diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 30d8d33491dddd86466dc2df917270d8499c5415..52226e14bd7dba34b483a77ba22424e4241f8145 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -46,6 +46,12 @@ __pgdat->node_start_pfn; \ }) +#elif defined(CONFIG_SPARSEMEM_VMEMMAP) + +/* memmap is virtually contigious. */ +#define __pfn_to_page(pfn) (vmemmap + (pfn)) +#define __page_to_pfn(page) ((page) - vmemmap) + #elif defined(CONFIG_SPARSEMEM) /* * Note: section's mem_map is encorded to reflect its start_pfn. diff --git a/include/linux/mm.h b/include/linux/mm.h index 1692dd6cb9153bd6fa2fcdf13f2352e84500eeae..d216abbd0574f0c92cb740277e38867c4ce5d418 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1218,5 +1218,11 @@ extern int randomize_va_space; const char * arch_vma_name(struct vm_area_struct *vma); +struct page *sparse_early_mem_map_populate(unsigned long pnum, int nid); +int vmemmap_populate(struct page *start_page, unsigned long pages, int node); +int vmemmap_populate_pmd(pud_t *, unsigned long, unsigned long, int); +void *vmemmap_alloc_block(unsigned long size, int node); +void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/Makefile b/mm/Makefile index 245e33ab00c4455893b020115b2c4bcd057456be..d28f63e05b46dee52f491df8f084daf734aefa1a 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o +obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c new file mode 100644 index 0000000000000000000000000000000000000000..7bb7a4b96d74cb712a188c8d45d6c2cf447210f0 --- /dev/null +++ b/mm/sparse-vmemmap.c @@ -0,0 +1,181 @@ +/* + * Virtual Memory Map support + * + * (C) 2007 sgi. Christoph Lameter . + * + * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn, + * virt_to_page, page_address() to be implemented as a base offset + * calculation without memory access. + * + * However, virtual mappings need a page table and TLBs. Many Linux + * architectures already map their physical space using 1-1 mappings + * via TLBs. For those arches the virtual memmory map is essentially + * for free if we use the same page size as the 1-1 mappings. In that + * case the overhead consists of a few additional pages that are + * allocated to create a view of memory for vmemmap. + * + * Special Kconfig settings: + * + * CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP + * + * The architecture has its own functions to populate the memory + * map and provides a vmemmap_populate function. + * + * CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP_PMD + * + * The architecture provides functions to populate the pmd level + * of the vmemmap mappings. Allowing mappings using large pages + * where available. + * + * If neither are set then PAGE_SIZE mappings are generated which + * require one PTE/TLB per PAGE_SIZE chunk of the virtual memory map. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Allocate a block of memory to be used to back the virtual memory map + * or to back the page tables that are used to create the mapping. + * Uses the main allocators if they are available, else bootmem. + */ +void * __meminit vmemmap_alloc_block(unsigned long size, int node) +{ + /* If the main allocator is up use that, fallback to bootmem. */ + if (slab_is_available()) { + struct page *page = alloc_pages_node(node, + GFP_KERNEL | __GFP_ZERO, get_order(size)); + if (page) + return page_address(page); + return NULL; + } else + return __alloc_bootmem_node(NODE_DATA(node), size, size, + __pa(MAX_DMA_ADDRESS)); +} + +#ifndef CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP +void __meminit vmemmap_verify(pte_t *pte, int node, + unsigned long start, unsigned long end) +{ + unsigned long pfn = pte_pfn(*pte); + int actual_node = early_pfn_to_nid(pfn); + + if (actual_node != node) + printk(KERN_WARNING "[%lx-%lx] potential offnode " + "page_structs\n", start, end - 1); +} + +#ifndef CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP_PMD +static int __meminit vmemmap_populate_pte(pmd_t *pmd, unsigned long addr, + unsigned long end, int node) +{ + pte_t *pte; + + for (pte = pte_offset_kernel(pmd, addr); addr < end; + pte++, addr += PAGE_SIZE) + if (pte_none(*pte)) { + pte_t entry; + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return -ENOMEM; + + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte(pte, entry); + + } else + vmemmap_verify(pte, node, addr + PAGE_SIZE, end); + + return 0; +} + +int __meminit vmemmap_populate_pmd(pud_t *pud, unsigned long addr, + unsigned long end, int node) +{ + pmd_t *pmd; + int error = 0; + unsigned long next; + + for (pmd = pmd_offset(pud, addr); addr < end && !error; + pmd++, addr = next) { + if (pmd_none(*pmd)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return -ENOMEM; + + pmd_populate_kernel(&init_mm, pmd, p); + } else + vmemmap_verify((pte_t *)pmd, node, + pmd_addr_end(addr, end), end); + next = pmd_addr_end(addr, end); + error = vmemmap_populate_pte(pmd, addr, next, node); + } + return error; +} +#endif /* CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP_PMD */ + +static int __meminit vmemmap_populate_pud(pgd_t *pgd, unsigned long addr, + unsigned long end, int node) +{ + pud_t *pud; + int error = 0; + unsigned long next; + + for (pud = pud_offset(pgd, addr); addr < end && !error; + pud++, addr = next) { + if (pud_none(*pud)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return -ENOMEM; + + pud_populate(&init_mm, pud, p); + } + next = pud_addr_end(addr, end); + error = vmemmap_populate_pmd(pud, addr, next, node); + } + return error; +} + +int __meminit vmemmap_populate(struct page *start_page, + unsigned long nr, int node) +{ + pgd_t *pgd; + unsigned long addr = (unsigned long)start_page; + unsigned long end = (unsigned long)(start_page + nr); + unsigned long next; + int error = 0; + + printk(KERN_DEBUG "[%lx-%lx] Virtual memory section" + " (%ld pages) node %d\n", addr, end - 1, nr, node); + + for (pgd = pgd_offset_k(addr); addr < end && !error; + pgd++, addr = next) { + if (pgd_none(*pgd)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return -ENOMEM; + + pgd_populate(&init_mm, pgd, p); + } + next = pgd_addr_end(addr,end); + error = vmemmap_populate_pud(pgd, addr, next, node); + } + return error; +} +#endif /* !CONFIG_ARCH_POPULATES_SPARSEMEM_VMEMMAP */ + +struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid) +{ + struct page *map = pfn_to_page(pnum * PAGES_PER_SECTION); + int error = vmemmap_populate(map, PAGES_PER_SECTION, nid); + if (error) + return NULL; + + return map; +} diff --git a/mm/sparse.c b/mm/sparse.c index 54f3940406cba1e6bf980e273e171c856296d148..52843a76feede7b7f46b15874b7ff68dc32ca9a2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -9,6 +9,8 @@ #include #include #include +#include +#include /* * Permanent SPARSEMEM data: @@ -222,11 +224,10 @@ void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size) return NULL; } -static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) +#ifndef CONFIG_SPARSEMEM_VMEMMAP +struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid) { struct page *map; - struct mem_section *ms = __nr_to_section(pnum); - int nid = sparse_early_nid(ms); map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION); if (map) @@ -239,10 +240,22 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) map = alloc_bootmem_node(NODE_DATA(nid), sizeof(struct page) * PAGES_PER_SECTION); + return map; +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ + +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); if (map) return map; - printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__); + printk(KERN_ERR "%s: sparsemem memory map backing failed " + "some memory will not be available.\n", __FUNCTION__); ms->section_mem_map = 0; return NULL; }