[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>

4 files changed, 71 insertions, 1 deletions

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 0ecbf9aad8e1..d955078a1441 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -18,6 +18,7 @@
 #define _LINUX_DELAYACCT_H
 
 #include <linux/sched.h>
+#include <linux/taskstats_kern.h>
 
 /*
  * Per-task flags relevant to delay accounting
@@ -35,6 +36,7 @@ extern void __delayacct_tsk_init(struct task_struct *);
 extern void __delayacct_tsk_exit(struct task_struct *);
 extern void __delayacct_blkio_start(void);
 extern void __delayacct_blkio_end(void);
+extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 
 static inline void delayacct_set_flag(int flag)
 {
@@ -74,6 +76,16 @@ static inline void delayacct_blkio_end(void)
                 __delayacct_blkio_end();
 }
 
+static inline int delayacct_add_tsk(struct taskstats *d,
+                                        struct task_struct *tsk)
+{
+        if (likely(!delayacct_on))
+                return -EINVAL;
+        if (!tsk->delays)
+                return 0;
+        return __delayacct_add_tsk(d, tsk);
+}
+
 #else
 static inline void delayacct_set_flag(int flag)
 {}
@@ -89,6 +101,9 @@ static inline void delayacct_blkio_start(void)
 {}
 static inline void delayacct_blkio_end(void)
 {}
+static inline int delayacct_add_tsk(struct taskstats *d,
+                                        struct task_struct *tsk)
+{ return 0; }
 #endif /* CONFIG_TASK_DELAY_ACCT */
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f751062d89a2..3c5610ca0c92 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -990,6 +990,7 @@ struct task_struct {
          */
         struct pipe_inode_info *splice_pipe;
 #ifdef  CONFIG_TASK_DELAY_ACCT
+        spinlock_t delays_lock;
         struct task_delay_info *delays;
 #endif
 };
diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h
index 51f62759bea9..c6aeca32348e 100644
--- a/include/linux/taskstats.h
+++ b/include/linux/taskstats.h
@@ -34,7 +34,60 @@
 struct taskstats {
 
         /* Version 1 */
-        __u64   version;
+        __u16   version;
+        __u16   padding[3];     /* Userspace should not interpret the padding
+                                 * field which can be replaced by useful
+                                 * fields if struct taskstats is extended.
+                                 */
+
+        /* Delay accounting fields start
+         *
+         * All values, until comment "Delay accounting fields end" are
+         * available only if delay accounting is enabled, even though the last
+         * few fields are not delays
+         *
+         * xxx_count is the number of delay values recorded
+         * xxx_delay_total is the corresponding cumulative delay in nanoseconds
+         *
+         * xxx_delay_total wraps around to zero on overflow
+         * xxx_count incremented regardless of overflow
+         */
+
+        /* Delay waiting for cpu, while runnable
+         * count, delay_total NOT updated atomically
+         */
+        __u64   cpu_count;
+        __u64   cpu_delay_total;
+
+        /* Following four fields atomically updated using task->delays->lock */
+
+        /* Delay waiting for synchronous block I/O to complete
+         * does not account for delays in I/O submission
+         */
+        __u64   blkio_count;
+        __u64   blkio_delay_total;
+
+        /* Delay waiting for page fault I/O (swap in only) */
+        __u64   swapin_count;
+        __u64   swapin_delay_total;
+
+        /* cpu "wall-clock" running time
+         * On some architectures, value will adjust for cpu time stolen
+         * from the kernel in involuntary waits due to virtualization.
+         * Value is cumulative, in nanoseconds, without a corresponding count
+         * and wraps around to zero silently on overflow
+         */
+        __u64   cpu_run_real_total;
+
+        /* cpu "virtual" running time
+         * Uses time intervals seen by the kernel i.e. no adjustment
+         * for kernel's involuntary waits due to virtualization.
+         * Value is cumulative, in nanoseconds, without a corresponding count
+         * and wraps around to zero silently on overflow
+         */
+        __u64   cpu_run_virtual_total;
+        /* Delay accounting fields end */
+        /* version 1 ends here */
 };
 
 
diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h
index bd0ecb969c26..fc9da2e26443 100644
--- a/include/linux/taskstats_kern.h
+++ b/include/linux/taskstats_kern.h
@@ -17,6 +17,7 @@ enum {
 
 #ifdef CONFIG_TASKSTATS
 extern kmem_cache_t *taskstats_cache;
+extern struct mutex taskstats_exit_mutex;
 
 static inline void taskstats_exit_alloc(struct taskstats **ptidstats,
                                         struct taskstats **ptgidstats)