Message-ID: <20260130163756.2674225-2-tianyou.li@intel.com>
Date: Sat, 31 Jan 2026 00:37:55 +0800
From: Tianyou Li <tianyou.li@...el.com>
To: David Hildenbrand <david@...nel.org>,
	Oscar Salvador <osalvador@...e.de>,
	Mike Rapoport <rppt@...nel.org>,
	Wei Yang <richard.weiyang@...il.com>,
	Michal Hocko <mhocko@...e.com>
Cc: linux-mm@...ck.org,
	Yong Hu <yong.hu@...el.com>,
	Nanhai Zou <nanhai.zou@...el.com>,
	Yuan Liu <yuan1.liu@...el.com>,
	Tim Chen <tim.c.chen@...ux.intel.com>,
	Qiuxu Zhuo <qiuxu.zhuo@...el.com>,
	Yu C Chen <yu.c.chen@...el.com>,
	Pan Deng <pan.deng@...el.com>,
	Tianyou Li <tianyou.li@...el.com>,
	Chen Zhang <zhangchen.kidd@...com>,
	linux-kernel@...r.kernel.org
Subject: [PATCH v9 1/2] mm/memory hotplug/unplug: Add online_memory_block_pages() and offline_memory_block_pages()

Encapsulate the mhp_init_memmap_on_memory() and online_pages() into
online_memory_block_pages(). Thus we can further optimize the
set_zone_contiguous() to check the whole memory block range, instead
of check the zone contiguous in separate range.

Correspondingly, encapsulate the mhp_deinit_memmap_on_memory() and
offline_pages() into offline_memory_block_pages().

Furthermore, move most of memory_block_online() to the new function
mhp_block_online(struct memory_block *block) and correspondingly
memory_block_offline() to mhp_block_offline(struct memory_block *block).

Tested-by: Yuan Liu <yuan1.liu@...el.com>
Reviewed-by: Yuan Liu <yuan1.liu@...el.com>
Signed-off-by: Tianyou Li <tianyou.li@...el.com>
---
 drivers/base/memory.c          | 115 +---------------------------
 include/linux/memory_hotplug.h |  13 +---
 include/linux/mm.h             |   6 ++
 mm/memory_hotplug.c            | 132 ++++++++++++++++++++++++++++++++-
 4 files changed, 141 insertions(+), 125 deletions(-)

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 751f248ca4a8..40f014c5dbb1 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -209,115 +209,6 @@ int memory_notify(enum memory_block_state state, void *v)
 	return blocking_notifier_call_chain(&memory_chain, state, v);
 }
 
-#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
-static unsigned long memblk_nr_poison(struct memory_block *mem);
-#else
-static inline unsigned long memblk_nr_poison(struct memory_block *mem)
-{
-	return 0;
-}
-#endif
-
-/*
- * Must acquire mem_hotplug_lock in write mode.
- */
-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 = 0;
-	struct zone *zone;
-	int ret;
-
-	if (memblk_nr_poison(mem))
-		return -EHWPOISON;
-
-	zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
-				  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 (mem->altmap)
-		nr_vmemmap_pages = mem->altmap->free;
-
-	mem_hotplug_begin();
-	if (nr_vmemmap_pages) {
-		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
-		if (ret)
-			goto out;
-	}
-
-	ret = online_pages(start_pfn + nr_vmemmap_pages,
-			   nr_pages - nr_vmemmap_pages, zone, mem->group);
-	if (ret) {
-		if (nr_vmemmap_pages)
-			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
-		goto out;
-	}
-
-	/*
-	 * Account once onlining succeeded. If the zone was unpopulated, it is
-	 * now already properly populated.
-	 */
-	if (nr_vmemmap_pages)
-		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
-					  nr_vmemmap_pages);
-
-	mem->zone = zone;
-out:
-	mem_hotplug_done();
-	return ret;
-}
-
-/*
- * Must acquire mem_hotplug_lock in write mode.
- */
-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 = 0;
-	int ret;
-
-	if (!mem->zone)
-		return -EINVAL;
-
-	/*
-	 * Unaccount before offlining, such that unpopulated zone and kthreads
-	 * can properly be torn down in offline_pages().
-	 */
-	if (mem->altmap)
-		nr_vmemmap_pages = mem->altmap->free;
-
-	mem_hotplug_begin();
-	if (nr_vmemmap_pages)
-		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
-					  -nr_vmemmap_pages);
-
-	ret = offline_pages(start_pfn + nr_vmemmap_pages,
-			    nr_pages - nr_vmemmap_pages, mem->zone, mem->group);
-	if (ret) {
-		/* offline_pages() failed. Account back. */
-		if (nr_vmemmap_pages)
-			adjust_present_page_count(pfn_to_page(start_pfn),
-						  mem->group, nr_vmemmap_pages);
-		goto out;
-	}
-
-	if (nr_vmemmap_pages)
-		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
-
-	mem->zone = NULL;
-out:
-	mem_hotplug_done();
-	return ret;
-}
-
 /*
  * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
  * OK to have direct references to sparsemem variables in here.
@@ -329,10 +220,10 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 
 	switch (action) {
 	case MEM_ONLINE:
-		ret = memory_block_online(mem);
+		ret = mhp_block_online(mem);
 		break;
 	case MEM_OFFLINE:
-		ret = memory_block_offline(mem);
+		ret = mhp_block_offline(mem);
 		break;
 	default:
 		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
@@ -1243,7 +1134,7 @@ void memblk_nr_poison_sub(unsigned long pfn, long i)
 		atomic_long_sub(i, &mem->nr_hwpoison);
 }
 
-static unsigned long memblk_nr_poison(struct memory_block *mem)
+unsigned long memblk_nr_poison(struct memory_block *mem)
 {
 	return atomic_long_read(&mem->nr_hwpoison);
 }
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index f2f16cdd73ee..8783a11da464 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -12,6 +12,7 @@ struct zone;
 struct pglist_data;
 struct mem_section;
 struct memory_group;
+struct memory_block;
 struct resource;
 struct vmem_altmap;
 struct dev_pagemap;
@@ -106,11 +107,7 @@ extern void adjust_present_page_count(struct page *page,
 				      struct memory_group *group,
 				      long nr_pages);
 /* VM interface that may be used by firmware interface */
-extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
-				     struct zone *zone);
-extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
-extern int online_pages(unsigned long pfn, unsigned long nr_pages,
-			struct zone *zone, struct memory_group *group);
+extern int mhp_block_online(struct memory_block *block);
 extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
 		unsigned long end_pfn);
 
@@ -261,8 +258,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern void try_offline_node(int nid);
-extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-			 struct zone *zone, struct memory_group *group);
+extern int mhp_block_offline(struct memory_block *block);
 extern int remove_memory(u64 start, u64 size);
 extern void __remove_memory(u64 start, u64 size);
 extern int offline_and_remove_memory(u64 start, u64 size);
@@ -270,8 +266,7 @@ extern int offline_and_remove_memory(u64 start, u64 size);
 #else
 static inline void try_offline_node(int nid) {}
 
-static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-				struct zone *zone, struct memory_group *group)
+static inline int mhp_block_offline(struct memory_block *block)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6f959d8ca4b4..967605d95131 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4377,6 +4377,7 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
 extern void memblk_nr_poison_inc(unsigned long pfn);
 extern void memblk_nr_poison_sub(unsigned long pfn, long i);
+extern unsigned long memblk_nr_poison(struct memory_block *mem);
 #else
 static inline void memblk_nr_poison_inc(unsigned long pfn)
 {
@@ -4385,6 +4386,11 @@ static inline void memblk_nr_poison_inc(unsigned long pfn)
 static inline void memblk_nr_poison_sub(unsigned long pfn, long i)
 {
 }
+
+static inline unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+	return 0;
+}
 #endif
 
 #ifndef arch_memory_failure
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c8f492b5daf0..62d6bc8ea2dd 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1085,7 +1085,7 @@ void adjust_present_page_count(struct page *page, struct memory_group *group,
 		group->present_kernel_pages += nr_pages;
 }
 
-int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
+static int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 			      struct zone *zone)
 {
 	unsigned long end_pfn = pfn + nr_pages;
@@ -1116,7 +1116,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 	return ret;
 }
 
-void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
+static void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 {
 	unsigned long end_pfn = pfn + nr_pages;
 
@@ -1139,7 +1139,7 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 /*
  * Must be called with mem_hotplug_lock in write mode.
  */
-int online_pages(unsigned long pfn, unsigned long nr_pages,
+static int online_pages(unsigned long pfn, unsigned long nr_pages,
 		       struct zone *zone, struct memory_group *group)
 {
 	struct memory_notify mem_arg = {
@@ -1254,6 +1254,74 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	return ret;
 }
 
+static int online_memory_block_pages(unsigned long start_pfn, unsigned long nr_pages,
+			unsigned long nr_vmemmap_pages, struct zone *zone,
+			struct memory_group *group)
+{
+	int ret;
+
+	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, group);
+	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(pfn_to_page(start_pfn), group,
+					  nr_vmemmap_pages);
+
+	return ret;
+}
+
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
+int mhp_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 = 0;
+	struct zone *zone;
+	int ret;
+
+	if (memblk_nr_poison(mem))
+		return -EHWPOISON;
+
+	zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
+				  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 (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
+	mem_hotplug_begin();
+	ret = online_memory_block_pages(start_pfn, nr_pages, nr_vmemmap_pages,
+					zone, mem->group);
+	if (!ret)
+		mem->zone = zone;
+	mem_hotplug_done();
+
+	return ret;
+}
+
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
 static pg_data_t *hotadd_init_pgdat(int nid)
 {
@@ -1896,7 +1964,7 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
 /*
  * Must be called with mem_hotplug_lock in write mode.
  */
-int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+static int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
 	unsigned long pfn, managed_pages, system_ram_pages = 0;
@@ -2101,6 +2169,62 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	return ret;
 }
 
+static int offline_memory_block_pages(unsigned long start_pfn,
+		unsigned long nr_pages, unsigned long nr_vmemmap_pages,
+		struct zone *zone, struct memory_group *group)
+{
+	int ret;
+
+	if (nr_vmemmap_pages)
+		adjust_present_page_count(pfn_to_page(start_pfn), group,
+					  -nr_vmemmap_pages);
+
+	ret = offline_pages(start_pfn + nr_vmemmap_pages,
+			    nr_pages - nr_vmemmap_pages, zone, group);
+	if (ret) {
+		/* offline_pages() failed. Account back. */
+		if (nr_vmemmap_pages)
+			adjust_present_page_count(pfn_to_page(start_pfn),
+						  group, nr_vmemmap_pages);
+		return ret;
+	}
+
+	if (nr_vmemmap_pages)
+		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+
+	return ret;
+}
+
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
+int mhp_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 = 0;
+	int ret;
+
+	if (!mem->zone)
+		return -EINVAL;
+
+	/*
+	 * Unaccount before offlining, such that unpopulated zone and kthreads
+	 * can properly be torn down in offline_pages().
+	 */
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
+	mem_hotplug_begin();
+	ret = offline_memory_block_pages(start_pfn, nr_pages, nr_vmemmap_pages,
+					 mem->zone, mem->group);
+	if (!ret)
+		mem->zone = NULL;
+	mem_hotplug_done();
+
+	return ret;
+}
+
 static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 {
 	int *nid = arg;
-- 
2.47.1

Powered by blists - more mailing lists