[PATCH] per-task-delay-accounting: setup

Initialization code related to collection of per-task "delay" statistics which
measure how long it had to wait for cpu, sync block io, swapping etc.  The
collection of statistics and the interface are in other patches.  This patch
sets up the data structures and allows the statistics collection to be
disabled through a kernel boot parameter.

Signed-off-by: Shailabh Nagar <nagar@watson.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>

4 files changed, 92 insertions, 0 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 47dbcd570cd..87bb34cc893 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
+obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
new file mode 100644
index 00000000000..fbf7f228495
--- /dev/null
+++ b/kernel/delayacct.c
@@ -0,0 +1,87 @@
+/* delayacct.c - per-task delay accounting
+ *
+ * Copyright (C) Shailabh Nagar, IBM Corp. 2006
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/sysctl.h>
+#include <linux/delayacct.h>
+
+int delayacct_on __read_mostly;	/* Delay accounting turned on/off */
+kmem_cache_t *delayacct_cache;
+
+static int __init delayacct_setup_enable(char *str)
+{
+	delayacct_on = 1;
+	return 1;
+}
+__setup("delayacct", delayacct_setup_enable);
+
+void delayacct_init(void)
+{
+	delayacct_cache = kmem_cache_create("delayacct_cache",
+					sizeof(struct task_delay_info),
+					0,
+					SLAB_PANIC,
+					NULL, NULL);
+	delayacct_tsk_init(&init_task);
+}
+
+void __delayacct_tsk_init(struct task_struct *tsk)
+{
+	tsk->delays = kmem_cache_zalloc(delayacct_cache, SLAB_KERNEL);
+	if (tsk->delays)
+		spin_lock_init(&tsk->delays->lock);
+}
+
+void __delayacct_tsk_exit(struct task_struct *tsk)
+{
+	kmem_cache_free(delayacct_cache, tsk->delays);
+	tsk->delays = NULL;
+}
+
+/*
+ * Start accounting for a delay statistic using
+ * its starting timestamp (@start)
+ */
+
+static inline void delayacct_start(struct timespec *start)
+{
+	do_posix_clock_monotonic_gettime(start);
+}
+
+/*
+ * Finish delay accounting for a statistic using
+ * its timestamps (@start, @end), accumalator (@total) and @count
+ */
+
+static void delayacct_end(struct timespec *start, struct timespec *end,
+				u64 *total, u32 *count)
+{
+	struct timespec ts;
+	s64 ns;
+
+	do_posix_clock_monotonic_gettime(end);
+	ts = timespec_sub(*end, *start);
+	ns = timespec_to_ns(&ts);
+	if (ns < 0)
+		return;
+
+	spin_lock(&current->delays->lock);
+	*total += ns;
+	(*count)++;
+	spin_unlock(&current->delays->lock);
+}
+
diff --git a/kernel/exit.c b/kernel/exit.c
index 6664c084783..3c2cf91defa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -25,6 +25,7 @@
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/mempolicy.h>
+#include <linux/delayacct.h>
 #include <linux/cpuset.h>
 #include <linux/syscalls.h>
 #include <linux/signal.h>
@@ -900,6 +901,7 @@ fastcall NORET_TYPE void do_exit(long code)
 #endif
 	if (unlikely(tsk->audit_context))
 		audit_free(tsk);
+	delayacct_tsk_exit(tsk);
 	exit_mm(tsk);
 
 	if (group_dead)
diff --git a/kernel/fork.c b/kernel/fork.c
index 926e5a68ea9..451cfd35bf2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -43,6 +43,7 @@
 #include <linux/rmap.h>
 #include <linux/acct.h>
 #include <linux/cn_proc.h>
+#include <linux/delayacct.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1000,6 +1001,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_put_domain;
 
 	p->did_exec = 0;
+	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	copy_flags(clone_flags, p);
 	p->pid = pid;
 	retval = -EFAULT;