Re: [PATCH v3 2/2] drm/imagination: Fix page count for page table for map() interface

[Alessio Belle <Alessio.Belle@imgtec.com>]

Hi Brajesh,

On Fri, 2026-09-18 at 16:11 +0530, Brajesh Gupta wrote:
> The GPU virtual start address wasn't included in the calculation for the
> amount of page tables required for mapping a BO object in map() interface.
> It resulted in map failure later due to not enough pages at L0/L1 level.
> Update pvr_mmu_op_context_create() interface to pass device address as well
> to allow correct calculation for page table memory.
> 
> Miscalculation of page table pages for mapping a BO starting at a device
> address 0x8001b45000 of size 0x8ca000:
>                old       new
> L0 count       5          6
> L1 count       1          1

Suggestion for a simpler example, taken from the (wrong) example from Sashiko
and that might help calm it down: if L0 tables cover 2MB (0x200000), the range
defined by device address 0x80001ff000 (general heap at 2MB - 4KB) and size
0x2000 (two 4KB pages) requires two L0 pages to be mapped, but without the base
address a range of 0x2000 computes to a single L0 page which is not enough.

> 
> Fixes: ff5f643de0bf ("drm/imagination: Add GEM and VM related code")
> Signed-off-by: Brajesh Gupta <brajesh.gupta@imgtec.com>
> 

nit: Trailers should be a single block without empty lines and your signed off
line should come after everything else.

Thanks,
Alessio

> Reviewed-by: Alexandru Dadu <alexandru.dadu@imgtec.com>
> Reviewed-by: Alessio Belle <alessio.belle@imgtec.com>
> ---
>  drivers/gpu/drm/imagination/pvr_mmu.c | 14 ++++++++------
>  drivers/gpu/drm/imagination/pvr_mmu.h |  2 +-
>  drivers/gpu/drm/imagination/pvr_vm.c  |  4 ++--
>  3 files changed, 11 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/imagination/pvr_mmu.c b/drivers/gpu/drm/imagination/pvr_mmu.c
> index 23261d9ad3fd..62eae7fcd5a2 100644
> --- a/drivers/gpu/drm/imagination/pvr_mmu.c
> +++ b/drivers/gpu/drm/imagination/pvr_mmu.c
> @@ -2336,6 +2336,7 @@ void pvr_mmu_op_context_destroy(struct pvr_mmu_op_context *op_ctx)
>   * pvr_mmu_op_context_create() - Create an MMU op context.
>   * @ctx: MMU context associated with owning VM context.
>   * @sgt: Scatter gather table containing pages pinned for use by this context.
> + * @device_addr: Virtual device address at the start of the requested mapping.
>   * @sgt_offset: Start offset of the requested device-virtual memory mapping.
>   * @size: Size in bytes of the requested device-virtual memory mapping. For an
>   * unmapping, this should be zero so that no page tables are allocated.
> @@ -2347,8 +2348,9 @@ void pvr_mmu_op_context_destroy(struct pvr_mmu_op_context *op_ctx)
>   */
>  struct pvr_mmu_op_context *
>  pvr_mmu_op_context_create(struct pvr_mmu_context *ctx, struct sg_table *sgt,
> -			  u64 sgt_offset, u64 size)
> +			  u64 device_addr, u64 sgt_offset, u64 size)
>  {
> +	u64 start_addr = device_addr + sgt_offset;
>  	int err;
>  
>  	struct pvr_mmu_op_context *op_ctx = kzalloc_obj(*op_ctx);
> @@ -2364,16 +2366,16 @@ pvr_mmu_op_context_create(struct pvr_mmu_context *ctx, struct sg_table *sgt,
>  	if (size) {
>  		/*
>  		 * The number of page table objects we need to prealloc is
> -		 * indicated by the mapping size, start offset and the sizes
> +		 * indicated by the mapping size, start address and the sizes
>  		 * of the areas mapped per PT or PD. The range calculation is
>  		 * identical to that for the index into a table for a device
>  		 * address, so we reuse those functions here.
>  		 */
> -		const u32 l1_start_idx = pvr_page_table_l2_idx(sgt_offset);
> -		const u32 l1_end_idx = pvr_page_table_l2_idx(sgt_offset + size);
> +		const u32 l1_start_idx = pvr_page_table_l2_idx(start_addr);
> +		const u32 l1_end_idx = pvr_page_table_l2_idx(start_addr + size);
>  		const u32 l1_count = l1_end_idx - l1_start_idx + 1;
> -		const u32 l0_start_idx = pvr_page_table_l1_idx(sgt_offset);
> -		const u32 l0_end_idx = pvr_page_table_l1_idx(sgt_offset + size);
> +		const u32 l0_start_idx = pvr_page_table_l1_idx(start_addr);
> +		const u32 l0_end_idx = pvr_page_table_l1_idx(start_addr + size);
>  		const u32 l0_count = l0_end_idx - l0_start_idx + 1;
>  
>  		/*
> diff --git a/drivers/gpu/drm/imagination/pvr_mmu.h b/drivers/gpu/drm/imagination/pvr_mmu.h
> index a8ecd460168d..2c02d61ba0a2 100644
> --- a/drivers/gpu/drm/imagination/pvr_mmu.h
> +++ b/drivers/gpu/drm/imagination/pvr_mmu.h
> @@ -99,7 +99,7 @@ dma_addr_t pvr_mmu_get_root_table_dma_addr(struct pvr_mmu_context *ctx);
>  void pvr_mmu_op_context_destroy(struct pvr_mmu_op_context *op_ctx);
>  struct pvr_mmu_op_context *
>  pvr_mmu_op_context_create(struct pvr_mmu_context *ctx,
> -			  struct sg_table *sgt, u64 sgt_offset, u64 size);
> +			  struct sg_table *sgt, u64 device_addr, u64 sgt_offset, u64 size);
>  
>  int pvr_mmu_map(struct pvr_mmu_op_context *op_ctx, u64 size, u64 flags,
>  		u64 device_addr);
> diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
> index 396d349fb6ce..867a4a44958a 100644
> --- a/drivers/gpu/drm/imagination/pvr_vm.c
> +++ b/drivers/gpu/drm/imagination/pvr_vm.c
> @@ -276,7 +276,7 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op,
>  		goto err_bind_op_fini;
>  
>  	bind_op->mmu_op_ctx =
> -		pvr_mmu_op_context_create(vm_ctx->mmu_ctx, sgt, offset, size);
> +		pvr_mmu_op_context_create(vm_ctx->mmu_ctx, sgt, device_addr, offset, size);
>  	err = PTR_ERR_OR_ZERO(bind_op->mmu_op_ctx);
>  	if (err) {
>  		bind_op->mmu_op_ctx = NULL;
> @@ -318,7 +318,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
>  	}
>  
>  	bind_op->mmu_op_ctx =
> -		pvr_mmu_op_context_create(vm_ctx->mmu_ctx, NULL, 0, 0);
> +		pvr_mmu_op_context_create(vm_ctx->mmu_ctx, NULL, device_addr, 0, 0);
>  	err = PTR_ERR_OR_ZERO(bind_op->mmu_op_ctx);
>  	if (err) {
>  		bind_op->mmu_op_ctx = NULL;
>