On Tue, 2010-11-16 at 22:42 -0700, Grant Grundler wrote: > On Wed, Nov 17, 2010 at 12:26:42AM -0500, Kyle McMartin wrote: > > On Tue, Nov 16, 2010 at 10:22:18PM -0700, Grant Grundler wrote: > > > I agree. The kernel is expected to emulate/handle unaligned loads/stores. > > > > > > I thought we had all that misaligned access handlers working years ago and > > > somewhere probably have a user space program to test it. Oh...ldd won't be > > > user space since we don't have a PA2.0 64-bit user space. LDD support > > > can't be as well tested. > > > > > > On that note, can you try a 32-bit kernel? (SMP maybe) > > > > > > > We really shouldn't be fixing up unaligned access in the kernel, since > > we can just fix the code... If ipv6 is causing them, there must be some > > missing define that's getting defaulted to something un-padded, > > otherwise sparc wouldn't work at all (it definitely does /not/ fix > > unalignd accesses, period.) > > I agree but thought davem refused patches to use get/put_unaligned macros > in networking code. Searching for "davem ulog put_unaligned" shows him > accepting such patches. So this is clearly the right path to pursue. DaveM's argument is that these are exceptions in packet handling rather than the norm. As you know, using unaligned on parisc (and sparc) does byte loads, which is horrifically inefficient in a critical network path. So it's faster to process the exceptions periodically than penalise the fast path. James -- To unsubscribe from this list: send the line "unsubscribe linux-parisc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
