From mboxrd@z Thu Jan  1 00:00:00 1970
From: benh@au1.ibm.com (Benjamin Herrenschmidt)
Date: Fri, 02 Mar 2018 10:25:34 +1100
Subject: [PATCH v2 00/10] Copy Offload in NVMe Fabrics with P2P PCI Memory
In-Reply-To: <595acefb-18fc-e650-e172-bae271263c4c@deltatee.com>
References: <20180228234006.21093-1-logang@deltatee.com>
 <1519876489.4592.3.camel@kernel.crashing.org>
 <1519876569.4592.4.camel@au1.ibm.com>
 <CAPcyv4h7mcFphv3j_vW-CGxXa2pjQgLqpBOLzHuTzAFzygai-Q@mail.gmail.com>
 <1519936477.4592.23.camel@au1.ibm.com>
 <CAPcyv4goHsYytq60ehJUori8Xq+Z0p8dV-8_oRALj244H4YtwQ@mail.gmail.com>
 <2079ba48-5ae5-5b44-cce1-8175712dd395@deltatee.com>
 <43ba615f-a6e1-9444-65e1-494169cb415d@deltatee.com>
 <1519945204.4592.45.camel@au1.ibm.com>
 <595acefb-18fc-e650-e172-bae271263c4c@deltatee.com>
Message-ID: <1519946734.4592.48.camel@au1.ibm.com>

On Thu, 2018-03-01@16:19 -0700, Logan Gunthorpe wrote:
> 
> On 01/03/18 04:00 PM, Benjamin Herrenschmidt wrote:
> > We use only 52 in practice but yes.
> > 
> > >   That's 64PB. If you use need
> > > a sparse vmemmap for the entire space it will take 16TB which leaves you
> > > with 63.98PB of address space left. (Similar calculations for other
> > > numbers of address bits.)
> > 
> > We only have 52 bits of virtual space for the kernel with the radix
> > MMU.
> 
> Ok, assuming you only have 52 bits of physical address space: the sparse 
> vmemmap takes 1TB and you're left with 3.9PB of address space for other 
> things. So, again, why doesn't that work? Is my math wrong

The big problem is not the vmemmap, it's the linear mapping.

Cheers,
Ben.