10 files changed, 358 insertions, 237 deletions
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 3ebe77566788..af0029d30dbe 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -11,6 +11,7 @@
 #include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/device.h>
 #include <linux/of.h>
 #include <linux/slab.h>
@@ -28,7 +29,7 @@
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
 static bool scale_freq_invariant;
-DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1;
+DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 0;
 EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
@@ -293,13 +294,15 @@ void topology_normalize_cpu_scale(void)
 
 	capacity_scale = 1;
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
+		capacity = raw_capacity[cpu] *
+			   (per_cpu(capacity_freq_ref, cpu) ?: 1);
 		capacity_scale = max(capacity, capacity_scale);
 	}
 
 	pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale);
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
+		capacity = raw_capacity[cpu] *
+			   (per_cpu(capacity_freq_ref, cpu) ?: 1);
 		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
 			capacity_scale);
 		topology_set_cpu_scale(cpu, capacity);
@@ -506,6 +509,10 @@ core_initcall(free_raw_capacity);
 #endif
 
 #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
+
+/* Used to enable the SMT control */
+static unsigned int max_smt_thread_num = 1;
+
 /*
  * This function returns the logic cpu number of the node.
  * There are basically three kinds of return values:
@@ -565,6 +572,8 @@ static int __init parse_core(struct device_node *core, int package_id,
 		i++;
 	} while (1);
 
+	max_smt_thread_num = max_t(unsigned int, max_smt_thread_num, i);
+
 	cpu = get_cpu_for_node(core);
 	if (cpu >= 0) {
 		if (!leaf) {
@@ -677,6 +686,17 @@ static int __init parse_socket(struct device_node *socket)
 	if (!has_socket)
 		ret = parse_cluster(socket, 0, -1, 0);
 
+	/*
+	 * Reset the max_smt_thread_num to 1 on failure. Since on failure
+	 * we need to notify the framework the SMT is not supported, but
+	 * max_smt_thread_num can be initialized to the SMT thread number
+	 * of the cores which are successfully parsed.
+	 */
+	if (ret)
+		max_smt_thread_num = 1;
+
+	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+
 	return ret;
 }
 
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 741497324d78..a482708566bc 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -569,11 +569,28 @@ void component_master_del(struct device *parent,
 }
 EXPORT_SYMBOL_GPL(component_master_del);
 
+bool component_master_is_bound(struct device *parent,
+	const struct component_master_ops *ops)
+{
+	struct aggregate_device *adev;
+
+	guard(mutex)(&component_mutex);
+	adev = __aggregate_find(parent, ops);
+	if (!adev)
+		return 0;
+
+	return adev->bound;
+}
+EXPORT_SYMBOL_GPL(component_master_is_bound);
+
 static void component_unbind(struct component *component,
 	struct aggregate_device *adev, void *data)
 {
 	WARN_ON(!component->bound);
 
+	dev_dbg(adev->parent, "unbinding %s component %p (ops %ps)\n",
+		dev_name(component->dev), component, component->ops);
+
 	if (component->ops && component->ops->unbind)
 		component->ops->unbind(component->dev, adev->parent, data);
 	component->bound = false;
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 93e7779ef21e..d8a733ea5e1a 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -576,7 +576,10 @@ void *devres_open_group(struct device *dev, void *id, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(devres_open_group);
 
-/* Find devres group with ID @id.  If @id is NULL, look for the latest. */
+/*
+ * Find devres group with ID @id.  If @id is NULL, look for the latest open
+ * group.
+ */
 static struct devres_group *find_group(struct device *dev, void *id)
 {
 	struct devres_node *node;
@@ -687,6 +690,13 @@ int devres_release_group(struct device *dev, void *id)
 		spin_unlock_irqrestore(&dev->devres_lock, flags);
 
 		release_nodes(dev, &todo);
+	} else if (list_empty(&dev->devres_head)) {
+		/*
+		 * dev is probably dying via devres_release_all(): groups
+		 * have already been removed and are on the process of
+		 * being released - don't touch and don't warn.
+		 */
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
 	} else {
 		WARN_ON(1);
 		spin_unlock_irqrestore(&dev->devres_lock, flags);
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index b848764ef018..6dd1a8860f1c 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -63,22 +63,6 @@ __setup("devtmpfs.mount=", mount_param);
 
 static struct vfsmount *mnt;
 
-static struct dentry *public_dev_mount(struct file_system_type *fs_type, int flags,
-		      const char *dev_name, void *data)
-{
-	struct super_block *s = mnt->mnt_sb;
-	int err;
-
-	atomic_inc(&s->s_active);
-	down_write(&s->s_umount);
-	err = reconfigure_single(s, flags, data);
-	if (err < 0) {
-		deactivate_locked_super(s);
-		return ERR_PTR(err);
-	}
-	return dget(s->s_root);
-}
-
 static struct file_system_type internal_fs_type = {
 	.name = "devtmpfs",
 #ifdef CONFIG_TMPFS
@@ -89,9 +73,40 @@ static struct file_system_type internal_fs_type = {
 	.kill_sb = kill_litter_super,
 };
 
+/* Simply take a ref on the existing mount */
+static int devtmpfs_get_tree(struct fs_context *fc)
+{
+	struct super_block *sb = mnt->mnt_sb;
+
+	atomic_inc(&sb->s_active);
+	down_write(&sb->s_umount);
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+/* Ops are filled in during init depending on underlying shmem or ramfs type */
+struct fs_context_operations devtmpfs_context_ops = {};
+
+/* Call the underlying initialization and set to our ops */
+static int devtmpfs_init_fs_context(struct fs_context *fc)
+{
+	int ret;
+#ifdef CONFIG_TMPFS
+	ret = shmem_init_fs_context(fc);
+#else
+	ret = ramfs_init_fs_context(fc);
+#endif
+	if (ret < 0)
+		return ret;
+
+	fc->ops = &devtmpfs_context_ops;
+
+	return 0;
+}
+
 static struct file_system_type dev_fs_type = {
 	.name = "devtmpfs",
-	.mount = public_dev_mount,
+	.init_fs_context = devtmpfs_init_fs_context,
 };
 
 static int devtmpfs_submit_req(struct req *req, const char *tmp)
@@ -160,18 +175,17 @@ static int dev_mkdir(const char *name, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
-	int err;
 
 	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	err = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode);
-	if (!err)
+	dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode);
+	if (!IS_ERR(dentry))
 		/* mark as kernel-created inode */
 		d_inode(dentry)->i_private = &thread;
 	done_path_create(&path, dentry);
-	return err;
+	return PTR_ERR_OR_ZERO(dentry);
 }
 
 static int create_path(const char *nodepath)
@@ -245,15 +259,12 @@ static int dev_rmdir(const char *name)
 	dentry = kern_path_locked(name, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
-	if (d_really_is_positive(dentry)) {
-		if (d_inode(dentry)->i_private == &thread)
-			err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry),
-					dentry);
-		else
-			err = -EPERM;
-	} else {
-		err = -ENOENT;
-	}
+	if (d_inode(dentry)->i_private == &thread)
+		err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry),
+				dentry);
+	else
+		err = -EPERM;
+
 	dput(dentry);
 	inode_unlock(d_inode(parent.dentry));
 	path_put(&parent);
@@ -310,6 +321,8 @@ static int handle_remove(const char *nodename, struct device *dev)
 {
 	struct path parent;
 	struct dentry *dentry;
+	struct kstat stat;
+	struct path p;
 	int deleted = 0;
 	int err;
 
@@ -317,32 +330,28 @@ static int handle_remove(const char *nodename, struct device *dev)
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (d_really_is_positive(dentry)) {
-		struct kstat stat;
-		struct path p = {.mnt = parent.mnt, .dentry = dentry};
-		err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
-				  AT_STATX_SYNC_AS_STAT);
-		if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
-			struct iattr newattrs;
-			/*
-			 * before unlinking this node, reset permissions
-			 * of possible references like hardlinks
-			 */
-			newattrs.ia_uid = GLOBAL_ROOT_UID;
-			newattrs.ia_gid = GLOBAL_ROOT_GID;
-			newattrs.ia_mode = stat.mode & ~0777;
-			newattrs.ia_valid =
-				ATTR_UID|ATTR_GID|ATTR_MODE;
-			inode_lock(d_inode(dentry));
-			notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
-			inode_unlock(d_inode(dentry));
-			err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry),
-					 dentry, NULL);
-			if (!err || err == -ENOENT)
-				deleted = 1;
-		}
-	} else {
-		err = -ENOENT;
+	p.mnt = parent.mnt;
+	p.dentry = dentry;
+	err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
+			  AT_STATX_SYNC_AS_STAT);
+	if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+		struct iattr newattrs;
+		/*
+		 * before unlinking this node, reset permissions
+		 * of possible references like hardlinks
+		 */
+		newattrs.ia_uid = GLOBAL_ROOT_UID;
+		newattrs.ia_gid = GLOBAL_ROOT_GID;
+		newattrs.ia_mode = stat.mode & ~0777;
+		newattrs.ia_valid =
+			ATTR_UID|ATTR_GID|ATTR_MODE;
+		inode_lock(d_inode(dentry));
+		notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
+		inode_unlock(d_inode(dentry));
+		err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry),
+				 dentry, NULL);
+		if (!err || err == -ENOENT)
+			deleted = 1;
 	}
 	dput(dentry);
 	inode_unlock(d_inode(parent.dentry));
@@ -443,6 +452,31 @@ static int __ref devtmpfsd(void *p)
 }
 
 /*
+ * Get the underlying (shmem/ramfs) context ops to build ours
+ */
+static int devtmpfs_configure_context(void)
+{
+	struct fs_context *fc;
+
+	fc = fs_context_for_reconfigure(mnt->mnt_root, mnt->mnt_sb->s_flags,
+					MS_RMT_MASK);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	/* Set up devtmpfs_context_ops based on underlying type */
+	devtmpfs_context_ops.free	      = fc->ops->free;
+	devtmpfs_context_ops.dup	      = fc->ops->dup;
+	devtmpfs_context_ops.parse_param      = fc->ops->parse_param;
+	devtmpfs_context_ops.parse_monolithic = fc->ops->parse_monolithic;
+	devtmpfs_context_ops.get_tree	      = &devtmpfs_get_tree;
+	devtmpfs_context_ops.reconfigure      = fc->ops->reconfigure;
+
+	put_fs_context(fc);
+
+	return 0;
+}
+
+/*
  * Create devtmpfs instance, driver-core devices will add their device
  * nodes here.
  */
@@ -456,6 +490,13 @@ int __init devtmpfs_init(void)
 		pr_err("unable to create devtmpfs %ld\n", PTR_ERR(mnt));
 		return PTR_ERR(mnt);
 	}
+
+	err = devtmpfs_configure_context();
+	if (err) {
+		pr_err("unable to configure devtmpfs type %d\n", err);
+		return err;
+	}
+
 	err = register_filesystem(&dev_fs_type);
 	if (err) {
 		pr_err("unable to register devtmpfs type %d\n", err);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 6f2a33722c52..1813cfd0c4bd 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1451,7 +1451,8 @@ static int platform_dma_configure(struct device *dev)
 		attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
 		ret = acpi_dma_configure(dev, attr);
 	}
-	if (ret || drv->driver_managed_dma)
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (ret || !dev->driver || drv->driver_managed_dma)
 		return ret;
 
 	ret = iommu_device_use_default_domain(dev);
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index e18ba676cdf6..b69bcb37c830 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -259,39 +259,6 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(pm_clk_add_clk);
 
-
-/**
- * of_pm_clk_add_clk - Start using a device clock for power management.
- * @dev: Device whose clock is going to be used for power management.
- * @name: Name of clock that is going to be used for power management.
- *
- * Add the clock described in the 'clocks' device-tree node that matches
- * with the 'name' provided, to the list of clocks used for the power
- * management of @dev. On success, returns 0. Returns a negative error
- * code if the clock is not found or cannot be added.
- */
-int of_pm_clk_add_clk(struct device *dev, const char *name)
-{
-	struct clk *clk;
-	int ret;
-
-	if (!dev || !dev->of_node || !name)
-		return -EINVAL;
-
-	clk = of_clk_get_by_name(dev->of_node, name);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
-
-	ret = pm_clk_add_clk(dev, clk);
-	if (ret) {
-		clk_put(clk);
-		return ret;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(of_pm_clk_add_clk);
-
 /**
  * of_pm_clk_add_clks - Start using device clock(s) for power management.
  * @dev: Device whose clock(s) is going to be used for power management.
@@ -377,46 +344,6 @@ static void __pm_clk_remove(struct pm_clock_entry *ce)
 }
 
 /**
- * pm_clk_remove - Stop using a device clock for power management.
- * @dev: Device whose clock should not be used for PM any more.
- * @con_id: Connection ID of the clock.
- *
- * Remove the clock represented by @con_id from the list of clocks used for
- * the power management of @dev.
- */
-void pm_clk_remove(struct device *dev, const char *con_id)
-{
-	struct pm_subsys_data *psd = dev_to_psd(dev);
-	struct pm_clock_entry *ce;
-
-	if (!psd)
-		return;
-
-	pm_clk_list_lock(psd);
-
-	list_for_each_entry(ce, &psd->clock_list, node) {
-		if (!con_id && !ce->con_id)
-			goto remove;
-		else if (!con_id || !ce->con_id)
-			continue;
-		else if (!strcmp(con_id, ce->con_id))
-			goto remove;
-	}
-
-	pm_clk_list_unlock(psd);
-	return;
-
- remove:
-	list_del(&ce->node);
-	if (ce->enabled_when_prepared)
-		psd->clock_op_might_sleep--;
-	pm_clk_list_unlock(psd);
-
-	__pm_clk_remove(ce);
-}
-EXPORT_SYMBOL_GPL(pm_clk_remove);
-
-/**
  * pm_clk_remove_clk - Stop using a device clock for power management.
  * @dev: Device whose clock should not be used for PM any more.
  * @clk: Clock pointer
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
index 4fa525668cb7..6502720bb564 100644
--- a/drivers/base/power/generic_ops.c
+++ b/drivers/base/power/generic_ops.c
@@ -115,18 +115,6 @@ int pm_generic_freeze_noirq(struct device *dev)
 EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq);
 
 /**
- * pm_generic_freeze_late - Generic freeze_late callback for subsystems.
- * @dev: Device to freeze.
- */
-int pm_generic_freeze_late(struct device *dev)
-{
-	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-
-	return pm && pm->freeze_late ? pm->freeze_late(dev) : 0;
-}
-EXPORT_SYMBOL_GPL(pm_generic_freeze_late);
-
-/**
  * pm_generic_freeze - Generic freeze callback for subsystems.
  * @dev: Device to freeze.
  */
@@ -187,18 +175,6 @@ int pm_generic_thaw_noirq(struct device *dev)
 EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq);
 
 /**
- * pm_generic_thaw_early - Generic thaw_early callback for subsystems.
- * @dev: Device to thaw.
- */
-int pm_generic_thaw_early(struct device *dev)
-{
-	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-
-	return pm && pm->thaw_early ? pm->thaw_early(dev) : 0;
-}
-EXPORT_SYMBOL_GPL(pm_generic_thaw_early);
-
-/**
  * pm_generic_thaw - Generic thaw callback for subsystems.
  * @dev: Device to thaw.
  */
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 40e1d8d8a589..ac2a197c1234 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -249,7 +249,7 @@ static int dpm_wait_fn(struct device *dev, void *async_ptr)
 
 static void dpm_wait_for_children(struct device *dev, bool async)
 {
-       device_for_each_child(dev, &async, dpm_wait_fn);
+	device_for_each_child(dev, &async, dpm_wait_fn);
 }
 
 static void dpm_wait_for_suppliers(struct device *dev, bool async)
@@ -599,27 +599,34 @@ static bool is_async(struct device *dev)
 
 static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
-	reinit_completion(&dev->power.completion);
+	if (!is_async(dev))
+		return false;
 
-	if (is_async(dev)) {
-		dev->power.async_in_progress = true;
+	dev->power.work_in_progress = true;
 
-		get_device(dev);
+	get_device(dev);
+
+	if (async_schedule_dev_nocall(func, dev))
+		return true;
 
-		if (async_schedule_dev_nocall(func, dev))
-			return true;
+	put_device(dev);
 
-		put_device(dev);
-	}
 	/*
-	 * Because async_schedule_dev_nocall() above has returned false or it
-	 * has not been called at all, func() is not running and it is safe to
-	 * update the async_in_progress flag without extra synchronization.
+	 * async_schedule_dev_nocall() above has returned false, so func() is
+	 * not running and it is safe to update power.work_in_progress without
+	 * extra synchronization.
 	 */
-	dev->power.async_in_progress = false;
+	dev->power.work_in_progress = false;
+
 	return false;
 }
 
+static void dpm_clear_async_state(struct device *dev)
+{
+	reinit_completion(&dev->power.completion);
+	dev->power.work_in_progress = false;
+}
+
 /**
  * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
@@ -656,15 +663,13 @@ static void device_resume_noirq(struct device *dev, pm_message_t state, bool asy
 	 * so change its status accordingly.
 	 *
 	 * Otherwise, the device is going to be resumed, so set its PM-runtime
-	 * status to "active" unless its power.set_active flag is clear, in
+	 * status to "active" unless its power.smart_suspend flag is clear, in
 	 * which case it is not necessary to update its PM-runtime status.
 	 */
-	if (skip_resume) {
+	if (skip_resume)
 		pm_runtime_set_suspended(dev);
-	} else if (dev->power.set_active) {
+	else if (dev_pm_smart_suspend(dev))
 		pm_runtime_set_active(dev);
-		dev->power.set_active = false;
-	}
 
 	if (dev->pm_domain) {
 		info = "noirq power domain ";
@@ -731,14 +736,16 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	 * Trigger the resume of "async" devices upfront so they don't have to
 	 * wait for the "non-async" ones they don't depend on.
 	 */
-	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry) {
+		dpm_clear_async_state(dev);
 		dpm_async_fn(dev, async_resume_noirq);
+	}
 
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
 		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 
-		if (!dev->power.async_in_progress) {
+		if (!dev->power.work_in_progress) {
 			get_device(dev);
 
 			mutex_unlock(&dpm_list_mtx);
@@ -871,14 +878,16 @@ void dpm_resume_early(pm_message_t state)
 	 * Trigger the resume of "async" devices upfront so they don't have to
 	 * wait for the "non-async" ones they don't depend on.
 	 */
-	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry) {
+		dpm_clear_async_state(dev);
 		dpm_async_fn(dev, async_resume_early);
+	}
 
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
 		list_move_tail(&dev->power.entry, &dpm_suspended_list);
 
-		if (!dev->power.async_in_progress) {
+		if (!dev->power.work_in_progress) {
 			get_device(dev);
 
 			mutex_unlock(&dpm_list_mtx);
@@ -929,7 +938,17 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.syscore)
 		goto Complete;
 
+	if (!dev->power.is_suspended)
+		goto Complete;
+
 	if (dev->power.direct_complete) {
+		/*
+		 * Allow new children to be added under the device after this
+		 * point if it has no PM callbacks.
+		 */
+		if (dev->power.no_pm_callbacks)
+			dev->power.is_prepared = false;
+
 		/* Match the pm_runtime_disable() in device_suspend(). */
 		pm_runtime_enable(dev);
 		goto Complete;
@@ -947,9 +966,6 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	 */
 	dev->power.is_prepared = false;
 
-	if (!dev->power.is_suspended)
-		goto Unlock;
-
 	if (dev->pm_domain) {
 		info = "power domain ";
 		callback = pm_op(&dev->pm_domain->ops, state);
@@ -989,7 +1005,6 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	error = dpm_run_callback(callback, dev, state, info);
 	dev->power.is_suspended = false;
 
- Unlock:
 	device_unlock(dev);
 	dpm_watchdog_clear(&wd);
 
@@ -1037,14 +1052,16 @@ void dpm_resume(pm_message_t state)
 	 * Trigger the resume of "async" devices upfront so they don't have to
 	 * wait for the "non-async" ones they don't depend on.
 	 */
-	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
+		dpm_clear_async_state(dev);
 		dpm_async_fn(dev, async_resume);
+	}
 
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
 		list_move_tail(&dev->power.entry, &dpm_prepared_list);
 
-		if (!dev->power.async_in_progress) {
+		if (!dev->power.work_in_progress) {
 			get_device(dev);
 
 			mutex_unlock(&dpm_list_mtx);
@@ -1109,6 +1126,8 @@ static void device_complete(struct device *dev, pm_message_t state)
 	device_unlock(dev);
 
 out:
+	/* If enabling runtime PM for the device is blocked, unblock it. */
+	pm_runtime_unblock(dev);
 	pm_runtime_put(dev);
 }
 
@@ -1270,24 +1289,17 @@ Skip:
 	dev->power.is_noirq_suspended = true;
 
 	/*
-	 * Skipping the resume of devices that were in use right before the
-	 * system suspend (as indicated by their PM-runtime usage counters)
-	 * would be suboptimal.  Also resume them if doing that is not allowed
-	 * to be skipped.
+	 * Devices must be resumed unless they are explicitly allowed to be left
+	 * in suspend, but even in that case skipping the resume of devices that
+	 * were in use right before the system suspend (as indicated by their
+	 * runtime PM usage counters and child counters) would be suboptimal.
 	 */
-	if (atomic_read(&dev->power.usage_count) > 1 ||
-	    !(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
-	      dev->power.may_skip_resume))
+	if (!(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
+	      dev->power.may_skip_resume) || !pm_runtime_need_not_resume(dev))
 		dev->power.must_resume = true;
 
-	if (dev->power.must_resume) {
-		if (dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) {
-			dev->power.set_active = true;
-			if (dev->parent && !dev->parent->power.ignore_children)
-				dev->parent->power.set_active = true;
-		}
+	if (dev->power.must_resume)
 		dpm_superior_set_must_resume(dev);
-	}
 
 Complete:
 	complete_all(&dev->power.completion);
@@ -1320,6 +1332,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state)
 
 		list_move(&dev->power.entry, &dpm_noirq_list);
 
+		dpm_clear_async_state(dev);
 		if (dpm_async_fn(dev, async_suspend_noirq))
 			continue;
 
@@ -1404,6 +1417,10 @@ static int device_suspend_late(struct device *dev, pm_message_t state, bool asyn
 	TRACE_DEVICE(dev);
 	TRACE_SUSPEND(0);
 
+	/*
+	 * Disable runtime PM for the device without checking if there is a
+	 * pending resume request for it.
+	 */
 	__pm_runtime_disable(dev, false);
 
 	dpm_wait_for_subordinate(dev, async);
@@ -1493,6 +1510,7 @@ int dpm_suspend_late(pm_message_t state)
 
 		list_move(&dev->power.entry, &dpm_late_early_list);
 
+		dpm_clear_async_state(dev);
 		if (dpm_async_fn(dev, async_suspend_late))
 			continue;
 
@@ -1650,6 +1668,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 			pm_runtime_disable(dev);
 			if (pm_runtime_status_suspended(dev)) {
 				pm_dev_dbg(dev, state, "direct-complete ");
+				dev->power.is_suspended = true;
 				goto Complete;
 			}
 
@@ -1760,6 +1779,7 @@ int dpm_suspend(pm_message_t state)
 
 		list_move(&dev->power.entry, &dpm_suspended_list);
 
+		dpm_clear_async_state(dev);
 		if (dpm_async_fn(dev, async_suspend))
 			continue;
 
@@ -1791,6 +1811,46 @@ int dpm_suspend(pm_message_t state)
 	return error;
 }
 
+static bool device_prepare_smart_suspend(struct device *dev)
+{
+	struct device_link *link;
+	bool ret = true;
+	int idx;
+
+	/*
+	 * The "smart suspend" feature is enabled for devices whose drivers ask
+	 * for it and for devices without PM callbacks.
+	 *
+	 * However, if "smart suspend" is not enabled for the device's parent
+	 * or any of its suppliers that take runtime PM into account, it cannot
+	 * be enabled for the device either.
+	 */
+	if (!dev->power.no_pm_callbacks &&
+	    !dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+		return false;
+
+	if (dev->parent && !dev_pm_smart_suspend(dev->parent) &&
+	    !dev->parent->power.ignore_children && !pm_runtime_blocked(dev->parent))
+		return false;
+
+	idx = device_links_read_lock();
+
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
+		if (!(link->flags & DL_FLAG_PM_RUNTIME))
+			continue;
+
+		if (!dev_pm_smart_suspend(link->supplier) &&
+		    !pm_runtime_blocked(link->supplier)) {
+			ret = false;
+			break;
+		}
+	}
+
+	device_links_read_unlock(idx);
+
+	return ret;
+}
+
 /**
  * device_prepare - Prepare a device for system power transition.
  * @dev: Device to handle.
@@ -1802,6 +1862,7 @@ int dpm_suspend(pm_message_t state)
 static int device_prepare(struct device *dev, pm_message_t state)
 {
 	int (*callback)(struct device *) = NULL;
+	bool smart_suspend;
 	int ret = 0;
 
 	/*
@@ -1811,6 +1872,13 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	 * it again during the complete phase.
 	 */
 	pm_runtime_get_noresume(dev);
+	/*
+	 * If runtime PM is disabled for the device at this point and it has
+	 * never been enabled so far, it should not be enabled until this system
+	 * suspend-resume cycle is complete, so prepare to trigger a warning on
+	 * subsequent attempts to enable it.
+	 */
+	smart_suspend = !pm_runtime_block_if_disabled(dev);
 
 	if (dev->power.syscore)
 		return 0;
@@ -1845,6 +1913,13 @@ unlock:
 		pm_runtime_put(dev);
 		return ret;
 	}
+	/* Do not enable "smart suspend" for devices with disabled runtime PM. */
+	if (smart_suspend)
+		smart_suspend = device_prepare_smart_suspend(dev);
+
+	spin_lock_irq(&dev->power.lock);
+
+	dev->power.smart_suspend = smart_suspend;
 	/*
 	 * A positive return value from ->prepare() means "this device appears
 	 * to be runtime-suspended and its state is fine, so if it really is
@@ -1852,11 +1927,12 @@ unlock:
 	 * will do the same thing with all of its descendants".  This only
 	 * applies to suspend transitions, however.
 	 */
-	spin_lock_irq(&dev->power.lock);
 	dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
 		(ret > 0 || dev->power.no_pm_callbacks) &&
 		!dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE);
+
 	spin_unlock_irq(&dev->power.lock);
+
 	return 0;
 }
 
@@ -2020,6 +2096,5 @@ void device_pm_check_callbacks(struct device *dev)
 
 bool dev_pm_skip_suspend(struct device *dev)
 {
-	return dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) &&
-		pm_runtime_status_suspended(dev);
+	return dev_pm_smart_suspend(dev) && pm_runtime_status_suspended(dev);
 }
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 2ee45841486b..0e127b0329c0 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -448,8 +448,19 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 		retval = __rpm_callback(cb, dev);
 	}
 
-	dev->power.runtime_error = retval;
-	return retval != -EACCES ? retval : -EIO;
+	/*
+	 * Since -EACCES means that runtime PM is disabled for the given device,
+	 * it should not be returned by runtime PM callbacks.  If it is returned
+	 * nevertheless, assume it to be a transient error and convert it to
+	 * -EAGAIN.
+	 */
+	if (retval == -EACCES)
+		retval = -EAGAIN;
+
+	if (retval != -EAGAIN && retval != -EBUSY)
+		dev->power.runtime_error = retval;
+
+	return retval;
 }
 
 /**
@@ -725,21 +736,18 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
 
-	if (retval == -EAGAIN || retval == -EBUSY) {
-		dev->power.runtime_error = 0;
+	/*
+	 * On transient errors, if the callback routine failed an autosuspend,
+	 * and if the last_busy time has been updated so that there is a new
+	 * autosuspend expiration time, automatically reschedule another
+	 * autosuspend.
+	 */
+	if (!dev->power.runtime_error && (rpmflags & RPM_AUTO) &&
+	    pm_runtime_autosuspend_expiration(dev) != 0)
+		goto repeat;
+
+	pm_runtime_cancel_pending(dev);
 
-		/*
-		 * If the callback routine failed an autosuspend, and
-		 * if the last_busy time has been updated so that there
-		 * is a new autosuspend expiration time, automatically
-		 * reschedule another autosuspend.
-		 */
-		if ((rpmflags & RPM_AUTO) &&
-		    pm_runtime_autosuspend_expiration(dev) != 0)
-			goto repeat;
-	} else {
-		pm_runtime_cancel_pending(dev);
-	}
 	goto out;
 }
 
@@ -1460,20 +1468,31 @@ int pm_runtime_barrier(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_barrier);
 
-/**
- * __pm_runtime_disable - Disable runtime PM of a device.
- * @dev: Device to handle.
- * @check_resume: If set, check if there's a resume request for the device.
- *
- * Increment power.disable_depth for the device and if it was zero previously,
- * cancel all pending runtime PM requests for the device and wait for all
- * operations in progress to complete.  The device can be either active or
- * suspended after its runtime PM has been disabled.
- *
- * If @check_resume is set and there's a resume request pending when
- * __pm_runtime_disable() is called and power.disable_depth is zero, the
- * function will wake up the device before disabling its runtime PM.
- */
+bool pm_runtime_block_if_disabled(struct device *dev)
+{
+	bool ret;
+
+	spin_lock_irq(&dev->power.lock);
+
+	ret = !pm_runtime_enabled(dev);
+	if (ret && dev->power.last_status == RPM_INVALID)
+		dev->power.last_status = RPM_BLOCKED;
+
+	spin_unlock_irq(&dev->power.lock);
+
+	return ret;
+}
+
+void pm_runtime_unblock(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.last_status == RPM_BLOCKED)
+		dev->power.last_status = RPM_INVALID;
+
+	spin_unlock_irq(&dev->power.lock);
+}
+
 void __pm_runtime_disable(struct device *dev, bool check_resume)
 {
 	spin_lock_irq(&dev->power.lock);
@@ -1532,6 +1551,10 @@ void pm_runtime_enable(struct device *dev)
 	if (--dev->power.disable_depth > 0)
 		goto out;
 
+	if (dev->power.last_status == RPM_BLOCKED) {
+		dev_warn(dev, "Attempt to enable runtime PM when it is blocked\n");
+		dump_stack();
+	}
 	dev->power.last_status = RPM_INVALID;
 	dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
 
@@ -1764,8 +1787,8 @@ void pm_runtime_init(struct device *dev)
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
-	hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	dev->power.suspend_timer.function = pm_suspend_timer_fn;
+	hrtimer_setup(&dev->power.suspend_timer, pm_suspend_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS);
 
 	init_waitqueue_head(&dev->power.wait_queue);
 }
@@ -1874,7 +1897,7 @@ void pm_runtime_drop_link(struct device_link *link)
 	pm_request_idle(link->supplier);
 }
 
-static bool pm_runtime_need_not_resume(struct device *dev)
+bool pm_runtime_need_not_resume(struct device *dev)
 {
 	return atomic_read(&dev->power.usage_count) <= 1 &&
 		(atomic_read(&dev->power.child_count) == 0 ||
@@ -1959,7 +1982,7 @@ int pm_runtime_force_resume(struct device *dev)
 	int (*callback)(struct device *);
 	int ret = 0;
 
-	if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume)
+	if (!dev->power.needs_force_resume)
 		goto out;
 
 	/*
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index b1f8508c3966..f7fcf2de1301 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -21,6 +21,37 @@ static const struct regcache_ops *cache_types[] = {
 	&regcache_flat_ops,
 };
 
+static int regcache_defaults_cmp(const void *a, const void *b)
+{
+	const struct reg_default *x = a;
+	const struct reg_default *y = b;
+
+	if (x->reg > y->reg)
+		return 1;
+	else if (x->reg < y->reg)
+		return -1;
+	else
+		return 0;
+}
+
+static void regcache_defaults_swap(void *a, void *b, int size)
+{
+	struct reg_default *x = a;
+	struct reg_default *y = b;
+	struct reg_default tmp;
+
+	tmp = *x;
+	*x = *y;
+	*y = tmp;
+}
+
+void regcache_sort_defaults(struct reg_default *defaults, unsigned int ndefaults)
+{
+	sort(defaults, ndefaults, sizeof(*defaults),
+	     regcache_defaults_cmp, regcache_defaults_swap);
+}
+EXPORT_SYMBOL_GPL(regcache_sort_defaults);
+
 static int regcache_hw_init(struct regmap *map)
 {
 	int i, j;