5 files changed, 89 insertions, 132 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2db62d98e395..7bd9cd366d41 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/fwnode.h>
@@ -3179,6 +3180,8 @@ void device_shutdown(void)
 	wait_for_device_probe();
 	device_block_probing();
 
+	cpufreq_suspend();
+
 	spin_lock(&devices_kset->list_lock);
 	/*
 	 * Walk the devices list backward, shutting down each in turn.
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 20c39d1bcef8..55907c27075b 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -100,26 +100,9 @@ unsigned long __weak memory_block_size_bytes(void)
 }
 EXPORT_SYMBOL_GPL(memory_block_size_bytes);
 
-static unsigned long get_memory_block_size(void)
-{
-	unsigned long block_sz;
-
-	block_sz = memory_block_size_bytes();
-
-	/* Validate blk_sz is a power of 2 and not less than section size */
-	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
-		WARN_ON(1);
-		block_sz = MIN_MEMORY_BLOCK_SIZE;
-	}
-
-	return block_sz;
-}
-
 /*
- * use this as the physical section index that this memsection
- * uses.
+ * Show the first physical section index (number) of this memory block.
  */
-
 static ssize_t phys_index_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -131,7 +114,10 @@ static ssize_t phys_index_show(struct device *dev,
 }
 
 /*
- * Show whether the section of memory is likely to be hot-removable
+ * Show whether the memory block is likely to be offlineable (or is already
+ * offline). Once offline, the memory block could be removed. The return
+ * value does, however, not indicate that there is a way to remove the
+ * memory block.
  */
 static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
@@ -455,12 +441,12 @@ static DEVICE_ATTR_RO(phys_device);
 static DEVICE_ATTR_RO(removable);
 
 /*
- * Block size attribute stuff
+ * Show the memory block size (shared by all memory blocks).
  */
 static ssize_t block_size_bytes_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lx\n", get_memory_block_size());
+	return sprintf(buf, "%lx\n", memory_block_size_bytes());
 }
 
 static DEVICE_ATTR_RO(block_size_bytes);
@@ -554,6 +540,9 @@ static ssize_t soft_offline_page_store(struct device *dev,
 	pfn >>= PAGE_SHIFT;
 	if (!pfn_valid(pfn))
 		return -ENXIO;
+	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
+	if (!pfn_to_online_page(pfn))
+		return -EIO;
 	ret = soft_offline_page(pfn_to_page(pfn), 0);
 	return ret == 0 ? count : ret;
 }
@@ -670,10 +659,10 @@ static int init_memory_block(struct memory_block **memory,
 		return -ENOMEM;
 
 	mem->start_section_nr = block_id * sections_per_block;
-	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
+	mem->nid = NUMA_NO_NODE;
 
 	ret = register_memory(mem);
 
@@ -810,19 +799,22 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 /*
  * Initialize the sysfs support for memory devices...
  */
-int __init memory_dev_init(void)
+void __init memory_dev_init(void)
 {
 	int ret;
 	int err;
 	unsigned long block_sz, nr;
 
+	/* Validate the configured memory block size */
+	block_sz = memory_block_size_bytes();
+	if (!is_power_of_2(block_sz) || block_sz < MIN_MEMORY_BLOCK_SIZE)
+		panic("Memory block size not suitable: 0x%lx\n", block_sz);
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
 		goto out;
 
-	block_sz = get_memory_block_size();
-	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
-
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
@@ -838,8 +830,7 @@ int __init memory_dev_init(void)
 
 out:
 	if (ret)
-		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
-	return ret;
+		panic("%s() failed: %d\n", __func__, ret);
 }
 
 /**
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 75b7e6f6535b..296546ffed6c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -427,6 +427,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d AnonHugePages:  %8lu kB\n"
 		       "Node %d ShmemHugePages: %8lu kB\n"
 		       "Node %d ShmemPmdMapped: %8lu kB\n"
+		       "Node %d FileHugePages: %8lu kB\n"
+		       "Node %d FilePmdMapped: %8lu kB\n"
 #endif
 			,
 		       nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
@@ -452,6 +454,10 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_THPS) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
 				       HPAGE_PMD_NR)
 #endif
 		       );
@@ -756,15 +762,13 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 static int register_mem_sect_under_node(struct memory_block *mem_blk,
 					 void *arg)
 {
+	unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
+	unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
 	int ret, nid = *(int *)arg;
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+	unsigned long pfn;
 
-	mem_blk->nid = nid;
-
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
-	sect_end_pfn += PAGES_PER_SECTION - 1;
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
 		int page_nid;
 
 		/*
@@ -789,6 +793,13 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 			if (page_nid != nid)
 				continue;
 		}
+
+		/*
+		 * If this memory block spans multiple nodes, we only indicate
+		 * the last processed node.
+		 */
+		mem_blk->nid = nid;
+
 		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
@@ -804,32 +815,18 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 }
 
 /*
- * Unregister memory block device under all nodes that it spans.
- * Has to be called with mem_sysfs_mutex held (due to unlinked_nodes).
+ * Unregister a memory block device under the node it spans. Memory blocks
+ * with multiple nodes cannot be offlined and therefore also never be removed.
  */
 void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 {
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
-	static nodemask_t unlinked_nodes;
-
-	nodes_clear(unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
-		int nid;
+	if (mem_blk->nid == NUMA_NO_NODE)
+		return;
 
-		nid = get_nid_for_pfn(pfn);
-		if (nid < 0)
-			continue;
-		if (!node_online(nid))
-			continue;
-		if (node_test_and_set(nid, unlinked_nodes))
-			continue;
-		sysfs_remove_link(&node_devices[nid]->dev.kobj,
-			 kobject_name(&mem_blk->dev.kobj));
-		sysfs_remove_link(&mem_blk->dev.kobj,
-			 kobject_name(&node_devices[nid]->dev.kobj));
-	}
+	sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
+			  kobject_name(&mem_blk->dev.kobj));
+	sysfs_remove_link(&mem_blk->dev.kobj,
+			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
 int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b6c6c7d97d5b..b230beb6ccb4 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -241,12 +241,8 @@ struct resource *platform_get_resource_byname(struct platform_device *dev,
 }
 EXPORT_SYMBOL_GPL(platform_get_resource_byname);
 
-/**
- * platform_get_irq_byname - get an IRQ for a device by name
- * @dev: platform device
- * @name: IRQ name
- */
-int platform_get_irq_byname(struct platform_device *dev, const char *name)
+static int __platform_get_irq_byname(struct platform_device *dev,
+				     const char *name)
 {
 	struct resource *r;
 
@@ -262,12 +258,48 @@ int platform_get_irq_byname(struct platform_device *dev, const char *name)
 	if (r)
 		return r->start;
 
-	dev_err(&dev->dev, "IRQ %s not found\n", name);
 	return -ENXIO;
 }
+
+/**
+ * platform_get_irq_byname - get an IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an IRQ like platform_get_irq(), but then by name rather then by index.
+ *
+ * Return: IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname(struct platform_device *dev, const char *name)
+{
+	int ret;
+
+	ret = __platform_get_irq_byname(dev, name);
+	if (ret < 0 && ret != -EPROBE_DEFER)
+		dev_err(&dev->dev, "IRQ %s not found\n", name);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(platform_get_irq_byname);
 
 /**
+ * platform_get_irq_byname_optional - get an optional IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an optional IRQ by name like platform_get_irq_byname(). Except that it
+ * does not print an error message if an IRQ can not be obtained.
+ *
+ * Return: IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname_optional(struct platform_device *dev,
+				     const char *name)
+{
+	return __platform_get_irq_byname(dev, name);
+}
+EXPORT_SYMBOL_GPL(platform_get_irq_byname_optional);
+
+/**
  * platform_add_devices - add a numbers of platform devices
  * @devs: array of platform devices to add
  * @num: number of platform devices in array
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 6c90fd7e2ff8..350dcafd751f 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -115,20 +115,10 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	switch (type) {
-	case DEV_PM_QOS_RESUME_LATENCY:
+	if (type == DEV_PM_QOS_RESUME_LATENCY) {
 		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
 			: pm_qos_read_value(&qos->resume_latency);
-		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->min_frequency);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->max_frequency);
-		break;
-	default:
+	} else {
 		WARN_ON(1);
 		ret = 0;
 	}
@@ -169,14 +159,6 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 			req->dev->power.set_latency_tolerance(req->dev, value);
 		}
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = pm_qos_update_target(&qos->min_frequency,
-					   &req->data.pnode, action, value);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = pm_qos_update_target(&qos->max_frequency,
-					   &req->data.pnode, action, value);
-		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -227,24 +209,6 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 
-	c = &qos->min_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MAX;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
-	c = &qos->max_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MIN;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -305,18 +269,6 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		memset(req, 0, sizeof(*req));
 	}
 
-	c = &qos->min_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
-	c = &qos->max_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -428,8 +380,6 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
-	case DEV_PM_QOS_MIN_FREQUENCY:
-	case DEV_PM_QOS_MAX_FREQUENCY:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -557,14 +507,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier,
 		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
 						       notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->min_frequency.notifiers,
-						       notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->max_frequency.notifiers,
-						       notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
@@ -604,14 +546,6 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
 							 notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->min_frequency.notifiers,
-							 notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->max_frequency.notifiers,
-							 notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;