Power management fixes for 6.16-rc5

- Prevent the Intel RAPL power capping driver from allowing PL1 to be
    exceeded by mistake on systems when PL1 cannot be disabled (Zhang
    Rui).
 
  - Fix a typo in the ABI documentation (Sumanth Gavini).
 
  - Allow swap to be used a bit longer during system suspend and
    hibernation to avoid suspend failures under memory pressure (Mario
    Limonciello).
 -----BEGIN PGP SIGNATURE-----
 
 iQFGBAABCAAwFiEEcM8Aw/RY0dgsiRUR7l+9nS/U47UFAmhoNlcSHHJqd0Byand5
 c29ja2kubmV0AAoJEO5fvZ0v1OO1ihIH/0cmL1jGT/syrPc9cKi3aWrzA0vn1TAp
 28QCPmP0u35DoegSl2PclwcT66CKC1qPCqNTAgLZUBoXw4SILCxqorPdBJoj/jNi
 i4nhXwE7xRfAHuPpkCQRYcU/uVkSczF1SKtCz0Tvy8oacqEcHJ5wA3iqkr6CNCTe
 FZP+dkZB5citAaH09ysNQAQsewsrJEsgVQFwClgE0qzQrd1sRwVAuq8gtNlS4LFq
 5vtRxpSwCAIFUCFKwxfWiRZBQNFoEJMcPXdPVo7L1AoV8L57Y8dwVPim0+mOiK4i
 LWoP165J9/U//r28ujVlxq96U7pv1F0fJ9mCPxTeyAU5YYsymZv5Et4=
 =bk6K
 -----END PGP SIGNATURE-----

Merge tag 'pm-6.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These address system suspend failures under memory pressure in some
  configurations, fix up RAPL handling on platforms where PL1 cannot be
  disabled, and fix a documentation typo:

   - Prevent the Intel RAPL power capping driver from allowing PL1 to be
     exceeded by mistake on systems when PL1 cannot be disabled (Zhang
     Rui)

   - Fix a typo in the ABI documentation (Sumanth Gavini)

   - Allow swap to be used a bit longer during system suspend and
     hibernation to avoid suspend failures under memory pressure (Mario
     Limonciello)"

* tag 'pm-6.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: sleep: docs: Replace "diasble" with "disable"
  powercap: intel_rapl: Do not change CLAMPING bit if ENABLE bit cannot be changed
  PM: Restrict swap use to later in the suspend sequence

Documentation/ABI/testing/sysfs-devices-power

@@ -56,7 +56,7 @@ Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../async attribute allows the user space to
-		enable or diasble the device's suspend and resume callbacks to
+		enable or disable the device's suspend and resume callbacks to
 		be executed asynchronously (ie. in separate threads, in parallel
 		with the main suspend/resume thread) during system-wide power
 		transitions (eg. suspend to RAM, hibernation).

drivers/base/power/main.c

@@ -1236,6 +1236,7 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
+	pm_restore_gfp_mask();
 	dpm_resume(state);
 	dpm_complete(state);
 }
@@ -2176,8 +2177,10 @@ int dpm_suspend_start(pm_message_t state)
 	error = dpm_prepare(state);
 	if (error)
 		dpm_save_failed_step(SUSPEND_PREPARE);
-	else
+	else {
+		pm_restrict_gfp_mask();
 		error = dpm_suspend(state);
+	}
 
 	dpm_show_time(starttime, state, error, "start");
 	return error;

drivers/powercap/intel_rapl_common.c

@@ -341,12 +341,28 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
 {
 	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
 	struct rapl_defaults *defaults = get_defaults(rd->rp);
+	u64 val;
 	int ret;
 
 	cpus_read_lock();
 	ret = rapl_write_pl_data(rd, POWER_LIMIT1, PL_ENABLE, mode);
-	if (!ret && defaults->set_floor_freq)
+	if (ret)
+		goto end;
+
+	ret = rapl_read_pl_data(rd, POWER_LIMIT1, PL_ENABLE, false, &val);
+	if (ret)
+		goto end;
+
+	if (mode != val) {
+		pr_debug("%s cannot be %s\n", power_zone->name,
+			 str_enabled_disabled(mode));
+		goto end;
+	}
+
+	if (defaults->set_floor_freq)
 		defaults->set_floor_freq(rd, mode);
+
+end:
 	cpus_read_unlock();
 
 	return ret;

include/linux/suspend.h

@@ -446,6 +446,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern void ksys_sync_helper(void);
 extern void pm_report_hw_sleep_time(u64 t);
 extern void pm_report_max_hw_sleep(u64 t);
+void pm_restrict_gfp_mask(void);
+void pm_restore_gfp_mask(void);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -492,6 +494,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 static inline void pm_report_hw_sleep_time(u64 t) {};
 static inline void pm_report_max_hw_sleep(u64 t) {};
 
+static inline void pm_restrict_gfp_mask(void) {}
+static inline void pm_restore_gfp_mask(void) {}
+
 static inline void ksys_sync_helper(void) {}
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)

kernel/kexec_core.c

@@ -1136,6 +1136,7 @@ int kernel_kexec(void)
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
+		pm_restore_gfp_mask();
 		console_resume_all();
 		thaw_processes();
  Restore_console:

kernel/power/hibernate.c

@@ -423,7 +423,6 @@ int hibernation_snapshot(int platform_mode)
 	}
 
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
 
@@ -559,7 +558,6 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
@@ -571,7 +569,6 @@ int hibernation_restore(int platform_mode)
 		BUG_ON(!error);
 	}
 	dpm_resume_end(PMSG_RECOVER);
-	pm_restore_gfp_mask();
 	console_resume_all();
 	pm_restore_console();
 	return error;

kernel/power/power.h

@@ -239,11 +239,6 @@ static inline void suspend_test_finish(const char *label) {}
 /* kernel/power/main.c */
 extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
-void pm_restrict_gfp_mask(void);
-void pm_restore_gfp_mask(void);
-#else
-static inline void pm_restrict_gfp_mask(void) {}
-static inline void pm_restore_gfp_mask(void) {}
 #endif
 
 #ifdef CONFIG_HIGHMEM

kernel/power/suspend.c

@@ -540,6 +540,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	return error;
 
  Recover_platform:
+	pm_restore_gfp_mask();
 	platform_recover(state);
 	goto Resume_devices;
 }
@@ -606,9 +607,7 @@ static int enter_state(suspend_state_t state)
 
 	trace_suspend_resume(TPS("suspend_enter"), state, false);
 	pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
-	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
-	pm_restore_gfp_mask();
 
  Finish:
 	events_check_enabled = false;