diff options
| -rw-r--r-- | tools/perf/Documentation/perf-script.txt | 4 | ||||
| -rw-r--r-- | tools/perf/builtin-script.c | 68 | ||||
| -rw-r--r-- | tools/perf/util/thread-stack.c | 7 | ||||
| -rw-r--r-- | tools/perf/util/thread-stack.h | 1 |
4 files changed, 79 insertions, 1 deletions
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index a46030d8962d..1f6c70594f0f 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -177,6 +177,10 @@ OPTIONS "tr end" for "bE". However the "x" flag will be display separately in those cases e.g. "jcc (x)" for a condition branch within a transaction. + The callindent field is synthesized and may have a value when + Instruction Trace decoding. For calls and returns, it will display the + name of the symbol indented with spaces to reflect the stack depth. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 56b2fb8135ce..971ff91b16cb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -21,6 +21,7 @@ #include "util/cpumap.h" #include "util/thread_map.h" #include "util/stat.h" +#include "util/thread-stack.h" #include <linux/bitmap.h> #include <linux/stringify.h> #include "asm/bug.h" @@ -63,6 +64,7 @@ enum perf_output_field { PERF_OUTPUT_DATA_SRC = 1U << 17, PERF_OUTPUT_WEIGHT = 1U << 18, PERF_OUTPUT_BPF_OUTPUT = 1U << 19, + PERF_OUTPUT_CALLINDENT = 1U << 20, }; struct output_option { @@ -89,6 +91,7 @@ struct output_option { {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC}, {.str = "weight", .field = PERF_OUTPUT_WEIGHT}, {.str = "bpf-output", .field = PERF_OUTPUT_BPF_OUTPUT}, + {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT}, }; /* default set to maintain compatibility with current format */ @@ -562,6 +565,62 @@ static void print_sample_addr(struct perf_sample *sample, } } +static void print_sample_callindent(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al) +{ + struct perf_event_attr *attr = &evsel->attr; + size_t depth = thread_stack__depth(thread); + struct addr_location addr_al; + const char *name = NULL; + static int spacing; + int len = 0; + u64 ip = 0; + + /* + * The 'return' has already been popped off the stack so the depth has + * to be adjusted to match the 'call'. + */ + if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN) + depth += 1; + + if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { + if (sample_addr_correlates_sym(attr)) { + thread__resolve(thread, &addr_al, sample); + if (addr_al.sym) + name = addr_al.sym->name; + else + ip = sample->addr; + } else { + ip = sample->addr; + } + } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) { + if (al->sym) + name = al->sym->name; + else + ip = sample->ip; + } + + if (name) + len = printf("%*s%s", (int)depth * 4, "", name); + else if (ip) + len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip); + + if (len < 0) + return; + + /* + * Try to keep the output length from changing frequently so that the + * output lines up more nicely. + */ + if (len > spacing || (len && len < spacing - 52)) + spacing = round_up(len + 4, 32); + + if (len < spacing) + printf("%*s", spacing - len, ""); +} + static void print_sample_bts(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, @@ -570,6 +629,9 @@ static void print_sample_bts(struct perf_sample *sample, struct perf_event_attr *attr = &evsel->attr; bool print_srcline_last = false; + if (PRINT_FIELD(CALLINDENT)) + print_sample_callindent(sample, evsel, thread, al); + /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[attr->type].print_ip_opts; @@ -2053,7 +2115,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "comma separated output fields prepend with 'type:'. " "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields), + "addr,symoff,period,iregs,brstack,brstacksym,flags," + "callindent", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", @@ -2292,6 +2355,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) script.session = session; script__setup_sample_type(&script); + if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) + itrace_synth_opts.thread_stack = true; + session->itrace_synth_opts = &itrace_synth_opts; if (cpu_list) { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 825086aa9a08..d3301529f6a7 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -616,3 +616,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm, return err; } + +size_t thread_stack__depth(struct thread *thread) +{ + if (!thread->ts) + return 0; + return thread->ts->cnt; +} diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h index ad44c7944b8e..b7e41c4ebfdd 100644 --- a/tools/perf/util/thread-stack.h +++ b/tools/perf/util/thread-stack.h @@ -87,6 +87,7 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, size_t sz, u64 ip); int thread_stack__flush(struct thread *thread); void thread_stack__free(struct thread *thread); +size_t thread_stack__depth(struct thread *thread); struct call_return_processor * call_return_processor__new(int (*process)(struct call_return *cr, void *data), |