[PATCH/RFC 2/8] numa - Migrate-on-Fault - add cpuset control

[Lee Schermerhorn <lee.schermerhorn@hp.com>]

Migrate-on-fault - add migrate on fault per cpuset control

Add a migrate_on_fault control file to cpusets.  Default is
disabled ['0'].  When set '1', enables migrate-on-fault for
tasks in the cpuset once they notice the flag:  for already
running tasks, this means after they update their cpuset memory
state.

To avoid adding #ifdefs to kernel/cpuset.c [at Paul Jackson's
request], most of the migrate-on-fault support is unconditionally
included in cpuset.c.  However, the control file will only be
created if migrate-on-fault is configured.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>

 include/linux/cpuset.h |   16 ++++++++++++++++
 include/linux/sched.h  |   19 +++++++++++++++++++
 kernel/cpuset.c        |   34 +++++++++++++++++++++++++++++++++-
 mm/Kconfig             |    1 +
 4 files changed, 69 insertions(+), 1 deletion(-)

Index: linux-2.6.36-mmotm-101103-1217/include/linux/sched.h
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/include/linux/sched.h
+++ linux-2.6.36-mmotm-101103-1217/include/linux/sched.h
@@ -1457,6 +1457,7 @@ struct task_struct {
 	short il_next;
 	short shared_huge_policy_enabled:1;
 	short shared_file_policy_enabled:1;
+	short migrate_on_fault_enabled:1;
 #endif
 	atomic_t fs_excl;	/* holding fs exclusive resources */
 	struct rcu_head rcu;
@@ -1905,6 +1906,24 @@ static int shared_file_policy_enabled(st
 {
 	return 0;
 }
+#endif
+
+#ifdef CONFIG_MIGRATE_ON_FAULT
+static inline void set_migrate_on_fault_enabled(struct task_struct *tsk,
+							int val)
+{
+	tsk->migrate_on_fault_enabled = !!val;
+}
+static inline int migrate_on_fault_enabled(struct task_struct *tsk)
+{
+	return tsk->migrate_on_fault_enabled;
+}
+#else
+static void set_shared_file_policy_enabled(struct task_struct *tsk, int val) { }
+static inline int migrate_on_fault_enabled(struct task_struct *tsk)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
Index: linux-2.6.36-mmotm-101103-1217/kernel/cpuset.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/kernel/cpuset.c
+++ linux-2.6.36-mmotm-101103-1217/kernel/cpuset.c
@@ -134,6 +134,7 @@ typedef enum {
 	CS_SPREAD_SLAB,
 	CS_SHARED_HUGE_POLICY,
  	CS_SHARED_FILE_POLICY,
+	CS_MIGRATE_ON_FAULT,
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
@@ -182,6 +183,11 @@ static inline int is_shared_file_policy(
 	return test_bit(CS_SHARED_FILE_POLICY, &cs->flags);
 }
 
+static inline int is_migrate_on_fault(const struct cpuset *cs)
+{
+	return test_bit(CS_MIGRATE_ON_FAULT,  &cs->flags);
+}
+
 static struct cpuset top_cpuset = {
 	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
 };
@@ -341,6 +347,12 @@ static void cpuset_update_task_cpuset_fl
 		set_shared_file_policy_enabled(tsk, 1);
 	else
 		set_shared_file_policy_enabled(tsk, 0);
+
+	if (is_migrate_on_fault(cs))
+		set_migrate_on_fault_enabled(tsk, 1);
+	else
+		set_migrate_on_fault_enabled(tsk, 0);
+
 }
 
 /*
@@ -1281,7 +1293,8 @@ static int update_flag(cpuset_flagbits_t
 	cpuset_flags_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
 			|| (is_spread_page(cs) != is_spread_page(trialcs))
 			|| (is_shared_huge_policy(cs) != is_shared_huge_policy(trialcs))
-			|| (is_shared_file_policy(cs) != is_shared_file_policy(trialcs)));
+			|| (is_shared_file_policy(cs) != is_shared_file_policy(trialcs))
+			|| (is_migrate_on_fault(cs) != is_migrate_on_fault(trialcs)));
 
 	mutex_lock(&callback_mutex);
 	cs->flags = trialcs->flags;
@@ -1519,6 +1532,7 @@ typedef enum {
 	FILE_SPREAD_SLAB,
 	FILE_SHARED_HUGE_POLICY,
 	FILE_SHARED_FILE_POLICY,
+	FILE_MIGRATE_ON_FAULT,
 } cpuset_filetype_t;
 
 static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
@@ -1564,6 +1578,9 @@ static int cpuset_write_u64(struct cgrou
 	case FILE_SHARED_FILE_POLICY:
 		retval = update_flag(CS_SHARED_FILE_POLICY, cs, val);
 		break;
+	case FILE_MIGRATE_ON_FAULT:
+		retval = update_flag(CS_MIGRATE_ON_FAULT, cs, val);
+		break;
 	default:
 		retval = -EINVAL;
 		break;
@@ -1732,6 +1749,8 @@ static u64 cpuset_read_u64(struct cgroup
 		return is_shared_huge_policy(cs);
 	case FILE_SHARED_FILE_POLICY:
 		return is_shared_file_policy(cs);
+	case FILE_MIGRATE_ON_FAULT:
+		return is_migrate_on_fault(cs);
 	default:
 		BUG();
 	}
@@ -1863,6 +1882,13 @@ static struct cftype cft_shared_file_pol
 	.private = FILE_SHARED_FILE_POLICY,
 };
 
+static struct cftype cft_migrate_on_fault = {
+	.name = "migrate_on_fault",
+	.read_u64 = cpuset_read_u64,
+	.write_u64 = cpuset_write_u64,
+	.private = FILE_MIGRATE_ON_FAULT,
+};
+
 static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	int err;
@@ -1879,6 +1905,10 @@ static int cpuset_populate(struct cgroup
 	err = add_shared_xxx_policy_file(cont, ss, &cft_shared_file_policy);
 	if (err < 0)
 		return err;
+	err = add_migrate_on_fault_file(cont, ss,
+						&cft_migrate_on_fault);
+	if (err < 0)
+		return err;
 	/* memory_pressure_enabled is in root cpuset only */
 	if (!cont->parent)
 		err = cgroup_add_file(cont, ss,
@@ -1957,6 +1987,8 @@ static struct cgroup_subsys_state *cpuse
 		set_bit(CS_SHARED_HUGE_POLICY, &cs->flags);
 	if (is_shared_file_policy(parent))
 		set_bit(CS_SHARED_FILE_POLICY, &cs->flags);
+	if (is_migrate_on_fault(parent))
+		set_bit(CS_MIGRATE_ON_FAULT, &cs->flags);
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
 	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
Index: linux-2.6.36-mmotm-101103-1217/mm/Kconfig
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/mm/Kconfig
+++ linux-2.6.36-mmotm-101103-1217/mm/Kconfig
@@ -204,6 +204,7 @@ config MIGRATE_ON_FAULT
 	bool "Migrate unmapped page on fault"
 	depends on MIGRATION
 	depends on SWAP
+	select CPUSETS
 	help
 	  Allows "misplaced" pages found in a page cache at fault time to be
 	  migrated to the node specified by the applicable policy when the
Index: linux-2.6.36-mmotm-101103-1217/include/linux/cpuset.h
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/include/linux/cpuset.h
+++ linux-2.6.36-mmotm-101103-1217/include/linux/cpuset.h
@@ -148,6 +148,22 @@ static inline int add_shared_xxx_policy_
 }
 #endif
 
+#ifdef CONFIG_MIGRATE_ON_FAULT
+static inline int add_migrate_on_fault_file(struct cgroup *cg,
+						struct cgroup_subsys *ss,
+						struct cftype *cft)
+{
+	return cgroup_add_file(cg, ss, cft);
+}
+#else
+static inline int add_migrate_on_fault_file(struct cgroup *cont,
+						struct cgroup_subsys *ss,
+						struct cftype *cft)
+{
+	return 0;
+}
+#endif
+
 extern void __init cpuset_init_shared_huge_policy(int dflt);
 extern void __init cpuset_init_shared_file_policy(int dflt);