summaryrefslogtreecommitdiff
path: root/mm/sparse.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/sparse.c')
-rw-r--r--mm/sparse.c544
1 files changed, 8 insertions, 536 deletions
diff --git a/mm/sparse.c b/mm/sparse.c
index b5b2b6f7041b..007fd52c621e 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -79,7 +79,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid)
return section;
}
-static int __meminit sparse_index_init(unsigned long section_nr, int nid)
+int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
struct mem_section *section;
@@ -103,7 +103,7 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
return 0;
}
#else /* !SPARSEMEM_EXTREME */
-static inline int sparse_index_init(unsigned long section_nr, int nid)
+int sparse_index_init(unsigned long section_nr, int nid)
{
return 0;
}
@@ -161,58 +161,12 @@ static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
* those loops early.
*/
unsigned long __highest_present_section_nr;
-static void __section_mark_present(struct mem_section *ms,
- unsigned long section_nr)
-{
- if (section_nr > __highest_present_section_nr)
- __highest_present_section_nr = section_nr;
-
- ms->section_mem_map |= SECTION_MARKED_PRESENT;
-}
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)
-{
- 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_nr = pfn_to_section_nr(pfn + nr_pages - 1);
- unsigned long nr, start_sec_nr = pfn_to_section_nr(pfn);
-
- for (nr = start_sec_nr; nr <= end_sec_nr; 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;
- }
-}
-#else
-void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
-{
-}
-#endif
-
/* Record a memory area against a node. */
static void __init memory_present(int nid, unsigned long start, unsigned long end)
{
@@ -260,42 +214,6 @@ static void __init memblocks_present(void)
memory_present(nid, start, end);
}
-/*
- * 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 > PFN_SECTION_SHIFT);
- BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
- return coded_mem_map;
-}
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-/*
- * 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);
-}
-#endif /* CONFIG_MEMORY_HOTPLUG */
-
-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);
@@ -306,102 +224,6 @@ size_t mem_section_usage_size(void)
return sizeof(struct mem_section_usage) + usemap_size();
}
-#ifdef CONFIG_MEMORY_HOTREMOVE
-static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat)
-{
-#ifndef CONFIG_NUMA
- VM_BUG_ON(pgdat != &contig_page_data);
- return __pa_symbol(&contig_page_data);
-#else
- return __pa(pgdat);
-#endif
-}
-
-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 = pgdat_to_phys(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 = MEMBLOCK_ALLOC_ACCESSIBLE;
- 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(pgdat_to_phys(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
unsigned long __init section_map_size(void)
{
@@ -498,7 +320,6 @@ void __init sparse_init_early_section(int nid, struct page *map,
unsigned long pnum, unsigned long flags)
{
BUG_ON(!sparse_usagebuf || sparse_usagebuf >= sparse_usagebuf_end);
- check_usemap_section_nr(nid, sparse_usagebuf);
sparse_init_one_section(__nr_to_section(pnum), pnum, map,
sparse_usagebuf, SECTION_IS_EARLY | flags);
sparse_usagebuf = (void *)sparse_usagebuf + mem_section_usage_size();
@@ -509,8 +330,7 @@ static int __init sparse_usage_init(int nid, unsigned long map_count)
unsigned long size;
size = mem_section_usage_size() * map_count;
- sparse_usagebuf = sparse_early_usemaps_alloc_pgdat_section(
- NODE_DATA(nid), size);
+ sparse_usagebuf = memblock_alloc_node(size, SMP_CACHE_BYTES, nid);
if (!sparse_usagebuf) {
sparse_usagebuf_end = NULL;
return -ENOMEM;
@@ -600,6 +420,11 @@ void __init sparse_init(void)
BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
memblocks_present();
+ if (compound_info_has_mask()) {
+ VM_WARN_ON_ONCE(!IS_ALIGNED((unsigned long) pfn_to_page(0),
+ MAX_FOLIO_VMEMMAP_ALIGN));
+ }
+
pnum_begin = first_present_section_nr();
nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
@@ -623,356 +448,3 @@ void __init sparse_init(void)
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;
- }
-}
-
-/* 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;
- }
-}
-
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static struct page * __meminit populate_section_memmap(unsigned long pfn,
- unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
- struct dev_pagemap *pgmap)
-{
- return __populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
-}
-
-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);
-}
-
-static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
-{
- 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;
-
- 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 -EINVAL;
-
- bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
- return 0;
-}
-
-static bool is_subsection_map_empty(struct mem_section *ms)
-{
- return bitmap_empty(&ms->usage->subsection_map[0],
- SUBSECTIONS_PER_SECTION);
-}
-
-static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
-{
- struct mem_section *ms = __pfn_to_section(pfn);
- DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
- unsigned long *subsection_map;
- int rc = 0;
-
- 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
- bitmap_or(subsection_map, map, subsection_map,
- SUBSECTIONS_PER_SECTION);
-
- return rc;
-}
-#else
-static struct page * __meminit populate_section_memmap(unsigned long pfn,
- unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
- struct dev_pagemap *pgmap)
-{
- 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)
-{
- unsigned long maps_section_nr, removing_section_nr, i;
- unsigned long type, 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++) {
- type = bootmem_type(page);
-
- BUG_ON(type == NODE_INFO);
-
- maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
- removing_section_nr = bootmem_info(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);
- }
-}
-
-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)
-{
- struct mem_section *ms = __pfn_to_section(pfn);
- bool section_is_early = early_section(ms);
- struct page *memmap = NULL;
- bool empty;
-
- if (clear_subsection_map(pfn, nr_pages))
- return;
-
- empty = is_subsection_map_empty(ms);
- if (empty) {
- unsigned long section_nr = pfn_to_section_nr(pfn);
-
- /*
- * 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;
-
- /*
- * 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_rcu(ms->usage, rcu);
- WRITE_ONCE(ms->usage, NULL);
- }
- memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
- }
-
- /*
- * The memmap of early sections is always fully populated. See
- * section_activate() and pfn_valid() .
- */
- if (!section_is_early) {
- memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
- depopulate_section_memmap(pfn, nr_pages, altmap);
- } else if (memmap) {
- memmap_boot_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page),
- PAGE_SIZE)));
- free_map_bootmem(memmap);
- }
-
- 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,
- struct dev_pagemap *pgmap)
-{
- struct mem_section *ms = __pfn_to_section(pfn);
- struct mem_section_usage *usage = NULL;
- struct page *memmap;
- int rc;
-
- if (!ms->usage) {
- usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
- if (!usage)
- return ERR_PTR(-ENOMEM);
- ms->usage = usage;
- }
-
- rc = fill_subsection_map(pfn, nr_pages);
- 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, pgmap);
- if (!memmap) {
- section_deactivate(pfn, nr_pages, altmap);
- return ERR_PTR(-ENOMEM);
- }
- memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
-
- 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: alternate pfns to allocate the memmap backing store
- * @pgmap: alternate compound page geometry for devmap mappings
- *
- * 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.
- * * -ENOMEM - Out of memory.
- */
-int __meminit sparse_add_section(int nid, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap,
- struct dev_pagemap *pgmap)
-{
- 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, pgmap);
- 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, section_nr);
-
- /* Align memmap to section boundary in the subsection case */
- if (section_nr_to_pfn(section_nr) != start_pfn)
- memmap = pfn_to_page(section_nr_to_pfn(section_nr));
- sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
-
- return 0;
-}
-
-void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap)
-{
- struct mem_section *ms = __pfn_to_section(pfn);
-
- if (WARN_ON_ONCE(!valid_section(ms)))
- return;
-
- section_deactivate(pfn, nr_pages, altmap);
-}
-#endif /* CONFIG_MEMORY_HOTPLUG */