On Thu, Oct 17, 2024 at 11:43 AM <boyuan.zhang@xxxxxxx> wrote:
>
> From: Boyuan Zhang <boyuan.zhang@xxxxxxx>
>
> Pass instance parameter to amdgpu_vcn_sw_fini(), and perform
> sw fini ONLY for the given vcn instance, instead of for all
> vcn instances. Modify each vcn generation accordingly.
>
> Signed-off-by: Boyuan Zhang <boyuan.zhang@xxxxxxx>
Reviewed-by: Alex Deucher <alexander.deucher@xxxxxxx>
Thinking about these patches that modify amdgpu_vcn.c to add the
instance to them, will this break anything due to changes in ordering?
If so, we may want to squash all of these together into one patch.
Alex
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 36 ++++++++++++-------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h | 2 +-
> drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 5 ++--
> drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 5 ++--
> drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 17 ++++++------
> drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 20 +++++++-------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 21 +++++++--------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 16 +++++------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 21 +++++++--------
> drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 21 +++++++--------
> 10 files changed, 81 insertions(+), 83 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> index 791b95867ac2..307615ffeb79 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> @@ -248,33 +248,31 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int inst)
> return 0;
> }
>
> -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
> +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int inst)
> {
> - int i, j;
> -
> - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
> - if (adev->vcn.harvest_config & (1 << j))
> - continue;
> + int i;
>
> - amdgpu_bo_free_kernel(
> - &adev->vcn.inst[j].dpg_sram_bo,
> - &adev->vcn.inst[j].dpg_sram_gpu_addr,
> - (void **)&adev->vcn.inst[j].dpg_sram_cpu_addr);
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
>
> - kvfree(adev->vcn.inst[j].saved_bo);
> + amdgpu_bo_free_kernel(
> + &adev->vcn.inst[inst].dpg_sram_bo,
> + &adev->vcn.inst[inst].dpg_sram_gpu_addr,
> + (void **)&adev->vcn.inst[inst].dpg_sram_cpu_addr);
>
> - amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo,
> - &adev->vcn.inst[j].gpu_addr,
> - (void **)&adev->vcn.inst[j].cpu_addr);
> + kvfree(adev->vcn.inst[inst].saved_bo);
>
> - amdgpu_ring_fini(&adev->vcn.inst[j].ring_dec);
> + amdgpu_bo_free_kernel(&adev->vcn.inst[inst].vcpu_bo,
> + &adev->vcn.inst[inst].gpu_addr,
> + (void **)&adev->vcn.inst[inst].cpu_addr);
>
> - for (i = 0; i < adev->vcn.num_enc_rings; ++i)
> - amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]);
> + amdgpu_ring_fini(&adev->vcn.inst[inst].ring_dec);
>
> - amdgpu_ucode_release(&adev->vcn.inst[j].fw);
> - }
> + for (i = 0; i < adev->vcn.num_enc_rings; ++i)
> + amdgpu_ring_fini(&adev->vcn.inst[inst].ring_enc[i]);
>
> + amdgpu_ucode_release(&adev->vcn.inst[inst].fw);
> +done:
> mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
> mutex_destroy(&adev->vcn.vcn_pg_lock);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> index 825b70a396cd..883b9f9776a1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> @@ -485,7 +485,7 @@ enum vcn_ring_type {
>
> int amdgpu_vcn_early_init(struct amdgpu_device *adev, int inst);
> int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int inst);
> -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev);
> +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int inst);
> int amdgpu_vcn_suspend(struct amdgpu_device *adev);
> int amdgpu_vcn_resume(struct amdgpu_device *adev);
> void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring);
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
> index 70d865724463..8203f80be316 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
> @@ -222,8 +222,9 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block)
> */
> static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> - int r;
> struct amdgpu_device *adev = ip_block->adev;
> + int inst = ip_block->instance;
> + int r;
>
> r = amdgpu_vcn_suspend(adev);
> if (r)
> @@ -231,7 +232,7 @@ static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block)
>
> jpeg_v1_0_sw_fini(ip_block);
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
> index 834311e13a4c..0481a07054eb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
> @@ -245,9 +245,10 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
> */
> static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> - int r, idx;
> struct amdgpu_device *adev = ip_block->adev;
> + int inst = ip_block->instance;
> volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> fw_shared->present_flag_0 = 0;
> @@ -260,7 +261,7 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> index f6d2e3e3bf32..ed972d843f93 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> @@ -297,17 +297,18 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
> */
> static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> - int i, r, idx;
> struct amdgpu_device *adev = ip_block->adev;
> volatile struct amdgpu_fw_shared *fw_shared;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - }
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
> +
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + done:
> drm_dev_exit(idx);
> }
>
> @@ -319,7 +320,7 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> index 9b62296cc233..c45bebeb0aaa 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> @@ -306,19 +306,19 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
> static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> - int i, r, idx;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - volatile struct amdgpu_fw_shared *fw_shared;
> + volatile struct amdgpu_fw_shared *fw_shared;
>
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - fw_shared->sw_ring.is_enabled = false;
> - }
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
>
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + fw_shared->sw_ring.is_enabled = false;
> + done:
> drm_dev_exit(idx);
> }
>
> @@ -329,7 +329,7 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
> return r;
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> index 79d5ef8f857c..c87b4e46f2b0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> @@ -258,20 +258,19 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
> static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> - int i, r, idx;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - volatile struct amdgpu_vcn4_fw_shared *fw_shared;
> + volatile struct amdgpu_vcn4_fw_shared *fw_shared;
>
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> -
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - fw_shared->sq.is_enabled = 0;
> - }
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
>
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + fw_shared->sq.is_enabled = 0;
> + done:
> drm_dev_exit(idx);
> }
>
> @@ -282,7 +281,7 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> index 0932e992d088..0b55d801ae88 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> @@ -219,16 +219,16 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
> static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> - int i, r, idx;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(&adev->ddev, &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - volatile struct amdgpu_vcn4_fw_shared *fw_shared;
> + volatile struct amdgpu_vcn4_fw_shared *fw_shared;
> +
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + fw_shared->sq.is_enabled = cpu_to_le32(false);
>
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - fw_shared->sq.is_enabled = cpu_to_le32(false);
> - }
> drm_dev_exit(idx);
> }
>
> @@ -239,7 +239,7 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
> index e551ba1d1e12..b88fdb00cc5e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
> @@ -227,20 +227,19 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
> static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> - int i, r, idx;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - volatile struct amdgpu_vcn4_fw_shared *fw_shared;
> -
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + volatile struct amdgpu_vcn4_fw_shared *fw_shared;
>
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - fw_shared->sq.is_enabled = 0;
> - }
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
>
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + fw_shared->sq.is_enabled = 0;
> + done:
> drm_dev_exit(idx);
> }
>
> @@ -251,7 +250,7 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
> index dc15a74bb3d8..15cdc7be9062 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
> @@ -194,20 +194,19 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
> static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> - int i, r, idx;
> + int inst = ip_block->instance;
> + int r, idx;
>
> if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
> - volatile struct amdgpu_vcn5_fw_shared *fw_shared;
> -
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + volatile struct amdgpu_vcn5_fw_shared *fw_shared;
>
> - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> - fw_shared->present_flag_0 = 0;
> - fw_shared->sq.is_enabled = 0;
> - }
> + if (adev->vcn.harvest_config & (1 << inst))
> + goto done;
>
> + fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
> + fw_shared->present_flag_0 = 0;
> + fw_shared->sq.is_enabled = 0;
> + done:
> drm_dev_exit(idx);
> }
>
> @@ -215,7 +214,7 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
> if (r)
> return r;
>
> - r = amdgpu_vcn_sw_fini(adev);
> + r = amdgpu_vcn_sw_fini(adev, inst);
>
> kfree(adev->vcn.ip_dump);
>
> --
> 2.34.1
>
