arm64: topology: DT and MPIDR support

index 0172e6d..7ebcd31 100644
@@ -20,9 +20,6 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
-#define mc_capable()	(cpu_topology[0].cluster_id != -1)
-#define smt_capable()	(cpu_topology[0].thread_id != -1)
-
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);

index 3e06b0b..ff662b2 100644
@@ -43,9 +43,6 @@ static void update_siblings_masks(unsigned int cpuid)
 		 * reset it to default behaviour
 		 */
 		pr_debug("CPU%u: No topology information configured\n", cpuid);
-		cpuid_topo->core_id = 0;
-		cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling);
-		cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling);
 		return;
 	}
 

@@ -87,9 +84,12 @@ void __init init_cpu_topology(void)
 		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
 
 		cpu_topo->thread_id = -1;
-		cpu_topo->core_id =  -1;
+		cpu_topo->core_id = 0;
 		cpu_topo->cluster_id = -1;
+
 		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
 	}
 }

index ff662b2..43514f9 100644
@@ -17,10 +17,192 @@
 #include <linux/percpu.h>
 #include <linux/node.h>
 #include <linux/nodemask.h>
+#include <linux/of.h>
 #include <linux/sched.h>
 
 #include <asm/topology.h>
 
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node)
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			of_node_put(cpu_node);
+			return cpu;
+		}
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+
+	of_node_put(cpu_node);
+	return -1;
+}
+
+static int __init parse_core(struct device_node *core, int cluster_id,
+			     int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				cpu_topology[cpu].cluster_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+				of_node_put(t);
+				return -EINVAL;
+			}
+			of_node_put(t);
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return -EINVAL;
+		}
+
+		cpu_topology[cpu].cluster_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int cluster_id __initdata;
+	int core_id = 0;
+	int i, ret;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			leaf = false;
+			ret = parse_cluster(c, depth + 1);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0) {
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+				of_node_put(c);
+				return -EINVAL;
+			}
+
+			if (leaf) {
+				ret = parse_core(c, cluster_id, core_id++);
+			} else {
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+				ret = -EINVAL;
+			}
+
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+
+	return 0;
+}
+
+static int __init parse_dt_topology(void)
+{
+	struct device_node *cn, *map;
+	int ret = 0;
+	int cpu;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return 0;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	map = of_get_child_by_name(cn, "cpu-map");
+	if (!map)
+		goto out;
+
+	ret = parse_cluster(map, 0);
+	if (ret != 0)
+		goto out_map;
+
+	/*
+	 * Check that all cores are in the topology; the SMP code will
+	 * only mark cores described in the DT as possible.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (cpu_topology[cpu].cluster_id == -1) {
+			pr_err("CPU%d: No topology information specified\n",
+			       cpu);
+			ret = -EINVAL;
+		}
+	}
+
+out_map:
+	of_node_put(map);
+out:
+	of_node_put(cn);
+	return ret;
+}
+
 /*
  * cpu topology table
  */

@@ -39,8 +221,7 @@ static void update_siblings_masks(unsigned int cpuid)
 
 	if (cpuid_topo->cluster_id == -1) {
 		/*
-		 * DT does not contain topology information for this cpu
-		 * reset it to default behaviour
+		 * DT does not contain topology information for this cpu.
 		 */
 		pr_debug("CPU%u: No topology information configured\n", cpuid);
 		return;

@@ -71,15 +252,10 @@ void store_cpu_topology(unsigned int cpuid)
 	update_siblings_masks(cpuid);
 }
 
-/*
- * init_cpu_topology is called at boot when only one cpu is running
- * which prevent simultaneous write access to cpu_topology array
- */
-void __init init_cpu_topology(void)
+static void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
 
-	/* init core mask and power*/
 	for_each_possible_cpu(cpu) {
 		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
 

@@ -93,3 +269,15 @@ void __init init_cpu_topology(void)
 		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
 	}
 }
+
+void __init init_cpu_topology(void)
+{
+	reset_cpu_topology();
+
+	/*
+	 * Discard anything that was parsed if we hit an error so we
+	 * don't use partial information.
+	 */
+	if (parse_dt_topology())
+		reset_cpu_topology();
+}

index c404fb0..b3b3287 100644
@@ -18,6 +18,8 @@
 
 #define INVALID_HWID		ULONG_MAX
 
+#define MPIDR_UP_BITMASK	(0x1 << 30)
+#define MPIDR_MT_BITMASK	(0x1 << 24)
 #define MPIDR_HWID_BITMASK	0xff00ffffff
 
 #define MPIDR_LEVEL_BITS_SHIFT	3

@@ -30,6 +32,9 @@
 #define MPIDR_AFFINITY_LEVEL(mpidr, level) \
 	((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
 
+#define MPIDR_AFF_MASK(level) \
+	((u64)MPIDR_LEVEL_MASK << MPIDR_LEVEL_SHIFT(level))
+
 #define read_cpuid(reg) ({						\
 	u64 __val;							\
 	asm("mrs	%0, " #reg : "=r" (__val));			\

64 lines not on this page · raw message

index b3b3287..7639e8b 100644
@@ -32,9 +32,6 @@
 #define MPIDR_AFFINITY_LEVEL(mpidr, level) \
 	((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
 
-#define MPIDR_AFF_MASK(level) \
-	((u64)MPIDR_LEVEL_MASK << MPIDR_LEVEL_SHIFT(level))
-
 #define read_cpuid(reg) ({						\
 	u64 __val;							\
 	asm("mrs	%0, " #reg : "=r" (__val));			\

index f7f3478..26fc5b0 100644
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 
 #include <asm/cputype.h>
-#include <asm/smp_plat.h>
 #include <asm/topology.h>
 
 /*

@@ -364,12 +363,6 @@ static void update_siblings_masks(unsigned int cpuid)
 	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
 	int cpu;
 
-	if (cpuid_topo->cluster_id == -1) {
-		/* No topology information for this cpu ?! */
-		pr_err("CPU%u: No topology information configured\n", cpuid);
-		return;
-	}
-
 	/* update core and thread sibling masks */
 	for_each_possible_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];

@@ -410,19 +403,15 @@ void store_cpu_topology(unsigned int cpuid)
 		/* Multiprocessor system : Multi-threads per core */
 		cpuid_topo->thread_id  = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-		cpuid_topo->cluster_id =
-			((mpidr & MPIDR_AFF_MASK(2)) >> mpidr_hash.shift_aff[2] |
-			 (mpidr & MPIDR_AFF_MASK(3)) >> mpidr_hash.shift_aff[3])
-			>> mpidr_hash.shift_aff[1] >> mpidr_hash.shift_aff[0];
+		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
+					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
 	} else {
 		/* Multiprocessor system : Single-thread per core */
 		cpuid_topo->thread_id  = -1;
 		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-		cpuid_topo->cluster_id =
-			((mpidr & MPIDR_AFF_MASK(1)) >> mpidr_hash.shift_aff[1] |
-			 (mpidr & MPIDR_AFF_MASK(2)) >> mpidr_hash.shift_aff[2] |
-			 (mpidr & MPIDR_AFF_MASK(3)) >> mpidr_hash.shift_aff[3])
-			>> mpidr_hash.shift_aff[0];
+		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
+					 MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
+					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
 	}
 
 	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %llx\n",

index 3b2479c..ed0b443 100644
@@ -19,11 +19,35 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/cputype.h>
 #include <asm/smp_plat.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;

@@ -162,6 +186,38 @@ 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@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;

@@ -205,6 +261,91 @@ 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
  */

@@ -288,6 +429,7 @@ void store_cpu_topology(unsigned int cpuid)
 
 topology_populated:
 	update_siblings_masks(cpuid);
+	update_cpu_power(cpuid);
 }
 
 static void __init reset_cpu_topology(void)

@@ -308,6 +450,14 @@ 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();

@@ -318,4 +468,7 @@ void __init init_cpu_topology(void)
 	 */
 	if (parse_dt_topology())
 		reset_cpu_topology();
+
+	reset_cpu_power();
+	parse_dt_cpu_power();
 }

index ed0b443..f7f3478 100644
@@ -202,6 +202,8 @@ struct cpu_efficiency {
  * use the default SCHED_POWER_SCALE value for cpu_scale.
  */
 static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
 	{ NULL, },
 };