On Fri, 26 Oct 2018 19:34:31 -0300 Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> wrote: > > About the performance consideration: > > As said by James in b92df1de5, > > "I have tested this patch on a virtual model of a Samurai CPU with a > > sparse memory map. The kernel boot time drops from 109 to 62 seconds." > > Thus it would be better if we remain memblock_next_valid_pfn on arm/arm64. > > > > Didn't we decide to drop these? (and 50 - 51) <looks back at the thread> I can't see where that was decided. Pavel felt that three of the original six patches weren't worthwhile and those have been dropped. What remained was: arm-arm64-introduce-config_have_memblock_pfn_valid.patch Subject: arm: arm64: introduce CONFIG_HAVE_MEMBLOCK_PFN_VALID mm-page_alloc-remain-memblock_next_valid_pfn-on-arm-arm64.patch Subject: mm: page_alloc: restore memblock_next_valid_pfn() on arm/arm64 mm-page_alloc-reduce-unnecessary-binary-search-in-memblock_next_valid_pfn.patch Subject: mm: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn So as there's doubt I guess we should omit those for now?
