perf stat: Change and clean up sys_perf_event_open error handling

This patch makes several changes to "perf stat":

- "perf stat" will no longer go ahead and run the application when one or
more of the specified events could not be opened.
- Use error() and die() instead of pr_err() so that the output is more
consistent with "perf top" and "perf record".
- Handle permission errors in a more robust way, and in a similar way to
"perf record" and "perf top".

In addition, the sys_perf_event_open() error handling of "perf top" and "perf
record" is made more consistent and adds the following phrase when an event
doesn't open (with something ther than an access or permission error):

"/bin/dmesg may provide additional information."

This is added because kernel code doesn't have a good way of expressing
detailed errors to user space, so its only avenue is to use printk's.  However,
many users may not think of looking at dmesg to find out why an event is being
rejected.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <fweisbec@gmail.com>
Cc: Ian Munsie <ianmunsi@au1.ibm.com>
Cc: Michael Ellerman <michaele@au1.ibm.com>
LKML-Reference: <1290217044-26293-1-git-send-email-cjashfor@linux.vnet.ibm.com>
Signed-off-by: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-record.c

@@ -326,7 +326,7 @@ static void create_counter(int counter, int cpu)
 				goto try_again;
 			}
 			printf("\n");
-			error("perfcounter syscall returned with %d (%s)\n",
+			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
 					fd[nr_cpu][counter][thread_index], strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)

tools/perf/builtin-stat.c

@@ -153,9 +153,9 @@ struct stats			walltime_nsecs_stats;
 	 attrs[counter].config == PERF_COUNT_##c)
 
 #define ERR_PERF_OPEN \
-"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
+"counter %d, sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information."
 
-static int create_perf_stat_counter(int counter)
+static int create_perf_stat_counter(int counter, bool *perm_err)
 {
 	struct perf_event_attr *attr = attrs + counter;
 	int thread;
@@ -171,11 +171,14 @@ static int create_perf_stat_counter(int counter)
 		for (cpu = 0; cpu < nr_cpus; cpu++) {
 			fd[cpu][counter][0] = sys_perf_event_open(attr,
 					-1, cpumap[cpu], -1, 0);
-			if (fd[cpu][counter][0] < 0)
-				pr_debug(ERR_PERF_OPEN, counter,
+			if (fd[cpu][counter][0] < 0) {
+				if (errno == EPERM || errno == EACCES)
+					*perm_err = true;
+				error(ERR_PERF_OPEN, counter,
 					 fd[cpu][counter][0], strerror(errno));
-			else
+			} else {
 				++ncreated;
+			}
 		}
 	} else {
 		attr->inherit = !no_inherit;
@@ -186,12 +189,15 @@ static int create_perf_stat_counter(int counter)
 		for (thread = 0; thread < thread_num; thread++) {
 			fd[0][counter][thread] = sys_perf_event_open(attr,
 				all_tids[thread], -1, -1, 0);
-			if (fd[0][counter][thread] < 0)
-				pr_debug(ERR_PERF_OPEN, counter,
+			if (fd[0][counter][thread] < 0) {
+				if (errno == EPERM || errno == EACCES)
+					*perm_err = true;
+				error(ERR_PERF_OPEN, counter,
 					 fd[0][counter][thread],
 					 strerror(errno));
-			else
+			} else {
 				++ncreated;
+			}
 		}
 	}
 
@@ -332,6 +338,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 	int status = 0;
 	int counter, ncreated = 0;
 	int child_ready_pipe[2], go_pipe[2];
+	bool perm_err = false;
 	const bool forks = (argc > 0);
 	char buf;
 
@@ -390,12 +397,15 @@ static int run_perf_stat(int argc __used, const char **argv)
 	}
 
 	for (counter = 0; counter < nr_counters; counter++)
-		ncreated += create_perf_stat_counter(counter);
+		ncreated += create_perf_stat_counter(counter, &perm_err);
 
-	if (ncreated == 0) {
-		pr_err("No permission to collect %sstats.\n"
-		       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
-		       system_wide ? "system-wide " : "");
+	if (ncreated < nr_counters) {
+		if (perm_err)
+			error("You may not have permission to collect %sstats.\n"
+			      "\t Consider tweaking"
+			      " /proc/sys/kernel/perf_event_paranoid or running as root.",
+			      system_wide ? "system-wide " : "");
+		die("Not all events could be opened.\n");
 		if (child_pid != -1)
 			kill(child_pid, SIGTERM);
 		return -1;

tools/perf/builtin-top.c

@@ -1214,7 +1214,9 @@ static void start_counter(int i, int counter)
 			int err = errno;
 
 			if (err == EPERM || err == EACCES)
-				die("No permission - are you root?\n");
+				die("Permission error - are you root?\n"
+					"\t Consider tweaking"
+					" /proc/sys/kernel/perf_event_paranoid.\n");
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
@@ -1231,7 +1233,7 @@ static void start_counter(int i, int counter)
 				goto try_again;
 			}
 			printf("\n");
-			error("perfcounter syscall returned with %d (%s)\n",
+			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
 					fd[i][counter][thread_index], strerror(err));
 			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 			exit(-1);