perf trace: Pass augmented args to the arg formatters when available

If the tracepoint payload is bigger than what a syscall expected from
what is in its format file in tracefs, then that will be used as
augmented args, i.e. the expansion of syscall arg pointers, with things
like a filename, structs, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-bsbqx7xi2ot4q9bf570f7tqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 22ab8e67c7600865d7fc7a884feba24f15bbe66b..7deae6c8cb2555683ab02e57b5eb63f3e1300813 100644 (file)
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -856,10 +856,12 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
        struct event_format *tp_format;
        int                 nr_args;
+       int                 args_size;
        bool                is_exit;
        bool                is_open;
        struct format_field *args;
@@ -1258,10 +1260,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-       struct format_field *field;
+       struct format_field *field, *last_field = NULL;
        int idx = 0, len;
 
        for (field = sc->args; field; field = field->next, ++idx) {
+               last_field = field;
+
                if (sc->fmt && sc->fmt->arg[idx].scnprintf)
                        continue;
 
@@ -1292,6 +1296,9 @@ static int syscall__set_arg_fmts(struct syscall *sc)
                }
        }
 
+       if (last_field)
+               sc->args_size = last_field->offset + last_field->size;
+
        return 0;
 }
 
@@ -1472,14 +1479,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 }
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
-                                     unsigned char *args, struct trace *trace,
-                                     struct thread *thread)
+                                     unsigned char *args, void *augmented_args, int augmented_args_size,
+                                     struct trace *trace, struct thread *thread)
 {
        size_t printed = 0;
        unsigned long val;
        u8 bit = 1;
        struct syscall_arg arg = {
                .args   = args,
+               .augmented = {
+                       .size = augmented_args_size,
+                       .args = augmented_args,
+               },
                .idx    = 0,
                .mask   = 0,
                .trace  = trace,
@@ -1692,7 +1703,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
        printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
 
        printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
-                                          args, trace, thread);
+                                          args, NULL, 0, trace, thread);
 
        if (sc->is_exit) {
                if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
@@ -1723,7 +1734,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
        int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
        struct syscall *sc = trace__syscall_info(trace, evsel, id);
        char msg[1024];
-       void *args;
+       void *args, *augmented_args = NULL;
+       int augmented_args_size;
 
        if (sc == NULL)
                return -1;
@@ -1738,7 +1750,11 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
                goto out_put;
 
        args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-       syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+       augmented_args_size = sample->raw_size - sc->args_size;
+       if (augmented_args_size > 0)
+               augmented_args = sample->raw_data + sc->args_size;
+
+       syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
        fprintf(trace->output, "%s", msg);
        err = 0;
 out_put:

diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 9615af5d412b1a93622e130ad19a7b8ea325f4ce..6ca044d3d851688106d84bca526394f816fdc9ce 100644 (file)
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -30,9 +30,34 @@ struct thread;
 
 size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
 
+/**
+ * augmented_arg: extra payload for syscall pointer arguments
+ 
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
+ * then its the arguments contents, so that we can show more than just a
+ * pointer. This will be done initially with eBPF, the start of that is at the
+ * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
+ * will eventually be done automagically caching the running kernel tracefs
+ * events data into an eBPF C script, that then gets compiled and its .o file
+ * cached for subsequent use. For char pointers like the ones for 'open' like
+ * syscalls its easy, for the rest we should use DWARF or better, BTF, much
+ * more compact.
+ *
+ * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
+ * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
+ * @value: u64 aligned, for structs, pathnames
+ */
+struct augmented_arg {
+       int  size;
+       int  int_arg;
+       u64  value[];
+};
+
 /**
  * @val: value of syscall argument being formatted
  * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
+ * @augmented_args_size: augmented_args total payload size
  * @thread: tid state (maps, pid, tid, etc)
  * @trace: 'perf trace' internals: all threads, etc
  * @parm: private area, may be an strarray, for instance
@@ -43,6 +68,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
 struct syscall_arg {
        unsigned long val;
        unsigned char *args;
+       struct {
+               struct augmented_arg *args;
+               int                  size;
+       } augmented;
        struct thread *thread;
        struct trace  *trace;
        void          *parm;