[PATCH] Add pgcollapse controls to task_struct

[Alex Thorlton]

This patch just adds the necessary bits to the task_struct so that the scans can
eventually be controlled on a per-mm basis.  As I mentioned previously, we might
want to add some more counters here.

Signed-off-by: Alex Thorlton <athorlton@xxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Bob Liu <lliubbo@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx

---
 include/linux/sched.h | 12 ++++++++++++
 kernel/fork.c         |  6 ++++++
 2 files changed, 18 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e344bb..109be66 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1661,6 +1661,18 @@ struct task_struct {
 	unsigned int	sequential_io;
 	unsigned int	sequential_io_avg;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct callback_head pgcollapse_work;
+	/* default scan 8*512 pte (or vmas) every 30 second */
+	unsigned int pgcollapse_pages_to_scan;
+	unsigned int pgcollapse_pages_collapsed;
+	unsigned int pgcollapse_full_scans;
+	unsigned int pgcollapse_scan_sleep_millisecs;
+	/* during fragmentation poll the hugepage allocator once every minute */
+	unsigned int pgcollapse_alloc_sleep_millisecs;
+	unsigned long pgcollapse_last_scan;
+	unsigned long pgcollapse_scan_address;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b7d746..8c55309 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1355,6 +1355,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* need to pull these values from sysctl or something */
+	p->pgcollapse_pages_to_scan = HPAGE_PMD_NR * 8;
+	p->pgcollapse_scan_sleep_millisecs = 10000;
+	p->pgcollapse_alloc_sleep_millisecs = 60000;
+#endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	retval = sched_fork(clone_flags, p);
-- 
1.7.12.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/