[PATCH v2 1/5] mm/hotplug: Embed vmem_altmap details in memory block

["Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>]

With memmap on memory, some architecture needs more details w.r.t altmap
such as base_pfn, end_pfn, etc to unmap vmemmap memory.

Embed vmem_altmap data structure to memory_bock and use that instead of
nr_vmemmap_pages.

On memory unplug, if the kernel finds any memory block in the range to
be using vmem_altmap, the kernel fails to unplug the memory if the
request is not a single memory block unplug.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/base/memory.c    | 28 +++++++++++++++++++---------
 include/linux/memory.h   | 25 +++++++++++++++++++------
 include/linux/memremap.h | 18 +-----------------
 mm/memory_hotplug.c      | 31 ++++++++++++++-----------------
 4 files changed, 53 insertions(+), 49 deletions(-)

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index b456ac213610..523cc1d37c81 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -106,6 +106,7 @@ static void memory_block_release(struct device *dev)
 {
 	struct memory_block *mem = to_memory_block(dev);
 
+	WARN(mem->altmap.alloc, "Altmap not fully unmapped");
 	kfree(mem);
 }
 
@@ -183,7 +184,7 @@ 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;
+	unsigned long nr_vmemmap_pages = 0;
 	struct zone *zone;
 	int ret;
 
@@ -200,6 +201,9 @@ static int memory_block_online(struct memory_block *mem)
 	 * stage helps to keep accounting easier to follow - e.g vmemmaps
 	 * belong to the same zone as the memory they backed.
 	 */
+	if (mem->altmap.alloc)
+		nr_vmemmap_pages = mem->altmap.alloc + mem->altmap.reserve;
+
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
@@ -230,7 +234,7 @@ 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;
+	unsigned long nr_vmemmap_pages = 0;
 	int ret;
 
 	if (!mem->zone)
@@ -240,6 +244,9 @@ static int memory_block_offline(struct memory_block *mem)
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().
 	 */
+	if (mem->altmap.alloc)
+		nr_vmemmap_pages = mem->altmap.alloc + mem->altmap.reserve;
+
 	if (nr_vmemmap_pages)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
@@ -726,7 +733,7 @@ void memory_block_add_nid(struct memory_block *mem, int nid,
 #endif
 
 static int add_memory_block(unsigned long block_id, unsigned long state,
-			    unsigned long nr_vmemmap_pages,
+			    struct vmem_altmap *altmap,
 			    struct memory_group *group)
 {
 	struct memory_block *mem;
@@ -744,7 +751,10 @@ static int add_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;
+	if (altmap)
+		memcpy(&mem->altmap, altmap, sizeof(*altmap));
+	else
+		mem->altmap.alloc = 0;
 	INIT_LIST_HEAD(&mem->group_next);
 
 #ifndef CONFIG_NUMA
@@ -783,14 +793,14 @@ static int __init add_boot_memory_block(unsigned long base_section_nr)
 	if (section_count == 0)
 		return 0;
 	return add_memory_block(memory_block_id(base_section_nr),
-				MEM_ONLINE, 0,  NULL);
+				MEM_ONLINE, NULL,  NULL);
 }
 
 static int add_hotplug_memory_block(unsigned long block_id,
-				    unsigned long nr_vmemmap_pages,
+				    struct vmem_altmap *altmap,
 				    struct memory_group *group)
 {
-	return add_memory_block(block_id, MEM_OFFLINE, nr_vmemmap_pages, group);
+	return add_memory_block(block_id, MEM_OFFLINE, altmap, group);
 }
 
 static void remove_memory_block(struct memory_block *memory)
@@ -818,7 +828,7 @@ static void remove_memory_block(struct memory_block *memory)
  * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group)
 {
 	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
@@ -832,7 +842,7 @@ 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 = add_hotplug_memory_block(block_id, vmemmap_pages, group);
+		ret = add_hotplug_memory_block(block_id, altmap, group);
 		if (ret)
 			break;
 	}
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 31343566c221..87f12924250f 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -64,6 +64,23 @@ struct memory_group {
 	};
 };
 
+/**
+ * struct vmem_altmap - pre-allocated storage for vmemmap_populate
+ * @base_pfn: base of the entire dev_pagemap mapping
+ * @reserve: pages mapped, but reserved for driver use (relative to @base)
+ * @free: free pages set aside in the mapping for memmap storage
+ * @align: pages reserved to meet allocation alignments
+ * @alloc: track pages consumed, private to vmemmap_populate()
+ */
+struct vmem_altmap {
+	unsigned long base_pfn;
+	const unsigned long end_pfn;
+	const unsigned long reserve;
+	unsigned long free;
+	unsigned long align;
+	unsigned long alloc;
+};
+
 struct memory_block {
 	unsigned long start_section_nr;
 	unsigned long state;		/* serialized by the dev->lock */
@@ -77,11 +94,7 @@ struct memory_block {
 	 */
 	struct zone *zone;
 	struct device dev;
-	/*
-	 * Number of vmemmap pages. These pages
-	 * lay at the beginning of the memory block.
-	 */
-	unsigned long nr_vmemmap_pages;
+	struct vmem_altmap altmap;
 	struct memory_group *group;	/* group (if any) for this block */
 	struct list_head group_next;	/* next block inside memory group */
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
@@ -147,7 +160,7 @@ static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1314d9c5f05b..4cb326f85302 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_MEMREMAP_H_
 #define _LINUX_MEMREMAP_H_
 
+#include <linux/memory.h>
 #include <linux/mmzone.h>
 #include <linux/range.h>
 #include <linux/ioport.h>
@@ -10,23 +11,6 @@
 struct resource;
 struct device;
 
-/**
- * struct vmem_altmap - pre-allocated storage for vmemmap_populate
- * @base_pfn: base of the entire dev_pagemap mapping
- * @reserve: pages mapped, but reserved for driver use (relative to @base)
- * @free: free pages set aside in the mapping for memmap storage
- * @align: pages reserved to meet allocation alignments
- * @alloc: track pages consumed, private to vmemmap_populate()
- */
-struct vmem_altmap {
-	unsigned long base_pfn;
-	const unsigned long end_pfn;
-	const unsigned long reserve;
-	unsigned long free;
-	unsigned long align;
-	unsigned long alloc;
-};
-
 /*
  * Specialize ZONE_DEVICE memory into multiple types each has a different
  * usage.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3f231cf1b410..c4bac38cc147 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1354,7 +1354,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		goto error;
 
 	/* create memory block devices after memory was added */
-	ret = create_memory_block_devices(start, size, mhp_altmap.alloc,
+	ret = create_memory_block_devices(start, size, &mhp_altmap,
 					  group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
@@ -1956,12 +1956,18 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 	return 0;
 }
 
-static int get_nr_vmemmap_pages_cb(struct memory_block *mem, void *arg)
+static int get_vmemmap_altmap_cb(struct memory_block *mem, void *arg)
 {
+	struct vmem_altmap **altmap = (struct vmem_altmap **)arg;
 	/*
-	 * If not set, continue with the next block.
+	 * If we have any pages allocated from altmap
+	 * return the altmap details and break callback.
 	 */
-	return mem->nr_vmemmap_pages;
+	if (mem->altmap.alloc) {
+		*altmap = &mem->altmap;
+		return 1;
+	}
+	return 0;
 }
 
 static int check_cpu_on_node(int nid)
@@ -2036,9 +2042,8 @@ EXPORT_SYMBOL(try_offline_node);
 
 static int __ref try_remove_memory(u64 start, u64 size)
 {
-	struct vmem_altmap mhp_altmap = {};
+	int ret;
 	struct vmem_altmap *altmap = NULL;
-	unsigned long nr_vmemmap_pages;
 	int rc = 0, nid = NUMA_NO_NODE;
 
 	BUG_ON(check_hotplug_memory_range(start, size));
@@ -2060,24 +2065,16 @@ static int __ref try_remove_memory(u64 start, u64 size)
 	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
 	 * the same granularity it was added - a single memory block.
 	 */
+
 	if (mhp_memmap_on_memory()) {
-		nr_vmemmap_pages = walk_memory_blocks(start, size, NULL,
-						      get_nr_vmemmap_pages_cb);
-		if (nr_vmemmap_pages) {
+		ret = walk_memory_blocks(start, size, &altmap, get_vmemmap_altmap_cb);
+		if (ret) {
 			if (size != memory_block_size_bytes()) {
 				pr_warn("Refuse to remove %#llx - %#llx,"
 					"wrong granularity\n",
 					start, start + size);
 				return -EINVAL;
 			}
-
-			/*
-			 * Let remove_pmd_table->free_hugepage_table do the
-			 * right thing if we used vmem_altmap when hot-adding
-			 * the range.
-			 */
-			mhp_altmap.alloc = nr_vmemmap_pages;
-			altmap = &mhp_altmap;
 		}
 	}
 
-- 
2.41.0