Merge branch 'pm-cpufreq'

Additional cpufreq updates for 4.18-rc1: fixes and cleanups in the
core and drivers and intel_pstate extension to do iowait boosting
on systems with HWP that improves performance quite a bit.

* pm-cpufreq:
  cpufreq: imx6q: check speed grades for i.MX6ULL
  cpufreq: governors: Fix long idle detection logic in load calculation
  cpufreq: intel_pstate: enable boost for Skylake Xeon
  cpufreq: intel_pstate: New sysfs entry to control HWP boost
  cpufreq: intel_pstate: HWP boost performance on IO wakeup
  cpufreq: intel_pstate: Add HWP boost utility and sched util hooks
  cpufreq: ti-cpufreq: Use devres managed API in probe()
  cpufreq: ti-cpufreq: Fix an incorrect error return value
  cpufreq: ACPI: make function acpi_cpufreq_fast_switch() static
  cpufreq: kryo: allow building as a loadable module

drivers/cpufreq/Kconfig.arm

@@ -125,7 +125,7 @@ config ARM_OMAP2PLUS_CPUFREQ
 	default ARCH_OMAP2PLUS
 
 config ARM_QCOM_CPUFREQ_KRYO
-	bool "Qualcomm Kryo based CPUFreq"
+	tristate "Qualcomm Kryo based CPUFreq"
 	depends on ARM64
 	depends on QCOM_QFPROM
 	depends on QCOM_SMEM

drivers/cpufreq/acpi-cpufreq.c

@@ -465,7 +465,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	return result;
 }
 
-unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
+static unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 					     unsigned int target_freq)
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;

drivers/cpufreq/cpufreq_governor.c

@@ -165,7 +165,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			 * calls, so the previous load value can be used then.
 			 */
 			load = j_cdbs->prev_load;
-		} else if (unlikely(time_elapsed > 2 * sampling_rate &&
+		} else if (unlikely((int)idle_time > 2 * sampling_rate &&
 				    j_cdbs->prev_load)) {
 			/*
 			 * If the CPU had gone completely idle and a task has
@@ -185,10 +185,8 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			 * clear prev_load to guarantee that the load will be
 			 * computed again next time.
 			 *
-			 * Detecting this situation is easy: the governor's
-			 * utilization update handler would not have run during
-			 * CPU-idle periods.  Hence, an unusually large
-			 * 'time_elapsed' (as compared to the sampling rate)
+			 * Detecting this situation is easy: an unusually large
+			 * 'idle_time' (as compared to the sampling rate)
 			 * indicates this scenario.
 			 */
 			load = j_cdbs->prev_load;
@@ -217,8 +215,8 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			j_cdbs->prev_load = load;
 		}
 
-		if (time_elapsed > 2 * sampling_rate) {
-			unsigned int periods = time_elapsed / sampling_rate;
+		if (unlikely((int)idle_time > 2 * sampling_rate)) {
+			unsigned int periods = idle_time / sampling_rate;
 
 			if (periods < idle_periods)
 				idle_periods = periods;

drivers/cpufreq/imx6q-cpufreq.c

@@ -266,6 +266,8 @@ static void imx6q_opp_check_speed_grading(struct device *dev)
 }
 
 #define OCOTP_CFG3_6UL_SPEED_696MHZ	0x2
+#define OCOTP_CFG3_6ULL_SPEED_792MHZ	0x2
+#define OCOTP_CFG3_6ULL_SPEED_900MHZ	0x3
 
 static void imx6ul_opp_check_speed_grading(struct device *dev)
 {
@@ -287,16 +289,30 @@ static void imx6ul_opp_check_speed_grading(struct device *dev)
 	 * Speed GRADING[1:0] defines the max speed of ARM:
 	 * 2b'00: Reserved;
 	 * 2b'01: 528000000Hz;
-	 * 2b'10: 696000000Hz;
-	 * 2b'11: Reserved;
+	 * 2b'10: 696000000Hz on i.MX6UL, 792000000Hz on i.MX6ULL;
+	 * 2b'11: 900000000Hz on i.MX6ULL only;
 	 * We need to set the max speed of ARM according to fuse map.
 	 */
 	val = readl_relaxed(base + OCOTP_CFG3);
 	val >>= OCOTP_CFG3_SPEED_SHIFT;
 	val &= 0x3;
+
+	if (of_machine_is_compatible("fsl,imx6ul")) {
 		if (val != OCOTP_CFG3_6UL_SPEED_696MHZ)
 			if (dev_pm_opp_disable(dev, 696000000))
 				dev_warn(dev, "failed to disable 696MHz OPP\n");
+	}
+
+	if (of_machine_is_compatible("fsl,imx6ull")) {
+		if (val != OCOTP_CFG3_6ULL_SPEED_792MHZ)
+			if (dev_pm_opp_disable(dev, 792000000))
+				dev_warn(dev, "failed to disable 792MHz OPP\n");
+
+		if (val != OCOTP_CFG3_6ULL_SPEED_900MHZ)
+			if (dev_pm_opp_disable(dev, 900000000))
+				dev_warn(dev, "failed to disable 900MHz OPP\n");
+	}
+
 	iounmap(base);
 put_node:
 	of_node_put(np);
@@ -356,7 +372,8 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		goto put_reg;
 	}
 
-	if (of_machine_is_compatible("fsl,imx6ul"))
+	if (of_machine_is_compatible("fsl,imx6ul") ||
+	    of_machine_is_compatible("fsl,imx6ull"))
 		imx6ul_opp_check_speed_grading(cpu_dev);
 	else
 		imx6q_opp_check_speed_grading(cpu_dev);

drivers/cpufreq/intel_pstate.c

@@ -221,6 +221,11 @@ struct global_params {
  *			preference/bias
  * @epp_saved:		Saved EPP/EPB during system suspend or CPU offline
  *			operation
+ * @hwp_req_cached:	Cached value of the last HWP Request MSR
+ * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
+ * @last_io_update:	Last time when IO wake flag was set
+ * @sched_flags:	Store scheduler flags for possible cross CPU update
+ * @hwp_boost_min:	Last HWP boosted min performance
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -253,6 +258,11 @@ struct cpudata {
 	s16 epp_policy;
 	s16 epp_default;
 	s16 epp_saved;
+	u64 hwp_req_cached;
+	u64 hwp_cap_cached;
+	u64 last_io_update;
+	unsigned int sched_flags;
+	u32 hwp_boost_min;
 };
 
 static struct cpudata **all_cpu_data;
@@ -285,6 +295,7 @@ static struct pstate_funcs pstate_funcs __read_mostly;
 
 static int hwp_active __read_mostly;
 static bool per_cpu_limits __read_mostly;
+static bool hwp_boost __read_mostly;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
@@ -689,6 +700,7 @@ static void intel_pstate_get_hwp_max(unsigned int cpu, int *phy_max,
 	u64 cap;
 
 	rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+	WRITE_ONCE(all_cpu_data[cpu]->hwp_cap_cached, cap);
 	if (global.no_turbo)
 		*current_max = HWP_GUARANTEED_PERF(cap);
 	else
@@ -763,6 +775,7 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 		intel_pstate_set_epb(cpu, epp);
 	}
 skip_epp:
+	WRITE_ONCE(cpu_data->hwp_req_cached, value);
 	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
 
@@ -1020,6 +1033,30 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	return count;
 }
 
+static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", hwp_boost);
+}
+
+static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b,
+				       const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	ret = kstrtouint(buf, 10, &input);
+	if (ret)
+		return ret;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	hwp_boost = !!input;
+	intel_pstate_update_policies();
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return count;
+}
+
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
@@ -1029,6 +1066,7 @@ define_one_global_rw(max_perf_pct);
 define_one_global_rw(min_perf_pct);
 define_one_global_ro(turbo_pct);
 define_one_global_ro(num_pstates);
+define_one_global_rw(hwp_dynamic_boost);
 
 static struct attribute *intel_pstate_attributes[] = {
 	&status.attr,
@@ -1069,6 +1107,11 @@ static void __init intel_pstate_sysfs_expose_params(void)
 	rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr);
 	WARN_ON(rc);
 
+	if (hwp_active) {
+		rc = sysfs_create_file(intel_pstate_kobject,
+				       &hwp_dynamic_boost.attr);
+		WARN_ON(rc);
+	}
 }
 /************************** sysfs end ************************/
 
@@ -1381,6 +1424,116 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	intel_pstate_set_min_pstate(cpu);
 }
 
+/*
+ * Long hold time will keep high perf limits for long time,
+ * which negatively impacts perf/watt for some workloads,
+ * like specpower. 3ms is based on experiements on some
+ * workoads.
+ */
+static int hwp_boost_hold_time_ns = 3 * NSEC_PER_MSEC;
+
+static inline void intel_pstate_hwp_boost_up(struct cpudata *cpu)
+{
+	u64 hwp_req = READ_ONCE(cpu->hwp_req_cached);
+	u32 max_limit = (hwp_req & 0xff00) >> 8;
+	u32 min_limit = (hwp_req & 0xff);
+	u32 boost_level1;
+
+	/*
+	 * Cases to consider (User changes via sysfs or boot time):
+	 * If, P0 (Turbo max) = P1 (Guaranteed max) = min:
+	 *	No boost, return.
+	 * If, P0 (Turbo max) > P1 (Guaranteed max) = min:
+	 *     Should result in one level boost only for P0.
+	 * If, P0 (Turbo max) = P1 (Guaranteed max) > min:
+	 *     Should result in two level boost:
+	 *         (min + p1)/2 and P1.
+	 * If, P0 (Turbo max) > P1 (Guaranteed max) > min:
+	 *     Should result in three level boost:
+	 *        (min + p1)/2, P1 and P0.
+	 */
+
+	/* If max and min are equal or already at max, nothing to boost */
+	if (max_limit == min_limit || cpu->hwp_boost_min >= max_limit)
+		return;
+
+	if (!cpu->hwp_boost_min)
+		cpu->hwp_boost_min = min_limit;
+
+	/* level at half way mark between min and guranteed */
+	boost_level1 = (HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) + min_limit) >> 1;
+
+	if (cpu->hwp_boost_min < boost_level1)
+		cpu->hwp_boost_min = boost_level1;
+	else if (cpu->hwp_boost_min < HWP_GUARANTEED_PERF(cpu->hwp_cap_cached))
+		cpu->hwp_boost_min = HWP_GUARANTEED_PERF(cpu->hwp_cap_cached);
+	else if (cpu->hwp_boost_min == HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) &&
+		 max_limit != HWP_GUARANTEED_PERF(cpu->hwp_cap_cached))
+		cpu->hwp_boost_min = max_limit;
+	else
+		return;
+
+	hwp_req = (hwp_req & ~GENMASK_ULL(7, 0)) | cpu->hwp_boost_min;
+	wrmsrl(MSR_HWP_REQUEST, hwp_req);
+	cpu->last_update = cpu->sample.time;
+}
+
+static inline void intel_pstate_hwp_boost_down(struct cpudata *cpu)
+{
+	if (cpu->hwp_boost_min) {
+		bool expired;
+
+		/* Check if we are idle for hold time to boost down */
+		expired = time_after64(cpu->sample.time, cpu->last_update +
+				       hwp_boost_hold_time_ns);
+		if (expired) {
+			wrmsrl(MSR_HWP_REQUEST, cpu->hwp_req_cached);
+			cpu->hwp_boost_min = 0;
+		}
+	}
+	cpu->last_update = cpu->sample.time;
+}
+
+static inline void intel_pstate_update_util_hwp_local(struct cpudata *cpu,
+						      u64 time)
+{
+	cpu->sample.time = time;
+
+	if (cpu->sched_flags & SCHED_CPUFREQ_IOWAIT) {
+		bool do_io = false;
+
+		cpu->sched_flags = 0;
+		/*
+		 * Set iowait_boost flag and update time. Since IO WAIT flag
+		 * is set all the time, we can't just conclude that there is
+		 * some IO bound activity is scheduled on this CPU with just
+		 * one occurrence. If we receive at least two in two
+		 * consecutive ticks, then we treat as boost candidate.
+		 */
+		if (time_before64(time, cpu->last_io_update + 2 * TICK_NSEC))
+			do_io = true;
+
+		cpu->last_io_update = time;
+
+		if (do_io)
+			intel_pstate_hwp_boost_up(cpu);
+
+	} else {
+		intel_pstate_hwp_boost_down(cpu);
+	}
+}
+
+static inline void intel_pstate_update_util_hwp(struct update_util_data *data,
+						u64 time, unsigned int flags)
+{
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+
+	cpu->sched_flags |= flags;
+
+	if (smp_processor_id() == cpu->cpu)
+		intel_pstate_update_util_hwp_local(cpu, time);
+}
+
 static inline void intel_pstate_calc_avg_perf(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
@@ -1641,6 +1794,12 @@ static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
 	{}
 };
 
+static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
+	ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
+	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs),
+	{}
+};
+
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
@@ -1671,6 +1830,10 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 			intel_pstate_disable_ee(cpunum);
 
 		intel_pstate_hwp_enable(cpu);
+
+		id = x86_match_cpu(intel_pstate_hwp_boost_ids);
+		if (id)
+			hwp_boost = true;
 	}
 
 	intel_pstate_get_cpu_pstates(cpu);
@@ -1684,7 +1847,7 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 {
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	if (hwp_active)
+	if (hwp_active && !hwp_boost)
 		return;
 
 	if (cpu->update_util_set)
@@ -1693,7 +1856,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
 	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
-				     intel_pstate_update_util);
+				     (hwp_active ?
+				      intel_pstate_update_util_hwp :
+				      intel_pstate_update_util));
 	cpu->update_util_set = true;
 }
 
@@ -1805,8 +1970,16 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		intel_pstate_set_update_util_hook(policy->cpu);
 	}
 
-	if (hwp_active)
+	if (hwp_active) {
+		/*
+		 * When hwp_boost was active before and dynamically it
+		 * was turned off, in that case we need to clear the
+		 * update util hook.
+		 */
+		if (!hwp_boost)
+			intel_pstate_clear_update_util_hook(policy->cpu);
 		intel_pstate_hwp_set(policy->cpu);
+	}
 
 	mutex_unlock(&intel_pstate_limits_lock);
 

drivers/cpufreq/ti-cpufreq.c

@@ -217,7 +217,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 	if (!match)
 		return -ENODEV;
 
-	opp_data = kzalloc(sizeof(*opp_data), GFP_KERNEL);
+	opp_data = devm_kzalloc(&pdev->dev, sizeof(*opp_data), GFP_KERNEL);
 	if (!opp_data)
 		return -ENOMEM;
 
@@ -226,8 +226,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 	opp_data->cpu_dev = get_cpu_device(0);
 	if (!opp_data->cpu_dev) {
 		pr_err("%s: Failed to get device for CPU0\n", __func__);
-		ret = ENODEV;
-		goto free_opp_data;
+		return -ENODEV;
 	}
 
 	opp_data->opp_node = dev_pm_opp_of_get_opp_desc_node(opp_data->cpu_dev);
@@ -285,8 +284,6 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 
 fail_put_node:
 	of_node_put(opp_data->opp_node);
-free_opp_data:
-	kfree(opp_data);
 
 	return ret;
 }