[RFC PATCH 2/2] sched: Remove SD_WAKE_AFFINE flag and replace it with SD_BALANCE_WAKE

[Yuyang Du]

SD_BALANCE_{FORK|EXEC|WAKE} flags are for select_task_rq() to select a
CPU to run a new task or a waking task. SD_WAKE_AFFINE is a flag to
try selecting the waker CPU to run the waking task.

SD_BALANCE_WAKE is not a sched_domain flag, but SD_WAKE_AFFINE is.
Conceptually, SD_BALANCE_WAKE should be a sched_domain flag just like
the other two, so we first make SD_BALANCE_WAKE a sched_domain flag.

Moreover, the semantic of SD_WAKE_AFFINE is included in the semantic
of SD_BALANCE_WAKE. When in wakeup balancing, it is natual to try
the waker CPU if the waker CPU is allowed, in that sense, we don't
need a separate flag to specify it, not mentioning that SD_WAKE_AFFINE
is almost enabled in every sched_domains.

With the above combined, there is no need to have SD_WAKE_AFFINE, so
we remove and replace it with SD_BALANCE_WAKE. This can be accomplished
without any functionality change.

Signed-off-by: Yuyang Du <yuyang.du@xxxxxxxxx>
---
 include/linux/sched.h   |    1 -
 kernel/sched/core.c     |    7 +++----
 kernel/sched/deadline.c |    2 +-
 kernel/sched/fair.c     |    9 ++++-----
 kernel/sched/rt.c       |    2 +-
 5 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c39244d..fca0c39 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1014,7 +1014,6 @@ extern void wake_up_q(struct wake_q_head *head);
 #define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
-#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
 #define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu power */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e00b8ea..2206fe1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5670,7 +5670,7 @@ static int sd_degenerate(struct sched_domain *sd)
 	}
 
 	/* Following flags don't use groups */
-	if (sd->flags & (SD_WAKE_AFFINE))
+	if (sd->flags & (SD_BALANCE_WAKE))
 		return 0;
 
 	return 1;
@@ -6355,8 +6355,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 					| 1*SD_BALANCE_NEWIDLE
 					| 1*SD_BALANCE_EXEC
 					| 1*SD_BALANCE_FORK
-					| 0*SD_BALANCE_WAKE
-					| 1*SD_WAKE_AFFINE
+					| 1*SD_BALANCE_WAKE
 					| 0*SD_SHARE_CPUCAPACITY
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 0*SD_SERIALIZE
@@ -6399,7 +6398,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
 			sd->flags &= ~(SD_BALANCE_EXEC |
 				       SD_BALANCE_FORK |
-				       SD_WAKE_AFFINE);
+				       SD_BALANCE_WAKE);
 		}
 
 #endif
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcb7f02..037ab0f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1323,7 +1323,7 @@ static int find_later_rq(struct task_struct *task)
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_AFFINE) {
+		if (sd->flags & SD_BALANCE_WAKE) {
 
 			/*
 			 * If possible, preempting this_cpu is
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e8..43f522a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5287,8 +5287,7 @@ static int cpu_util(int cpu)
  * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
  * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
- * Balances load by selecting the idlest cpu in the idlest group, or under
- * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
+ * Balances load by selecting the idlest cpu in the idlest group.
  *
  * Returns the target cpu number.
  *
@@ -5315,9 +5314,9 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 		/*
 		 * If both cpu and prev_cpu are part of this domain,
-		 * cpu is a valid SD_WAKE_AFFINE target.
+		 * cpu is a valid SD_BALANCE_WAKE target.
 		 */
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+		if (want_affine && (tmp->flags & SD_BALANCE_WAKE) &&
 		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
 			affine_sd = tmp;
 			break;
@@ -5330,7 +5329,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	}
 
 	if (affine_sd) {
-		sd = NULL; /* Prefer wake_affine over balance flags */
+		sd = NULL; /* Prefer SD_BALANCE_WAKE over other balance flags */
 		if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
 			new_cpu = cpu;
 	}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d5690b7..d1c8f41 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1655,7 +1655,7 @@ static int find_lowest_rq(struct task_struct *task)
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_AFFINE) {
+		if (sd->flags & SD_BALANCE_WAKE) {
 			int best_cpu;
 
 			/*
-- 
1.7.9.5