On Tue, 27 Mar 2018 11:57:07 +0800 Wei Yang <richard.weiyang@xxxxxxxxx> wrote: > find_min_pfn_for_node() iterate on pfn range to find the minimum pfn for a > node. The memblock_region in memblock_type are already ordered, which means > the first hit in iteration is the minimum pfn. > > This patch returns the fist hit instead of iterating the whole regions. > > ... > > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -6365,14 +6365,14 @@ unsigned long __init node_map_pfn_alignment(void) > /* Find the lowest pfn for a node */ > static unsigned long __init find_min_pfn_for_node(int nid) > { > - unsigned long min_pfn = ULONG_MAX; > - unsigned long start_pfn; > + unsigned long min_pfn; > int i; > > - for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL) > - min_pfn = min(min_pfn, start_pfn); > + for_each_mem_pfn_range(i, nid, &min_pfn, NULL, NULL) { > + break; > + } That would be the weirdest-looking code snippet in mm/! Can't we just use a single and simple call to __next_mem_pfn_range(), or something like that? > > ... >