Merge tag 'pm-6.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These make the intel_pstate driver work as expected on all hybrid
  platforms to date (regardless of possible platform firmware issues),
  fix hybrid sleep on systems using suspend-to-idle by default, make the
  generic power domains code handle disabled idle states properly and
  update pm-graph.

  Specifics:

   - Make intel_pstate use what is known about the hardware instead of
     relying on information from the platform firmware (ACPI CPPC in
     particular) to establish the relationship between the HWP CPU
     performance levels and frequencies on all hybrid platforms
     available to date (Rafael Wysocki)

   - Allow hybrid sleep to use suspend-to-idle as a system suspend
     method if it is the current suspend method of choice (Mario
     Limonciello)

   - Fix handling of unavailable/disabled idle states in the generic
     power domains code (Sudeep Holla)

   - Update the pm-graph suite of utilities to version 5.10 which is
     fixes-mostly and does not add any new features (Todd Brandt)"

* tag 'pm-6.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: domains: Fix handling of unavailable/disabled idle states
  pm-graph v5.10
  cpufreq: intel_pstate: hybrid: Use known scaling factor for P-cores
  cpufreq: intel_pstate: Read all MSRs on the target CPU
  PM: hibernate: Allow hybrid sleep to work with s2idle

2 files changed, 51 insertions, 86 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index ead135c7044c..6471b559230e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2952,6 +2952,10 @@ static int genpd_iterate_idle_states(struct device_node *dn,
 		np = it.node;
 		if (!of_match_node(idle_state_match, np))
 			continue;
+
+		if (!of_device_is_available(np))
+			continue;
+
 		if (states) {
 			ret = genpd_parse_state(&states[i], np);
 			if (ret) {
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fc3ebeb0bbe5..6ff73c30769f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -27,6 +27,7 @@
 #include <linux/pm_qos.h>
 #include <trace/events/power.h>
 
+#include <asm/cpu.h>
 #include <asm/div64.h>
 #include <asm/msr.h>
 #include <asm/cpu_device_id.h>
@@ -280,10 +281,10 @@ static struct cpudata **all_cpu_data;
  * structure is used to store those callbacks.
  */
 struct pstate_funcs {
-	int (*get_max)(void);
-	int (*get_max_physical)(void);
-	int (*get_min)(void);
-	int (*get_turbo)(void);
+	int (*get_max)(int cpu);
+	int (*get_max_physical)(int cpu);
+	int (*get_min)(int cpu);
+	int (*get_turbo)(int cpu);
 	int (*get_scaling)(void);
 	int (*get_cpu_scaling)(int cpu);
 	int (*get_aperf_mperf_shift)(void);
@@ -398,16 +399,6 @@ static int intel_pstate_get_cppc_guaranteed(int cpu)
 
 	return cppc_perf.nominal_perf;
 }
-
-static u32 intel_pstate_cppc_nominal(int cpu)
-{
-	u64 nominal_perf;
-
-	if (cppc_get_nominal_perf(cpu, &nominal_perf))
-		return 0;
-
-	return nominal_perf;
-}
 #else /* CONFIG_ACPI_CPPC_LIB */
 static inline void intel_pstate_set_itmt_prio(int cpu)
 {
@@ -531,35 +522,18 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 {
 	int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
 	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
-	int perf_ctl_turbo = pstate_funcs.get_turbo();
-	int turbo_freq = perf_ctl_turbo * perf_ctl_scaling;
+	int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
 	int scaling = cpu->pstate.scaling;
 
 	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
-	pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, pstate_funcs.get_max());
 	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
 	pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
 	pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
 	pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
 	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);
 
-	/*
-	 * If the product of the HWP performance scaling factor and the HWP_CAP
-	 * highest performance is greater than the maximum turbo frequency
-	 * corresponding to the pstate_funcs.get_turbo() return value, the
-	 * scaling factor is too high, so recompute it to make the HWP_CAP
-	 * highest performance correspond to the maximum turbo frequency.
-	 */
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling;
-	if (turbo_freq < cpu->pstate.turbo_freq) {
-		cpu->pstate.turbo_freq = turbo_freq;
-		scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate);
-		cpu->pstate.scaling = scaling;
-
-		pr_debug("CPU%d: refined HWP-to-frequency scaling factor: %d\n",
-			 cpu->cpu, scaling);
-	}
-
+	cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling,
+					   perf_ctl_scaling);
 	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
 					 perf_ctl_scaling);
 
@@ -1740,7 +1714,7 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	intel_pstate_update_epp_defaults(cpudata);
 }
 
-static int atom_get_min_pstate(void)
+static int atom_get_min_pstate(int not_used)
 {
 	u64 value;
 
@@ -1748,7 +1722,7 @@ static int atom_get_min_pstate(void)
 	return (value >> 8) & 0x7F;
 }
 
-static int atom_get_max_pstate(void)
+static int atom_get_max_pstate(int not_used)
 {
 	u64 value;
 
@@ -1756,7 +1730,7 @@ static int atom_get_max_pstate(void)
 	return (value >> 16) & 0x7F;
 }
 
-static int atom_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(int not_used)
 {
 	u64 value;
 
@@ -1834,23 +1808,23 @@ static void atom_get_vid(struct cpudata *cpudata)
 	cpudata->vid.turbo = value & 0x7f;
 }
 
-static int core_get_min_pstate(void)
+static int core_get_min_pstate(int cpu)
 {
 	u64 value;
 
-	rdmsrl(MSR_PLATFORM_INFO, value);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
 	return (value >> 40) & 0xFF;
 }
 
-static int core_get_max_pstate_physical(void)
+static int core_get_max_pstate_physical(int cpu)
 {
 	u64 value;
 
-	rdmsrl(MSR_PLATFORM_INFO, value);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
 	return (value >> 8) & 0xFF;
 }
 
-static int core_get_tdp_ratio(u64 plat_info)
+static int core_get_tdp_ratio(int cpu, u64 plat_info)
 {
 	/* Check how many TDP levels present */
 	if (plat_info & 0x600000000) {
@@ -1860,13 +1834,13 @@ static int core_get_tdp_ratio(u64 plat_info)
 		int err;
 
 		/* Get the TDP level (0, 1, 2) to get ratios */
-		err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+		err = rdmsrl_safe_on_cpu(cpu, MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
 		if (err)
 			return err;
 
 		/* TDP MSR are continuous starting at 0x648 */
 		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
-		err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+		err = rdmsrl_safe_on_cpu(cpu, tdp_msr, &tdp_ratio);
 		if (err)
 			return err;
 
@@ -1883,7 +1857,7 @@ static int core_get_tdp_ratio(u64 plat_info)
 	return -ENXIO;
 }
 
-static int core_get_max_pstate(void)
+static int core_get_max_pstate(int cpu)
 {
 	u64 tar;
 	u64 plat_info;
@@ -1891,10 +1865,10 @@ static int core_get_max_pstate(void)
 	int tdp_ratio;
 	int err;
 
-	rdmsrl(MSR_PLATFORM_INFO, plat_info);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &plat_info);
 	max_pstate = (plat_info >> 8) & 0xFF;
 
-	tdp_ratio = core_get_tdp_ratio(plat_info);
+	tdp_ratio = core_get_tdp_ratio(cpu, plat_info);
 	if (tdp_ratio <= 0)
 		return max_pstate;
 
@@ -1903,7 +1877,7 @@ static int core_get_max_pstate(void)
 		return tdp_ratio;
 	}
 
-	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
+	err = rdmsrl_safe_on_cpu(cpu, MSR_TURBO_ACTIVATION_RATIO, &tar);
 	if (!err) {
 		int tar_levels;
 
@@ -1918,13 +1892,13 @@ static int core_get_max_pstate(void)
 	return max_pstate;
 }
 
-static int core_get_turbo_pstate(void)
+static int core_get_turbo_pstate(int cpu)
 {
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
-	nont = core_get_max_pstate();
+	rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+	nont = core_get_max_pstate(cpu);
 	ret = (value) & 255;
 	if (ret <= nont)
 		ret = nont;
@@ -1952,50 +1926,37 @@ static int knl_get_aperf_mperf_shift(void)
 	return 10;
 }
 
-static int knl_get_turbo_pstate(void)
+static int knl_get_turbo_pstate(int cpu)
 {
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
-	nont = core_get_max_pstate();
+	rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+	nont = core_get_max_pstate(cpu);
 	ret = (((value) >> 8) & 0xFF);
 	if (ret <= nont)
 		ret = nont;
 	return ret;
 }
 
-#ifdef CONFIG_ACPI_CPPC_LIB
-static u32 hybrid_ref_perf;
-
-static int hybrid_get_cpu_scaling(int cpu)
+static void hybrid_get_type(void *data)
 {
-	return DIV_ROUND_UP(core_get_scaling() * hybrid_ref_perf,
-			    intel_pstate_cppc_nominal(cpu));
+	u8 *cpu_type = data;
+
+	*cpu_type = get_this_hybrid_cpu_type();
 }
 
-static void intel_pstate_cppc_set_cpu_scaling(void)
+static int hybrid_get_cpu_scaling(int cpu)
 {
-	u32 min_nominal_perf = U32_MAX;
-	int cpu;
+	u8 cpu_type = 0;
 
-	for_each_present_cpu(cpu) {
-		u32 nominal_perf = intel_pstate_cppc_nominal(cpu);
+	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
+	/* P-cores have a smaller perf level-to-freqency scaling factor. */
+	if (cpu_type == 0x40)
+		return 78741;
 
-		if (nominal_perf && nominal_perf < min_nominal_perf)
-			min_nominal_perf = nominal_perf;
-	}
-
-	if (min_nominal_perf < U32_MAX) {
-		hybrid_ref_perf = min_nominal_perf;
-		pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
-	}
+	return core_get_scaling();
 }
-#else
-static inline void intel_pstate_cppc_set_cpu_scaling(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_LIB */
 
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
@@ -2025,10 +1986,10 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu)
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
-	int perf_ctl_max_phys = pstate_funcs.get_max_physical();
+	int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu);
 	int perf_ctl_scaling = pstate_funcs.get_scaling();
 
-	cpu->pstate.min_pstate = pstate_funcs.get_min();
+	cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu);
 	cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
 	cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;
 
@@ -2044,8 +2005,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 		}
 	} else {
 		cpu->pstate.scaling = perf_ctl_scaling;
-		cpu->pstate.max_pstate = pstate_funcs.get_max();
-		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+		cpu->pstate.max_pstate = pstate_funcs.get_max(cpu->cpu);
+		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(cpu->cpu);
 	}
 
 	if (cpu->pstate.scaling == perf_ctl_scaling) {
@@ -3221,9 +3182,9 @@ static unsigned int force_load __initdata;
 
 static int __init intel_pstate_msrs_not_valid(void)
 {
-	if (!pstate_funcs.get_max() ||
-	    !pstate_funcs.get_min() ||
-	    !pstate_funcs.get_turbo())
+	if (!pstate_funcs.get_max(0) ||
+	    !pstate_funcs.get_min(0) ||
+	    !pstate_funcs.get_turbo(0))
 		return -ENODEV;
 
 	return 0;
@@ -3450,7 +3411,7 @@ static int __init intel_pstate_init(void)
 				default_driver = &intel_pstate;
 
 			if (boot_cpu_has(X86_FEATURE_HYBRID_CPU))
-				intel_pstate_cppc_set_cpu_scaling();
+				pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
 
 			goto hwp_cpu_matched;
 		}