Merge tag 'pm-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add support for 'artificial' Energy Models in which power
  numbers for different entities may be in different scales, add support
  for some new hardware, fix bugs and clean up code in multiple places.

  Specifics:

   - Update the Energy Model support code to allow the Energy Model to
     be artificial, which means that the power values may not be on a
     uniform scale with other devices providing power information, and
     update the cpufreq_cooling and devfreq_cooling thermal drivers to
     support artificial Energy Models (Lukasz Luba).

   - Make DTPM check the Energy Model type (Lukasz Luba).

   - Fix policy counter decrementation in cpufreq if Energy Model is in
     use (Pierre Gondois).

   - Add CPU-based scaling support to passive devfreq governor (Saravana
     Kannan, Chanwoo Choi).

   - Update the rk3399_dmc devfreq driver (Brian Norris).

   - Export dev_pm_ops instead of suspend() and resume() in the IIO
     chemical scd30 driver (Jonathan Cameron).

   - Add namespace variants of EXPORT[_GPL]_SIMPLE_DEV_PM_OPS and
     PM-runtime counterparts (Jonathan Cameron).

   - Move symbol exports in the IIO chemical scd30 driver into the
     IIO_SCD30 namespace (Jonathan Cameron).

   - Avoid device PM-runtime usage count underflows (Rafael Wysocki).

   - Allow dynamic debug to control printing of PM messages (David
     Cohen).

   - Fix some kernel-doc comments in hibernation code (Yang Li, Haowen
     Bai).

   - Preserve ACPI-table override during hibernation (Amadeusz
     Sławiński).

   - Improve support for suspend-to-RAM for PSCI OSI mode (Ulf Hansson).

   - Make Intel RAPL power capping driver support the RaptorLake and
     AlderLake N processors (Zhang Rui, Sumeet Pawnikar).

   - Remove redundant store to value after multiply in the RAPL power
     capping driver (Colin Ian King).

   - Add AlderLake processor support to the intel_idle driver (Zhang
     Rui).

   - Fix regression leading to no genpd governor in the PSCI cpuidle
     driver and fix the riscv-sbi cpuidle driver to allow a genpd
     governor to be used (Ulf Hansson).

   - Fix cpufreq governor clean up code to avoid using kfree() directly
     to free kobject-based items (Kevin Hao).

   - Prepare cpufreq for powerpc's asm/prom.h cleanup (Christophe
     Leroy).

   - Make intel_pstate notify frequency invariance code when no_turbo is
     turned on and off (Chen Yu).

   - Add Sapphire Rapids OOB mode support to intel_pstate (Srinivas
     Pandruvada).

   - Make cpufreq avoid unnecessary frequency updates due to mismatch
     between hardware and the frequency table (Viresh Kumar).

   - Make remove_cpu_dev_symlink() clear the real_cpus mask to simplify
     code (Viresh Kumar).

   - Rearrange cpufreq_offline() and cpufreq_remove_dev() to make the
     calling convention for some driver callbacks consistent (Rafael
     Wysocki).

   - Avoid accessing half-initialized cpufreq policies from the show()
     and store() sysfs functions (Schspa Shi).

   - Rearrange cpufreq_offline() to make the calling convention for some
     driver callbacks consistent (Schspa Shi).

   - Update CPPC handling in cpufreq (Pierre Gondois).

   - Extend dev_pm_domain_detach() doc (Krzysztof Kozlowski).

   - Move genpd's time-accounting to ktime_get_mono_fast_ns() (Ulf
     Hansson).

   - Improve the way genpd deals with its governors (Ulf Hansson).

   - Update the turbostat utility to version 2022.04.16 (Len Brown, Dan
     Merillat, Sumeet Pawnikar, Zephaniah E. Loss-Cutler-Hull, Chen Yu)"

* tag 'pm-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (94 commits)
  PM: domains: Trust domain-idle-states from DT to be correct by genpd
  PM: domains: Measure power-on/off latencies in genpd based on a governor
  PM: domains: Allocate governor data dynamically based on a genpd governor
  PM: domains: Clean up some code in pm_genpd_init() and genpd_remove()
  PM: domains: Fix initialization of genpd's next_wakeup
  PM: domains: Fixup QoS latency measurements for IRQ safe devices in genpd
  PM: domains: Measure suspend/resume latencies in genpd based on governor
  PM: domains: Move the next_wakeup variable into the struct gpd_timing_data
  PM: domains: Allocate gpd_timing_data dynamically based on governor
  PM: domains: Skip another warning in irq_safe_dev_in_sleep_domain()
  PM: domains: Rename irq_safe_dev_in_no_sleep_domain() in genpd
  PM: domains: Don't check PM_QOS_FLAG_NO_POWER_OFF in genpd
  PM: domains: Drop redundant code for genpd always-on governor
  PM: domains: Add GENPD_FLAG_RPM_ALWAYS_ON for the always-on governor
  powercap: intel_rapl: remove redundant store to value after multiply
  cpufreq: CPPC: Enable dvfs_possible_from_any_cpu
  cpufreq: CPPC: Enable fast_switch
  ACPI: CPPC: Assume no transition latency if no PCCT
  ACPI: bus: Set CPPC _OSC bits for all and when CPPC_LIB is supported
  ACPI: CPPC: Check _OSC for flexible address space
  ...

kernel/power/Makefile

@@ -1,6 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
+ifeq ($(CONFIG_DYNAMIC_DEBUG), y)
+CFLAGS_swap.o                   := -DDEBUG
+CFLAGS_snapshot.o               := -DDEBUG
+CFLAGS_energy_model.o           := -DDEBUG
+endif
 
 KASAN_SANITIZE_snapshot.o	:= n
 

kernel/power/energy_model.c

@@ -54,28 +54,15 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
-static int em_debug_units_show(struct seq_file *s, void *unused)
+static int em_debug_flags_show(struct seq_file *s, void *unused)
 {
 	struct em_perf_domain *pd = s->private;
-	char *units = (pd->flags & EM_PERF_DOMAIN_MILLIWATTS) ?
-		"milliWatts" : "bogoWatts";
 
-	seq_printf(s, "%s\n", units);
+	seq_printf(s, "%#lx\n", pd->flags);
 
 	return 0;
 }
-DEFINE_SHOW_ATTRIBUTE(em_debug_units);
-
-static int em_debug_skip_inefficiencies_show(struct seq_file *s, void *unused)
-{
-	struct em_perf_domain *pd = s->private;
-	int enabled = (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES) ? 1 : 0;
-
-	seq_printf(s, "%d\n", enabled);
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(em_debug_skip_inefficiencies);
+DEFINE_SHOW_ATTRIBUTE(em_debug_flags);
 
 static void em_debug_create_pd(struct device *dev)
 {
@@ -89,9 +76,8 @@ static void em_debug_create_pd(struct device *dev)
 		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
 				    &em_debug_cpus_fops);
 
-	debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops);
-	debugfs_create_file("skip-inefficiencies", 0444, d, dev->em_pd,
-			    &em_debug_skip_inefficiencies_fops);
+	debugfs_create_file("flags", 0444, d, dev->em_pd,
+			    &em_debug_flags_fops);
 
 	/* Create a sub-directory for each performance state */
 	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
@@ -121,7 +107,8 @@ static void em_debug_remove_pd(struct device *dev) {}
 #endif
 
 static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
-				int nr_states, struct em_data_callback *cb)
+				int nr_states, struct em_data_callback *cb,
+				unsigned long flags)
 {
 	unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX;
 	struct em_perf_state *table;
@@ -139,7 +126,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, dev);
+		ret = cb->active_power(dev, &power, &freq);
 		if (ret) {
 			dev_err(dev, "EM: invalid perf. state: %d\n",
 				ret);
@@ -173,10 +160,22 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
 	for (i = nr_states - 1; i >= 0; i--) {
-		unsigned long power_res = em_scale_power(table[i].power);
+		unsigned long power_res, cost;
+
+		if (flags & EM_PERF_DOMAIN_ARTIFICIAL) {
+			ret = cb->get_cost(dev, table[i].frequency, &cost);
+			if (ret || !cost || cost > EM_MAX_POWER) {
+				dev_err(dev, "EM: invalid cost %lu %d\n",
+					cost, ret);
+				goto free_ps_table;
+			}
+		} else {
+			power_res = em_scale_power(table[i].power);
+			cost = div64_u64(fmax * power_res, table[i].frequency);
+		}
+
+		table[i].cost = cost;
 
-		table[i].cost = div64_u64(fmax * power_res,
-					  table[i].frequency);
 		if (table[i].cost >= prev_cost) {
 			table[i].flags = EM_PERF_STATE_INEFFICIENT;
 			dev_dbg(dev, "EM: OPP:%lu is inefficient\n",
@@ -197,7 +196,8 @@ free_ps_table:
 }
 
 static int em_create_pd(struct device *dev, int nr_states,
-			struct em_data_callback *cb, cpumask_t *cpus)
+			struct em_data_callback *cb, cpumask_t *cpus,
+			unsigned long flags)
 {
 	struct em_perf_domain *pd;
 	struct device *cpu_dev;
@@ -215,7 +215,7 @@ static int em_create_pd(struct device *dev, int nr_states,
 			return -ENOMEM;
 	}
 
-	ret = em_create_perf_table(dev, pd, nr_states, cb);
+	ret = em_create_perf_table(dev, pd, nr_states, cb, flags);
 	if (ret) {
 		kfree(pd);
 		return ret;
@@ -259,6 +259,8 @@ static void em_cpufreq_update_efficiencies(struct device *dev)
 			found++;
 	}
 
+	cpufreq_cpu_put(policy);
+
 	if (!found)
 		return;
 
@@ -332,6 +334,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				bool milliwatts)
 {
 	unsigned long cap, prev_cap = 0;
+	unsigned long flags = 0;
 	int cpu, ret;
 
 	if (!dev || !nr_states || !cb)
@@ -378,12 +381,16 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 		}
 	}
 
-	ret = em_create_pd(dev, nr_states, cb, cpus);
+	if (milliwatts)
+		flags |= EM_PERF_DOMAIN_MILLIWATTS;
+	else if (cb->get_cost)
+		flags |= EM_PERF_DOMAIN_ARTIFICIAL;
+
+	ret = em_create_pd(dev, nr_states, cb, cpus, flags);
 	if (ret)
 		goto unlock;
 
-	if (milliwatts)
-		dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS;
+	dev->em_pd->flags |= flags;
 
 	em_cpufreq_update_efficiencies(dev);
 

kernel/power/main.c

@@ -545,35 +545,6 @@ static int __init pm_debug_messages_setup(char *str)
 }
 __setup("pm_debug_messages", pm_debug_messages_setup);
 
-/**
- * __pm_pr_dbg - Print a suspend debug message to the kernel log.
- * @defer: Whether or not to use printk_deferred() to print the message.
- * @fmt: Message format.
- *
- * The message will be emitted if enabled through the pm_debug_messages
- * sysfs attribute.
- */
-void __pm_pr_dbg(bool defer, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	if (!pm_debug_messages_on)
-		return;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	if (defer)
-		printk_deferred(KERN_DEBUG "PM: %pV", &vaf);
-	else
-		printk(KERN_DEBUG "PM: %pV", &vaf);
-
-	va_end(args);
-}
-
 #else /* !CONFIG_PM_SLEEP_DEBUG */
 static inline void pm_print_times_init(void) {}
 #endif /* CONFIG_PM_SLEEP_DEBUG */

kernel/power/process.c

@@ -6,9 +6,6 @@
  * Originally from swsusp.
  */
 
-
-#undef DEBUG
-
 #include <linux/interrupt.h>
 #include <linux/oom.h>
 #include <linux/suspend.h>

kernel/power/snapshot.c

@@ -326,7 +326,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	return ret;
 }
 
-/**
+/*
  * Data types related to memory bitmaps.
  *
  * Memory bitmap is a structure consisting of many linked lists of
@@ -427,6 +427,10 @@ struct memory_bitmap {
 
 /**
  * alloc_rtree_node - Allocate a new node and add it to the radix tree.
+ * @gfp_mask: GFP mask for the allocation.
+ * @safe_needed: Get pages not used before hibernation (restore only)
+ * @ca: Pointer to a linked list of pages ("a chain") to allocate from
+ * @list: Radix Tree node to add.
  *
  * This function is used to allocate inner nodes as well as the
  * leave nodes of the radix tree. It also adds the node to the
@@ -902,7 +906,7 @@ static bool rtree_next_node(struct memory_bitmap *bm)
 }
 
 /**
- * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap.
+ * memory_bm_next_pfn - Find the next set bit in a memory bitmap.
  * @bm: Memory bitmap.
  *
  * Starting from the last returned position this function searches for the next
@@ -1937,7 +1941,7 @@ static inline int get_highmem_buffer(int safe_needed)
 }
 
 /**
- * alloc_highmem_image_pages - Allocate some highmem pages for the image.
+ * alloc_highmem_pages - Allocate some highmem pages for the image.
  *
  * Try to allocate as many pages as needed, but if the number of free highmem
  * pages is less than that, allocate them all.
@@ -2224,7 +2228,7 @@ static int check_header(struct swsusp_info *info)
 }
 
 /**
- * load header - Check the image header and copy the data from it.
+ * load_header - Check the image header and copy the data from it.
  */
 static int load_header(struct swsusp_info *info)
 {