Merge tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These include a significant update of the generic power domains
  (genpd) and Operating Performance Points (OPP) frameworks, mostly
  related to the introduction of power domain performance levels,
  cpufreq updates (new driver for Qualcomm Kryo processors, updates of
  the existing drivers, some core fixes, schedutil governor
  improvements), PCI power management fixes, ACPI workaround for
  EC-based wakeup events handling on resume from suspend-to-idle, and
  major updates of the turbostat and pm-graph utilities.

  Specifics:

   - Introduce power domain performance levels into the the generic
     power domains (genpd) and Operating Performance Points (OPP)
     frameworks (Viresh Kumar, Rajendra Nayak, Dan Carpenter).

   - Fix two issues in the runtime PM framework related to the
     initialization and removal of devices using device links (Ulf
     Hansson).

   - Clean up the initialization of drivers for devices in PM domains
     (Ulf Hansson, Geert Uytterhoeven).

   - Fix a cpufreq core issue related to the policy sysfs interface
     causing CPU online to fail for CPUs sharing one cpufreq policy in
     some situations (Tao Wang).

   - Make it possible to use platform-specific suspend/resume hooks in
     the cpufreq-dt driver and make the Armada 37xx DVFS use that
     feature (Viresh Kumar, Miquel Raynal).

   - Optimize policy transition notifications in cpufreq (Viresh Kumar).

   - Improve the iowait boost mechanism in the schedutil cpufreq
     governor (Patrick Bellasi).

   - Improve the handling of deferred frequency updates in the schedutil
     cpufreq governor (Joel Fernandes, Dietmar Eggemann, Rafael Wysocki,
     Viresh Kumar).

   - Add a new cpufreq driver for Qualcomm Kryo (Ilia Lin).

   - Fix and clean up some cpufreq drivers (Colin Ian King, Dmitry
     Osipenko, Doug Smythies, Luc Van Oostenryck, Simon Horman, Viresh
     Kumar).

   - Fix the handling of PCI devices with the DPM_SMART_SUSPEND flag set
     and update stale comments in the PCI core PM code (Rafael Wysocki).

   - Work around an issue related to the handling of EC-based wakeup
     events in the ACPI PM core during resume from suspend-to-idle if
     the EC has been put into the low-power mode (Rafael Wysocki).

   - Improve the handling of wakeup source objects in the PM core (Doug
     Berger, Mahendran Ganesh, Rafael Wysocki).

   - Update the driver core to prevent deferred probe from breaking
     suspend/resume ordering (Feng Kan).

   - Clean up the PM core somewhat (Bjorn Helgaas, Ulf Hansson, Rafael
     Wysocki).

   - Make the core suspend/resume code and cpufreq support the RT patch
     (Sebastian Andrzej Siewior, Thomas Gleixner).

   - Consolidate the PM QoS handling in cpuidle governors (Rafael
     Wysocki).

   - Fix a possible crash in the hibernation core (Tetsuo Handa).

   - Update the rockchip-io Adaptive Voltage Scaling (AVS) driver (David
     Wu).

   - Update the turbostat utility (fixes, cleanups, new CPU IDs, new
     command line options, built-in "Low Power Idle" counters support,
     new POLL and POLL% columns) and add an entry for it to MAINTAINERS
     (Len Brown, Artem Bityutskiy, Chen Yu, Laura Abbott, Matt Turner,
     Prarit Bhargava, Srinivas Pandruvada).

   - Update the pm-graph to version 5.1 (Todd Brandt).

   - Update the intel_pstate_tracer utility (Doug Smythies)"

* tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (128 commits)
  tools/power turbostat: update version number
  tools/power turbostat: Add Node in output
  tools/power turbostat: add node information into turbostat calculations
  tools/power turbostat: remove num_ from cpu_topology struct
  tools/power turbostat: rename num_cores_per_pkg to num_cores_per_node
  tools/power turbostat: track thread ID in cpu_topology
  tools/power turbostat: Calculate additional node information for a package
  tools/power turbostat: Fix node and siblings lookup data
  tools/power turbostat: set max_num_cpus equal to the cpumask length
  tools/power turbostat: if --num_iterations, print for specific number of iterations
  tools/power turbostat: Add Cannon Lake support
  tools/power turbostat: delete duplicate #defines
  x86: msr-index.h: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: add POLL and POLL% column
  tools/power turbostat: Fix --hide Pk%pc10
  tools/power turbostat: Build-in "Low Power Idle" counters support
  tools/power turbostat: Don't make man pages executable
  tools/power turbostat: remove blank lines
  tools/power turbostat: a small C-states dump readability immprovement
  ...

1 files changed, 87 insertions, 13 deletions

diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 72a2975499db..739da90ff3f6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -23,6 +23,8 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
+#include "cpufreq-dt.h"
+
 /* Power management in North Bridge register set */
 #define ARMADA_37XX_NB_L0L1	0x18
 #define ARMADA_37XX_NB_L2L3	0x1C
@@ -56,6 +58,16 @@
  */
 #define LOAD_LEVEL_NR	4
 
+struct armada37xx_cpufreq_state {
+	struct regmap *regmap;
+	u32 nb_l0l1;
+	u32 nb_l2l3;
+	u32 nb_dyn_mod;
+	u32 nb_cpu_load;
+};
+
+static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
+
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
@@ -136,7 +148,7 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
-static void __init armada37xx_cpufreq_disable_dvfs(struct regmap *base)
+static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
 		mask = ARMADA_37XX_NB_DFS_EN;
@@ -162,10 +174,47 @@ static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base)
 	regmap_update_bits(base, reg, mask, mask);
 }
 
+static int armada37xx_cpufreq_suspend(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	regmap_read(state->regmap, ARMADA_37XX_NB_L0L1, &state->nb_l0l1);
+	regmap_read(state->regmap, ARMADA_37XX_NB_L2L3, &state->nb_l2l3);
+	regmap_read(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		    &state->nb_cpu_load);
+	regmap_read(state->regmap, ARMADA_37XX_NB_DYN_MOD, &state->nb_dyn_mod);
+
+	return 0;
+}
+
+static int armada37xx_cpufreq_resume(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	/* Ensure DVFS is disabled otherwise the following registers are RO */
+	armada37xx_cpufreq_disable_dvfs(state->regmap);
+
+	regmap_write(state->regmap, ARMADA_37XX_NB_L0L1, state->nb_l0l1);
+	regmap_write(state->regmap, ARMADA_37XX_NB_L2L3, state->nb_l2l3);
+	regmap_write(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		     state->nb_cpu_load);
+
+	/*
+	 * NB_DYN_MOD register is the one that actually enable back DVFS if it
+	 * was enabled before the suspend operation. This must be done last
+	 * otherwise other registers are not writable.
+	 */
+	regmap_write(state->regmap, ARMADA_37XX_NB_DYN_MOD, state->nb_dyn_mod);
+
+	return 0;
+}
+
 static int __init armada37xx_cpufreq_driver_init(void)
 {
+	struct cpufreq_dt_platform_data pdata;
 	struct armada_37xx_dvfs *dvfs;
 	struct platform_device *pdev;
+	unsigned long freq;
 	unsigned int cur_frequency;
 	struct regmap *nb_pm_base;
 	struct device *cpu_dev;
@@ -207,33 +256,58 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	}
 
 	dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
-	if (!dvfs)
+	if (!dvfs) {
+		clk_put(clk);
 		return -EINVAL;
+	}
+
+	armada37xx_cpufreq_state = kmalloc(sizeof(*armada37xx_cpufreq_state),
+					   GFP_KERNEL);
+	if (!armada37xx_cpufreq_state) {
+		clk_put(clk);
+		return -ENOMEM;
+	}
+
+	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
-		unsigned long freq = cur_frequency / dvfs->divider[load_lvl];
+		freq = cur_frequency / dvfs->divider[load_lvl];
 
 		ret = dev_pm_opp_add(cpu_dev, freq, 0);
-		if (ret) {
-			/* clean-up the already added opp before leaving */
-			while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
-				freq = cur_frequency / dvfs->divider[load_lvl];
-				dev_pm_opp_remove(cpu_dev, freq);
-			}
-			return ret;
-		}
+		if (ret)
+			goto remove_opp;
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
 	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
 
-	pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+	pdata.suspend = armada37xx_cpufreq_suspend;
+	pdata.resume = armada37xx_cpufreq_resume;
+
+	pdev = platform_device_register_data(NULL, "cpufreq-dt", -1, &pdata,
+					     sizeof(pdata));
+	ret = PTR_ERR_OR_ZERO(pdev);
+	if (ret)
+		goto disable_dvfs;
+
+	return 0;
+
+disable_dvfs:
+	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
+remove_opp:
+	/* clean-up the already added opp before leaving */
+	while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
+		freq = cur_frequency / dvfs->divider[load_lvl];
+		dev_pm_opp_remove(cpu_dev, freq);
+	}
+
+	kfree(armada37xx_cpufreq_state);
 
-	return PTR_ERR_OR_ZERO(pdev);
+	return ret;
 }
 /* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
 late_initcall(armada37xx_cpufreq_driver_init);