1 files changed, 224 insertions, 131 deletions

diff --git a/mm/sparse.c b/mm/sparse.c
index fd13166949b5..72f010d9bff5 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -83,8 +83,15 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
 	struct mem_section *section;
 
+	/*
+	 * An existing section is possible in the sub-section hotplug
+	 * case. First hot-add instantiates, follow-on hot-add reuses
+	 * the existing section.
+	 *
+	 * The mem_hotplug_lock resolves the apparent race below.
+	 */
 	if (mem_section[root])
-		return -EEXIST;
+		return 0;
 
 	section = sparse_index_alloc(nid);
 	if (!section)
@@ -102,7 +109,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
 {
 	unsigned long root_nr;
 	struct mem_section *root = NULL;
@@ -121,9 +128,9 @@ int __section_nr(struct mem_section* ms)
 	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
 }
 #else
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
 {
-	return (int)(ms - mem_section[0]);
+	return (unsigned long)(ms - mem_section[0]);
 }
 #endif
 
@@ -178,10 +185,10 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
  * Keeping track of this gives us an easy way to break out of
  * those loops early.
  */
-int __highest_present_section_nr;
+unsigned long __highest_present_section_nr;
 static void section_mark_present(struct mem_section *ms)
 {
-	int section_nr = __section_nr(ms);
+	unsigned long section_nr = __section_nr(ms);
 
 	if (section_nr > __highest_present_section_nr)
 		__highest_present_section_nr = section_nr;
@@ -189,7 +196,7 @@ static void section_mark_present(struct mem_section *ms)
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 }
 
-static inline int next_present_section_nr(int section_nr)
+static inline unsigned long next_present_section_nr(unsigned long section_nr)
 {
 	do {
 		section_nr++;
@@ -210,6 +217,41 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
+void subsection_mask_set(unsigned long *map, unsigned long pfn,
+		unsigned long nr_pages)
+{
+	int idx = subsection_map_index(pfn);
+	int end = subsection_map_index(pfn + nr_pages - 1);
+
+	bitmap_set(map, idx, end - idx + 1);
+}
+
+void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
+{
+	int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+	unsigned long nr, start_sec = pfn_to_section_nr(pfn);
+
+	if (!nr_pages)
+		return;
+
+	for (nr = start_sec; nr <= end_sec; nr++) {
+		struct mem_section *ms;
+		unsigned long pfns;
+
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		ms = __nr_to_section(nr);
+		subsection_mask_set(ms->usage->subsection_map, pfn, pfns);
+
+		pr_debug("%s: sec: %lu pfns: %lu set(%d, %d)\n", __func__, nr,
+				pfns, subsection_map_index(pfn),
+				subsection_map_index(pfn + pfns - 1));
+
+		pfn += pfns;
+		nr_pages -= pfns;
+	}
+}
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -288,33 +330,31 @@ 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, unsigned long flags)
 {
 	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->section_mem_map |= sparse_encode_mem_map(mem_map, pnum)
+		| SECTION_HAS_MEM_MAP | flags;
+	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 +370,16 @@ 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 +393,7 @@ 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 +421,15 @@ 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 */
@@ -404,8 +446,8 @@ static unsigned long __init section_map_size(void)
 	return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
 }
 
-struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid,
-		struct vmem_altmap *altmap)
+struct page __init *__populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
 	unsigned long size = section_map_size();
 	struct page *map = sparse_buffer_alloc(size);
@@ -474,32 +516,35 @@ 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;
 	}
 	sparse_buffer_init(map_count * section_map_size(), nid);
 	for_each_present_section_nr(pnum_begin, pnum) {
+		unsigned long pfn = section_nr_to_pfn(pnum);
+
 		if (pnum >= pnum_end)
 			break;
 
-		map = sparse_mem_map_populate(pnum, nid, NULL);
+		map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
+				nid, NULL);
 		if (!map) {
 			pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
 			       __func__, nid);
 			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,
+				SECTION_IS_EARLY);
+		usage = (void *) usage + mem_section_usage_size();
 	}
 	sparse_buffer_fini();
 	return;
@@ -590,21 +635,20 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-		struct vmem_altmap *altmap)
+static struct page *populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
-	/* This will make the necessary allocations eventually. */
-	return sparse_mem_map_populate(pnum, nid, altmap);
+	return __populate_section_memmap(pfn, nr_pages, nid, altmap);
 }
-static void __kfree_section_memmap(struct page *memmap,
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
 		struct vmem_altmap *altmap)
 {
-	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+	unsigned long start = (unsigned long) pfn_to_page(pfn);
+	unsigned long end = start + nr_pages * sizeof(struct page);
 
 	vmemmap_free(start, end, altmap);
 }
-#ifdef CONFIG_MEMORY_HOTREMOVE
 static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
@@ -612,9 +656,9 @@ static void free_map_bootmem(struct page *memmap)
 
 	vmemmap_free(start, end, NULL);
 }
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 #else
-static struct page *__kmalloc_section_memmap(void)
+struct page *populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
 	struct page *page, *ret;
 	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
@@ -635,15 +679,11 @@ got_map_ptr:
 	return ret;
 }
 
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
 		struct vmem_altmap *altmap)
 {
-	return __kmalloc_section_memmap();
-}
+	struct page *memmap = pfn_to_page(pfn);
 
-static void __kfree_section_memmap(struct page *memmap,
-		struct vmem_altmap *altmap)
-{
 	if (is_vmalloc_addr(memmap))
 		vfree(memmap);
 	else
@@ -651,7 +691,6 @@ static void __kfree_section_memmap(struct page *memmap,
 			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
@@ -681,13 +720,122 @@ static void free_map_bootmem(struct page *memmap)
 			put_page_bootmem(page);
 	}
 }
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap)
+{
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
+	struct mem_section *ms = __pfn_to_section(pfn);
+	bool section_is_early = early_section(ms);
+	struct page *memmap = NULL;
+	unsigned long *subsection_map = ms->usage
+		? &ms->usage->subsection_map[0] : NULL;
+
+	subsection_mask_set(map, pfn, nr_pages);
+	if (subsection_map)
+		bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
+
+	if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
+				"section already deactivated (%#lx + %ld)\n",
+				pfn, nr_pages))
+		return;
+
+	/*
+	 * There are 3 cases to handle across two configurations
+	 * (SPARSEMEM_VMEMMAP={y,n}):
+	 *
+	 * 1/ deactivation of a partial hot-added section (only possible
+	 * in the SPARSEMEM_VMEMMAP=y case).
+	 *    a/ section was present at memory init
+	 *    b/ section was hot-added post memory init
+	 * 2/ deactivation of a complete hot-added section
+	 * 3/ deactivation of a complete section from memory init
+	 *
+	 * For 1/, when subsection_map does not empty we will not be
+	 * freeing the usage map, but still need to free the vmemmap
+	 * range.
+	 *
+	 * For 2/ and 3/ the SPARSEMEM_VMEMMAP={y,n} cases are unified
+	 */
+	bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
+	if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+
+		if (!section_is_early) {
+			kfree(ms->usage);
+			ms->usage = NULL;
+		}
+		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+		ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
+	}
+
+	if (section_is_early && memmap)
+		free_map_bootmem(memmap);
+	else
+		depopulate_section_memmap(pfn, nr_pages, altmap);
+}
+
+static struct page * __meminit section_activate(int nid, unsigned long pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap)
+{
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	struct mem_section *ms = __pfn_to_section(pfn);
+	struct mem_section_usage *usage = NULL;
+	unsigned long *subsection_map;
+	struct page *memmap;
+	int rc = 0;
+
+	subsection_mask_set(map, pfn, nr_pages);
+
+	if (!ms->usage) {
+		usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
+		if (!usage)
+			return ERR_PTR(-ENOMEM);
+		ms->usage = usage;
+	}
+	subsection_map = &ms->usage->subsection_map[0];
+
+	if (bitmap_empty(map, SUBSECTIONS_PER_SECTION))
+		rc = -EINVAL;
+	else if (bitmap_intersects(map, subsection_map, SUBSECTIONS_PER_SECTION))
+		rc = -EEXIST;
+	else
+		bitmap_or(subsection_map, map, subsection_map,
+				SUBSECTIONS_PER_SECTION);
+
+	if (rc) {
+		if (usage)
+			ms->usage = NULL;
+		kfree(usage);
+		return ERR_PTR(rc);
+	}
+
+	/*
+	 * The early init code does not consider partially populated
+	 * initial sections, it simply assumes that memory will never be
+	 * referenced.  If we hot-add memory into such a section then we
+	 * do not need to populate the memmap and can simply reuse what
+	 * is already there.
+	 */
+	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
+		return pfn_to_page(pfn);
+
+	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+	if (!memmap) {
+		section_deactivate(pfn, nr_pages, altmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return memmap;
+}
+
 /**
- * sparse_add_one_section - add a memory section
+ * sparse_add_section - add a memory section, or populate an existing one
  * @nid: The node to add section on
  * @start_pfn: start pfn of the memory range
+ * @nr_pages: number of pfns to add in the section
  * @altmap: device page map
  *
  * This is only intended for hotplug.
@@ -697,56 +845,40 @@ static void free_map_bootmem(struct page *memmap)
  * * -EEXIST	- Section has been present.
  * * -ENOMEM	- Out of memory.
  */
-int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
-				     struct vmem_altmap *altmap)
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct mem_section *ms;
 	struct page *memmap;
-	unsigned long *usemap;
 	int ret;
 
-	/*
-	 * no locking for this, because it does its own
-	 * plus, it does a kmalloc
-	 */
 	ret = sparse_index_init(section_nr, nid);
-	if (ret < 0 && ret != -EEXIST)
+	if (ret < 0)
 		return ret;
-	ret = 0;
-	memmap = kmalloc_section_memmap(section_nr, nid, altmap);
-	if (!memmap)
-		return -ENOMEM;
-	usemap = __kmalloc_section_usemap();
-	if (!usemap) {
-		__kfree_section_memmap(memmap, altmap);
-		return -ENOMEM;
-	}
 
-	ms = __pfn_to_section(start_pfn);
-	if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
-		ret = -EEXIST;
-		goto out;
-	}
+	memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+	if (IS_ERR(memmap))
+		return PTR_ERR(memmap);
 
 	/*
 	 * Poison uninitialized struct pages in order to catch invalid flags
 	 * combinations.
 	 */
-	page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION);
+	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
 
+	ms = __pfn_to_section(start_pfn);
+	set_section_nid(section_nr, nid);
 	section_mark_present(ms);
-	sparse_init_one_section(ms, section_nr, memmap, usemap);
 
-out:
-	if (ret < 0) {
-		kfree(usemap);
-		__kfree_section_memmap(memmap, altmap);
-	}
-	return ret;
+	/* Align memmap to section boundary in the subsection case */
+	if (section_nr_to_pfn(section_nr) != start_pfn)
+		memmap = pfn_to_kaddr(section_nr_to_pfn(section_nr));
+	sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
+
+	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 #ifdef CONFIG_MEMORY_FAILURE
 static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 {
@@ -777,51 +909,12 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 }
 #endif
 
-static void free_section_usemap(struct page *memmap, unsigned long *usemap,
+void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
+		unsigned long nr_pages, unsigned long map_offset,
 		struct vmem_altmap *altmap)
 {
-	struct page *usemap_page;
-
-	if (!usemap)
-		return;
-
-	usemap_page = virt_to_page(usemap);
-	/*
-	 * Check to see if allocation came from hot-plug-add
-	 */
-	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
-		kfree(usemap);
-		if (memmap)
-			__kfree_section_memmap(memmap, altmap);
-		return;
-	}
-
-	/*
-	 * The usemap came from bootmem. This is packed with other usemaps
-	 * on the section which has pgdat at boot time. Just keep it as is now.
-	 */
-
-	if (memmap)
-		free_map_bootmem(memmap);
-}
-
-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;
-
-	if (ms->section_mem_map) {
-		usemap = ms->pageblock_flags;
-		memmap = sparse_decode_mem_map(ms->section_mem_map,
-						__section_nr(ms));
-		ms->section_mem_map = 0;
-		ms->pageblock_flags = NULL;
-	}
-
-	clear_hwpoisoned_pages(memmap + map_offset,
-			PAGES_PER_SECTION - map_offset);
-	free_section_usemap(memmap, usemap, altmap);
+	clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+			nr_pages - map_offset);
+	section_deactivate(pfn, nr_pages, altmap);
 }
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif /* CONFIG_MEMORY_HOTPLUG */