On Sat, 6 Jun 2015 13:15:38 +0200 (CEST) Jan Engelhardt <jengelh@xxxxxxx> wrote: > x > On Friday 2015-06-05 00:04, Neal P. Murphy wrote: > >The theory: > > - Use two kernel pages for the counters for each group of 256 > > addresses. > > - Change counters to 64-bit. > > - Change to __get_free_pages/free_pages, using order=2 (two > > consecutive pages), and zero both pages. > > - Change "%u" to "%llu" as needed. > > - Everything else pretty much stays the same. > > > >I also changed tmpbuf to two pages (Justin Case's idea), but I > >don't know if that's really necessary. > > > >Did I miss anything? > > I applied it. Thanks! It never occurred to me that a long long might someday be longer than 64 bits. And I haven't had to program C structs for more than one ARCH for around 25 years, when I had to make a home-brew DB work on m68k, m88k, Sparc and MIPS. Using about as many different compilers and OSes. *I* thought I was being clever using explicit padding to align elements by hand. I've applied your tweaks to my patch. Neal -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
