[COMMON] soc: samsung: topology: Make new CPU topology support for ARCH_EXYNOS

Change-Id: I02fb470e14ca0bd556782ef9f75d1e2c9448bc18
Signed-off-by: Daeyeong Lee <daeyeong.lee@samsung.com>

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2058ebde89b856105bf3a4583bd5c455c45ef92a..7b0a86621e516b6cab0cf2feee161f95ec0a44bf 100644 (file)
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -20,7 +20,7 @@ arm64-obj-y           := debug-monitors.o entry.o irq.o fpsimd.o              \
                           hyp-stub.o psci.o cpu_ops.o insn.o   \
                           return_address.o cpuinfo.o cpu_errata.o              \
                           cpufeature.o alternative.o cacheinfo.o               \
-                          smp.o smp_spin_table.o topology.o smccc-call.o
+                          smp.o smp_spin_table.o smccc-call.o
 
 extra-$(CONFIG_EFI)                    := efi-entry.o
 
@@ -56,6 +56,10 @@ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)         += crash_dump.o
 
+ifndef CONFIG_ARCH_EXYNOS
+arm64-obj-y                                    += topology.o
+endif
+
 ifeq ($(CONFIG_KVM),y)
 arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR)    += bpi.o
 endif

diff --git a/drivers/soc/samsung/Makefile b/drivers/soc/samsung/Makefile
index 163be71f2ed55f5e319f1cf89bdd8cebfff25d81..4fae92b7e10a9668bd78ff78b5dd72539a8f975b 100644 (file)
--- a/drivers/soc/samsung/Makefile
+++ b/drivers/soc/samsung/Makefile
@@ -35,6 +35,9 @@ obj-$(CONFIG_EXYNOS_PM_DOMAINS) += pm_domains.o
 #CPUHOTPLUG
 obj-$(CONFIG_ARCH_EXYNOS)      += exynos-cpu_hotplug.o
 
+# CPU Topology
+obj-$(CONFIG_ARCH_EXYNOS)      += exynos-topology.o
+
 #CPU Power Management
 obj-$(CONFIG_ARCH_EXYNOS)      += exynos-cpupm.o
 

diff --git a/drivers/soc/samsung/exynos-topology.c b/drivers/soc/samsung/exynos-topology.c
new file mode 100644 (file)
index 0000000..7f8bc72
--- /dev/null
+++ b/drivers/soc/samsung/exynos-topology.c
@@ -0,0 +1,399 @@
+/*
+ * drivers/soc/samsung/exynos-topology.c
+ *
+ * Copyright (C) 2018 Samsung Electronics.
+ *
+ * Based on the arm64 version written by Mark Brown in turn based on
+ * arch/arm64/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/arch_topology.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/sched/topology.h>
+#include <linux/sched_energy.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include <asm/cpu.h>
+#include <asm/cputype.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) {
+                       topology_parse_cpu_capacity(cpu_node, cpu);
+                       of_node_put(cpu_node);
+                       return cpu;
+               }
+       }
+
+       pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+
+       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("%pOF: Can't get CPU for thread\n",
+                                      t);
+                               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("%pOF: Core has both threads and CPU\n",
+                              core);
+                       return -EINVAL;
+               }
+
+               cpu_topology[cpu].cluster_id = cluster_id;
+               cpu_topology[cpu].core_id = core_id;
+       } else if (leaf) {
+               pr_err("%pOF: Can't get CPU for leaf core\n", core);
+               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("%pOF: cpu-map children should be clusters\n",
+                                      c);
+                               of_node_put(c);
+                               return -EINVAL;
+                       }
+
+                       if (leaf) {
+                               ret = parse_core(c, cluster_id, core_id++);
+                       } else {
+                               pr_err("%pOF: Non-leaf cluster with core %s\n",
+                                      cluster, name);
+                               ret = -EINVAL;
+                       }
+
+                       of_node_put(c);
+                       if (ret != 0)
+                               return ret;
+               }
+               i++;
+       } while (c);
+
+       if (leaf && !has_cores)
+               pr_warn("%pOF: empty cluster\n", cluster);
+
+       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;
+
+       init_sched_energy_costs();
+
+       ret = parse_cluster(map, 0);
+       if (ret != 0)
+               goto out_map;
+
+       topology_normalize_cpu_scale();
+
+       /*
+        * 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)
+                       ret = -EINVAL;
+
+out_map:
+       of_node_put(map);
+out:
+       of_node_put(cn);
+       return ret;
+}
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+       return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+       struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+       int cpu;
+
+       /* update core and thread sibling masks */
+       for_each_possible_cpu(cpu) {
+               cpu_topo = &cpu_topology[cpu];
+
+               if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+                       continue;
+
+               cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+               if (cpu != cpuid)
+                       cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+               if (cpuid_topo->core_id != cpu_topo->core_id)
+                       continue;
+
+               cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+               if (cpu != cpuid)
+                       cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+       }
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+       struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
+       u64 mpidr;
+
+       if (cpuid_topo->cluster_id != -1)
+               goto topology_populated;
+
+       mpidr = read_cpuid_mpidr();
+
+       /* Uniprocessor systems can rely on default topology values */
+       if (mpidr & MPIDR_UP_BITMASK)
+               return;
+
+       /* Create cpu topology mapping based on MPIDR. */
+       if (mpidr & MPIDR_MT_BITMASK) {
+               /* 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_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_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 %#016llx\n",
+                cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id,
+                cpuid_topo->thread_id, mpidr);
+
+topology_populated:
+       update_siblings_masks(cpuid);
+       topology_detect_flags();
+}
+
+#ifdef CONFIG_SCHED_SMT
+static int smt_flags(void)
+{
+       return cpu_smt_flags() | topology_smt_flags();
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static int core_flags(void)
+{
+       return cpu_core_flags() | topology_core_flags();
+}
+#endif
+
+static int cpu_flags(void)
+{
+       return topology_cpu_flags();
+}
+
+static inline
+const struct sched_group_energy * const cpu_core_energy(int cpu)
+{
+       struct sched_group_energy *sge = sge_array[cpu][SD_LEVEL0];
+       unsigned long capacity;
+       int max_cap_idx;
+
+       if (!sge) {
+               pr_warn("Invalid sched_group_energy for CPU%d\n", cpu);
+               return NULL;
+       }
+
+       max_cap_idx = sge->nr_cap_states - 1;
+       capacity = sge->cap_states[max_cap_idx].cap;
+
+       printk_deferred("cpu=%d set cpu scale %lu from energy model\n",
+                       cpu, capacity);
+
+       topology_set_cpu_scale(cpu, capacity);
+
+       return sge;
+}
+
+static inline
+const struct sched_group_energy * const cpu_cluster_energy(int cpu)
+{
+       struct sched_group_energy *sge = sge_array[cpu][SD_LEVEL1];
+
+       if (!sge) {
+               pr_warn("Invalid sched_group_energy for Cluster%d\n", cpu);
+               return NULL;
+       }
+
+       return sge;
+}
+
+static inline
+const struct sched_group_energy * const cpu_system_energy(int cpu)
+{
+       struct sched_group_energy *sge = sge_array[cpu][SD_LEVEL2];
+
+       if (!sge) {
+               pr_warn("Invalid sched_group_energy for System%d\n", cpu);
+               return NULL;
+       }
+
+       return sge;
+}
+
+static struct sched_domain_topology_level arm64_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+       { cpu_smt_mask, smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+       { cpu_coregroup_mask, core_flags, cpu_core_energy, SD_INIT_NAME(MC) },
+#endif
+       { cpu_cpu_mask, cpu_flags, cpu_cluster_energy, SD_INIT_NAME(DIE) },
+       { cpu_cpu_mask, NULL, cpu_system_energy, SD_INIT_NAME(SYS) },
+       { NULL, }
+};
+
+static void __init reset_cpu_topology(void)
+{
+       unsigned int cpu;
+
+       for_each_possible_cpu(cpu) {
+               struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+               cpu_topo->thread_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);
+       }
+}
+
+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 (of_have_populated_dt() && parse_dt_topology())
+               reset_cpu_topology();
+       else
+               set_sched_topology(arm64_topology);
+}