aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
authorRafael J. Wysocki <rafael.j.wysocki@intel.com>2024-09-11 18:25:54 +0200
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2024-09-11 18:25:54 +0200
commit415dff1c96cc553b52e13685495fef5d66c875f7 (patch)
treeacee5f94ef5bed24cc0b551c673c12abb3324a0a /arch/x86/kernel/cpu
parent83710aaff08a5b650db166eed28e9ae377311da6 (diff)
parent9bcf30348f327658c93894fca6392e147f4383a5 (diff)
Merge branch 'pm-cpufreq'
Merge cpufreq updates for 6.12-rc1: - Remove LATENCY_MULTIPLIER from cpufreq (Qais Yousef). - Add support for Granite Rapids and Sierra Forest in OOB mode to the intel_pstate cpufreq driver (Srinivas Pandruvada). - Add basic support for CPU capacity scaling on x86 and make the intel_pstate driver set asymmetric CPU capacity on hybrid systems without SMT (Rafael Wysocki). - Add missing MODULE_DESCRIPTION() macros to the powerpc cpufreq driver (Jeff Johnson). - Several OF related cleanups in cpufreq drivers (Rob Herring). - Enable COMPILE_TEST for ARM drivers (Rob Herrring). - Introduce quirks for syscon failures and use socinfo to get revision for TI cpufreq driver (Dhruva Gole, Nishanth Menon). - Minor cleanups in amd-pstate driver (Anastasia Belova, Dhananjay Ugwekar). - Minor cleanups for loongson, cpufreq-dt and powernv cpufreq drivers (Danila Tikhonov, Huacai Chen, and Liu Jing). - Make amd-pstate validate return of any attempt to update EPP limits, which fixes the masking hardware problems (Mario Limonciello). - Move the calculation of the AMD boost numerator outside of amd-pstate, correcting acpi-cpufreq on systems with preferred cores (Mario Limonciello). - Harden preferred core detection in amd-pstate to avoid potential false positives (Mario Limonciello). - Add extra unit test coverage for mode state machine (Mario Limonciello). - Fix an "Uninitialized variables" issue in amd-pstste (Qianqiang Liu). * pm-cpufreq: (35 commits) cpufreq/amd-pstate-ut: Fix an "Uninitialized variables" issue cpufreq/amd-pstate-ut: Add test case for mode switches cpufreq/amd-pstate: Export symbols for changing modes amd-pstate: Add missing documentation for `amd_pstate_prefcore_ranking` cpufreq: amd-pstate: Add documentation for `amd_pstate_hw_prefcore` cpufreq: amd-pstate: Optimize amd_pstate_update_limits() cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator() x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator() x86/amd: Move amd_get_highest_perf() out of amd-pstate ACPI: CPPC: Adjust debug messages in amd_set_max_freq_ratio() to warn ACPI: CPPC: Drop check for non zero perf ratio x86/amd: Rename amd_get_highest_perf() to amd_get_boost_ratio_numerator() ACPI: CPPC: Adjust return code for inline functions in !CONFIG_ACPI_CPPC_LIB x86/amd: Move amd_get_highest_perf() from amd.c to cppc.c cpufreq/amd-pstate: Catch failures for amd_pstate_epp_update_limit() cpufreq: ti-cpufreq: Use socinfo to get revision in AM62 family cpufreq: Fix the cacography in powernv-cpufreq.c cpufreq: ti-cpufreq: Introduce quirks to handle syscon fails appropriately cpufreq: loongson3: Use raw_smp_processor_id() in do_service_request() cpufreq: amd-pstate: add check for cpufreq_cpu_get's return value ...
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/amd.c16
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c89
2 files changed, 87 insertions, 18 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1e0fe5f8ab84..015971adadfc 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1190,22 +1190,6 @@ unsigned long amd_get_dr_addr_mask(unsigned int dr)
}
EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
-u32 amd_get_highest_perf(void)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
- (c->x86_model >= 0x70 && c->x86_model < 0x80)))
- return 166;
-
- if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
- (c->x86_model >= 0x40 && c->x86_model < 0x70)))
- return 166;
-
- return 255;
-}
-EXPORT_SYMBOL_GPL(amd_get_highest_perf);
-
static void zenbleed_check_cpu(void *unused)
{
struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 0b69bfbf345d..f642de2ebdac 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -349,9 +349,89 @@ static DECLARE_WORK(disable_freq_invariance_work,
DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
+static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key);
+
+struct arch_hybrid_cpu_scale {
+ unsigned long capacity;
+ unsigned long freq_ratio;
+};
+
+static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale;
+
+/**
+ * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling
+ *
+ * Allocate memory for per-CPU data used by hybrid CPU capacity scaling,
+ * initialize it and set the static key controlling its code paths.
+ *
+ * Must be called before arch_set_cpu_capacity().
+ */
+bool arch_enable_hybrid_capacity_scale(void)
+{
+ int cpu;
+
+ if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) {
+ WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled");
+ return true;
+ }
+
+ arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale);
+ if (!arch_cpu_scale)
+ return false;
+
+ for_each_possible_cpu(cpu) {
+ per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE;
+ per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio;
+ }
+
+ static_branch_enable(&arch_hybrid_cap_scale_key);
+
+ pr_info("Hybrid CPU capacity scaling enabled\n");
+
+ return true;
+}
+
+/**
+ * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU
+ * @cpu: Target CPU.
+ * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap.
+ * @max_cap: System-wide maximum CPU capacity.
+ * @cap_freq: Frequency of @cpu corresponding to @cap.
+ * @base_freq: Frequency of @cpu at which MPERF counts.
+ *
+ * The units in which @cap and @max_cap are expressed do not matter, so long
+ * as they are consistent, because the former is effectively divided by the
+ * latter. Analogously for @cap_freq and @base_freq.
+ *
+ * After calling this function for all CPUs, call arch_rebuild_sched_domains()
+ * to let the scheduler know that capacity-aware scheduling can be used going
+ * forward.
+ */
+void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap,
+ unsigned long cap_freq, unsigned long base_freq)
+{
+ if (static_branch_likely(&arch_hybrid_cap_scale_key)) {
+ WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity,
+ div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap));
+ WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio,
+ div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq));
+ } else {
+ WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled");
+ }
+}
+
+unsigned long arch_scale_cpu_capacity(int cpu)
+{
+ if (static_branch_unlikely(&arch_hybrid_cap_scale_key))
+ return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity);
+
+ return SCHED_CAPACITY_SCALE;
+}
+EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity);
+
static void scale_freq_tick(u64 acnt, u64 mcnt)
{
- u64 freq_scale;
+ u64 freq_scale, freq_ratio;
if (!arch_scale_freq_invariant())
return;
@@ -359,7 +439,12 @@ static void scale_freq_tick(u64 acnt, u64 mcnt)
if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
goto error;
- if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
+ if (static_branch_unlikely(&arch_hybrid_cap_scale_key))
+ freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio);
+ else
+ freq_ratio = arch_max_freq_ratio;
+
+ if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt)
goto error;
freq_scale = div64_u64(acnt, mcnt);
Powered by cgit, Gruvboxed by Blaster4385.