On Fri, 25 Jan 2008, John W. Linville wrote: > > Quoth Herbert Xu: > > "OK. Let me clarify this a bit more. We require at least one > of the following rules to be met: > > * the IPv4/IPv6 header is aligned by 8 bytes on reception; > * or the platform provides unaligned exception handlers. Ok, so the wireless stack currently does neither. It warns about lack of 4-byte alignment (not 8), and it does so for everything. > That puts mac80211 in an awkward position. It is not architecture > code, so it can't make any assumptions about what is or isn't OK. > So, we need to present aligned data to the network stack. We can *easily* just have a "CONFIG_EXPENSIVE_UNALIGNED" thing, and force architectures to set that, and then just have the mac80211 code re-align the packet as required if it is set. Or you guys could ask the network people to do that at an even higher level. > We could put the alignment onus on mac80211, but this has proven to be > very solvable at (near?) zero cost by all the other drivers. >From personal experience, I would not be in the least surprised if there are DMA engines that simply cannot even do non-aligned DMA's. And from a performance standpoint, it's also very possible that unaligned DMA accesses (if they end up being done as such by a stupid DMA engine) are more expensive than unaligned CPU data. Linus - To unsubscribe from this list: send the line "unsubscribe linux-wireless" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
