1 files changed, 108 insertions, 69 deletions

diff --git a/mm/sparse.c b/mm/sparse.c
index c184b69460b7..1aee5a481571 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -209,6 +209,7 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 static void subsection_mask_set(unsigned long *map, unsigned long pfn,
 		unsigned long nr_pages)
 {
@@ -243,6 +244,11 @@ void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
 		nr_pages -= pfns;
 	}
 }
+#else
+void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
+{
+}
+#endif
 
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
@@ -660,39 +666,67 @@ static void free_map_bootmem(struct page *memmap)
 
 	vmemmap_free(start, end, NULL);
 }
-#else
-struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+
+static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
 {
-	struct page *page, *ret;
-	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
+	struct mem_section *ms = __pfn_to_section(pfn);
+	unsigned long *subsection_map = ms->usage
+		? &ms->usage->subsection_map[0] : NULL;
 
-	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
-	if (page)
-		goto got_map_page;
+	subsection_mask_set(map, pfn, nr_pages);
+	if (subsection_map)
+		bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
 
-	ret = vmalloc(memmap_size);
-	if (ret)
-		goto got_map_ptr;
+	if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
+				"section already deactivated (%#lx + %ld)\n",
+				pfn, nr_pages))
+		return -EINVAL;
 
-	return NULL;
-got_map_page:
-	ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
-got_map_ptr:
+	bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
+	return 0;
+}
 
-	return ret;
+static bool is_subsection_map_empty(struct mem_section *ms)
+{
+	return bitmap_empty(&ms->usage->subsection_map[0],
+			    SUBSECTIONS_PER_SECTION);
 }
 
-static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap)
+static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
 {
-	struct page *memmap = pfn_to_page(pfn);
+	struct mem_section *ms = __pfn_to_section(pfn);
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	unsigned long *subsection_map;
+	int rc = 0;
 
-	if (is_vmalloc_addr(memmap))
-		vfree(memmap);
+	subsection_mask_set(map, pfn, nr_pages);
+
+	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
-		free_pages((unsigned long)memmap,
-			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
+		bitmap_or(subsection_map, map, subsection_map,
+				SUBSECTIONS_PER_SECTION);
+
+	return rc;
+}
+#else
+struct page * __meminit populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+{
+	return kvmalloc_node(array_size(sizeof(struct page),
+					PAGES_PER_SECTION), GFP_KERNEL, nid);
+}
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap)
+{
+	kvfree(pfn_to_page(pfn));
 }
 
 static void free_map_bootmem(struct page *memmap)
@@ -724,47 +758,52 @@ static void free_map_bootmem(struct page *memmap)
 			put_page_bootmem(page);
 	}
 }
+
+static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+	return 0;
+}
+
+static bool is_subsection_map_empty(struct mem_section *ms)
+{
+	return true;
+}
+
+static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+	return 0;
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+/*
+ * To deactivate a memory region, 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
+ */
 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;
+	bool empty;
 
-	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))
+	if (clear_subsection_map(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)) {
+	empty = is_subsection_map_empty(ms);
+	if (empty) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
 		/*
@@ -779,43 +818,39 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 			ms->usage = NULL;
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		ms->section_mem_map = (unsigned long)NULL;
+		/*
+		 * Mark the section invalid so that valid_section()
+		 * return false. This prevents code from dereferencing
+		 * ms->usage array.
+		 */
+		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
 	}
 
 	if (section_is_early && memmap)
 		free_map_bootmem(memmap);
 	else
 		depopulate_section_memmap(pfn, nr_pages, altmap);
+
+	if (empty)
+		ms->section_mem_map = (unsigned long)NULL;
 }
 
 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);
 
+	rc = fill_subsection_map(pfn, nr_pages);
 	if (rc) {
 		if (usage)
 			ms->usage = NULL;
@@ -851,6 +886,10 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  *
  * This is only intended for hotplug.
  *
+ * Note that only VMEMMAP supports sub-section aligned hotplug,
+ * the proper alignment and size are gated by check_pfn_span().
+ *
+ *
  * Return:
  * * 0		- On success.
  * * -EEXIST	- Section has been present.
@@ -876,7 +915,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	 * Poison uninitialized struct pages in order to catch invalid flags
 	 * combinations.
 	 */
-	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+	page_init_poison(memmap, sizeof(struct page) * nr_pages);
 
 	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);
@@ -884,7 +923,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 
 	/* 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));
+		memmap = pfn_to_page(section_nr_to_pfn(section_nr));
 	sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
 
 	return 0;