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)
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)
{
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);
}
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);
#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);
}
vmemmap_free(start, end, NULL);
}
#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;
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
}
#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.
* * -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_usage *usage;
struct mem_section *ms;
struct page *memmap;
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;
- usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
- if (!usage) {
- __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, usage, 0);
-out:
- if (ret < 0) {
- kfree(usage);
- __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_FAILURE
}
#endif
-static void free_section_usage(struct mem_section *ms, struct page *memmap,
- struct mem_section_usage *usage, struct vmem_altmap *altmap)
-{
- if (!usage)
- return;
-
- /*
- * Check to see if allocation came from hot-plug-add
- */
- if (!early_section(ms)) {
- kfree(usage);
- 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 mem_section *ms, unsigned long map_offset,
- struct vmem_altmap *altmap)
+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 *memmap = NULL;
- struct mem_section_usage *usage = NULL;
-
- if (ms->section_mem_map) {
- usage = ms->usage;
- memmap = sparse_decode_mem_map(ms->section_mem_map,
- __section_nr(ms));
- ms->section_mem_map = 0;
- ms->usage = NULL;
- }
-
- clear_hwpoisoned_pages(memmap + map_offset,
- PAGES_PER_SECTION - map_offset);
- free_section_usage(ms, memmap, usage, altmap);
+ clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+ nr_pages - map_offset);
+ section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */