Merge tag 'amd-drm-next-6.17-2025-07-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.17-2025-07-01:

amdgpu:
- FAMS2 fixes
- OLED fixes
- Misc cleanups
- AUX fixes
- DMCUB updates
- SR-IOV hibernation support
- RAS updates
- DP tunneling fixes
- DML2 fixes
- Backlight improvements
- Suspend improvements
- Use scaling for non-native modes on eDP
- SDMA 4.4.x fixes
- PCIe DPM fixes
- SDMA 5.x fixes
- Cleaner shader updates for GC 9.x
- Remove fence slab
- ISP genpd support
- Parition handling rework
- SDMA FW checks for userq support
- Add missing firmware declaration
- Fix leak in amdgpu_ctx_mgr_entity_fini()
- Freesync fix
- Ring reset refactoring
- Legacy dpm verbosity changes

amdkfd:
- GWS fix
- mtype fix for ext coherent system memory
- MMU notifier fix
- gfx7/8 fix

radeon:
- CS validation support for additional GL extensions
- Bump driver version for new CS validation checks

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

1 files changed, 17 insertions, 44 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 6716ac281c49..7e26a44dcc1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -534,41 +534,17 @@ bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_rin
 static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
 {
 	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
-	int r = -EOPNOTSUPP;
 
-	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;
-	}
+	if (sdma_instance->funcs->soft_reset_kernel_queue)
+		return sdma_instance->funcs->soft_reset_kernel_queue(adev, instance_id);
 
-	return r;
+	return -EOPNOTSUPP;
 }
 
 /**
  * amdgpu_sdma_reset_engine - Reset a specific SDMA engine
  * @adev: Pointer to the AMDGPU device
- * @instance_id: ID of the SDMA engine instance to reset
+ * @instance_id: Logical ID of the SDMA engine instance to reset
  *
  * Returns: 0 on success, or a negative error code on failure.
  */
@@ -578,35 +554,35 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
 	struct amdgpu_ring *gfx_ring = &sdma_instance->ring;
 	struct amdgpu_ring *page_ring = &sdma_instance->page;
-	bool gfx_sched_stopped = false, page_sched_stopped = false;
 
 	mutex_lock(&sdma_instance->engine_reset_mutex);
 	/* Stop the scheduler's work queue for the GFX and page rings if they are running.
 	* This ensures that no new tasks are submitted to the queues while
 	* the reset is in progress.
 	*/
-	if (!amdgpu_ring_sched_ready(gfx_ring)) {
-		drm_sched_wqueue_stop(&gfx_ring->sched);
-		gfx_sched_stopped = true;
-	}
+	drm_sched_wqueue_stop(&gfx_ring->sched);
 
-	if (adev->sdma.has_page_queue && !amdgpu_ring_sched_ready(page_ring)) {
+	if (adev->sdma.has_page_queue)
 		drm_sched_wqueue_stop(&page_ring->sched);
-		page_sched_stopped = true;
-	}
 
-	if (sdma_instance->funcs->stop_kernel_queue)
+	if (sdma_instance->funcs->stop_kernel_queue) {
 		sdma_instance->funcs->stop_kernel_queue(gfx_ring);
+		if (adev->sdma.has_page_queue)
+			sdma_instance->funcs->stop_kernel_queue(page_ring);
+	}
 
 	/* Perform the SDMA reset for the specified instance */
 	ret = amdgpu_sdma_soft_reset(adev, instance_id);
 	if (ret) {
-		dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
+		dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id);
 		goto exit;
 	}
 
-	if (sdma_instance->funcs->start_kernel_queue)
+	if (sdma_instance->funcs->start_kernel_queue) {
 		sdma_instance->funcs->start_kernel_queue(gfx_ring);
+		if (adev->sdma.has_page_queue)
+			sdma_instance->funcs->start_kernel_queue(page_ring);
+	}
 
 exit:
 	/* Restart the scheduler's work queue for the GFX and page rings
@@ -614,12 +590,9 @@ exit:
 	 * to be submitted to the queues after the reset is complete.
 	 */
 	if (!ret) {
-		if (gfx_sched_stopped && amdgpu_ring_sched_ready(gfx_ring)) {
-			drm_sched_wqueue_start(&gfx_ring->sched);
-		}
-		if (page_sched_stopped && amdgpu_ring_sched_ready(page_ring)) {
+		drm_sched_wqueue_start(&gfx_ring->sched);
+		if (adev->sdma.has_page_queue)
 			drm_sched_wqueue_start(&page_ring->sched);
-		}
 	}
 	mutex_unlock(&sdma_instance->engine_reset_mutex);