From 91daee306a51ca7b4d3ca7fdcf7472b0ed2c80c1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Apr 2016 09:11:13 +0200 Subject: perf script: Process event update events Andreas reported following command produces no output: # cat test.py #!/usr/bin/env python def stat__krava(cpu, thread, time, val, ena, run): print "event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % \ ("krava", cpu, thread, time, val, ena, run) # perf stat -a -I 1000 -e cycles,"cpu/config=0x6530160,name=krava/" record | perf script -s test.py ^C # The reason is that 'perf script' does not process event update events and will never get the event name update thus the python callback is never called. The fix is just to add already existing callback we use in 'perf stat report'. Committer note: After the patch: # perf stat -a -I 1000 -e cycles,"cpu/config=0x6530160,name=krava/" record | perf script -s test.py event krava cpu -1, thread -1, time 1000239179, val 1789051, ena 4000690920, run 4000690920 event krava cpu -1, thread -1, time 2000479061, val 2391338, ena 4000879596, run 4000879596 event krava cpu -1, thread -1, time 3000740802, val 1939121, ena 4000977209, run 4000977209 event krava cpu -1, thread -1, time 4001006730, val 2356115, ena 4001000489, run 4001000489 ^C # Reported-by: Andreas Hollmann Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1460013073-18444-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3770c3dffe5e..59009aa7e2ca 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1961,6 +1961,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, + .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, -- cgit v1.2.3 From a5e8e825bd1704c488bf6a46936aaf3b9f203d6a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 8 Apr 2016 11:25:59 -0300 Subject: perf script: Use readdir() instead of deprecated readdir_r() The readdir() function is thread safe as long as just one thread uses a DIR, which is the case in 'perf script', so, to avoid breaking the build with glibc-2.23.90 (upcoming 2.24), use it instead of readdir_r(). See: http://man7.org/linux/man-pages/man3/readdir.3.html "However, in modern implementations (including the glibc implementation), concurrent calls to readdir() that specify different directory streams are thread-safe. In cases where multiple threads must read from the same directory stream, using readdir() with external synchronization is still preferable to the use of the deprecated readdir_r(3) function." Noticed while building on a Fedora Rawhide docker container. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-mt3xz7n2hl49ni2vx7kuq74g@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 70 ++++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 36 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 59009aa7e2ca..8f6ab2ac855a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1415,21 +1415,19 @@ static int is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\ - while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) && \ - lang_next) \ - if ((lang_dirent.d_type == DT_DIR || \ - (lang_dirent.d_type == DT_UNKNOWN && \ - is_directory(scripts_path, &lang_dirent))) && \ - (strcmp(lang_dirent.d_name, ".")) && \ - (strcmp(lang_dirent.d_name, ".."))) - -#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\ - while (!readdir_r(lang_dir, &script_dirent, &script_next) && \ - script_next) \ - if (script_dirent.d_type != DT_DIR && \ - (script_dirent.d_type != DT_UNKNOWN || \ - !is_directory(lang_path, &script_dirent))) +#define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ + while ((lang_dirent = readdir(scripts_dir)) != NULL) \ + if ((lang_dirent->d_type == DT_DIR || \ + (lang_dirent->d_type == DT_UNKNOWN && \ + is_directory(scripts_path, lang_dirent))) && \ + (strcmp(lang_dirent->d_name, ".")) && \ + (strcmp(lang_dirent->d_name, ".."))) + +#define for_each_script(lang_path, lang_dir, script_dirent) \ + while ((script_dirent = readdir(lang_dir)) != NULL) \ + if (script_dirent->d_type != DT_DIR && \ + (script_dirent->d_type != DT_UNKNOWN || \ + !is_directory(lang_path, script_dirent))) #define RECORD_SUFFIX "-record" @@ -1575,7 +1573,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset __maybe_unused) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; char script_path[MAXPATHLEN]; @@ -1590,19 +1588,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused, if (!scripts_dir) return -1; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - script_root = get_script_root(&script_dirent, REPORT_SUFFIX); + for_each_script(lang_path, lang_dir, script_dirent) { + script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -1690,7 +1688,7 @@ static int check_ev_match(char *dir_name, char *scriptname, */ int find_scripts(char **scripts_array, char **scripts_path_array) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; struct perf_session *session; @@ -1713,9 +1711,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array) return -1; } - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); #ifdef NO_LIBPERL if (strstr(lang_path, "perl")) continue; @@ -1729,16 +1727,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array) if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { + for_each_script(lang_path, lang_dir, script_dirent) { /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent.d_name, "top.")) + if (strstr(script_dirent->d_name, "top.")) continue; sprintf(scripts_path_array[i], "%s/%s", lang_path, - script_dirent.d_name); - temp = strchr(script_dirent.d_name, '.'); + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], - (temp - script_dirent.d_name) + 1, - "%s", script_dirent.d_name); + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); if (check_ev_match(lang_path, scripts_array[i], session)) @@ -1756,7 +1754,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array) static char *get_script_path(const char *script_root, const char *suffix) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; char script_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; @@ -1769,21 +1767,21 @@ static char *get_script_path(const char *script_root, const char *suffix) if (!scripts_dir) return NULL; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - __script_root = get_script_root(&script_dirent, suffix); + for_each_script(lang_path, lang_dir, script_dirent) { + __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); closedir(lang_dir); closedir(scripts_dir); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); return strdup(script_path); } free(__script_root); -- cgit v1.2.3 From 6186de9a491af030889b372193fc9f38c248e69a Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Mon, 11 Apr 2016 10:18:11 -0300 Subject: perf evsel: Allow specifying a file to output in perf_evsel__print_ip As this function will be used in 'perf trace'. Cc: Jiri Olsa Link: http://lkml.kernel.org/n/tip-8x297v9utnxq77onikevvlse@git.kernel.org [ Split from a larger patch ] Signed-off-by: Milian Wolff --- tools/perf/builtin-script.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8f6ab2ac855a..dbf208f0cdc2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -580,7 +580,7 @@ static void print_sample_bts(struct perf_sample *sample, } } perf_evsel__print_ip(evsel, sample, al, print_opts, - scripting_max_stack); + scripting_max_stack, stdout); } /* print branch_to information */ @@ -790,7 +790,7 @@ static void process_event(struct perf_script *script, perf_evsel__print_ip(evsel, sample, al, output[attr->type].print_ip_opts, - scripting_max_stack); + scripting_max_stack, stdout); } if (PRINT_FIELD(IREGS)) -- cgit v1.2.3 From db3617f362d7e205621c1ccc22b77d224a81ee14 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Apr 2016 10:53:51 -0300 Subject: perf evsel: Allow passing a left alignment when printing a symbol For callchains, etc where we want it to align just below the syscall name, for instance, in 'perf trace' Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-uk9ekchd67651c625ltaur5y@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index dbf208f0cdc2..60fde9f5025c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -579,7 +579,7 @@ static void print_sample_bts(struct perf_sample *sample, print_opts &= ~PRINT_IP_OPT_SRCLINE; } } - perf_evsel__print_ip(evsel, sample, al, print_opts, + perf_evsel__print_ip(evsel, sample, al, 0, print_opts, scripting_max_stack, stdout); } @@ -788,7 +788,7 @@ static void process_event(struct perf_script *script, else printf("\n"); - perf_evsel__print_ip(evsel, sample, al, + perf_evsel__print_ip(evsel, sample, al, 0, output[attr->type].print_ip_opts, scripting_max_stack, stdout); } -- cgit v1.2.3 From ff0c107806cf9d237e50e21de66d6909391071cd Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Apr 2016 11:14:06 -0300 Subject: perf evsel: Rename print_ip() to fprintf_sym() As it receives a FILE, and its more than just the IP, which can even be requested not to be printed. For consistency with other similar methods in tools/perf/, name it as perf_evsel__fprintf_sym() and make it return the number of bytes printed, just like 'fprintf(3)' Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-84gawlqa3lhk63nf0t9vnqnn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 60fde9f5025c..ddd5b79e94c2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -579,8 +579,8 @@ static void print_sample_bts(struct perf_sample *sample, print_opts &= ~PRINT_IP_OPT_SRCLINE; } } - perf_evsel__print_ip(evsel, sample, al, 0, print_opts, - scripting_max_stack, stdout); + perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts, + scripting_max_stack, stdout); } /* print branch_to information */ @@ -788,9 +788,9 @@ static void process_event(struct perf_script *script, else printf("\n"); - perf_evsel__print_ip(evsel, sample, al, 0, - output[attr->type].print_ip_opts, - scripting_max_stack, stdout); + perf_evsel__fprintf_sym(evsel, sample, al, 0, + output[attr->type].print_ip_opts, + scripting_max_stack, stdout); } if (PRINT_FIELD(IREGS)) -- cgit v1.2.3 From e20ab86e51218f9949f41fb39a6c4f63b662f135 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 12 Apr 2016 15:16:15 -0300 Subject: perf evsel: Move some methods from session.[ch] to evsel.[ch] Those were converted to be evsel methods long ago, move the source to where it belongs. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-vja8rjmkw3gd5ungaeyb5s2j@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ddd5b79e94c2..838c0bc38105 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -317,19 +317,19 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) - output[type].print_ip_opts |= PRINT_IP_OPT_IP; + output[type].print_ip_opts |= EVSEL__PRINT_IP; if (PRINT_FIELD(SYM)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYM; + output[type].print_ip_opts |= EVSEL__PRINT_SYM; if (PRINT_FIELD(DSO)) - output[type].print_ip_opts |= PRINT_IP_OPT_DSO; + output[type].print_ip_opts |= EVSEL__PRINT_DSO; if (PRINT_FIELD(SYMOFFSET)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET; + output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; if (PRINT_FIELD(SRCLINE)) - output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE; + output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } /* @@ -574,9 +574,9 @@ static void print_sample_bts(struct perf_sample *sample, printf("\n"); } else { printf(" "); - if (print_opts & PRINT_IP_OPT_SRCLINE) { + if (print_opts & EVSEL__PRINT_SRCLINE) { print_srcline_last = true; - print_opts &= ~PRINT_IP_OPT_SRCLINE; + print_opts &= ~EVSEL__PRINT_SRCLINE; } } perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts, -- cgit v1.2.3 From de446b40d5ddb2c3f1fe453ac405543663f9ac5d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Apr 2016 14:56:06 -0300 Subject: perf evsel: Remove symbol_conf usage # perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 672 Traceback (most recent call last): File "", line 1, in ImportError: /tmp/build/perf/python/perf.so: undefined symbol: symbol_conf test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! # To fix it just pass a parameter to perf_evsel__fprintf_sym telling if callchains should be printed. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-comrsr20bsnr8bg0n6rfwv12@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 838c0bc38105..717ba0215234 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -580,6 +580,7 @@ static void print_sample_bts(struct perf_sample *sample, } } perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts, + symbol_conf.use_callchain, scripting_max_stack, stdout); } @@ -790,6 +791,7 @@ static void process_event(struct perf_script *script, perf_evsel__fprintf_sym(evsel, sample, al, 0, output[attr->type].print_ip_opts, + symbol_conf.use_callchain, scripting_max_stack, stdout); } -- cgit v1.2.3 From 6f736735e30f51805f6be31d20a4bf5b0ae91bae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Apr 2016 17:45:51 -0300 Subject: perf evsel: Require that callchains be resolved before calling fprintf_{sym,callchain} This way the print routine merely does printing, not requiring access to the resolving machinery, which helps disentangling the object files and easing creating subsets with a limited functionality set. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-2ti2jbra8fypdfawwwm3aee3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 717ba0215234..875d84e7ba5b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -569,19 +569,23 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[attr->type].print_ip_opts; + struct callchain_cursor *cursor = NULL, cursor_callchain; - if (symbol_conf.use_callchain && sample->callchain) { - printf("\n"); - } else { - printf(" "); + if (symbol_conf.use_callchain && sample->callchain && + thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &cursor_callchain; + + if (cursor == NULL) { + putchar(' '); if (print_opts & EVSEL__PRINT_SRCLINE) { print_srcline_last = true; print_opts &= ~EVSEL__PRINT_SRCLINE; } - } - perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts, - symbol_conf.use_callchain, - scripting_max_stack, stdout); + } else + putchar('\n'); + + sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout); } /* print branch_to information */ @@ -784,15 +788,15 @@ static void process_event(struct perf_script *script, printf("%16" PRIu64, sample->weight); if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else - printf("\n"); + struct callchain_cursor *cursor = NULL, cursor_callchain; + + if (symbol_conf.use_callchain && + thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &cursor_callchain; - perf_evsel__fprintf_sym(evsel, sample, al, 0, - output[attr->type].print_ip_opts, - symbol_conf.use_callchain, - scripting_max_stack, stdout); + putchar(cursor ? '\n' : ' '); + sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) -- cgit v1.2.3 From 6125cc8dac432948a31df4d4ac20dd2d4f8c6c27 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Apr 2016 18:15:18 -0300 Subject: perf script: Add --max-stack knob Works just like with 'perf report'. In some cases we may want to have more than 127 entries, the default maximum. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-mqkz2p5ok2978gztb0vsnocc@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 875d84e7ba5b..0e93282b405e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -22,6 +22,7 @@ #include "util/thread_map.h" #include "util/stat.h" #include +#include #include "asm/bug.h" #include "util/mem-events.h" @@ -2027,6 +2028,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "only consider symbols in these pids"), OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "only consider symbols in these tids"), + OPT_UINTEGER(0, "max-stack", &scripting_max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, -- cgit v1.2.3 From 922315210b8007a26374e30712813b714af71cac Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 18 Apr 2016 11:31:46 -0300 Subject: perf script: Check sample->callchain before using it Found by code inspection, while looking at thread__resolve_callchain() callsites, one had it, the other didn't. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-6r8i2afd3523thuuaxl39yhk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0e93282b405e..5099740aa50b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -791,7 +791,7 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL, cursor_callchain; - if (symbol_conf.use_callchain && + if (symbol_conf.use_callchain && sample->callchain && thread__resolve_callchain(al->thread, &cursor_callchain, evsel, sample, NULL, NULL, scripting_max_stack) == 0) cursor = &cursor_callchain; -- cgit v1.2.3 From e557b674a9470dae99916be6105e6780b3a072ca Mon Sep 17 00:00:00 2001 From: Chris Phlipot Date: Tue, 19 Apr 2016 19:32:11 -0700 Subject: perf script: Fix segfault when printing callchains This fixes a bug caused by an unitialized callchain cursor. The crash frist appeared in: 6f736735e30f ("perf evsel: Require that callchains be resolved before calling fprintf_{sym,callchain}") The callchain cursor is a struct that contains pointers, that when uninitialized will cause unpredictable behavior (usually a crash) when trying to append to the callchain. The existing implementation has the following issues: 1. The callchain cursor used is not initialized, resulting in unpredictable behavior when used. 2. The cursor is declared on the stack. Even if it is properly initalized, the implmentation will leak memory when the function returns, since all the references to the callchain_nodes allocated by callchain_cursor_append will be lost when the cursor goes out of scope. 3. Storing the cursor on the stack is inefficient. Even if memory is properly freed when it goes out of scope, a performance penalty will be incurred due to reallocation of callchain nodes. callchain_cursor_append is designed to avoid these reallocations when an existing cursor is reused. This patch fixes the crash by replacing cursor_callchain with a reference to the global callchain_cursor which also resolves all 3 issues mentioned above. How to reproduce the crash: $ perf record --call-graph=dwarf stress -t 1 -c 1 $ perf script > /dev/null Segfault Signed-off-by: Chris Phlipot Tested-by: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Fixes: 6f736735e30f ("perf evsel: Require that callchains be resolved before calling fprintf_{sym,callchain}") Link: http://lkml.kernel.org/r/1461119531-2529-1-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5099740aa50b..f43b0c6f88f4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -570,12 +570,12 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[attr->type].print_ip_opts; - struct callchain_cursor *cursor = NULL, cursor_callchain; + struct callchain_cursor *cursor = NULL; if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &cursor_callchain; + cursor = &callchain_cursor; if (cursor == NULL) { putchar(' '); @@ -789,12 +789,12 @@ static void process_event(struct perf_script *script, printf("%16" PRIu64, sample->weight); if (PRINT_FIELD(IP)) { - struct callchain_cursor *cursor = NULL, cursor_callchain; + struct callchain_cursor *cursor = NULL; if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &cursor_callchain; + cursor = &callchain_cursor; putchar(cursor ? '\n' : ' '); sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); -- cgit v1.2.3 From 4cb93446c587d56e2a54f4f83113daba2c0b6dee Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 27 Apr 2016 10:16:24 -0300 Subject: perf tools: Set the maximum allowed stack from /proc/sys/kernel/perf_event_max_stack There is an upper limit to what tooling considers a valid callchain, and it was tied to the hardcoded value in the kernel, PERF_MAX_STACK_DEPTH (127), now that this can be tuned via a sysctl, make it read it and use that as the upper limit, falling back to PERF_MAX_STACK_DEPTH for kernels where this sysctl isn't present. Cc: Adrian Hunter Cc: Brendan Gregg Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-yjqsd30nnkogvj5oyx9ghir9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index f43b0c6f88f4..efca81679bb3 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2031,7 +2031,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) OPT_UINTEGER(0, "max-stack", &scripting_max_stack, "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " - "Default: " __stringify(PERF_MAX_STACK_DEPTH)), + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, @@ -2067,6 +2067,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; + scripting_max_stack = sysctl_perf_event_max_stack; + setup_scripting(); argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, -- cgit v1.2.3