From: Lyude Paul <lyude@redhat.com>
To: Alistair Popple <apopple@nvidia.com>,
linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>
Cc: "Alex Sierra" <alex.sierra@amd.com>,
"Ralph Campbell" <rcampbell@nvidia.com>,
"Matthew Wilcox (Oracle)" <willy@infradead.org>,
dri-devel@lists.freedesktop.org,
"Karol Herbst" <kherbst@redhat.com>,
nouveau@lists.freedesktop.org, "David Airlie" <airlied@linux.ie>,
"Michael Ellerman" <mpe@ellerman.id.au>,
"Felix Kuehling" <Felix.Kuehling@amd.com>,
"Pan, Xinhui" <Xinhui.Pan@amd.com>,
linux-kernel@vger.kernel.org,
"Nicholas Piggin" <npiggin@gmail.com>,
"Ben Skeggs" <bskeggs@redhat.com>,
"John Hubbard" <jhubbard@nvidia.com>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Dan Williams" <dan.j.williams@intel.com>,
amd-gfx@lists.freedesktop.org, linuxppc-dev@lists.ozlabs.org,
"Christian König" <christian.koenig@amd.com>,
"Jason Gunthorpe" <jgg@nvidia.com>
Subject: Re: [PATCH 6/7] nouveau/dmem: Evict device private memory during release
Date: Mon, 26 Sep 2022 17:35:11 -0400 [thread overview]
Message-ID: <881735bda9b1ba0ecf3648af201840233508f206.camel@redhat.com> (raw)
In-Reply-To: <072e1ce590fe101a4cdbd5e91b1702efebb6d0fd.1664171943.git-series.apopple@nvidia.com>
On Mon, 2022-09-26 at 16:03 +1000, Alistair Popple wrote:
> When the module is unloaded or a GPU is unbound from the module it is
> possible for device private pages to be left mapped in currently running
> processes. This leads to a kernel crash when the pages are either freed
> or accessed from the CPU because the GPU and associated data structures
> and callbacks have all been freed.
>
> Fix this by migrating any mappings back to normal CPU memory prior to
> freeing the GPU memory chunks and associated device private pages.
>
> Signed-off-by: Alistair Popple <apopple@nvidia.com>
>
> ---
>
> I assume the AMD driver might have a similar issue. However I can't see
> where device private (or coherent) pages actually get unmapped/freed
> during teardown as I couldn't find any relevant calls to
> devm_memunmap(), memunmap(), devm_release_mem_region() or
> release_mem_region(). So it appears that ZONE_DEVICE pages are not being
> properly freed during module unload, unless I'm missing something?
I've got no idea, will poke Ben to see if they know the answer to this
> ---
> drivers/gpu/drm/nouveau/nouveau_dmem.c | 48 +++++++++++++++++++++++++++-
> 1 file changed, 48 insertions(+)
>
> diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
> index 66ebbd4..3b247b8 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
> @@ -369,6 +369,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm)
> mutex_unlock(&drm->dmem->mutex);
> }
>
> +/*
> + * Evict all pages mapping a chunk.
> + */
> +void
> +nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
> +{
> + unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT;
> + unsigned long *src_pfns, *dst_pfns;
> + dma_addr_t *dma_addrs;
> + struct nouveau_fence *fence;
> +
> + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
> + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
> + dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
> +
> + migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
> + npages);
> +
> + for (i = 0; i < npages; i++) {
> + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) {
> + struct page *dpage;
> +
> + /*
> + * _GFP_NOFAIL because the GPU is going away and there
> + * is nothing sensible we can do if we can't copy the
> + * data back.
> + */
You'll have to excuse me for a moment since this area of nouveau isn't one of
my strongpoints, but are we sure about this? IIRC __GFP_NOFAIL means infinite
retry, in the case of a GPU hotplug event I would assume we would rather just
stop trying to migrate things to the GPU and just drop the data instead of
hanging on infinite retries.
> + dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL);
> + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
> + nouveau_dmem_copy_one(chunk->drm,
> + migrate_pfn_to_page(src_pfns[i]), dpage,
> + &dma_addrs[i]);
> + }
> + }
> +
> + nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence);
> + migrate_device_pages(src_pfns, dst_pfns, npages);
> + nouveau_dmem_fence_done(&fence);
> + migrate_device_finalize(src_pfns, dst_pfns, npages);
> + kfree(src_pfns);
> + kfree(dst_pfns);
> + for (i = 0; i < npages; i++)
> + dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
> + kfree(dma_addrs);
> +}
> +
> void
> nouveau_dmem_fini(struct nouveau_drm *drm)
> {
> @@ -380,8 +426,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm)
> mutex_lock(&drm->dmem->mutex);
>
> list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) {
> + nouveau_dmem_evict_chunk(chunk);
> nouveau_bo_unpin(chunk->bo);
> nouveau_bo_ref(NULL, &chunk->bo);
> + WARN_ON(chunk->callocated);
> list_del(&chunk->list);
> memunmap_pages(&chunk->pagemap);
> release_mem_region(chunk->pagemap.range.start,
--
Cheers,
Lyude Paul (she/her)
Software Engineer at Red Hat
next prev parent reply other threads:[~2022-09-26 21:35 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-26 6:03 [PATCH 0/7] Fix several device private page reference counting issues Alistair Popple
2022-09-26 6:03 ` [PATCH 1/7] mm/memory.c: Fix race when faulting a device private page Alistair Popple
2022-09-29 0:07 ` Michael Ellerman
2022-09-29 1:40 ` Alistair Popple
2022-09-29 5:07 ` Michael Ellerman
2022-09-26 6:03 ` [PATCH 2/7] mm: Free device private pages have zero refcount Alistair Popple
2022-09-26 14:36 ` Jason Gunthorpe
2022-09-27 2:06 ` Alistair Popple
2022-09-29 20:18 ` Dan Williams
2022-09-30 0:45 ` Alistair Popple
2022-09-30 1:49 ` Dan Williams
2022-09-26 6:03 ` [PATCH 3/7] mm/migrate_device.c: Refactor migrate_vma and migrate_deivce_coherent_page() Alistair Popple
2022-09-26 6:03 ` [PATCH 4/7] mm/migrate_device.c: Add migrate_device_range() Alistair Popple
2022-09-26 6:03 ` [PATCH 5/7] nouveau/dmem: Refactor nouveau_dmem_fault_copy_one() Alistair Popple
2022-09-26 21:29 ` Lyude Paul
2022-09-28 11:30 ` Alistair Popple
2022-09-26 6:03 ` [PATCH 6/7] nouveau/dmem: Evict device private memory during release Alistair Popple
2022-09-26 13:28 ` kernel test robot
2022-09-26 21:35 ` Lyude Paul [this message]
2022-09-26 22:14 ` John Hubbard
2022-09-26 23:45 ` Alistair Popple
2022-09-28 21:39 ` Lyude Paul
2022-09-26 23:07 ` Felix Kuehling
2022-09-27 1:39 ` Alistair Popple
2022-09-28 21:23 ` Lyude Paul
2022-09-26 6:03 ` [PATCH 7/7] hmm-tests: Add test for migrate_device_range() Alistair Popple
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=881735bda9b1ba0ecf3648af201840233508f206.camel@redhat.com \
--to=lyude@redhat.com \
--cc=Felix.Kuehling@amd.com \
--cc=Xinhui.Pan@amd.com \
--cc=airlied@linux.ie \
--cc=akpm@linux-foundation.org \
--cc=alex.sierra@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=apopple@nvidia.com \
--cc=bskeggs@redhat.com \
--cc=christian.koenig@amd.com \
--cc=dan.j.williams@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=kherbst@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=nouveau@lists.freedesktop.org \
--cc=npiggin@gmail.com \
--cc=rcampbell@nvidia.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).