Merge branches 'pm-cpuidle', 'pm-cpufreq' and 'pm-devfreq'

Merge cpuidle, cpufreq and devfreq updates for 6.8-rc1:

 - Add support for the Sierra Forest, Grand Ridge and Meteorlake SoCs to
   the intel_idle cpuidle driver (Artem Bityutskiy, Zhang Rui).

 - Do not enable interrupts when entering idle in the haltpoll cpuidle
   driver (Borislav Petkov).

 - Add Emerald Rapids support in no-HWP mode to the intel_pstate cpufreq
   driver (Zhenguo Yao).

 - Use EPP values programmed by the platform firmware as balance
   performance ones by default in intel_pstate (Srinivas Pandruvada).

 - Add a missing function return value check to the SCMI cpufreq driver
   to avoid unexpected behavior (Alexandra Diupina).

 - Fix parameter type warning in the armada-8k cpufreq driver (Gregory
   CLEMENT).

 - Rework trans_stat_show() in the devfreq core code to avoid buffer
   overflows (Christian Marangi).

 - Synchronize devfreq_monitor_[start/stop] so as to prevent a timer
   list corruption from occurring when devfreq governors are switched
   frequently (Mukesh Ojha).

* pm-cpuidle:
  cpuidle: haltpoll: Do not enable interrupts when entering idle
  intel_idle: add Sierra Forest SoC support
  intel_idle: add Grand Ridge SoC support
  intel_idle: Add Meteorlake support

* pm-cpufreq:
  cpufreq: intel_pstate: Add Emerald Rapids support in no-HWP mode
  cpufreq: armada-8k: Fix parameter type warning
  cpufreq: scmi: process the result of devm_of_clk_add_hw_provider()
  cpufreq: intel_pstate: Prioritize firmware-provided balance performance EPP

* pm-devfreq:
  PM / devfreq: Synchronize devfreq_monitor_[start/stop]
  PM / devfreq: Convert to use sysfs_emit_at() API
  PM / devfreq: Fix buffer overflow in trans_stat_show

Author: rafaeljw

Documentation/ABI/testing/sysfs-class-devfreq

@@ -52,6 +52,9 @@ Description:
 
 			echo 0 > /sys/class/devfreq/.../trans_stat
 
+		If the transition table is bigger than PAGE_SIZE, reading
+		this will return an -EFBIG error.
+
 What:		/sys/class/devfreq/.../available_frequencies
 Date:		October 2012
 Contact:	Nishanth Menon <nm@ti.com>

drivers/cpufreq/armada-8k-cpufreq.c

@@ -57,7 +57,7 @@ static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 		if (IS_ERR(clk)) {
 			pr_warn("Cannot get clock for CPU %d\n", cpu);
 		} else {
@@ -165,7 +165,7 @@ static int __init armada_8k_cpufreq_init(void)
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 
 		if (IS_ERR(clk)) {
 			pr_err("Cannot get clock for CPU %d\n", cpu);

drivers/cpufreq/intel_pstate.c

@@ -1691,13 +1691,6 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 {
 	cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 
-	/*
-	 * If this CPU gen doesn't call for change in balance_perf
-	 * EPP return.
-	 */
-	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
-		return;
-
 	/*
 	 * If the EPP is set by firmware, which means that firmware enabled HWP
 	 * - Is equal or less than 0x80 (default balance_perf EPP)
@@ -1710,6 +1703,13 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 		return;
 	}
 
+	/*
+	 * If this CPU gen doesn't call for change in balance_perf
+	 * EPP return.
+	 */
+	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
+		return;
+
 	/*
 	 * Use hard coded value per gen to update the balance_perf
 	 * and default EPP.
@@ -2406,6 +2406,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(ICELAKE_X,		core_funcs),
 	X86_MATCH(TIGERLAKE,		core_funcs),
 	X86_MATCH(SAPPHIRERAPIDS_X,	core_funcs),
+	X86_MATCH(EMERALDRAPIDS_X,      core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

drivers/cpufreq/scmi-cpufreq.c

@@ -334,8 +334,11 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev)
 
 #ifdef CONFIG_COMMON_CLK
 	/* dummy clock provider as needed by OPP if clocks property is used */
-	if (of_property_present(dev->of_node, "#clock-cells"))
-		devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+	if (of_property_present(dev->of_node, "#clock-cells")) {
+		ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+		if (ret)
+			return dev_err_probe(dev, ret, "%s: registering clock provider failed\n", __func__);
+	}
 #endif
 
 	ret = cpufreq_register_driver(&scmi_cpufreq_driver);

drivers/cpuidle/cpuidle-haltpoll.c

@@ -25,13 +25,12 @@ MODULE_PARM_DESC(force, "Load unconditionally");
 static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
 static enum cpuhp_state haltpoll_hp_state;
 
-static int default_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv, int index)
+static __cpuidle int default_enter_idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
 {
-	if (current_clr_polling_and_test()) {
-		local_irq_enable();
+	if (current_clr_polling_and_test())
 		return index;
-	}
+
 	arch_cpu_idle();
 	return index;
 }

drivers/devfreq/devfreq.c

@@ -461,10 +461,14 @@ static void devfreq_monitor(struct work_struct *work)
 	if (err)
 		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
 
+	if (devfreq->stop_polling)
+		goto out;
+
 	queue_delayed_work(devfreq_wq, &devfreq->work,
 				msecs_to_jiffies(devfreq->profile->polling_ms));
-	mutex_unlock(&devfreq->lock);
 
+out:
+	mutex_unlock(&devfreq->lock);
 	trace_devfreq_monitor(devfreq);
 }
 
@@ -483,6 +487,10 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (delayed_work_pending(&devfreq->work))
+		goto out;
+
 	switch (devfreq->profile->timer) {
 	case DEVFREQ_TIMER_DEFERRABLE:
 		INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
@@ -491,12 +499,16 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 		INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
 		break;
 	default:
-		return;
+		goto out;
 	}
 
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
+
+out:
+	devfreq->stop_polling = false;
+	mutex_unlock(&devfreq->lock);
 }
 EXPORT_SYMBOL(devfreq_monitor_start);
 
@@ -513,6 +525,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (devfreq->stop_polling) {
+		mutex_unlock(&devfreq->lock);
+		return;
+	}
+
+	devfreq->stop_polling = true;
+	mutex_unlock(&devfreq->lock);
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_stop);
@@ -1688,7 +1708,7 @@ static ssize_t trans_stat_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
-	ssize_t len;
+	ssize_t len = 0;
 	int i, j;
 	unsigned int max_state;
 
@@ -1697,7 +1717,7 @@ static ssize_t trans_stat_show(struct device *dev,
 	max_state = df->max_state;
 
 	if (max_state == 0)
-		return sprintf(buf, "Not Supported.\n");
+		return sysfs_emit(buf, "Not Supported.\n");
 
 	mutex_lock(&df->lock);
 	if (!df->stop_polling &&
@@ -1707,31 +1727,49 @@ static ssize_t trans_stat_show(struct device *dev,
 	}
 	mutex_unlock(&df->lock);
 
-	len = sprintf(buf, "     From  :   To\n");
-	len += sprintf(buf + len, "           :");
-	for (i = 0; i < max_state; i++)
-		len += sprintf(buf + len, "%10lu",
-				df->freq_table[i]);
+	len += sysfs_emit_at(buf, len, "     From  :   To\n");
+	len += sysfs_emit_at(buf, len, "           :");
+	for (i = 0; i < max_state; i++) {
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu",
+				     df->freq_table[i]);
+	}
 
-	len += sprintf(buf + len, "   time(ms)\n");
+	if (len >= PAGE_SIZE - 1)
+		return PAGE_SIZE - 1;
+	len += sysfs_emit_at(buf, len, "   time(ms)\n");
 
 	for (i = 0; i < max_state; i++) {
-		if (df->freq_table[i] == df->previous_freq)
-			len += sprintf(buf + len, "*");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		if (df->freq_table[2] == df->previous_freq)
+			len += sysfs_emit_at(buf, len, "*");
 		else
-			len += sprintf(buf + len, " ");
-
-		len += sprintf(buf + len, "%10lu:", df->freq_table[i]);
-		for (j = 0; j < max_state; j++)
-			len += sprintf(buf + len, "%10u",
+			len += sysfs_emit_at(buf, len, " ");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu:", df->freq_table[i]);
+		for (j = 0; j < max_state; j++) {
+			if (len >= PAGE_SIZE - 1)
+				break;
+			len += sysfs_emit_at(buf, len, "%10u",
 				df->stats.trans_table[(i * max_state) + j]);
+		}
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10llu\n", (u64)
+				     jiffies64_to_msecs(df->stats.time_in_state[i]));
+	}
 
-		len += sprintf(buf + len, "%10llu\n", (u64)
-			jiffies64_to_msecs(df->stats.time_in_state[i]));
+	if (len < PAGE_SIZE - 1)
+		len += sysfs_emit_at(buf, len, "Total transition : %u\n",
+				     df->stats.total_trans);
+	if (len >= PAGE_SIZE - 1) {
+		pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n");
+		return -EFBIG;
 	}
 
-	len += sprintf(buf + len, "Total transition : %u\n",
-					df->stats.total_trans);
 	return len;
 }
 

drivers/idle/intel_idle.c

@@ -923,6 +923,35 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state mtl_l_cstates[] __initdata = {
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 420,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C10",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 930,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state gmt_cstates[] __initdata = {
 	{
 		.name = "C1",
@@ -1242,6 +1271,72 @@ static struct cpuidle_state snr_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state grr_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state srf_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 270,
+		.target_residency = 700,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6SP",
+		.desc = "MWAIT 0x23",
+		.flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 900,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
@@ -1349,6 +1444,10 @@ static const struct idle_cpu idle_cpu_adl_l __initconst = {
 	.state_table = adl_l_cstates,
 };
 
+static const struct idle_cpu idle_cpu_mtl_l __initconst = {
+	.state_table = mtl_l_cstates,
+};
+
 static const struct idle_cpu idle_cpu_gmt __initconst = {
 	.state_table = gmt_cstates,
 };
@@ -1387,6 +1486,18 @@ static const struct idle_cpu idle_cpu_snr __initconst = {
 	.use_acpi = true,
 };
 
+static const struct idle_cpu idle_cpu_grr __initconst = {
+	.state_table = grr_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
+static const struct idle_cpu idle_cpu_srf __initconst = {
+	.state_table = srf_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&idle_cpu_nhx),
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&idle_cpu_nehalem),
@@ -1423,6 +1534,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&idle_cpu_adl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&idle_cpu_adl_l),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&idle_cpu_mtl_l),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&idle_cpu_gmt),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&idle_cpu_spr),
@@ -1432,6 +1544,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&idle_cpu_bxt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&idle_cpu_dnv),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_snr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&idle_cpu_grr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&idle_cpu_srf),
 	{}
 };