perf_counter tools: Handle kernels with !CONFIG_PERF_COUNTER

If perf is run on a !CONFIG_PERF_COUNTER kernel right now it
bails out with no messages or with confusing messages.

Standardize this case some more and explain the situation.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8786629..deaee42 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -356,9 +356,6 @@
 	if (fd[nr_cpu][counter] < 0) {
 		int err = errno;
 
-		if (verbose)
-			error("sys_perf_counter_open() syscall returned with %d (%s)\n",
-				fd[nr_cpu][counter], strerror(err));
 		if (err == EPERM)
 			die("Permission error - are you root?\n");
 
@@ -376,6 +373,10 @@
 			attr->config = PERF_COUNT_CPU_CLOCK;
 			goto try_again;
 		}
+		printf("\n");
+		error("perfcounter syscall returned with %d (%s)\n",
+			fd[nr_cpu][counter], strerror(err));
+		die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n");
 		exit(-1);
 	}