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: <19925e9c-90c4-406f-9160-7f1e8da9352d@gmail.com>
Date: Wed, 18 Sep 2024 13:20:10 +0200
From: Antonino Maniscalco <antomani103@...il.com>
To: neil.armstrong@...aro.org, Rob Clark <robdclark@...il.com>,
 Sean Paul <sean@...rly.run>, Konrad Dybcio <konrad.dybcio@...aro.org>,
 Abhinav Kumar <quic_abhinavk@...cinc.com>,
 Dmitry Baryshkov <dmitry.baryshkov@...aro.org>,
 Marijn Suijten <marijn.suijten@...ainline.org>,
 David Airlie <airlied@...il.com>, Daniel Vetter <daniel@...ll.ch>,
 Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
 Maxime Ripard <mripard@...nel.org>, Thomas Zimmermann <tzimmermann@...e.de>,
 Jonathan Corbet <corbet@....net>
Cc: linux-arm-msm@...r.kernel.org, dri-devel@...ts.freedesktop.org,
 freedreno@...ts.freedesktop.org, linux-kernel@...r.kernel.org,
 linux-doc@...r.kernel.org, Akhil P Oommen <quic_akhilpo@...cinc.com>,
 Sharat Masetty <smasetty@...eaurora.org>
Subject: Re: [PATCH v4 00/11] Preemption support for A7XX

On 9/18/24 9:46 AM, Neil Armstrong wrote:
> Hi,
> 
> On 17/09/2024 13:14, Antonino Maniscalco wrote:
>> This series implements preemption for A7XX targets, which allows the 
>> GPU to
>> switch to an higher priority ring when work is pushed to it, reducing 
>> latency
>> for high priority submissions.
>>
>> This series enables L1 preemption with skip_save_restore which requires
>> the following userspace patches to function:
>>
>> https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30544
>>
>> A flag is added to `msm_submitqueue_create` to only allow submissions
>> from compatible userspace to be preempted, therefore maintaining
>> compatibility.
>>
>> Preemption is currently only enabled by default on A750, it can be
>> enabled on other targets through the `enable_preemption` module
>> parameter. This is because more testing is required on other targets.
>>
>> For testing on other HW it is sufficient to set that parameter to a
>> value of 1, then using the branch of mesa linked above, `TU_DEBUG=hiprio`
>> allows to run any application as high priority therefore preempting
>> submissions from other applications.
>>
>> The `msm_gpu_preemption_trigger` and `msm_gpu_preemption_irq` traces
>> added in this series can be used to observe preemption's behavior as
>> well as measuring preemption latency.
>>
>> Some commits from this series are based on a previous series to enable
>> preemption on A6XX targets:
>>
>> https://lkml.kernel.org/1520489185-21828-1-git-send-email-smasetty@codeaurora.org
>>
>> Signed-off-by: Antonino Maniscalco <antomani103@...il.com>
>> ---
>> Changes in v4:
>> - Added missing register in pwrup list
>> - Removed and rearrange barriers
>> - Renamed `skip_inline_wptr` to `restore_wptr`
>> - Track ctx seqno per ring
>> - Removed secure preempt context
>> - NOP out postamble to disable it instantly
>> - Only emit pwrup reglist once
>> - Document bv_rptr_addr
>> - Removed unused A6XX_PREEMPT_USER_RECORD_SIZE
>> - Set name on preempt record buffer
>> - Link to v3: 
>> https://lore.kernel.org/r/20240905-preemption-a750-t-v3-0-fd947699f7bc@gmail.com
>>
>> Changes in v3:
>> - Added documentation about preemption
>> - Use quirks to determine which target supports preemption
>> - Add a module parameter to force disabling or enabling preemption
>> - Clear postamble when profiling
>> - Define A6XX_CP_CONTEXT_SWITCH_CNTL_LEVEL fields in a6xx.xml
>> - Make preemption records MAP_PRIV
>> - Removed user ctx record (NON_PRIV) and patch 2/9 as it's not needed
>>    anymore
>> - Link to v2: 
>> https://lore.kernel.org/r/20240830-preemption-a750-t-v2-0-86aeead2cd80@gmail.com
>>
>> Changes in v2:
>> - Added preept_record_size for X185 in PATCH 3/7
>> - Added patches to reset perf counters
>> - Dropped unused defines
>> - Dropped unused variable (fixes warning)
>> - Only enable preemption on a750
>> - Reject MSM_SUBMITQUEUE_ALLOW_PREEMPT for unsupported targets
>> - Added Akhil's Reviewed-By tags to patches 1/9,2/9,3/9
>> - Added Neil's Tested-By tags
>> - Added explanation for UAPI changes in commit message
>> - Link to v1: 
>> https://lore.kernel.org/r/20240815-preemption-a750-t-v1-0-7bda26c34037@gmail.com
>>
>> ---
>> Antonino Maniscalco (11):
>>        drm/msm: Fix bv_fence being used as bv_rptr
>>        drm/msm/A6XX: Track current_ctx_seqno per ring
>>        drm/msm: Add a `preempt_record_size` field
>>        drm/msm: Add CONTEXT_SWITCH_CNTL bitfields
>>        drm/msm/A6xx: Implement preemption for A7XX targets
>>        drm/msm/A6xx: Sync relevant adreno_pm4.xml changes
>>        drm/msm/A6xx: Use posamble to reset counters on preemption
>>        drm/msm/A6xx: Add traces for preemption
>>        drm/msm/A6XX: Add a flag to allow preemption to submitqueue_create
>>        drm/msm/A6xx: Enable preemption for A750
>>        Documentation: document adreno preemption
>>
>>   Documentation/gpu/msm-preemption.rst               |  98 +++++
>>   drivers/gpu/drm/msm/Makefile                       |   1 +
>>   drivers/gpu/drm/msm/adreno/a2xx_gpu.c              |   2 +-
>>   drivers/gpu/drm/msm/adreno/a3xx_gpu.c              |   2 +-
>>   drivers/gpu/drm/msm/adreno/a4xx_gpu.c              |   2 +-
>>   drivers/gpu/drm/msm/adreno/a5xx_gpu.c              |   6 +-
>>   drivers/gpu/drm/msm/adreno/a6xx_catalog.c          |   7 +-
>>   drivers/gpu/drm/msm/adreno/a6xx_gpu.c              | 325 
>> ++++++++++++++-
>>   drivers/gpu/drm/msm/adreno/a6xx_gpu.h              | 174 ++++++++
>>   drivers/gpu/drm/msm/adreno/a6xx_preempt.c          | 440 
>> +++++++++++++++++++++
>>   drivers/gpu/drm/msm/adreno/adreno_gpu.h            |   9 +-
>>   drivers/gpu/drm/msm/msm_drv.c                      |   4 +
>>   drivers/gpu/drm/msm/msm_gpu.c                      |   2 +-
>>   drivers/gpu/drm/msm/msm_gpu.h                      |  11 -
>>   drivers/gpu/drm/msm/msm_gpu_trace.h                |  28 ++
>>   drivers/gpu/drm/msm/msm_ringbuffer.h               |  18 +
>>   drivers/gpu/drm/msm/msm_submitqueue.c              |   3 +
>>   drivers/gpu/drm/msm/registers/adreno/a6xx.xml      |   7 +-
>>   .../gpu/drm/msm/registers/adreno/adreno_pm4.xml    |  39 +-
>>   include/uapi/drm/msm_drm.h                         |   5 +-
>>   20 files changed, 1117 insertions(+), 66 deletions(-)
>> ---
>> base-commit: 7c626ce4bae1ac14f60076d00eafe71af30450ba
>> change-id: 20240815-preemption-a750-t-fcee9a844b39
>>
>> Best regards,
> 
> I've been running vulkan-cts 
> (1.3.7.3-0-gd71a36db16d98313c431829432a136dbda692a08 from Yocto)
> on SM8650-QRD, SM8550-QRD & SM8450-HDK boards with enable_preemption in 
> default value
> and forced to 1, and I've seen no regression so far
> 
> On SM8550, I've seen a few:
> platform 3d6a000.gmu: [drm:a6xx_hfi_send_msg.constprop.0 [msm]] *ERROR* 
> Message HFI_H2F_MSG_GX_BW_PERF_VOTE id 2743 timed out waiting for response
> platform 3d6a000.gmu: [drm:a6xx_hfi_send_msg.constprop.0 [msm]] *ERROR* 
> Unexpected message id 2743 on the response queue
> but it's unrelated to preempt
> 
> and on SM8450:
> platform 3d6a000.gmu: [drm:a6xx_gmu_set_oob [msm]] *ERROR* Timeout 
> waiting for GMU OOB set GPU_SET: 0x0
> msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] 
> *ERROR* 7.3.0.1: hangcheck detected gpu lockup rb 0!
> msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] 
> *ERROR* 7.3.0.1:     completed fence: 331235
> msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] 
> *ERROR* 7.3.0.1:     submitted fence: 331236
> adreno 3d00000.gpu: [drm:a6xx_irq [msm]] *ERROR* gpu fault ring 0 fence 
> 50de4 status 00800005 rb 0000/0699 ib1 0000000000000000/0000 ib2 
> 0000000000000000/0000
> msm_dpu ae01000.display-controller: [drm:recover_worker [msm]] *ERROR* 
> 7.3.0.1: hangcheck recover!
> msm_dpu ae01000.display-controller: [drm:recover_worker [msm]] *ERROR* 
> 7.3.0.1: offending task: deqp-vk (/usr/lib/vulkan-cts/deqp-vk)
> msm_dpu ae01000.display-controller: [drm:recover_worker [msm]] *ERROR* 
> 7.3.0.1: hangcheck recover!
> leading to a VK_ERROR_DEVICE_LOST, but again unrelated to preempt support.
> 
> So you can also add:
> Tested-by: Neil Armstrong <neil.armstrong@...aro.org> # on SM8550-QRD
> Tested-by: Neil Armstrong <neil.armstrong@...aro.org> # on SM8450-HDK
> 
> Thanks,
> Neil

Thanks for testing! Enabling for those targets then.

Best regards,
-- 
Antonino Maniscalco <antomani103@...il.com>


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ