perf trace: Handle legacy syscalls tracepoints

Currently the code skips the first field with the expectation that it is 'nr'.
But older kernels do not have the 'nr' field:

    field:int nr;   offset:8;   size:4; signed:1;

Change perf-trace to drop the field if it exists after parsing the format file.

This fixes the off-by-one problem with older kernels (e.g., RHEL6). e.g,
perf-trace shows this for write:

  1.515 ( 0.006 ms): dd/4245 write(buf: 2</dev/pts/0>, count: 140733837536224       ) = 26

where 2 is really the fd, the huge number is really the buf address, etc.  With
this patch you get the more appropriate:

  1.813 ( 0.003 ms): dd/6330 write(fd: 2</dev/pts/0>, buf: 0x7fff22fc81f0, count: 25) = 25

Based-on-a-patch-by: David Ahern <dsahern@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gvpdave4u2yq2jnzbcdznpvf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 14 insertions, 4 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6af6bcec930e..001c6ae9a1b1 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1135,6 +1135,8 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 
 struct syscall {
         struct event_format *tp_format;
+        int                 nr_args;
+        struct format_field *args;
         const char          *name;
         bool                filtered;
         bool                is_exit;
@@ -1442,14 +1444,14 @@ static int syscall__set_arg_fmts(struct syscall *sc)
         struct format_field *field;
         int idx = 0;
 
-        sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *));
+        sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
         if (sc->arg_scnprintf == NULL)
                 return -1;
 
         if (sc->fmt)
                 sc->arg_parm = sc->fmt->arg_parm;
 
-        for (field = sc->tp_format->format.fields->next; field; field = field->next) {
+        for (field = sc->args; field; field = field->next) {
                 if (sc->fmt && sc->fmt->arg_scnprintf[idx])
                         sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
                 else if (field->flags & FIELD_IS_POINTER)
@@ -1515,6 +1517,14 @@ static int trace__read_syscall_info(struct trace *trace, int id)
         if (sc->tp_format == NULL)
                 return -1;
 
+        sc->args = sc->tp_format->format.fields;
+        sc->nr_args = sc->tp_format->format.nr_fields;
+        /* drop nr field - not relevant here; does not exist on older kernels */
+        if (sc->args && strcmp(sc->args->name, "nr") == 0) {
+                sc->args = sc->args->next;
+                --sc->nr_args;
+        }
+
         sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
 
         return syscall__set_arg_fmts(sc);
@@ -1537,7 +1547,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
         unsigned char *p;
         unsigned long val;
 
-        if (sc->tp_format != NULL) {
+        if (sc->args != NULL) {
                 struct format_field *field;
                 u8 bit = 1;
                 struct syscall_arg arg = {
@@ -1547,7 +1557,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                         .thread = thread,
                 };
 
-                for (field = sc->tp_format->format.fields->next; field;
+                for (field = sc->args; field;
                      field = field->next, ++arg.idx, bit <<= 1) {
                         if (arg.mask & bit)
                                 continue;