From mboxrd@z Thu Jan  1 00:00:00 1970
From: jglisse@redhat.com (Jerome Glisse)
Date: Thu, 1 Mar 2018 16:18:18 -0500
Subject: [PATCH v2 00/10] Copy Offload in NVMe Fabrics with P2P PCI Memory
In-Reply-To: <1de70207-40ce-29f0-6093-337112852475@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>
 <1519938210.4592.30.camel@au1.ibm.com>
 <1de70207-40ce-29f0-6093-337112852475@deltatee.com>
Message-ID: <20180301211817.GC6742@redhat.com>

On Thu, Mar 01, 2018@02:11:34PM -0700, Logan Gunthorpe wrote:
> 
> 
> On 01/03/18 02:03 PM, Benjamin Herrenschmidt wrote:
> > However, what happens if anything calls page_address() on them ? Some
> > DMA ops do that for example, or some devices might ...
> 
> Although we could probably work around it with some pain, we rely on
> page_address() and virt_to_phys(), etc to work on these pages. So on x86,
> yes, it makes it into the linear mapping.

This is pretty easy to do with HMM:

unsigned long hmm_page_to_phys_pfn(struct page *page)
{
    struct hmm_devmem *devmem;
    unsigned long ppfn;

    /* Sanity test maybe BUG_ON() */
    if (!is_device_private_page(page))
        return -1UL;

    devmem = page->pgmap->data;
    ppfn = page_to_page(page) - devmem->pfn_first;
    return ppfn + devmem->device_phys_base_pfn;
}

Note that last field does not exist in today HMM because i did not need
such helper so far but this can be added.

Cheers,
J?r?me