X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fsparse.c;h=36511c7b5e2c797067ccb539646f580aa8ec1012;hb=251b97f552b1ad414cc5a9ccc8e4e94503edd5fc;hp=f6a43c09c322cdb39077392ec1c77e9904c52d82;hpb=f315ccb3e679f271583f2a4f463ad9b65665b751;p=linux-2.6 diff --git a/mm/sparse.c b/mm/sparse.c index f6a43c09c3..36511c7b5e 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -8,6 +8,7 @@ #include #include #include +#include "internal.h" #include #include #include @@ -149,8 +150,18 @@ static inline int sparse_early_nid(struct mem_section *section) /* Record a memory area against a node. */ void __init memory_present(int nid, unsigned long start, unsigned long end) { + unsigned long max_arch_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT); unsigned long pfn; + /* + * Sanity checks - do not allow an architecture to pass + * in larger pfns than the maximum scope of sparsemem: + */ + if (start >= max_arch_pfn) + return; + if (end >= max_arch_pfn) + end = max_arch_pfn; + start &= PAGE_SECTION_MASK; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { unsigned long section = pfn_to_section_nr(pfn); @@ -198,12 +209,12 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p } /* - * We need this if we ever free the mem_maps. While not implemented yet, - * this function is included for parity with its sibling. + * Decode mem_map from the coded memmap */ -static __attribute((unused)) 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); } @@ -222,7 +233,7 @@ static int __meminit sparse_init_one_section(struct mem_section *ms, return 1; } -static unsigned long usemap_size(void) +unsigned long usemap_size(void) { unsigned long size_bytes; size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8; @@ -250,7 +261,7 @@ static unsigned long *__init sparse_early_usemap_alloc(unsigned long pnum) /* Stupid: suppress gcc warning for SPARSEMEM && !NUMA */ nid = 0; - printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__); + printk(KERN_WARNING "%s: allocation failed\n", __func__); return NULL; } @@ -263,8 +274,8 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid) if (map) return map; - map = alloc_bootmem_node(NODE_DATA(nid), - sizeof(struct page) * PAGES_PER_SECTION); + map = alloc_bootmem_pages_node(NODE_DATA(nid), + PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION)); return map; } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ @@ -280,11 +291,14 @@ struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) return map; printk(KERN_ERR "%s: sparsemem memory map backing failed " - "some memory will not be available.\n", __FUNCTION__); + "some memory will not be available.\n", __func__); ms->section_mem_map = 0; return NULL; } +void __attribute__((weak)) __meminit vmemmap_populate_print_last(void) +{ +} /* * Allocate the accumulated non-linear sections, allocate a mem_map * for each and record the physical to section mapping. @@ -294,22 +308,50 @@ void __init sparse_init(void) unsigned long pnum; struct page *map; unsigned long *usemap; + unsigned long **usemap_map; + int size; + + /* + * map is using big page (aka 2M in x86 64 bit) + * usemap is less one page (aka 24 bytes) + * so alloc 2M (with 2M align) and 24 bytes in turn will + * make next 2M slip to one more 2M later. + * then in big system, the memory will have a lot of holes... + * here try to allocate 2M pages continously. + * + * powerpc need to call sparse_init_one_section right after each + * sparse_early_mem_map_alloc, so allocate usemap_map at first. + */ + size = sizeof(unsigned long *) * NR_MEM_SECTIONS; + usemap_map = alloc_bootmem(size); + if (!usemap_map) + panic("can not allocate usemap_map\n"); for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { if (!present_section_nr(pnum)) continue; + usemap_map[pnum] = sparse_early_usemap_alloc(pnum); + } - map = sparse_early_mem_map_alloc(pnum); - if (!map) + for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { + if (!present_section_nr(pnum)) continue; - usemap = sparse_early_usemap_alloc(pnum); + usemap = usemap_map[pnum]; if (!usemap) continue; + map = sparse_early_mem_map_alloc(pnum); + if (!map) + continue; + sparse_init_one_section(__nr_to_section(pnum), pnum, map, usemap); } + + vmemmap_populate_print_last(); + + free_bootmem(__pa(usemap_map), size); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -324,6 +366,9 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) { return; /* XXX: Not implemented yet */ } +static void free_map_bootmem(struct page *page, unsigned long nr_pages) +{ +} #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) { @@ -361,8 +406,69 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) free_pages((unsigned long)memmap, get_order(sizeof(struct page) * nr_pages)); } + +static void free_map_bootmem(struct page *page, unsigned long nr_pages) +{ + unsigned long maps_section_nr, removing_section_nr, i; + int magic; + + for (i = 0; i < nr_pages; i++, page++) { + magic = atomic_read(&page->_mapcount); + + BUG_ON(magic == NODE_INFO); + + maps_section_nr = pfn_to_section_nr(page_to_pfn(page)); + removing_section_nr = page->private; + + /* + * 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 free_section_usemap(struct page *memmap, unsigned long *usemap) +{ + struct page *usemap_page; + unsigned long nr_pages; + + if (!usemap) + return; + + usemap_page = virt_to_page(usemap); + /* + * Check to see if allocation came from hot-plug-add + */ + if (PageSlab(usemap_page)) { + kfree(usemap); + if (memmap) + __kfree_section_memmap(memmap, PAGES_PER_SECTION); + 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) { + struct page *memmap_page; + memmap_page = virt_to_page(memmap); + + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + + free_map_bootmem(memmap_page, nr_pages); + } +} + /* * returns the number of sections whose mem_maps were properly * set. If this is <=0, then that means that the passed-in @@ -415,4 +521,20 @@ out: } return ret; } + +void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) +{ + struct page *memmap = NULL; + unsigned long *usemap = NULL; + + if (ms->section_mem_map) { + usemap = ms->pageblock_flags; + memmap = sparse_decode_mem_map(ms->section_mem_map, + __section_nr(ms)); + ms->section_mem_map = 0; + ms->pageblock_flags = NULL; + } + + free_section_usemap(memmap, usemap); +} #endif