AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <christian.koenig@amd.com>
To: Boris Brezillon <boris.brezillon@collabora.com>,
	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>,
	amd-gfx@lists.freedesktop.org, kernel@collabora.com
Subject: Re: [PATCH v5 02/16] drm/shmem: Provide a generic {begin,end}_cpu_access() implementation
Date: Thu, 30 Oct 2025 15:31:44 +0100	[thread overview]
Message-ID: <abbd34de-cbbf-4188-a236-e3eccc357fab@amd.com> (raw)
In-Reply-To: <20251030140525.366636-3-boris.brezillon@collabora.com>

On 10/30/25 15:05, Boris Brezillon wrote:
> The default implementation simply takes care of invalidating/flushing
> caches around CPU accesses. It takes care of both the exporter and
> the importers, which forces us to overload the default
> ::[un]map_dma_buf() implementation provided by drm_gem.c to store the
> sgt.
> 
> v5:
> - New patch
> 
> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
> ---
>  drivers/gpu/drm/drm_gem_shmem_helper.c | 114 +++++++++++++++++++++++++
>  include/drm/drm_gem_shmem_helper.h     |  10 +++
>  2 files changed, 124 insertions(+)
> 
> diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
> index dc94a27710e5..e49c75739c20 100644
> --- a/drivers/gpu/drm/drm_gem_shmem_helper.c
> +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
> @@ -893,6 +893,120 @@ struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev,
>  }
>  EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_import_no_map);
>  
> +/**
> + * drm_gem_shmem_prime_unmap_dma_buf - Default unmap_dma_buf() for exported buffers
> + * @attach: attachment
> + * @sgt: SG table to unmap
> + * @dir: type of access done by this attachment
> + *
> + * Default implementation for dma_buf_ops::map_dma_buf(). This is just a wrapper
> + * around drm_gem_map_dma_buf() that lets us set the dma_buf_attachment::priv
> + * to the sgt so that drm_gem_shmem_prime_{begin,end}_cpu_access() can sync
> + * around CPU accesses.
> + */
> +struct sg_table *
> +drm_gem_shmem_prime_map_dma_buf(struct dma_buf_attachment *attach,
> +				enum dma_data_direction dir)
> +{
> +	struct sg_table *sgt = drm_gem_map_dma_buf(attach, dir);
> +
> +	if (!IS_ERR(sgt))
> +		attach->priv = sgt;
> +
> +	return sgt;
> +}
> +EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_map_dma_buf);
> +
> +/**
> + * drm_gem_shmem_prime_unmap_dma_buf - Default unmap_dma_buf() for exported buffers
> + * @attach: attachment
> + * @sgt: SG table to unmap
> + * @dir: type of access done by this attachment
> + *
> + * Default implementation for dma_buf_ops::unmap_dma_buf(). This is just a wrapper
> + * around drm_gem_unmap_dma_buf() that lets us reset the dma_buf_attachment::priv
> + * field so that drm_gem_shmem_prime_{begin,end}_cpu_access() don't consider it
> + * as a mapped attachment to sync against.
> + */
> +void drm_gem_shmem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
> +				       struct sg_table *sgt,
> +				       enum dma_data_direction dir)
> +{
> +	attach->priv = NULL;
> +	drm_gem_unmap_dma_buf(attach, sgt, dir);
> +}
> +EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_unmap_dma_buf);
> +
> +/**
> + * drm_gem_shmem_prime_begin_cpu_access - Default end_cpu_access() for exported buffers
> + * @dma_buf: The exported DMA buffer this acts on
> + * @dir: direction of the access
> + *
> + * Default implementation for dma_buf_ops::begin_cpu_access(). This only takes care of
> + * cache maintenance.
> + */
> +int drm_gem_shmem_prime_begin_cpu_access(struct dma_buf *dma_buf,
> +					 enum dma_data_direction dir)
> +{
> +	struct drm_gem_object *obj = dma_buf->priv;
> +	struct drm_device *dev = obj->dev;
> +	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
> +	struct dma_buf_attachment *attach;
> +
> +	dma_resv_lock(obj->resv, NULL);
> +	if (shmem->sgt)
> +		dma_sync_sgtable_for_cpu(dev->dev, shmem->sgt, dir);
> +
> +	if (shmem->vaddr)
> +		invalidate_kernel_vmap_range(shmem->vaddr, shmem->base.size);
> +


> +	list_for_each_entry(attach, &dma_buf->attachments, node) {
> +		struct sg_table *sgt = attach->priv;
> +
> +		if (sgt)
> +			dma_sync_sgtable_for_cpu(attach->dev, sgt, dir);
> +	}

This conflicts with the debugging hack in DMA-buf.

I've recently send out a patch to fix that, but it hasn't been pushed yet.

Apart from that looks absolutely reasonable to me.

Regards,
Christian.

> +	dma_resv_unlock(obj->resv);
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_begin_cpu_access);
> +
> +/**
> + * drm_gem_shmem_prime_end_cpu_access - Default end_cpu_access() for exported buffers
> + * @dma_buf: The exported DMA buffer this acts on
> + * @dir: direction of the access
> + *
> + * Default implementation for dma_buf_ops::end_cpu_access(). This only takes care of
> + * cache maintenance.
> + */
> +int drm_gem_shmem_prime_end_cpu_access(struct dma_buf *dma_buf,
> +				       enum dma_data_direction dir)
> +{
> +	struct drm_gem_object *obj = dma_buf->priv;
> +	struct drm_device *dev = obj->dev;
> +	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
> +	struct dma_buf_attachment *attach;
> +
> +	dma_resv_lock(obj->resv, NULL);
> +	list_for_each_entry(attach, &dma_buf->attachments, node) {
> +		struct sg_table *sgt = attach->priv;
> +
> +		if (sgt)
> +			dma_sync_sgtable_for_device(attach->dev, sgt, dir);
> +	}
> +
> +	if (shmem->vaddr)
> +		flush_kernel_vmap_range(shmem->vaddr, shmem->base.size);
> +
> +	if (shmem->sgt)
> +		dma_sync_sgtable_for_device(dev->dev, shmem->sgt, dir);
> +
> +	dma_resv_unlock(obj->resv);
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_end_cpu_access);
> +
>  MODULE_DESCRIPTION("DRM SHMEM memory-management helpers");
>  MODULE_IMPORT_NS("DMA_BUF");
>  MODULE_LICENSE("GPL v2");
> diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
> index 589f7bfe7506..075275d6b2fd 100644
> --- a/include/drm/drm_gem_shmem_helper.h
> +++ b/include/drm/drm_gem_shmem_helper.h
> @@ -291,6 +291,16 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
>  			      struct drm_mode_create_dumb *args);
>  struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev,
>  							 struct dma_buf *buf);
> +struct sg_table *
> +drm_gem_shmem_prime_map_dma_buf(struct dma_buf_attachment *attach,
> +				enum dma_data_direction dir);
> +void drm_gem_shmem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
> +				       struct sg_table *sgt,
> +				       enum dma_data_direction dir);
> +int drm_gem_shmem_prime_begin_cpu_access(struct dma_buf *dma_buf,
> +					 enum dma_data_direction dir);
> +int drm_gem_shmem_prime_end_cpu_access(struct dma_buf *dma_buf,
> +				       enum dma_data_direction dir);
>  
>  /**
>   * DRM_GEM_SHMEM_DRIVER_OPS - Default shmem GEM operations


  reply	other threads:[~2025-10-30 14:32 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-30 14:05 [PATCH v5 00/16] drm/panfrost, panthor: Cached maps and explicit flushing Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 01/16] drm/prime: Simplify life of drivers needing custom dma_buf_ops Boris Brezillon
2025-10-30 14:25   ` Christian König
2025-10-30 14:35     ` Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 02/16] drm/shmem: Provide a generic {begin, end}_cpu_access() implementation Boris Brezillon
2025-10-30 14:31   ` Christian König [this message]
2025-11-04  8:08     ` [PATCH v5 02/16] drm/shmem: Provide a generic {begin,end}_cpu_access() implementation Boris Brezillon
2025-11-03 20:34   ` [PATCH v5 02/16] drm/shmem: Provide a generic {begin, end}_cpu_access() implementation Akash Goel
2025-11-04  7:42     ` Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 03/16] drm/shmem: Add a drm_gem_shmem_sync() helper Boris Brezillon
2025-11-14 15:02   ` Steven Price
2025-10-30 14:05 ` [PATCH v5 04/16] drm/panthor: Provide a custom dma_buf implementation Boris Brezillon
2025-11-14 15:02   ` Steven Price
2025-10-30 14:05 ` [PATCH v5 05/16] drm/panthor: Fix panthor_gpu_coherency_set() Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 06/16] drm/panthor: Expose the selected coherency protocol to the UMD Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 07/16] drm/panthor: Add a PANTHOR_BO_SYNC ioctl Boris Brezillon
2025-10-31  7:25   ` Marcin Ślusarz
2025-11-03 20:42   ` Akash Goel
2025-11-04  7:41     ` Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 08/16] drm/panthor: Add an ioctl to query BO flags Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 09/16] drm/panthor: Add flag to map GEM object Write-Back Cacheable Boris Brezillon
2025-11-03 16:43   ` Akash Goel
2025-11-03 17:13     ` Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 10/16] drm/panthor: Bump the driver version to 1.6 Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 11/16] drm/panfrost: Provide a custom dma_buf implementation Boris Brezillon
2025-11-14 16:17   ` Steven Price
2025-10-30 14:05 ` [PATCH v5 12/16] drm/panfrost: Expose the selected coherency protocol to the UMD Boris Brezillon
2025-11-14 16:19   ` Steven Price
2025-10-30 14:05 ` [PATCH v5 13/16] drm/panfrost: Add a PANFROST_SYNC_BO ioctl Boris Brezillon
2025-10-31  7:08   ` Marcin Ślusarz
2025-10-31  8:49     ` Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 14/16] drm/panfrost: Add an ioctl to query BO flags Boris Brezillon
2025-10-30 14:05 ` [PATCH v5 15/16] drm/panfrost: Add flag to map GEM object Write-Back Cacheable Boris Brezillon
2025-11-14 16:22   ` Steven Price
2025-10-30 14:05 ` [PATCH v5 16/16] drm/panfrost: Bump the driver version to 1.6 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=abbd34de-cbbf-4188-a236-e3eccc357fab@amd.com \
    --to=christian.koenig@amd.com \
    --cc=abhinav.kumar@linux.dev \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=boris.brezillon@collabora.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