From 23fa18eaa71266feff7ba8d83022d9e1cc83c65a Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:42:03 +0000
Subject: [PATCH] disable pwm7
---
kernel/arch/arm64/kernel/topology.c | 522 ++++++++++++++++++++-------------------------------------
1 files changed, 187 insertions(+), 335 deletions(-)
diff --git a/kernel/arch/arm64/kernel/topology.c b/kernel/arch/arm64/kernel/topology.c
index 655a308..f35af19 100644
--- a/kernel/arch/arm64/kernel/topology.c
+++ b/kernel/arch/arm64/kernel/topology.c
@@ -14,332 +14,13 @@
#include <linux/acpi.h>
#include <linux/arch_topology.h>
#include <linux/cacheinfo.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
+#include <linux/cpufreq.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/slab.h>
-#include <linux/smp.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;
-
- cpu = of_cpu_node_to_id(cpu_node);
- if (cpu >= 0)
- topology_parse_cpu_capacity(cpu_node, cpu);
- else
- pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
-
- of_node_put(cpu_node);
- return cpu;
-}
-
-static int __init parse_core(struct device_node *core, int package_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].package_id = package_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].package_id = package_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 package_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, package_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)
- package_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;
-
- 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].package_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)
-{
- const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
-
- /* Find the smaller of NUMA, core or LLC siblings */
- if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
- /* not numa in package, lets use the package siblings */
- core_mask = &cpu_topology[cpu].core_sibling;
- }
- if (cpu_topology[cpu].llc_id != -1) {
- if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
- core_mask = &cpu_topology[cpu].llc_sibling;
- }
-
- return core_mask;
-}
-
-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_online_cpu(cpu) {
- cpu_topo = &cpu_topology[cpu];
-
- if (cpuid_topo->llc_id == cpu_topo->llc_id) {
- cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
- cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
- }
-
- if (cpuid_topo->package_id != cpu_topo->package_id)
- continue;
-
- cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
- 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);
- 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->package_id != -1)
- goto topology_populated;
-
- mpidr = read_cpuid_mpidr();
-
- /* Uniprocessor systems can rely on default topology values */
- if (mpidr & MPIDR_UP_BITMASK)
- return;
-
- /*
- * This would be the place to create cpu topology based on MPIDR.
- *
- * However, it cannot be trusted to depict the actual topology; some
- * pieces of the architecture enforce an artificial cap on Aff0 values
- * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an
- * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up
- * having absolutely no relationship to the actual underlying system
- * topology, and cannot be reasonably used as core / package ID.
- *
- * If the MT bit is set, Aff0 *could* be used to define a thread ID, but
- * we still wouldn't be able to obtain a sane core ID. This means we
- * need to entirely ignore MPIDR for any topology deduction.
- */
- cpuid_topo->thread_id = -1;
- cpuid_topo->core_id = cpuid;
- cpuid_topo->package_id = cpu_to_node(cpuid);
-
- pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
- cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
- cpuid_topo->thread_id, mpidr);
-
-topology_populated:
- update_siblings_masks(cpuid);
-}
-
-static void clear_cpu_topology(int cpu)
-{
- struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
- cpumask_clear(&cpu_topo->llc_sibling);
- cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
-
- 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);
-}
-
-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->package_id = -1;
- cpu_topo->llc_id = -1;
-
- clear_cpu_topology(cpu);
- }
-}
-
-void remove_cpu_topology(unsigned int cpu)
-{
- int sibling;
-
- for_each_cpu(sibling, topology_core_cpumask(cpu))
- cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
- for_each_cpu(sibling, topology_sibling_cpumask(cpu))
- cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
- for_each_cpu(sibling, topology_llc_cpumask(cpu))
- cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
-
- clear_cpu_topology(cpu);
-}
#ifdef CONFIG_ACPI
static bool __init acpi_cpu_is_threaded(int cpu)
@@ -360,9 +41,12 @@
* Propagate the topology information of the processor_topology_node tree to the
* cpu_topology array.
*/
-static int __init parse_acpi_topology(void)
+int __init parse_acpi_topology(void)
{
int cpu, topology_id;
+
+ if (acpi_disabled)
+ return 0;
for_each_possible_cpu(cpu) {
int i, cache_id;
@@ -397,24 +81,192 @@
return 0;
}
-
-#else
-static inline int __init parse_acpi_topology(void)
-{
- return -EINVAL;
-}
#endif
-void __init init_cpu_topology(void)
+#ifdef CONFIG_ARM64_AMU_EXTN
+
+#undef pr_fmt
+#define pr_fmt(fmt) "AMU: " fmt
+
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
+static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
+static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
+static cpumask_var_t amu_fie_cpus;
+
+/* Initialize counter reference per-cpu variables for the current CPU */
+void init_cpu_freq_invariance_counters(void)
{
- reset_cpu_topology();
+ this_cpu_write(arch_core_cycles_prev,
+ read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0));
+ this_cpu_write(arch_const_cycles_prev,
+ read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0));
+}
+
+static int validate_cpu_freq_invariance_counters(int cpu)
+{
+ u64 max_freq_hz, ratio;
+
+ if (!cpu_has_amu_feat(cpu)) {
+ pr_debug("CPU%d: counters are not supported.\n", cpu);
+ return -EINVAL;
+ }
+
+ if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
+ !per_cpu(arch_core_cycles_prev, cpu))) {
+ pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
+ return -EINVAL;
+ }
+
+ /* Convert maximum frequency from KHz to Hz and validate */
+ max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000ULL;
+ if (unlikely(!max_freq_hz)) {
+ pr_debug("CPU%d: invalid maximum frequency.\n", cpu);
+ return -EINVAL;
+ }
/*
- * Discard anything that was parsed if we hit an error so we
- * don't use partial information.
+ * Pre-compute the fixed ratio between the frequency of the constant
+ * counter and the maximum frequency of the CPU.
+ *
+ * const_freq
+ * arch_max_freq_scale = ---------------- * SCHED_CAPACITY_SCALE²
+ * cpuinfo_max_freq
+ *
+ * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE²
+ * in order to ensure a good resolution for arch_max_freq_scale for
+ * very low arch timer frequencies (down to the KHz range which should
+ * be unlikely).
*/
- if (!acpi_disabled && parse_acpi_topology())
- reset_cpu_topology();
- else if (of_have_populated_dt() && parse_dt_topology())
- reset_cpu_topology();
+ ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT);
+ ratio = div64_u64(ratio, max_freq_hz);
+ if (!ratio) {
+ WARN_ONCE(1, "System timer frequency too low.\n");
+ return -EINVAL;
+ }
+
+ per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
+
+ return 0;
}
+
+static inline bool
+enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus)
+{
+ struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+ if (!policy) {
+ pr_debug("CPU%d: No cpufreq policy found.\n", cpu);
+ return false;
+ }
+
+ if (cpumask_subset(policy->related_cpus, valid_cpus))
+ cpumask_or(amu_fie_cpus, policy->related_cpus,
+ amu_fie_cpus);
+
+ cpufreq_cpu_put(policy);
+
+ return true;
+}
+
+static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
+#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key)
+
+static int __init init_amu_fie(void)
+{
+ cpumask_var_t valid_cpus;
+ bool have_policy = false;
+ int ret = 0;
+ int cpu;
+
+ if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL))
+ return -ENOMEM;
+
+ if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto free_valid_mask;
+ }
+
+ for_each_present_cpu(cpu) {
+ if (validate_cpu_freq_invariance_counters(cpu))
+ continue;
+ cpumask_set_cpu(cpu, valid_cpus);
+ have_policy |= enable_policy_freq_counters(cpu, valid_cpus);
+ }
+
+ /*
+ * If we are not restricted by cpufreq policies, we only enable
+ * the use of the AMU feature for FIE if all CPUs support AMU.
+ * Otherwise, enable_policy_freq_counters has already enabled
+ * policy cpus.
+ */
+ if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask))
+ cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus);
+
+ if (!cpumask_empty(amu_fie_cpus)) {
+ pr_info("CPUs[%*pbl]: counters will be used for FIE.",
+ cpumask_pr_args(amu_fie_cpus));
+ static_branch_enable(&amu_fie_key);
+ }
+
+ /*
+ * If the system is not fully invariant after AMU init, disable
+ * partial use of counters for frequency invariance.
+ */
+ if (!topology_scale_freq_invariant())
+ static_branch_disable(&amu_fie_key);
+
+free_valid_mask:
+ free_cpumask_var(valid_cpus);
+
+ return ret;
+}
+late_initcall_sync(init_amu_fie);
+
+bool arch_freq_counters_available(const struct cpumask *cpus)
+{
+ return amu_freq_invariant() &&
+ cpumask_subset(cpus, amu_fie_cpus);
+}
+
+void topology_scale_freq_tick(void)
+{
+ u64 prev_core_cnt, prev_const_cnt;
+ u64 core_cnt, const_cnt, scale;
+ int cpu = smp_processor_id();
+
+ if (!amu_freq_invariant())
+ return;
+
+ if (!cpumask_test_cpu(cpu, amu_fie_cpus))
+ return;
+
+ const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0);
+ core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0);
+ prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
+ prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+
+ if (unlikely(core_cnt <= prev_core_cnt ||
+ const_cnt <= prev_const_cnt))
+ goto store_and_exit;
+
+ /*
+ * /\core arch_max_freq_scale
+ * scale = ------- * --------------------
+ * /\const SCHED_CAPACITY_SCALE
+ *
+ * See validate_cpu_freq_invariance_counters() for details on
+ * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
+ */
+ scale = core_cnt - prev_core_cnt;
+ scale *= this_cpu_read(arch_max_freq_scale);
+ scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
+ const_cnt - prev_const_cnt);
+
+ scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
+ this_cpu_write(freq_scale, (unsigned long)scale);
+
+store_and_exit:
+ this_cpu_write(arch_core_cycles_prev, core_cnt);
+ this_cpu_write(arch_const_cycles_prev, const_cnt);
+}
+#endif /* CONFIG_ARM64_AMU_EXTN */
--
Gitblit v1.6.2