Merge tag 'pm-6.8-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 new processors (Sierra Forest, Grand Ridge and
  Meteor Lake) to the intel_idle driver, make intel_pstate run on
  Emerald Rapids without HWP support and adjust it to utilize EPP values
  supplied by the platform firmware, fix issues, clean up code and
  improve documentation.

  The most significant fix addresses deadlocks in the core system-wide
  resume code that occur if async_schedule_dev() attempts to run its
  argument function synchronously (for example, due to a memory
  allocation failure). It rearranges the code in question which may
  increase the system resume time in some cases, but this basically is a
  removal of a premature optimization. That optimization will be added
  back later, but properly this time.

  Specifics:

   - 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 balanced
     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)

   - Fix possible deadlocks in the core system-wide PM code that occur
     if device-handling functions cannot be executed asynchronously
     during resume from system-wide suspend (Rafael J. Wysocki)

   - Clean up unnecessary local variable initializations in multiple
     places in the hibernation code (Wang chaodong, Li zeming)

   - Adjust core hibernation code to avoid missing wakeup events that
     occur after saving an image to persistent storage (Chris Feng)

   - Update hibernation code to enforce correct ordering during image
     compression and decompression (Hongchen Zhang)

   - Use kmap_local_page() instead of kmap_atomic() in copy_data_page()
     during hibernation and restore (Chen Haonan)

   - Adjust documentation and code comments to reflect recent tasks
     freezer changes (Kevin Hao)

   - Repair excess function parameter description warning in the
     hibernation image-saving code (Randy Dunlap)

   - Fix _set_required_opps when opp is NULL (Bryan O'Donoghue)

   - Use device_get_match_data() in the OPP code for TI (Rob Herring)

   - Clean up OPP level and other parts and call dev_pm_opp_set_opp()
     recursively for required OPPs (Viresh Kumar)"

* tag 'pm-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (35 commits)
  OPP: Rename 'rate_clk_single'
  OPP: Pass rounded rate to _set_opp()
  OPP: Relocate dev_pm_opp_sync_regulators()
  PM: sleep: Fix possible deadlocks in core system-wide PM code
  OPP: Move dev_pm_opp_icc_bw to internal opp.h
  async: Introduce async_schedule_dev_nocall()
  async: Split async_schedule_node_domain()
  cpuidle: haltpoll: Do not enable interrupts when entering idle
  OPP: Fix _set_required_opps when opp is NULL
  OPP: The level field is always of unsigned int type
  PM: hibernate: Repair excess function parameter description warning
  PM: sleep: Remove obsolete comment from unlock_system_sleep()
  cpufreq: intel_pstate: Add Emerald Rapids support in no-HWP mode
  Documentation: PM: Adjust freezing-of-tasks.rst to the freezer changes
  PM: hibernate: Use kmap_local_page() in copy_data_page()
  intel_idle: add Sierra Forest SoC support
  intel_idle: add Grand Ridge SoC support
  PM / devfreq: Synchronize devfreq_monitor_[start/stop]
  cpufreq: armada-8k: Fix parameter type warning
  PM: hibernate: Enforce ordering during image compression/decompression
  ...

6 files changed, 101 insertions, 69 deletions

diff --git a/kernel/async.c b/kernel/async.c
index b2c4ba5686ee..673bba6bdf3a 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -145,6 +145,39 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
+static async_cookie_t __async_schedule_node_domain(async_func_t func,
+						   void *data, int node,
+						   struct async_domain *domain,
+						   struct async_entry *entry)
+{
+	async_cookie_t newcookie;
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&entry->domain_list);
+	INIT_LIST_HEAD(&entry->global_list);
+	INIT_WORK(&entry->work, async_run_entry_fn);
+	entry->func = func;
+	entry->data = data;
+	entry->domain = domain;
+
+	spin_lock_irqsave(&async_lock, flags);
+
+	/* allocate cookie and queue */
+	newcookie = entry->cookie = next_cookie++;
+
+	list_add_tail(&entry->domain_list, &domain->pending);
+	if (domain->registered)
+		list_add_tail(&entry->global_list, &async_global_pending);
+
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* schedule for execution */
+	queue_work_node(node, system_unbound_wq, &entry->work);
+
+	return newcookie;
+}
+
 /**
  * async_schedule_node_domain - NUMA specific version of async_schedule_domain
  * @func: function to execute asynchronously
@@ -186,29 +219,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
 		func(data, newcookie);
 		return newcookie;
 	}
-	INIT_LIST_HEAD(&entry->domain_list);
-	INIT_LIST_HEAD(&entry->global_list);
-	INIT_WORK(&entry->work, async_run_entry_fn);
-	entry->func = func;
-	entry->data = data;
-	entry->domain = domain;
-
-	spin_lock_irqsave(&async_lock, flags);
-
-	/* allocate cookie and queue */
-	newcookie = entry->cookie = next_cookie++;
-
-	list_add_tail(&entry->domain_list, &domain->pending);
-	if (domain->registered)
-		list_add_tail(&entry->global_list, &async_global_pending);
-
-	atomic_inc(&entry_count);
-	spin_unlock_irqrestore(&async_lock, flags);
-
-	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
 
-	return newcookie;
+	return __async_schedule_node_domain(func, data, node, domain, entry);
 }
 EXPORT_SYMBOL_GPL(async_schedule_node_domain);
 
@@ -232,6 +244,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 EXPORT_SYMBOL_GPL(async_schedule_node);
 
 /**
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
+ *
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
+ */
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
+{
+	struct async_entry *entry;
+
+	entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+	/* Give up if there is no memory or too much work. */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		return false;
+	}
+
+	__async_schedule_node_domain(func, dev, dev_to_node(dev),
+				     &async_dfl_domain, entry);
+	return true;
+}
+
+/**
  * async_synchronize_full - synchronize all asynchronous function calls
  *
  * This function waits until all asynchronous function calls have been done.
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index dee341ae4ace..4b0b7cf2e019 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -642,9 +642,9 @@ int hibernation_platform_enter(void)
  */
 static void power_down(void)
 {
-#ifdef CONFIG_SUSPEND
 	int error;
 
+#ifdef CONFIG_SUSPEND
 	if (hibernation_mode == HIBERNATION_SUSPEND) {
 		error = suspend_devices_and_enter(mem_sleep_current);
 		if (error) {
@@ -667,7 +667,13 @@ static void power_down(void)
 		kernel_restart(NULL);
 		break;
 	case HIBERNATION_PLATFORM:
-		hibernation_platform_enter();
+		error = hibernation_platform_enter();
+		if (error == -EAGAIN || error == -EBUSY) {
+			swsusp_unmark();
+			events_check_enabled = false;
+			pr_info("Wakeup event detected during hibernation, rolling back.\n");
+			return;
+		}
 		fallthrough;
 	case HIBERNATION_SHUTDOWN:
 		if (kernel_can_power_off())
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f6425ae3e8b0..b1ae9b677d03 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -60,22 +60,6 @@ EXPORT_SYMBOL_GPL(lock_system_sleep);
 
 void unlock_system_sleep(unsigned int flags)
 {
-	/*
-	 * Don't use freezer_count() because we don't want the call to
-	 * try_to_freeze() here.
-	 *
-	 * Reason:
-	 * Fundamentally, we just don't need it, because freezing condition
-	 * doesn't come into effect until we release the
-	 * system_transition_mutex lock, since the freezer always works with
-	 * system_transition_mutex held.
-	 *
-	 * More importantly, in the case of hibernation,
-	 * unlock_system_sleep() gets called in snapshot_read() and
-	 * snapshot_write() when the freezing condition is still in effect.
-	 * Which means, if we use try_to_freeze() here, it would make them
-	 * enter the refrigerator, thus causing hibernation to lockup.
-	 */
 	if (!(flags & PF_NOFREEZE))
 		current->flags &= ~PF_NOFREEZE;
 	mutex_unlock(&system_transition_mutex);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 17fd9aaaf084..8499a39c62f4 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,6 +175,8 @@ extern int swsusp_write(unsigned int flags);
 void swsusp_close(void);
 #ifdef CONFIG_SUSPEND
 extern int swsusp_unmark(void);
+#else
+static inline int swsusp_unmark(void) { return 0; }
 #endif
 
 struct __kernel_old_timeval;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 50a15408c3fc..5c96ff067c64 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1119,7 +1119,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 int create_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
-	int error = 0;
+	int error;
 
 	if (forbidden_pages_map && free_pages_map)
 		return 0;
@@ -1487,11 +1487,11 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	s_page = pfn_to_page(src_pfn);
 	d_page = pfn_to_page(dst_pfn);
 	if (PageHighMem(s_page)) {
-		src = kmap_atomic(s_page);
-		dst = kmap_atomic(d_page);
+		src = kmap_local_page(s_page);
+		dst = kmap_local_page(d_page);
 		zeros_only = do_copy_page(dst, src);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
+		kunmap_local(dst);
+		kunmap_local(src);
 	} else {
 		if (PageHighMem(d_page)) {
 			/*
@@ -1499,9 +1499,9 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 			 * data modified by kmap_atomic()
 			 */
 			zeros_only = safe_copy_page(buffer, s_page);
-			dst = kmap_atomic(d_page);
+			dst = kmap_local_page(d_page);
 			copy_page(dst, buffer);
-			kunmap_atomic(dst);
+			kunmap_local(dst);
 		} else {
 			zeros_only = safe_copy_page(page_address(d_page), s_page);
 		}
@@ -2778,7 +2778,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
-	int error = 0;
+	int error;
 
 next:
 	/* Check if we have already loaded the entire image */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a2cb0babb5ec..6053ddddaf65 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -451,7 +451,7 @@ err_close:
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		struct hib_bio_batch *hb)
 {
-	int error = 0;
+	int error;
 	sector_t offset;
 
 	if (!handle->cur)
@@ -606,11 +606,11 @@ static int crc32_threadfn(void *data)
 	unsigned i;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -619,7 +619,7 @@ static int crc32_threadfn(void *data)
 		for (i = 0; i < d->run_threads; i++)
 			*d->crc32 = crc32_le(*d->crc32,
 			                     d->unc[i], *d->unc_len[i]);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -649,12 +649,12 @@ static int lzo_compress_threadfn(void *data)
 	struct cmp_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -663,7 +663,7 @@ static int lzo_compress_threadfn(void *data)
 		d->ret = lzo1x_1_compress(d->unc, d->unc_len,
 		                          d->cmp + LZO_HEADER, &d->cmp_len,
 		                          d->wrk);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -798,7 +798,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 
 			data[thr].unc_len = off;
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -806,12 +806,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			break;
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -850,7 +850,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			}
 		}
 
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 
@@ -1132,12 +1132,12 @@ static int lzo_decompress_threadfn(void *data)
 	struct dec_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -1150,7 +1150,7 @@ static int lzo_decompress_threadfn(void *data)
 			flush_icache_range((unsigned long)d->unc,
 					   (unsigned long)d->unc + d->unc_len);
 
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -1335,7 +1335,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		if (crc->run_threads) {
-			wait_event(crc->done, atomic_read(&crc->stop));
+			wait_event(crc->done, atomic_read_acquire(&crc->stop));
 			atomic_set(&crc->stop, 0);
 			crc->run_threads = 0;
 		}
@@ -1371,7 +1371,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 					pg = 0;
 			}
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -1390,7 +1390,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -1421,7 +1421,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 				ret = snapshot_write_next(snapshot);
 				if (ret <= 0) {
 					crc->run_threads = thr + 1;
-					atomic_set(&crc->ready, 1);
+					atomic_set_release(&crc->ready, 1);
 					wake_up(&crc->go);
 					goto out_finish;
 				}
@@ -1429,13 +1429,13 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 	}
 
 out_finish:
 	if (crc->run_threads) {
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 	stop = ktime_get();
@@ -1566,7 +1566,6 @@ put:
 
 /**
  * swsusp_close - close resume device.
- * @exclusive: Close the resume device which is exclusively opened.
  */
 
 void swsusp_close(void)