dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: "Christian König" <christian.koenig@amd.com>
To: Andrey Grodzovsky <andrey.grodzovsky@amd.com>,
	dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org
Cc: horace.chen@amd.com, Monk.Liu@amd.com
Subject: Re: [RFC v2 2/8] drm/amdgpu: Move scheduler init to after XGMI is ready
Date: Thu, 23 Dec 2021 09:39:43 +0100	[thread overview]
Message-ID: <4f8564b4-752c-5d0e-437e-6dcff8eb54fe@amd.com> (raw)
In-Reply-To: <20211222220506.789133-3-andrey.grodzovsky@amd.com>

Am 22.12.21 um 23:05 schrieb Andrey Grodzovsky:
> Before we initialize schedulers we must know which reset
> domain are we in - for single device there iis a single
> domain per device and so single wq per device. For XGMI
> the reset domain spans the entire XGMI hive and so the
> reset wq is per hive.
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 45 ++++++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 34 ++--------------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  2 +
>   3 files changed, 51 insertions(+), 30 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 0f3e6c078f88..7c063fd37389 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -2284,6 +2284,47 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
>   	return r;
>   }
>   
> +static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
> +{
> +	long timeout;
> +	int r, i;
> +
> +	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> +		struct amdgpu_ring *ring = adev->rings[i];
> +
> +		/* No need to setup the GPU scheduler for rings that don't need it */
> +		if (!ring || ring->no_scheduler)
> +			continue;
> +
> +		switch (ring->funcs->type) {
> +		case AMDGPU_RING_TYPE_GFX:
> +			timeout = adev->gfx_timeout;
> +			break;
> +		case AMDGPU_RING_TYPE_COMPUTE:
> +			timeout = adev->compute_timeout;
> +			break;
> +		case AMDGPU_RING_TYPE_SDMA:
> +			timeout = adev->sdma_timeout;
> +			break;
> +		default:
> +			timeout = adev->video_timeout;
> +			break;
> +		}
> +
> +		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
> +				   ring->num_hw_submission, amdgpu_job_hang_limit,
> +				   timeout, adev->reset_domain.wq, ring->sched_score, ring->name);
> +		if (r) {
> +			DRM_ERROR("Failed to create scheduler on ring %s.\n",
> +				  ring->name);
> +			return r;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
> +
>   /**
>    * amdgpu_device_ip_init - run init for hardware IPs
>    *
> @@ -2412,6 +2453,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
>   		}
>   	}
>   
> +	r = amdgpu_device_init_schedulers(adev);
> +	if (r)
> +		goto init_failed;
> +
>   	/* Don't init kfd if whole hive need to be reset during init */
>   	if (!adev->gmc.xgmi.pending_reset)
>   		amdgpu_amdkfd_device_init(adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 3b7e86ea7167..5527c68c51de 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -456,8 +456,6 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>   				  atomic_t *sched_score)
>   {
>   	struct amdgpu_device *adev = ring->adev;
> -	long timeout;
> -	int r;
>   
>   	if (!adev)
>   		return -EINVAL;
> @@ -477,36 +475,12 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>   	spin_lock_init(&ring->fence_drv.lock);
>   	ring->fence_drv.fences = kcalloc(num_hw_submission * 2, sizeof(void *),
>   					 GFP_KERNEL);
> -	if (!ring->fence_drv.fences)
> -		return -ENOMEM;
>   
> -	/* No need to setup the GPU scheduler for rings that don't need it */
> -	if (ring->no_scheduler)
> -		return 0;
> +	ring->num_hw_submission = num_hw_submission;
> +	ring->sched_score = sched_score;
>   
> -	switch (ring->funcs->type) {
> -	case AMDGPU_RING_TYPE_GFX:
> -		timeout = adev->gfx_timeout;
> -		break;
> -	case AMDGPU_RING_TYPE_COMPUTE:
> -		timeout = adev->compute_timeout;
> -		break;
> -	case AMDGPU_RING_TYPE_SDMA:
> -		timeout = adev->sdma_timeout;
> -		break;
> -	default:
> -		timeout = adev->video_timeout;
> -		break;
> -	}
> -
> -	r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
> -			   num_hw_submission, amdgpu_job_hang_limit,
> -			   timeout, NULL, sched_score, ring->name);
> -	if (r) {
> -		DRM_ERROR("Failed to create scheduler on ring %s.\n",
> -			  ring->name);
> -		return r;
> -	}
> +	if (!ring->fence_drv.fences)
> +		return -ENOMEM;
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> index 4d380e79752c..a4b8279e3011 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> @@ -253,6 +253,8 @@ struct amdgpu_ring {
>   	bool			has_compute_vm_bug;
>   	bool			no_scheduler;
>   	int			hw_prio;
> +	unsigned 		num_hw_submission;
> +	atomic_t		*sched_score;
>   };
>   
>   #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))


  reply	other threads:[~2021-12-23  8:39 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-22 22:04 [RFC v2 0/8] Define and use reset domain for GPU recovery in amdgpu Andrey Grodzovsky
2021-12-22 22:04 ` [RFC v2 1/8] drm/amdgpu: Introduce reset domain Andrey Grodzovsky
2021-12-22 22:05 ` [RFC v2 2/8] drm/amdgpu: Move scheduler init to after XGMI is ready Andrey Grodzovsky
2021-12-23  8:39   ` Christian König [this message]
2021-12-22 22:05 ` [RFC v2 3/8] drm/amdgpu: Fix crash on modprobe Andrey Grodzovsky
2021-12-23  8:40   ` Christian König
2021-12-22 22:05 ` [RFC v2 4/8] drm/amdgpu: Serialize non TDR gpu recovery with TDRs Andrey Grodzovsky
2021-12-23  8:41   ` Christian König
2022-01-05  9:54   ` Lazar, Lijo
2022-01-05 12:31     ` Christian König
2022-01-05 13:11       ` Lazar, Lijo
2022-01-05 13:15         ` Christian König
2022-01-05 13:26           ` Lazar, Lijo
2022-01-05 13:41             ` Christian König
2022-01-05 18:11       ` Andrey Grodzovsky
2022-01-17 19:14         ` Andrey Grodzovsky
2022-01-17 19:17           ` Christian König
2022-01-17 19:21             ` Andrey Grodzovsky
2022-01-26 15:52               ` Andrey Grodzovsky
2022-01-28 16:57                 ` Grodzovsky, Andrey
2022-02-07  2:41                   ` JingWen Chen
2022-02-07  3:08                     ` Grodzovsky, Andrey
2021-12-22 22:13 ` [RFC v2 5/8] drm/amd/virt: For SRIOV send GPU reset directly to TDR queue Andrey Grodzovsky
2021-12-22 22:13   ` [RFC v2 6/8] drm/amdgpu: Drop hive->in_reset Andrey Grodzovsky
2021-12-22 22:13   ` [RFC v2 7/8] drm/amdgpu: Drop concurrent GPU reset protection for device Andrey Grodzovsky
2021-12-22 22:14   ` [RFC v2 8/8] drm/amd/virt: Drop concurrent GPU reset protection for SRIOV Andrey Grodzovsky
2021-12-23  8:42     ` Christian König
2021-12-23 10:14       ` Liu, Monk
2021-12-24  8:58         ` Deng, Emily
2021-12-24  9:57           ` JingWen Chen
2021-12-30 18:45             ` Andrey Grodzovsky
2022-01-03 10:17               ` Christian König
2022-01-04  9:07                 ` JingWen Chen
2022-01-04 10:18                   ` Christian König
2022-01-04 10:49                     ` Liu, Monk
2022-01-04 11:36                       ` Christian König
2022-01-04 16:56                         ` Andrey Grodzovsky
2022-01-05  7:34                           ` JingWen Chen
2022-01-05  7:59                             ` Christian König
2022-01-05 18:24                               ` Andrey Grodzovsky
2022-01-06  4:59                                 ` JingWen Chen
2022-01-06  5:18                                   ` JingWen Chen
2022-01-06  9:13                                     ` Christian König
2022-01-06 19:13                                     ` Andrey Grodzovsky
2022-01-07  3:57                                       ` JingWen Chen
2022-01-07  5:46                                         ` JingWen Chen
2022-01-07 16:02                                           ` Andrey Grodzovsky
2022-01-12  6:28                                             ` JingWen Chen
2022-01-04 17:13                         ` Liu, Shaoyun
2022-01-04 20:54                           ` Andrey Grodzovsky
2022-01-05  0:01                             ` Liu, Shaoyun
2022-01-05  7:25                         ` JingWen Chen
2021-12-30 18:39           ` Andrey Grodzovsky
2021-12-23 18:07     ` Liu, Shaoyun
2021-12-23 18:29   ` [RFC v3 5/8] drm/amd/virt: For SRIOV send GPU reset directly to TDR queue Andrey Grodzovsky

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=4f8564b4-752c-5d0e-437e-6dcff8eb54fe@amd.com \
    --to=christian.koenig@amd.com \
    --cc=Monk.Liu@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=andrey.grodzovsky@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=horace.chen@amd.com \
    /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).