[PATCH] per-task-delay-accounting: delay accounting usage of taskstats interface

Usage of taskstats interface by delay accounting.

Signed-off-by: Shailabh Nagar <nagar@us.ibm.com>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>
Cc: Jes Sorensen <jes@sgi.com>
Cc: Peter Chubb <peterc@gelato.unsw.edu.au>
Cc: Erich Focht <efocht@ess.nec.de>
Cc: Levent Serinol <lserinol@gmail.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 72 insertions, 6 deletions

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 3546b0800f9..1be274a462c 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -41,6 +41,10 @@ void delayacct_init(void)
 
 void __delayacct_tsk_init(struct task_struct *tsk)
 {
+	spin_lock_init(&tsk->delays_lock);
+	/* No need to acquire tsk->delays_lock for allocation here unless
+	   __delayacct_tsk_init called after tsk is attached to tasklist
+	*/
 	tsk->delays = kmem_cache_zalloc(delayacct_cache, SLAB_KERNEL);
 	if (tsk->delays)
 		spin_lock_init(&tsk->delays->lock);
@@ -48,8 +52,11 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 
 void __delayacct_tsk_exit(struct task_struct *tsk)
 {
-	kmem_cache_free(delayacct_cache, tsk->delays);
+	struct task_delay_info *delays = tsk->delays;
+	spin_lock(&tsk->delays_lock);
 	tsk->delays = NULL;
+	spin_unlock(&tsk->delays_lock);
+	kmem_cache_free(delayacct_cache, delays);
 }
 
 /*
@@ -104,3 +111,56 @@ void __delayacct_blkio_end(void)
 			&current->delays->blkio_delay,
 			&current->delays->blkio_count);
 }
+
+int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
+{
+	s64 tmp;
+	struct timespec ts;
+	unsigned long t1,t2,t3;
+
+	spin_lock(&tsk->delays_lock);
+
+	/* Though tsk->delays accessed later, early exit avoids
+	 * unnecessary returning of other data
+	 */
+	if (!tsk->delays)
+		goto done;
+
+	tmp = (s64)d->cpu_run_real_total;
+	cputime_to_timespec(tsk->utime + tsk->stime, &ts);
+	tmp += timespec_to_ns(&ts);
+	d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
+
+	/*
+	 * No locking available for sched_info (and too expensive to add one)
+	 * Mitigate by taking snapshot of values
+	 */
+	t1 = tsk->sched_info.pcnt;
+	t2 = tsk->sched_info.run_delay;
+	t3 = tsk->sched_info.cpu_time;
+
+	d->cpu_count += t1;
+
+	jiffies_to_timespec(t2, &ts);
+	tmp = (s64)d->cpu_delay_total + timespec_to_ns(&ts);
+	d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp;
+
+	tmp = (s64)d->cpu_run_virtual_total + (s64)jiffies_to_usecs(t3) * 1000;
+	d->cpu_run_virtual_total =
+		(tmp < (s64)d->cpu_run_virtual_total) ?	0 : tmp;
+
+	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
+
+	spin_lock(&tsk->delays->lock);
+	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
+	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
+	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
+	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
+	d->blkio_count += tsk->delays->blkio_count;
+	d->swapin_count += tsk->delays->swapin_count;
+	spin_unlock(&tsk->delays->lock);
+
+done:
+	spin_unlock(&tsk->delays_lock);
+	return 0;
+}
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 82ec9137d90..ea9506de3b8 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -18,13 +18,13 @@
 
 #include <linux/kernel.h>
 #include <linux/taskstats_kern.h>
+#include <linux/delayacct.h>
 #include <net/genetlink.h>
 #include <asm/atomic.h>
 
 static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 };
 static int family_registered;
 kmem_cache_t *taskstats_cache;
-static DEFINE_MUTEX(taskstats_exit_mutex);
 
 static struct genl_family family = {
 	.id		= GENL_ID_GENERATE,
@@ -120,7 +120,10 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk,
 	 *		goto err;
 	 */
 
-err:
+	rc = delayacct_add_tsk(stats, tsk);
+	stats->version = TASKSTATS_VERSION;
+
+	/* Define err: label here if needed */
 	put_task_struct(tsk);
 	return rc;
 
@@ -152,8 +155,14 @@ static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk,
 		 *		break;
 		 */
 
+		rc = delayacct_add_tsk(stats, tsk);
+		if (rc)
+			break;
+
 	} while_each_thread(first, tsk);
 	read_unlock(&tasklist_lock);
+	stats->version = TASKSTATS_VERSION;
+
 
 	/*
 	 * Accounting subsytems can also add calls here if they don't
@@ -233,8 +242,6 @@ void taskstats_exit_send(struct task_struct *tsk, struct taskstats *tidstats,
 	if (!family_registered || !tidstats)
 		return;
 
-	mutex_lock(&taskstats_exit_mutex);
-
 	is_thread_group = !thread_group_empty(tsk);
 	rc = 0;
 
@@ -292,7 +299,6 @@ nla_put_failure:
 err_skb:
 	nlmsg_free(rep_skb);
 ret:
-	mutex_unlock(&taskstats_exit_mutex);
 	return;
 }