diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e5e8f9db3a84b185d97fb9e972530f67d181d6a4..82b030244aa765e63f7ea0690f94b7a9e6aec94b 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -47,6 +47,9 @@ extern long memblock_remove(phys_addr_t base, phys_addr_t size); extern long __init memblock_free(phys_addr_t base, phys_addr_t size); extern long __init memblock_reserve(phys_addr_t base, phys_addr_t size); +/* The numa aware allocator is only available if + * CONFIG_ARCH_POPULATES_NODE_MAP is set + */ extern phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); extern phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align); diff --git a/mm/memblock.c b/mm/memblock.c index 468ff43a72b4a299f0d16d625a79a61d6627af52..af7e4d9cf400b1109a48c2f6b4f082969569d38a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -15,6 +15,7 @@ #include #include #include +#include #include struct memblock memblock; @@ -451,11 +452,36 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) /* * Additional node-local allocators. Search for node memory is bottom up * and walks memblock regions within that node bottom-up as well, but allocation - * within an memblock region is top-down. + * within an memblock region is top-down. XXX I plan to fix that at some stage + * + * WARNING: Only available after early_node_map[] has been populated, + * on some architectures, that is after all the calls to add_active_range() + * have been done to populate it. */ phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid) { +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + /* + * This code originates from sparc which really wants use to walk by addresses + * and returns the nid. This is not very convenient for early_pfn_map[] users + * as the map isn't sorted yet, and it really wants to be walked by nid. + * + * For now, I implement the inefficient method below which walks the early + * map multiple times. Eventually we may want to use an ARCH config option + * to implement a completely different method for both case. + */ + unsigned long start_pfn, end_pfn; + int i; + + for (i = 0; i < MAX_NUMNODES; i++) { + get_pfn_range_for_nid(i, &start_pfn, &end_pfn); + if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn)) + continue; + *nid = i; + return min(end, PFN_PHYS(end_pfn)); + } +#endif *nid = 0; return end;