From f7380c12ec6cfd69f274ba6181cd01c764f877bb Mon Sep 17 00:00:00 2001 From: Dima Kogan Date: Tue, 29 Mar 2016 12:47:53 -0300 Subject: perf script perl: Perl scripts now get a backtrace, like the python ones We have some infrastructure to use perl or python to analyze logs generated by perf. Prior to this patch, only the python tools had access to backtrace information. This patch makes this information available to perl scripts as well. Example: Let's look at malloc() calls made by the seq utility. First we create a probe point: $ perf probe -x /lib/x86_64-linux-gnu/libc.so.6 malloc Added new events: ... Now we run seq, while monitoring malloc() calls with perf $ perf record --call-graph=dwarf -e probe_libc:malloc seq 5 1 2 3 4 5 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.064 MB perf.data (6 samples) ] We can use perf to look at its log to see the malloc calls and the backtrace $ perf script seq 14195 [000] 1927993.748254: probe_libc:malloc: (7f9ff8edd320) bytes=0x22 7f9ff8edd320 malloc (/lib/x86_64-linux-gnu/libc-2.22.so) 7f9ff8e8eab0 set_binding_values.part.0 (/lib/x86_64-linux-gnu/libc-2.22.so) 7f9ff8e8eda1 __bindtextdomain (/lib/x86_64-linux-gnu/libc-2.22.so) 401b22 main (/usr/bin/seq) 7f9ff8e82610 __libc_start_main (/lib/x86_64-linux-gnu/libc-2.22.so) 402799 _start (/usr/bin/seq) ... We can also use the scripting facilities. We create a skeleton perl script that simply prints out the events $ perf script -g perl generated Perl script: perf-script.pl We can then use this script to see the malloc() calls with a backtrace. Prior to this patch, the backtrace was not available to the perl scripts. $ perf script -s perf-script.pl probe_libc::malloc 0 1927993.748254260 14195 seq __probe_ip=140325052863264, bytes=34 [7f9ff8edd320] malloc [7f9ff8e8eab0] set_binding_values.part.0 [7f9ff8e8eda1] __bindtextdomain [401b22] main [7f9ff8e82610] __libc_start_main [402799] _start ... Tested-by: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/87mvphzld0.fsf@secretsauce.net Signed-off-by: Dima Kogan --- .../perf/util/scripting-engines/trace-event-perl.c | 114 +++++++++++++++++++-- 1 file changed, 106 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/scripting-engines/trace-event-perl.c') diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index b3aabc0d4eb0..1d160855cda9 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -31,6 +31,8 @@ #include #include "../../perf.h" +#include "../callchain.h" +#include "../machine.h" #include "../thread.h" #include "../event.h" #include "../trace-event.h" @@ -248,10 +250,78 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } +static SV *perl_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + AV *list; + + list = newAV(); + if (!list) + goto exit; + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + HV *elem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + elem = newHV(); + if (!elem) + goto exit; + + hv_stores(elem, "ip", newSVuv(node->ip)); + + if (node->sym) { + HV *sym = newHV(); + if (!sym) + goto exit; + hv_stores(sym, "start", newSVuv(node->sym->start)); + hv_stores(sym, "end", newSVuv(node->sym->end)); + hv_stores(sym, "binding", newSVuv(node->sym->binding)); + hv_stores(sym, "name", newSVpvn(node->sym->name, + node->sym->namelen)); + hv_stores(elem, "sym", newRV_noinc((SV*)sym)); + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + hv_stores(elem, "dso", newSVpv(dsoname,0)); + } + + callchain_cursor_advance(&callchain_cursor); + av_push(list, newRV_noinc((SV*)elem)); + } + +exit: + return newRV_noinc((SV*)list); +} + static void perl_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread) + struct addr_location *al) { + struct thread *thread = al->thread; struct event_format *event = evsel->tp_format; struct format_field *field; static char handler[256]; @@ -295,6 +365,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(ns))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); /* common fields other than pid can be accessed via xsub fns */ @@ -329,6 +400,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(nsecs))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); call_pv("main::trace_unhandled", G_SCALAR); } SPAGAIN; @@ -366,7 +438,7 @@ static void perl_process_event(union perf_event *event, struct perf_evsel *evsel, struct addr_location *al) { - perl_process_tracepoint(sample, evsel, al->thread); + perl_process_tracepoint(sample, evsel, al); perl_process_event_generic(event, sample, evsel); } @@ -490,7 +562,27 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "use Perf::Trace::Util;\n\n"); fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); - fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); + fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n"); + + + fprintf(ofp, "\n\ +sub print_backtrace\n\ +{\n\ + my $callchain = shift;\n\ + for my $node (@$callchain)\n\ + {\n\ + if(exists $node->{sym})\n\ + {\n\ + printf( \"\\t[\\%%x] \\%%s\\n\", $node->{ip}, $node->{sym}{name});\n\ + }\n\ + else\n\ + {\n\ + printf( \"\\t[\\%%x]\\n\", $node{ip});\n\ + }\n\ + }\n\ +}\n\n\ +"); + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); @@ -502,7 +594,8 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$common_secs, "); fprintf(ofp, "$common_nsecs,\n"); fprintf(ofp, "\t $common_pid, "); - fprintf(ofp, "$common_comm,\n\t "); + fprintf(ofp, "$common_comm, "); + fprintf(ofp, "$common_callchain,\n\t "); not_first = 0; count = 0; @@ -519,7 +612,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm);\n\n"); + "$common_pid, $common_comm, $common_callchain);\n\n"); fprintf(ofp, "\tprintf(\""); @@ -581,17 +674,22 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$%s", f->name); } - fprintf(ofp, ");\n"); + fprintf(ofp, ");\n\n"); + + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); } fprintf(ofp, "sub trace_unhandled\n{\n\tmy ($event_name, $context, " "$common_cpu, $common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm) = @_;\n\n"); + "$common_pid, $common_comm, $common_callchain) = @_;\n\n"); fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t $common_pid, " - "$common_comm);\n}\n\n"); + "$common_comm, $common_callchain);\n"); + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); fprintf(ofp, "sub print_header\n{\n" "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" -- cgit v1.2.3 From 76e20522b709f3772e415d70b108028454a86ad5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 5 Apr 2016 12:21:44 -0300 Subject: perf script perl: Do error checking on new backtrace routine This ended up triggering these warnings when building on Ubuntu 12.04.5: util/scripting-engines/trace-event-perl.c: In function 'perl_process_callchain': util/scripting-engines/trace-event-perl.c:293:4: error: value computed is not used [-Werror=unused-value] util/scripting-engines/trace-event-perl.c:294:4: error: value computed is not used [-Werror=unused-value] util/scripting-engines/trace-event-perl.c:295:4: error: value computed is not used [-Werror=unused-value] util/scripting-engines/trace-event-perl.c:297:4: error: value computed is not used [-Werror=unused-value] util/scripting-engines/trace-event-perl.c:309:4: error: value computed is not used [-Werror=unused-value] cc1: all warnings being treated as errors mv: cannot stat `/tmp/build/perf/util/scripting-engines/.trace-event-perl.o.tmp': No such file or directory make[4]: *** [/tmp/build/perf/util/scripting-engines/trace-event-perl.o] Error 1 Fix it by doing error checking when building the perl data structures related to callchains. Cc: Adrian Hunter Cc: David Ahern Cc: Dima Kogan Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Fixes: f7380c12ec6c ("perf script perl: Perl scripts now get a backtrace, like the python ones") Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/util/scripting-engines/trace-event-perl.c | 30 +++++++++++++++------- 1 file changed, 21 insertions(+), 9 deletions(-) (limited to 'tools/perf/util/scripting-engines/trace-event-perl.c') diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 1d160855cda9..35ed00a600fb 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -283,18 +283,27 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (!elem) goto exit; - hv_stores(elem, "ip", newSVuv(node->ip)); + if (!hv_stores(elem, "ip", newSVuv(node->ip))) { + hv_undef(elem); + goto exit; + } if (node->sym) { HV *sym = newHV(); - if (!sym) + if (!sym) { + hv_undef(elem); + goto exit; + } + if (!hv_stores(sym, "start", newSVuv(node->sym->start)) || + !hv_stores(sym, "end", newSVuv(node->sym->end)) || + !hv_stores(sym, "binding", newSVuv(node->sym->binding)) || + !hv_stores(sym, "name", newSVpvn(node->sym->name, + node->sym->namelen)) || + !hv_stores(elem, "sym", newRV_noinc((SV*)sym))) { + hv_undef(sym); + hv_undef(elem); goto exit; - hv_stores(sym, "start", newSVuv(node->sym->start)); - hv_stores(sym, "end", newSVuv(node->sym->end)); - hv_stores(sym, "binding", newSVuv(node->sym->binding)); - hv_stores(sym, "name", newSVpvn(node->sym->name, - node->sym->namelen)); - hv_stores(elem, "sym", newRV_noinc((SV*)sym)); + } } if (node->map) { @@ -306,7 +315,10 @@ static SV *perl_process_callchain(struct perf_sample *sample, else if (map->dso->name) dsoname = map->dso->name; } - hv_stores(elem, "dso", newSVpv(dsoname,0)); + if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { + hv_undef(elem); + goto exit; + } } callchain_cursor_advance(&callchain_cursor); -- cgit v1.2.3 From 91d7b2de318ff701451dfc7ede1c029b150ef0e9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Apr 2016 14:48:07 -0300 Subject: perf callchain: Start moving away from global per thread cursors The recent perf_evsel__fprintf_callchain() move to evsel.c added several new symbol requirements to the python binding, for instance: # perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 18030 Traceback (most recent call last): File "", line 1, in ImportError: /tmp/build/perf/python/perf.so: undefined symbol: callchain_cursor test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! # This would require linking against callchain.c to access to the global callchain_cursor variables. Since lots of functions already receive as a parameter a callchain_cursor struct pointer, make that be the case for some more function so that we can start phasing out usage of yet another global variable. Cc: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-djko3097eyg2rn66v2qcqfvn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kmem.c | 2 +- tools/perf/util/callchain.c | 5 +++-- tools/perf/util/callchain.h | 3 ++- tools/perf/util/evsel.c | 9 ++++---- tools/perf/util/hist.c | 2 +- tools/perf/util/machine.c | 26 +++++++++++++--------- tools/perf/util/machine.h | 4 ++++ .../perf/util/scripting-engines/trace-event-perl.c | 2 +- .../util/scripting-engines/trace-event-python.c | 2 +- 9 files changed, 33 insertions(+), 22 deletions(-) (limited to 'tools/perf/util/scripting-engines/trace-event-perl.c') diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c9cb3be47cff..58adfee230de 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -375,7 +375,7 @@ static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample) } al.thread = machine__findnew_thread(machine, sample->pid, sample->tid); - sample__resolve_callchain(sample, NULL, evsel, &al, 16); + sample__resolve_callchain(sample, &callchain_cursor, NULL, evsel, &al, 16); callchain_cursor_commit(&callchain_cursor); while (true) { diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 24b4bd0d7754..2b4ceaf058bb 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -788,7 +788,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, return 0; } -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack) { @@ -797,7 +798,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || sort__has_parent) { - return thread__resolve_callchain(al->thread, evsel, sample, + return thread__resolve_callchain(al->thread, cursor, evsel, sample, parent, al, max_stack); } return 0; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index d2a9e694810c..cae5a7b1f5c8 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -212,7 +212,8 @@ struct hist_entry; int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); int record_callchain_opt(const struct option *opt, const char *arg, int unset); -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6e86598682be..38f464a4fa04 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2349,6 +2349,7 @@ int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample * FILE *fp) { int printed = 0; + struct callchain_cursor cursor; struct callchain_cursor_node *node; int print_ip = print_opts & EVSEL__PRINT_IP; int print_sym = print_opts & EVSEL__PRINT_SYM; @@ -2362,14 +2363,14 @@ int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample * if (sample->callchain) { struct addr_location node_al; - if (thread__resolve_callchain(al->thread, evsel, + if (thread__resolve_callchain(al->thread, &cursor, evsel, sample, NULL, NULL, stack_depth) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return printed; } - callchain_cursor_commit(&callchain_cursor); + callchain_cursor_commit(&cursor); if (print_symoffset) node_al = *al; @@ -2377,7 +2378,7 @@ int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample * while (stack_depth) { u64 addr = 0; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(&cursor); if (!node) break; @@ -2420,7 +2421,7 @@ int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample * stack_depth--; next: - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(&cursor); } } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 3d34c57dfbe2..991a351a8a41 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -953,7 +953,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, { int err, err2; - err = sample__resolve_callchain(iter->sample, &iter->parent, + err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); if (err) return err; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 80b9b6a87990..0c4dabc69932 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1599,6 +1599,7 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, } static int add_callchain_ip(struct thread *thread, + struct callchain_cursor *cursor, struct symbol **parent, struct addr_location *root_al, u8 *cpumode, @@ -1630,7 +1631,7 @@ static int add_callchain_ip(struct thread *thread, * It seems the callchain is corrupted. * Discard all. */ - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); return 1; } return 0; @@ -1648,13 +1649,13 @@ static int add_callchain_ip(struct thread *thread, /* Treat this symbol as the root, forgetting its callees. */ *root_al = al; - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); } } if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; - return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); + return callchain_cursor_append(cursor, al.addr, al.map, al.sym); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1724,6 +1725,7 @@ static int remove_loops(struct branch_entry *l, int nr) * negative error code on other errors. */ static int resolve_lbr_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -1778,7 +1780,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; } - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; } @@ -1789,6 +1791,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, } static int thread__resolve_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, @@ -1803,10 +1806,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, int skip_idx = -1; int first_call = 0; - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); if (has_branch_callstack(evsel)) { - err = resolve_lbr_callchain_sample(thread, sample, parent, + err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, root_al, max_stack); if (err) return (err < 0) ? err : 0; @@ -1863,10 +1866,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, nr = remove_loops(be, nr); for (i = 0; i < nr; i++) { - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].to); if (!err) - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from); if (err == -EINVAL) break; @@ -1896,7 +1899,7 @@ check_calls: #endif ip = chain->ips[j]; - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; @@ -1916,13 +1919,14 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) } int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, int max_stack) { - int ret = thread__resolve_callchain_sample(thread, evsel, + int ret = thread__resolve_callchain_sample(thread, cursor, evsel, sample, parent, root_al, max_stack); if (ret) @@ -1938,7 +1942,7 @@ int thread__resolve_callchain(struct thread *thread, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, + return unwind__get_entries(unwind_entry, cursor, thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 8499db281158..382873bdc563 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -141,7 +141,11 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al); + +struct callchain_cursor; + int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 35ed00a600fb..ae1cebc307c5 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -263,7 +263,7 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, evsel, + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, PERF_MAX_STACK_DEPTH) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index fbd05242b4e5..525eb49e7ba6 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -323,7 +323,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, evsel, + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); -- 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/Documentation/perf-report.txt | 2 +- tools/perf/Documentation/perf-script.txt | 2 +- tools/perf/Documentation/perf-top.txt | 2 +- tools/perf/Documentation/perf-trace.txt | 2 +- tools/perf/builtin-report.c | 4 ++-- tools/perf/builtin-script.c | 4 +++- tools/perf/builtin-top.c | 4 ++-- tools/perf/builtin-trace.c | 4 ++-- tools/perf/perf.c | 5 +++++ tools/perf/tests/hists_cumulate.c | 2 +- tools/perf/tests/hists_filter.c | 2 +- tools/perf/tests/hists_output.c | 2 +- tools/perf/util/machine.c | 6 +++--- tools/perf/util/scripting-engines/trace-event-perl.c | 2 +- tools/perf/util/util.c | 2 ++ tools/perf/util/util.h | 1 + 16 files changed, 28 insertions(+), 18 deletions(-) (limited to 'tools/perf/util/scripting-engines/trace-event-perl.c') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 496d42cdf02b..ebaf849e30ef 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -248,7 +248,7 @@ OPTIONS Note that when using the --itrace option the synthesized callchain size will override this value if the synthesized callchain size is bigger. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. -G:: --inverted:: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 4fc44c75263f..a856a1095893 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -267,7 +267,7 @@ include::itrace.txt[] Note that when using the --itrace option the synthesized callchain size will override this value if the synthesized callchain size is bigger. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. --ns:: Use 9 decimal places when displaying time (i.e. show the nanoseconds) diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 19f046f027cd..91d638df3a6b 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -177,7 +177,7 @@ Default is to monitor all CPUS. between information loss and faster processing especially for workloads that can have a very long callchain stack. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. --ignore-callees=:: Ignore callees of the function(s) matching the given regex. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index c075c002eaa4..6afe20121bc0 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -143,7 +143,7 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. Implies '--call-graph dwarf' when --call-graph not present on the command line, on systems where DWARF unwinding was built in. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. --min-stack:: Set the stack depth limit when parsing the callchain, anything diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1d5be0bd426f..8d9b88af901d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_events = true, .ordering_requires_timestamps = true, }, - .max_stack = PERF_MAX_STACK_DEPTH, + .max_stack = sysctl_perf_event_max_stack, .pretty_printing_style = "normal", .socket_filter = -1, }; @@ -744,7 +744,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INTEGER(0, "max-stack", &report.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('G', "inverted", &report.inverted_callchain, "alias for inverted call graph"), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", 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, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c130a11d3a0d..da18517b1d40 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1103,7 +1103,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) }, .proc_map_timeout = 500, }, - .max_stack = PERF_MAX_STACK_DEPTH, + .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, }; struct record_opts *opts = &top.record_opts; @@ -1171,7 +1171,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Accumulate callchains of children and show total overhead as well"), OPT_INTEGER(0, "max-stack", &top.max_stack, "Set the maximum stack depth when parsing the callchain. " - "Default: " __stringify(PERF_MAX_STACK_DEPTH)), + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 48b00f042599..f4f3389c92c7 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3106,7 +3106,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) OPT_UINTEGER(0, "max-stack", &trace.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_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), OPT_END() @@ -3150,7 +3150,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) mmap_pages_user_set = false; if (trace.max_stack == UINT_MAX) { - trace.max_stack = PERF_MAX_STACK_DEPTH; + trace.max_stack = sysctl_perf_event_max_stack; max_stack_user_set = false; } diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 7b2df2b46525..83ffe7cd7330 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -17,6 +17,7 @@ #include #include "util/bpf-loader.h" #include "util/debug.h" +#include #include #include #include @@ -533,6 +534,7 @@ int main(int argc, const char **argv) { const char *cmd; char sbuf[STRERR_BUFSIZE]; + int value; /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); @@ -542,6 +544,9 @@ int main(int argc, const char **argv) page_size = sysconf(_SC_PAGE_SIZE); cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE); + if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) + sysctl_perf_event_max_stack = value; + cmd = extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index ed5aa9eaeb6c..4a2bbff9b1ee 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -101,7 +101,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (machine__resolve(machine, &al, &sample) < 0) goto out; - if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index b825d24f8186..e846f8c42013 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -81,7 +81,7 @@ static int add_hist_entries(struct perf_evlist *evlist, al.socket = fake_samples[i].socket; if (hist_entry_iter__add(&iter, &al, - PERF_MAX_STACK_DEPTH, NULL) < 0) { + sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; } diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index d3556fbe8c5c..7cd8738e842f 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -67,7 +67,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (machine__resolve(machine, &al, &sample) < 0) goto out; - if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 656c1d7ee7d4..2cb95bbf9ea6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1764,7 +1764,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, */ int mix_chain_nr = i + 1 + lbr_nr + 1; - if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) { + if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) { pr_warning("corrupted callchain. skipping...\n"); return 0; } @@ -1825,7 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - if (chain->nr < PERF_MAX_STACK_DEPTH) + if (chain->nr < sysctl_perf_event_max_stack) skip_idx = arch_skip_callchain_idx(thread, chain); /* @@ -1886,7 +1886,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) { + if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) { pr_warning("corrupted callchain. skipping...\n"); return 0; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index ae1cebc307c5..62c7f6988e0e 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -265,7 +265,7 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, - PERF_MAX_STACK_DEPTH) != 0) { + sysctl_perf_event_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 9473d46c00bb..619ba2061b62 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -33,6 +33,8 @@ struct callchain_param callchain_param = { unsigned int page_size; int cacheline_size; +unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; + bool test_attr__enabled; bool perf_host = true; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 26a924651e7b..88f607af1f47 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -267,6 +267,7 @@ void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; +extern unsigned int sysctl_perf_event_max_stack; struct parse_tag { char tag; -- cgit v1.2.3