Re: [PATCH v5] RO/NX protection for loadable kernel modules

[Andi Kleen]

Rusty Russell <rusty@xxxxxxxxxxxxxxx> writes:
>
> (I like the idea of trying kmalloc and falling back, simply because it reduces 
> TLB pressure,

I implemented this for 32bit in 2.4, but I always had second thoughts
if that was really reducing TLB pressure.

x86 CPUs have separated TLBs for 2MB and 4K and they all have much
more 4K entries. So it might actually be worse to use the 2MB TLBs for
this.

> but that's probably best done after unification).

Trying kmalloc doesn't work on x86-64

-Andi

-- 
ak@xxxxxxxxxxxxxxx -- Speaking for myself only.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/