Merge tag 'drm-next-2022-12-13' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest highlight is that the accel subsystem framework is merged.
  Hopefully for 6.3 we will be able to line up a driver to use it.

  In drivers land, i915 enables DG2 support by default now, and nouveau
  has a big stability refactoring and initial ampere support, AMD
  includes new hw IP support and should build on ARM again. There is
  also an ofdrm driver to take over offb on platforms it's used.

  Stuff outside my tree, the dma-buf patches hit a few places, the vc4
  firmware changes also do, and i915 has some interactions with MEI for
  discrete GPUs. I think all of those should have been acked/reviewed by
  relevant parties.

  New driver:
   - ofdrm - replacement for offb

  fbdev:
   - add support for nomodeset

  fourcc:
   - add Vivante tiled modifier

  core:
   - atomic-helpers: CRTC primary plane test fixes, fb access hooks
   - connector: TV API consistency, cmdline parser improvements
   - send connector hotplug on cleanup
   - sort makefile objects

  tests:
   - sort kunit tests
   - improve DP-MST tests
   - add kunit helpers to create a device

  sched:
   - module param for scheduling policy
   - refcounting fix

  buddy:
   - add back random seed log

  ttm:
   - convert ttm_resource to size_t
   - optimize pool allocations

  edid:
   - HFVSDB parsing support fixes
   - logging/debug improvements
   - DSC quirks

  dma-buf:
   - Add unlocked vmap and attachment mapping
   - move drivers to common locking convention
   - locking improvements

  firmware:
   - new API for rPI firmware and vc4

  xilinx:
   - zynqmp: displayport bridge support
   - dpsub fix

  bridge:
   - adv7533: Remove dynamic lane switching
   - it6505: Runtime PM support, sync improvements
   - ps8640: Handle AUX defer messages
   - tc358775: Drop soft-reset over I2C

  panel:
   - panel-edp: Add INX N116BGE-EA2 C2 and C4 support.
   - Jadard JD9365DA-H3
   - NewVision NV3051D

  amdgpu:
   - DCN support on ARM
   - DCN 2.1 secure display
   - Sienna Cichlid mode2 reset fixes
   - new GC 11.x firmware versions
   - drop AMD specific DSC workarounds in favour of drm code
   - clang warning fixes
   - scheduler rework
   - SR-IOV fixes
   - GPUVM locking fixes
   - fix memory leak in CS IOCTL error path
   - flexible array updates
   - enable new GC/PSP/SMU/NBIO IP
   - GFX preemption support for gfx9

  amdkfd:
   - cache size fixes
   - userptr fixes
   - enable cooperative launch on gfx 10.3
   - enable GC 11.0.4 KFD support

  radeon:
   - replace kmap with kmap_local_page
   - ACPI ref count fix
   - HDA audio notifier support

  i915:
   - DG2 enabled by default
   - MTL enablement work
   - hotplug refactoring
   - VBT improvements
   - Display and watermark refactoring
   - ADL-P workaround
   - temp disable runtime_pm for discrete-
   - fix for A380 as a secondary GPU
   - Wa_18017747507 for DG2
   - CS timestamp support fixes for gen5 and earlier
   - never purge busy TTM objects
   - use i915_sg_dma_sizes for all backends
   - demote GuC kernel contexts to normal priority
   - gvt: refactor for new MDEV interface
   - enable DC power states on eDP ports
   - fix gen 2/3 workarounds

  nouveau:
   - fix page fault handling
   - Ampere acceleration support
   - driver stability improvements
   - nva3 backlight support

  msm:
   - MSM_INFO_GET_FLAGS support
   - DPU: XR30 and P010 image formats
   - Qualcomm SM6115 support
   - DSI PHY support for QCM2290
   - HDMI: refactored dev init path
   - remove exclusive-fence hack
   - fix speed-bin detection
   - enable clamp to idle on 7c3
   - improved hangcheck detection

  vmwgfx:
   - fb and cursor refactoring
   - convert to generic hashtable
   - cursor improvements

  etnaviv:
   - hw workarounds
   - softpin MMU fixes

  ast:
   - atomic gamma LUT support
   - convert to SHMEM

  lcdif:
   - support YUV planes
   - Increase DMA burst size
   - FIFO threshold tuning

  meson:
   - fix return type of cvbs mode_valid

  mgag200:
   - fix PLL setup on some revisions

  sun4i:
   - A100 and D1 support

  udl:
   - modesetting improvements
   - hot unplug support

  vc4:
   - support PAL-M
   - fix regression preventing 4K @ 60Hz
   - fix NULL ptr deref

  v3d:
   - switch to drm managed resources

  renesas:
   - RZ/G2L DSI support
   - DU Kconfig cleanup

  mediatek:
   - fixup dpi and hdmi
   - MT8188 dpi support
   - MT8195 AFBC support

  tegra:
   - NVDEC hardware on Tegra234 SoC

  hdlcd:
   - switch to drm managed resources

  ingenic:
   - fix registration error path

  hisilicon:
   - convert to drm_mode_init

  maildp:
   - use managed resources

  mtk:
   - use drm_mode_init

  rockchip:
   - use drm_mode_copy"

* tag 'drm-next-2022-12-13' of git://anongit.freedesktop.org/drm/drm: (1397 commits)
  drm/amdgpu: fix mmhub register base coding error
  drm/amdgpu: add tmz support for GC IP v11.0.4
  drm/amdgpu: enable GFX Clock Gating control for GC IP v11.0.4
  drm/amdgpu: enable GFX Power Gating for GC IP v11.0.4
  drm/amdgpu: enable GFX IP v11.0.4 CG support
  drm/amdgpu: Make amdgpu_ring_mux functions as static
  drm/amdgpu: generally allow over-commit during BO allocation
  drm/amd/display: fix array index out of bound error in DCN32 DML
  drm/amd/display: 3.2.215
  drm/amd/display: set optimized required for comp buf changes
  drm/amd/display: Add debug option to skip PSR CRTC disable
  drm/amd/display: correct DML calc error of UrgentLatency
  drm/amd/display: correct static_screen_event_mask
  drm/amd/display: Ensure commit_streams returns the DC return code
  drm/amd/display: read invalid ddc pin status cause engine busy
  drm/amd/display: Bypass DET swath fill check for max clocks
  drm/amd/display: Disable uclk pstate for subvp pipes
  drm/amd/display: Fix DCN2.1 default DSC clocks
  drm/amd/display: Enable dp_hdmi21_pcon support
  drm/amd/display: prevent seamless boot on displays that don't have the preferred dig
  ...

1 files changed, 59 insertions, 138 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f1e9663b40510..cfa411c120724 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -37,6 +37,7 @@
 #include <linux/pci-p2pdma.h>
 
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/amdgpu_drm.h>
 #include <linux/vgaarb.h>
@@ -1568,7 +1569,7 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
  * @pdev: pci dev pointer
  * @state: vga_switcheroo state
  *
- * Callback for the switcheroo driver.  Suspends or resumes the
+ * Callback for the switcheroo driver.  Suspends or resumes
  * the asics before or after it is powered up using ACPI methods.
  */
 static void amdgpu_switcheroo_set_state(struct pci_dev *pdev,
@@ -1915,6 +1916,16 @@ static void amdgpu_device_enable_virtual_display(struct amdgpu_device *adev)
 	}
 }
 
+void amdgpu_device_set_sriov_virtual_display(struct amdgpu_device *adev)
+{
+	if (amdgpu_sriov_vf(adev) && !adev->enable_virtual_display) {
+		adev->mode_info.num_crtc = 1;
+		adev->enable_virtual_display = true;
+		DRM_INFO("virtual_display:%d, num_crtc:%d\n",
+			 adev->enable_virtual_display, adev->mode_info.num_crtc);
+	}
+}
+
 /**
  * amdgpu_device_parse_gpu_info_fw - parse gpu info firmware
  *
@@ -2397,7 +2408,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			adev->ip_blocks[i].status.hw = true;
 
 			/* right after GMC hw init, we create CSA */
-			if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
+			if (amdgpu_mcbp) {
 				r = amdgpu_allocate_static_csa(adev, &adev->virt.csa_obj,
 								AMDGPU_GEM_DOMAIN_VRAM,
 								AMDGPU_CSA_SIZE);
@@ -2462,6 +2473,11 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!amdgpu_sriov_vf(adev)) {
 				struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 
+				if (WARN_ON(!hive)) {
+					r = -ENOENT;
+					goto init_failed;
+				}
+
 				if (!hive->reset_domain ||
 				    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 					r = -ENOENT;
@@ -3347,8 +3363,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
  */
 bool amdgpu_device_has_dc_support(struct amdgpu_device *adev)
 {
-	if (amdgpu_sriov_vf(adev) ||
-	    adev->enable_virtual_display ||
+	if (adev->enable_virtual_display ||
 	    (adev->harvest_ip_mask & AMD_HARVEST_IP_DMU_MASK))
 		return false;
 
@@ -4171,21 +4186,15 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 
 	r = amdgpu_device_ip_resume(adev);
 
-	/* no matter what r is, always need to properly release full GPU */
-	if (amdgpu_sriov_vf(adev)) {
-		amdgpu_virt_init_data_exchange(adev);
-		amdgpu_virt_release_full_gpu(adev, true);
-	}
-
 	if (r) {
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
-		return r;
+		goto exit;
 	}
 	amdgpu_fence_driver_hw_init(adev);
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		return r;
+		goto exit;
 
 	queue_delayed_work(system_wq, &adev->delayed_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
@@ -4193,9 +4202,18 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	if (!adev->in_s0ix) {
 		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 		if (r)
-			return r;
+			goto exit;
 	}
 
+exit:
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_init_data_exchange(adev);
+		amdgpu_virt_release_full_gpu(adev, true);
+	}
+
+	if (r)
+		return r;
+
 	/* Make sure IB tests flushed */
 	flush_delayed_work(&adev->delayed_init_work);
 
@@ -4213,25 +4231,27 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 
 	amdgpu_ras_resume(adev);
 
-	/*
-	 * Most of the connector probing functions try to acquire runtime pm
-	 * refs to ensure that the GPU is powered on when connector polling is
-	 * performed. Since we're calling this from a runtime PM callback,
-	 * trying to acquire rpm refs will cause us to deadlock.
-	 *
-	 * Since we're guaranteed to be holding the rpm lock, it's safe to
-	 * temporarily disable the rpm helpers so this doesn't deadlock us.
-	 */
+	if (adev->mode_info.num_crtc) {
+		/*
+		 * Most of the connector probing functions try to acquire runtime pm
+		 * refs to ensure that the GPU is powered on when connector polling is
+		 * performed. Since we're calling this from a runtime PM callback,
+		 * trying to acquire rpm refs will cause us to deadlock.
+		 *
+		 * Since we're guaranteed to be holding the rpm lock, it's safe to
+		 * temporarily disable the rpm helpers so this doesn't deadlock us.
+		 */
 #ifdef CONFIG_PM
-	dev->dev->power.disable_depth++;
+		dev->dev->power.disable_depth++;
 #endif
-	if (!amdgpu_device_has_dc_support(adev))
-		drm_helper_hpd_irq_event(dev);
-	else
-		drm_kms_helper_hotplug_event(dev);
+		if (!adev->dc_enabled)
+			drm_helper_hpd_irq_event(dev);
+		else
+			drm_kms_helper_hotplug_event(dev);
 #ifdef CONFIG_PM
-	dev->dev->power.disable_depth--;
+		dev->dev->power.disable_depth--;
 #endif
+	}
 	adev->in_suspend = false;
 
 	if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0))
@@ -4580,6 +4600,10 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 	if (amdgpu_gpu_recovery == 0)
 		goto disabled;
 
+	/* Skip soft reset check in fatal error mode */
+	if (!amdgpu_ras_is_poison_mode_supported(adev))
+		return true;
+
 	if (!amdgpu_device_ip_check_soft_reset(adev)) {
 		dev_info(adev->dev,"Timeout, but no hardware hang detected.\n");
 		return false;
@@ -5027,6 +5051,8 @@ static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev)
 		pm_runtime_enable(&(p->dev));
 		pm_runtime_resume(&(p->dev));
 	}
+
+	pci_dev_put(p);
 }
 
 static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
@@ -5065,6 +5091,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 		if (expires < ktime_get_mono_fast_ns()) {
 			dev_warn(adev->dev, "failed to suspend display audio\n");
+			pci_dev_put(p);
 			/* TODO: abort the succeeding gpu reset? */
 			return -ETIMEDOUT;
 		}
@@ -5072,97 +5099,10 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 	pm_runtime_disable(&(p->dev));
 
+	pci_dev_put(p);
 	return 0;
 }
 
-static void amdgpu_device_recheck_guilty_jobs(
-	struct amdgpu_device *adev, struct list_head *device_list_handle,
-	struct amdgpu_reset_context *reset_context)
-{
-	int i, r = 0;
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		int ret = 0;
-		struct drm_sched_job *s_job;
-
-		if (!ring || !ring->sched.thread)
-			continue;
-
-		s_job = list_first_entry_or_null(&ring->sched.pending_list,
-				struct drm_sched_job, list);
-		if (s_job == NULL)
-			continue;
-
-		/* clear job's guilty and depend the folowing step to decide the real one */
-		drm_sched_reset_karma(s_job);
-		drm_sched_resubmit_jobs_ext(&ring->sched, 1);
-
-		if (!s_job->s_fence->parent) {
-			DRM_WARN("Failed to get a HW fence for job!");
-			continue;
-		}
-
-		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
-		if (ret == 0) { /* timeout */
-			DRM_ERROR("Found the real bad job! ring:%s, job_id:%llx\n",
-						ring->sched.name, s_job->id);
-
-
-			amdgpu_fence_driver_isr_toggle(adev, true);
-
-			/* Clear this failed job from fence array */
-			amdgpu_fence_driver_clear_job_fences(ring);
-
-			amdgpu_fence_driver_isr_toggle(adev, false);
-
-			/* Since the job won't signal and we go for
-			 * another resubmit drop this parent pointer
-			 */
-			dma_fence_put(s_job->s_fence->parent);
-			s_job->s_fence->parent = NULL;
-
-			/* set guilty */
-			drm_sched_increase_karma(s_job);
-			amdgpu_reset_prepare_hwcontext(adev, reset_context);
-retry:
-			/* do hw reset */
-			if (amdgpu_sriov_vf(adev)) {
-				amdgpu_virt_fini_data_exchange(adev);
-				r = amdgpu_device_reset_sriov(adev, false);
-				if (r)
-					adev->asic_reset_res = r;
-			} else {
-				clear_bit(AMDGPU_SKIP_HW_RESET,
-					  &reset_context->flags);
-				r = amdgpu_do_asic_reset(device_list_handle,
-							 reset_context);
-				if (r && r == -EAGAIN)
-					goto retry;
-			}
-
-			/*
-			 * add reset counter so that the following
-			 * resubmitted job could flush vmid
-			 */
-			atomic_inc(&adev->gpu_reset_counter);
-			continue;
-		}
-
-		/* got the hw fence, signal finished fence */
-		atomic_dec(ring->sched.score);
-		dma_fence_get(&s_job->s_fence->finished);
-		dma_fence_signal(&s_job->s_fence->finished);
-		dma_fence_put(&s_job->s_fence->finished);
-
-		/* remove node from list and free the job */
-		spin_lock(&ring->sched.job_list_lock);
-		list_del_init(&s_job->list);
-		spin_unlock(&ring->sched.job_list_lock);
-		ring->sched.ops->free_job(s_job);
-	}
-}
-
 static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -5183,7 +5123,6 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
 
 }
 
-
 /**
  * amdgpu_device_gpu_recover - reset the asic and recover scheduler
  *
@@ -5206,7 +5145,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	int i, r = 0;
 	bool need_emergency_restart = false;
 	bool audio_suspended = false;
-	int tmp_vram_lost_counter;
 	bool gpu_reset_for_dev_remove = false;
 
 	gpu_reset_for_dev_remove =
@@ -5352,7 +5290,6 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		amdgpu_device_stop_pending_resets(tmp_adev);
 	}
 
-	tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter));
 	/* Actual ASIC resets if needed.*/
 	/* Host driver will handle XGMI hive reset for SRIOV */
 	if (amdgpu_sriov_vf(adev)) {
@@ -5377,29 +5314,13 @@ skip_hw_reset:
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 
-		/*
-		 * Sometimes a later bad compute job can block a good gfx job as gfx
-		 * and compute ring share internal GC HW mutually. We add an additional
-		 * guilty jobs recheck step to find the real guilty job, it synchronously
-		 * submits and pends for the first job being signaled. If it gets timeout,
-		 * we identify it as a real guilty job.
-		 */
-		if (amdgpu_gpu_recovery == 2 &&
-			!(tmp_vram_lost_counter < atomic_read(&adev->vram_lost_counter)))
-			amdgpu_device_recheck_guilty_jobs(
-				tmp_adev, device_list_handle, reset_context);
-
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
 			if (!ring || !ring->sched.thread)
 				continue;
 
-			/* No point to resubmit jobs if we didn't HW reset*/
-			if (!tmp_adev->asic_reset_res && !job_signaled)
-				drm_sched_resubmit_jobs(&ring->sched);
-
-			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
+			drm_sched_start(&ring->sched, true);
 		}
 
 		if (adev->enable_mes && adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))
@@ -5441,6 +5362,8 @@ skip_sched_resume:
 			amdgpu_device_resume_display_audio(tmp_adev);
 
 		amdgpu_device_unset_mp1_state(tmp_adev);
+
+		amdgpu_ras_set_error_query_ready(tmp_adev, true);
 	}
 
 recover_end:
@@ -5852,8 +5775,6 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 		if (!ring || !ring->sched.thread)
 			continue;
 
-
-		drm_sched_resubmit_jobs(&ring->sched);
 		drm_sched_start(&ring->sched, true);
 	}