[PATCH 23/29] drm/amdgpu: hw_init for each vcn instance
Khatri, Sunil
sunil.khatri at amd.com
Tue Oct 29 10:04:16 UTC 2024
Acked-by: Sunil Khatri <sunil.khatri at amd.com>
On 10/25/2024 8:05 AM, boyuan.zhang at amd.com wrote:
> From: Boyuan Zhang <boyuan.zhang at amd.com>
>
> Pass instance parameter to amdgpu_vcn_hw_init(), and perform
> hw init ONLY for the given vcn instance, instead of for all
> vcn instances. Modify each vcn generation accordingly.
>
> Signed-off-by: Boyuan Zhang <boyuan.zhang at amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 39 +++++++------
> drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 73 ++++++++++++-------------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 37 ++++++-------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 67 +++++++++++------------
> drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 21 ++++---
> drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 21 ++++---
> 6 files changed, 123 insertions(+), 135 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> index d135e63e7301..8ce3cea6cf44 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> @@ -338,37 +338,36 @@ static int vcn_v2_5_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> struct amdgpu_ring *ring;
> - int i, j, r = 0;
> + int inst = ip_block->instance;
> + int i, r = 0;
>
> if (amdgpu_sriov_vf(adev))
> r = vcn_v2_5_sriov_start(adev);
>
> - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
> - if (adev->vcn.harvest_config & (1 << j))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return r;
>
> - if (amdgpu_sriov_vf(adev)) {
> - adev->vcn.inst[j].ring_enc[0].sched.ready = true;
> - adev->vcn.inst[j].ring_enc[1].sched.ready = false;
> - adev->vcn.inst[j].ring_enc[2].sched.ready = false;
> - adev->vcn.inst[j].ring_dec.sched.ready = true;
> - } else {
> + if (amdgpu_sriov_vf(adev)) {
> + adev->vcn.inst[inst].ring_enc[0].sched.ready = true;
> + adev->vcn.inst[inst].ring_enc[1].sched.ready = false;
> + adev->vcn.inst[inst].ring_enc[2].sched.ready = false;
> + adev->vcn.inst[inst].ring_dec.sched.ready = true;
> + } else {
> +
> + ring = &adev->vcn.inst[inst].ring_dec;
>
> - ring = &adev->vcn.inst[j].ring_dec;
> + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> + ring->doorbell_index, inst);
>
> - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> - ring->doorbell_index, j);
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
>
> + for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
> + ring = &adev->vcn.inst[inst].ring_enc[i];
> r = amdgpu_ring_test_helper(ring);
> if (r)
> return r;
> -
> - for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
> - ring = &adev->vcn.inst[j].ring_enc[i];
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> - }
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> index d00b7a7cbdce..36100c2612d9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
> @@ -345,8 +345,9 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
> static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> + int inst = ip_block->instance;
> struct amdgpu_ring *ring;
> - int i, j, r;
> + int j, r;
>
> if (amdgpu_sriov_vf(adev)) {
> r = vcn_v3_0_start_sriov(adev);
> @@ -354,57 +355,53 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
> return r;
>
> /* initialize VCN dec and enc ring buffers */
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
> +
> + ring = &adev->vcn.inst[inst].ring_dec;
> + if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, inst)) {
> + ring->sched.ready = false;
> + ring->no_scheduler = true;
> + dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
> + } else {
> + ring->wptr = 0;
> + ring->wptr_old = 0;
> + vcn_v3_0_dec_ring_set_wptr(ring);
> + ring->sched.ready = true;
> + }
>
> - ring = &adev->vcn.inst[i].ring_dec;
> - if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) {
> + for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
> + ring = &adev->vcn.inst[inst].ring_enc[j];
> + if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, inst)) {
> ring->sched.ready = false;
> ring->no_scheduler = true;
> dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
> } else {
> ring->wptr = 0;
> ring->wptr_old = 0;
> - vcn_v3_0_dec_ring_set_wptr(ring);
> + vcn_v3_0_enc_ring_set_wptr(ring);
> ring->sched.ready = true;
> }
> -
> - for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
> - ring = &adev->vcn.inst[i].ring_enc[j];
> - if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) {
> - ring->sched.ready = false;
> - ring->no_scheduler = true;
> - dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
> - } else {
> - ring->wptr = 0;
> - ring->wptr_old = 0;
> - vcn_v3_0_enc_ring_set_wptr(ring);
> - ring->sched.ready = true;
> - }
> - }
> }
> - } else {
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + }
>
> - ring = &adev->vcn.inst[i].ring_dec;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
>
> - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> - ring->doorbell_index, i);
> + ring = &adev->vcn.inst[inst].ring_dec;
>
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> + ring->doorbell_index, inst);
>
> - for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
> - ring = &adev->vcn.inst[i].ring_enc[j];
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> - }
> - }
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
> +
> + for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
> + ring = &adev->vcn.inst[inst].ring_enc[j];
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
> }
>
> return 0;
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> index 7c3a62f84707..00ff7affc647 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
> @@ -299,37 +299,34 @@ static int vcn_v4_0_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> struct amdgpu_ring *ring;
> - int i, r;
> + int inst = ip_block->instance;
> + int r;
>
> if (amdgpu_sriov_vf(adev)) {
> r = vcn_v4_0_start_sriov(adev);
> if (r)
> return r;
>
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
>
> - ring = &adev->vcn.inst[i].ring_enc[0];
> - ring->wptr = 0;
> - ring->wptr_old = 0;
> - vcn_v4_0_unified_ring_set_wptr(ring);
> - ring->sched.ready = true;
> - }
> + ring = &adev->vcn.inst[inst].ring_enc[0];
> + ring->wptr = 0;
> + ring->wptr_old = 0;
> + vcn_v4_0_unified_ring_set_wptr(ring);
> + ring->sched.ready = true;
> } else {
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
>
> - ring = &adev->vcn.inst[i].ring_enc[0];
> + ring = &adev->vcn.inst[inst].ring_enc[0];
>
> - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> - ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i), i);
> + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> + ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * inst), inst);
>
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> - }
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
> }
>
> return 0;
> 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 5a3de3dbc3c9..feb373a96cfb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> @@ -257,49 +257,46 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> struct amdgpu_ring *ring;
> - int i, r, vcn_inst;
> + int inst = ip_block->instance;
> + int r = 0, vcn_inst;
>
> if (amdgpu_sriov_vf(adev)) {
> r = vcn_v4_0_3_start_sriov(adev);
> if (r)
> return r;
>
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - ring = &adev->vcn.inst[i].ring_enc[0];
> - ring->wptr = 0;
> - ring->wptr_old = 0;
> - vcn_v4_0_3_unified_ring_set_wptr(ring);
> - ring->sched.ready = true;
> - }
> + ring = &adev->vcn.inst[inst].ring_enc[0];
> + ring->wptr = 0;
> + ring->wptr_old = 0;
> + vcn_v4_0_3_unified_ring_set_wptr(ring);
> + ring->sched.ready = true;
> } else {
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - vcn_inst = GET_INST(VCN, i);
> - ring = &adev->vcn.inst[i].ring_enc[0];
> -
> - if (ring->use_doorbell) {
> - adev->nbio.funcs->vcn_doorbell_range(
> - adev, ring->use_doorbell,
> - (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
> - 9 * vcn_inst,
> - adev->vcn.inst[i].aid_id);
> -
> - WREG32_SOC15(
> - VCN, GET_INST(VCN, ring->me),
> - regVCN_RB1_DB_CTRL,
> - ring->doorbell_index
> - << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
> - VCN_RB1_DB_CTRL__EN_MASK);
> -
> - /* Read DB_CTRL to flush the write DB_CTRL command. */
> - RREG32_SOC15(
> - VCN, GET_INST(VCN, ring->me),
> - regVCN_RB1_DB_CTRL);
> - }
> -
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> + vcn_inst = GET_INST(VCN, inst);
> + ring = &adev->vcn.inst[inst].ring_enc[0];
> +
> + if (ring->use_doorbell) {
> + adev->nbio.funcs->vcn_doorbell_range(
> + adev, ring->use_doorbell,
> + (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
> + 9 * vcn_inst,
> + adev->vcn.inst[inst].aid_id);
> +
> + WREG32_SOC15(
> + VCN, GET_INST(VCN, ring->me),
> + regVCN_RB1_DB_CTRL,
> + ring->doorbell_index
> + << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
> + VCN_RB1_DB_CTRL__EN_MASK);
> +
> + /* Read DB_CTRL to flush the write DB_CTRL command. */
> + RREG32_SOC15(
> + VCN, GET_INST(VCN, ring->me),
> + regVCN_RB1_DB_CTRL);
> }
> +
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
> }
>
> return r;
> 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 2c9f863c40b1..fb1e1d5bcdbe 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
> @@ -268,21 +268,20 @@ static int vcn_v4_0_5_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> struct amdgpu_ring *ring;
> - int i, r;
> + int inst = ip_block->instance;
> + int r;
>
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
>
> - ring = &adev->vcn.inst[i].ring_enc[0];
> + ring = &adev->vcn.inst[inst].ring_enc[0];
>
> - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> - ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i), i);
> + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> + ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * inst), inst);
>
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> - }
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
>
> return 0;
> }
> 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 9d67e884952a..137c3b452433 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
> @@ -232,21 +232,20 @@ static int vcn_v5_0_0_hw_init(struct amdgpu_ip_block *ip_block)
> {
> struct amdgpu_device *adev = ip_block->adev;
> struct amdgpu_ring *ring;
> - int i, r;
> + int inst = ip_block->instance;
> + int r;
>
> - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> - if (adev->vcn.harvest_config & (1 << i))
> - continue;
> + if (adev->vcn.harvest_config & (1 << inst))
> + return 0;
>
> - ring = &adev->vcn.inst[i].ring_enc[0];
> + ring = &adev->vcn.inst[inst].ring_enc[0];
>
> - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> - ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i), i);
> + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
> + ((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * inst), inst);
>
> - r = amdgpu_ring_test_helper(ring);
> - if (r)
> - return r;
> - }
> + r = amdgpu_ring_test_helper(ring);
> + if (r)
> + return r;
>
> return 0;
> }
More information about the amd-gfx
mailing list