Re: [PATCH] drm/amdgpu: Make the submission path memory reclaim safe

[Oleksandr Natalenko <oleksandr@natalenko.name>]

[-- Attachment #1: Type: text/plain, Size: 5274 bytes --]

On středa 13. listopadu 2024 14:48:38, středoevropský standardní čas Tvrtko Ursulin wrote:
> From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> 
> As commit 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
> points out, ever since
> a6149f039369 ("drm/sched: Convert drm scheduler to use a work queue rather than kthread"),
> any workqueue flushing done from the job submission path must only
> involve memory reclaim safe workqueues to be safe against reclaim
> deadlocks.
> 
> This is also pointed out by workqueue sanity checks:
> 
>  [ ] workqueue: WQ_MEM_RECLAIM sdma0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_device_delay_enable_gfx_off [amdgpu]
> ...
>  [ ] Workqueue: sdma0 drm_sched_run_job_work [gpu_sched]
> ...
>  [ ] Call Trace:
>  [ ]  <TASK>
> ...
>  [ ]  ? check_flush_dependency+0xf5/0x110
> ...
>  [ ]  cancel_delayed_work_sync+0x6e/0x80
>  [ ]  amdgpu_gfx_off_ctrl+0xab/0x140 [amdgpu]
>  [ ]  amdgpu_ring_alloc+0x40/0x50 [amdgpu]
>  [ ]  amdgpu_ib_schedule+0xf4/0x810 [amdgpu]
>  [ ]  ? drm_sched_run_job_work+0x22c/0x430 [gpu_sched]
>  [ ]  amdgpu_job_run+0xaa/0x1f0 [amdgpu]
>  [ ]  drm_sched_run_job_work+0x257/0x430 [gpu_sched]
>  [ ]  process_one_work+0x217/0x720
> ...
>  [ ]  </TASK>
> 
> Fix this by creating a memory reclaim safe driver workqueue and make the
> submission path use it.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> References: 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
> Fixes: a6149f039369 ("drm/sched: Convert drm scheduler to use a work queue rather than kthread")
> Cc: stable@vger.kernel.org
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: Philipp Stanner <pstanner@redhat.com>
> Cc: Alex Deucher <alexander.deucher@amd.com>
> Cc: Christian König <christian.koenig@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu.h     |  2 ++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 25 +++++++++++++++++++++++++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c |  5 +++--
>  3 files changed, 30 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 7645e498faa4..a6aad687537e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -268,6 +268,8 @@ extern int amdgpu_agp;
>  
>  extern int amdgpu_wbrf;
>  
> +extern struct workqueue_struct *amdgpu_reclaim_wq;
> +
>  #define AMDGPU_VM_MAX_NUM_CTX			4096
>  #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
>  #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 38686203bea6..f5b7172e8042 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -255,6 +255,8 @@ struct amdgpu_watchdog_timer amdgpu_watchdog_timer = {
>  	.period = 0x0, /* default to 0x0 (timeout disable) */
>  };
>  
> +struct workqueue_struct *amdgpu_reclaim_wq;
> +
>  /**
>   * DOC: vramlimit (int)
>   * Restrict the total amount of VRAM in MiB for testing.  The default is 0 (Use full VRAM).
> @@ -2971,6 +2973,21 @@ static struct pci_driver amdgpu_kms_pci_driver = {
>  	.dev_groups = amdgpu_sysfs_groups,
>  };
>  
> +static int amdgpu_wq_init(void)
> +{
> +	amdgpu_reclaim_wq =
> +		alloc_workqueue("amdgpu-reclaim", WQ_MEM_RECLAIM, 0);
> +	if (!amdgpu_reclaim_wq)
> +		return -ENOMEM;
> +
> +	return 0;
> +}
> +
> +static void amdgpu_wq_fini(void)
> +{
> +	destroy_workqueue(amdgpu_reclaim_wq);
> +}
> +
>  static int __init amdgpu_init(void)
>  {
>  	int r;
> @@ -2978,6 +2995,10 @@ static int __init amdgpu_init(void)
>  	if (drm_firmware_drivers_only())
>  		return -EINVAL;
>  
> +	r = amdgpu_wq_init();
> +	if (r)
> +		goto error_wq;
> +
>  	r = amdgpu_sync_init();
>  	if (r)
>  		goto error_sync;
> @@ -3006,6 +3027,9 @@ static int __init amdgpu_init(void)
>  	amdgpu_sync_fini();
>  
>  error_sync:
> +	amdgpu_wq_fini();
> +
> +error_wq:
>  	return r;
>  }
>  
> @@ -3017,6 +3041,7 @@ static void __exit amdgpu_exit(void)
>  	amdgpu_acpi_release();
>  	amdgpu_sync_fini();
>  	amdgpu_fence_slab_fini();
> +	amdgpu_wq_fini();
>  	mmu_notifier_synchronize();
>  	amdgpu_xcp_drv_release();
>  }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> index 2f3f09dfb1fd..f8fd71d9382f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
> @@ -790,8 +790,9 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
>  						AMD_IP_BLOCK_TYPE_GFX, true))
>  					adev->gfx.gfx_off_state = true;
>  			} else {
> -				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
> -					      delay);
> +				queue_delayed_work(amdgpu_reclaim_wq,
> +						   &adev->gfx.gfx_off_delay_work,
> +						   delay);
>  			}
>  		}
>  	} else {

I can confirm this fixed the warning for me.

Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>

What's the fate of this submission?

Thank you.

-- 
Oleksandr Natalenko, MSE

[-- Attachment #2: This is a digitally signed message part. --]
[-- Type: application/pgp-signature, Size: 833 bytes --]