Merge tag 'amd-drm-fixes-6.11-2024-07-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-6.11-2024-07-18:

amdgpu:
- Bump driver version for GFX12 DCC
- DC documention warning fixes
- VCN unified queue power fix
- SMU fix
- RAS fix
- Display corruption fix

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240718215258.79356-1-alexander.deucher@amd.com

18 files changed, 246 insertions, 141 deletions

diff --git a/Documentation/gpu/amdgpu/display/dcn-blocks.rst b/Documentation/gpu/amdgpu/display/dcn-blocks.rst
index a3fbd3ea028b..5e34366f6dbe 100644
--- a/Documentation/gpu/amdgpu/display/dcn-blocks.rst
+++ b/Documentation/gpu/amdgpu/display/dcn-blocks.rst
@@ -8,37 +8,22 @@ and the code documentation when it is automatically generated.
 DCHUBBUB
 --------
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :internal:
-
 HUBP
 ----
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :internal:
-
 DPP
 ---
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
    :internal:
 
 MPC
@@ -48,10 +33,8 @@ MPC
    :doc: overview
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
    :internal:
+   :no-identifiers: mpcc_blnd_cfg mpcc_alpha_blend_mode
 
 OPP
 ---
@@ -60,19 +43,13 @@ OPP
    :doc: overview
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
    :internal:
 
 DIO
 ---
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
    :internal:
diff --git a/Documentation/gpu/amdgpu/display/display-manager.rst b/Documentation/gpu/amdgpu/display/display-manager.rst
index 67a811e6891f..b269ff3f7a54 100644
--- a/Documentation/gpu/amdgpu/display/display-manager.rst
+++ b/Documentation/gpu/amdgpu/display/display-manager.rst
@@ -132,7 +132,7 @@ The DRM blend mode and its elements are then mapped by AMDGPU display manager
 (MPC), as follows:
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :functions: mpcc_blnd_cfg
+   :identifiers: mpcc_blnd_cfg
 
 Therefore, the blending configuration for a single MPCC instance on the MPC
 tree is defined by :c:type:`mpcc_blnd_cfg`, where
@@ -144,7 +144,7 @@ alpha and plane alpha values. It sets one of the three modes for
 :c:type:`MPCC_ALPHA_BLND_MODE`, as described below.
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :functions: mpcc_alpha_blend_mode
+   :identifiers: mpcc_alpha_blend_mode
 
 DM then maps the elements of `enum mpcc_alpha_blend_mode` to those in the DRM
 blend formula, as follows:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 78089f2f79f5..094498a0964b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -116,9 +116,10 @@
  * - 3.55.0 - Add AMDGPU_INFO_GPUVM_FAULT query
  * - 3.56.0 - Update IB start address and size alignment for decode and encode
  * - 3.57.0 - Compute tunneling on GFX10+
+ * - 3.58.0 - Add GFX12 DCC support
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	57
+#define KMS_DRIVER_MINOR	58
 #define KMS_DRIVER_PATCHLEVEL	0
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 800cc7a148b2..7cdff355cedb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1591,6 +1591,68 @@ static void psp_ras_ta_check_status(struct psp_context *psp)
 	}
 }
 
+static int psp_ras_send_cmd(struct psp_context *psp,
+		enum ras_command cmd_id, void *in, void *out)
+{
+	struct ta_ras_shared_memory *ras_cmd;
+	uint32_t cmd = cmd_id;
+	int ret = 0;
+
+	if (!in)
+		return -EINVAL;
+
+	mutex_lock(&psp->ras_context.mutex);
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
+	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+
+	switch (cmd) {
+	case TA_RAS_COMMAND__ENABLE_FEATURES:
+	case TA_RAS_COMMAND__DISABLE_FEATURES:
+		memcpy(&ras_cmd->ras_in_message,
+			in, sizeof(ras_cmd->ras_in_message));
+		break;
+	case TA_RAS_COMMAND__TRIGGER_ERROR:
+		memcpy(&ras_cmd->ras_in_message.trigger_error,
+			in, sizeof(ras_cmd->ras_in_message.trigger_error));
+		break;
+	case TA_RAS_COMMAND__QUERY_ADDRESS:
+		memcpy(&ras_cmd->ras_in_message.address,
+			in, sizeof(ras_cmd->ras_in_message.address));
+		break;
+	default:
+		dev_err(psp->adev->dev, "Invalid ras cmd id: %u\n", cmd);
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	ras_cmd->cmd_id = cmd;
+	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+
+	switch (cmd) {
+	case TA_RAS_COMMAND__TRIGGER_ERROR:
+		if (ret || psp->cmd_buf_mem->resp.status)
+			ret = -EINVAL;
+		else if (out)
+			memcpy(out, &ras_cmd->ras_status, sizeof(ras_cmd->ras_status));
+		break;
+	case TA_RAS_COMMAND__QUERY_ADDRESS:
+		if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
+			ret = -EINVAL;
+		else if (out)
+			memcpy(out,
+				&ras_cmd->ras_out_message.address,
+				sizeof(ras_cmd->ras_out_message.address));
+		break;
+	default:
+		break;
+	}
+
+err_out:
+	mutex_unlock(&psp->ras_context.mutex);
+
+	return ret;
+}
+
 int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
 	struct ta_ras_shared_memory *ras_cmd;
@@ -1632,23 +1694,15 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 int psp_ras_enable_features(struct psp_context *psp,
 		union ta_ras_cmd_input *info, bool enable)
 {
-	struct ta_ras_shared_memory *ras_cmd;
+	enum ras_command cmd_id;
 	int ret;
 
-	if (!psp->ras_context.context.initialized)
+	if (!psp->ras_context.context.initialized || !info)
 		return -EINVAL;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
-
-	if (enable)
-		ras_cmd->cmd_id = TA_RAS_COMMAND__ENABLE_FEATURES;
-	else
-		ras_cmd->cmd_id = TA_RAS_COMMAND__DISABLE_FEATURES;
-
-	ras_cmd->ras_in_message = *info;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+	cmd_id = enable ?
+		TA_RAS_COMMAND__ENABLE_FEATURES : TA_RAS_COMMAND__DISABLE_FEATURES;
+	ret = psp_ras_send_cmd(psp, cmd_id, info, NULL);
 	if (ret)
 		return -EINVAL;
 
@@ -1672,6 +1726,8 @@ int psp_ras_terminate(struct psp_context *psp)
 
 	psp->ras_context.context.initialized = false;
 
+	mutex_destroy(&psp->ras_context.mutex);
+
 	return ret;
 }
 
@@ -1756,9 +1812,10 @@ int psp_ras_initialize(struct psp_context *psp)
 
 	ret = psp_ta_load(psp, &psp->ras_context.context);
 
-	if (!ret && !ras_cmd->ras_status)
+	if (!ret && !ras_cmd->ras_status) {
 		psp->ras_context.context.initialized = true;
-	else {
+		mutex_init(&psp->ras_context.mutex);
+	} else {
 		if (ras_cmd->ras_status)
 			dev_warn(adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
 
@@ -1772,12 +1829,12 @@ int psp_ras_initialize(struct psp_context *psp)
 int psp_ras_trigger_error(struct psp_context *psp,
 			  struct ta_ras_trigger_error_input *info, uint32_t instance_mask)
 {
-	struct ta_ras_shared_memory *ras_cmd;
 	struct amdgpu_device *adev = psp->adev;
 	int ret;
 	uint32_t dev_mask;
+	uint32_t ras_status = 0;
 
-	if (!psp->ras_context.context.initialized)
+	if (!psp->ras_context.context.initialized || !info)
 		return -EINVAL;
 
 	switch (info->block_id) {
@@ -1801,13 +1858,8 @@ int psp_ras_trigger_error(struct psp_context *psp,
 	dev_mask &= AMDGPU_RAS_INST_MASK;
 	info->sub_block_index |= dev_mask;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
-
-	ras_cmd->cmd_id = TA_RAS_COMMAND__TRIGGER_ERROR;
-	ras_cmd->ras_in_message.trigger_error = *info;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+	ret = psp_ras_send_cmd(psp,
+			TA_RAS_COMMAND__TRIGGER_ERROR, info, &ras_status);
 	if (ret)
 		return -EINVAL;
 
@@ -1817,9 +1869,9 @@ int psp_ras_trigger_error(struct psp_context *psp,
 	if (amdgpu_ras_intr_triggered())
 		return 0;
 
-	if (ras_cmd->ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
+	if (ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
 		return -EACCES;
-	else if (ras_cmd->ras_status)
+	else if (ras_status)
 		return -EINVAL;
 
 	return 0;
@@ -1829,25 +1881,16 @@ int psp_ras_query_address(struct psp_context *psp,
 			  struct ta_ras_query_address_input *addr_in,
 			  struct ta_ras_query_address_output *addr_out)
 {
-	struct ta_ras_shared_memory *ras_cmd;
 	int ret;
 
-	if (!psp->ras_context.context.initialized)
-		return -EINVAL;
-
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
-
-	ras_cmd->cmd_id = TA_RAS_COMMAND__QUERY_ADDRESS;
-	ras_cmd->ras_in_message.address = *addr_in;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
-	if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
+	if (!psp->ras_context.context.initialized ||
+		!addr_in || !addr_out)
 		return -EINVAL;
 
-	*addr_out = ras_cmd->ras_out_message.address;
+	ret = psp_ras_send_cmd(psp,
+			TA_RAS_COMMAND__QUERY_ADDRESS, addr_in, addr_out);
 
-	return 0;
+	return ret;
 }
 // ras end
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 3635303e6548..74a96516c913 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -200,6 +200,7 @@ struct psp_xgmi_context {
 struct psp_ras_context {
 	struct ta_context		context;
 	struct amdgpu_ras		*ras;
+	struct mutex			mutex;
 };
 
 #define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 8e8afbd237bc..0c856005df6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -348,6 +348,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 
 	context->session_id = ta_id;
 
+	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
 		goto err_free_shared_buf;
@@ -366,6 +367,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		ret = -EFAULT;
 
 err_free_shared_buf:
+	mutex_unlock(&psp->ras_context.mutex);
 	kfree(shared_buf);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 8d65b096db90..43f44cc201cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -147,6 +147,10 @@ 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);
+
 	hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
@@ -275,18 +279,6 @@ 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;
@@ -397,7 +389,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+		/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+		    !adev->vcn.using_unified_queue) {
 			struct dpg_pause_state new_state;
 
 			if (fence[j] ||
@@ -443,7 +437,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 	       AMD_PG_STATE_UNGATE);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    !adev->vcn.using_unified_queue) {
 		struct dpg_pause_state new_state;
 
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
@@ -469,8 +465,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
 	if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
-		ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+	    ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
+	    !adev->vcn.using_unified_queue)
 		atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
 	atomic_dec(&ring->adev->vcn.total_submission_cnt);
@@ -724,12 +724,11 @@ 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,
@@ -742,7 +741,7 @@ 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);
@@ -761,7 +760,7 @@ 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);
@@ -851,15 +850,15 @@ 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,
@@ -873,7 +872,7 @@ 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;
@@ -895,7 +894,7 @@ 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);
@@ -918,15 +917,15 @@ 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,
@@ -940,7 +939,7 @@ 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;
@@ -962,7 +961,7 @@ 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 9f06def236fd..1a5439abd1a0 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 {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 5fd1b6b44577..2d7755e2b6c3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -137,6 +137,13 @@ struct vblank_control_work {
 	bool enable;
 };
 
+/**
+ * struct idle_workqueue - Work data for periodic action in idle
+ * @work: Kernel work data for the work event
+ * @dm: amdgpu display manager device
+ * @enable: true if idle worker is enabled
+ * @running: true if idle worker is running
+ */
 struct idle_workqueue {
 	struct work_struct work;
 	struct amdgpu_display_manager *dm;
@@ -502,6 +509,12 @@ struct amdgpu_display_manager {
 	 * Deferred work for vblank control events.
 	 */
 	struct workqueue_struct *vblank_control_workqueue;
+
+	/**
+	 * @idle_workqueue:
+	 *
+	 * Periodic work for idle events.
+	 */
 	struct idle_workqueue *idle_workqueue;
 
 	struct drm_atomic_state *cached_state;
@@ -587,7 +600,9 @@ struct amdgpu_display_manager {
 	 */
 	struct mutex dpia_aux_lock;
 
-	/*
+	/**
+	 * @bb_from_dmub:
+	 *
 	 * Bounding box data read from dmub during early initialization for DCN4+
 	 */
 	struct dml2_soc_bb *bb_from_dmub;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 9ac7fc717a92..0150f2581ee4 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -147,16 +147,28 @@ struct cnv_color_keyer_params {
 	int color_keyer_blue_high;
 };
 
-/* new for dcn2: set the 8bit alpha values based on the 2 bit alpha
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT0   default: 0b00000000
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT1   default: 0b01010101
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT2   default: 0b10101010
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT3   default: 0b11111111
+/**
+ * struct cnv_alpha_2bit_lut - Set the 8bit alpha values based on the 2 bit alpha
  */
 struct cnv_alpha_2bit_lut {
+	/**
+	* @lut0: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT0. Default: 0b00000000
+	*/
 	int lut0;
+
+	/**
+	 * @lut1: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT1. Default: 0b01010101
+	 */
 	int lut1;
+
+	/**
+	 * @lut2: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT2. Default: 0b10101010
+	 */
 	int lut2;
+
+	/**
+	 * @lut3: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT3. Default: 0b11111111
+	 */
 	int lut3;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 40a9b3471208..3a89cc0cffc1 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -1039,6 +1039,20 @@ struct mpc_funcs {
 	*/
 	void (*program_lut_mode)(struct mpc *mpc, const enum MCM_LUT_ID id, const enum MCM_LUT_XABLE xable,
 			bool lut_bank_a, int mpcc_id);
+	/**
+	* @program_3dlut_size:
+	*
+	* Program 3D LUT size.
+	*
+	* Parameters:
+	* - [in/out] mpc - MPC context.
+	* - [in] is_17x17x17 - is 3dlut 17x17x17
+	* - [in] mpcc_id
+	*
+	* Return:
+	*
+	* void
+	*/
 	void (*program_3dlut_size)(struct mpc *mpc, bool is_17x17x17, int mpcc_id);
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 127fb1a51654..747679cb4944 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -205,9 +205,24 @@ struct gamma_coefficients {
 	struct fixed31_32 user_brightness;
 };
 
+/**
+ * struct pwl_float_data - Fixed point RGB color
+ */
 struct pwl_float_data {
+	/**
+	 * @r: Component Red.
+	 */
 	struct fixed31_32 r;
+
+	/**
+	 * @g: Component Green.
+	 */
+
 	struct fixed31_32 g;
+
+	/**
+	 * @b: Component Blue.
+	 */
 	struct fixed31_32 b;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
index 50459d7a0f85..b76737b7b9e4 100644
--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
+++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
@@ -26,6 +26,16 @@
 #include "core_types.h"
 #include "link_enc_cfg.h"
 
+/**
+ * DOC: overview
+ *
+ * Display Input Output (DIO), is the display input and output unit in DCN. It
+ * includes output encoders to support different display output, like
+ * DisplayPort, HDMI, DVI interface, and others. It also includes the control
+ * and status channels for these interfaces.
+ */
+
+
 void set_dio_throttled_vcp_size(struct pipe_ctx *pipe_ctx,
 		struct fixed31_32 throttled_vcp_size)
 {
@@ -254,12 +264,31 @@ static const struct link_hwss dio_link_hwss = {
 	},
 };
 
+/**
+ * can_use_dio_link_hwss - Check if the link_hwss is accessible
+ *
+ * @link: Reference a link struct containing one or more sinks and the
+ *	  connective status.
+ * @link_res: Mappable hardware resource used to enable a link.
+ *
+ * Returns:
+ * Return true if the link encoder is accessible from link.
+ */
 bool can_use_dio_link_hwss(const struct dc_link *link,
 		const struct link_resource *link_res)
 {
 	return link->link_enc != NULL;
 }
 
+/**
+ * get_dio_link_hwss - Return link_hwss reference
+ *
+ * This function behaves like a get function to return the link_hwss populated
+ * in the link_hwss_dio.c file.
+ *
+ * Returns:
+ * Return the reference to the filled struct of link_hwss.
+ */
 const struct link_hwss *get_dio_link_hwss(void)
 {
 	return &dio_link_hwss;
diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
index a1f72fe378ee..45f0e091fcb0 100644
--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
@@ -23,15 +23,6 @@
  *
  */
 
-/**
- * DOC: overview
- *
- * Display Input Output (DIO), is the display input and output unit in DCN. It
- * includes output encoders to support different display output, like
- * DisplayPort, HDMI, DVI interface, and others. It also includes the control
- * and status channels for these interfaces.
- */
-
 #ifndef __LINK_HWSS_DIO_H__
 #define __LINK_HWSS_DIO_H__
 
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
index 336488c0574e..94427875bcdd 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
@@ -945,19 +945,10 @@ void optc1_set_drr(
 				OTG_FORCE_LOCK_ON_EVENT, 0,
 				OTG_SET_V_TOTAL_MIN_MASK_EN, 0,
 				OTG_SET_V_TOTAL_MIN_MASK, 0);
-
-		// Setup manual flow control for EOF via TRIG_A
-		optc->funcs->setup_manual_trigger(optc);
-
-	} else {
-		REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
-				OTG_SET_V_TOTAL_MIN_MASK, 0,
-				OTG_V_TOTAL_MIN_SEL, 0,
-				OTG_V_TOTAL_MAX_SEL, 0,
-				OTG_FORCE_LOCK_ON_EVENT, 0);
-
-		optc->funcs->set_vtotal_min_max(optc, 0, 0);
 	}
+
+	// Setup manual flow control for EOF via TRIG_A
+	optc->funcs->setup_manual_trigger(optc);
 }
 
 void optc1_set_vtotal_min_max(struct timing_generator *optc, int vtotal_min, int vtotal_max)
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
index 43417cff2c9b..b4694985a40a 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
@@ -453,6 +453,16 @@ void optc2_setup_manual_trigger(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	/* Set the min/max selectors unconditionally so that
+	 * DMCUB fw may change OTG timings when necessary
+	 * TODO: Remove the w/a after fixing the issue in DMCUB firmware
+	 */
+	REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
+				 OTG_V_TOTAL_MIN_SEL, 1,
+				 OTG_V_TOTAL_MAX_SEL, 1,
+				 OTG_FORCE_LOCK_ON_EVENT, 0,
+				 OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */
+
 	REG_SET_8(OTG_TRIGA_CNTL, 0,
 			OTG_TRIGA_SOURCE_SELECT, 21,
 			OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fb8643d25d1b..9d7454b3c314 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1924,20 +1924,12 @@ static int smu_disable_dpms(struct smu_context *smu)
 	}
 
 	/*
-	 * For SMU 13.0.4/11 and 14.0.0, PMFW will handle the features disablement properly
+	 * For GFX11 and subsequent APUs, PMFW will handle the features disablement properly
 	 * for gpu reset and S0i3 cases. Driver involvement is unnecessary.
 	 */
-	if (amdgpu_in_reset(adev) || adev->in_s0ix) {
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 4):
-		case IP_VERSION(13, 0, 11):
-		case IP_VERSION(14, 0, 0):
-		case IP_VERSION(14, 0, 1):
-			return 0;
-		default:
-			break;
-		}
-	}
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) >= 11 &&
+	    smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix))
+		return 0;
 
 	/*
 	 * For gpu reset, runpm and hibernation through BACO,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 5d47d58944f6..8798ebfcea83 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -69,6 +69,9 @@
 #define SMU_14_0_0_UMD_PSTATE_SOCCLK			678
 #define SMU_14_0_0_UMD_PSTATE_FCLK			1800
 
+#define SMU_14_0_4_UMD_PSTATE_GFXCLK			938
+#define SMU_14_0_4_UMD_PSTATE_SOCCLK			938
+
 #define FEATURE_MASK(feature) (1ULL << feature)
 #define SMC_DPM_FEATURE ( \
 	FEATURE_MASK(FEATURE_CCLK_DPM_BIT) | \
@@ -1296,19 +1299,28 @@ static int smu_v14_0_common_get_dpm_profile_freq(struct smu_context *smu,
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_GFXCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			clk_limit = SMU_14_0_4_UMD_PSTATE_GFXCLK;
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_GFXCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &clk_limit);
 		else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &clk_limit, NULL);
 		break;
 	case SMU_SOCCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_SOCCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			clk_limit = SMU_14_0_4_UMD_PSTATE_SOCCLK;
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_SOCCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &clk_limit);
 		break;
 	case SMU_FCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_FCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &clk_limit);
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_FCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &clk_limit);
 		else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK)