diff options
Diffstat (limited to 'mm/sparse-vmemmap.c')
| -rw-r--r-- | mm/sparse-vmemmap.c | 484 |
1 files changed, 403 insertions, 81 deletions
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 37522d6cb398..5a2469fb1838 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -41,6 +41,8 @@ #define VMEMMAP_POPULATE_PAGEREF 0x0001 #include "internal.h" +#include "mm_init.h" +#include "sparse.h" /* * Allocate a block of memory to be used to back the virtual memory map @@ -62,7 +64,7 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) if (slab_is_available()) { gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN; int order = get_order(size); - static bool warned; + static bool warned __meminitdata; struct page *page; page = alloc_pages_node(node, gfp_mask, order); @@ -87,15 +89,10 @@ static void * __meminit altmap_alloc_block_buf(unsigned long size, void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap) { - void *ptr; - if (altmap) return altmap_alloc_block_buf(size, altmap); - ptr = sparse_buffer_alloc(size); - if (!ptr) - ptr = vmemmap_alloc_block(size, node); - return ptr; + return vmemmap_alloc_block(size, node); } static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap) @@ -151,7 +148,7 @@ void __meminit vmemmap_verify(pte_t *pte, int node, start, end - 1); } -pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, +static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap, unsigned long ptpfn, unsigned long flags) { @@ -195,7 +192,7 @@ static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node) return p; } -pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) +static pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) { pmd_t *pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { @@ -208,7 +205,7 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) +static pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { @@ -221,7 +218,7 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) return pud; } -p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +static p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) { p4d_t *p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { @@ -234,7 +231,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) return p4d; } -pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) +static pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) { @@ -303,59 +300,6 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, } /* - * Undo populate_hvo, and replace it with a normal base page mapping. - * Used in memory init in case a HVO mapping needs to be undone. - * - * This can happen when it is discovered that a memblock allocated - * hugetlb page spans multiple zones, which can only be verified - * after zones have been initialized. - * - * We know that: - * 1) The first @headsize / PAGE_SIZE vmemmap pages were individually - * allocated through memblock, and mapped. - * - * 2) The rest of the vmemmap pages are mirrors of the last head page. - */ -int __meminit vmemmap_undo_hvo(unsigned long addr, unsigned long end, - int node, unsigned long headsize) -{ - unsigned long maddr, pfn; - pte_t *pte; - int headpages; - - /* - * Should only be called early in boot, so nothing will - * be accessing these page structures. - */ - WARN_ON(!early_boot_irqs_disabled); - - headpages = headsize >> PAGE_SHIFT; - - /* - * Clear mirrored mappings for tail page structs. - */ - for (maddr = addr + headsize; maddr < end; maddr += PAGE_SIZE) { - pte = virt_to_kpte(maddr); - pte_clear(&init_mm, maddr, pte); - } - - /* - * Clear and free mappings for head page and first tail page - * structs. - */ - for (maddr = addr; headpages-- > 0; maddr += PAGE_SIZE) { - pte = virt_to_kpte(maddr); - pfn = pte_pfn(ptep_get(pte)); - pte_clear(&init_mm, maddr, pte); - memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE); - } - - flush_tlb_kernel_range(addr, end); - - return vmemmap_populate(addr, end, node, NULL); -} - -/* * Write protect the mirrored tail page structs for HVO. This will be * called from the hugetlb code when gathering and initializing the * memblock allocated gigantic pages. The write protect can't be @@ -378,16 +322,54 @@ void vmemmap_wrprotect_hvo(unsigned long addr, unsigned long end, } } -/* - * Populate vmemmap pages HVO-style. The first page contains the head - * page and needed tail pages, the other ones are mirrors of the first - * page. - */ +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *zone) +{ + struct page *p, *tail; + unsigned int idx; + int node = zone_to_nid(zone); + + if (WARN_ON_ONCE(order < VMEMMAP_TAIL_MIN_ORDER)) + return NULL; + if (WARN_ON_ONCE(order > MAX_FOLIO_ORDER)) + return NULL; + + idx = order - VMEMMAP_TAIL_MIN_ORDER; + tail = zone->vmemmap_tails[idx]; + if (tail) + return tail; + + /* + * Only allocate the page, but do not initialize it. + * + * Any initialization done here will be overwritten by memmap_init(). + * + * hugetlb_bootmem_struct_page_init() will take care of initialization + * after memmap_init(). + */ + + p = vmemmap_alloc_block_zero(PAGE_SIZE, node); + if (!p) + return NULL; + + tail = virt_to_page(p); + zone->vmemmap_tails[idx] = tail; + + return tail; +} + int __meminit vmemmap_populate_hvo(unsigned long addr, unsigned long end, - int node, unsigned long headsize) + unsigned int order, struct zone *zone, + unsigned long headsize) { - pte_t *pte; unsigned long maddr; + struct page *tail; + pte_t *pte; + int node = zone_to_nid(zone); + + tail = vmemmap_get_tail(order, zone); + if (!tail) + return -ENOMEM; for (maddr = addr; maddr < addr + headsize; maddr += PAGE_SIZE) { pte = vmemmap_populate_address(maddr, node, NULL, -1, 0); @@ -399,18 +381,24 @@ int __meminit vmemmap_populate_hvo(unsigned long addr, unsigned long end, * Reuse the last page struct page mapped above for the rest. */ return vmemmap_populate_range(maddr, end, node, NULL, - pte_pfn(ptep_get(pte)), 0); + page_to_pfn(tail), 0); } +#endif void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next) { + WARN_ON_ONCE(!pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL)); } int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next) { - return 0; + if (!pmd_leaf(pmdp_get(pmd))) + return 0; + vmemmap_verify((pte_t *)pmd, node, addr, next); + + return 1; } int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end, @@ -578,6 +566,8 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; + flush_cache_vmap(start, end); + return pfn_to_page(pfn); } @@ -593,15 +583,347 @@ void __init sparse_vmemmap_init_nid_early(int nid) { hugetlb_vmemmap_init_early(nid); } +#endif + +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); +} + +static void __init sparse_init_subsection_map_range(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; + } +} + +void __init sparse_init_subsection_map(void) +{ + int i, nid; + unsigned long start, end; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) + sparse_init_subsection_map_range(start, end - start); +} + +#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 = __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 = __nr_to_section(section_nr); + + ms->section_mem_map &= ~SECTION_IS_ONLINE; + } +} + +static int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) +{ + const unsigned int order = pgmap ? pgmap->vmemmap_shift : 0; + const unsigned long pages_per_compound = 1UL << order; + + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION)); + VM_WARN_ON_ONCE(nr_pages > PAGES_PER_SECTION); + + if (!vmemmap_can_optimize(altmap, pgmap)) + return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE); + + if (order < PFN_SECTION_SHIFT) { + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, pages_per_compound)); + return VMEMMAP_RESERVE_NR * nr_pages / pages_per_compound; + } + + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION)); + + if (IS_ALIGNED(pfn, pages_per_compound)) + return VMEMMAP_RESERVE_NR; + + return 0; +} + +static struct page * __meminit populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + struct page *page = __populate_section_memmap(pfn, nr_pages, nid, altmap, + pgmap); + + memmap_pages_add(section_nr_vmemmap_pages(pfn, nr_pages, altmap, pgmap)); + + return page; +} + +static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) +{ + unsigned long start = (unsigned long) pfn_to_page(pfn); + unsigned long end = start + nr_pages * sizeof(struct page); + + memmap_pages_add(-section_nr_vmemmap_pages(pfn, nr_pages, altmap, pgmap)); + 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); + unsigned long pfn = page_to_pfn(memmap); + + memmap_boot_pages_add(-section_nr_vmemmap_pages(pfn, PAGES_PER_SECTION, + NULL, NULL)); + 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; +} /* - * This is called just before the initialization of page structures - * through memmap_init. Zones are now initialized, so any work that - * needs to be done that needs zone information can be done from - * here. + * To deactivate a memory region, there are 3 cases to handle: + * + * 1. deactivation of a partial hot-added section: + * 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. */ -void __init sparse_vmemmap_init_nid_late(int nid) +static void section_deactivate(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { - hugetlb_vmemmap_init_late(nid); + 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) { + /* + * 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 = pfn_to_page(SECTION_ALIGN_DOWN(pfn)); + } + + /* + * The memmap of early sections is always fully populated. See + * section_activate() and pfn_valid() . + */ + if (!section_is_early) + depopulate_section_memmap(pfn, nr_pages, altmap, pgmap); + else if (memmap) + free_map_bootmem(memmap); + + if (empty) + ms->section_mem_map = (unsigned long)NULL; } -#endif + +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, pgmap); + 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: 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); + __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 dev_pagemap *pgmap) +{ + struct mem_section *ms = __pfn_to_section(pfn); + + if (WARN_ON_ONCE(!valid_section(ms))) + return; + + section_deactivate(pfn, nr_pages, altmap, pgmap); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ |