Re: [PATCH 21/29] drm/amdgpu: sw_init for each vcn instance

["Khatri, Sunil" <sunil.khatri@xxxxxxx>]

On 10/25/2024 8:05 AM, boyuan.zhang@xxxxxxx wrote:

From: Boyuan Zhang <boyuan.zhang@xxxxxxx>

Pass instance parameter to amdgpu_vcn_sw_init(), and perform
sw 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@xxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 83 ++++++++++++-------------
 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   |  6 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c   |  7 ++-
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c   |  7 ++-
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c |  5 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c |  7 ++-
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c |  7 ++-
 10 files changed, 69 insertions(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 21701738030f..2c55166e27d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -111,24 +111,23 @@ int amdgpu_vcn_early_init(struct amdgpu_device *adev, int inst)
 	return r;
 }
 
-int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
+int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int inst)
 {
 	unsigned long bo_size;
 	const struct common_firmware_header *hdr;
 	unsigned char fw_check;
 	unsigned int fw_shared_size, log_offset;
-	int i, r;
+	int r;
+
+	adev->vcn.inst[inst].adev = adev;
+	adev->vcn.inst[inst].work_inst = inst;
+	INIT_DELAYED_WORK(&adev->vcn.inst[inst].idle_work, amdgpu_vcn_idle_work_handler);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		adev->vcn.inst[i].adev = adev;
-		adev->vcn.inst[i].work_inst = i;
-		INIT_DELAYED_WORK(&adev->vcn.inst[i].idle_work, amdgpu_vcn_idle_work_handler);
-	}
 	mutex_init(&adev->vcn.vcn_pg_lock);
 	mutex_init(&adev->vcn.vcn1_jpeg1_workaround);
 	atomic_set(&adev->vcn.total_submission_cnt, 0);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++)
-		atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
+
+	atomic_set(&adev->vcn.inst[inst].dpg_enc_submission_cnt, 0);
 
 	if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
 	    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
@@ -206,45 +205,43 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	if (amdgpu_vcnfw_log)
 		bo_size += AMDGPU_VCNFW_LOG_SIZE;
 
-	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;
 
-		r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
-					    AMDGPU_GEM_DOMAIN_VRAM |
-					    AMDGPU_GEM_DOMAIN_GTT,
-					    &adev->vcn.inst[i].vcpu_bo,
-					    &adev->vcn.inst[i].gpu_addr,
-					    &adev->vcn.inst[i].cpu_addr);
-		if (r) {
-			dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
-			return r;
-		}
+	r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
+					AMDGPU_GEM_DOMAIN_VRAM |
+					AMDGPU_GEM_DOMAIN_GTT,
+					&adev->vcn.inst[inst].vcpu_bo,
+					&adev->vcn.inst[inst].gpu_addr,
+					&adev->vcn.inst[inst].cpu_addr);
+	if (r) {
+		dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
+		return r;
+	}
 
-		adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr +
-				bo_size - fw_shared_size;
-		adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr +
-				bo_size - fw_shared_size;
+	adev->vcn.inst[inst].fw_shared.cpu_addr = adev->vcn.inst[inst].cpu_addr +
+			bo_size - fw_shared_size;
+	adev->vcn.inst[inst].fw_shared.gpu_addr = adev->vcn.inst[inst].gpu_addr +
+			bo_size - fw_shared_size;
 
-		adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size;
+	adev->vcn.inst[inst].fw_shared.mem_size = fw_shared_size;
 
-		if (amdgpu_vcnfw_log) {
-			adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
-			adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
-			adev->vcn.inst[i].fw_shared.log_offset = log_offset;
-		}
+	if (amdgpu_vcnfw_log) {
+		adev->vcn.inst[inst].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
+		adev->vcn.inst[inst].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
+		adev->vcn.inst[inst].fw_shared.log_offset = log_offset;
+	}
 
-		if (adev->vcn.indirect_sram) {
-			r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
-					AMDGPU_GEM_DOMAIN_VRAM |
-					AMDGPU_GEM_DOMAIN_GTT,
-					&adev->vcn.inst[i].dpg_sram_bo,
-					&adev->vcn.inst[i].dpg_sram_gpu_addr,
-					&adev->vcn.inst[i].dpg_sram_cpu_addr);
-			if (r) {
-				dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r);
-				return r;
-			}
+	if (adev->vcn.indirect_sram) {
+		r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
+				AMDGPU_GEM_DOMAIN_VRAM |
+				AMDGPU_GEM_DOMAIN_GTT,
+				&adev->vcn.inst[inst].dpg_sram_bo,
+				&adev->vcn.inst[inst].dpg_sram_gpu_addr,
+				&adev->vcn.inst[inst].dpg_sram_cpu_addr);
+		if (r) {
+			dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", inst, r);
+			return r;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 58fbb87e5ec4..4809da69bd1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -484,7 +484,7 @@ 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 amdgpu_vcn_sw_init(struct amdgpu_device *adev, int inst);
 int amdgpu_vcn_sw_fini(struct amdgpu_device *adev);
 int amdgpu_vcn_suspend(struct amdgpu_device *adev);
 int amdgpu_vcn_resume(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 6fd509e6744d..808d69ab0904 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -126,11 +126,12 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v1_0_sw_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, r;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_1_0);
 	uint32_t *ptr;
-	struct amdgpu_device *adev = ip_block->adev;
 
 	/* VCN DEC TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
@@ -146,7 +147,7 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 8f7038190a43..a86cff00d761 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -131,11 +131,12 @@ static int vcn_v2_0_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v2_0_sw_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, r;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_0);
 	uint32_t *ptr;
-	struct amdgpu_device *adev = ip_block->adev;
 	volatile struct amdgpu_fw_shared *fw_shared;
 
 	/* VCN DEC TRAP */
@@ -154,7 +155,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 74814370ddc9..9967ac3fc51b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -156,12 +156,12 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v2_5_sw_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, r;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_5);
 	uint32_t *ptr;
-	struct amdgpu_device *adev = ip_block->adev;
-	int inst = ip_block->instance;
 
 	if (adev->vcn.harvest_config & (1 << inst))
 		goto sw_init;
@@ -185,7 +185,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 sw_init:
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	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 a7fb5dda51dd..e89088e3cd1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -160,14 +160,15 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
+	struct amdgpu_device *adev = ip_block->adev;
+	int inst = ip_block->instance;
 	struct amdgpu_ring *ring;
-	int inst = ip_block->instance, j, r;
 	int vcn_doorbell_index = 0;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_3_0);
 	uint32_t *ptr;
-	struct amdgpu_device *adev = ip_block->adev;
+	int j, r;

Looks like j is unused. fix this and patch looks good to me.
Acked-by: Sunil Khatri <sunil.khatri@xxxxxxx>

 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		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 c0c2a071ea15..1b492197c2b7 100644

--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -168,14 +168,15 @@ static int vcn_v4_0_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
  */
 static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
-	int inst = ip_block->instance, r;
+	int inst = ip_block->instance;
+	struct amdgpu_ring *ring;
+	int r;
 
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0);
 	uint32_t *ptr;
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		return r;
 
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 1d1ee6da7647..5b61000f3004 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -127,12 +127,13 @@ static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int inst = ip_block->instance;
 	struct amdgpu_ring *ring;
-	int inst = ip_block->instance, r, vcn_inst;
+	int r, vcn_inst;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
 	uint32_t *ptr;
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (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 81efc53e7cd3..4d944636d02b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -131,13 +131,14 @@ static int vcn_v4_0_5_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
-	int inst = ip_block->instance, r;
+	int inst = ip_block->instance;
+	struct amdgpu_ring *ring;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5);
 	uint32_t *ptr;
+	int r;
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		return r;
 
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 7873ca91da4c..8efedf943581 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -115,13 +115,14 @@ static int vcn_v5_0_0_early_init(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
-	int inst = ip_block->instance, r;
+	int inst = ip_block->instance;
+	struct amdgpu_ring *ring;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_5_0);
 	uint32_t *ptr;
+	int r;
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, inst);
 	if (r)
 		return r;