Merge tag 'pm-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix two cpufreq issues, one in the core and one in the
  conservative governor, and two issues related to system sleep:

   - Restore the cpufreq core behavior changed inadvertently during the
     6.19 development cycle to call cpufreq_frequency_table_cpuinfo()
     for cpufreq policies getting re-initialized which ensures that
     policy->max and policy->cpuinfo_max_freq will be valid going
     forward (Viresh Kumar)

   - Adjust the cached requested frequency in the conservative cpufreq
     governor on policy limits changes to prevent it from becoming stale
     in some cases (Viresh Kumar)

   - Prevent pm_restore_gfp_mask() from triggering a WARN_ON() in some
     code paths in which it is legitimately called without invoking
     pm_restrict_gfp_mask() previously (Youngjun Park)

   - Update snapshot_write_finalize() to take trailing zero pages into
     account properly which prevents user space restore from failing
     subsequently in some cases (Alberto Garcia)"

* tag 'pm-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: sleep: Drop spurious WARN_ON() from pm_restore_gfp_mask()
  PM: hibernate: Drain trailing zero pages on userspace restore
  cpufreq: conservative: Reset requested_freq on limits change
  cpufreq: Don't skip cpufreq_frequency_table_cpuinfo()

Author: torvalds

drivers/cpufreq/cpufreq.c

@@ -1427,12 +1427,9 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy,
 		 * If there is a problem with its frequency table, take it
 		 * offline and drop it.
 		 */
-		if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING &&
-		    policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) {
-			ret = cpufreq_table_validate_and_sort(policy);
-			if (ret)
-				goto out_offline_policy;
-		}
+		ret = cpufreq_table_validate_and_sort(policy);
+		if (ret)
+			goto out_offline_policy;
 
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);

drivers/cpufreq/cpufreq_conservative.c

@@ -313,6 +313,17 @@ static void cs_start(struct cpufreq_policy *policy)
 	dbs_info->requested_freq = policy->cur;
 }
 
+static void cs_limits(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	/*
+	 * The limits have changed, so may have the current frequency. Reset
+	 * requested_freq to avoid any unintended outcomes due to the mismatch.
+	 */
+	dbs_info->requested_freq = policy->cur;
+}
+
 static struct dbs_governor cs_governor = {
 	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
 	.kobj_type = { .default_groups = cs_groups },
@@ -322,6 +333,7 @@ static struct dbs_governor cs_governor = {
 	.init = cs_init,
 	.exit = cs_exit,
 	.start = cs_start,
+	.limits = cs_limits,
 };
 
 #define CPU_FREQ_GOV_CONSERVATIVE	(cs_governor.gov)

drivers/cpufreq/cpufreq_governor.c

@@ -563,6 +563,7 @@ EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop);
 
 void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 {
+	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs;
 
 	/* Protect gov->gdbs_data against cpufreq_dbs_governor_exit() */
@@ -574,6 +575,8 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 	mutex_lock(&policy_dbs->update_mutex);
 	cpufreq_policy_apply_limits(policy);
 	gov_update_sample_delay(policy_dbs, 0);
+	if (gov->limits)
+		gov->limits(policy);
 	mutex_unlock(&policy_dbs->update_mutex);
 
 out:

drivers/cpufreq/cpufreq_governor.h

@@ -138,6 +138,7 @@ struct dbs_governor {
 	int (*init)(struct dbs_data *dbs_data);
 	void (*exit)(struct dbs_data *dbs_data);
 	void (*start)(struct cpufreq_policy *policy);
+	void (*limits)(struct cpufreq_policy *policy);
 };
 
 static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)

drivers/cpufreq/freq_table.c

@@ -360,6 +360,10 @@ int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy)
 	if (policy_has_boost_freq(policy))
 		policy->boost_supported = true;
 
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING ||
+	    policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_DESCENDING)
+		return 0;
+
 	return set_freq_table_sorted(policy);
 }
 

kernel/power/main.c

@@ -40,7 +40,7 @@ void pm_restore_gfp_mask(void)
 {
 	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 
-	if (WARN_ON(!saved_gfp_count) || --saved_gfp_count)
+	if (!saved_gfp_count || --saved_gfp_count)
 		return;
 
 	gfp_allowed_mask = saved_gfp_mask;

kernel/power/snapshot.c

@@ -2855,6 +2855,17 @@ int snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	int error;
 
+	/*
+	 * Call snapshot_write_next() to drain any trailing zero pages,
+	 * but make sure we're in the data page region first.
+	 * This function can return PAGE_SIZE if the kernel was expecting
+	 * another copy page. Return -ENODATA in that situation.
+	 */
+	if (handle->cur > nr_meta_pages + 1) {
+		error = snapshot_write_next(handle);
+		if (error)
+			return error > 0 ? -ENODATA : error;
+	}
 	copy_last_highmem_page();
 	error = hibernate_restore_protect_page(handle->buffer);
 	/* Do that only if we have loaded the image entirely */