Re: [PATCH v4 05/10] drm/panfrost: Handle page mapping failure

[Boris Brezillon <boris.brezillon@collabora.com>]

On Wed,  1 Oct 2025 03:20:26 +0100
Adrián Larumbe <adrian.larumbe@collabora.com> wrote:

> When mapping the pages of a BO, either a heap type at page fault time or
> else a non-heap BO at object creation time, if the ARM page table mapping
> function fails, we unmap what had been mapped so far and bail out.
> 
> Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
> ---
>  drivers/gpu/drm/panfrost/panfrost_mmu.c | 49 ++++++++++++++++++++++---
>  1 file changed, 44 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
> index cf272b167feb..fb17c32855a5 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
> @@ -393,13 +393,32 @@ static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
>  	pm_runtime_put_autosuspend(pfdev->base.dev);
>  }
>  
> +static void mmu_unmap_range(struct panfrost_mmu *mmu, u64 iova, size_t len)
> +{
> +	struct io_pgtable_ops *ops = mmu->pgtbl_ops;
> +	size_t pgsize, unmapped_len = 0;
> +	size_t unmapped_page, pgcount;
> +
> +	while (unmapped_len < len) {
> +		pgsize = get_pgsize(iova, len - unmapped_len, &pgcount);
> +
> +		unmapped_page = ops->unmap_pages(ops, iova, pgsize, pgcount, NULL);
> +		WARN_ON(unmapped_page != pgsize * pgcount);
> +
> +		iova += pgsize * pgcount;
> +		unmapped_len += pgsize * pgcount;
> +	}
> +}
> +
>  static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
>  		      u64 iova, int prot, struct sg_table *sgt)
>  {
>  	unsigned int count;
>  	struct scatterlist *sgl;
>  	struct io_pgtable_ops *ops = mmu->pgtbl_ops;
> +	size_t total_mapped = 0;
>  	u64 start_iova = iova;
> +	int ret;
>  
>  	for_each_sgtable_dma_sg(sgt, sgl, count) {
>  		unsigned long paddr = sg_dma_address(sgl);
> @@ -413,10 +432,14 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
>  			size_t pgcount, mapped = 0;
>  			size_t pgsize = get_pgsize(iova | paddr, len, &pgcount);
>  
> -			ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot,
> +			ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot,
>  				       GFP_KERNEL, &mapped);
> +			if (ret)
> +				goto err_unmap_pages;
> +
>  			/* Don't get stuck if things have gone wrong */
>  			mapped = max(mapped, pgsize);
> +			total_mapped += mapped;
>  			iova += mapped;
>  			paddr += mapped;
>  			len -= mapped;
> @@ -426,6 +449,10 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
>  	panfrost_mmu_flush_range(pfdev, mmu, start_iova, iova - start_iova);
>  
>  	return 0;
> +
> +err_unmap_pages:
> +	mmu_unmap_range(mmu, start_iova, total_mapped);
> +	return ret;
>  }
>  
>  int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
> @@ -436,6 +463,7 @@ int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
>  	struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
>  	struct sg_table *sgt;
>  	int prot = IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE;
> +	int ret;
>  
>  	if (WARN_ON(mapping->active))
>  		return 0;
> @@ -447,11 +475,18 @@ int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
>  	if (WARN_ON(IS_ERR(sgt)))
>  		return PTR_ERR(sgt);
>  
> -	mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT,
> -		   prot, sgt);
> +	ret = mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT,
> +			 prot, sgt);
> +	if (ret)
> +		goto err_put_pages;
> +
>  	mapping->active = true;
>  
>  	return 0;
> +
> +err_put_pages:
> +	drm_gem_shmem_put_pages_locked(shmem);
> +	return ret;
>  }
>  
>  void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping)
> @@ -635,8 +670,10 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
>  	if (ret)
>  		goto err_map;
>  
> -	mmu_map_sg(pfdev, bomapping->mmu, addr,
> -		   IOMMU_WRITE | IOMMU_READ | IOMMU_CACHE | IOMMU_NOEXEC, sgt);
> +	ret = mmu_map_sg(pfdev, bomapping->mmu, addr,
> +			 IOMMU_WRITE | IOMMU_READ | IOMMU_CACHE | IOMMU_NOEXEC, sgt);
> +	if (ret)
> +		goto err_mmu_map_sg;
>  
>  	bomapping->active = true;
>  	bo->heap_rss_size += SZ_2M;
> @@ -650,6 +687,8 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
>  
>  	return 0;
>  
> +err_mmu_map_sg:
> +	dma_unmap_sgtable(pfdev->base.dev, sgt, DMA_BIDIRECTIONAL, 0);

You also need to clear the sgts[]/pages[] entries you added earlier,
otherwise the next time you have a fault it will bail-out before
attempting an mmu_map_sg().

IIRC, Dmitry had a similar fix in his shmem-shrinker series.

>  err_map:
>  	sg_free_table(sgt);
>  err_unlock: