Merge tag 'amd-drm-next-6.16-2025-05-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.16-2025-05-09:

amdgpu:
- IPS fixes
- DSC cleanup
- DC Scaling updates
- DC FP fixes
- Fused I2C-over-AUX updates
- SubVP fixes
- Freesync fix
- DMUB AUX fixes
- VCN fix
- Hibernation fixes
- HDP fixes
- DCN 2.1 fixes
- DPIA fixes
- DMUB updates
- Use drm_file_err in amdgpu
- Enforce isolation updates
- Use new dma_fence helpers
- USERQ fixes
- Documentation updates
- Misc code cleanups
- SR-IOV updates
- RAS updates
- PSP 12 cleanups

amdkfd:
- Update error messages for SDMA
- Userptr updates

drm:
- Add drm_file_err function

dma-buf:
- Add a helper to sort and deduplicate dma_fence arrays

From: Alex Deucher <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Dave Airlie <[email protected]>

1 files changed, 42 insertions, 64 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 529c9696c2f3..6716ac281c49 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -26,6 +26,8 @@
 #include "amdgpu_sdma.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_reset.h"
+#include "gc/gc_10_1_0_offset.h"
+#include "gc/gc_10_3_0_sh_mask.h"
 
 #define AMDGPU_CSA_SDMA_SIZE 64
 /* SDMA CSA reside in the 3rd page of CSA */
@@ -76,22 +78,14 @@ uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev) || vmid == 0 || !adev->gfx.mcbp)
 		return 0;
 
-	if (ring->is_mes_queue) {
-		uint32_t offset = 0;
+	r = amdgpu_sdma_get_index_from_ring(ring, &index);
 
-		offset = offsetof(struct amdgpu_mes_ctx_meta_data,
-				  sdma[ring->idx].sdma_meta_data);
-		csa_mc_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
-	} else {
-		r = amdgpu_sdma_get_index_from_ring(ring, &index);
-
-		if (r || index > 31)
-			csa_mc_addr = 0;
-		else
-			csa_mc_addr = amdgpu_csa_vaddr(adev) +
-				AMDGPU_CSA_SDMA_OFFSET +
-				index * AMDGPU_CSA_SDMA_SIZE;
-	}
+	if (r || index > 31)
+		csa_mc_addr = 0;
+	else
+		csa_mc_addr = amdgpu_csa_vaddr(adev) +
+			AMDGPU_CSA_SDMA_OFFSET +
+			index * AMDGPU_CSA_SDMA_SIZE;
 
 	return csa_mc_addr;
 }
@@ -537,28 +531,38 @@ bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_rin
 		return false;
 }
 
-/**
- * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks
- * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions
- *
- * This function allows KFD and AMDGPU to register their own callbacks for handling
- * pre-reset and post-reset operations for engine reset. These are needed because engine
- * reset will stop all queues on that engine.
- */
-void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs)
+static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
 {
-	if (!funcs)
-		return;
+	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
+	int r = -EOPNOTSUPP;
 
-	/* Ensure the reset_callback_list is initialized */
-	if (!adev->sdma.reset_callback_list.next) {
-		INIT_LIST_HEAD(&adev->sdma.reset_callback_list);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(4, 4, 2):
+	case IP_VERSION(4, 4, 4):
+	case IP_VERSION(4, 4, 5):
+		/* For SDMA 4.x, use the existing DPM interface for backward compatibility */
+		r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+		break;
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 1):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 5):
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 2):
+	case IP_VERSION(5, 2, 4):
+	case IP_VERSION(5, 2, 5):
+	case IP_VERSION(5, 2, 6):
+	case IP_VERSION(5, 2, 3):
+	case IP_VERSION(5, 2, 1):
+	case IP_VERSION(5, 2, 7):
+		if (sdma_instance->funcs->soft_reset_kernel_queue)
+			r = sdma_instance->funcs->soft_reset_kernel_queue(adev, instance_id);
+		break;
+	default:
+		break;
 	}
-	/* Initialize the list node in the callback structure */
-	INIT_LIST_HEAD(&funcs->list);
 
-	/* Add the callback structure to the global list */
-	list_add_tail(&funcs->list, &adev->sdma.reset_callback_list);
+	return r;
 }
 
 /**
@@ -566,16 +570,10 @@ void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct
  * @adev: Pointer to the AMDGPU device
  * @instance_id: ID of the SDMA engine instance to reset
  *
- * This function performs the following steps:
- * 1. Calls all registered pre_reset callbacks to allow KFD and AMDGPU to save their state.
- * 2. Resets the specified SDMA engine instance.
- * 3. Calls all registered post_reset callbacks to allow KFD and AMDGPU to restore their state.
- *
  * Returns: 0 on success, or a negative error code on failure.
  */
 int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 {
-	struct sdma_on_reset_funcs *funcs;
 	int ret = 0;
 	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
 	struct amdgpu_ring *gfx_ring = &sdma_instance->ring;
@@ -597,38 +595,18 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 		page_sched_stopped = true;
 	}
 
-	/* Invoke all registered pre_reset callbacks */
-	list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) {
-		if (funcs->pre_reset) {
-			ret = funcs->pre_reset(adev, instance_id);
-			if (ret) {
-				dev_err(adev->dev,
-				"beforeReset callback failed for instance %u: %d\n",
-					instance_id, ret);
-				goto exit;
-			}
-		}
-	}
+	if (sdma_instance->funcs->stop_kernel_queue)
+		sdma_instance->funcs->stop_kernel_queue(gfx_ring);
 
 	/* Perform the SDMA reset for the specified instance */
-	ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+	ret = amdgpu_sdma_soft_reset(adev, instance_id);
 	if (ret) {
 		dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
 		goto exit;
 	}
 
-	/* Invoke all registered post_reset callbacks */
-	list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) {
-		if (funcs->post_reset) {
-			ret = funcs->post_reset(adev, instance_id);
-			if (ret) {
-				dev_err(adev->dev,
-				"afterReset callback failed for instance %u: %d\n",
-					instance_id, ret);
-				goto exit;
-			}
-		}
-	}
+	if (sdma_instance->funcs->start_kernel_queue)
+		sdma_instance->funcs->start_kernel_queue(gfx_ring);
 
 exit:
 	/* Restart the scheduler's work queue for the GFX and page rings