From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
To: Felix Kuehling <felix.kuehling@amd.com>, Daniel Vetter <daniel@ffwll.ch>
Cc: ckoenig.leichtzumerken@gmail.com, gregkh@linuxfoundation.org,
daniel.vetter@ffwll.ch, amd-gfx@lists.freedesktop.org,
helgaas@kernel.org, dri-devel@lists.freedesktop.org,
linux-pci@vger.kernel.org, Alexander.Deucher@amd.com
Subject: Re: [PATCH v5 20/27] drm: Scope all DRM IOCTLs with drm_dev_enter/exit
Date: Thu, 29 Apr 2021 12:33:29 -0400 [thread overview]
Message-ID: <6d56684c-1964-f023-7d23-f0e5042941c5@amd.com> (raw)
In-Reply-To: <9c91bdae-d78c-202b-8b58-6977929f1273@amd.com>
On 2021-04-29 12:29 p.m., Felix Kuehling wrote:
> Am 2021-04-29 um 12:21 p.m. schrieb Andrey Grodzovsky:
>>
>>
>> On 2021-04-29 12:15 p.m., Felix Kuehling wrote:
>>> Am 2021-04-29 um 12:04 p.m. schrieb Andrey Grodzovsky:
>>>> So as I understand your preferred approach is that I scope any
>>>> back_end, HW specific function with drm_dev_enter/exit because that
>>>> where MMIO
>>>> access takes place. But besides explicit MMIO access thorough
>>>> register accessors in the HW back-end there is also indirect MMIO
>>>> access
>>>> taking place throughout the code in the driver because of various VRAM
>>>> BOs which provide CPU access to VRAM through the VRAM BAR. This kind of
>>>> access is spread all over in the driver and even in mid-layers such as
>>>> TTM and not limited to HW back-end functions. It means it's much harder
>>>> to spot such places to surgically scope them with drm_dev_enter/exit
>>>> and
>>>> also that any new such code introduced will immediately break hot
>>>> unplug
>>>> because the developers can't be expected to remember making their code
>>>> robust to this specific use case. That why when we discussed internally
>>>> what approach to take to protecting code with drm_dev_enter/exit we
>>>> opted for using the widest available scope.
>>>
>>> VRAM can also be mapped in user mode. Is there anything preventing user
>>> mode from accessing the memory after unplug? I guess the best you could
>>> do is unmap it from the CPU page table and let the application segfault
>>> on the next access. Or replace the mapping with a dummy page in system
>>> memory?
>>
>> We indeed unmap but instead of letting it segfault insert dummy page on
>> the next page fault. See here
>> https://cgit.freedesktop.org/~agrodzov/linux/commit/?h=drm-misc-next&id=6dde3330ffa450e2e6da4d19e2fd0bb94b66b6ce
>> And I am aware that this doesn't take care of KFD user mapping.
>> As you know, we had some discussions with you on this topic and it's on
>> my TODO list to follow up on this to solve it for KFD too.
>
> ROCm user mode maps VRAM BOs using render nodes. So I'd expect
> ttm_bo_vm_dummy_page to work for KFD as well.
>
> I guess we'd need something special for KFD's doorbell and MMIO (HDP
> flush) mappings. Was that the discussion about the file address space?
Yes
Andrey
>
> Regards,
> Felix
>
>
>>
>> Andrey
>>
>>>
>>> Regards,
>>> Felix
>>>
>>>
>>>>
>>>> Andrey
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2021-04-29 16:33 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-28 15:11 [PATCH v5 00/27] RFC Support hot device unplug in amdgpu Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 01/27] drm/ttm: Remap all page faults to per process dummy page Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 02/27] drm/ttm: Expose ttm_tt_unpopulate for driver use Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 03/27] drm/amdgpu: Split amdgpu_device_fini into early and late Andrey Grodzovsky
2021-04-29 7:04 ` Christian König
2021-04-30 3:10 ` Alex Deucher
2021-04-30 5:19 ` Lazar, Lijo
2021-04-30 5:39 ` Andrey Grodzovsky
2021-04-30 5:49 ` Lazar, Lijo
2021-04-28 15:11 ` [PATCH v5 04/27] drm/amdkfd: Split kfd suspend from devie exit Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 05/27] drm/amdgpu: Add early fini callback Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 06/27] drm/amdgpu: Handle IOMMU enabled case Andrey Grodzovsky
2021-04-29 7:08 ` Christian König
2021-05-03 20:43 ` Andrey Grodzovsky
2021-05-04 7:03 ` Christian König
2021-05-04 15:43 ` Andrey Grodzovsky
2021-05-05 14:51 ` Andrey Grodzovsky
2021-04-30 3:13 ` Alex Deucher
2021-05-03 18:00 ` Andrey Grodzovsky
2021-05-04 17:05 ` Felix Kuehling
2021-05-05 14:05 ` Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 07/27] drm/amdgpu: Remap all page faults to per process dummy page Andrey Grodzovsky
2021-04-29 7:09 ` Christian König
2021-04-28 15:11 ` [PATCH v5 08/27] PCI: add support for dev_groups to struct pci_device_driver Andrey Grodzovsky
2021-04-28 16:53 ` Bjorn Helgaas
2021-04-29 16:53 ` Andrey Grodzovsky
2021-04-29 19:23 ` Bjorn Helgaas
2021-04-29 20:36 ` Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 09/27] dmr/amdgpu: Move some sysfs attrs creation to default_attr Andrey Grodzovsky
2021-04-28 17:23 ` Bjorn Helgaas
2021-04-29 7:11 ` Christian König
2021-04-28 15:11 ` [PATCH v5 10/27] drm/amdgpu: Guard against write accesses after device removal Andrey Grodzovsky
2021-04-29 7:14 ` Christian König
2021-04-28 15:11 ` [PATCH v5 11/27] drm/sched: Make timeout timer rearm conditional Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 12/27] drm/amdgpu: Prevent any job recoveries after device is unplugged Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 13/27] drm/amdgpu: When filizing the fence driver. stop scheduler first Andrey Grodzovsky
2021-04-29 7:15 ` Christian König
2021-04-29 17:12 ` Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 14/27] drm/amdgpu: Fix hang on device removal Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 15/27] drm/scheduler: Fix hang when sched_entity released Andrey Grodzovsky
2021-04-29 7:18 ` Christian König
2021-04-29 17:06 ` Andrey Grodzovsky
2021-04-30 6:47 ` Christian König
2021-04-30 16:10 ` Andrey Grodzovsky
2021-05-05 13:57 ` Andrey Grodzovsky
2021-05-07 16:29 ` Daniel Vetter
2021-05-07 16:32 ` Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 16/27] drm/amdgpu: Unmap all MMIO mappings Andrey Grodzovsky
2021-04-29 7:19 ` Christian König
2021-04-29 16:55 ` Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 17/27] drm/amdgpu: Add rw_sem to pushing job into sched queue Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 18/27] drm/sched: Expose drm_sched_entity_kill_jobs Andrey Grodzovsky
2021-04-28 15:11 ` [PATCH v5 19/27] drm/amdgpu: Finilise device fences on device remove Andrey Grodzovsky
2021-04-28 15:20 ` Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 20/27] drm: Scope all DRM IOCTLs with drm_dev_enter/exit Andrey Grodzovsky
2021-04-29 11:23 ` Daniel Vetter
2021-04-29 11:32 ` Daniel Vetter
2021-04-29 16:04 ` Andrey Grodzovsky
2021-04-29 16:15 ` Felix Kuehling
2021-04-29 16:21 ` Andrey Grodzovsky
2021-04-29 16:29 ` Felix Kuehling
2021-04-29 16:33 ` Andrey Grodzovsky [this message]
2021-04-29 19:05 ` Daniel Vetter
2021-04-29 20:34 ` Andrey Grodzovsky
2021-04-30 10:25 ` Daniel Vetter
2021-04-30 17:27 ` Andrey Grodzovsky
2021-05-05 13:57 ` Andrey Grodzovsky
2021-05-06 9:40 ` Daniel Vetter
2021-05-06 16:25 ` Andrey Grodzovsky
2021-05-07 9:11 ` Daniel Vetter
2021-05-07 15:39 ` Andrey Grodzovsky
2021-05-07 16:24 ` Daniel Vetter
2021-05-07 18:00 ` Andrey Grodzovsky
2021-05-10 15:46 ` Daniel Vetter
2021-04-28 15:12 ` [PATCH v5 21/27] drm/amdgpu: Add support for hot-unplug feature at DRM level Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 22/27] drm/amd/display: Scope all DM queued work with drm_dev_enter/exit Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 23/27] drm/amd/powerplay: Scope all PM " Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 24/27] drm/amdkfd: Scope all KFD " Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 25/27] drm/amdgpu: Scope all amdgpu " Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 26/27] drm/amd/display: Remove superflous drm_mode_config_cleanup Andrey Grodzovsky
2021-04-28 15:12 ` [PATCH v5 27/27] drm/amdgpu: Verify DMA opearations from device are done Andrey Grodzovsky
2021-04-28 17:07 ` [PATCH v5 00/27] RFC Support hot device unplug in amdgpu Bjorn Helgaas
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=6d56684c-1964-f023-7d23-f0e5042941c5@amd.com \
--to=andrey.grodzovsky@amd.com \
--cc=Alexander.Deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=ckoenig.leichtzumerken@gmail.com \
--cc=daniel.vetter@ffwll.ch \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=gregkh@linuxfoundation.org \
--cc=helgaas@kernel.org \
--cc=linux-pci@vger.kernel.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).