Merge tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Regular fixes for the week to end the merge window, i915 and xe have a
  few each, amdgpu makes up most of it with a bunch of SR-IOV related
  fixes amongst others.

  i915:
   - Fix BMG support to UHBR13.5
   - Two PSR fixes
   - Fix colorimetry detection for DP

  xe:
   - Fix macro for checking minimum GuC version
   - Fix CCS offset calculation for some BMG SKUs
   - Fix locking on memory usage reporting via fdinfo and BO destroy
   - Fix GPU page fault handler on a closed VM
   - Fix overflow in oa batch buffer

  amdgpu:
   - MES 12 fix
   - KFD fence sync fix
   - SR-IOV fixes
   - VCN 4.0.6 fix
   - SDMA 7.x fix
   - Bump driver version to note cleared VRAM support
   - SWSMU fix
   - CU occupancy logic fix
   - SDMA queue fix"

* tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm/kernel: (79 commits)
  drm/amd/pm: update workload mask after the setting
  drm/amdgpu: bump driver version for cleared VRAM
  drm/amdgpu: fix vbios fetching for SR-IOV
  drm/amdgpu: fix PTE copy corruption for sdma 7
  drm/amdkfd: Add SDMA queue quantum support for GFX12
  drm/amdgpu/vcn: enable AV1 on both instances
  drm/amdkfd: Fix CU occupancy for GFX 9.4.3
  drm/amdkfd: Update logic for CU occupancy calculations
  drm/amdgpu: skip coredump after job timeout in SRIOV
  drm/amdgpu: sync to KFD fences before clearing PTEs
  drm/amdgpu/mes12: set enable_level_process_quantum_check
  drm/i915/dp: Fix colorimetry detection
  drm/amdgpu/mes12: reduce timeout
  drm/amdgpu/mes11: reduce timeout
  drm/amdgpu: use GEM references instead of TTMs v2
  drm/amd/display: Allow backlight to go below `AMDGPU_DM_DEFAULT_MIN_BACKLIGHT`
  drm/amd/display: Fix kdoc entry for 'tps' in 'dc_process_dmub_dpia_set_tps_notification'
  drm/amdgpu: update golden regs for gfx12
  drm/amdgpu: clean up vbios fetching code
  drm/amd/display: handle nulled pipe context in DCE110's set_drr()
  ...

1 files changed, 3 insertions, 86 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f4628412dac4..c2394c8b4d6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4107,9 +4107,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->mm_stats.lock);
 	spin_lock_init(&adev->wb.lock);
 
-	INIT_LIST_HEAD(&adev->shadow_list);
-	mutex_init(&adev->shadow_list_lock);
-
 	INIT_LIST_HEAD(&adev->reset_list);
 
 	INIT_LIST_HEAD(&adev->ras_list);
@@ -5030,80 +5027,6 @@ static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_device_recover_vram - Recover some VRAM contents
- *
- * @adev: amdgpu_device pointer
- *
- * Restores the contents of VRAM buffers from the shadows in GTT.  Used to
- * restore things like GPUVM page tables after a GPU reset where
- * the contents of VRAM might be lost.
- *
- * Returns:
- * 0 on success, negative error code on failure.
- */
-static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
-{
-	struct dma_fence *fence = NULL, *next = NULL;
-	struct amdgpu_bo *shadow;
-	struct amdgpu_bo_vm *vmbo;
-	long r = 1, tmo;
-
-	if (amdgpu_sriov_runtime(adev))
-		tmo = msecs_to_jiffies(8000);
-	else
-		tmo = msecs_to_jiffies(100);
-
-	dev_info(adev->dev, "recover vram bo from shadow start\n");
-	mutex_lock(&adev->shadow_list_lock);
-	list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) {
-		/* If vm is compute context or adev is APU, shadow will be NULL */
-		if (!vmbo->shadow)
-			continue;
-		shadow = vmbo->shadow;
-
-		/* No need to recover an evicted BO */
-		if (!shadow->tbo.resource ||
-		    shadow->tbo.resource->mem_type != TTM_PL_TT ||
-		    shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET ||
-		    shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM)
-			continue;
-
-		r = amdgpu_bo_restore_shadow(shadow, &next);
-		if (r)
-			break;
-
-		if (fence) {
-			tmo = dma_fence_wait_timeout(fence, false, tmo);
-			dma_fence_put(fence);
-			fence = next;
-			if (tmo == 0) {
-				r = -ETIMEDOUT;
-				break;
-			} else if (tmo < 0) {
-				r = tmo;
-				break;
-			}
-		} else {
-			fence = next;
-		}
-	}
-	mutex_unlock(&adev->shadow_list_lock);
-
-	if (fence)
-		tmo = dma_fence_wait_timeout(fence, false, tmo);
-	dma_fence_put(fence);
-
-	if (r < 0 || tmo <= 0) {
-		dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
-		return -EIO;
-	}
-
-	dev_info(adev->dev, "recover vram bo from shadow done\n");
-	return 0;
-}
-
-
-/**
  * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
  *
  * @adev: amdgpu_device pointer
@@ -5165,12 +5088,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
+	if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST)
 		amdgpu_inc_vram_lost(adev);
-		r = amdgpu_device_recover_vram(adev);
-	}
-	if (r)
-		return r;
 
 	/* need to be called during full access so we can't do it later like
 	 * bare-metal does.
@@ -5569,9 +5488,7 @@ out:
 			}
 		}
 
-		if (!r)
-			r = amdgpu_device_recover_vram(tmp_adev);
-		else
+		if (r)
 			tmp_adev->asic_reset_res = r;
 	}
 
@@ -6189,7 +6106,7 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 		p2p_addressable = !(adev->gmc.aper_base & address_mask ||
 				     aper_limit & address_mask);
 	}
-	return is_large_bar && p2p_access && p2p_addressable;
+	return pcie_p2p && is_large_bar && p2p_access && p2p_addressable;
 #else
 	return false;
 #endif