[PATCH v6 01/12] mm/sparsemem: Introduce struct mem_section_usage

[Dan Williams]

Towards enabling memory hotplug to track partial population of a
section, introduce 'struct mem_section_usage'.

A pointer to a 'struct mem_section_usage' instance replaces the existing
pointer to a 'pageblock_flags' bitmap. Effectively it adds one more
'unsigned long' beyond the 'pageblock_flags' (usemap) allocation to
house a new 'map_active' bitmap.  The new bitmap enables the memory
hot{plug,remove} implementation to act on incremental sub-divisions of a
section.

The primary motivation for this functionality is to support platforms
that mix "System RAM" and "Persistent Memory" within a single section,
or multiple PMEM ranges with different mapping lifetimes within a single
section. The section restriction for hotplug has caused an ongoing saga
of hacks and bugs for devm_memremap_pages() users.

Beyond the fixups to teach existing paths how to retrieve the 'usemap'
from a section, and updates to usemap allocation path, there are no
expected behavior changes.

Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
 include/linux/mmzone.h |   23 ++++++++++++--
 mm/memory_hotplug.c    |   18 ++++++-----
 mm/page_alloc.c        |    2 +
 mm/sparse.c            |   81 ++++++++++++++++++++++++------------------------
 4 files changed, 71 insertions(+), 53 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 70394cabaf4e..f0bbd85dc19a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1160,6 +1160,19 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SECTION_ALIGN_UP(pfn)	(((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
+#define SECTION_ACTIVE_SIZE ((1UL << SECTION_SIZE_BITS) / BITS_PER_LONG)
+#define SECTION_ACTIVE_MASK (~(SECTION_ACTIVE_SIZE - 1))
+
+struct mem_section_usage {
+	/*
+	 * SECTION_ACTIVE_SIZE portions of the section that are populated in
+	 * the memmap
+	 */
+	unsigned long map_active;
+	/* See declaration of similar field in struct zone */
+	unsigned long pageblock_flags[0];
+};
+
 struct page;
 struct page_ext;
 struct mem_section {
@@ -1177,8 +1190,7 @@ struct mem_section {
 	 */
 	unsigned long section_mem_map;
 
-	/* See declaration of similar field in struct zone */
-	unsigned long *pageblock_flags;
+	struct mem_section_usage *usage;
 #ifdef CONFIG_PAGE_EXTENSION
 	/*
 	 * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use
@@ -1209,6 +1221,11 @@ extern struct mem_section **mem_section;
 extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
 #endif
 
+static inline unsigned long *section_to_usemap(struct mem_section *ms)
+{
+	return ms->usage->pageblock_flags;
+}
+
 static inline struct mem_section *__nr_to_section(unsigned long nr)
 {
 #ifdef CONFIG_SPARSEMEM_EXTREME
@@ -1220,7 +1237,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
 extern int __section_nr(struct mem_section* ms);
-extern unsigned long usemap_size(void);
+extern size_t mem_section_usage_size(void);
 
 /*
  * We use the lower bits of the mem_map pointer to store
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 52fef4a81e4c..8b7415736d21 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -165,9 +165,10 @@ void put_page_bootmem(struct page *page)
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
-	unsigned long *usemap, mapsize, section_nr, i;
+	unsigned long mapsize, section_nr, i;
 	struct mem_section *ms;
 	struct page *page, *memmap;
+	struct mem_section_usage *usage;
 
 	section_nr = pfn_to_section_nr(start_pfn);
 	ms = __nr_to_section(section_nr);
@@ -187,10 +188,10 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 	for (i = 0; i < mapsize; i++, page++)
 		get_page_bootmem(section_nr, page, SECTION_INFO);
 
-	usemap = ms->pageblock_flags;
-	page = virt_to_page(usemap);
+	usage = ms->usage;
+	page = virt_to_page(usage);
 
-	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
 
 	for (i = 0; i < mapsize; i++, page++)
 		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
@@ -199,9 +200,10 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 #else /* CONFIG_SPARSEMEM_VMEMMAP */
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
-	unsigned long *usemap, mapsize, section_nr, i;
+	unsigned long mapsize, section_nr, i;
 	struct mem_section *ms;
 	struct page *page, *memmap;
+	struct mem_section_usage *usage;
 
 	section_nr = pfn_to_section_nr(start_pfn);
 	ms = __nr_to_section(section_nr);
@@ -210,10 +212,10 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 
 	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
 
-	usemap = ms->pageblock_flags;
-	page = virt_to_page(usemap);
+	usage = ms->usage;
+	page = virt_to_page(usage);
 
-	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
 
 	for (i = 0; i < mapsize; i++, page++)
 		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index deea16489e2b..f671401a7c0b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -390,7 +390,7 @@ static inline unsigned long *get_pageblock_bitmap(struct page *page,
 							unsigned long pfn)
 {
 #ifdef CONFIG_SPARSEMEM
-	return __pfn_to_section(pfn)->pageblock_flags;
+	return section_to_usemap(__pfn_to_section(pfn));
 #else
 	return page_zone(page)->pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
diff --git a/mm/sparse.c b/mm/sparse.c
index fd13166949b5..f87de7ad32c8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -288,33 +288,31 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 
 static void __meminit sparse_init_one_section(struct mem_section *ms,
 		unsigned long pnum, struct page *mem_map,
-		unsigned long *pageblock_bitmap)
+		struct mem_section_usage *usage)
 {
 	ms->section_mem_map &= ~SECTION_MAP_MASK;
 	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
 							SECTION_HAS_MEM_MAP;
- 	ms->pageblock_flags = pageblock_bitmap;
+	ms->usage = usage;
 }
 
-unsigned long usemap_size(void)
+static unsigned long usemap_size(void)
 {
 	return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static unsigned long *__kmalloc_section_usemap(void)
+size_t mem_section_usage_size(void)
 {
-	return kmalloc(usemap_size(), GFP_KERNEL);
+	return sizeof(struct mem_section_usage) + usemap_size();
 }
-#endif /* CONFIG_MEMORY_HOTPLUG */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static unsigned long * __init
+static struct mem_section_usage * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
+	struct mem_section_usage *usage;
 	unsigned long goal, limit;
-	unsigned long *p;
 	int nid;
 	/*
 	 * A page may contain usemaps for other sections preventing the
@@ -330,15 +328,16 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	limit = goal + (1UL << PA_SECTION_SHIFT);
 	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
 again:
-	p = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid);
-	if (!p && limit) {
+	usage = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid);
+	if (!usage && limit) {
 		limit = 0;
 		goto again;
 	}
-	return p;
+	return usage;
 }
 
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+		struct mem_section_usage *usage)
 {
 	unsigned long usemap_snr, pgdat_snr;
 	static unsigned long old_usemap_snr;
@@ -352,7 +351,7 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 		old_pgdat_snr = NR_MEM_SECTIONS;
 	}
 
-	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
+	usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT);
 	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
 	if (usemap_snr == pgdat_snr)
 		return;
@@ -380,14 +379,15 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 		usemap_snr, pgdat_snr, nid);
 }
 #else
-static unsigned long * __init
+static struct mem_section_usage * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
 	return memblock_alloc_node(size, SMP_CACHE_BYTES, pgdat->node_id);
 }
 
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+		struct mem_section_usage *usage)
 {
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
@@ -474,14 +474,13 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 				   unsigned long pnum_end,
 				   unsigned long map_count)
 {
-	unsigned long pnum, usemap_longs, *usemap;
+	struct mem_section_usage *usage;
+	unsigned long pnum;
 	struct page *map;
 
-	usemap_longs = BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS);
-	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid),
-							  usemap_size() *
-							  map_count);
-	if (!usemap) {
+	usage = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid),
+			mem_section_usage_size() * map_count);
+	if (!usage) {
 		pr_err("%s: node[%d] usemap allocation failed", __func__, nid);
 		goto failed;
 	}
@@ -497,9 +496,9 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 			pnum_begin = pnum;
 			goto failed;
 		}
-		check_usemap_section_nr(nid, usemap);
-		sparse_init_one_section(__nr_to_section(pnum), pnum, map, usemap);
-		usemap += usemap_longs;
+		check_usemap_section_nr(nid, usage);
+		sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage);
+		usage = (void *) usage + mem_section_usage_size();
 	}
 	sparse_buffer_fini();
 	return;
@@ -701,9 +700,9 @@ int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
 				     struct vmem_altmap *altmap)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
+	struct mem_section_usage *usage;
 	struct mem_section *ms;
 	struct page *memmap;
-	unsigned long *usemap;
 	int ret;
 
 	/*
@@ -717,8 +716,8 @@ int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
 	memmap = kmalloc_section_memmap(section_nr, nid, altmap);
 	if (!memmap)
 		return -ENOMEM;
-	usemap = __kmalloc_section_usemap();
-	if (!usemap) {
+	usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
+	if (!usage) {
 		__kfree_section_memmap(memmap, altmap);
 		return -ENOMEM;
 	}
@@ -736,11 +735,11 @@ int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
 	page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION);
 
 	section_mark_present(ms);
-	sparse_init_one_section(ms, section_nr, memmap, usemap);
+	sparse_init_one_section(ms, section_nr, memmap, usage);
 
 out:
 	if (ret < 0) {
-		kfree(usemap);
+		kfree(usage);
 		__kfree_section_memmap(memmap, altmap);
 	}
 	return ret;
@@ -777,20 +776,20 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 }
 #endif
 
-static void free_section_usemap(struct page *memmap, unsigned long *usemap,
-		struct vmem_altmap *altmap)
+static void free_section_usage(struct page *memmap,
+		struct mem_section_usage *usage, struct vmem_altmap *altmap)
 {
-	struct page *usemap_page;
+	struct page *usage_page;
 
-	if (!usemap)
+	if (!usage)
 		return;
 
-	usemap_page = virt_to_page(usemap);
+	usage_page = virt_to_page(usage);
 	/*
 	 * Check to see if allocation came from hot-plug-add
 	 */
-	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
-		kfree(usemap);
+	if (PageSlab(usage_page) || PageCompound(usage_page)) {
+		kfree(usage);
 		if (memmap)
 			__kfree_section_memmap(memmap, altmap);
 		return;
@@ -809,19 +808,19 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
 		unsigned long map_offset, struct vmem_altmap *altmap)
 {
 	struct page *memmap = NULL;
-	unsigned long *usemap = NULL;
+	struct mem_section_usage *usage = NULL;
 
 	if (ms->section_mem_map) {
-		usemap = ms->pageblock_flags;
+		usage = ms->usage;
 		memmap = sparse_decode_mem_map(ms->section_mem_map,
 						__section_nr(ms));
 		ms->section_mem_map = 0;
-		ms->pageblock_flags = NULL;
+		ms->usage = NULL;
 	}
 
 	clear_hwpoisoned_pages(memmap + map_offset,
 			PAGES_PER_SECTION - map_offset);
-	free_section_usemap(memmap, usemap, altmap);
+	free_section_usage(memmap, usage, altmap);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif /* CONFIG_MEMORY_HOTPLUG */