Merge tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Intel have enabled DG2 on certain SKUs for laptops, AMD has started
  some new GPU support, msm has user allocated VA controls

  dma-buf:
   - add dma_resv_replace_fences
   - add dma_resv_get_singleton
   - make dma_excl_fence private

  core:
   - EDID parser refactorings
   - switch drivers to drm_mode_copy/duplicate
   - DRM managed mutex initialization

  display-helper:
   - put HDMI, SCDC, HDCP, DSC and DP into new module

  gem:
   - rework fence handling

  ttm:
   - rework bulk move handling
   - add common debugfs for resource managers
   - convert to kvcalloc

  format helpers:
   - support monochrome formats
   - RGB888, RGB565 to XRGB8888 conversions

  fbdev:
   - cfb/sys_imageblit fixes
   - pagelist corruption fix
   - create offb platform device
   - deferred io improvements

  sysfb:
   - Kconfig rework
   - support for VESA mode selection

  bridge:
   - conversions to devm_drm_of_get_bridge
   - conversions to panel_bridge
   - analogix_dp - autosuspend support
   - it66121 - audio support
   - tc358767 - DSI to DPI support
   - icn6211 - PLL/I2C fixes, DT property
   - adv7611 - enable DRM_BRIDGE_OP_HPD
   - anx7625 - fill ELD if no monitor
   - dw_hdmi - add audio support
   - lontium LT9211 support, i.MXMP LDB
   - it6505: Kconfig fix, DPCD set power fix
   - adv7511 - CEC support for ADV7535

  panel:
   - ltk035c5444t, B133UAN01, NV3052C panel support
   - DataImage FG040346DSSWBG04 support
   - st7735r - DT bindings fix
   - ssd130x - fixes

  i915:
   - DG2 laptop PCI-IDs ("motherboard down")
   - Initial RPL-P PCI IDs
   - compute engine ABI
   - DG2 Tile4 support
   - DG2 CCS clear color compression support
   - DG2 render/media compression formats support
   - ATS-M platform info
   - RPL-S PCI IDs added
   - Bump ADL-P DMC version to v2.16
   - Support static DRRS
   - Support multiple eDP/LVDS native mode refresh rates
   - DP HDR support for HSW+
   - Lots of display refactoring + fixes
   - GuC hwconfig support and query
   - sysfs support for multi-tile
   - fdinfo per-client gpu utilisation
   - add geometry subslices query
   - fix prime mmap with LMEM
   - fix vm open count and remove vma refcounts
   - contiguous allocation fixes
   - steered register write support
   - small PCI BAR enablement
   - GuC error capture support
   - sunset igpu legacy mmap support for newer devices
   - GuC version 70.1.1 support

  amdgpu:
   - Initial SoC21 support
   - SMU 13.x enablement
   - SMU 13.0.4 support
   - ttm_eu cleanups
   - USB-C, GPUVM updates
   - TMZ fixes for RV
   - RAS support for VCN
   - PM sysfs code cleanup
   - DC FP rework
   - extend CG/PG flags to 64-bit
   - SI dpm lockdep fix
   - runtime PM fixes

  amdkfd:
   - RAS/SVM fixes
   - TLB flush fixes
   - CRIU GWS support
   - ignore bogus MEC signals more efficiently

  msm:
   - Fourcc modifier for tiled but not compressed layouts
   - Support for userspace allocated IOVA (GPU virtual address)
   - DPU: DSC (Display Stream Compression) support
   - DP: eDP support
   - DP: conversion to use drm_bridge and drm_bridge_connector
   - Merge DPU1 and MDP5 MDSS driver
   - DPU: writeback support

  nouveau:
   - make some structures static
   - make some variables static
   - switch to drm_gem_plane_helper_prepare_fb

  radeon:
   - misc fixes/cleanups

  mxsfb:
   - rework crtc mode setting
   - LCDIF CRC support

  etnaviv:
   - fencing improvements
   - fix address space collisions
   - cleanup MMU reference handling

  gma500:
   - GEM/GTT improvements
   - connector handling fixes

  komeda:
   - switch to plane reset helper

  mediatek:
   - MIPI DSI improvements

  omapdrm:
   - GEM improvements

  qxl:
   - aarch64 support

  vc4:
   - add a CL submission tracepoint
   - HDMI YUV support
   - HDMI/clock improvements
   - drop is_hdmi caching

  virtio:
   - remove restriction of non-zero blob types

  vmwgfx:
   - support for cursormob and cursorbypass 4
   - fence improvements

  tidss:
   - reset DISPC on startup

  solomon:
   - SPI support
   - DT improvements

  sun4i:
   - allwinner D1 support
   - drop is_hdmi caching

  imx:
   - use swap() instead of open-coding
   - use devm_platform_ioremap_resource
   - remove redunant initializations

  ast:
   - Displayport support

  rockchip:
   - Refactor IOMMU initialisation
   - make some structures static
   - replace drm_detect_hdmi_monitor with drm_display_info.is_hdmi
   - support swapped YUV formats,
   - clock improvements
   - rk3568 support
   - VOP2 support

  mediatek:
   - MT8186 support

  tegra:
   - debugabillity improvements"

* tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm: (1740 commits)
  drm/i915/dsi: fix VBT send packet port selection for ICL+
  drm/i915/uc: Fix undefined behavior due to shift overflowing the constant
  drm/i915/reg: fix undefined behavior due to shift overflowing the constant
  drm/i915/gt: Fix use of static in macro mismatch
  drm/i915/audio: fix audio code enable/disable pipe logging
  drm/i915: Fix CFI violation with show_dynamic_id()
  drm/i915: Fix 'mixing different enum types' warnings in intel_display_power.c
  drm/i915/gt: Fix build error without CONFIG_PM
  drm/msm/dpu: handle pm_runtime_get_sync() errors in bind path
  drm/msm/dpu: add DRM_MODE_ROTATE_180 back to supported rotations
  drm/msm: don't free the IRQ if it was not requested
  drm/msm/dpu: limit writeback modes according to max_linewidth
  drm/amd: Don't reset dGPUs if the system is going to s2idle
  drm/amdgpu: Unmap legacy queue when MES is enabled
  drm: msm: fix possible memory leak in mdp5_crtc_cursor_set()
  drm/msm: Fix fb plane offset calculation
  drm/msm/a6xx: Fix refcount leak in a6xx_gpu_init
  drm/msm/dsi: don't powerup at modeset time for parade-ps8640
  drm/rockchip: Change register space names in vop2
  dt-bindings: display: rockchip: make reg-names mandatory for VOP2
  ...

1 files changed, 119 insertions, 28 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 424c22a841f4..035891ec59d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -66,6 +66,8 @@ const char *ras_block_string[] = {
 	"mp1",
 	"fuse",
 	"mca",
+	"vcn",
+	"jpeg",
 };
 
 const char *ras_mca_block_string[] = {
@@ -1513,12 +1515,106 @@ static int amdgpu_ras_fs_fini(struct amdgpu_device *adev)
 /* ras fs end */
 
 /* ih begin */
+
+/* For the hardware that cannot enable bif ring for both ras_controller_irq
+ * and ras_err_evnet_athub_irq ih cookies, the driver has to poll status
+ * register to check whether the interrupt is triggered or not, and properly
+ * ack the interrupt if it is there
+ */
+void amdgpu_ras_interrupt_fatal_error_handler(struct amdgpu_device *adev)
+{
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF))
+		return;
+
+	if (adev->nbio.ras &&
+	    adev->nbio.ras->handle_ras_controller_intr_no_bifring)
+		adev->nbio.ras->handle_ras_controller_intr_no_bifring(adev);
+
+	if (adev->nbio.ras &&
+	    adev->nbio.ras->handle_ras_err_event_athub_intr_no_bifring)
+		adev->nbio.ras->handle_ras_err_event_athub_intr_no_bifring(adev);
+}
+
+static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *obj,
+				struct amdgpu_iv_entry *entry)
+{
+	bool poison_stat = false;
+	struct amdgpu_device *adev = obj->adev;
+	struct ras_err_data err_data = {0, 0, 0, NULL};
+	struct amdgpu_ras_block_object *block_obj =
+		amdgpu_ras_get_ras_block(adev, obj->head.block, 0);
+
+	if (!block_obj || !block_obj->hw_ops)
+		return;
+
+	/* both query_poison_status and handle_poison_consumption are optional,
+	 * but at least one of them should be implemented if we need poison
+	 * consumption handler
+	 */
+	if (block_obj->hw_ops->query_poison_status) {
+		poison_stat = block_obj->hw_ops->query_poison_status(adev);
+		if (!poison_stat) {
+			/* Not poison consumption interrupt, no need to handle it */
+			dev_info(adev->dev, "No RAS poison status in %s poison IH.\n",
+					block_obj->ras_comm.name);
+
+			return;
+		}
+	}
+
+	if (!adev->gmc.xgmi.connected_to_cpu)
+		amdgpu_umc_poison_handler(adev, &err_data, false);
+
+	if (block_obj->hw_ops->handle_poison_consumption)
+		poison_stat = block_obj->hw_ops->handle_poison_consumption(adev);
+
+	/* gpu reset is fallback for failed and default cases */
+	if (poison_stat) {
+		dev_info(adev->dev, "GPU reset for %s RAS poison consumption is issued!\n",
+				block_obj->ras_comm.name);
+		amdgpu_ras_reset_gpu(adev);
+	}
+}
+
+static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj,
+				struct amdgpu_iv_entry *entry)
+{
+	dev_info(obj->adev->dev,
+		"Poison is created, no user action is needed.\n");
+}
+
+static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
+				struct amdgpu_iv_entry *entry)
+{
+	struct ras_ih_data *data = &obj->ih_data;
+	struct ras_err_data err_data = {0, 0, 0, NULL};
+	int ret;
+
+	if (!data->cb)
+		return;
+
+	/* Let IP handle its data, maybe we need get the output
+	 * from the callback to update the error type/count, etc
+	 */
+	ret = data->cb(obj->adev, &err_data, entry);
+	/* ue will trigger an interrupt, and in that case
+	 * we need do a reset to recovery the whole system.
+	 * But leave IP do that recovery, here we just dispatch
+	 * the error.
+	 */
+	if (ret == AMDGPU_RAS_SUCCESS) {
+		/* these counts could be left as 0 if
+		 * some blocks do not count error number
+		 */
+		obj->err_data.ue_count += err_data.ue_count;
+		obj->err_data.ce_count += err_data.ce_count;
+	}
+}
+
 static void amdgpu_ras_interrupt_handler(struct ras_manager *obj)
 {
 	struct ras_ih_data *data = &obj->ih_data;
 	struct amdgpu_iv_entry entry;
-	int ret;
-	struct ras_err_data err_data = {0, 0, 0, NULL};
 
 	while (data->rptr != data->wptr) {
 		rmb();
@@ -1529,30 +1625,17 @@ static void amdgpu_ras_interrupt_handler(struct ras_manager *obj)
 		data->rptr = (data->aligned_element_size +
 				data->rptr) % data->ring_size;
 
-		if (data->cb) {
-			if (amdgpu_ras_is_poison_mode_supported(obj->adev) &&
-			    obj->head.block == AMDGPU_RAS_BLOCK__UMC)
-				dev_info(obj->adev->dev,
-						"Poison is created, no user action is needed.\n");
-			else {
-				/* Let IP handle its data, maybe we need get the output
-				 * from the callback to udpate the error type/count, etc
-				 */
-				memset(&err_data, 0, sizeof(err_data));
-				ret = data->cb(obj->adev, &err_data, &entry);
-				/* ue will trigger an interrupt, and in that case
-				 * we need do a reset to recovery the whole system.
-				 * But leave IP do that recovery, here we just dispatch
-				 * the error.
-				 */
-				if (ret == AMDGPU_RAS_SUCCESS) {
-					/* these counts could be left as 0 if
-					 * some blocks do not count error number
-					 */
-					obj->err_data.ue_count += err_data.ue_count;
-					obj->err_data.ce_count += err_data.ce_count;
-				}
-			}
+		if (amdgpu_ras_is_poison_mode_supported(obj->adev)) {
+			if (obj->head.block == AMDGPU_RAS_BLOCK__UMC)
+				amdgpu_ras_interrupt_poison_creation_handler(obj, &entry);
+			else
+				amdgpu_ras_interrupt_poison_consumption_handler(obj, &entry);
+		} else {
+			if (obj->head.block == AMDGPU_RAS_BLOCK__UMC)
+				amdgpu_ras_interrupt_umc_handler(obj, &entry);
+			else
+				dev_warn(obj->adev->dev,
+					"No RAS interrupt handler for non-UMC block with poison disabled.\n");
 		}
 	}
 }
@@ -1847,7 +1930,6 @@ static int amdgpu_ras_realloc_eh_data_space(struct amdgpu_device *adev,
 	void *bps = kmalloc(align_space * sizeof(*data->bps), GFP_KERNEL);
 
 	if (!bps) {
-		kfree(bps);
 		return -ENOMEM;
 	}
 
@@ -2205,6 +2287,13 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 			dev_info(adev->dev, "SRAM ECC is active.\n");
 			adev->ras_hw_enabled |= ~(1 << AMDGPU_RAS_BLOCK__UMC |
 						    1 << AMDGPU_RAS_BLOCK__DF);
+
+			if (adev->ip_versions[VCN_HWIP][0] == IP_VERSION(2, 6, 0))
+				adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__VCN |
+						1 << AMDGPU_RAS_BLOCK__JPEG);
+			else
+				adev->ras_hw_enabled &= ~(1 << AMDGPU_RAS_BLOCK__VCN |
+						1 << AMDGPU_RAS_BLOCK__JPEG);
 		} else {
 			dev_info(adev->dev, "SRAM ECC is not presented.\n");
 		}
@@ -2436,7 +2525,9 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 		return 0;
 
 	ras_obj = container_of(ras_block, struct amdgpu_ras_block_object, ras_comm);
-	if (ras_obj->ras_cb) {
+	if (ras_obj->ras_cb || (ras_obj->hw_ops &&
+	    (ras_obj->hw_ops->query_poison_status ||
+	    ras_obj->hw_ops->handle_poison_consumption))) {
 		r = amdgpu_ras_interrupt_add_handler(adev, ras_block);
 		if (r)
 			goto cleanup;