perf trace: Exclude the kernel part of the callchain leading to a syscall

[deliverable/linux.git] / tools / perf / builtin-trace.c

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8440e2b92c6c42d7c88d72bf67a19eac685bccb4..cfa5ce8fdb7bf881151282ef58490b5591eadbf5 100644 (file)
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -34,8 +34,10 @@
 #include "trace-event.h"
 #include "util/parse-events.h"
 #include "util/bpf-loader.h"
+#include "callchain.h"
+#include "syscalltbl.h"
 
-#include <libaudit.h>
+#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <linux/futex.h>
@@ -114,10 +116,7 @@
 
 struct trace {
        struct perf_tool        tool;
-       struct {
-               int             machine;
-               int             open_id;
-       }                       audit;
+       struct syscalltbl       *sctbl;
        struct {
                int             max;
                struct syscall  *table;
@@ -160,9 +159,11 @@ struct trace {
        bool                    show_comm;
        bool                    show_tool_stats;
        bool                    trace_syscalls;
+       bool                    kernel_syscallchains;
        bool                    force;
        bool                    vfs_getname;
        int                     trace_pgfaults;
+       int                     open_id;
 };
 
 struct tp_field {
@@ -1780,7 +1781,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 {
        char tp_name[128];
        struct syscall *sc;
-       const char *name = audit_syscall_to_name(id, trace->audit.machine);
+       const char *name = syscalltbl__name(trace->sctbl, id);
 
        if (name == NULL)
                return -1;
@@ -1855,7 +1856,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
        strlist__for_each(pos, trace->ev_qualifier) {
                const char *sc = pos->s;
-               int id = audit_name_to_syscall(sc, trace->audit.machine);
+               int id = syscalltbl__id(trace->sctbl, sc);
 
                if (id < 0) {
                        if (err == 0) {
@@ -2137,7 +2138,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
        ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
-       if (id == trace->audit.open_id && ret >= 0 && ttrace->filename.pending_open) {
+       if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
                trace__set_fd_pathname(thread, ret, ttrace->filename.name);
                ttrace->filename.pending_open = false;
                ++trace->stats.vfs_getname;
@@ -2191,6 +2192,21 @@ signed_print:
                goto signed_print;
 
        fputc('\n', trace->output);
+
+       if (sample->callchain) {
+               struct addr_location al;
+               /* TODO: user-configurable print_opts */
+               const unsigned int print_opts = PRINT_IP_OPT_SYM
+                                             | PRINT_IP_OPT_DSO;
+
+               if (machine__resolve(trace->host, &al, sample) < 0) {
+                       pr_err("problem processing %d event, skipping it.\n",
+                              event->header.type);
+                       goto out_put;
+               }
+               perf_evsel__fprintf_callchain(evsel, sample, &al, 38, print_opts,
+                                             scripting_max_stack, trace->output);
+       }
 out:
        ttrace->entry_pending = false;
        err = 0;
@@ -2646,6 +2662,15 @@ static int trace__add_syscall_newtp(struct trace *trace)
        perf_evlist__add(evlist, sys_enter);
        perf_evlist__add(evlist, sys_exit);
 
+       if (trace->opts.callgraph_set && !trace->kernel_syscallchains) {
+               /*
+                * We're interested only in the user space callchain
+                * leading to the syscall, allow overriding that for
+                * debugging reasons using --kernel_syscall_callchains
+                */
+               sys_exit->attr.exclude_callchain_kernel = 1;
+       }
+
        trace->syscalls.events.sys_enter = sys_enter;
        trace->syscalls.events.sys_exit  = sys_exit;
 
@@ -3189,10 +3214,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                NULL
        };
        struct trace trace = {
-               .audit = {
-                       .machine = audit_detect_machine(),
-                       .open_id = audit_name_to_syscall("open", trace.audit.machine),
-               },
                .syscalls = {
                        . max = -1,
                },
@@ -3210,6 +3231,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                .output = stderr,
                .show_comm = true,
                .trace_syscalls = true,
+               .kernel_syscallchains = false,
        };
        const char *output_name = NULL;
        const char *ev_qualifier_str = NULL;
@@ -3255,6 +3277,11 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Trace pagefaults", parse_pagefaults, "maj"),
        OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
        OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
+       OPT_CALLBACK(0, "call-graph", &trace.opts,
+                    "record_mode[,record_size]", record_callchain_help,
+                    &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, "proc-map-timeout", &trace.opts.proc_map_timeout,
                        "per thread proc mmap processing timeout in ms"),
        OPT_END()
@@ -3267,8 +3294,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
        signal(SIGFPE, sighandler_dump_stack);
 
        trace.evlist = perf_evlist__new();
+       trace.sctbl = syscalltbl__new();
 
-       if (trace.evlist == NULL) {
+       if (trace.evlist == NULL || trace.sctbl == NULL) {
                pr_err("Not enough memory to run!\n");
                err = -ENOMEM;
                goto out;
@@ -3277,11 +3305,21 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
        argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
                                 trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
+       err = bpf__setup_stdout(trace.evlist);
+       if (err) {
+               bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
+               pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
+               goto out;
+       }
+
        if (trace.trace_pgfaults) {
                trace.opts.sample_address = true;
                trace.opts.sample_time = true;
        }
 
+       if (trace.opts.callgraph_set)
+               symbol_conf.use_callchain = true;
+
        if (trace.evlist->nr_entries > 0)
                evlist__set_evsel_handler(trace.evlist, trace__event_handler);
 
@@ -3306,6 +3344,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                }
        }
 
+       trace.open_id = syscalltbl__id(trace.sctbl, "open");
+
        if (ev_qualifier_str != NULL) {
                const char *s = ev_qualifier_str;
                struct strlist_config slist_config = {