Merge tag 'drm-next-2025-08-08' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "This is the fixes that built up in the merge window, mostly amdgpu and
  xe with one i915 display fix, seems like things are pretty good for
  rc1.

  i915:
   - DP LPFS fixes

  xe:
   - SRIOV: PF fixes and removal of need of module param
   - Fix driver unbind around Devcoredump
   - Mark xe driver as BROKEN if kernel page size is not 4kB

  amdgpu:
   - GC 9.5.0 fixes
   - SMU fix
   - DCE 6 DC fixes
   - mmhub client ID fixes
   - VRR fix
   - Backlight fix
   - UserQ fix
   - Legacy reset fix
   - Misc fixes

  amdkfd:
   - CRIU fix
   - Debugfs fix"

* tag 'drm-next-2025-08-08' of https://gitlab.freedesktop.org/drm/kernel: (28 commits)
  drm/amdgpu: add missing vram lost check for LEGACY RESET
  drm/amdgpu/discovery: fix fw based ip discovery
  drm/amdkfd: Destroy KFD debugfs after destroy KFD wq
  amdgpu/amdgpu_discovery: increase timeout limit for IFWI init
  drm/amdgpu: Update SDMA firmware version check for user queue support
  drm/amdgpu: Add NULL check for asic_funcs
  drm/amd/display: Revert "drm/amd/display: Fix AMDGPU_MAX_BL_LEVEL value"
  drm/amd/display: fix a Null pointer dereference vulnerability
  drm/amd/display: Add primary plane to commits for correct VRR handling
  drm/amdgpu: update mmhub 3.3 client id mappings
  drm/amdgpu: update mmhub 3.0.1 client id mappings
  drm/amdgpu: Retain job->vm in amdgpu_job_prepare_job
  drm/amd/display: Fix DCE 6.0 and 6.4 PLL programming.
  drm/amd/display: Don't overwrite dce60_clk_mgr
  drm/amdkfd: Fix checkpoint-restore on multi-xcc
  drm/amd: Restore cached manual clock settings during resume
  drm/amd: Restore cached power limit during resume
  drm/amdgpu: Update external revid for GC v9.5.0
  drm/amdgpu: Update supported modes for GC v9.5.0
  Mark xe driver as BROKEN if kernel page size is not 4kB
  ...

1 files changed, 41 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 81b3443c8d7f..efe0058b48ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -276,7 +276,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 	u32 msg;
 
 	if (!amdgpu_sriov_vf(adev)) {
-		/* It can take up to a second for IFWI init to complete on some dGPUs,
+		/* It can take up to two second for IFWI init to complete on some dGPUs,
 		 * but generally it should be in the 60-100ms range.  Normally this starts
 		 * as soon as the device gets power so by the time the OS loads this has long
 		 * completed.  However, when a card is hotplugged via e.g., USB4, we need to
@@ -284,7 +284,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 		 * continue.
 		 */
 
-		for (i = 0; i < 1000; i++) {
+		for (i = 0; i < 2000; i++) {
 			msg = RREG32(mmMP0_SMN_C2PMSG_33);
 			if (msg & 0x80000000)
 				break;
@@ -2555,40 +2555,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_RAVEN:
-	case CHIP_VEGA20:
-	case CHIP_ARCTURUS:
-	case CHIP_ALDEBARAN:
-		/* this is not fatal.  We have a fallback below
-		 * if the new firmwares are not present. some of
-		 * this will be overridden below to keep things
-		 * consistent with the current behavior.
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
 		 */
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (!r) {
-			amdgpu_discovery_harvest_ip(adev);
-			amdgpu_discovery_get_gfx_info(adev);
-			amdgpu_discovery_get_mall_info(adev);
-			amdgpu_discovery_get_vcn_info(adev);
-		}
-		break;
-	default:
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (r) {
-			drm_err(&adev->ddev, "discovery failed: %d\n", r);
-			return r;
-		}
-
-		amdgpu_discovery_harvest_ip(adev);
-		amdgpu_discovery_get_gfx_info(adev);
-		amdgpu_discovery_get_mall_info(adev);
-		amdgpu_discovery_get_vcn_info(adev);
-		break;
-	}
-
-	switch (adev->asic_type) {
-	case CHIP_VEGA10:
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2611,6 +2582,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 0);
 		break;
 	case CHIP_VEGA12:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2633,6 +2609,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 1);
 		break;
 	case CHIP_RAVEN:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 1;
 		adev->vcn.num_vcn_inst = 1;
@@ -2674,6 +2655,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		}
 		break;
 	case CHIP_VEGA20:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega20_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 8;
@@ -2697,6 +2683,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0);
 		break;
 	case CHIP_ARCTURUS:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		arct_reg_base_init(adev);
 		adev->sdma.num_instances = 8;
 		adev->vcn.num_vcn_inst = 2;
@@ -2725,6 +2716,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0);
 		break;
 	case CHIP_ALDEBARAN:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		aldebaran_reg_base_init(adev);
 		adev->sdma.num_instances = 5;
 		adev->vcn.num_vcn_inst = 2;
@@ -2751,6 +2747,16 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
 		break;
 	default:
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (r) {
+			drm_err(&adev->ddev, "discovery failed: %d\n", r);
+			return r;
+		}
+
+		amdgpu_discovery_harvest_ip(adev);
+		amdgpu_discovery_get_gfx_info(adev);
+		amdgpu_discovery_get_mall_info(adev);
+		amdgpu_discovery_get_vcn_info(adev);
 		break;
 	}