@@ -19,9 +19,33 @@
#include <linux/nodemask.h>
#include <linux/of.h>
#include <linux/sched.h>
+#include <linux/slab.h>
#include <asm/topology.h>
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+ per_cpu(cpu_scale, cpu) = power;
+}
+
static int __init get_cpu_for_node(struct device_node *node)
{
struct device_node *cpu_node;
@@ -159,6 +183,38 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
return 0;
}
+struct cpu_efficiency {
+ const char *compatible;
+ unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+ { NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu) __cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
static int __init parse_dt_topology(void)
{
struct device_node *cn, *map;
@@ -202,6 +258,91 @@ out:
return ret;
}
+static void __init parse_dt_cpu_power(void)
+{
+ const struct cpu_efficiency *cpu_eff;
+ struct device_node *cn;
+ unsigned long min_capacity = ULONG_MAX;
+ unsigned long max_capacity = 0;
+ unsigned long capacity = 0;
+ int cpu;
+
+ __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+ GFP_NOWAIT);
+
+ for_each_possible_cpu(cpu) {
+ const u32 *rate;
+ int len;
+
+ /* Too early to use cpu->of_node */
+ cn = of_get_cpu_node(cpu, NULL);
+ if (!cn) {
+ pr_err("Missing device node for CPU %d\n", cpu);
+ continue;
+ }
+
+ for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+ if (of_device_is_compatible(cn, cpu_eff->compatible))
+ break;
+
+ if (cpu_eff->compatible == NULL) {
+ pr_warn("%s: Unknown CPU type\n", cn->full_name);
+ continue;
+ }
+
+ rate = of_get_property(cn, "clock-frequency", &len);
+ if (!rate || len != 4) {
+ pr_err("%s: Missing clock-frequency property\n",
+ cn->full_name);
+ continue;
+ }
+
+ capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+ /* Save min capacity of the system */
+ if (capacity < min_capacity)
+ min_capacity = capacity;
+
+ /* Save max capacity of the system */
+ if (capacity > max_capacity)
+ max_capacity = capacity;
+
+ cpu_capacity(cpu) = capacity;
+ }
+
+ /* If min and max capacities are equal we bypass the update of the
+ * cpu_scale because all CPUs have the same capacity. Otherwise, we
+ * compute a middle_capacity factor that will ensure that the capacity
+ * of an 'average' CPU of the system will be as close as possible to
+ * SCHED_POWER_SCALE, which is the default value, but with the
+ * constraint explained near table_efficiency[].
+ */
+ if (min_capacity == max_capacity)
+ return;
+ else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+ middle_capacity = (min_capacity + max_capacity)
+ >> (SCHED_POWER_SHIFT+1);
+ else
+ middle_capacity = ((max_capacity / 3)
+ >> (SCHED_POWER_SHIFT-1)) + 1;
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+ if (!cpu_capacity(cpu))
+ return;
+
+ set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+ pr_info("CPU%u: update cpu_power %lu\n",
+ cpu, arch_scale_freq_power(NULL, cpu));
+}
+
/*
* cpu topology table
*/
@@ -249,6 +390,7 @@ static void update_siblings_masks(unsigned int cpuid)
void store_cpu_topology(unsigned int cpuid)
{
update_siblings_masks(cpuid);
+ update_cpu_power(cpuid);
}
static void __init reset_cpu_topology(void)
@@ -269,6 +411,14 @@ static void __init reset_cpu_topology(void)
}
}
+static void __init reset_cpu_power(void)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu)
+ set_power_scale(cpu, SCHED_POWER_SCALE);
+}
+
void __init init_cpu_topology(void)
{
reset_cpu_topology();
@@ -279,4 +429,7 @@ void __init init_cpu_topology(void)
*/
if (parse_dt_topology())
reset_cpu_topology();
+
+ reset_cpu_power();
+ parse_dt_cpu_power();
}