Nice

Useful when you have several compat directories with different Linux versions.

Builds on ppcports. I will try it on x86 later.

Given you tested it, that looks good to me as a whole now (with that small nitpick above).

Looks good to me.

Lgtm :)

Lookgs good to me.

Can you explain why this change reduces the number of L1 data cache misses?

OK from manpages.

Fix tiny regression in documentation reference.

Style changes.

Go ahead and make findnext and findprev look less weird.

OK from manpages.

Stop trying to insert 'found' into the splay search code.

left over debug printf.

In D21449#491256, @jhibbits wrote:

In D21449#468106, @markj wrote:

Please take a look at D21491, which moves the page array into KVA on amd64. It looks like you're doing that already, but I don't see what's preventing the vm_page address range from being allocated from the kernel map's vmem arena(s).

I don't see a benefit in burning KVA on this on AIM64 (already being done on Book-E, which is much more limited in physmem). @luporl has the minidump scanner dumping all mapped memory, which would include this block anyway, so we free up the precious KVA for other stuff.