perf trace: Add --max-stack knob

Similar to the one in the other tools (report, script, top).

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lh7kk5a5t3erwxw31ah0cgar@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 1bbcf305d233132ad90cdc1a057250edbb904052..2ee0c4fee18d3de3ad68b4df21646fe0a35f9af1 100644 (file)
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -129,6 +129,15 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --event::
        Trace other events, see 'perf list' for a complete list.
 
+--max-stack::
+        Set the stack depth limit when parsing the callchain, anything
+        beyond the specified depth will be ignored. Note that at this point
+        this is just about the presentation part, i.e. the kernel is still
+        not limiting, the overhead of callchains needs to be set via the
+        knobs in --call-graph dwarf.
+
+        Default: 127
+
 --proc-map-timeout::
        When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
        because the file may be huge. A time out is needed in such cases.

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5e5a95e34a5319cd729c4102d3f14322b482df13..39a158923acf87812fce013a0a870c6938c48882 100644 (file)
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -46,6 +46,7 @@
 #include <linux/audit.h>
 #include <sys/ptrace.h>
 #include <linux/random.h>
+#include <linux/stringify.h>
 
 #ifndef O_CLOEXEC
 # define O_CLOEXEC             02000000
@@ -106,6 +107,7 @@ struct trace {
                u64             vfs_getname,
                                proc_getname;
        } stats;
+       unsigned int            max_stack;
        bool                    not_ev_qualifier;
        bool                    live;
        bool                    full_time;
@@ -1892,7 +1894,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_evsel *evse
 
        if (machine__resolve(trace->host, &al, sample) < 0 ||
            thread__resolve_callchain(al.thread, &callchain_cursor, evsel,
-                                     sample, NULL, NULL, scripting_max_stack)) {
+                                     sample, NULL, NULL, trace->max_stack)) {
                pr_err("Problem processing %s callchain, skipping...\n",
                        perf_evsel__name(evsel));
                return 0;
@@ -3029,6 +3031,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                .show_comm = true,
                .trace_syscalls = true,
                .kernel_syscallchains = false,
+               .max_stack = PERF_MAX_STACK_DEPTH,
        };
        const char *output_name = NULL;
        const char *ev_qualifier_str = NULL;
@@ -3079,6 +3082,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                     &record_parse_callchain_opt),
        OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
                    "Show the kernel callchains on the syscall exit path"),
+       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)),
        OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
                        "per thread proc mmap processing timeout in ms"),
        OPT_END()