s390/hiperdispatch: Introduce hiperdispatch

When LPAR is in vertical polarization, CPUs get different polarization
values, namely vertical high, vertical medium and vertical low. These
values represent the likelyhood of the CPU getting physical runtime.
Vertical high CPUs will always get runtime and others get varying
runtime depending on the load the CEC is under.

Vertical high and vertical medium CPUs are considered the CPUs which the
current LPAR has the entitlement to run on. The vertical lows are on the
other hand are borrowed CPUs which would only be given to the LPAR by
hipervisor when the other LPARs are not utilizing them.

Using the CPU capacities, hint linux scheduler when it should prioritise
vertical high and vertical medium CPUs over vertical low CPUs.
By tracking various system statistics hiperdispatch determines when to
adjust cpu capacities.
After each adjustment, rebuilding of scheduler domains is necessary to
notify the scheduler about capacity changes but since this operation is
costly it should be done as sparsely as possible.

Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Co-developed-by: Tobias Huschle <huschle@linux.ibm.com>
Signed-off-by: Tobias Huschle <huschle@linux.ibm.com>
Signed-off-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

1 files changed, 14 insertions, 4 deletions

diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 58da6d1bae45..813e5da9a973 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/nodemask.h>
 #include <linux/node.h>
+#include <asm/hiperdispatch.h>
 #include <asm/sysinfo.h>
 
 #define PTF_HORIZONTAL	(0UL)
@@ -47,6 +48,7 @@ static int topology_mode = TOPOLOGY_MODE_UNINITIALIZED;
 static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
+static int cpu_management;
 
 static DECLARE_WORK(topology_work, topology_work_fn);
 
@@ -144,6 +146,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core,
 			cpumask_set_cpu(cpu, &book->mask);
 			cpumask_set_cpu(cpu, &socket->mask);
 			smp_cpu_set_polarization(cpu, tl_core->pp);
+			smp_cpu_set_capacity(cpu, CPU_CAPACITY_HIGH);
 		}
 	}
 }
@@ -270,6 +273,7 @@ void update_cpu_masks(void)
 			topo->drawer_id = id;
 		}
 	}
+	hd_reset_state();
 	for_each_online_cpu(cpu) {
 		topo = &cpu_topology[cpu];
 		pkg_first = cpumask_first(&topo->core_mask);
@@ -278,8 +282,10 @@ void update_cpu_masks(void)
 			for_each_cpu(sibling, &topo->core_mask) {
 				topo_sibling = &cpu_topology[sibling];
 				smt_first = cpumask_first(&topo_sibling->thread_mask);
-				if (sibling == smt_first)
+				if (sibling == smt_first) {
 					topo_package->booted_cores++;
+					hd_add_core(sibling);
+				}
 			}
 		} else {
 			topo->booted_cores = topo_package->booted_cores;
@@ -303,8 +309,10 @@ static void __arch_update_dedicated_flag(void *arg)
 static int __arch_update_cpu_topology(void)
 {
 	struct sysinfo_15_1_x *info = tl_info;
-	int rc = 0;
+	int rc, hd_status;
 
+	hd_status = 0;
+	rc = 0;
 	mutex_lock(&smp_cpu_state_mutex);
 	if (MACHINE_HAS_TOPOLOGY) {
 		rc = 1;
@@ -314,7 +322,11 @@ static int __arch_update_cpu_topology(void)
 	update_cpu_masks();
 	if (!MACHINE_HAS_TOPOLOGY)
 		topology_update_polarization_simple();
+	if (cpu_management == 1)
+		hd_status = hd_enable_hiperdispatch();
 	mutex_unlock(&smp_cpu_state_mutex);
+	if (hd_status == 0)
+		hd_disable_hiperdispatch();
 	return rc;
 }
 
@@ -374,8 +386,6 @@ void topology_expect_change(void)
 	set_topology_timer();
 }
 
-static int cpu_management;
-
 static int set_polarization(int polarization)
 {
 	int rc = 0;