On Wed, Jul 10, 2024 at 2:10 PM <boyuan.zhang@xxxxxxx> wrote:
>
> From: Boyuan Zhang <boyuan.zhang@xxxxxxx>
>
> Determine whether VCN using unified queue in sw_init, instead of calling
> functions later on.
>
> Signed-off-by: Boyuan Zhang <boyuan.zhang@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 39 ++++++++++---------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h | 1 +
> 2 files changed, 16 insertions(+), 24 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> index dad5f9722e14..43bed7730bd1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> @@ -139,6 +139,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
> }
> }
>
> + /* from vcn4 and above, only unified queue is used */
> + adev->vcn.using_unified_queue =
> + amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0) ? true : false;
You can drop the "? true : false" part. A lot of static checkers will
complain about that as it's not necessary.
With that fixed, the series is:
Acked-by: Alex Deucher <alexander.deucher@xxxxxxx>
> +
> hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
> adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
>
> @@ -266,18 +270,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
> return 0;
> }
>
> -/* from vcn4 and above, only unified queue is used */
> -static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring)
> -{
> - struct amdgpu_device *adev = ring->adev;
> - bool ret = false;
> -
> - if (amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0))
> - ret = true;
> -
> - return ret;
> -}
> -
> bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
> {
> bool ret = false;
> @@ -747,12 +739,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
> struct amdgpu_job *job;
> struct amdgpu_ib *ib;
> uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr);
> - bool sq = amdgpu_vcn_using_unified_queue(ring);
> uint32_t *ib_checksum;
> uint32_t ib_pack_in_dw;
> int i, r;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> ib_size_dw += 8;
>
> r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
> @@ -765,7 +756,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
> ib->length_dw = 0;
>
> /* single queue headers */
> - if (sq) {
> + if (adev->vcn.using_unified_queue) {
> ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
> + 4 + 2; /* engine info + decoding ib in dw */
> ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
> @@ -784,7 +775,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
> for (i = ib->length_dw; i < ib_size_dw; ++i)
> ib->ptr[i] = 0x0;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
>
> r = amdgpu_job_submit_direct(job, ring, &f);
> @@ -874,15 +865,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
> struct dma_fence **fence)
> {
> unsigned int ib_size_dw = 16;
> + struct amdgpu_device *adev = ring->adev;
> struct amdgpu_job *job;
> struct amdgpu_ib *ib;
> struct dma_fence *f = NULL;
> uint32_t *ib_checksum = NULL;
> uint64_t addr;
> - bool sq = amdgpu_vcn_using_unified_queue(ring);
> int i, r;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> ib_size_dw += 8;
>
> r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
> @@ -896,7 +887,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
>
> ib->length_dw = 0;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
>
> ib->ptr[ib->length_dw++] = 0x00000018;
> @@ -918,7 +909,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
> for (i = ib->length_dw; i < ib_size_dw; ++i)
> ib->ptr[i] = 0x0;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
>
> r = amdgpu_job_submit_direct(job, ring, &f);
> @@ -941,15 +932,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
> struct dma_fence **fence)
> {
> unsigned int ib_size_dw = 16;
> + struct amdgpu_device *adev = ring->adev;
> struct amdgpu_job *job;
> struct amdgpu_ib *ib;
> struct dma_fence *f = NULL;
> uint32_t *ib_checksum = NULL;
> uint64_t addr;
> - bool sq = amdgpu_vcn_using_unified_queue(ring);
> int i, r;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> ib_size_dw += 8;
>
> r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
> @@ -963,7 +954,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
>
> ib->length_dw = 0;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
>
> ib->ptr[ib->length_dw++] = 0x00000018;
> @@ -985,7 +976,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
> for (i = ib->length_dw; i < ib_size_dw; ++i)
> ib->ptr[i] = 0x0;
>
> - if (sq)
> + if (adev->vcn.using_unified_queue)
> amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
>
> r = amdgpu_job_submit_direct(job, ring, &f);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> index 081695e74932..838c0935f683 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> @@ -329,6 +329,7 @@ struct amdgpu_vcn {
>
> uint16_t inst_mask;
> uint8_t num_inst_per_aid;
> + bool using_unified_queue;
> };
>
> struct amdgpu_fw_shared_rb_ptrs_struct {
> --
> 2.34.1
>
