ASR_BASE
Change-Id: Icf3719cc0afe3eeb3edc7fa80a2eb5199ca9dda1
diff --git a/marvell/linux/mm/sparse.c b/marvell/linux/mm/sparse.c
new file mode 100644
index 0000000..191e29c
--- /dev/null
+++ b/marvell/linux/mm/sparse.c
@@ -0,0 +1,947 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sparse memory mappings.
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/mmzone.h>
+#include <linux/memblock.h>
+#include <linux/compiler.h>
+#include <linux/highmem.h>
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
+#include "internal.h"
+#include <asm/dma.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+/*
+ * Permanent SPARSEMEM data:
+ *
+ * 1) mem_section - memory sections, mem_map's for valid memory
+ */
+#ifdef CONFIG_SPARSEMEM_EXTREME
+struct mem_section **mem_section;
+#else
+struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
+ ____cacheline_internodealigned_in_smp;
+#endif
+EXPORT_SYMBOL(mem_section);
+
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+/*
+ * If we did not store the node number in the page then we have to
+ * do a lookup in the section_to_node_table in order to find which
+ * node the page belongs to.
+ */
+#if MAX_NUMNODES <= 256
+static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#else
+static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#endif
+
+int page_to_nid(const struct page *page)
+{
+ return section_to_node_table[page_to_section(page)];
+}
+EXPORT_SYMBOL(page_to_nid);
+
+static void set_section_nid(unsigned long section_nr, int nid)
+{
+ section_to_node_table[section_nr] = nid;
+}
+#else /* !NODE_NOT_IN_PAGE_FLAGS */
+static inline void set_section_nid(unsigned long section_nr, int nid)
+{
+}
+#endif
+
+#ifdef CONFIG_SPARSEMEM_EXTREME
+static noinline struct mem_section __ref *sparse_index_alloc(int nid)
+{
+ struct mem_section *section = NULL;
+ unsigned long array_size = SECTIONS_PER_ROOT *
+ sizeof(struct mem_section);
+
+ if (slab_is_available()) {
+ section = kzalloc_node(array_size, GFP_KERNEL, nid);
+ } else {
+ section = memblock_alloc_node(array_size, SMP_CACHE_BYTES,
+ nid);
+ if (!section)
+ panic("%s: Failed to allocate %lu bytes nid=%d\n",
+ __func__, array_size, nid);
+ }
+
+ return section;
+}
+
+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 0;
+
+ section = sparse_index_alloc(nid);
+ if (!section)
+ return -ENOMEM;
+
+ mem_section[root] = section;
+
+ return 0;
+}
+#else /* !SPARSEMEM_EXTREME */
+static inline int sparse_index_init(unsigned long section_nr, int nid)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SPARSEMEM_EXTREME
+unsigned long __section_nr(struct mem_section *ms)
+{
+ unsigned long root_nr;
+ struct mem_section *root = NULL;
+
+ for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
+ root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
+ if (!root)
+ continue;
+
+ if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
+ break;
+ }
+
+ VM_BUG_ON(!root);
+
+ return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
+}
+#else
+unsigned long __section_nr(struct mem_section *ms)
+{
+ return (unsigned long)(ms - mem_section[0]);
+}
+#endif
+
+/*
+ * During early boot, before section_mem_map is used for an actual
+ * mem_map, we use section_mem_map to store the section's NUMA
+ * node. This keeps us from having to use another data structure. The
+ * node information is cleared just before we store the real mem_map.
+ */
+static inline unsigned long sparse_encode_early_nid(int nid)
+{
+ return (nid << SECTION_NID_SHIFT);
+}
+
+static inline int sparse_early_nid(struct mem_section *section)
+{
+ return (section->section_mem_map >> SECTION_NID_SHIFT);
+}
+
+/* Validate the physical addressing limitations of the model */
+void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
+ unsigned long *end_pfn)
+{
+ unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
+
+ /*
+ * Sanity checks - do not allow an architecture to pass
+ * in larger pfns than the maximum scope of sparsemem:
+ */
+ if (*start_pfn > max_sparsemem_pfn) {
+ mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+ "Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+ *start_pfn, *end_pfn, max_sparsemem_pfn);
+ WARN_ON_ONCE(1);
+ *start_pfn = max_sparsemem_pfn;
+ *end_pfn = max_sparsemem_pfn;
+ } else if (*end_pfn > max_sparsemem_pfn) {
+ mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+ "End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+ *start_pfn, *end_pfn, max_sparsemem_pfn);
+ WARN_ON_ONCE(1);
+ *end_pfn = max_sparsemem_pfn;
+ }
+}
+
+/*
+ * There are a number of times that we loop over NR_MEM_SECTIONS,
+ * looking for section_present() on each. But, when we have very
+ * large physical address spaces, NR_MEM_SECTIONS can also be
+ * very large which makes the loops quite long.
+ *
+ * Keeping track of this gives us an easy way to break out of
+ * those loops early.
+ */
+unsigned long __highest_present_section_nr;
+static void section_mark_present(struct mem_section *ms)
+{
+ unsigned long section_nr = __section_nr(ms);
+
+ if (section_nr > __highest_present_section_nr)
+ __highest_present_section_nr = section_nr;
+
+ ms->section_mem_map |= SECTION_MARKED_PRESENT;
+}
+
+static inline unsigned long next_present_section_nr(unsigned long section_nr)
+{
+ do {
+ section_nr++;
+ if (present_section_nr(section_nr))
+ return section_nr;
+ } while ((section_nr <= __highest_present_section_nr));
+
+ return -1;
+}
+#define for_each_present_section_nr(start, section_nr) \
+ for (section_nr = next_present_section_nr(start-1); \
+ ((section_nr != -1) && \
+ (section_nr <= __highest_present_section_nr)); \
+ section_nr = next_present_section_nr(section_nr))
+
+static inline unsigned long first_present_section_nr(void)
+{
+ return next_present_section_nr(-1);
+}
+
+static 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)
+{
+ unsigned long pfn;
+
+#ifdef CONFIG_SPARSEMEM_EXTREME
+ if (unlikely(!mem_section)) {
+ unsigned long size, align;
+
+ size = sizeof(struct mem_section*) * NR_SECTION_ROOTS;
+ align = 1 << (INTERNODE_CACHE_SHIFT);
+ mem_section = memblock_alloc(size, align);
+ if (!mem_section)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, size, align);
+ }
+#endif
+
+ start &= PAGE_SECTION_MASK;
+ mminit_validate_memmodel_limits(&start, &end);
+ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
+ unsigned long section = pfn_to_section_nr(pfn);
+ struct mem_section *ms;
+
+ sparse_index_init(section, nid);
+ set_section_nid(section, nid);
+
+ ms = __nr_to_section(section);
+ if (!ms->section_mem_map) {
+ ms->section_mem_map = sparse_encode_early_nid(nid) |
+ SECTION_IS_ONLINE;
+ section_mark_present(ms);
+ }
+ }
+}
+
+/*
+ * Mark all memblocks as present using memory_present(). This is a
+ * convienence function that is useful for a number of arches
+ * to mark all of the systems memory as present during initialization.
+ */
+void __init memblocks_present(void)
+{
+ struct memblock_region *reg;
+
+ for_each_memblock(memory, reg) {
+ memory_present(memblock_get_region_node(reg),
+ memblock_region_memory_base_pfn(reg),
+ memblock_region_memory_end_pfn(reg));
+ }
+}
+
+/*
+ * Subtle, we encode the real pfn into the mem_map such that
+ * the identity pfn - section_mem_map will return the actual
+ * physical page frame number.
+ */
+static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
+{
+ unsigned long coded_mem_map =
+ (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
+ BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<<PFN_SECTION_SHIFT));
+ BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
+ return coded_mem_map;
+}
+
+/*
+ * Decode mem_map from the coded memmap
+ */
+struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
+{
+ /* mask off the extra low bits of information */
+ coded_mem_map &= SECTION_MAP_MASK;
+ return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
+}
+
+static void __meminit sparse_init_one_section(struct mem_section *ms,
+ unsigned long pnum, struct page *mem_map,
+ 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 | flags;
+ ms->usage = usage;
+}
+
+static unsigned long usemap_size(void)
+{
+ return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
+}
+
+size_t mem_section_usage_size(void)
+{
+ return sizeof(struct mem_section_usage) + usemap_size();
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+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;
+ int nid;
+ /*
+ * A page may contain usemaps for other sections preventing the
+ * page being freed and making a section unremovable while
+ * other sections referencing the usemap remain active. Similarly,
+ * a pgdat can prevent a section being removed. If section A
+ * contains a pgdat and section B contains the usemap, both
+ * sections become inter-dependent. This allocates usemaps
+ * from the same section as the pgdat where possible to avoid
+ * this problem.
+ */
+ goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+ limit = goal + (1UL << PA_SECTION_SHIFT);
+ nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+ usage = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid);
+ if (!usage && limit) {
+ limit = 0;
+ goto again;
+ }
+ return usage;
+}
+
+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;
+ static unsigned long old_pgdat_snr;
+ struct pglist_data *pgdat = NODE_DATA(nid);
+ int usemap_nid;
+
+ /* First call */
+ if (!old_usemap_snr) {
+ old_usemap_snr = NR_MEM_SECTIONS;
+ old_pgdat_snr = NR_MEM_SECTIONS;
+ }
+
+ 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;
+
+ if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
+ /* skip redundant message */
+ return;
+
+ old_usemap_snr = usemap_snr;
+ old_pgdat_snr = pgdat_snr;
+
+ usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
+ if (usemap_nid != nid) {
+ pr_info("node %d must be removed before remove section %ld\n",
+ nid, usemap_snr);
+ return;
+ }
+ /*
+ * There is a circular dependency.
+ * Some platforms allow un-removable section because they will just
+ * gather other removable sections for dynamic partitioning.
+ * Just notify un-removable section's number here.
+ */
+ pr_info("Section %ld and %ld (node %d) have a circular dependency on usemap and pgdat allocations\n",
+ usemap_snr, pgdat_snr, nid);
+}
+#else
+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,
+ struct mem_section_usage *usage)
+{
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static unsigned long __init section_map_size(void)
+{
+ return ALIGN(sizeof(struct page) * PAGES_PER_SECTION, PMD_SIZE);
+}
+
+#else
+static unsigned long __init section_map_size(void)
+{
+ return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
+}
+
+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);
+ phys_addr_t addr = __pa(MAX_DMA_ADDRESS);
+
+ if (map)
+ return map;
+
+ map = memblock_alloc_try_nid(size,
+ PAGE_SIZE, addr,
+ MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+ if (!map)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n",
+ __func__, size, PAGE_SIZE, nid, &addr);
+
+ return map;
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+static void *sparsemap_buf __meminitdata;
+static void *sparsemap_buf_end __meminitdata;
+
+static inline void __meminit sparse_buffer_free(unsigned long size)
+{
+ WARN_ON(!sparsemap_buf || size == 0);
+ memblock_free_early(__pa(sparsemap_buf), size);
+}
+
+static void __init sparse_buffer_init(unsigned long size, int nid)
+{
+ phys_addr_t addr = __pa(MAX_DMA_ADDRESS);
+ WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */
+ sparsemap_buf =
+ memblock_alloc_try_nid_raw(size, PAGE_SIZE,
+ addr,
+ MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+ sparsemap_buf_end = sparsemap_buf + size;
+}
+
+static void __init sparse_buffer_fini(void)
+{
+ unsigned long size = sparsemap_buf_end - sparsemap_buf;
+
+ if (sparsemap_buf && size > 0)
+ sparse_buffer_free(size);
+ sparsemap_buf = NULL;
+}
+
+void * __meminit sparse_buffer_alloc(unsigned long size)
+{
+ void *ptr = NULL;
+
+ if (sparsemap_buf) {
+ ptr = (void *) roundup((unsigned long)sparsemap_buf, size);
+ if (ptr + size > sparsemap_buf_end)
+ ptr = NULL;
+ else {
+ /* Free redundant aligned space */
+ if ((unsigned long)(ptr - sparsemap_buf) > 0)
+ sparse_buffer_free((unsigned long)(ptr - sparsemap_buf));
+ sparsemap_buf = ptr + size;
+ }
+ }
+ return ptr;
+}
+
+void __weak __meminit vmemmap_populate_print_last(void)
+{
+}
+
+/*
+ * Initialize sparse on a specific node. The node spans [pnum_begin, pnum_end)
+ * And number of present sections in this node is map_count.
+ */
+static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
+ unsigned long pnum_end,
+ unsigned long map_count)
+{
+ struct mem_section_usage *usage;
+ unsigned long pnum;
+ struct page *map;
+
+ 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 = __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;
+ sparse_buffer_fini();
+ goto failed;
+ }
+ 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;
+failed:
+ /* We failed to allocate, mark all the following pnums as not present */
+ for_each_present_section_nr(pnum_begin, pnum) {
+ struct mem_section *ms;
+
+ if (pnum >= pnum_end)
+ break;
+ ms = __nr_to_section(pnum);
+ ms->section_mem_map = 0;
+ }
+}
+
+/*
+ * Allocate the accumulated non-linear sections, allocate a mem_map
+ * for each and record the physical to section mapping.
+ */
+void __init sparse_init(void)
+{
+ unsigned long pnum_begin = first_present_section_nr();
+ int nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
+ unsigned long pnum_end, map_count = 1;
+
+ /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
+ set_pageblock_order();
+
+ for_each_present_section_nr(pnum_begin + 1, pnum_end) {
+ int nid = sparse_early_nid(__nr_to_section(pnum_end));
+
+ if (nid == nid_begin) {
+ map_count++;
+ continue;
+ }
+ /* Init node with sections in range [pnum_begin, pnum_end) */
+ sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count);
+ nid_begin = nid;
+ pnum_begin = pnum_end;
+ map_count = 1;
+ }
+ /* cover the last node */
+ sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count);
+ vmemmap_populate_print_last();
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+/* Mark all memory sections within the pfn range as online */
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ unsigned long section_nr = pfn_to_section_nr(pfn);
+ struct mem_section *ms;
+
+ /* onlining code should never touch invalid ranges */
+ if (WARN_ON(!valid_section_nr(section_nr)))
+ continue;
+
+ ms = __nr_to_section(section_nr);
+ ms->section_mem_map |= SECTION_IS_ONLINE;
+ }
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/* Mark all memory sections within the pfn range as offline */
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ unsigned long section_nr = pfn_to_section_nr(pfn);
+ struct mem_section *ms;
+
+ /*
+ * TODO this needs some double checking. Offlining code makes
+ * sure to check pfn_valid but those checks might be just bogus
+ */
+ if (WARN_ON(!valid_section_nr(section_nr)))
+ continue;
+
+ ms = __nr_to_section(section_nr);
+ ms->section_mem_map &= ~SECTION_IS_ONLINE;
+ }
+}
+#endif
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static struct page * __meminit populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+{
+ return __populate_section_memmap(pfn, nr_pages, nid, altmap);
+}
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
+{
+ unsigned long start = (unsigned long) pfn_to_page(pfn);
+ unsigned long end = start + nr_pages * sizeof(struct page);
+
+ vmemmap_free(start, end, altmap);
+}
+static void free_map_bootmem(struct page *memmap)
+{
+ unsigned long start = (unsigned long)memmap;
+ unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+
+ 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)
+{
+ struct page *page, *ret;
+ unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
+
+ page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
+ if (page)
+ goto got_map_page;
+
+ ret = vmalloc(memmap_size);
+ if (ret)
+ goto got_map_ptr;
+
+ return NULL;
+got_map_page:
+ ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
+got_map_ptr:
+
+ return ret;
+}
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
+{
+ struct page *memmap = pfn_to_page(pfn);
+
+ if (is_vmalloc_addr(memmap))
+ vfree(memmap);
+ else
+ free_pages((unsigned long)memmap,
+ get_order(sizeof(struct page) * PAGES_PER_SECTION));
+}
+
+static void free_map_bootmem(struct page *memmap)
+{
+ unsigned long maps_section_nr, removing_section_nr, i;
+ unsigned long magic, nr_pages;
+ struct page *page = virt_to_page(memmap);
+
+ nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
+ >> PAGE_SHIFT;
+
+ for (i = 0; i < nr_pages; i++, page++) {
+ magic = (unsigned long) page->freelist;
+
+ BUG_ON(magic == NODE_INFO);
+
+ maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
+ removing_section_nr = page_private(page);
+
+ /*
+ * When this function is called, the removing section is
+ * logical offlined state. This means all pages are isolated
+ * from page allocator. If removing section's memmap is placed
+ * on the same section, it must not be freed.
+ * If it is freed, page allocator may allocate it which will
+ * be removed physically soon.
+ */
+ if (maps_section_nr != removing_section_nr)
+ put_page_bootmem(page);
+ }
+}
+#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;
+ bool empty;
+ 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);
+ empty = bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION);
+ if (empty) {
+ unsigned long section_nr = pfn_to_section_nr(pfn);
+
+ /*
+ * When removing an early section, the usage map is kept (as the
+ * usage maps of other sections fall into the same page). It
+ * will be re-used when re-adding the section - which is then no
+ * longer an early section. If the usage map is PageReserved, it
+ * was allocated during boot.
+ */
+ if (!PageReserved(virt_to_page(ms->usage))) {
+ kfree(ms->usage);
+ ms->usage = NULL;
+ }
+ memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+ /*
+ * 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);
+
+ 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_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.
+ *
+ * Return:
+ * * 0 - On success.
+ * * -EEXIST - Section has been present.
+ * * -ENOMEM - Out of memory.
+ */
+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;
+ int ret;
+
+ ret = sparse_index_init(section_nr, nid);
+ if (ret < 0)
+ return ret;
+
+ 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) * nr_pages);
+
+ ms = __nr_to_section(section_nr);
+ set_section_nid(section_nr, nid);
+ section_mark_present(ms);
+
+ /* 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
+static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+ int i;
+
+ /*
+ * A further optimization is to have per section refcounted
+ * num_poisoned_pages. But that would need more space per memmap, so
+ * for now just do a quick global check to speed up this routine in the
+ * absence of bad pages.
+ */
+ if (atomic_long_read(&num_poisoned_pages) == 0)
+ return;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (PageHWPoison(&memmap[i])) {
+ num_poisoned_pages_dec();
+ ClearPageHWPoison(&memmap[i]);
+ }
+ }
+}
+#else
+static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+}
+#endif
+
+void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
+ unsigned long nr_pages, unsigned long map_offset,
+ struct vmem_altmap *altmap)
+{
+ clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+ nr_pages - map_offset);
+ section_deactivate(pfn, nr_pages, altmap);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */