X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fsparse.c;h=6ce4aab69e9974aea1838092efc26601ea7598b4;hb=d327cf7449e6fd5cbac784c641770e9366faa386;hp=1f4dbb867b8af7a04040cb3c8c4195d2bab7e4ed;hpb=5c0e3066474b57c56ff0d88ca31d95bd14232fee;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/sparse.c b/mm/sparse.c index 1f4dbb8..6ce4aab 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -8,6 +8,7 @@ #include #include #include +#include "internal.h" #include #include #include @@ -61,9 +62,12 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) unsigned long array_size = SECTIONS_PER_ROOT * sizeof(struct mem_section); - if (slab_is_available()) - section = kmalloc_node(array_size, GFP_KERNEL, nid); - else + if (slab_is_available()) { + if (node_state(nid, N_HIGH_MEMORY)) + section = kmalloc_node(array_size, GFP_KERNEL, nid); + else + section = kmalloc(array_size, GFP_KERNEL); + } else section = alloc_bootmem_node(NODE_DATA(nid), array_size); if (section) @@ -83,6 +87,8 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid) return -EEXIST; section = sparse_index_alloc(nid); + if (!section) + return -ENOMEM; /* * This lock keeps two different sections from * reallocating for the same index @@ -144,12 +150,39 @@ 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; + } +} + /* Record a memory area against a node. */ void __init memory_present(int nid, unsigned long start, unsigned long end) { unsigned long pfn; 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; @@ -174,6 +207,7 @@ unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn, unsigned long pfn; unsigned long nr_pages = 0; + mminit_validate_memmodel_limits(&start_pfn, &end_pfn); for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { if (nid != early_pfn_to_nid(pfn)) continue; @@ -196,12 +230,12 @@ 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); } @@ -220,13 +254,7 @@ static int __meminit sparse_init_one_section(struct mem_section *ms, return 1; } -__attribute__((weak)) __init -void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size) -{ - return NULL; -} - -static unsigned long usemap_size(void) +unsigned long usemap_size(void) { unsigned long size_bytes; size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8; @@ -241,25 +269,101 @@ static unsigned long *__kmalloc_section_usemap(void) } #endif /* CONFIG_MEMORY_HOTPLUG */ -static unsigned long *sparse_early_usemap_alloc(unsigned long pnum) +#ifdef CONFIG_MEMORY_HOTREMOVE +static unsigned long * __init +sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat) +{ + unsigned long section_nr; + + /* + * A page may contain usemaps for other sections preventing the + * page being freed and making a section unremovable while + * other sections referencing the usemap retmain 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. + */ + section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); + return alloc_bootmem_section(usemap_size(), section_nr); +} + +static void __init check_usemap_section_nr(int nid, unsigned long *usemap) +{ + unsigned long usemap_snr, pgdat_snr; + static unsigned long old_usemap_snr = NR_MEM_SECTIONS; + static unsigned long old_pgdat_snr = NR_MEM_SECTIONS; + struct pglist_data *pgdat = NODE_DATA(nid); + int usemap_nid; + + usemap_snr = pfn_to_section_nr(__pa(usemap) >> 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) { + printk(KERN_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. + */ + printk(KERN_INFO "Section %ld and %ld (node %d)", usemap_snr, + pgdat_snr, nid); + printk(KERN_CONT + " have a circular dependency on usemap and pgdat allocations\n"); +} +#else +static unsigned long * __init +sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat) +{ + return NULL; +} + +static void __init check_usemap_section_nr(int nid, unsigned long *usemap) +{ +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + +static unsigned long *__init sparse_early_usemap_alloc(unsigned long pnum) { unsigned long *usemap; struct mem_section *ms = __nr_to_section(pnum); int nid = sparse_early_nid(ms); - usemap = alloc_bootmem_node(NODE_DATA(nid), usemap_size()); + usemap = sparse_early_usemap_alloc_pgdat_section(NODE_DATA(nid)); if (usemap) return usemap; + usemap = alloc_bootmem_node(NODE_DATA(nid), usemap_size()); + if (usemap) { + check_usemap_section_nr(nid, usemap); + return usemap; + } + /* 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; } #ifndef CONFIG_SPARSEMEM_VMEMMAP -struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid) +struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid) { struct page *map; @@ -267,33 +371,31 @@ struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid) if (map) return map; - map = alloc_bootmem_high_node(NODE_DATA(nid), - sizeof(struct page) * PAGES_PER_SECTION); - 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 */ -struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) +static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) { struct page *map; struct mem_section *ms = __nr_to_section(pnum); int nid = sparse_early_nid(ms); - map = sparse_early_mem_map_populate(pnum, nid); + map = sparse_mem_map_populate(pnum, nid); if (map) 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. @@ -303,25 +405,68 @@ 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 +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, + unsigned long nr_pages) +{ + /* This will make the necessary allocations eventually. */ + return sparse_mem_map_populate(pnum, nid); +} +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) { struct page *page, *ret; @@ -344,29 +489,89 @@ got_map_ptr: return ret; } -static int vaddr_in_vmalloc_area(void *addr) +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, + unsigned long nr_pages) { - if (addr >= (void *)VMALLOC_START && - addr < (void *)VMALLOC_END) - return 1; - return 0; + return __kmalloc_section_memmap(nr_pages); } static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) { - if (vaddr_in_vmalloc_area(memmap)) + if (is_vmalloc_addr(memmap)) vfree(memmap); else 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 * map was not consumed and must be freed. */ -int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, +int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages) { unsigned long section_nr = pfn_to_section_nr(start_pfn); @@ -381,9 +586,17 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, * no locking for this, because it does its own * plus, it does a kmalloc */ - sparse_index_init(section_nr, pgdat->node_id); - memmap = __kmalloc_section_memmap(nr_pages); + ret = sparse_index_init(section_nr, pgdat->node_id); + if (ret < 0 && ret != -EEXIST) + return ret; + memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages); + if (!memmap) + return -ENOMEM; usemap = __kmalloc_section_usemap(); + if (!usemap) { + __kfree_section_memmap(memmap, nr_pages); + return -ENOMEM; + } pgdat_resize_lock(pgdat, &flags); @@ -393,18 +606,32 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, goto out; } - if (!usemap) { - ret = -ENOMEM; - goto out; - } ms->section_mem_map |= SECTION_MARKED_PRESENT; ret = sparse_init_one_section(ms, section_nr, memmap, usemap); out: pgdat_resize_unlock(pgdat, &flags); - if (ret <= 0) + if (ret <= 0) { + kfree(usemap); __kfree_section_memmap(memmap, nr_pages); + } 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