Oprofile Multiplexing Patch

This patch introduces multiplexing support for the Oprofile kernel
module. It basically adds a new function pointer in oprofile_operator
allowing each architecture to supply its callback to switch between
different sets of event when the timer expires. Userspace tools can
modify the time slice through /dev/oprofile/time_slice.

It also modifies the number of counters exposed to the userspace through
/dev/oprofile. For example, the number of counters for AMD CPUs are
changed to 32 and multiplexed in the sets of 4.

Signed-off-by: Jason Yeh <[email protected]>
Signed-off-by: Robert Richter <[email protected]>
Cc: oprofile-list <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

drivers/oprofile/oprof.c

@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/oprofile.h>
 #include <linux/moduleparam.h>
+#include <linux/workqueue.h>
+#include <linux/time.h>
 #include <asm/mutex.h>
 
 #include "oprof.h"
@@ -19,13 +21,18 @@
 #include "cpu_buffer.h"
 #include "buffer_sync.h"
 #include "oprofile_stats.h"
+
+static unsigned long is_setup;
+static void switch_worker(struct work_struct *work);
+static DECLARE_DELAYED_WORK(switch_work, switch_worker);
+static DEFINE_MUTEX(start_mutex);
  
 struct oprofile_operations oprofile_ops;
 
+unsigned long timeout_jiffies;
 unsigned long oprofile_started;
 unsigned long backtrace_depth;
-static unsigned long is_setup;
-static DEFINE_MUTEX(start_mutex);
+/* Multiplexing defaults at 1 msec*/
 
 /* timer
    0 - use performance monitoring hardware if available
@@ -87,6 +94,16 @@ out:
 	return err;
 }
 
+static void start_switch_worker(void)
+{
+	schedule_delayed_work(&switch_work, timeout_jiffies);
+}
+
+static void switch_worker(struct work_struct *work)
+{
+	if (!oprofile_ops.switch_events())
+		start_switch_worker();
+}
 
 /* Actually start profiling (echo 1>/dev/oprofile/enable) */
 int oprofile_start(void)
@@ -94,7 +111,6 @@ int oprofile_start(void)
 	int err = -EINVAL;
  
 	mutex_lock(&start_mutex);
- 
 	if (!is_setup)
 		goto out;
 
@@ -108,6 +124,9 @@ int oprofile_start(void)
 	if ((err = oprofile_ops.start()))
 		goto out;
 
+	if (oprofile_ops.switch_events)
+		start_switch_worker();
+
 	oprofile_started = 1;
 out:
 	mutex_unlock(&start_mutex);
@@ -123,6 +142,7 @@ void oprofile_stop(void)
 		goto out;
 	oprofile_ops.stop();
 	oprofile_started = 0;
+	cancel_delayed_work_sync(&switch_work);
 	/* wake up the daemon to read what remains */
 	wake_up_buffer_waiter();
 out:
@@ -155,6 +175,32 @@ post_sync:
 	mutex_unlock(&start_mutex);
 }
 
+/* User inputs in ms, converts to jiffies */
+int oprofile_set_timeout(unsigned long val_msec)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (oprofile_started) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	if (!oprofile_ops.switch_events) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	timeout_jiffies = msecs_to_jiffies(val_msec);
+	if (timeout_jiffies == MAX_JIFFY_OFFSET)
+		timeout_jiffies = msecs_to_jiffies(1);
+
+out:
+	mutex_unlock(&start_mutex);
+	return err;
+
+}
 
 int oprofile_set_backtrace(unsigned long val)
 {
@@ -179,10 +225,16 @@ out:
 	return err;
 }
 
+static void __init oprofile_switch_timer_init(void)
+{
+	timeout_jiffies = msecs_to_jiffies(1);
+}
+
 static int __init oprofile_init(void)
 {
 	int err;
 
+	oprofile_switch_timer_init();
 	err = oprofile_arch_init(&oprofile_ops);
 
 	if (err < 0 || timer) {

drivers/oprofile/oprof.h

@@ -27,7 +27,8 @@ extern unsigned long fs_buffer_watershed;
 extern struct oprofile_operations oprofile_ops;
 extern unsigned long oprofile_started;
 extern unsigned long backtrace_depth;
- 
+extern unsigned long timeout_jiffies;
+
 struct super_block;
 struct dentry;
 
@@ -35,5 +36,6 @@ void oprofile_create_files(struct super_block * sb, struct dentry * root);
 void oprofile_timer_init(struct oprofile_operations * ops);
 
 int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_timeout(unsigned long time);
  
 #endif /* OPROF_H */

drivers/oprofile/oprofile_files.c

@@ -9,6 +9,7 @@
 
 #include <linux/fs.h>
 #include <linux/oprofile.h>
+#include <linux/jiffies.h>
 
 #include "event_buffer.h"
 #include "oprofile_stats.h"
@@ -18,6 +19,40 @@ unsigned long fs_buffer_size = 131072;
 unsigned long fs_cpu_buffer_size = 8192;
 unsigned long fs_buffer_watershed = 32768; /* FIXME: tune */
 
+static ssize_t timeout_read(struct file *file, char __user *buf,
+		size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(jiffies_to_msecs(timeout_jiffies),
+				buf, count, offset);
+}
+
+
+static ssize_t timeout_write(struct file *file, char const __user *buf,
+		size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	retval = oprofile_set_timeout(val);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations timeout_fops = {
+	.read		= timeout_read,
+	.write		= timeout_write,
+};
+
+
 static ssize_t depth_read(struct file * file, char __user * buf, size_t count, loff_t * offset)
 {
 	return oprofilefs_ulong_to_user(backtrace_depth, buf, count, offset);
@@ -85,11 +120,10 @@ static ssize_t enable_write(struct file * file, char const __user * buf, size_t
 
 	if (*offset)
 		return -EINVAL;
-
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
 	if (retval)
 		return retval;
- 
+
 	if (val)
 		retval = oprofile_start();
 	else
@@ -129,6 +163,7 @@ void oprofile_create_files(struct super_block * sb, struct dentry * root)
 	oprofilefs_create_file(sb, root, "cpu_type", &cpu_type_fops); 
 	oprofilefs_create_file(sb, root, "backtrace_depth", &depth_fops);
 	oprofilefs_create_file(sb, root, "pointer_size", &pointer_size_fops);
+	oprofilefs_create_file(sb, root, "timeout_ms", &timeout_fops);
 	oprofile_create_stats_files(sb, root);
 	if (oprofile_ops.create_files)
 		oprofile_ops.create_files(sb, root);