linux-kernel - Re: [RESEND PATCH 2/3] nouveau: fix mixed normal and device private page migration

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <a9aba057-3786-8204-f782-6e8f3c290b35@nvidia.com>
Date:   Thu, 25 Jun 2020 10:25:38 -0700
From:   Ralph Campbell <rcampbell@...dia.com>
To:     Christoph Hellwig <hch@....de>
CC:     <nouveau@...ts.freedesktop.org>, <linux-kernel@...r.kernel.org>,
        "Jerome Glisse" <jglisse@...hat.com>,
        John Hubbard <jhubbard@...dia.com>,
        "Jason Gunthorpe" <jgg@...lanox.com>,
        Ben Skeggs <bskeggs@...hat.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        <linux-mm@...ck.org>, Bharata B Rao <bharata@...ux.ibm.com>
Subject: Re: [RESEND PATCH 2/3] nouveau: fix mixed normal and device private
 page migration

Making sure to include linux-mm and Bharata B Rao for IBM's
use of migrate_vma*().

On 6/24/20 11:10 AM, Ralph Campbell wrote:
> 
> On 6/24/20 12:23 AM, Christoph Hellwig wrote:
>> On Mon, Jun 22, 2020 at 04:38:53PM -0700, Ralph Campbell wrote:
>>> The OpenCL function clEnqueueSVMMigrateMem(), without any flags, will
>>> migrate memory in the given address range to device private memory. The
>>> source pages might already have been migrated to device private memory.
>>> In that case, the source struct page is not checked to see if it is
>>> a device private page and incorrectly computes the GPU's physical
>>> address of local memory leading to data corruption.
>>> Fix this by checking the source struct page and computing the correct
>>> physical address.
>>
>> I'm really worried about all this delicate code to fix the mixed
>> ranges.  Can't we make it clear at the migrate_vma_* level if we want
>> to migrate from or two device private memory, and then skip all the work
>> for regions of memory that already are in the right place?  This might be
>> a little more work initially, but I think it leads to a much better
>> API.
>>
> 
> The current code does encode the direction with src_owner != NULL meaning
> device private to system memory and src_owner == NULL meaning system
> memory to device private memory. This patch would obviously defeat that
> so perhaps a flag could be added to the struct migrate_vma to indicate the
> direction but I'm unclear how that makes things less delicate.
> Can you expand on what you are worried about?
> 
> The issue with invalidations might be better addressed by letting the device
> driver handle device private page TLB invalidations when migrating to
> system memory and changing migrate_vma_setup() to only invalidate CPU
> TLB entries for normal pages being migrated to device private memory.
> If a page isn't migrating, it seems inefficient to invalidate those TLB
> entries.
> 
> Any other suggestions?

After a night's sleep, I think this might work. What do others think?

1) Add a new MMU_NOTIFY_MIGRATE enum to mmu_notifier_event.

2) Change migrate_vma_collect() to use the new MMU_NOTIFY_MIGRATE event type.

3) Modify nouveau_svmm_invalidate_range_start() to simply return (no invalidations)
for MMU_NOTIFY_MIGRATE mmu notifier callbacks.

4) Leave the src_owner check in migrate_vma_collect_pmd() for normal pages so if the
device driver is migrating normal pages to device private memory, the driver would
set src_owner = NULL and already migrated device private pages would be skipped.
Since the mmu notifier callback did nothing, the device private entries remain valid
in the device's MMU. migrate_vma_collect_pmd() would still invalidate the CPU page
tables for migrated normal pages.
If the driver is migrating device private pages to system memory, it would set
src_owner != NULL, normal pages would be skipped, but now the device driver has to
invalidate device MMU mappings in the "alloc and copy" before doing the copy.
This would be after migrate_vma_setup() returns so the list of migrating device
pages is known to the driver.

The rest of the migrate_vma_pages() and migrate_vma_finalize() remain the same.