AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Price <steven.price@arm.com>
To: Boris Brezillon <boris.brezillon@collabora.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 v5 15/16] drm/panfrost: Add flag to map GEM object Write-Back Cacheable
Date: Fri, 14 Nov 2025 16:22:06 +0000	[thread overview]
Message-ID: <468df8dc-0dab-449f-b48a-50470403ca3b@arm.com> (raw)
In-Reply-To: <20251030140525.366636-16-boris.brezillon@collabora.com>

On 30/10/2025 14:05, Boris Brezillon wrote:
> From: Faith Ekstrand <faith.ekstrand@collabora.com>
> 
> Will be used by the UMD to optimize CPU accesses to buffers
> that are frequently read by the CPU, or on which the access
> pattern makes non-cacheable mappings inefficient.
> 
> Mapping buffers CPU-cached implies taking care of the CPU
> cache maintenance in the UMD, unless the GPU is IO coherent.
> 
> v2:
> - Add more to the commit message
> 
> v3:
> - No changes
> 
> v4:
> - Fix the map_wc test in panfrost_ioctl_query_bo_info()
> 
> v5:
> - Drop Steve's R-b (enough has changed to justify a new review)
> 
> Signed-off-by: Faith Ekstrand <faith.ekstrand@collabora.com>
> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>

Reviewed-by: Steven Price <steven.price@arm.com>

> ---
>  drivers/gpu/drm/panfrost/panfrost_drv.c | 10 ++++++--
>  drivers/gpu/drm/panfrost/panfrost_gem.c | 33 +++++++++++++++++++++++++
>  drivers/gpu/drm/panfrost/panfrost_gem.h |  5 ++++
>  include/uapi/drm/panfrost_drm.h         |  5 +++-
>  4 files changed, 50 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
> index ba03a4420264..74b7dc75d88b 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_drv.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
> @@ -125,6 +125,10 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct
>  	return 0;
>  }
>  
> +#define PANFROST_BO_FLAGS	(PANFROST_BO_NOEXEC | \
> +				 PANFROST_BO_HEAP | \
> +				 PANFROST_BO_WB_MMAP)
> +
>  static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
>  		struct drm_file *file)
>  {
> @@ -134,8 +138,7 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
>  	struct panfrost_gem_mapping *mapping;
>  	int ret;
>  
> -	if (!args->size || args->pad ||
> -	    (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
> +	if (!args->size || args->pad || (args->flags & ~PANFROST_BO_FLAGS))
>  		return -EINVAL;
>  
>  	/* Heaps should never be executable */
> @@ -652,6 +655,9 @@ static int panfrost_ioctl_query_bo_info(struct drm_device *dev, void *data,
>  
>  		if (bo->is_heap)
>  			args->create_flags |= PANFROST_BO_HEAP;
> +
> +		if (!bo->base.map_wc)
> +			args->create_flags |= PANFROST_BO_WB_MMAP;
>  	}
>  
>  	drm_gem_object_put(gem_obj);
> diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
> index 05d3f8a6fa78..1c600939c17a 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_gem.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
> @@ -269,6 +269,7 @@ static const struct drm_gem_object_funcs panfrost_gem_funcs = {
>  	.vmap = drm_gem_shmem_object_vmap,
>  	.vunmap = drm_gem_shmem_object_vunmap,
>  	.mmap = drm_gem_shmem_object_mmap,
> +	.export = drm_gem_prime_export,
>  	.status = panfrost_gem_status,
>  	.rss = panfrost_gem_rss,
>  	.vm_ops = &drm_gem_shmem_vm_ops,
> @@ -302,12 +303,42 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t
>  	return &obj->base.base;
>  }
>  
> +static bool
> +should_map_wc(struct panfrost_gem_object *bo)
> +{
> +	struct panfrost_device *pfdev = to_panfrost_device(bo->base.base.dev);
> +
> +	/* We can't do uncached mappings if the device is coherent,
> +	 * because the zeroing done by the shmem layer at page allocation
> +	 * time happens on a cached mapping which isn't CPU-flushed (at least
> +	 * not on Arm64 where the flush is deferred to PTE setup time, and
> +	 * only done conditionally based on the mapping permissions). We can't
> +	 * rely on dma_map_sgtable()/dma_sync_sgtable_for_xxx() either to flush
> +	 * those, because they are NOPed if dma_dev_coherent() returns true.
> +	 */
> +	if (pfdev->coherent)
> +		return false;
> +
> +	/* Cached mappings are explicitly requested, so no write-combine. */
> +	if (bo->wb_mmap)
> +		return false;
> +
> +	/* The default is write-combine. */
> +	return true;
> +}
> +
>  struct panfrost_gem_object *
>  panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
>  {
>  	struct drm_gem_shmem_object *shmem;
>  	struct panfrost_gem_object *bo;
>  
> +	/* The heap buffer is not supposed to be CPU-visible, so don't allow
> +	 * WB_MMAP on those.
> +	 */
> +	if ((flags & PANFROST_BO_HEAP) && (flags & PANFROST_BO_WB_MMAP))
> +		return ERR_PTR(-EINVAL);
> +
>  	/* Round up heap allocations to 2MB to keep fault handling simple */
>  	if (flags & PANFROST_BO_HEAP)
>  		size = roundup(size, SZ_2M);
> @@ -319,6 +350,8 @@ panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
>  	bo = to_panfrost_bo(&shmem->base);
>  	bo->noexec = !!(flags & PANFROST_BO_NOEXEC);
>  	bo->is_heap = !!(flags & PANFROST_BO_HEAP);
> +	bo->wb_mmap = !!(flags & PANFROST_BO_WB_MMAP);
> +	bo->base.map_wc = should_map_wc(bo);
>  
>  	return bo;
>  }
> diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
> index 87b918f30baa..d2d532b3007a 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_gem.h
> +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
> @@ -98,6 +98,11 @@ struct panfrost_gem_object {
>  	bool noexec		:1;
>  	bool is_heap		:1;
>  
> +	/* On coherent devices, this reflects the creation flags, not the true
> +	 * cacheability attribute of the mapping.
> +	 */
> +	bool wb_mmap		:1;
> +
>  #ifdef CONFIG_DEBUG_FS
>  	struct panfrost_gem_debugfs debugfs;
>  #endif
> diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h
> index 743c79a38f1b..82f4e69bafb4 100644
> --- a/include/uapi/drm/panfrost_drm.h
> +++ b/include/uapi/drm/panfrost_drm.h
> @@ -101,9 +101,12 @@ struct drm_panfrost_wait_bo {
>  	__s64 timeout_ns;	/* absolute */
>  };
>  
> -/* Valid flags to pass to drm_panfrost_create_bo */
> +/* Valid flags to pass to drm_panfrost_create_bo.
> + * PANFROST_BO_WB_MMAP can't be set if PANFROST_BO_HEAP is.
> + */
>  #define PANFROST_BO_NOEXEC	1
>  #define PANFROST_BO_HEAP	2
> +#define PANFROST_BO_WB_MMAP	4
>  
>  /**
>   * struct drm_panfrost_create_bo - ioctl argument for creating Panfrost BOs.


  reply	other threads:[~2025-11-14 16:22 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   ` [PATCH v5 02/16] drm/shmem: Provide a generic {begin,end}_cpu_access() implementation Christian König
2025-11-04  8:08     ` 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 [this message]
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=468df8dc-0dab-449f-b48a-50470403ca3b@arm.com \
    --to=steven.price@arm.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=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=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