4 files changed, 132 insertions, 52 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 4a8bf8cda52b..54ba506e5a89 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -150,7 +150,7 @@ void fwnode_links_purge(struct fwnode_handle *fwnode)
 	fwnode_links_purge_consumers(fwnode);
 }
 
-static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode)
+void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode)
 {
 	struct fwnode_handle *child;
 
@@ -164,6 +164,7 @@ static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode)
 	fwnode_for_each_available_child_node(fwnode, child)
 		fw_devlink_purge_absent_suppliers(child);
 }
+EXPORT_SYMBOL_GPL(fw_devlink_purge_absent_suppliers);
 
 #ifdef CONFIG_SRCU
 static DEFINE_MUTEX(device_links_lock);
@@ -193,6 +194,17 @@ int device_links_read_lock_held(void)
 {
 	return srcu_read_lock_held(&device_links_srcu);
 }
+
+static void device_link_synchronize_removal(void)
+{
+	synchronize_srcu(&device_links_srcu);
+}
+
+static void device_link_remove_from_lists(struct device_link *link)
+{
+	list_del_rcu(&link->s_node);
+	list_del_rcu(&link->c_node);
+}
 #else /* !CONFIG_SRCU */
 static DECLARE_RWSEM(device_links_lock);
 
@@ -223,6 +235,16 @@ int device_links_read_lock_held(void)
 	return lockdep_is_held(&device_links_lock);
 }
 #endif
+
+static inline void device_link_synchronize_removal(void)
+{
+}
+
+static void device_link_remove_from_lists(struct device_link *link)
+{
+	list_del(&link->s_node);
+	list_del(&link->c_node);
+}
 #endif /* !CONFIG_SRCU */
 
 static bool device_is_ancestor(struct device *dev, struct device *target)
@@ -444,8 +466,13 @@ static struct attribute *devlink_attrs[] = {
 };
 ATTRIBUTE_GROUPS(devlink);
 
-static void device_link_free(struct device_link *link)
+static void device_link_release_fn(struct work_struct *work)
 {
+	struct device_link *link = container_of(work, struct device_link, rm_work);
+
+	/* Ensure that all references to the link object have been dropped. */
+	device_link_synchronize_removal();
+
 	while (refcount_dec_not_one(&link->rpm_active))
 		pm_runtime_put(link->supplier);
 
@@ -454,24 +481,19 @@ static void device_link_free(struct device_link *link)
 	kfree(link);
 }
 
-#ifdef CONFIG_SRCU
-static void __device_link_free_srcu(struct rcu_head *rhead)
-{
-	device_link_free(container_of(rhead, struct device_link, rcu_head));
-}
-
 static void devlink_dev_release(struct device *dev)
 {
 	struct device_link *link = to_devlink(dev);
 
-	call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu);
-}
-#else
-static void devlink_dev_release(struct device *dev)
-{
-	device_link_free(to_devlink(dev));
+	INIT_WORK(&link->rm_work, device_link_release_fn);
+	/*
+	 * It may take a while to complete this work because of the SRCU
+	 * synchronization in device_link_release_fn() and if the consumer or
+	 * supplier devices get deleted when it runs, so put it into the "long"
+	 * workqueue.
+	 */
+	queue_work(system_long_wq, &link->rm_work);
 }
-#endif
 
 static struct class devlink_class = {
 	.name = "devlink",
@@ -845,7 +867,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(device_link_add);
 
-#ifdef CONFIG_SRCU
 static void __device_link_del(struct kref *kref)
 {
 	struct device_link *link = container_of(kref, struct device_link, kref);
@@ -855,25 +876,9 @@ static void __device_link_del(struct kref *kref)
 
 	pm_runtime_drop_link(link);
 
-	list_del_rcu(&link->s_node);
-	list_del_rcu(&link->c_node);
-	device_unregister(&link->link_dev);
-}
-#else /* !CONFIG_SRCU */
-static void __device_link_del(struct kref *kref)
-{
-	struct device_link *link = container_of(kref, struct device_link, kref);
-
-	dev_info(link->consumer, "Dropping the link to %s\n",
-		 dev_name(link->supplier));
-
-	pm_runtime_drop_link(link);
-
-	list_del(&link->s_node);
-	list_del(&link->c_node);
+	device_link_remove_from_lists(link);
 	device_unregister(&link->link_dev);
 }
-#endif /* !CONFIG_SRCU */
 
 static void device_link_put_kref(struct device_link *link)
 {
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 78355095e00d..4fdb8219cd08 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -15,6 +15,7 @@
 #include <linux/kernel_read_file.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/initrd.h>
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
 #include <linux/interrupt.h>
@@ -504,6 +505,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 	if (!path)
 		return -ENOMEM;
 
+	wait_for_initramfs();
 	for (i = 0; i < ARRAY_SIZE(fw_path); i++) {
 		size_t file_size = 0;
 		size_t *file_size_ptr = NULL;
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f35298425575..b31b3af5c490 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -169,30 +169,98 @@ int memory_notify(unsigned long val, void *v)
 	return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
+static int memory_block_online(struct memory_block *mem)
+{
+	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	struct zone *zone;
+	int ret;
+
+	zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages);
+
+	/*
+	 * Although vmemmap pages have a different lifecycle than the pages
+	 * they describe (they remain until the memory is unplugged), doing
+	 * their initialization and accounting at memory onlining/offlining
+	 * stage helps to keep accounting easier to follow - e.g vmemmaps
+	 * belong to the same zone as the memory they backed.
+	 */
+	if (nr_vmemmap_pages) {
+		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
+		if (ret)
+			return ret;
+	}
+
+	ret = online_pages(start_pfn + nr_vmemmap_pages,
+			   nr_pages - nr_vmemmap_pages, zone);
+	if (ret) {
+		if (nr_vmemmap_pages)
+			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+		return ret;
+	}
+
+	/*
+	 * Account once onlining succeeded. If the zone was unpopulated, it is
+	 * now already properly populated.
+	 */
+	if (nr_vmemmap_pages)
+		adjust_present_page_count(zone, nr_vmemmap_pages);
+
+	return ret;
+}
+
+static int memory_block_offline(struct memory_block *mem)
+{
+	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+
+	/*
+	 * Unaccount before offlining, such that unpopulated zone and kthreads
+	 * can properly be torn down in offline_pages().
+	 */
+	if (nr_vmemmap_pages)
+		adjust_present_page_count(zone, -nr_vmemmap_pages);
+
+	ret = offline_pages(start_pfn + nr_vmemmap_pages,
+			    nr_pages - nr_vmemmap_pages);
+	if (ret) {
+		/* offline_pages() failed. Account back. */
+		if (nr_vmemmap_pages)
+			adjust_present_page_count(zone, nr_vmemmap_pages);
+		return ret;
+	}
+
+	if (nr_vmemmap_pages)
+		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+
+	return ret;
+}
+
 /*
  * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(unsigned long start_section_nr, unsigned long action,
-		    int online_type, int nid)
+memory_block_action(struct memory_block *mem, unsigned long action)
 {
-	unsigned long start_pfn;
-	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	int ret;
 
-	start_pfn = section_nr_to_pfn(start_section_nr);
-
 	switch (action) {
 	case MEM_ONLINE:
-		ret = online_pages(start_pfn, nr_pages, online_type, nid);
+		ret = memory_block_online(mem);
 		break;
 	case MEM_OFFLINE:
-		ret = offline_pages(start_pfn, nr_pages);
+		ret = memory_block_offline(mem);
 		break;
 	default:
 		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
-		     "%ld\n", __func__, start_section_nr, action, action);
+		     "%ld\n", __func__, mem->start_section_nr, action, action);
 		ret = -EINVAL;
 	}
 
@@ -210,9 +278,7 @@ static int memory_block_change_state(struct memory_block *mem,
 	if (to_state == MEM_OFFLINE)
 		mem->state = MEM_GOING_OFFLINE;
 
-	ret = memory_block_action(mem->start_section_nr, to_state,
-				  mem->online_type, mem->nid);
-
+	ret = memory_block_action(mem, to_state);
 	mem->state = ret ? from_state_req : to_state;
 
 	return ret;
@@ -567,7 +633,8 @@ int register_memory(struct memory_block *memory)
 	return ret;
 }
 
-static int init_memory_block(unsigned long block_id, unsigned long state)
+static int init_memory_block(unsigned long block_id, unsigned long state,
+			     unsigned long nr_vmemmap_pages)
 {
 	struct memory_block *mem;
 	int ret = 0;
@@ -584,6 +651,7 @@ static int init_memory_block(unsigned long block_id, unsigned long state)
 	mem->start_section_nr = block_id * sections_per_block;
 	mem->state = state;
 	mem->nid = NUMA_NO_NODE;
+	mem->nr_vmemmap_pages = nr_vmemmap_pages;
 
 	ret = register_memory(mem);
 
@@ -603,7 +671,7 @@ static int add_memory_block(unsigned long base_section_nr)
 	if (section_count == 0)
 		return 0;
 	return init_memory_block(memory_block_id(base_section_nr),
-				 MEM_ONLINE);
+				 MEM_ONLINE, 0);
 }
 
 static void unregister_memory(struct memory_block *memory)
@@ -625,7 +693,8 @@ static void unregister_memory(struct memory_block *memory)
  *
  * Called under device_hotplug_lock.
  */
-int create_memory_block_devices(unsigned long start, unsigned long size)
+int create_memory_block_devices(unsigned long start, unsigned long size,
+				unsigned long vmemmap_pages)
 {
 	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
 	unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
@@ -638,7 +707,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
 		return -EINVAL;
 
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
-		ret = init_memory_block(block_id, MEM_OFFLINE);
+		ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages);
 		if (ret)
 			break;
 	}
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 1fc1a992f90c..b570848d23e0 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1637,6 +1637,7 @@ void pm_runtime_init(struct device *dev)
 	dev->power.request_pending = false;
 	dev->power.request = RPM_REQ_NONE;
 	dev->power.deferred_resume = false;
+	dev->power.needs_force_resume = 0;
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
@@ -1804,10 +1805,12 @@ int pm_runtime_force_suspend(struct device *dev)
 	 * its parent, but set its status to RPM_SUSPENDED anyway in case this
 	 * function will be called again for it in the meantime.
 	 */
-	if (pm_runtime_need_not_resume(dev))
+	if (pm_runtime_need_not_resume(dev)) {
 		pm_runtime_set_suspended(dev);
-	else
+	} else {
 		__update_runtime_status(dev, RPM_SUSPENDED);
+		dev->power.needs_force_resume = 1;
+	}
 
 	return 0;
 
@@ -1834,7 +1837,7 @@ int pm_runtime_force_resume(struct device *dev)
 	int (*callback)(struct device *);
 	int ret = 0;
 
-	if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev))
+	if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume)
 		goto out;
 
 	/*
@@ -1853,6 +1856,7 @@ int pm_runtime_force_resume(struct device *dev)
 
 	pm_runtime_mark_last_busy(dev);
 out:
+	dev->power.needs_force_resume = 0;
 	pm_runtime_enable(dev);
 	return ret;
 }