[RFC PATCH 0/5] Add support for memmap on memory feature on ppc64

[RFC PATCH 0/5] Add support for memmap on memory feature on ppc64

[Aneesh Kumar K.V]

This patch series update memmap on memory feature to fall back to
memmap allocation outside the memory block if the alignment rules are
not met. This makes the feature more useful on architectures like
ppc64 where alignment rules are different with 64K page size.

This patch series is dependent on dax vmemmap optimization series
posted here https://lore.kernel.org/linux-mm/20230616110826.344417-1-aneesh.kumar@linux.ibm.com


Aneesh Kumar K.V (5):
  mm/hotplug: Embed vmem_altmap details in memory block
  mm/hotplug: Allow architecture override for memmap on memory feature
  mm/hotplug: Simplify the handling of MHP_MEMMAP_ON_MEMORY flag
  mm/hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig
  powerpc/book3s64/memhotplug: Enable memmap on memory for radix

 arch/arm64/Kconfig                            |  4 +-
 arch/arm64/mm/mmu.c                           |  5 +
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/mm/book3s64/radix_pgtable.c      | 28 ++++++
 .../platforms/pseries/hotplug-memory.c        |  4 +-
 arch/x86/Kconfig                              |  4 +-
 arch/x86/mm/init_64.c                         |  6 ++
 drivers/acpi/acpi_memhotplug.c                |  3 +-
 drivers/base/memory.c                         | 28 ++++--
 include/linux/memory.h                        | 25 +++--
 include/linux/memory_hotplug.h                | 17 +++-
 include/linux/memremap.h                      | 18 +---
 mm/Kconfig                                    |  3 +
 mm/memory_hotplug.c                           | 95 +++++++++----------
 14 files changed, 151 insertions(+), 90 deletions(-)

-- 
2.41.0

[RFC PATCH 0/5] Add support for memmap on memory feature on ppc64

[Aneesh Kumar K.V]

This patch series update memmap on memory feature to fall back to
memmap allocation outside the memory block if the alignment rules are
not met. This makes the feature more useful on architectures like
ppc64 where alignment rules are different with 64K page size.

This patch series is dependent on dax vmemmap optimization series
posted here https://lore.kernel.org/linux-mm/20230616110826.344417-1-aneesh.kumar@linux.ibm.com


Aneesh Kumar K.V (5):
  mm/hotplug: Embed vmem_altmap details in memory block
  mm/hotplug: Allow architecture override for memmap on memory feature
  mm/hotplug: Simplify the handling of MHP_MEMMAP_ON_MEMORY flag
  mm/hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig
  powerpc/book3s64/memhotplug: Enable memmap on memory for radix

 arch/arm64/Kconfig                            |  4 +-
 arch/arm64/mm/mmu.c                           |  5 +
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/mm/book3s64/radix_pgtable.c      | 28 ++++++
 .../platforms/pseries/hotplug-memory.c        |  4 +-
 arch/x86/Kconfig                              |  4 +-
 arch/x86/mm/init_64.c                         |  6 ++
 drivers/acpi/acpi_memhotplug.c                |  3 +-
 drivers/base/memory.c                         | 28 ++++--
 include/linux/memory.h                        | 25 +++--
 include/linux/memory_hotplug.h                | 17 +++-
 include/linux/memremap.h                      | 18 +---
 mm/Kconfig                                    |  3 +
 mm/memory_hotplug.c                           | 95 +++++++++----------
 14 files changed, 151 insertions(+), 90 deletions(-)

-- 
2.41.0

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

[Aneesh Kumar K.V]

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      | 42 +++++++++++++++++-----------------------
 4 files changed, 57 insertions(+), 56 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 eb18d1ac7e84..88a9c4443fc0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1391,7 +1391,7 @@ 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);
@@ -1993,12 +1993,18 @@ 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)
@@ -2073,9 +2079,8 @@ 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));
@@ -2097,24 +2102,13 @@ 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) {
-			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;
+	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;
 		}
 	}
 
-- 
2.41.0

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

[Aneesh Kumar K.V]

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      | 42 +++++++++++++++++-----------------------
 4 files changed, 57 insertions(+), 56 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 eb18d1ac7e84..88a9c4443fc0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1391,7 +1391,7 @@ 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);
@@ -1993,12 +1993,18 @@ 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)
@@ -2073,9 +2079,8 @@ 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));
@@ -2097,24 +2102,13 @@ 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) {
-			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;
+	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;
 		}
 	}
 
-- 
2.41.0

[RFC PATCH 2/5] mm/hotplug: Allow architecture override for memmap on memory feature

[Aneesh Kumar K.V]

Some architectures like ppc64 wants to enable this feature only with radix
translation and their vemmap mappings have different alignment
requirements. Add overrider for mhp_supports_memmap_on_memory() and also
use altmap.reserve feature to adjust the pageblock alignment requirement.

The patch also fallback to allocation of memmap outside memblock if the
alignment rules are not met for memmap on memory allocation. This allows to
use the feature more widely allocating memmap as much as possible within
the memory block getting added.

A follow patch to enable memmap on memory for ppc64 will use this.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/arm64/mm/mmu.c            |  5 +++++
 arch/x86/mm/init_64.c          |  6 ++++++
 include/linux/memory_hotplug.h |  3 ++-
 mm/memory_hotplug.c            | 36 ++++++++++++++++++++++++----------
 4 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index af6bc8403ee4..a5165897ea58 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1335,6 +1335,11 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
 }
 
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return __mhp_supports_memmap_on_memory(size);
+}
+
 /*
  * This memory hotplug notifier helps prevent boot memory from being
  * inadvertently removed as it blocks pfn range offlining process in
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a190aae8ceaf..b318d26a70d4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1264,6 +1264,12 @@ void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 	__remove_pages(start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
+
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return __mhp_supports_memmap_on_memory(size);
+}
+
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 9fcbf5706595..2387391ee93a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -358,7 +358,8 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid,
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
 void arch_remove_linear_mapping(u64 start, u64 size);
-extern bool mhp_supports_memmap_on_memory(unsigned long size);
+bool mhp_supports_memmap_on_memory(unsigned long size);
+bool __mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 88a9c4443fc0..7cb112fb4996 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1284,7 +1284,8 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	return device_online(&mem->dev);
 }
 
-bool mhp_supports_memmap_on_memory(unsigned long size)
+/* Helper function for architecture to use. */
+bool __mhp_supports_memmap_on_memory(unsigned long size)
 {
 	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
 	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
@@ -1322,6 +1323,20 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
 	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
 }
 
+bool __weak mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return false;
+}
+
+/*
+ * Architectures may want to override the altmap reserve details based
+ * on the alignment requirement for vmemmap mapping.
+ */
+unsigned __weak long memory_block_align_base(struct resource *res)
+{
+	return 0;
+}
+
 /*
  * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
  * and online/offline operations (triggered e.g. by sysfs).
@@ -1332,7 +1347,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
 	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
 	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
-	struct vmem_altmap mhp_altmap = {};
+	struct vmem_altmap mhp_altmap = {
+		.base_pfn =  PHYS_PFN(res->start),
+		.end_pfn  =  PHYS_PFN(res->end),
+		.reserve  = memory_block_align_base(res),
+	};
 	struct memory_group *group = NULL;
 	u64 start, size;
 	bool new_node = false;
@@ -1376,13 +1395,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	 * Self hosted memmap array
 	 */
 	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
-		if (!mhp_supports_memmap_on_memory(size)) {
-			ret = -EINVAL;
-			goto error;
+		if (mhp_supports_memmap_on_memory(size)) {
+			mhp_altmap.free	= PHYS_PFN(size) - mhp_altmap.reserve;
+			params.altmap = &mhp_altmap;
 		}
-		mhp_altmap.free = PHYS_PFN(size);
-		mhp_altmap.base_pfn = PHYS_PFN(start);
-		params.altmap = &mhp_altmap;
+		/* if not supported don't use altmap */
 	}
 
 	/* call arch's memory hotadd */
@@ -1391,8 +1408,7 @@ 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,
-					  group);
+	ret = create_memory_block_devices(start, size, &mhp_altmap, group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
 		goto error;
-- 
2.41.0

[RFC PATCH 2/5] mm/hotplug: Allow architecture override for memmap on memory feature

[Aneesh Kumar K.V]

Some architectures like ppc64 wants to enable this feature only with radix
translation and their vemmap mappings have different alignment
requirements. Add overrider for mhp_supports_memmap_on_memory() and also
use altmap.reserve feature to adjust the pageblock alignment requirement.

The patch also fallback to allocation of memmap outside memblock if the
alignment rules are not met for memmap on memory allocation. This allows to
use the feature more widely allocating memmap as much as possible within
the memory block getting added.

A follow patch to enable memmap on memory for ppc64 will use this.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/arm64/mm/mmu.c            |  5 +++++
 arch/x86/mm/init_64.c          |  6 ++++++
 include/linux/memory_hotplug.h |  3 ++-
 mm/memory_hotplug.c            | 36 ++++++++++++++++++++++++----------
 4 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index af6bc8403ee4..a5165897ea58 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1335,6 +1335,11 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
 }
 
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return __mhp_supports_memmap_on_memory(size);
+}
+
 /*
  * This memory hotplug notifier helps prevent boot memory from being
  * inadvertently removed as it blocks pfn range offlining process in
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a190aae8ceaf..b318d26a70d4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1264,6 +1264,12 @@ void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 	__remove_pages(start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
+
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return __mhp_supports_memmap_on_memory(size);
+}
+
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 9fcbf5706595..2387391ee93a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -358,7 +358,8 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid,
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
 void arch_remove_linear_mapping(u64 start, u64 size);
-extern bool mhp_supports_memmap_on_memory(unsigned long size);
+bool mhp_supports_memmap_on_memory(unsigned long size);
+bool __mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 88a9c4443fc0..7cb112fb4996 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1284,7 +1284,8 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	return device_online(&mem->dev);
 }
 
-bool mhp_supports_memmap_on_memory(unsigned long size)
+/* Helper function for architecture to use. */
+bool __mhp_supports_memmap_on_memory(unsigned long size)
 {
 	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
 	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
@@ -1322,6 +1323,20 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
 	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
 }
 
+bool __weak mhp_supports_memmap_on_memory(unsigned long size)
+{
+	return false;
+}
+
+/*
+ * Architectures may want to override the altmap reserve details based
+ * on the alignment requirement for vmemmap mapping.
+ */
+unsigned __weak long memory_block_align_base(struct resource *res)
+{
+	return 0;
+}
+
 /*
  * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
  * and online/offline operations (triggered e.g. by sysfs).
@@ -1332,7 +1347,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
 	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
 	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
-	struct vmem_altmap mhp_altmap = {};
+	struct vmem_altmap mhp_altmap = {
+		.base_pfn =  PHYS_PFN(res->start),
+		.end_pfn  =  PHYS_PFN(res->end),
+		.reserve  = memory_block_align_base(res),
+	};
 	struct memory_group *group = NULL;
 	u64 start, size;
 	bool new_node = false;
@@ -1376,13 +1395,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	 * Self hosted memmap array
 	 */
 	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
-		if (!mhp_supports_memmap_on_memory(size)) {
-			ret = -EINVAL;
-			goto error;
+		if (mhp_supports_memmap_on_memory(size)) {
+			mhp_altmap.free	= PHYS_PFN(size) - mhp_altmap.reserve;
+			params.altmap = &mhp_altmap;
 		}
-		mhp_altmap.free = PHYS_PFN(size);
-		mhp_altmap.base_pfn = PHYS_PFN(start);
-		params.altmap = &mhp_altmap;
+		/* if not supported don't use altmap */
 	}
 
 	/* call arch's memory hotadd */
@@ -1391,8 +1408,7 @@ 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,
-					  group);
+	ret = create_memory_block_devices(start, size, &mhp_altmap, group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
 		goto error;
-- 
2.41.0

[RFC PATCH 3/5] mm/hotplug: Simplify the handling of MHP_MEMMAP_ON_MEMORY flag

[Aneesh Kumar K.V]

Instead of checking for memmap on memory feature enablement within the
functions checking for alignment, use the kernel parameter to control the
memory hotplug flags. The generic kernel now enables memmap on memory
feature if the hotplug flag request for the same.

The ACPI code now can pass the flag unconditionally because the kernel will
fallback to not using the feature if the alignment rules are not met.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/acpi/acpi_memhotplug.c |  3 +--
 include/linux/memory_hotplug.h | 14 ++++++++++++++
 mm/memory_hotplug.c            | 19 ++++---------------
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 24f662d8bd39..4d0096fc4cc2 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -211,8 +211,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (!info->length)
 			continue;
 
-		if (mhp_supports_memmap_on_memory(info->length))
-			mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+		mhp_flags |= get_memmap_on_memory_flags();
 		result = __add_memory(mgid, info->start_addr, info->length,
 				      mhp_flags);
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 2387391ee93a..add3e7829c80 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -362,4 +362,18 @@ bool mhp_supports_memmap_on_memory(unsigned long size);
 bool __mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+extern bool memmap_on_memory;
+static inline unsigned long get_memmap_on_memory_flags(void)
+{
+	if (memmap_on_memory)
+		return MHP_MEMMAP_ON_MEMORY;
+	return 0;
+}
+#else
+static inline unsigned long get_memmap_on_memory_flags(void)
+{
+	return 0;
+}
+#endif
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 7cb112fb4996..9cfa6fa31df5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -46,19 +46,9 @@
 /*
  * memory_hotplug.memmap_on_memory parameter
  */
-static bool memmap_on_memory __ro_after_init;
+bool memmap_on_memory __ro_after_init;
 module_param(memmap_on_memory, bool, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
-
-static inline bool mhp_memmap_on_memory(void)
-{
-	return memmap_on_memory;
-}
-#else
-static inline bool mhp_memmap_on_memory(void)
-{
-	return false;
-}
 #endif
 
 enum {
@@ -1317,10 +1307,9 @@ bool __mhp_supports_memmap_on_memory(unsigned long size)
 	 *       altmap as an alternative source of memory, and we do not exactly
 	 *       populate a single PMD.
 	 */
-	return mhp_memmap_on_memory() &&
-	       size == memory_block_size_bytes() &&
-	       IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
-	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
+	return size == memory_block_size_bytes() &&
+		IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
+		IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
 }
 
 bool __weak mhp_supports_memmap_on_memory(unsigned long size)
-- 
2.41.0

[RFC PATCH 3/5] mm/hotplug: Simplify the handling of MHP_MEMMAP_ON_MEMORY flag

[Aneesh Kumar K.V]

Instead of checking for memmap on memory feature enablement within the
functions checking for alignment, use the kernel parameter to control the
memory hotplug flags. The generic kernel now enables memmap on memory
feature if the hotplug flag request for the same.

The ACPI code now can pass the flag unconditionally because the kernel will
fallback to not using the feature if the alignment rules are not met.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/acpi/acpi_memhotplug.c |  3 +--
 include/linux/memory_hotplug.h | 14 ++++++++++++++
 mm/memory_hotplug.c            | 19 ++++---------------
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 24f662d8bd39..4d0096fc4cc2 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -211,8 +211,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (!info->length)
 			continue;
 
-		if (mhp_supports_memmap_on_memory(info->length))
-			mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+		mhp_flags |= get_memmap_on_memory_flags();
 		result = __add_memory(mgid, info->start_addr, info->length,
 				      mhp_flags);
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 2387391ee93a..add3e7829c80 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -362,4 +362,18 @@ bool mhp_supports_memmap_on_memory(unsigned long size);
 bool __mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+extern bool memmap_on_memory;
+static inline unsigned long get_memmap_on_memory_flags(void)
+{
+	if (memmap_on_memory)
+		return MHP_MEMMAP_ON_MEMORY;
+	return 0;
+}
+#else
+static inline unsigned long get_memmap_on_memory_flags(void)
+{
+	return 0;
+}
+#endif
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 7cb112fb4996..9cfa6fa31df5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -46,19 +46,9 @@
 /*
  * memory_hotplug.memmap_on_memory parameter
  */
-static bool memmap_on_memory __ro_after_init;
+bool memmap_on_memory __ro_after_init;
 module_param(memmap_on_memory, bool, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
-
-static inline bool mhp_memmap_on_memory(void)
-{
-	return memmap_on_memory;
-}
-#else
-static inline bool mhp_memmap_on_memory(void)
-{
-	return false;
-}
 #endif
 
 enum {
@@ -1317,10 +1307,9 @@ bool __mhp_supports_memmap_on_memory(unsigned long size)
 	 *       altmap as an alternative source of memory, and we do not exactly
 	 *       populate a single PMD.
 	 */
-	return mhp_memmap_on_memory() &&
-	       size == memory_block_size_bytes() &&
-	       IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
-	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
+	return size == memory_block_size_bytes() &&
+		IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
+		IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
 }
 
 bool __weak mhp_supports_memmap_on_memory(unsigned long size)
-- 
2.41.0

[RFC PATCH 4/5] mm/hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig

[Aneesh Kumar K.V]

Instead of adding menu entry with all supported architectures, add
mm/Kconfig variable and select the same from supported architectures.

No functional change in this patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/arm64/Kconfig | 4 +---
 arch/x86/Kconfig   | 4 +---
 mm/Kconfig         | 3 +++
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 343e1e1cae10..20e909dac7ab 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -78,6 +78,7 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_MEMTEST
@@ -338,9 +339,6 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 config SMP
 	def_bool y
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb383960b6ee..c77c881e35da 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,6 +101,7 @@ config X86
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -2656,9 +2657,6 @@ config ARCH_HAS_ADD_PAGES
 	def_bool y
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
diff --git a/mm/Kconfig b/mm/Kconfig
index 7b388c10baab..4e5862c001e4 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -544,6 +544,9 @@ config MHP_MEMMAP_ON_MEMORY
 	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
 	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 
+config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
+       bool
+
 endif # MEMORY_HOTPLUG
 
 # Heavily threaded applications may benefit from splitting the mm-wide
-- 
2.41.0

[RFC PATCH 4/5] mm/hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig

[Aneesh Kumar K.V]

Instead of adding menu entry with all supported architectures, add
mm/Kconfig variable and select the same from supported architectures.

No functional change in this patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/arm64/Kconfig | 4 +---
 arch/x86/Kconfig   | 4 +---
 mm/Kconfig         | 3 +++
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 343e1e1cae10..20e909dac7ab 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -78,6 +78,7 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_MEMTEST
@@ -338,9 +339,6 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 config SMP
 	def_bool y
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb383960b6ee..c77c881e35da 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,6 +101,7 @@ config X86
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -2656,9 +2657,6 @@ config ARCH_HAS_ADD_PAGES
 	def_bool y
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
diff --git a/mm/Kconfig b/mm/Kconfig
index 7b388c10baab..4e5862c001e4 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -544,6 +544,9 @@ config MHP_MEMMAP_ON_MEMORY
 	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
 	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 
+config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
+       bool
+
 endif # MEMORY_HOTPLUG
 
 # Heavily threaded applications may benefit from splitting the mm-wide
-- 
2.41.0

[RFC PATCH 5/5] powerpc/book3s64/memhotplug: Enable memmap on memory for radix

[Aneesh Kumar K.V]

Radix vmemmap mapping can map things correctly at the PMD level or PTE
level based on different device boundary checks. We also use altmap.reserve
feature to align things correctly at pageblock granularity. We can end up
loosing some pages in memory with this. For ex: with 256MB memory block
size, we require 4 pages to map vmemmap pages, In order to align things
correctly we end up adding a reserve of 28 pages. ie, for every 4096 pages
28 pages get reserved.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/mm/book3s64/radix_pgtable.c      | 28 +++++++++++++++++++
 .../platforms/pseries/hotplug-memory.c        |  4 ++-
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6bd9ca6f2448..1b0954854a12 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -158,6 +158,7 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if PPC_RADIX_MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index afbae37612ad..e0e292b87b4b 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1692,3 +1692,31 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 
 	return 1;
 }
+
+/*
+ * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details
+ * some of the restrictions. We don't check for PMD_SIZE because our
+ * vmemmap allocation code can fallback correctly. The pageblock
+ * alignment requirement is met using altmap->reserve blocks.
+ */
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	if (!radix_enabled())
+		return false;
+	/*
+	 * The pageblock alignment requirement is met by using
+	 * reserve blocks in altmap.
+	 */
+	return size == memory_block_size_bytes();
+}
+
+unsigned long memory_block_align_base(struct resource *res)
+{
+	unsigned long base_pfn = PHYS_PFN(res->start);
+	unsigned long align, size = resource_size(res);
+	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
+	unsigned long vmemmap_size = (nr_vmemmap_pages * sizeof(struct page))/PAGE_SIZE;
+
+	align = pageblock_align(base_pfn + vmemmap_size) - (base_pfn + vmemmap_size);
+	return align;
+}
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9c62c2c3b3d0..326db26d773e 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -617,6 +617,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 
 static int dlpar_add_lmb(struct drmem_lmb *lmb)
 {
+	mhp_t mhp_flags = MHP_NONE;
 	unsigned long block_sz;
 	int nid, rc;
 
@@ -637,7 +638,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 		nid = first_online_node;
 
 	/* Add the memory */
-	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE);
+	mhp_flags |= get_memmap_on_memory_flags();
+	rc = __add_memory(nid, lmb->base_addr, block_sz, mhp_flags);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
-- 
2.41.0

[RFC PATCH 5/5] powerpc/book3s64/memhotplug: Enable memmap on memory for radix

[Aneesh Kumar K.V]

Radix vmemmap mapping can map things correctly at the PMD level or PTE
level based on different device boundary checks. We also use altmap.reserve
feature to align things correctly at pageblock granularity. We can end up
loosing some pages in memory with this. For ex: with 256MB memory block
size, we require 4 pages to map vmemmap pages, In order to align things
correctly we end up adding a reserve of 28 pages. ie, for every 4096 pages
28 pages get reserved.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/mm/book3s64/radix_pgtable.c      | 28 +++++++++++++++++++
 .../platforms/pseries/hotplug-memory.c        |  4 ++-
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6bd9ca6f2448..1b0954854a12 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -158,6 +158,7 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if PPC_RADIX_MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index afbae37612ad..e0e292b87b4b 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1692,3 +1692,31 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 
 	return 1;
 }
+
+/*
+ * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details
+ * some of the restrictions. We don't check for PMD_SIZE because our
+ * vmemmap allocation code can fallback correctly. The pageblock
+ * alignment requirement is met using altmap->reserve blocks.
+ */
+bool mhp_supports_memmap_on_memory(unsigned long size)
+{
+	if (!radix_enabled())
+		return false;
+	/*
+	 * The pageblock alignment requirement is met by using
+	 * reserve blocks in altmap.
+	 */
+	return size == memory_block_size_bytes();
+}
+
+unsigned long memory_block_align_base(struct resource *res)
+{
+	unsigned long base_pfn = PHYS_PFN(res->start);
+	unsigned long align, size = resource_size(res);
+	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
+	unsigned long vmemmap_size = (nr_vmemmap_pages * sizeof(struct page))/PAGE_SIZE;
+
+	align = pageblock_align(base_pfn + vmemmap_size) - (base_pfn + vmemmap_size);
+	return align;
+}
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9c62c2c3b3d0..326db26d773e 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -617,6 +617,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 
 static int dlpar_add_lmb(struct drmem_lmb *lmb)
 {
+	mhp_t mhp_flags = MHP_NONE;
 	unsigned long block_sz;
 	int nid, rc;
 
@@ -637,7 +638,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 		nid = first_online_node;
 
 	/* Add the memory */
-	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE);
+	mhp_flags |= get_memmap_on_memory_flags();
+	rc = __add_memory(nid, lmb->base_addr, block_sz, mhp_flags);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
-- 
2.41.0