Merge tag 'drm-next-2023-09-08' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular rounds of rc1 fixes, a large bunch for amdgpu since it's three
  weeks in one go, one i915, one nouveau and one ivpu.

  I think there might be a few more fixes in misc that I haven't pulled
  in yet, but we should get them all for rc2.

  amdgpu:
   - Display replay fixes
   - Fixes for headless boards
   - Fix documentation breakage
   - RAS fixes
   - Handle newer IP discovery tables
   - SMU 13.0.6 fixes
   - SR-IOV fixes
   - Display vstartup fixes
   - NBIO 7.9 fixes
   - Display scaling mode fixes
   - Debugfs power reporting fix
   - GC 9.4.3 fixes
   - Dirty framebuffer fixes for fbcon
   - eDP fixes
   - DCN 3.1.5 fix
   - Display ODM fixes
   - GPU core dump fix
   - Re-enable zops property now that IGT test is fixed
   - Fix possible UAF in CS code
   - Cursor degamma fix

  amdkfd:
   - HMM fixes
   - Interrupt masking fix
   - GFX11 MQD fixes

  i915:
   - Mark requests for GuC virtual engines to avoid use-after-free

  nouveau:
   - Fix fence state in nouveau_fence_emit()

  ivpu:
   - replace strncpy"

* tag 'drm-next-2023-09-08' of git://anongit.freedesktop.org/drm/drm: (51 commits)
  drm/amdgpu: Restrict bootloader wait to SMUv13.0.6
  drm/amd/display: prevent potential division by zero errors
  drm/amd/display: enable cursor degamma for DCN3+ DRM legacy gamma
  drm/amd/display: limit the v_startup workaround to ASICs older than DCN3.1
  Revert "drm/amd/display: Remove v_startup workaround for dcn3+"
  drm/amdgpu: fix amdgpu_cs_p1_user_fence
  Revert "Revert "drm/amd/display: Implement zpos property""
  drm/amdkfd: Add missing gfx11 MQD manager callbacks
  drm/amdgpu: Free ras cmd input buffer properly
  drm/amdgpu: Hide xcp partition sysfs under SRIOV
  drm/amdgpu: use read-modify-write mode for gfx v9_4_3 SQ setting
  drm/amdkfd: use mask to get v9 interrupt sq data bits correctly
  drm/amdgpu: Allocate coredump memory in a nonblocking way
  drm/amdgpu: Support query ecc cap for aqua_vanjaram
  drm/amdgpu: Add umc_info v4_0 structure
  drm/amd/display: always switch off ODM before committing more streams
  drm/amd/display: Remove wait while locked
  drm/amd/display: update blank state on ODM changes
  drm/amd/display: Add smu write msg id fail retry process
  drm/amdgpu: Add SMU v13.0.6 default reset methods
  ...

1 files changed, 25 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e77f048c99d8..3f001a50b34a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -885,13 +885,20 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
  */
 static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 {
+	int ret;
+
 	amdgpu_asic_pre_asic_init(adev);
 
 	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3) ||
-	    adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0))
-		return amdgpu_atomfirmware_asic_init(adev, true);
-	else
+	    adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) {
+		amdgpu_psp_wait_for_bootloader(adev);
+		ret = amdgpu_atomfirmware_asic_init(adev, true);
+		return ret;
+	} else {
 		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	}
+
+	return 0;
 }
 
 /**
@@ -4694,9 +4701,12 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 	}
 
 	if (ret)
-		dev_err(adev->dev, "GPU mode1 reset failed\n");
+		goto mode1_reset_failed;
 
 	amdgpu_device_load_pci_state(adev->pdev);
+	ret = amdgpu_psp_wait_for_bootloader(adev);
+	if (ret)
+		goto mode1_reset_failed;
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -4707,7 +4717,17 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 		udelay(1);
 	}
 
+	if (i >= adev->usec_timeout) {
+		ret = -ETIMEDOUT;
+		goto mode1_reset_failed;
+	}
+
 	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
+
+	return 0;
+
+mode1_reset_failed:
+	dev_err(adev->dev, "GPU mode1 reset failed\n");
 	return ret;
 }
 
@@ -4849,7 +4869,7 @@ static void amdgpu_reset_capture_coredumpm(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 
 	ktime_get_ts64(&adev->reset_time);
-	dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_KERNEL,
+	dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_NOWAIT,
 		      amdgpu_devcoredump_read, amdgpu_devcoredump_free);
 }
 #endif