AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Boris Brezillon <boris.brezillon@collabora.com>
To: Steven Price <steven.price@arm.com>
Cc: dri-devel@lists.freedesktop.org,
	"Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
	"Maxime Ripard" <mripard@kernel.org>,
	"Thomas Zimmermann" <tzimmermann@suse.de>,
	"David Airlie" <airlied@gmail.com>,
	"Simona Vetter" <simona@ffwll.ch>,
	"Faith Ekstrand" <faith.ekstrand@collabora.com>,
	"Thierry Reding" <thierry.reding@gmail.com>,
	"Mikko Perttunen" <mperttunen@nvidia.com>,
	"Melissa Wen" <mwen@igalia.com>,
	"Maíra Canal" <mcanal@igalia.com>,
	"Lucas De Marchi" <lucas.demarchi@intel.com>,
	"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	"Frank Binns" <frank.binns@imgtec.com>,
	"Matt Coster" <matt.coster@imgtec.com>,
	"Rob Clark" <robin.clark@oss.qualcomm.com>,
	"Dmitry Baryshkov" <lumag@kernel.org>,
	"Abhinav Kumar" <abhinav.kumar@linux.dev>,
	"Jessica Zhang" <jessica.zhang@oss.qualcomm.com>,
	"Sean Paul" <sean@poorly.run>,
	"Marijn Suijten" <marijn.suijten@somainline.org>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Christian König" <christian.koenig@amd.com>,
	amd-gfx@lists.freedesktop.org, kernel@collabora.com
Subject: Re: [PATCH v6 06/16] drm/panthor: Expose the selected coherency protocol to the UMD
Date: Wed, 26 Nov 2025 14:25:04 +0100	[thread overview]
Message-ID: <20251126142504.5654962f@fedora> (raw)
In-Reply-To: <20251126124455.3656651-7-boris.brezillon@collabora.com>

On Wed, 26 Nov 2025 13:44:45 +0100
Boris Brezillon <boris.brezillon@collabora.com> wrote:

> If we want to be able to skip CPU cache maintenance operations on
> CPU-cached mappings, the UMD needs to know the kind of coherency
> in place. Add a field to drm_panthor_gpu_info to do that. We can re-use
> a padding field for that since this object is write-only from the
> KMD perspective, and the UMD should just ignore it.
> 
> v2:
> - New commit
> 
> v3:
> - Make coherency protocol a real enum, not a bitmask
> - Add BUILD_BUG_ON()s to make sure the values in panthor_regs.h and
>   those exposed through the uAPI match
> 
> v4:
> - Add Steve's R-b
> 
> v5:
> - No changes
> 
> v6:
> - No changes
> 
> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
> Reviewed-by: Steven Price <steven.price@arm.com>
> ---
>  drivers/gpu/drm/panthor/panthor_device.c | 10 +++++-
>  drivers/gpu/drm/panthor/panthor_gpu.c    |  2 +-
>  include/uapi/drm/panthor_drm.h           | 39 ++++++++++++++++++++++--
>  3 files changed, 46 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
> index e133b1e0ad6d..a66fc66999c2 100644
> --- a/drivers/gpu/drm/panthor/panthor_device.c
> +++ b/drivers/gpu/drm/panthor/panthor_device.c
> @@ -27,6 +27,12 @@
>  
>  static int panthor_gpu_coherency_init(struct panthor_device *ptdev)
>  {
> +	BUILD_BUG_ON(GPU_COHERENCY_NONE != DRM_PANTHOR_GPU_COHERENCY_NONE);
> +	BUILD_BUG_ON(GPU_COHERENCY_ACE_LITE != DRM_PANTHOR_GPU_COHERENCY_ACE_LITE);
> +	BUILD_BUG_ON(GPU_COHERENCY_ACE != DRM_PANTHOR_GPU_COHERENCY_ACE);
> +
> +	/* Start with no coherency, and update it if the device is flagged coherent. */
> +	ptdev->gpu_info.selected_coherency = GPU_COHERENCY_NONE;
>  	ptdev->coherent = device_get_dma_attr(ptdev->base.dev) == DEV_DMA_COHERENT;
>  
>  	if (!ptdev->coherent)
> @@ -36,8 +42,10 @@ static int panthor_gpu_coherency_init(struct panthor_device *ptdev)
>  	 * ACE protocol has never been supported for command stream frontend GPUs.
>  	 */
>  	if ((gpu_read(ptdev, GPU_COHERENCY_FEATURES) &
> -		      GPU_COHERENCY_PROT_BIT(ACE_LITE)))
> +		      GPU_COHERENCY_PROT_BIT(ACE_LITE))) {
> +		ptdev->gpu_info.selected_coherency = GPU_COHERENCY_ACE_LITE;
>  		return 0;
> +	}
>  
>  	drm_err(&ptdev->base, "Coherency not supported by the device");
>  	return -ENOTSUPP;
> diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
> index cd38da5ad26c..b7c64be0b6e2 100644
> --- a/drivers/gpu/drm/panthor/panthor_gpu.c
> +++ b/drivers/gpu/drm/panthor/panthor_gpu.c
> @@ -51,7 +51,7 @@ struct panthor_gpu {
>  static void panthor_gpu_coherency_set(struct panthor_device *ptdev)
>  {
>  	gpu_write(ptdev, GPU_COHERENCY_PROTOCOL,
> -		  ptdev->coherent ? GPU_COHERENCY_ACE_LITE : GPU_COHERENCY_NONE);
> +		  ptdev->gpu_info.selected_coherency);
>  }
>  
>  static void panthor_gpu_l2_config_set(struct panthor_device *ptdev)
> diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h
> index 467d365ed7ba..f0f637e0631d 100644
> --- a/include/uapi/drm/panthor_drm.h
> +++ b/include/uapi/drm/panthor_drm.h
> @@ -245,6 +245,26 @@ enum drm_panthor_dev_query_type {
>  	DRM_PANTHOR_DEV_QUERY_GROUP_PRIORITIES_INFO,
>  };
>  
> +/**
> + * enum drm_panthor_gpu_coherency: Type of GPU coherency
> + */
> +enum drm_panthor_gpu_coherency {
> +	/**
> +	 * @DRM_PANTHOR_GPU_COHERENCY_ACE_LITE: ACE Lite coherency.
> +	 */
> +	DRM_PANTHOR_GPU_COHERENCY_ACE_LITE = 0,
> +
> +	/**
> +	 * @DRM_PANTHOR_GPU_COHERENCY_ACE_LITE: ACE coherency.

Forgot to fix:

	 * @DRM_PANTHOR_GPU_COHERENCY_ACE: ACE coherency.

> +	 */
> +	DRM_PANTHOR_GPU_COHERENCY_ACE = 1,
> +
> +	/**
> +	 * @DRM_PANTHOR_GPU_COHERENCY_NONE: No coherency.
> +	 */
> +	DRM_PANTHOR_GPU_COHERENCY_NONE = 31,
> +};
> +
>  /**
>   * struct drm_panthor_gpu_info - GPU information
>   *
> @@ -301,7 +321,16 @@ struct drm_panthor_gpu_info {
>  	 */
>  	__u32 thread_max_barrier_size;
>  
> -	/** @coherency_features: Coherency features. */
> +	/**
> +	 * @coherency_features: Coherency features.
> +	 *
> +	 * Combination of drm_panthor_gpu_coherency flags.
> +	 *
> +	 * Note that this is just what the coherency protocols supported by the
> +	 * GPU, but the actual coherency in place depends on the SoC
> +	 * integration and is reflected by
> +	 * drm_panthor_gpu_info::selected_coherency.
> +	 */
>  	__u32 coherency_features;
>  
>  	/** @texture_features: Texture features. */
> @@ -310,8 +339,12 @@ struct drm_panthor_gpu_info {
>  	/** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */
>  	__u32 as_present;
>  
> -	/** @pad0: MBZ. */
> -	__u32 pad0;
> +	/**
> +	 * @select_coherency: Coherency selected for this device.
> +	 *
> +	 * One of drm_panthor_gpu_coherency.
> +	 */
> +	__u32 selected_coherency;
>  
>  	/** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */
>  	__u64 shader_present;


  reply	other threads:[~2025-11-26 13:25 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-26 12:44 [PATCH v6 00/16] drm/panfrost, panthor: Cached maps and explicit flushing Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 01/16] drm/prime: Simplify life of drivers needing custom dma_buf_ops Boris Brezillon
2025-11-26 16:20   ` Steven Price
2025-11-27  8:34   ` Thomas Zimmermann
2025-11-27  8:42     ` Thomas Zimmermann
2025-11-27  8:58       ` Thomas Zimmermann
2025-11-27 10:44         ` Boris Brezillon
2025-11-27 12:32           ` Boris Brezillon
2025-11-27 13:05             ` Boris Brezillon
2025-11-27 10:34       ` Boris Brezillon
2025-11-27 10:40     ` Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 02/16] drm/shmem: Provide a generic {begin, end}_cpu_access() implementation Boris Brezillon
2025-11-26 16:23   ` [PATCH v6 02/16] drm/shmem: Provide a generic {begin,end}_cpu_access() implementation Steven Price
2025-11-26 12:44 ` [PATCH v6 03/16] drm/shmem: Add a drm_gem_shmem_sync() helper Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 04/16] drm/panthor: Provide a custom dma_buf implementation Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 05/16] drm/panthor: Fix panthor_gpu_coherency_set() Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 06/16] drm/panthor: Expose the selected coherency protocol to the UMD Boris Brezillon
2025-11-26 13:25   ` Boris Brezillon [this message]
2025-11-26 12:44 ` [PATCH v6 07/16] drm/panthor: Add a PANTHOR_BO_SYNC ioctl Boris Brezillon
2025-11-26 16:25   ` Steven Price
2025-11-26 12:44 ` [PATCH v6 08/16] drm/panthor: Add an ioctl to query BO flags Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 09/16] drm/panthor: Add flag to map GEM object Write-Back Cacheable Boris Brezillon
2025-11-26 16:27   ` Steven Price
2025-11-26 12:44 ` [PATCH v6 10/16] drm/panthor: Bump the driver version to 1.6 Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 11/16] drm/panfrost: Provide a custom dma_buf implementation Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 12/16] drm/panfrost: Expose the selected coherency protocol to the UMD Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 13/16] drm/panfrost: Add a PANFROST_SYNC_BO ioctl Boris Brezillon
2025-11-26 16:47   ` Steven Price
2025-11-26 12:44 ` [PATCH v6 14/16] drm/panfrost: Add an ioctl to query BO flags Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 15/16] drm/panfrost: Add flag to map GEM object Write-Back Cacheable Boris Brezillon
2025-11-26 12:44 ` [PATCH v6 16/16] drm/panfrost: Bump the driver version to 1.6 Boris Brezillon
2025-11-26 16:20 ` [PATCH v6 00/16] drm/panfrost,panthor: Cached maps and explicit flushing Thomas Zimmermann
2025-11-26 17:24   ` Boris Brezillon

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=20251126142504.5654962f@fedora \
    --to=boris.brezillon@collabora.com \
    --cc=abhinav.kumar@linux.dev \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=faith.ekstrand@collabora.com \
    --cc=frank.binns@imgtec.com \
    --cc=jessica.zhang@oss.qualcomm.com \
    --cc=kernel@collabora.com \
    --cc=lucas.demarchi@intel.com \
    --cc=lumag@kernel.org \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=marijn.suijten@somainline.org \
    --cc=matt.coster@imgtec.com \
    --cc=mcanal@igalia.com \
    --cc=mperttunen@nvidia.com \
    --cc=mripard@kernel.org \
    --cc=mwen@igalia.com \
    --cc=robin.clark@oss.qualcomm.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=sean@poorly.run \
    --cc=simona@ffwll.ch \
    --cc=steven.price@arm.com \
    --cc=thierry.reding@gmail.com \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tzimmermann@suse.de \
    /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