@@ -23,6 +23,10 @@ static bool __ro_after_init feature_hdc;
bool __initdata opt_cpufreq_hwp;
static bool __ro_after_init opt_cpufreq_hdc = true;
+#define HWP_ENERGY_PERF_MAX_PERFORMANCE 0
+#define HWP_ENERGY_PERF_BALANCE 0x80
+#define HWP_ENERGY_PERF_MAX_POWERSAVE 0xff
+
union hwp_request
{
struct
@@ -560,6 +564,100 @@ int get_hwp_para(const unsigned int cpu,
return 0;
}
+int set_hwp_para(struct cpufreq_policy *policy,
+ const struct xen_set_cppc_para *set_cppc)
+{
+ unsigned int cpu = policy->cpu;
+ struct hwp_drv_data *data = per_cpu(hwp_drv_data, cpu);
+
+ if ( data == NULL )
+ return -EINVAL;
+
+ /* Validate all parameters first */
+ if ( set_cppc->set_params & ~XEN_SYSCTL_CPPC_SET_PARAM_MASK )
+ return -EINVAL;
+
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_ACT_WINDOW &&
+ !feature_hwp_activity_window )
+ return -EINVAL;
+
+ if ( !(set_cppc->set_params & XEN_SYSCTL_CPPC_SET_ACT_WINDOW) &&
+ set_cppc->activity_window )
+ return -EINVAL;
+
+ if ( set_cppc->activity_window & ~XEN_SYSCTL_CPPC_ACT_WINDOW_MASK )
+ return -EINVAL;
+
+ if ( (set_cppc->set_params & XEN_SYSCTL_CPPC_SET_DESIRED) &&
+ set_cppc->desired != 0 &&
+ (set_cppc->desired < data->hw.lowest ||
+ set_cppc->desired > data->hw.highest) )
+ return -EINVAL;
+
+ /*
+ * minimum & maximum are not validated against lowest or highest as
+ * hardware doesn't seem to care and the SDM says CPUs will clip
+ * internally.
+ */
+ if ( set_cppc->minimum > 255 ||
+ set_cppc->maximum > 255 ||
+ set_cppc->energy_perf > 255 )
+ return -EINVAL;
+
+ /* Apply presets */
+ switch ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_PRESET_MASK )
+ {
+ case XEN_SYSCTL_CPPC_SET_PRESET_POWERSAVE:
+ data->minimum = data->hw.lowest;
+ data->maximum = data->hw.lowest;
+ data->activity_window = 0;
+ data->energy_perf = HWP_ENERGY_PERF_MAX_POWERSAVE;
+ data->desired = 0;
+ break;
+
+ case XEN_SYSCTL_CPPC_SET_PRESET_PERFORMANCE:
+ data->minimum = data->hw.highest;
+ data->maximum = data->hw.highest;
+ data->activity_window = 0;
+ data->energy_perf = HWP_ENERGY_PERF_MAX_PERFORMANCE;
+ data->desired = 0;
+ break;
+
+ case XEN_SYSCTL_CPPC_SET_PRESET_BALANCE:
+ data->minimum = data->hw.lowest;
+ data->maximum = data->hw.highest;
+ data->activity_window = 0;
+ data->energy_perf = HWP_ENERGY_PERF_BALANCE;
+ data->desired = 0;
+ break;
+
+ case XEN_SYSCTL_CPPC_SET_PRESET_NONE:
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ /* Further customize presets if needed */
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_MINIMUM )
+ data->minimum = set_cppc->minimum;
+
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_MAXIMUM )
+ data->maximum = set_cppc->maximum;
+
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_ENERGY_PERF )
+ data->energy_perf = set_cppc->energy_perf;
+
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_DESIRED )
+ data->desired = set_cppc->desired;
+
+ if ( set_cppc->set_params & XEN_SYSCTL_CPPC_SET_ACT_WINDOW )
+ data->activity_window = set_cppc->activity_window &
+ XEN_SYSCTL_CPPC_ACT_WINDOW_MASK;
+
+ return hwp_cpufreq_target(policy, 0, 0);
+}
+
int __init hwp_register_driver(void)
{
return cpufreq_register_driver(&hwp_cpufreq_driver);
@@ -402,6 +402,19 @@ static int set_cpufreq_para(struct xen_sysctl_pm_op *op)
return ret;
}
+static int set_cpufreq_cppc(const struct xen_sysctl_pm_op *op)
+{
+ struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_policy, op->cpuid);
+
+ if ( !policy || !policy->governor )
+ return -EINVAL;
+
+ if ( !hwp_active() )
+ return -EINVAL;
+
+ return set_hwp_para(policy, &op->u.set_cppc);
+}
+
int do_pm_op(struct xen_sysctl_pm_op *op)
{
int ret = 0;
@@ -474,6 +487,10 @@ int do_pm_op(struct xen_sysctl_pm_op *op)
break;
}
+ case SET_CPUFREQ_CPPC:
+ ret = set_cpufreq_cppc(op);
+ break;
+
case GET_CPUFREQ_AVGFREQ:
{
op->u.get_avgfreq = cpufreq_driver_getavg(op->cpuid, USR_GETAVG);
@@ -250,5 +250,7 @@ extern bool __initdata opt_cpufreq_hwp;
int hwp_cmdline_parse(const char *s);
int get_hwp_para(const unsigned int cpu,
struct xen_cppc_para *cppc_para);
+int set_hwp_para(struct cpufreq_policy *policy,
+ const struct xen_set_cppc_para *set_cppc);
#endif /* __XEN_CPUFREQ_PM_H__ */
@@ -351,6 +351,62 @@ struct xen_cppc_para {
uint32_t activity_window;
};
+/*
+ * Set CPPC values.
+ *
+ * Configured the parameters for CPPC. Set bits in set_params control which
+ * values are applied.
+ *
+ * There are a set of presets along with individual fields. Presets are
+ * applied first, and then individual fields. This allows customizing
+ * a preset without having to specify every value.
+ *
+ * The preset options values are as follows:
+ *
+ * preset | minimum | maxium | energy_perf
+ * ------------+---------+---------+----------------
+ * powersave | lowest | lowest | powersave (255)
+ * ------------+---------+---------+----------------
+ * balance | lowest | highest | balance (128)
+ * ------------+---------+---------+----------------
+ * performance | highest | highest | performance (0)
+ *
+ * desired and activity_window are set to 0, hardware selected.
+ */
+struct xen_set_cppc_para {
+#define XEN_SYSCTL_CPPC_SET_DESIRED (1U << 0)
+#define XEN_SYSCTL_CPPC_SET_ENERGY_PERF (1U << 1)
+#define XEN_SYSCTL_CPPC_SET_ACT_WINDOW (1U << 2)
+#define XEN_SYSCTL_CPPC_SET_MINIMUM (1U << 3)
+#define XEN_SYSCTL_CPPC_SET_MAXIMUM (1U << 4)
+#define XEN_SYSCTL_CPPC_SET_PRESET_MASK 0xf000
+#define XEN_SYSCTL_CPPC_SET_PRESET_NONE 0x0000
+#define XEN_SYSCTL_CPPC_SET_PRESET_BALANCE 0x1000
+#define XEN_SYSCTL_CPPC_SET_PRESET_POWERSAVE 0x2000
+#define XEN_SYSCTL_CPPC_SET_PRESET_PERFORMANCE 0x3000
+#define XEN_SYSCTL_CPPC_SET_PARAM_MASK ( \
+ XEN_SYSCTL_CPPC_SET_PRESET_MASK | \
+ XEN_SYSCTL_CPPC_SET_DESIRED | \
+ XEN_SYSCTL_CPPC_SET_ENERGY_PERF | \
+ XEN_SYSCTL_CPPC_SET_ACT_WINDOW | \
+ XEN_SYSCTL_CPPC_SET_MINIMUM | \
+ XEN_SYSCTL_CPPC_SET_MAXIMUM )
+ uint32_t set_params; /* bitflags for valid values */
+ /* See comments in struct xen_cppc_para. */
+ uint32_t minimum;
+ uint32_t maximum;
+ uint32_t desired;
+ /*
+ * Hint to hardware for energy/performance preference.
+ * 0: Performance
+ * 128: Balance (Default)
+ * 255: Powersaving
+ */
+ uint32_t energy_perf;
+#define XEN_SYSCTL_CPPC_ACT_WINDOW_MASK 0x03ff
+ uint32_t activity_window;
+};
+
#define XEN_HWP_DRIVER "hwp"
/*
* cpufreq para name of this structure named
@@ -417,6 +473,7 @@ struct xen_sysctl_pm_op {
#define SET_CPUFREQ_GOV (CPUFREQ_PARA | 0x02)
#define SET_CPUFREQ_PARA (CPUFREQ_PARA | 0x03)
#define GET_CPUFREQ_AVGFREQ (CPUFREQ_PARA | 0x04)
+ #define SET_CPUFREQ_CPPC (CPUFREQ_PARA | 0x05)
/* set/reset scheduler power saving option */
#define XEN_SYSCTL_pm_op_set_sched_opt_smt 0x21
@@ -443,6 +500,7 @@ struct xen_sysctl_pm_op {
struct xen_get_cpufreq_para get_para;
struct xen_set_cpufreq_gov set_gov;
struct xen_set_cpufreq_para set_para;
+ struct xen_set_cppc_para set_cppc;
uint64_aligned_t get_avgfreq;
uint32_t set_sched_opt_smt;
#define XEN_SYSCTL_CX_UNLIMITED 0xffffffff
Add SET_CPUFREQ_HWP xen_sysctl_pm_op to set HWP parameters. The sysctl supports setting multiple values simultaneously as indicated by the set_params bits. This allows atomically applying new HWP configuration via a single wrmsr. XEN_SYSCTL_HWP_SET_PRESET_BALANCE/PERFORMANCE/POWERSAVE provide three common presets. Setting them depends on hardware limits which the hypervisor is already caching. So using them allows skipping a hypercall to query the limits (lowest/highest) to then set those same values. The code is organized to allow a preset to be refined with additional stuff if desired. "most_efficient" and "guaranteed" could be additional presets in the future, but the are not added now. Those levels can change at runtime, but we don't have code in place to monitor and update for those events. Signed-off-by: Jason Andryuk <jandryuk@gmail.com> --- v4: Remove IA32_ENERGY_BIAS support Validate parameters don't exceed 255 Use CPPC/cppc name set_cppc_para() add const set_cppc_para() return hwp_cpufreq_target() Expand sysctl comments v3: Remove cpufreq_governor_internal from set_cpufreq_hwp v2: Update for naming anonymous union Drop hwp_err for invalid input in set_hwp_para() Drop uint16_t cast in XEN_SYSCTL_HWP_SET_PARAM_MASK Drop parens for HWP_SET_PRESET defines Reference activity_window format comment Place SET_CPUFREQ_HWP after SET_CPUFREQ_PARA Add {HWP,IA32}_ENERGY_PERF_MAX_{PERFORMANCE,POWERSAVE} defines Order defines before fields in sysctl.h Use XEN_HWP_GOVERNOR Use per_cpu for hwp_drv_data --- xen/arch/x86/acpi/cpufreq/hwp.c | 98 ++++++++++++++++++++++++++++++ xen/drivers/acpi/pmstat.c | 17 ++++++ xen/include/acpi/cpufreq/cpufreq.h | 2 + xen/include/public/sysctl.h | 58 ++++++++++++++++++ 4 files changed, 175 insertions(+)