mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks

Currently, memmap_on_memory feature is only supported with memory block
sizes that result in vmemmap pages covering full page blocks.  This is
because memory onlining/offlining code requires applicable ranges to be
pageblock-aligned, for example, to set the migratetypes properly.

This patch helps to lift that restriction by reserving more pages than
required for vmemmap space.  This helps the start address to be page block
aligned with different memory block sizes.  Using this facility implies
the kernel will be reserving some pages for every memoryblock.  This
allows the memmap on memory feature to be widely useful with different
memory block size values.

For ex: with 64K page size and 256MiB memory block size, we require 4
pages to map vmemmap pages, To align things correctly we end up adding a
reserve of 28 pages.  ie, for every 4096 pages 28 pages get reserved.

Link: https://lkml.kernel.org/r/20230808091501.287660-5-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 113 insertions, 19 deletions

diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst
index bd77841041af..2994958c7ce8 100644
--- a/Documentation/admin-guide/mm/memory-hotplug.rst
+++ b/Documentation/admin-guide/mm/memory-hotplug.rst
@@ -433,6 +433,18 @@ The following module parameters are currently defined:
 				 memory in a way that huge pages in bigger
 				 granularity cannot be formed on hotplugged
 				 memory.
+
+				 With value "force" it could result in memory
+				 wastage due to memmap size limitations. For
+				 example, if the memmap for a memory block
+				 requires 1 MiB, but the pageblock size is 2
+				 MiB, 1 MiB of hotplugged memory will be wasted.
+				 Note that there are still cases where the
+				 feature cannot be enforced: for example, if the
+				 memmap is smaller than a single page, or if the
+				 architecture does not support the forced mode
+				 in all configurations.
+
 ``online_policy``		 read-write: Set the basic policy used for
 				 automatic zone selection when onlining memory
 				 blocks without specifying a target zone.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 746cb7c08c64..76b813991bdc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -41,17 +41,83 @@
 #include "internal.h"
 #include "shuffle.h"
 
+enum {
+	MEMMAP_ON_MEMORY_DISABLE = 0,
+	MEMMAP_ON_MEMORY_ENABLE,
+	MEMMAP_ON_MEMORY_FORCE,
+};
+
+static int memmap_mode __read_mostly = MEMMAP_ON_MEMORY_DISABLE;
+
+static inline unsigned long memory_block_memmap_size(void)
+{
+	return PHYS_PFN(memory_block_size_bytes()) * sizeof(struct page);
+}
+
+static inline unsigned long memory_block_memmap_on_memory_pages(void)
+{
+	unsigned long nr_pages = PFN_UP(memory_block_memmap_size());
+
+	/*
+	 * In "forced" memmap_on_memory mode, we add extra pages to align the
+	 * vmemmap size to cover full pageblocks. That way, we can add memory
+	 * even if the vmemmap size is not properly aligned, however, we might waste
+	 * memory.
+	 */
+	if (memmap_mode == MEMMAP_ON_MEMORY_FORCE)
+		return pageblock_align(nr_pages);
+	return nr_pages;
+}
+
 #ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
 /*
  * memory_hotplug.memmap_on_memory parameter
  */
-static 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 int set_memmap_mode(const char *val, const struct kernel_param *kp)
+{
+	int ret, mode;
+	bool enabled;
+
+	if (sysfs_streq(val, "force") ||  sysfs_streq(val, "FORCE")) {
+		mode = MEMMAP_ON_MEMORY_FORCE;
+	} else {
+		ret = kstrtobool(val, &enabled);
+		if (ret < 0)
+			return ret;
+		if (enabled)
+			mode = MEMMAP_ON_MEMORY_ENABLE;
+		else
+			mode = MEMMAP_ON_MEMORY_DISABLE;
+	}
+	*((int *)kp->arg) = mode;
+	if (mode == MEMMAP_ON_MEMORY_FORCE) {
+		unsigned long memmap_pages = memory_block_memmap_on_memory_pages();
+
+		pr_info_once("Memory hotplug will waste %ld pages in each memory block\n",
+			     memmap_pages - PFN_UP(memory_block_memmap_size()));
+	}
+	return 0;
+}
+
+static int get_memmap_mode(char *buffer, const struct kernel_param *kp)
+{
+	if (*((int *)kp->arg) == MEMMAP_ON_MEMORY_FORCE)
+		return sprintf(buffer,  "force\n");
+	return param_get_bool(buffer, kp);
+}
+
+static const struct kernel_param_ops memmap_mode_ops = {
+	.set = set_memmap_mode,
+	.get = get_memmap_mode,
+};
+module_param_cb(memmap_on_memory, &memmap_mode_ops, &memmap_mode, 0444);
+MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug\n"
+		 "With value \"force\" it could result in memory wastage due "
+		 "to memmap size limitations (Y/N/force)");
 
 static inline bool mhp_memmap_on_memory(void)
 {
-	return memmap_on_memory;
+	return memmap_mode != MEMMAP_ON_MEMORY_DISABLE;
 }
 #else
 static inline bool mhp_memmap_on_memory(void)
@@ -1247,11 +1313,6 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	return device_online(&mem->dev);
 }
 
-static inline unsigned long memory_block_memmap_size(void)
-{
-	return PHYS_PFN(memory_block_size_bytes()) * sizeof(struct page);
-}
-
 #ifndef arch_supports_memmap_on_memory
 static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
 {
@@ -1267,7 +1328,7 @@ static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
 static bool mhp_supports_memmap_on_memory(unsigned long size)
 {
 	unsigned long vmemmap_size = memory_block_memmap_size();
-	unsigned long remaining_size = size - vmemmap_size;
+	unsigned long memmap_pages = memory_block_memmap_on_memory_pages();
 
 	/*
 	 * Besides having arch support and the feature enabled at runtime, we
@@ -1295,10 +1356,28 @@ 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() &&
-	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)) &&
-	       arch_supports_memmap_on_memory(vmemmap_size);
+	if (!mhp_memmap_on_memory() || size != memory_block_size_bytes())
+		return false;
+
+	/*
+	 * Make sure the vmemmap allocation is fully contained
+	 * so that we always allocate vmemmap memory from altmap area.
+	 */
+	if (!IS_ALIGNED(vmemmap_size, PAGE_SIZE))
+		return false;
+
+	/*
+	 * start pfn should be pageblock_nr_pages aligned for correctly
+	 * setting migrate types
+	 */
+	if (!pageblock_aligned(memmap_pages))
+		return false;
+
+	if (memmap_pages == PHYS_PFN(memory_block_size_bytes()))
+		/* No effective hotplugged memory doesn't make sense. */
+		return false;
+
+	return arch_supports_memmap_on_memory(vmemmap_size);
 }
 
 /*
@@ -1311,7 +1390,10 @@ 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),
+	};
 	struct memory_group *group = NULL;
 	u64 start, size;
 	bool new_node = false;
@@ -1356,8 +1438,7 @@ 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 = memory_block_memmap_on_memory_pages();
 			params.altmap = &mhp_altmap;
 		}
 		/* fallback to not using altmap  */
@@ -1369,8 +1450,7 @@ 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,
-					  group);
+	ret = create_memory_block_devices(start, size, mhp_altmap.free, group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
 		goto error;
@@ -2096,6 +2176,8 @@ static int __ref try_remove_memory(u64 start, u64 size)
 			 * right thing if we used vmem_altmap when hot-adding
 			 * the range.
 			 */
+			mhp_altmap.base_pfn = PHYS_PFN(start);
+			mhp_altmap.free = nr_vmemmap_pages;
 			mhp_altmap.alloc = nr_vmemmap_pages;
 			altmap = &mhp_altmap;
 		}