sched: Introduce SD_SHARE_CAP_STATES sched_domain flag

cpufreq is currently keeping it a secret which cpus are sharing
clock source. The scheduler needs to know about clock domains as well
to become more energy aware. The SD_SHARE_CAP_STATES domain flag
indicates whether cpus belonging to the sched_domain share capacity
states (P-states).

There is no connection with cpufreq (yet). The flag must be set by
the arch specific topology code.

cc: Russell King <linux@arm.linux.org.uk>
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 614554765e4470466abac781c3a0bca7cec2cc1e..38e7be162b7946b0a6324c086833ba5f03d11a76 100644 (file)
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -277,7 +277,8 @@ void store_cpu_topology(unsigned int cpuid)
 
 static inline int cpu_corepower_flags(void)
 {
-       return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
+       return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN | \
+              SD_SHARE_CAP_STATES;
 }
 
 static struct sched_domain_topology_level arm_topology[] = {

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5bee272a86d8e660321204db0625e6411ea34959..09e2d43406ebada0e51c696d14d5ee47f0d0ec05 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -989,6 +989,7 @@ extern void wake_up_q(struct wake_q_head *head);
 #define SD_PREFER_SIBLING      0x1000  /* Prefer to place tasks in a sibling domain */
 #define SD_OVERLAP             0x2000  /* sched_domains of this level overlap */
 #define SD_NUMA                        0x4000  /* cross-node balancing */
+#define SD_SHARE_CAP_STATES    0x8000  /* Domain members share capacity state */
 
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f1b1c9eaeb107179219eb3dbe35d86df5778b5a3..2863d223c07effb6efcceaec2e6395aa18246d95 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5775,7 +5775,8 @@ static int sd_degenerate(struct sched_domain *sd)
                         SD_BALANCE_EXEC |
                         SD_SHARE_CPUCAPACITY |
                         SD_SHARE_PKG_RESOURCES |
-                        SD_SHARE_POWERDOMAIN)) {
+                        SD_SHARE_POWERDOMAIN |
+                        SD_SHARE_CAP_STATES)) {
                if (sd->groups != sd->groups->next)
                        return 0;
        }
@@ -5807,7 +5808,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
                                SD_SHARE_CPUCAPACITY |
                                SD_SHARE_PKG_RESOURCES |
                                SD_PREFER_SIBLING |
-                               SD_SHARE_POWERDOMAIN);
+                               SD_SHARE_POWERDOMAIN |
+                               SD_SHARE_CAP_STATES);
                if (nr_node_ids == 1)
                        pflags &= ~SD_SERIALIZE;
        }
@@ -6472,6 +6474,7 @@ static int sched_domains_curr_level;
  * SD_SHARE_PKG_RESOURCES - describes shared caches
  * SD_NUMA                - describes NUMA topologies
  * SD_SHARE_POWERDOMAIN   - describes shared power domain
+ * SD_SHARE_CAP_STATES    - describes shared capacity states
  *
  * Odd one out:
  * SD_ASYM_PACKING        - describes SMT quirks
@@ -6481,7 +6484,8 @@ static int sched_domains_curr_level;
         SD_SHARE_PKG_RESOURCES |       \
         SD_NUMA |                      \
         SD_ASYM_PACKING |              \
-        SD_SHARE_POWERDOMAIN)
+        SD_SHARE_POWERDOMAIN |         \
+        SD_SHARE_CAP_STATES)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl, int cpu)