[PATCH v3 4/7] mm/hotplug: Allow pageblock alignment via altmap reservation

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

Add a new kconfig option that can be selected if we want to allow
pageblock alignment by reserving pages in the vmemmap altmap area.
This implies we will be reserving some pages for every memoryblock
This also allows the memmap on memory feature to be widely useful
with different memory block size values.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 mm/Kconfig          |  9 +++++++
 mm/memory_hotplug.c | 59 +++++++++++++++++++++++++++++++++++++--------
 2 files changed, 58 insertions(+), 10 deletions(-)

diff --git a/mm/Kconfig b/mm/Kconfig
index 932349271e28..88a1472b2086 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -570,6 +570,15 @@ config MHP_MEMMAP_ON_MEMORY
 	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
 	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 
+config MHP_RESERVE_PAGES_MEMMAP_ON_MEMORY
+       bool "Allow Reserving pages for page block aligment"
+       depends on MHP_MEMMAP_ON_MEMORY
+       help
+	This option allows memmap on memory feature to be more useful
+	with different memory block sizes. This is achieved by marking some pages
+	in each memory block as reserved so that we can get page-block alignment
+	for the remaining pages.
+
 endif # MEMORY_HOTPLUG
 
 config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 07c99b0cc371..f36aec1f7626 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1252,15 +1252,17 @@ static inline bool arch_supports_memmap_on_memory(unsigned long size)
 {
 	unsigned long nr_vmemmap_pages = size >> PAGE_SHIFT;
 	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
-	unsigned long remaining_size = size - vmemmap_size;
 
-	return IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
-		IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
+	return IS_ALIGNED(vmemmap_size, PMD_SIZE);
 }
 #endif
 
 static bool mhp_supports_memmap_on_memory(unsigned long size)
 {
+	unsigned long nr_vmemmap_pages = size >> PAGE_SHIFT;
+	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
+	unsigned long remaining_size = size - vmemmap_size;
+
 	/*
 	 * Besides having arch support and the feature enabled at runtime, we
 	 * need a few more assumptions to hold true:
@@ -1287,9 +1289,30 @@ static 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() &&
-		arch_supports_memmap_on_memory(size);
+	if (!mhp_memmap_on_memory() || size != memory_block_size_bytes())
+		return false;
+	 /*
+	  * Without page reservation remaining pages should be pageblock aligned.
+	  */
+	if (!IS_ENABLED(CONFIG_MHP_RESERVE_PAGES_MEMMAP_ON_MEMORY) &&
+	    !IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)))
+		return false;
+
+	return arch_supports_memmap_on_memory(size);
+}
+
+static inline unsigned long memory_block_align_base(unsigned long size)
+{
+	if (IS_ENABLED(CONFIG_MHP_RESERVE_PAGES_MEMMAP_ON_MEMORY)) {
+		unsigned long align;
+		unsigned long nr_vmemmap_pages = size >> PAGE_SHIFT;
+		unsigned long vmemmap_size;
+
+		vmemmap_size = (nr_vmemmap_pages * sizeof(struct page)) >> PAGE_SHIFT;
+		align = pageblock_align(vmemmap_size) - vmemmap_size;
+		return align;
+	} else
+		return 0;
 }
 
 /*
@@ -1302,7 +1325,11 @@ 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(resource_size(res)),
+	};
 	struct memory_group *group = NULL;
 	u64 start, size;
 	bool new_node = false;
@@ -1347,8 +1374,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	 */
 	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
 		if (mhp_supports_memmap_on_memory(size)) {
-			mhp_altmap.free = PHYS_PFN(size);
-			mhp_altmap.base_pfn = PHYS_PFN(start);
+			mhp_altmap.free = PHYS_PFN(size) - mhp_altmap.reserve;
 			params.altmap = &mhp_altmap;
 		}
 		/* fallback to not using altmap  */
@@ -1360,7 +1386,7 @@ 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.alloc + mhp_altmap.reserve,
 					  group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
@@ -2260,3 +2286,16 @@ int offline_and_remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(offline_and_remove_memory);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
+
+static int __init memory_hotplug_init(void)
+{
+
+	if (IS_ENABLED(CONFIG_MHP_RESERVE_PAGES_MEMMAP_ON_MEMORY) &&
+	    mhp_memmap_on_memory()) {
+		pr_info("Memory hotplug will reserve %ld pages in each memory block\n",
+			memory_block_align_base(memory_block_size_bytes()));
+
+	}
+	return 0;
+}
+module_init(memory_hotplug_init);
-- 
2.41.0