dso); @@ -555,6 +583,12 @@ discard_symbol: rb_erase(&pos->rb_node, root); } } + if (curr_map != map && + self->kernel == DSO_TYPE_GUEST_KERNEL && + is_default_guest(kmaps->this_kerninfo)) { + dso__set_loaded(curr_map->dso, curr_map->type); + } + return count; } @@ -565,7 +599,10 @@ int dso__load_kallsyms(struct dso *self, const char *filename, return -1; symbols__fixup_end(&self->symbols[map->type]); - self->origin = DSO__ORIG_KERNEL; + if (self->kernel == DSO_TYPE_GUEST_KERNEL) + self->origin = DSO__ORIG_GUEST_KERNEL; + else + self->origin = DSO__ORIG_KERNEL; return dso__split_kallsyms(self, map, filter); } @@ -952,7 +989,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - if (!self->kernel) { + if (self->kernel == DSO_TYPE_USER) { self->adjust_symbols = (ehdr.e_type == ET_EXEC || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", @@ -984,7 +1021,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, section_name = elf_sec__name(&shdr, secstrs); - if (self->kernel || kmodule) { + if (self->kernel != DSO_TYPE_USER || kmodule) { char dso_name[PATH_MAX]; if (strcmp(section_name, @@ -1011,6 +1048,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, curr_dso = dso__new(dso_name); if (curr_dso == NULL) goto out_elf_end; + curr_dso->kernel = self->kernel; curr_map = map__new2(start, curr_dso, map->type); if (curr_map == NULL) { @@ -1021,7 +1059,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, curr_map->unmap_ip = identity__map_ip; curr_dso->origin = self->origin; map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&dsos__kernel, curr_dso); + dsos__add(&self->node, curr_dso); dso__set_loaded(curr_dso, map->type); } else curr_dso = curr_map->dso; @@ -1083,7 +1121,7 @@ static bool dso__build_id_equal(const struct dso *self, u8 *build_id) return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0; } -static bool __dsos__read_build_ids(struct list_head *head, bool with_hits) +bool __dsos__read_build_ids(struct list_head *head, bool with_hits) { bool have_build_id = false; struct dso *pos; @@ -1101,13 +1139,6 @@ static bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } -bool dsos__read_build_ids(bool with_hits) -{ - bool kbuildids = __dsos__read_build_ids(&dsos__kernel, with_hits), - ubuildids = __dsos__read_build_ids(&dsos__user, with_hits); - return kbuildids || ubuildids; -} - /* * Align offset to 4 bytes as needed for note name and descriptor data. */ @@ -1242,6 +1273,8 @@ char dso__symtab_origin(const struct dso *self) [DSO__ORIG_BUILDID] = 'b', [DSO__ORIG_DSO] = 'd', [DSO__ORIG_KMODULE] = 'K', + [DSO__ORIG_GUEST_KERNEL] = 'g', + [DSO__ORIG_GUEST_KMODULE] = 'G', }; if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND) @@ -1257,11 +1290,20 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) char build_id_hex[BUILD_ID_SIZE * 2 + 1]; int ret = -1; int fd; + struct kernel_info *kerninfo; + const char *root_dir; dso__set_loaded(self, map->type); - if (self->kernel) + if (self->kernel == DSO_TYPE_KERNEL) return dso__load_kernel_sym(self, map, filter); + else if (self->kernel == DSO_TYPE_GUEST_KERNEL) + return dso__load_guest_kernel_sym(self, map, filter); + + if (map->groups && map->groups->this_kerninfo) + kerninfo = map->groups->this_kerninfo; + else + kerninfo = NULL; name = malloc(size); if (!name) @@ -1315,6 +1357,13 @@ more: case DSO__ORIG_DSO: snprintf(name, size, "%s", self->long_name); break; + case DSO__ORIG_GUEST_KMODULE: + if (map->groups && map->groups->this_kerninfo) + root_dir = map->groups->this_kerninfo->root_dir; + else + root_dir = ""; + snprintf(name, size, "%s%s", root_dir, self->long_name); + break; default: goto out; @@ -1368,7 +1417,8 @@ struct map *map_groups__find_by_name(struct map_groups *self, return NULL; } -static int dso__kernel_module_get_build_id(struct dso *self) +static int dso__kernel_module_get_build_id(struct dso *self, + const char *root_dir) { char filename[PATH_MAX]; /* @@ -1378,8 +1428,8 @@ static int dso__kernel_module_get_build_id(struct dso *self) const char *name = self->short_name + 1; snprintf(filename, sizeof(filename), - "/sys/module/%.*s/notes/.note.gnu.build-id", - (int)strlen(name - 1), name); + "%s/sys/module/%.*s/notes/.note.gnu.build-id", + root_dir, (int)strlen(name) - 1, name); if (sysfs__read_build_id(filename, self->build_id, sizeof(self->build_id)) == 0) @@ -1388,7 +1438,8 @@ static int dso__kernel_module_get_build_id(struct dso *self) return 0; } -static int map_groups__set_modules_path_dir(struct map_groups *self, char *dir_name) +static int map_groups__set_modules_path_dir(struct map_groups *self, + const char *dir_name) { struct dirent *dent; DIR *dir = opendir(dir_name); @@ -1400,8 +1451,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dir_n while ((dent = readdir(dir)) != NULL) { char path[PATH_MAX]; + struct stat st; + + /*sshfs might return bad dent->d_type, so we have to stat*/ + sprintf(path, "%s/%s", dir_name, dent->d_name); + if (stat(path, &st)) + continue; - if (dent->d_type == DT_DIR) { + if (S_ISDIR(st.st_mode)) { if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) continue; @@ -1433,7 +1490,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dir_n if (long_name == NULL) goto failure; dso__set_long_name(map->dso, long_name); - dso__kernel_module_get_build_id(map->dso); + dso__kernel_module_get_build_id(map->dso, ""); } } @@ -1443,16 +1500,46 @@ failure: return -1; } -static int map_groups__set_modules_path(struct map_groups *self) +static char *get_kernel_version(const char *root_dir) { - struct utsname uts; + char version[PATH_MAX]; + FILE *file; + char *name, *tmp; + const char *prefix = "Linux version "; + + sprintf(version, "%s/proc/version", root_dir); + file = fopen(version, "r"); + if (!file) + return NULL; + + version[0] = '\0'; + tmp = fgets(version, sizeof(version), file); + fclose(file); + + name = strstr(version, prefix); + if (!name) + return NULL; + name += strlen(prefix); + tmp = strchr(name, ' '); + if (tmp) + *tmp = '\0'; + + return strdup(name); +} + +static int map_groups__set_modules_path(struct map_groups *self, + const char *root_dir) +{ + char *version; char modules_path[PATH_MAX]; - if (uname(&uts) < 0) + version = get_kernel_version(root_dir); + if (!version) return -1; - snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel", - uts.release); + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + root_dir, version); + free(version); return map_groups__set_modules_path_dir(self, modules_path); } @@ -1477,11 +1564,13 @@ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) } struct map *map_groups__new_module(struct map_groups *self, u64 start, - const char *filename) + const char *filename, + struct kernel_info *kerninfo) { struct map *map; - struct dso *dso = __dsos__findnew(&dsos__kernel, filename); + struct dso *dso; + dso = __dsos__findnew(&kerninfo->dsos__kernel, filename); if (dso == NULL) return NULL; @@ -1489,21 +1578,37 @@ struct map *map_groups__new_module(struct map_groups *self, u64 start, if (map == NULL) return NULL; - dso->origin = DSO__ORIG_KMODULE; + if (is_host_kernel(kerninfo)) + dso->origin = DSO__ORIG_KMODULE; + else + dso->origin = DSO__ORIG_GUEST_KMODULE; map_groups__insert(self, map); return map; } -static int map_groups__create_modules(struct map_groups *self) +static int map_groups__create_modules(struct kernel_info *kerninfo) { char *line = NULL; size_t n; - FILE *file = fopen("/proc/modules", "r"); + FILE *file; struct map *map; + const char *root_dir; + const char *modules; + char path[PATH_MAX]; + + if (is_default_guest(kerninfo)) + modules = symbol_conf.default_guest_modules; + else { + sprintf(path, "%s/proc/modules", kerninfo->root_dir); + modules = path; + } + file = fopen(modules, "r"); if (file == NULL) return -1; + root_dir = kerninfo->root_dir; + while (!feof(file)) { char name[PATH_MAX]; u64 start; @@ -1532,16 +1637,17 @@ static int map_groups__create_modules(struct map_groups *self) *sep = '\0'; snprintf(name, sizeof(name), "[%s]", line); - map = map_groups__new_module(self, start, name); + map = map_groups__new_module(&kerninfo->kmaps, + start, name, kerninfo); if (map == NULL) goto out_delete_line; - dso__kernel_module_get_build_id(map->dso); + dso__kernel_module_get_build_id(map->dso, root_dir); } free(line); fclose(file); - return map_groups__set_modules_path(self); + return map_groups__set_modules_path(&kerninfo->kmaps, root_dir); out_delete_line: free(line); @@ -1708,8 +1814,57 @@ out_fixup: return err; } -LIST_HEAD(dsos__user); -LIST_HEAD(dsos__kernel); +static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, + symbol_filter_t filter) +{ + int err; + const char *kallsyms_filename = NULL; + struct kernel_info *kerninfo; + char path[PATH_MAX]; + + if (!map->groups) { + pr_debug("Guest kernel map hasn't the point to groups\n"); + return -1; + } + kerninfo = map->groups->this_kerninfo; + + if (is_default_guest(kerninfo)) { + /* + * if the user specified a vmlinux filename, use it and only + * it, reporting errors to the user if it cannot be used. + * Or use file guest_kallsyms inputted by user on commandline + */ + if (symbol_conf.default_guest_vmlinux_name != NULL) { + err = dso__load_vmlinux(self, map, + symbol_conf.default_guest_vmlinux_name, filter); + goto out_try_fixup; + } + + kallsyms_filename = symbol_conf.default_guest_kallsyms; + if (!kallsyms_filename) + return -1; + } else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + kallsyms_filename = path; + } + + err = dso__load_kallsyms(self, kallsyms_filename, map, filter); + if (err > 0) + pr_debug("Using %s for symbols\n", kallsyms_filename); + +out_try_fixup: + if (err > 0) { + if (kallsyms_filename != NULL) { + kern_mmap_name(kerninfo, path); + dso__set_long_name(self, + strdup(path)); + } + map__fixup_start(map); + map__fixup_end(map); + } + + return err; +} static void dsos__add(struct list_head *head, struct dso *dso) { @@ -1752,10 +1907,16 @@ static void __dsos__fprintf(struct list_head *head, FILE *fp) } } -void dsos__fprintf(FILE *fp) +void dsos__fprintf(struct rb_root *kerninfo_root, FILE *fp) { - __dsos__fprintf(&dsos__kernel, fp); - __dsos__fprintf(&dsos__user, fp); + struct rb_node *nd; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + __dsos__fprintf(&pos->dsos__kernel, fp); + __dsos__fprintf(&pos->dsos__user, fp); + } } static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, @@ -1773,10 +1934,21 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, return ret; } -size_t dsos__fprintf_buildid(FILE *fp, bool with_hits) +size_t dsos__fprintf_buildid(struct rb_root *kerninfo_root, + FILE *fp, bool with_hits) { - return (__dsos__fprintf_buildid(&dsos__kernel, fp, with_hits) + - __dsos__fprintf_buildid(&dsos__user, fp, with_hits)); + struct rb_node *nd; + size_t ret = 0; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret += __dsos__fprintf_buildid(&pos->dsos__kernel, + fp, with_hits); + ret += __dsos__fprintf_buildid(&pos->dsos__user, + fp, with_hits); + } + return ret; } struct dso *dso__new_kernel(const char *name) @@ -1785,28 +1957,59 @@ struct dso *dso__new_kernel(const char *name) if (self != NULL) { dso__set_short_name(self, "[kernel]"); - self->kernel = 1; + self->kernel = DSO_TYPE_KERNEL; + } + + return self; +} + +static struct dso *dso__new_guest_kernel(struct kernel_info *kerninfo, + const char *name) +{ + char buff[PATH_MAX]; + struct dso *self; + + kern_mmap_name(kerninfo, buff); + self = dso__new(name ?: buff); + if (self != NULL) { + dso__set_short_name(self, "[guest.kernel]"); + self->kernel = DSO_TYPE_GUEST_KERNEL; } return self; } -void dso__read_running_kernel_build_id(struct dso *self) +void dso__read_running_kernel_build_id(struct dso *self, + struct kernel_info *kerninfo) { - if (sysfs__read_build_id("/sys/kernel/notes", self->build_id, + char path[PATH_MAX]; + + if (is_default_guest(kerninfo)) + return; + sprintf(path, "%s/sys/kernel/notes", kerninfo->root_dir); + if (sysfs__read_build_id(path, self->build_id, sizeof(self->build_id)) == 0) self->has_build_id = true; } -static struct dso *dsos__create_kernel(const char *vmlinux) +static struct dso *dsos__create_kernel(struct kernel_info *kerninfo) { - struct dso *kernel = dso__new_kernel(vmlinux); + const char *vmlinux_name = NULL; + struct dso *kernel; - if (kernel != NULL) { - dso__read_running_kernel_build_id(kernel); - dsos__add(&dsos__kernel, kernel); + if (is_host_kernel(kerninfo)) { + vmlinux_name = symbol_conf.vmlinux_name; + kernel = dso__new_kernel(vmlinux_name); + } else { + if (is_default_guest(kerninfo)) + vmlinux_name = symbol_conf.default_guest_vmlinux_name; + kernel = dso__new_guest_kernel(kerninfo, vmlinux_name); } + if (kernel != NULL) { + dso__read_running_kernel_build_id(kernel, kerninfo); + dsos__add(&kerninfo->dsos__kernel, kernel); + } return kernel; } @@ -1950,23 +2153,29 @@ out_free_comm_list: return -1; } -int map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES]) +int map_groups__create_kernel_maps(struct rb_root *kerninfo_root, pid_t pid) { - struct dso *kernel = dsos__create_kernel(symbol_conf.vmlinux_name); + struct kernel_info *kerninfo; + struct dso *kernel; + kerninfo = kerninfo__findnew(kerninfo_root, pid); + if (kerninfo == NULL) + return -1; + kernel = dsos__create_kernel(kerninfo); if (kernel == NULL) return -1; - if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0) + if (__map_groups__create_kernel_maps(&kerninfo->kmaps, + kerninfo->vmlinux_maps, kernel) < 0) return -1; - if (symbol_conf.use_modules && map_groups__create_modules(self) < 0) + if (symbol_conf.use_modules && + map_groups__create_modules(kerninfo) < 0) pr_debug("Problems creating module maps, continuing anyway...\n"); /* * Now that we have all the maps created, just set the ->end of them: */ - map_groups__fixup_end(self); + map_groups__fixup_end(&kerninfo->kmaps); return 0; } @@ -2012,3 +2221,46 @@ char *strxfrchar(char *s, char from, char to) return s; } + +int map_groups__create_guest_kernel_maps(struct rb_root *kerninfo_root) +{ + int ret = 0; + struct dirent **namelist = NULL; + int i, items = 0; + char path[PATH_MAX]; + pid_t pid; + + if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_modules || + symbol_conf.default_guest_kallsyms) { + map_groups__create_kernel_maps(kerninfo_root, + DEFAULT_GUEST_KERNEL_ID); + } + + if (symbol_conf.guestmount) { + items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + for (i = 0; i < items; i++) { + if (!isdigit(namelist[i]->d_name[0])) { + /* Filter out . and .. */ + continue; + } + pid = atoi(namelist[i]->d_name); + sprintf(path, "%s/%s/proc/kallsyms", + symbol_conf.guestmount, + namelist[i]->d_name); + ret = access(path, R_OK); + if (ret) { + pr_debug("Can't access file %s\n", path); + goto failure; + } + map_groups__create_kernel_maps(kerninfo_root, + pid); + } +failure: + free(namelist); + } + + return ret; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 757fae3f5ee0..478f5ab37787 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -69,10 +69,15 @@ struct symbol_conf { show_nr_samples, use_callchain, exclude_other, - full_paths; + full_paths, + show_cpu_utilization; const char *vmlinux_name, *field_sep; - char *dso_list_str, + const char *default_guest_vmlinux_name, + *default_guest_kallsyms, + *default_guest_modules; + const char *guestmount; + char *dso_list_str, *comm_list_str, *sym_list_str, *col_width_list_str; @@ -106,6 +111,13 @@ struct addr_location { u64 addr; char level; bool filtered; + unsigned int cpumode; +}; + +enum dso_kernel_type { + DSO_TYPE_USER = 0, + DSO_TYPE_KERNEL, + DSO_TYPE_GUEST_KERNEL }; struct dso { @@ -115,7 +127,7 @@ struct dso { u8 adjust_symbols:1; u8 slen_calculated:1; u8 has_build_id:1; - u8 kernel:1; + enum dso_kernel_type kernel; u8 hit:1; u8 annotate_warned:1; unsigned char origin; @@ -143,34 +155,30 @@ static inline void dso__set_loaded(struct dso *self, enum map_type type) void dso__sort_by_name(struct dso *self, enum map_type type); -extern struct list_head dsos__user, dsos__kernel; - struct dso *__dsos__findnew(struct list_head *head, const char *name); -static inline struct dso *dsos__findnew(const char *name) -{ - return __dsos__findnew(&dsos__user, name); -} - int dso__load(struct dso *self, struct map *map, symbol_filter_t filter); int dso__load_vmlinux_path(struct dso *self, struct map *map, symbol_filter_t filter); int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map, symbol_filter_t filter); -void dsos__fprintf(FILE *fp); -size_t dsos__fprintf_buildid(FILE *fp, bool with_hits); +void dsos__fprintf(struct rb_root *kerninfo_root, FILE *fp); +size_t dsos__fprintf_buildid(struct rb_root *kerninfo_root, + 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_GUEST_KERNEL, DSO__ORIG_JAVA_JIT, DSO__ORIG_BUILD_ID_CACHE, DSO__ORIG_FEDORA, DSO__ORIG_UBUNTU, DSO__ORIG_BUILDID, DSO__ORIG_DSO, + DSO__ORIG_GUEST_KMODULE, DSO__ORIG_KMODULE, DSO__ORIG_NOT_FOUND, }; @@ -178,19 +186,26 @@ enum dso_origin { 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); -void dso__read_running_kernel_build_id(struct dso *self); +void dso__read_running_kernel_build_id(struct dso *self, + struct kernel_info *kerninfo); struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, const char *name); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); -bool dsos__read_build_ids(bool with_hits); +bool __dsos__read_build_ids(struct list_head *head, bool with_hits); int build_id__sprintf(const u8 *self, int len, char *bf); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +int __map_groups__create_kernel_maps(struct map_groups *self, + struct map *vmlinux_maps[MAP__NR_TYPES], + struct dso *kernel); +int map_groups__create_kernel_maps(struct rb_root *kerninfo_root, pid_t pid); +int map_groups__create_guest_kernel_maps(struct rb_root *kerninfo_root); + int symbol__init(void); bool symbol_type__is_a(char symbol_type, enum map_type map_type); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 9c488fcadec9..1dfd9ff8bdcd 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -33,12 +33,12 @@ static inline struct map *thread__find_map(struct thread *self, void thread__find_addr_map(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al); void thread__find_addr_location(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al, symbol_filter_t filter); #endif /* __PERF_THREAD_H */ -- cgit v1.2.3 From 454c407ec17a0c63e4023ac0877d687945a7df4a Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Sat, 1 May 2010 01:41:20 -0500 Subject: perf: add perf-inject builtin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, perf 'live mode' writes build-ids at the end of the session, which isn't actually useful for processing live mode events. What would be better would be to have the build-ids sent before any of the samples that reference them, which can be done by processing the event stream and retrieving the build-ids on the first hit. Doing that in perf-record itself, however, is off-limits. This patch introduces perf-inject, which does the same job while leaving perf-record untouched. Normal mode perf still records the build-ids at the end of the session as it should, but for live mode, perf-inject can be injected in between the record and report steps e.g.: perf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i - perf-inject reads a perf-record event stream and repipes it to stdout. At any point the processing code can inject other events into the event stream - in this case build-ids (-b option) are read and injected as needed into the event stream. Build-ids are just the first user of perf-inject - potentially anything that needs userspace processing to augment the trace stream with additional information could make use of this facility. Cc: Ingo Molnar Cc: Steven Rostedt Cc: Frédéric Weisbecker LKML-Reference: <1272696080-16435-3-git-send-email-tzanussi@gmail.com> Signed-off-by: Tom Zanussi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 1 + tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-buildid-list.c | 2 +- tools/perf/builtin-diff.c | 4 +- tools/perf/builtin-inject.c | 228 +++++++++++++++++++++++++++++++++++++ tools/perf/builtin-kmem.c | 2 +- tools/perf/builtin-lock.c | 2 +- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-sched.c | 2 +- tools/perf/builtin-timechart.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/builtin-trace.c | 2 +- tools/perf/builtin.h | 1 + tools/perf/perf.c | 1 + tools/perf/util/header.c | 35 ++++-- tools/perf/util/session.c | 3 +- tools/perf/util/session.h | 3 +- tools/perf/util/trace-event-read.c | 19 +++- tools/perf/util/trace-event.h | 2 +- 20 files changed, 293 insertions(+), 24 deletions(-) create mode 100644 tools/perf/builtin-inject.c (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index c5ac0a991565..0ef5cfe52f2d 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -490,6 +490,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o BUILTIN_OBJS += $(OUTPUT)builtin-lock.o BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o BUILTIN_OBJS += $(OUTPUT)builtin-test.o +BUILTIN_OBJS += $(OUTPUT)builtin-inject.o PERFLIBS = $(LIB_FILE) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index b57dbcf62af3..ee154b58772b 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -554,7 +554,7 @@ static int __cmd_annotate(void) int ret; struct perf_session *session; - session = perf_session__new(input_name, O_RDONLY, force); + session = perf_session__new(input_name, O_RDONLY, force, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 7dc3b2e7a5e4..44a47e13bd67 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -39,7 +39,7 @@ static int __cmd_buildid_list(void) int err = -1; struct perf_session *session; - session = perf_session__new(input_name, O_RDONLY, force); + session = perf_session__new(input_name, O_RDONLY, force, false); if (session == NULL) return -1; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 207e860591e2..4cce68f23686 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -156,8 +156,8 @@ static int __cmd_diff(void) int ret, i; struct perf_session *session[2]; - session[0] = perf_session__new(input_old, O_RDONLY, force); - session[1] = perf_session__new(input_new, O_RDONLY, force); + session[0] = perf_session__new(input_old, O_RDONLY, force, false); + session[1] = perf_session__new(input_new, O_RDONLY, force, false); if (session[0] == NULL || session[1] == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c new file mode 100644 index 000000000000..a5902a3eadd3 --- /dev/null +++ b/tools/perf/builtin-inject.c @@ -0,0 +1,228 @@ +/* + * builtin-inject.c + * + * Builtin inject command: Examine the live mode (stdin) event stream + * and repipe it to stdout while optionally injecting additional + * events into it. + */ +#include "builtin.h" + +#include "perf.h" +#include "util/session.h" +#include "util/debug.h" + +#include "util/parse-options.h" + +static char const *input_name = "-"; +static bool inject_build_ids; + +static int event__repipe(event_t *event __used, + struct perf_session *session __used) +{ + uint32_t size; + void *buf = event; + + size = event->header.size; + + while (size) { + int ret = write(STDOUT_FILENO, buf, size); + if (ret < 0) + return -errno; + + size -= ret; + buf += ret; + } + + return 0; +} + +static int event__repipe_mmap(event_t *self, struct perf_session *session) +{ + int err; + + err = event__process_mmap(self, session); + event__repipe(self, session); + + return err; +} + +static int event__repipe_task(event_t *self, struct perf_session *session) +{ + int err; + + err = event__process_task(self, session); + event__repipe(self, session); + + return err; +} + +static int event__repipe_tracing_data(event_t *self, + struct perf_session *session) +{ + int err; + + event__repipe(self, session); + err = event__process_tracing_data(self, session); + + return err; +} + +static int read_buildid(struct map *self, struct perf_session *session) +{ + const char *name = self->dso->long_name; + int err; + + if (filename__read_build_id(self->dso->long_name, self->dso->build_id, + sizeof(self->dso->build_id)) > 0) { + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + self->dso->has_build_id = true; + + build_id__sprintf(self->dso->build_id, + sizeof(self->dso->build_id), + sbuild_id); + pr_debug("build id found for %s: %s\n", self->dso->long_name, + sbuild_id); + } + + if (self->dso->has_build_id) { + u16 misc = PERF_RECORD_MISC_USER; + struct machine *machine; + + misc = self->dso->kernel ? PERF_RECORD_MISC_KERNEL : misc; + + machine = perf_session__find_host_machine(session); + if (!machine) { + pr_err("Can't find machine for session\n"); + return -1; + } + + err = event__synthesize_build_id(self->dso, misc, + event__repipe, machine, + session); + if (err) { + pr_err("Can't synthesize build_id event for %s\n", + name); + return -1; + } + } else { + pr_debug("no build_id found for %s\n", name); + return -1; + } + + return 0; +} + +static int event__inject_buildid(event_t *event, struct perf_session *session) +{ + struct addr_location al; + struct thread *thread; + u8 cpumode; + int err = 0; + + cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + thread = perf_session__findnew(session, event->ip.pid); + if (thread == NULL) { + pr_err("problem processing %d event, skipping it.\n", + event->header.type); + err = -1; + goto repipe; + } + + thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, + event->ip.pid, event->ip.ip, &al); + + if (al.map != NULL) { + if (!al.map->dso->hit) { + al.map->dso->hit = 1; + if (map__load(al.map, NULL) >= 0) + read_buildid(al.map, session); + else + pr_warning("no symbols found in %s, maybe " + "install a debug package?\n", + al.map->dso->long_name); + } + } + +repipe: + event__repipe(event, session); + return err; +} + +struct perf_event_ops inject_ops = { + .sample = event__repipe, + .mmap = event__repipe, + .comm = event__repipe, + .fork = event__repipe, + .exit = event__repipe, + .lost = event__repipe, + .read = event__repipe, + .throttle = event__repipe, + .unthrottle = event__repipe, + .attr = event__repipe, + .event_type = event__repipe, + .tracing_data = event__repipe, + .build_id = event__repipe, +}; + +extern volatile int session_done; + +static void sig_handler(int sig __attribute__((__unused__))) +{ + session_done = 1; +} + +static int __cmd_inject(void) +{ + struct perf_session *session; + int ret = -EINVAL; + + signal(SIGINT, sig_handler); + + if (inject_build_ids) { + inject_ops.sample = event__inject_buildid; + inject_ops.mmap = event__repipe_mmap; + inject_ops.fork = event__repipe_task; + inject_ops.tracing_data = event__repipe_tracing_data; + } + + session = perf_session__new(input_name, O_RDONLY, false, true); + if (session == NULL) + return -ENOMEM; + + ret = perf_session__process_events(session, &inject_ops); + + perf_session__delete(session); + + return ret; +} + +static const char * const report_usage[] = { + "perf inject []", + NULL +}; + +static const struct option options[] = { + OPT_BOOLEAN('b', "inject build-ids", &inject_build_ids, + "Inject build-ids into the output stream"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show build ids, etc)"), + OPT_END() +}; + +int cmd_inject(int argc, const char **argv, const char *prefix __used) +{ + argc = parse_options(argc, argv, options, report_usage, 0); + + /* + * Any (unrecognized) arguments left? + */ + if (argc) + usage_with_options(report_usage, options); + + if (symbol__init() < 0) + return -1; + + return __cmd_inject(); +} diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index ee05dba9609a..31f60a2535e0 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -492,7 +492,7 @@ static void sort_result(void) static int __cmd_kmem(void) { int err = -EINVAL; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ce276750b140..6605000ed73d 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -818,7 +818,7 @@ static struct perf_event_ops eops = { static int read_events(void) { - session = perf_session__new(input_name, O_RDONLY, 0); + session = perf_session__new(input_name, O_RDONLY, 0, false); if (!session) die("Initializing perf session failed\n"); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 1a7379674c29..e382d93d369c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -548,7 +548,7 @@ static int __cmd_record(int argc, const char **argv) } session = perf_session__new(output_name, O_WRONLY, - write_mode == WRITE_FORCE); + write_mode == WRITE_FORCE, false); if (session == NULL) { pr_err("Not enough memory for reading perf file header\n"); return -1; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f1b46eb7ef9a..0152b5412cc3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -289,7 +289,7 @@ static int __cmd_report(void) signal(SIGINT, sig_handler); - session = perf_session__new(input_name, O_RDONLY, force); + session = perf_session__new(input_name, O_RDONLY, force, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 94453f1e4e01..aef6ed0e119c 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1660,7 +1660,7 @@ static struct perf_event_ops event_ops = { static int read_events(void) { int err = -EINVAL; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index c35aa44f82ba..5a52ed9fc10b 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -936,7 +936,7 @@ static struct perf_event_ops event_ops = { static int __cmd_timechart(void) { - struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0); + struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false); int ret = -EINVAL; if (session == NULL) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d95281f588d2..3de397764cb3 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1287,7 +1287,7 @@ static int __cmd_top(void) * FIXME: perf_session__new should allow passing a O_MMAP, so that all this * mmap reading, etc is encapsulated in it. Use O_WRONLY for now. */ - struct perf_session *session = perf_session__new(NULL, O_WRONLY, false); + struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 77f556f7604c..9c483e92e8db 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -661,7 +661,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used) if (!script_name) setup_pager(); - session = perf_session__new(input_name, O_RDONLY, 0); + session = perf_session__new(input_name, O_RDONLY, 0, false); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 34a8a9ab9617..921245b28583 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -34,5 +34,6 @@ extern int cmd_kmem(int argc, const char **argv, const char *prefix); extern int cmd_lock(int argc, const char **argv, const char *prefix); extern int cmd_kvm(int argc, const char **argv, const char *prefix); extern int cmd_test(int argc, const char **argv, const char *prefix); +extern int cmd_inject(int argc, const char **argv, const char *prefix); #endif diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 5ff9b5b46970..08e0e5d2b50e 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -309,6 +309,7 @@ static void handle_internal_command(int argc, const char **argv) { "lock", cmd_lock, 0 }, { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, + { "inject", cmd_inject, 0 }, }; unsigned int i; static const char ext[] = STRIP_EXTENSION; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 2d1d97e0746d..79da0e50ef8f 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -713,10 +713,18 @@ static int __event_process_build_id(struct build_id_event *bev, dso = __dsos__findnew(head, filename); if (dso != NULL) { + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + dso__set_build_id(dso, &bev->build_id); - if (filename[0] == '[') - dso->kernel = dso_type; - } + + if (filename[0] == '[') + dso->kernel = dso_type; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), + sbuild_id); + pr_debug("build id event received for %s: %s\n", + dso->long_name, sbuild_id); + } err = 0; out: @@ -767,7 +775,7 @@ static int perf_file_section__process(struct perf_file_section *self, switch (feat) { case HEADER_TRACE_INFO: - trace_report(fd); + trace_report(fd, false); break; case HEADER_BUILD_ID: @@ -782,12 +790,16 @@ static int perf_file_section__process(struct perf_file_section *self, } static int perf_file_header__read_pipe(struct perf_pipe_file_header *self, - struct perf_header *ph, int fd) + struct perf_header *ph, int fd, + bool repipe) { if (do_read(fd, self, sizeof(*self)) <= 0 || memcmp(&self->magic, __perf_magic, sizeof(self->magic))) return -1; + if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0) + return -1; + if (self->size != sizeof(*self)) { u64 size = bswap_64(self->size); @@ -805,7 +817,8 @@ static int perf_header__read_pipe(struct perf_session *session, int fd) struct perf_header *self = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, self, fd) < 0) { + if (perf_file_header__read_pipe(&f_header, self, fd, + session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } @@ -1096,12 +1109,17 @@ int event__process_tracing_data(event_t *self, lseek(session->fd, offset + sizeof(struct tracing_data_event), SEEK_SET); - size_read = trace_report(session->fd); + size_read = trace_report(session->fd, session->repipe); padding = ALIGN(size_read, sizeof(u64)) - size_read; if (read(session->fd, buf, padding) < 0) die("reading input file"); + if (session->repipe) { + int retw = write(STDOUT_FILENO, buf, padding); + if (retw <= 0 || retw != padding) + die("repiping tracing data padding"); + } if (size_read + padding != size) die("tracing data size mismatch"); @@ -1110,7 +1128,8 @@ int event__process_tracing_data(event_t *self, } int event__synthesize_build_id(struct dso *pos, u16 misc, - event__handler_t process, struct machine *machine, + event__handler_t process, + struct machine *machine, struct perf_session *session) { event_t ev; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a8dd73ed1581..5d353e70fe26 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -77,7 +77,7 @@ int perf_session__create_kernel_maps(struct perf_session *self) return ret; } -struct perf_session *perf_session__new(const char *filename, int mode, bool force) +struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe) { size_t len = filename ? strlen(filename) + 1 : 0; struct perf_session *self = zalloc(sizeof(*self) + len); @@ -97,6 +97,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc self->cwdlen = 0; self->unknown_events = 0; self->machines = RB_ROOT; + self->repipe = repipe; self->ordered_samples.flush_limit = ULLONG_MAX; INIT_LIST_HEAD(&self->ordered_samples.samples_head); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 61ca92e58ad4..f2b2c6a3a49d 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -34,6 +34,7 @@ struct perf_session { u64 sample_type; int fd; bool fd_pipe; + bool repipe; int cwdlen; char *cwd; struct ordered_samples ordered_samples; @@ -59,7 +60,7 @@ struct perf_event_ops { bool ordered_samples; }; -struct perf_session *perf_session__new(const char *filename, int mode, bool force); +struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe); void perf_session__delete(struct perf_session *self); void perf_event_header__bswap(struct perf_event_header *self); diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 44889c9b5630..43f19c1fed3a 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -51,6 +51,7 @@ static int long_size; static unsigned long page_size; static ssize_t calc_data_size; +static bool repipe; static int do_read(int fd, void *buf, int size) { @@ -62,6 +63,13 @@ static int do_read(int fd, void *buf, int size) if (ret <= 0) return -1; + if (repipe) { + int retw = write(STDOUT_FILENO, buf, ret); + + if (retw <= 0 || retw != ret) + die("repiping input file"); + } + size -= ret; buf += ret; } @@ -116,6 +124,13 @@ static char *read_string(void) if (!r) die("no data"); + if (repipe) { + int retw = write(STDOUT_FILENO, &c, 1); + + if (retw <= 0 || retw != r) + die("repiping input file string"); + } + buf[size++] = c; if (!c) @@ -454,7 +469,7 @@ struct record *trace_read_data(int cpu) return data; } -ssize_t trace_report(int fd) +ssize_t trace_report(int fd, bool __repipe) { char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; @@ -465,6 +480,7 @@ ssize_t trace_report(int fd) ssize_t size; calc_data_size = 1; + repipe = __repipe; input_fd = fd; @@ -499,6 +515,7 @@ ssize_t trace_report(int fd) size = calc_data_size - 1; calc_data_size = 0; + repipe = false; if (show_funcs) { print_funcs(); diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 1f45d468fd9a..ebfee80e4a07 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -163,7 +163,7 @@ struct record *trace_read_data(int cpu); void parse_set_info(int nr_cpus, int long_sz); -ssize_t trace_report(int fd); +ssize_t trace_report(int fd, bool repipe); void *malloc_or_die(unsigned int size); -- cgit v1.2.3 From 28e2a106d16046ca792722795f809e3f80a5af80 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2010 13:02:23 -0300 Subject: perf hist: Simplify the insertion of new hist_entry instances MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit And with that fix at least one bug: The first hit for an entry, the one that calls malloc to create a new instance in __perf_session__add_hist_entry, wasn't adding the count to the per cpumode (PERF_RECORD_MISC_USER, etc) total variable. Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 9 +++------ tools/perf/builtin-diff.c | 14 +++----------- tools/perf/builtin-report.c | 12 ++---------- tools/perf/util/hist.c | 36 +++++++++++++++++++++++------------- tools/perf/util/hist.h | 5 +---- 5 files changed, 32 insertions(+), 44 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ee154b58772b..c7ac45a59ed5 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -72,8 +72,6 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip) struct sym_priv *priv; struct sym_hist *h; - he->count++; - if (!sym || !he->ms.map) return 0; @@ -99,9 +97,8 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip) } static int perf_session__add_hist_entry(struct perf_session *self, - struct addr_location *al, u64 count) + struct addr_location *al) { - bool hit; struct hist_entry *he; if (sym_hist_filter != NULL && @@ -115,7 +112,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return 0; } - he = __perf_session__add_hist_entry(&self->hists, al, NULL, count, &hit); + he = __perf_session__add_hist_entry(&self->hists, al, NULL, 1); if (he == NULL) return -ENOMEM; @@ -135,7 +132,7 @@ static int process_sample_event(event_t *event, struct perf_session *session) return -1; } - if (!al.filtered && perf_session__add_hist_entry(session, &al, 1)) { + if (!al.filtered && perf_session__add_hist_entry(session, &al)) { pr_warning("problem incrementing symbol count, " "skipping event\n"); return -1; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 4cce68f23686..613a5c4f6d83 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -25,17 +25,9 @@ static bool show_displacement; static int perf_session__add_hist_entry(struct perf_session *self, struct addr_location *al, u64 count) { - bool hit; - struct hist_entry *he = __perf_session__add_hist_entry(&self->hists, - al, NULL, - count, &hit); - if (he == NULL) - return -ENOMEM; - - if (hit) - __perf_session__add_count(he, al, count); - - return 0; + if (__perf_session__add_hist_entry(&self->hists, al, NULL, count) != NULL) + return 0; + return -ENOMEM; } static int diff__process_sample_event(event_t *event, struct perf_session *session) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3a70c5807c04..5e2f47f88ec6 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -82,7 +82,6 @@ static int perf_session__add_hist_entry(struct perf_session *self, { struct map_symbol *syms = NULL; struct symbol *parent = NULL; - bool hit; int err = -ENOMEM; struct hist_entry *he; struct event_stat_id *stats; @@ -103,19 +102,12 @@ static int perf_session__add_hist_entry(struct perf_session *self, if (stats == NULL) goto out_free_syms; he = __perf_session__add_hist_entry(&stats->hists, al, parent, - data->period, &hit); + data->period); if (he == NULL) goto out_free_syms; - - if (hit) - __perf_session__add_count(he, al, data->period); - err = 0; - if (symbol_conf.use_callchain) { - if (!hit) - callchain_init(he->callchain); + if (symbol_conf.use_callchain) err = append_chain(he->callchain, data->callchain, syms); - } out_free_syms: free(syms); return err; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index ad6b22dde27f..e0c8a722e11f 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -8,13 +8,10 @@ struct callchain_param callchain_param = { .min_percent = 0.5 }; -void __perf_session__add_count(struct hist_entry *he, - struct addr_location *al, - u64 count) +static void perf_session__add_cpumode_count(struct hist_entry *he, + unsigned int cpumode, u64 count) { - he->count += count; - - switch (al->cpumode) { + switch (cpumode) { case PERF_RECORD_MISC_KERNEL: he->count_sys += count; break; @@ -36,10 +33,24 @@ void __perf_session__add_count(struct hist_entry *he, * histogram, sorted on item, collects counts */ +static struct hist_entry *hist_entry__new(struct hist_entry *template) +{ + size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0; + struct hist_entry *self = malloc(sizeof(*self) + callchain_size); + + if (self != NULL) { + *self = *template; + if (symbol_conf.use_callchain) + callchain_init(self->callchain); + } + + return self; +} + struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, struct addr_location *al, struct symbol *sym_parent, - u64 count, bool *hit) + u64 count) { struct rb_node **p = &hists->rb_node; struct rb_node *parent = NULL; @@ -64,8 +75,8 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, cmp = hist_entry__cmp(&entry, he); if (!cmp) { - *hit = true; - return he; + he->count += count; + goto out; } if (cmp < 0) @@ -74,14 +85,13 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, p = &(*p)->rb_right; } - he = malloc(sizeof(*he) + (symbol_conf.use_callchain ? - sizeof(struct callchain_node) : 0)); + he = hist_entry__new(&entry); if (!he) return NULL; - *he = entry; rb_link_node(&he->rb_node, parent, p); rb_insert_color(&he->rb_node, hists); - *hit = false; +out: + perf_session__add_cpumode_count(he, al->cpumode, count); return he; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 9df1c340ec92..b49013adb34b 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -12,13 +12,10 @@ struct addr_location; struct symbol; struct rb_root; -void __perf_session__add_count(struct hist_entry *he, - struct addr_location *al, - u64 count); struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, struct addr_location *al, struct symbol *parent, - u64 count, bool *hit); + u64 count); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); int hist_entry__fprintf(struct hist_entry *self, -- cgit v1.2.3 From 1c02c4d2e92f2097f1bba63ec71560b0e05a7f36 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 May 2010 13:04:11 -0300 Subject: perf hist: Introduce hists class and move lots of methods to it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In cbbc79a we introduced support for multiple events by introducing a new "event_stat_id" struct and then made several perf_session methods receive a point to it instead of a pointer to perf_session, and kept the event_stats and hists rb_tree in perf_session. While working on the new newt based browser, I realised that it would be better to introduce a new class, "hists" (short for "histograms"), renaming the "event_stat_id" struct and the perf_session methods that were really "hists" methods, as they manipulate only struct hists members, not touching anything in the other perf_session members. Other optimizations, such as calculating the maximum lenght of a symbol name present in an hists instance will be possible as we add them, avoiding a re-traversal just for finding that information. The rationale for the name "hists" to replace "event_stat_id" is that we may have multiple sets of hists for the same event_stat id, as, for instance, the 'perf diff' tool has, so event stat id is not what characterizes what this struct and the functions that manipulate it do. Cc: Eric B Munson Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 17 ++++---- tools/perf/builtin-diff.c | 50 +++++++++++------------ tools/perf/builtin-report.c | 71 ++++++++++++++++----------------- tools/perf/builtin-trace.c | 2 +- tools/perf/util/event.c | 2 +- tools/perf/util/event.h | 14 ------- tools/perf/util/hist.c | 92 +++++++++++++++++++------------------------ tools/perf/util/hist.h | 48 ++++++++++++---------- tools/perf/util/session.c | 2 +- tools/perf/util/session.h | 12 ++++-- 10 files changed, 146 insertions(+), 164 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index c7ac45a59ed5..3940964161b3 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -96,8 +96,7 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip) return 0; } -static int perf_session__add_hist_entry(struct perf_session *self, - struct addr_location *al) +static int hists__add_entry(struct hists *self, struct addr_location *al) { struct hist_entry *he; @@ -112,7 +111,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return 0; } - he = __perf_session__add_hist_entry(&self->hists, al, NULL, 1); + he = __hists__add_entry(self, al, NULL, 1); if (he == NULL) return -ENOMEM; @@ -132,7 +131,7 @@ static int process_sample_event(event_t *event, struct perf_session *session) return -1; } - if (!al.filtered && perf_session__add_hist_entry(session, &al)) { + if (!al.filtered && hists__add_entry(&session->hists, &al)) { pr_warning("problem incrementing symbol count, " "skipping event\n"); return -1; @@ -514,11 +513,11 @@ static void annotate_sym(struct hist_entry *he) free_source_line(he, len); } -static void perf_session__find_annotations(struct perf_session *self) +static void hists__find_annotations(struct hists *self) { struct rb_node *nd; - for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) { + for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); struct sym_priv *priv; @@ -570,9 +569,9 @@ static int __cmd_annotate(void) if (verbose > 2) perf_session__fprintf_dsos(session, stdout); - perf_session__collapse_resort(&session->hists); - perf_session__output_resort(&session->hists, session->event_total[0]); - perf_session__find_annotations(session); + hists__collapse_resort(&session->hists); + hists__output_resort(&session->hists); + hists__find_annotations(&session->hists); out_delete: perf_session__delete(session); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 613a5c4f6d83..3a95a0260a5b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -22,10 +22,10 @@ static char diff__default_sort_order[] = "dso,symbol"; static bool force; static bool show_displacement; -static int perf_session__add_hist_entry(struct perf_session *self, - struct addr_location *al, u64 count) +static int hists__add_entry(struct hists *self, + struct addr_location *al, u64 count) { - if (__perf_session__add_hist_entry(&self->hists, al, NULL, count) != NULL) + if (__hists__add_entry(self, al, NULL, count) != NULL) return 0; return -ENOMEM; } @@ -49,12 +49,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi event__parse_sample(event, session->sample_type, &data); - if (perf_session__add_hist_entry(session, &al, data.period)) { + if (hists__add_entry(&session->hists, &al, data.period)) { pr_warning("problem incrementing symbol count, skipping event\n"); return -1; } - session->events_stats.total += data.period; + session->hists.stats.total += data.period; return 0; } @@ -87,35 +87,34 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root, rb_insert_color(&he->rb_node, root); } -static void perf_session__resort_hist_entries(struct perf_session *self) +static void hists__resort_entries(struct hists *self) { unsigned long position = 1; struct rb_root tmp = RB_ROOT; - struct rb_node *next = rb_first(&self->hists); + struct rb_node *next = rb_first(&self->entries); while (next != NULL) { struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, &self->hists); + rb_erase(&n->rb_node, &self->entries); n->position = position++; perf_session__insert_hist_entry_by_name(&tmp, n); } - self->hists = tmp; + self->entries = tmp; } -static void perf_session__set_hist_entries_positions(struct perf_session *self) +static void hists__set_positions(struct hists *self) { - perf_session__output_resort(&self->hists, self->events_stats.total); - perf_session__resort_hist_entries(self); + hists__output_resort(self); + hists__resort_entries(self); } -static struct hist_entry * -perf_session__find_hist_entry(struct perf_session *self, - struct hist_entry *he) +static struct hist_entry *hists__find_entry(struct hists *self, + struct hist_entry *he) { - struct rb_node *n = self->hists.rb_node; + struct rb_node *n = self->entries.rb_node; while (n) { struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node); @@ -132,14 +131,13 @@ perf_session__find_hist_entry(struct perf_session *self, return NULL; } -static void perf_session__match_hists(struct perf_session *old_session, - struct perf_session *new_session) +static void hists__match(struct hists *older, struct hists *newer) { struct rb_node *nd; - for (nd = rb_first(&new_session->hists); nd; nd = rb_next(nd)) { + for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) { struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node); - pos->pair = perf_session__find_hist_entry(old_session, pos); + pos->pair = hists__find_entry(older, pos); } } @@ -159,15 +157,13 @@ static int __cmd_diff(void) goto out_delete; } - perf_session__output_resort(&session[1]->hists, - session[1]->events_stats.total); + hists__output_resort(&session[1]->hists); if (show_displacement) - perf_session__set_hist_entries_positions(session[0]); + hists__set_positions(&session[0]->hists); - perf_session__match_hists(session[0], session[1]); - perf_session__fprintf_hists(&session[1]->hists, session[0], - show_displacement, stdout, - session[1]->events_stats.total); + hists__match(&session[0]->hists, &session[1]->hists); + hists__fprintf(&session[1]->hists, &session[0]->hists, + show_displacement, stdout); out_delete: for (i = 0; i < 2; ++i) perf_session__delete(session[i]); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 642a6d8eb5dc..53077fd973f0 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -44,16 +44,17 @@ static char *pretty_printing_style = default_pretty_printing_style; static char callchain_default_opt[] = "fractal,0.5"; -static struct event_stat_id *get_stats(struct perf_session *self, - u64 event_stream, u32 type, u64 config) +static struct hists *perf_session__hists_findnew(struct perf_session *self, + u64 event_stream, u32 type, + u64 config) { - struct rb_node **p = &self->stats_by_id.rb_node; + struct rb_node **p = &self->hists_tree.rb_node; struct rb_node *parent = NULL; - struct event_stat_id *iter, *new; + struct hists *iter, *new; while (*p != NULL) { parent = *p; - iter = rb_entry(parent, struct event_stat_id, rb_node); + iter = rb_entry(parent, struct hists, rb_node); if (iter->config == config) return iter; @@ -64,15 +65,15 @@ static struct event_stat_id *get_stats(struct perf_session *self, p = &(*p)->rb_left; } - new = malloc(sizeof(struct event_stat_id)); + new = malloc(sizeof(struct hists)); if (new == NULL) return NULL; - memset(new, 0, sizeof(struct event_stat_id)); + memset(new, 0, sizeof(struct hists)); new->event_stream = event_stream; new->config = config; new->type = type; rb_link_node(&new->rb_node, parent, p); - rb_insert_color(&new->rb_node, &self->stats_by_id); + rb_insert_color(&new->rb_node, &self->hists_tree); return new; } @@ -84,7 +85,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, struct symbol *parent = NULL; int err = -ENOMEM; struct hist_entry *he; - struct event_stat_id *stats; + struct hists *hists; struct perf_event_attr *attr; if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) { @@ -96,13 +97,12 @@ static int perf_session__add_hist_entry(struct perf_session *self, attr = perf_header__find_attr(data->id, &self->header); if (attr) - stats = get_stats(self, data->id, attr->type, attr->config); + hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config); else - stats = get_stats(self, data->id, 0, 0); - if (stats == NULL) + hists = perf_session__hists_findnew(self, data->id, 0, 0); + if (hists == NULL) goto out_free_syms; - he = __perf_session__add_hist_entry(&stats->hists, al, parent, - data->period); + he = __hists__add_entry(hists, al, parent, data->period); if (he == NULL) goto out_free_syms; err = 0; @@ -117,18 +117,19 @@ static int add_event_total(struct perf_session *session, struct sample_data *data, struct perf_event_attr *attr) { - struct event_stat_id *stats; + struct hists *hists; if (attr) - stats = get_stats(session, data->id, attr->type, attr->config); + hists = perf_session__hists_findnew(session, data->id, + attr->type, attr->config); else - stats = get_stats(session, data->id, 0, 0); + hists = perf_session__hists_findnew(session, data->id, 0, 0); - if (!stats) + if (!hists) return -ENOMEM; - stats->stats.total += data->period; - session->events_stats.total += data->period; + hists->stats.total += data->period; + session->hists.stats.total += data->period; return 0; } @@ -292,35 +293,33 @@ static int __cmd_report(void) if (verbose > 2) perf_session__fprintf_dsos(session, stdout); - next = rb_first(&session->stats_by_id); + next = rb_first(&session->hists_tree); while (next) { - struct event_stat_id *stats; + struct hists *hists; u64 nr_hists; - stats = rb_entry(next, struct event_stat_id, rb_node); - perf_session__collapse_resort(&stats->hists); - nr_hists = perf_session__output_resort(&stats->hists, - stats->stats.total); + hists = rb_entry(next, struct hists, rb_node); + hists__collapse_resort(hists); + nr_hists = hists__output_resort(hists); if (use_browser) - perf_session__browse_hists(&stats->hists, nr_hists, - stats->stats.total, help, + perf_session__browse_hists(&hists->entries, nr_hists, + hists->stats.total, help, input_name); else { - if (rb_first(&session->stats_by_id) == - rb_last(&session->stats_by_id)) + if (rb_first(&session->hists.entries) == + rb_last(&session->hists.entries)) fprintf(stdout, "# Samples: %Ld\n#\n", - stats->stats.total); + hists->stats.total); else fprintf(stdout, "# Samples: %Ld %s\n#\n", - stats->stats.total, - __event_name(stats->type, stats->config)); + hists->stats.total, + __event_name(hists->type, hists->config)); - perf_session__fprintf_hists(&stats->hists, NULL, false, stdout, - stats->stats.total); + hists__fprintf(hists, NULL, false, stdout); fprintf(stdout, "\n\n"); } - next = rb_next(&stats->rb_node); + next = rb_next(&hists->rb_node); } if (!use_browser && sort_order == default_sort_order && diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 9c483e92e8db..6e268ca761e9 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -107,7 +107,7 @@ static int process_sample_event(event_t *event, struct perf_session *session) data.time, thread->comm); } - session->events_stats.total += data.period; + session->hists.stats.total += data.period; return 0; } diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index d2ea9dd9fdf1..cce006ec8f05 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -368,7 +368,7 @@ int event__process_comm(event_t *self, struct perf_session *session) int event__process_lost(event_t *self, struct perf_session *session) { dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost); - session->events_stats.lost += self->lost.lost; + session->hists.stats.lost += self->lost.lost; return 0; } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6cc1b1dced55..48c2cc9dae4f 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -131,20 +131,6 @@ typedef union event_union { struct build_id_event build_id; } event_t; -struct events_stats { - u64 total; - u64 lost; -}; - -struct event_stat_id { - struct rb_node rb_node; - struct rb_root hists; - struct events_stats stats; - u64 config; - u64 event_stream; - u32 type; -}; - void event__print_totals(void); struct perf_session; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0f154a530dfd..410cf56c9662 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -8,21 +8,21 @@ struct callchain_param callchain_param = { .min_percent = 0.5 }; -static void perf_session__add_cpumode_count(struct hist_entry *he, - unsigned int cpumode, u64 count) +static void hist_entry__add_cpumode_count(struct hist_entry *self, + unsigned int cpumode, u64 count) { switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - he->count_sys += count; + self->count_sys += count; break; case PERF_RECORD_MISC_USER: - he->count_us += count; + self->count_us += count; break; case PERF_RECORD_MISC_GUEST_KERNEL: - he->count_guest_sys += count; + self->count_guest_sys += count; break; case PERF_RECORD_MISC_GUEST_USER: - he->count_guest_us += count; + self->count_guest_us += count; break; default: break; @@ -47,12 +47,11 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return self; } -struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, - struct addr_location *al, - struct symbol *sym_parent, - u64 count) +struct hist_entry *__hists__add_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, u64 count) { - struct rb_node **p = &hists->rb_node; + struct rb_node **p = &self->entries.rb_node; struct rb_node *parent = NULL; struct hist_entry *he; struct hist_entry entry = { @@ -89,9 +88,9 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, if (!he) return NULL; rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, hists); + rb_insert_color(&he->rb_node, &self->entries); out: - perf_session__add_cpumode_count(he, al->cpumode, count); + hist_entry__add_cpumode_count(he, al->cpumode, count); return he; } @@ -167,7 +166,7 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he) rb_insert_color(&he->rb_node, root); } -void perf_session__collapse_resort(struct rb_root *hists) +void hists__collapse_resort(struct hists *self) { struct rb_root tmp; struct rb_node *next; @@ -177,28 +176,28 @@ void perf_session__collapse_resort(struct rb_root *hists) return; tmp = RB_ROOT; - next = rb_first(hists); + next = rb_first(&self->entries); while (next) { n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, hists); + rb_erase(&n->rb_node, &self->entries); collapse__insert_entry(&tmp, n); } - *hists = tmp; + self->entries = tmp; } /* * reverse the map, sort on count. */ -static void perf_session__insert_output_hist_entry(struct rb_root *root, - struct hist_entry *he, - u64 min_callchain_hits) +static void __hists__insert_output_entry(struct rb_root *entries, + struct hist_entry *he, + u64 min_callchain_hits) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &entries->rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; @@ -217,10 +216,10 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root, } rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + rb_insert_color(&he->rb_node, entries); } -u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples) +u64 hists__output_resort(struct hists *self) { struct rb_root tmp; struct rb_node *next; @@ -228,23 +227,21 @@ u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples) u64 min_callchain_hits; u64 nr_hists = 0; - min_callchain_hits = - total_samples * (callchain_param.min_percent / 100); + min_callchain_hits = self->stats.total * (callchain_param.min_percent / 100); tmp = RB_ROOT; - next = rb_first(hists); + next = rb_first(&self->entries); while (next) { n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, hists); - perf_session__insert_output_hist_entry(&tmp, n, - min_callchain_hits); + rb_erase(&n->rb_node, &self->entries); + __hists__insert_output_entry(&tmp, n, min_callchain_hits); ++nr_hists; } - *hists = tmp; + self->entries = tmp; return nr_hists; } @@ -500,12 +497,9 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, return ret; } -int hist_entry__snprintf(struct hist_entry *self, - char *s, size_t size, - struct perf_session *pair_session, - bool show_displacement, - long displacement, bool color, - u64 session_total) +int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, + struct hists *pair_hists, bool show_displacement, + long displacement, bool color, u64 session_total) { struct sort_entry *se; u64 count, total, count_sys, count_us, count_guest_sys, count_guest_us; @@ -515,9 +509,9 @@ int hist_entry__snprintf(struct hist_entry *self, if (symbol_conf.exclude_other && !self->parent) return 0; - if (pair_session) { + if (pair_hists) { count = self->pair ? self->pair->count : 0; - total = pair_session->events_stats.total; + total = pair_hists->stats.total; count_sys = self->pair ? self->pair->count_sys : 0; count_us = self->pair ? self->pair->count_us : 0; count_guest_sys = self->pair ? self->pair->count_guest_sys : 0; @@ -569,7 +563,7 @@ int hist_entry__snprintf(struct hist_entry *self, ret += snprintf(s + ret, size - ret, "%11lld", count); } - if (pair_session) { + if (pair_hists) { char bf[32]; double old_percent = 0, new_percent = 0, diff; @@ -615,14 +609,12 @@ int hist_entry__snprintf(struct hist_entry *self, return ret; } -int hist_entry__fprintf(struct hist_entry *self, - struct perf_session *pair_session, - bool show_displacement, - long displacement, FILE *fp, +int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists, + bool show_displacement, long displacement, FILE *fp, u64 session_total) { char bf[512]; - hist_entry__snprintf(self, bf, sizeof(bf), pair_session, + hist_entry__snprintf(self, bf, sizeof(bf), pair_hists, show_displacement, displacement, true, session_total); return fprintf(fp, "%s\n", bf); @@ -644,10 +636,8 @@ static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp, left_margin); } -size_t perf_session__fprintf_hists(struct rb_root *hists, - struct perf_session *pair, - bool show_displacement, FILE *fp, - u64 session_total) +size_t hists__fprintf(struct hists *self, struct hists *pair, + bool show_displacement, FILE *fp) { struct sort_entry *se; struct rb_node *nd; @@ -753,7 +743,7 @@ size_t perf_session__fprintf_hists(struct rb_root *hists, fprintf(fp, "\n#\n"); print_entries: - for (nd = rb_first(hists); nd; nd = rb_next(nd)) { + for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (show_displacement) { @@ -765,10 +755,10 @@ print_entries: ++position; } ret += hist_entry__fprintf(h, pair, show_displacement, - displacement, fp, session_total); + displacement, fp, self->stats.total); if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, fp, session_total); + ret += hist_entry__fprintf_callchain(h, fp, self->stats.total); if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index b49013adb34b..bdde81eca69f 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -6,34 +6,40 @@ extern struct callchain_param callchain_param; -struct perf_session; struct hist_entry; struct addr_location; struct symbol; struct rb_root; -struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, - struct addr_location *al, - struct symbol *parent, - u64 count); +struct events_stats { + u64 total; + u64 lost; +}; + +struct hists { + struct rb_node rb_node; + struct rb_root entries; + struct events_stats stats; + u64 config; + u64 event_stream; + u32 type; +}; + +struct hist_entry *__hists__add_entry(struct hists *self, + struct addr_location *al, + struct symbol *parent, u64 count); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); -int hist_entry__fprintf(struct hist_entry *self, - struct perf_session *pair_session, - bool show_displacement, - long displacement, FILE *fp, - u64 session_total); -int hist_entry__snprintf(struct hist_entry *self, - char *bf, size_t size, - struct perf_session *pair_session, - bool show_displacement, long displacement, - bool color, u64 session_total); +int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists, + bool show_displacement, long displacement, FILE *fp, + u64 total); +int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size, + struct hists *pair_hists, bool show_displacement, + long displacement, bool color, u64 total); void hist_entry__free(struct hist_entry *); -u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples); -void perf_session__collapse_resort(struct rb_root *hists); -size_t perf_session__fprintf_hists(struct rb_root *hists, - struct perf_session *pair, - bool show_displacement, FILE *fp, - u64 session_total); +u64 hists__output_resort(struct hists *self); +void hists__collapse_resort(struct hists *self); +size_t hists__fprintf(struct hists *self, struct hists *pair, + bool show_displacement, FILE *fp); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 4130036a0109..72a7f6ae0293 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -89,7 +89,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc memcpy(self->filename, filename, len); self->threads = RB_ROOT; - self->stats_by_id = RB_ROOT; + self->hists_tree = RB_ROOT; self->last_match = NULL; self->mmap_window = 32; self->cwd = NULL; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 242d528bfae2..46190f94b547 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -1,6 +1,7 @@ #ifndef __PERF_SESSION_H #define __PERF_SESSION_H +#include "hist.h" #include "event.h" #include "header.h" #include "symbol.h" @@ -28,11 +29,16 @@ struct perf_session { struct thread *last_match; struct machine host_machine; struct rb_root machines; - struct events_stats events_stats; - struct rb_root stats_by_id; + struct rb_root hists_tree; unsigned long event_total[PERF_RECORD_MAX]; unsigned long unknown_events; - struct rb_root hists; + /* + * FIXME: should point to the first entry in hists_tree and + * be a hists instance. Right now its only 'report' + * that is using ->hists_tree while all the rest use + * ->hists. + */ + struct hists hists; u64 sample_type; int fd; bool fd_pipe; -- cgit v1.2.3 From cee75ac7ecc27084accdb9d9d6fde65a09f047ae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 May 2010 13:16:55 -0300 Subject: perf hist: Clarify events_stats fields usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The events_stats.total field is too generic, rename it to .total_period, and also add a comment explaining that it is the sum of all the .period fields in samples, that is needed because we use auto-freq to avoid sampling artifacts. Ditto for events_stats.lost, that is the sum of all lost_event.lost fields, i.e. the number of events the kernel dropped. Looking at the users, builtin-sched.c can make use of these fields and stop doing it again. Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-report.c | 8 ++++---- tools/perf/builtin-sched.c | 17 ++++++----------- tools/perf/builtin-trace.c | 2 +- tools/perf/util/event.c | 2 +- tools/perf/util/hist.c | 20 ++++++++++---------- tools/perf/util/hist.h | 16 ++++++++++++++-- tools/perf/util/newt.c | 6 +++--- tools/perf/util/session.c | 2 +- 9 files changed, 41 insertions(+), 34 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 3a95a0260a5b..6dd4bdae8a87 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -54,7 +54,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi return -1; } - session->hists.stats.total += data.period; + session->hists.stats.total_period += data.period; return 0; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f13cda1ef059..b8f47ded6287 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -138,14 +138,14 @@ static int add_event_total(struct perf_session *session, if (!hists) return -ENOMEM; - hists->stats.total += data->period; + hists->stats.total_period += data->period; /* * FIXME: add_event_total should be moved from here to * perf_session__process_event so that the proper hist is passed to * the event_op methods. */ hists__inc_nr_events(hists, PERF_RECORD_SAMPLE); - session->hists.stats.total += data->period; + session->hists.stats.total_period += data->period; return 0; } @@ -322,10 +322,10 @@ static int __cmd_report(void) if (rb_first(&session->hists.entries) == rb_last(&session->hists.entries)) fprintf(stdout, "# Samples: %Ld\n#\n", - hists->stats.total); + hists->stats.total_period); else fprintf(stdout, "# Samples: %Ld %s\n#\n", - hists->stats.total, + hists->stats.total_period, __event_name(hists->type, hists->config)); hists__fprintf(hists, NULL, false, stdout); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index aef6ed0e119c..be7bc9264710 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1641,19 +1641,10 @@ static int process_sample_event(event_t *event, struct perf_session *session) return 0; } -static int process_lost_event(event_t *event __used, - struct perf_session *session __used) -{ - nr_lost_chunks++; - nr_lost_events += event->lost.lost; - - return 0; -} - static struct perf_event_ops event_ops = { .sample = process_sample_event, .comm = event__process_comm, - .lost = process_lost_event, + .lost = event__process_lost, .ordered_samples = true, }; @@ -1664,8 +1655,12 @@ static int read_events(void) if (session == NULL) return -ENOMEM; - if (perf_session__has_traces(session, "record -R")) + if (perf_session__has_traces(session, "record -R")) { err = perf_session__process_events(session, &event_ops); + nr_events = session->hists.stats.nr_events[0]; + nr_lost_events = session->hists.stats.total_lost; + nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST]; + } perf_session__delete(session); return err; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 95fcb0517a9d..dddf3f01b5ab 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -109,7 +109,7 @@ static int process_sample_event(event_t *event, struct perf_session *session) data.time, thread->comm); } - session->hists.stats.total += data.period; + session->hists.stats.total_period += data.period; return 0; } diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 3e8fec173041..50771b5813ee 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -385,7 +385,7 @@ int event__process_comm(event_t *self, struct perf_session *session) int event__process_lost(event_t *self, struct perf_session *session) { dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost); - session->hists.stats.lost += self->lost.lost; + session->hists.stats.total_lost += self->lost.lost; return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 1614ad710046..c59224518083 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -239,7 +239,7 @@ void hists__output_resort(struct hists *self) struct hist_entry *n; u64 min_callchain_hits; - min_callchain_hits = self->stats.total * (callchain_param.min_percent / 100); + min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100); tmp = RB_ROOT; next = rb_first(&self->entries); @@ -525,7 +525,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, if (pair_hists) { count = self->pair ? self->pair->count : 0; - total = pair_hists->stats.total; + total = pair_hists->stats.total_period; count_sys = self->pair ? self->pair->count_sys : 0; count_us = self->pair ? self->pair->count_us : 0; count_guest_sys = self->pair ? self->pair->count_guest_sys : 0; @@ -769,10 +769,10 @@ print_entries: ++position; } ret += hist_entry__fprintf(h, pair, show_displacement, - displacement, fp, self->stats.total); + displacement, fp, self->stats.total_period); if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, fp, self->stats.total); + ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period); if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, @@ -795,7 +795,7 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) { struct rb_node *nd; - self->nr_entries = self->stats.total = 0; + self->nr_entries = self->stats.total_period = 0; self->max_sym_namelen = 0; for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { @@ -812,7 +812,7 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) h->filtered &= ~(1 << HIST_FILTER__DSO); if (!h->filtered) { ++self->nr_entries; - self->stats.total += h->count; + self->stats.total_period += h->count; if (h->ms.sym && self->max_sym_namelen < h->ms.sym->namelen) self->max_sym_namelen = h->ms.sym->namelen; @@ -824,7 +824,7 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) { struct rb_node *nd; - self->nr_entries = self->stats.total = 0; + self->nr_entries = self->stats.total_period = 0; self->max_sym_namelen = 0; for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { @@ -837,7 +837,7 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) h->filtered &= ~(1 << HIST_FILTER__THREAD); if (!h->filtered) { ++self->nr_entries; - self->stats.total += h->count; + self->stats.total_period += h->count; if (h->ms.sym && self->max_sym_namelen < h->ms.sym->namelen) self->max_sym_namelen = h->ms.sym->namelen; @@ -1031,8 +1031,8 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head) void hists__inc_nr_events(struct hists *self, u32 type) { - ++self->hists.stats.nr_events[0]; - ++self->hists.stats.nr_events[type]; + ++self->stats.nr_events[0]; + ++self->stats.nr_events[type]; } size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 97b8962ff69a..da6b84814a50 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -37,9 +37,21 @@ struct sym_priv { struct sym_ext *ext; }; +/* + * The kernel collects the number of events it couldn't send in a stretch and + * when possible sends this number in a PERF_RECORD_LOST event. The number of + * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while + * total_lost tells exactly how many events the kernel in fact lost, i.e. it is + * the sum of all struct lost_event.lost fields reported. + * + * The total_period is needed because by default auto-freq is used, so + * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get + * the total number of low level events, it is necessary to to sum all struct + * sample_event.period and stash the result in total_period. + */ struct events_stats { - u64 total; - u64 lost; + u64 total_period; + u64 total_lost; u32 nr_events[PERF_RECORD_HEADER_MAX]; u32 nr_unknown_events; }; diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c index ba6acd04c082..010bacf40163 100644 --- a/tools/perf/util/newt.c +++ b/tools/perf/util/newt.c @@ -689,7 +689,7 @@ static int hist_browser__populate(struct hist_browser *self, struct hists *hists } snprintf(str, sizeof(str), "Samples: %Ld ", - hists->stats.total); + hists->stats.total_period); newtDrawRootText(0, 0, str); newtGetScreenSize(NULL, &rows); @@ -718,12 +718,12 @@ static int hist_browser__populate(struct hist_browser *self, struct hists *hists if (h->filtered) continue; - len = hist_entry__append_browser(h, self->tree, hists->stats.total); + len = hist_entry__append_browser(h, self->tree, hists->stats.total_period); if (len > max_len) max_len = len; if (symbol_conf.use_callchain) hist_entry__append_callchain_browser(h, self->tree, - hists->stats.total, idx++); + hists->stats.total_period, idx++); ++curr_hist; if (curr_hist % 5) ui_progress__update(progress, curr_hist); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7231f6b19fb4..25bfca4f10f0 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -549,7 +549,7 @@ static int perf_session__process_event(struct perf_session *self, dump_printf("%#Lx [%#x]: PERF_RECORD_%s", offset + head, event->header.size, event__name[event->header.type]); - hists__inc_nr_events(self, event->header.type); + hists__inc_nr_events(&self->hists, event->header.type); } if (self->header.needs_swap && event__swap_ops[event->header.type]) -- cgit v1.2.3 From c82ee828aa20487d254a5225d256cd422acee459 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 May 2010 14:19:35 -0300 Subject: perf report: Report number of events, not samples MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Number of samples is meaningless after we switched to auto-freq, so report the number of events, i.e. not the sum of the different periods, but the number PERF_RECORD_SAMPLE emitted by the kernel. While doing this I noticed that naming "count" to the sum of all the event periods can be confusing, so rename it to .period, just like in struct sample.data, so that we become more consistent. This helps with the next step, that was to record in struct hist_entry the number of sample events for each instance, we need that because we use it to generate the number of events when applying filters to the tree of hist entries like it is being done in the TUI report browser. Suggested-by: Ingo Molnar Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 6 ++-- tools/perf/builtin-report.c | 32 +++++++++++------ tools/perf/util/hist.c | 88 ++++++++++++++++++++++++--------------------- tools/perf/util/hist.h | 2 +- tools/perf/util/newt.c | 8 +++-- tools/perf/util/sort.h | 11 +++--- tools/perf/util/util.c | 22 ++++++++++++ tools/perf/util/util.h | 1 + 8 files changed, 107 insertions(+), 63 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 6dd4bdae8a87..a6e2fdc7a04e 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -23,9 +23,9 @@ static bool force; static bool show_displacement; static int hists__add_entry(struct hists *self, - struct addr_location *al, u64 count) + struct addr_location *al, u64 period) { - if (__hists__add_entry(self, al, NULL, count) != NULL) + if (__hists__add_entry(self, al, NULL, period) != NULL) return 0; return -ENOMEM; } @@ -50,7 +50,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi event__parse_sample(event, session->sample_type, &data); if (hists__add_entry(&session->hists, &al, data.period)) { - pr_warning("problem incrementing symbol count, skipping event\n"); + pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b8f47ded6287..68265120ee07 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -188,14 +188,14 @@ static int process_sample_event(event_t *event, struct perf_session *session) return 0; if (perf_session__add_hist_entry(session, &al, &data)) { - pr_debug("problem incrementing symbol count, skipping event\n"); + pr_debug("problem incrementing symbol period, skipping event\n"); return -1; } attr = perf_header__find_attr(data.id, &session->header); if (add_event_total(session, &data, attr)) { - pr_debug("problem adding event count\n"); + pr_debug("problem adding event period\n"); return -1; } @@ -269,11 +269,25 @@ static struct perf_event_ops event_ops = { extern volatile int session_done; -static void sig_handler(int sig __attribute__((__unused__))) +static void sig_handler(int sig __used) { session_done = 1; } +static size_t hists__fprintf_nr_sample_events(struct hists *self, + const char *evname, FILE *fp) +{ + size_t ret; + char unit; + unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE]; + + nr_events = convert_unit(nr_events, &unit); + ret = fprintf(fp, "# Events: %lu%c", nr_events, unit); + if (evname != NULL) + ret += fprintf(fp, " %s", evname); + return ret + fprintf(fp, "\n#\n"); +} + static int __cmd_report(void) { int ret = -EINVAL; @@ -319,14 +333,12 @@ static int __cmd_report(void) if (use_browser) hists__browse(hists, help, input_name); else { - if (rb_first(&session->hists.entries) == + const char *evname = NULL; + if (rb_first(&session->hists.entries) != rb_last(&session->hists.entries)) - fprintf(stdout, "# Samples: %Ld\n#\n", - hists->stats.total_period); - else - fprintf(stdout, "# Samples: %Ld %s\n#\n", - hists->stats.total_period, - __event_name(hists->type, hists->config)); + evname = __event_name(hists->type, hists->config); + + hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, NULL, false, stdout); fprintf(stdout, "\n\n"); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c59224518083..f75c5f62401c 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -9,21 +9,21 @@ struct callchain_param callchain_param = { .min_percent = 0.5 }; -static void hist_entry__add_cpumode_count(struct hist_entry *self, - unsigned int cpumode, u64 count) +static void hist_entry__add_cpumode_period(struct hist_entry *self, + unsigned int cpumode, u64 period) { switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - self->count_sys += count; + self->period_sys += period; break; case PERF_RECORD_MISC_USER: - self->count_us += count; + self->period_us += period; break; case PERF_RECORD_MISC_GUEST_KERNEL: - self->count_guest_sys += count; + self->period_guest_sys += period; break; case PERF_RECORD_MISC_GUEST_USER: - self->count_guest_us += count; + self->period_guest_us += period; break; default: break; @@ -31,7 +31,7 @@ static void hist_entry__add_cpumode_count(struct hist_entry *self, } /* - * histogram, sorted on item, collects counts + * histogram, sorted on item, collects periods */ static struct hist_entry *hist_entry__new(struct hist_entry *template) @@ -41,6 +41,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (self != NULL) { *self = *template; + self->nr_events = 1; if (symbol_conf.use_callchain) callchain_init(self->callchain); } @@ -57,7 +58,7 @@ static void hists__inc_nr_entries(struct hists *self, struct hist_entry *entry) struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *sym_parent, u64 count) + struct symbol *sym_parent, u64 period) { struct rb_node **p = &self->entries.rb_node; struct rb_node *parent = NULL; @@ -70,7 +71,7 @@ struct hist_entry *__hists__add_entry(struct hists *self, }, .ip = al->addr, .level = al->level, - .count = count, + .period = period, .parent = sym_parent, }; int cmp; @@ -82,7 +83,8 @@ struct hist_entry *__hists__add_entry(struct hists *self, cmp = hist_entry__cmp(&entry, he); if (!cmp) { - he->count += count; + he->period += period; + ++he->nr_events; goto out; } @@ -99,7 +101,7 @@ struct hist_entry *__hists__add_entry(struct hists *self, rb_insert_color(&he->rb_node, &self->entries); hists__inc_nr_entries(self, he); out: - hist_entry__add_cpumode_count(he, al->cpumode, count); + hist_entry__add_cpumode_period(he, al->cpumode, period); return he; } @@ -160,7 +162,7 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) cmp = hist_entry__collapse(iter, he); if (!cmp) { - iter->count += he->count; + iter->period += he->period; hist_entry__free(he); return false; } @@ -203,7 +205,7 @@ void hists__collapse_resort(struct hists *self) } /* - * reverse the map, sort on count. + * reverse the map, sort on period. */ static void __hists__insert_output_entry(struct rb_root *entries, @@ -222,7 +224,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (he->count > iter->count) + if (he->period > iter->period) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -288,7 +290,7 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, } static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, - int depth, int depth_mask, int count, + int depth, int depth_mask, int period, u64 total_samples, int hits, int left_margin) { @@ -301,7 +303,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, ret += fprintf(fp, "|"); else ret += fprintf(fp, " "); - if (!count && i == depth - 1) { + if (!period && i == depth - 1) { double percent; percent = hits * 100.0 / total_samples; @@ -516,7 +518,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, long displacement, bool color, u64 session_total) { struct sort_entry *se; - u64 count, total, count_sys, count_us, count_guest_sys, count_guest_us; + u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; const char *sep = symbol_conf.field_sep; int ret; @@ -524,57 +526,57 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, return 0; if (pair_hists) { - count = self->pair ? self->pair->count : 0; + period = self->pair ? self->pair->period : 0; total = pair_hists->stats.total_period; - count_sys = self->pair ? self->pair->count_sys : 0; - count_us = self->pair ? self->pair->count_us : 0; - count_guest_sys = self->pair ? self->pair->count_guest_sys : 0; - count_guest_us = self->pair ? self->pair->count_guest_us : 0; + period_sys = self->pair ? self->pair->period_sys : 0; + period_us = self->pair ? self->pair->period_us : 0; + period_guest_sys = self->pair ? self->pair->period_guest_sys : 0; + period_guest_us = self->pair ? self->pair->period_guest_us : 0; } else { - count = self->count; + period = self->period; total = session_total; - count_sys = self->count_sys; - count_us = self->count_us; - count_guest_sys = self->count_guest_sys; - count_guest_us = self->count_guest_us; + period_sys = self->period_sys; + period_us = self->period_us; + period_guest_sys = self->period_guest_sys; + period_guest_us = self->period_guest_us; } if (total) { if (color) ret = percent_color_snprintf(s, size, sep ? "%.2f" : " %6.2f%%", - (count * 100.0) / total); + (period * 100.0) / total); else ret = snprintf(s, size, sep ? "%.2f" : " %6.2f%%", - (count * 100.0) / total); + (period * 100.0) / total); if (symbol_conf.show_cpu_utilization) { ret += percent_color_snprintf(s + ret, size - ret, sep ? "%.2f" : " %6.2f%%", - (count_sys * 100.0) / total); + (period_sys * 100.0) / total); ret += percent_color_snprintf(s + ret, size - ret, sep ? "%.2f" : " %6.2f%%", - (count_us * 100.0) / total); + (period_us * 100.0) / total); if (perf_guest) { ret += percent_color_snprintf(s + ret, size - ret, sep ? "%.2f" : " %6.2f%%", - (count_guest_sys * 100.0) / + (period_guest_sys * 100.0) / total); ret += percent_color_snprintf(s + ret, size - ret, sep ? "%.2f" : " %6.2f%%", - (count_guest_us * 100.0) / + (period_guest_us * 100.0) / total); } } } else - ret = snprintf(s, size, sep ? "%lld" : "%12lld ", count); + ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period); if (symbol_conf.show_nr_samples) { if (sep) - ret += snprintf(s + ret, size - ret, "%c%lld", *sep, count); + ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period); else - ret += snprintf(s + ret, size - ret, "%11lld", count); + ret += snprintf(s + ret, size - ret, "%11lld", period); } if (pair_hists) { @@ -582,9 +584,9 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, double old_percent = 0, new_percent = 0, diff; if (total > 0) - old_percent = (count * 100.0) / total; + old_percent = (period * 100.0) / total; if (session_total > 0) - new_percent = (self->count * 100.0) / session_total; + new_percent = (self->period * 100.0) / session_total; diff = new_percent - old_percent; @@ -796,6 +798,7 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) struct rb_node *nd; self->nr_entries = self->stats.total_period = 0; + self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; self->max_sym_namelen = 0; for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { @@ -812,7 +815,8 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) h->filtered &= ~(1 << HIST_FILTER__DSO); if (!h->filtered) { ++self->nr_entries; - self->stats.total_period += h->count; + self->stats.total_period += h->period; + self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; if (h->ms.sym && self->max_sym_namelen < h->ms.sym->namelen) self->max_sym_namelen = h->ms.sym->namelen; @@ -825,6 +829,7 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) struct rb_node *nd; self->nr_entries = self->stats.total_period = 0; + self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; self->max_sym_namelen = 0; for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { @@ -837,7 +842,8 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) h->filtered &= ~(1 << HIST_FILTER__THREAD); if (!h->filtered) { ++self->nr_entries; - self->stats.total_period += h->count; + self->stats.total_period += h->period; + self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; if (h->ms.sym && self->max_sym_namelen < h->ms.sym->namelen) self->max_sym_namelen = h->ms.sym->namelen; @@ -881,7 +887,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip) h->sum++; h->ip[offset]++; - pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start, + pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start, self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]); return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index da6b84814a50..6f17dcd8412c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -69,7 +69,7 @@ struct hists { struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *parent, u64 count); + struct symbol *parent, u64 period); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists, diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c index 010bacf40163..3402453812b3 100644 --- a/tools/perf/util/newt.c +++ b/tools/perf/util/newt.c @@ -680,16 +680,18 @@ static int hist_browser__populate(struct hist_browser *self, struct hists *hists struct ui_progress *progress; struct rb_node *nd; u64 curr_hist = 0; - char seq[] = "."; + char seq[] = ".", unit; char str[256]; + unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE]; if (self->form) { newtFormDestroy(self->form); newtPopWindow(); } - snprintf(str, sizeof(str), "Samples: %Ld ", - hists->stats.total_period); + nr_events = convert_unit(nr_events, &unit); + snprintf(str, sizeof(str), "Events: %lu%c ", + nr_events, unit); newtDrawRootText(0, 0, str); newtGetScreenSize(NULL, &rows); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index af301acc461c..eab2e0b3b74e 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -43,14 +43,15 @@ extern enum sort_type sort__first_dimension; struct hist_entry { struct rb_node rb_node; - u64 count; - u64 count_sys; - u64 count_us; - u64 count_guest_sys; - u64 count_guest_us; + u64 period; + u64 period_sys; + u64 period_us; + u64 period_guest_sys; + u64 period_guest_us; struct map_symbol ms; struct thread *thread; u64 ip; + u32 nr_events; char level; u8 filtered; struct symbol *parent; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index f9b890fde681..214265674ddd 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -92,3 +92,25 @@ out_close_from: out: return err; } + +unsigned long convert_unit(unsigned long value, char *unit) +{ + *unit = ' '; + + if (value > 1000) { + value /= 1000; + *unit = 'K'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'M'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'G'; + } + + return value; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index fbf45d1b26f7..0795bf304b19 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -423,6 +423,7 @@ char **argv_split(const char *str, int *argcp); void argv_free(char **argv); bool strglobmatch(const char *str, const char *pat); bool strlazymatch(const char *str, const char *pat); +unsigned long convert_unit(unsigned long value, char *unit); #define _STR(x) #x #define STR(x) _STR(x) -- cgit v1.2.3