Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

1 files changed, 879 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
new file mode 100644
index 000000000000..493982f94649
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -0,0 +1,879 @@
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/list.h>
+#include "amdgpu.h"
+#include "amdgpu_aca.h"
+#include "amdgpu_ras.h"
+
+#define ACA_BANK_HWID(type, hwid, mcatype) [ACA_HWIP_TYPE_##type] = {hwid, mcatype}
+
+typedef int bank_handler_t(struct aca_handle *handle, struct aca_bank *bank, enum aca_error_type type, void *data);
+
+struct aca_banks {
+	int nr_banks;
+	struct list_head list;
+};
+
+struct aca_hwip {
+	int hwid;
+	int mcatype;
+};
+
+static struct aca_hwip aca_hwid_mcatypes[ACA_HWIP_TYPE_COUNT] = {
+	ACA_BANK_HWID(SMU,	0x01,	0x01),
+	ACA_BANK_HWID(PCS_XGMI, 0x50,	0x00),
+	ACA_BANK_HWID(UMC,	0x96,	0x00),
+};
+
+static void aca_banks_init(struct aca_banks *banks)
+{
+	if (!banks)
+		return;
+
+	memset(banks, 0, sizeof(*banks));
+	INIT_LIST_HEAD(&banks->list);
+}
+
+static int aca_banks_add_bank(struct aca_banks *banks, struct aca_bank *bank)
+{
+	struct aca_bank_node *node;
+
+	if (!bank)
+		return -EINVAL;
+
+	node = kvzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	memcpy(&node->bank, bank, sizeof(*bank));
+
+	INIT_LIST_HEAD(&node->node);
+	list_add_tail(&node->node, &banks->list);
+
+	banks->nr_banks++;
+
+	return 0;
+}
+
+static void aca_banks_release(struct aca_banks *banks)
+{
+	struct aca_bank_node *node, *tmp;
+
+	list_for_each_entry_safe(node, tmp, &banks->list, node) {
+		list_del(&node->node);
+		kvfree(node);
+	}
+}
+
+static int aca_smu_get_valid_aca_count(struct amdgpu_device *adev, enum aca_error_type type, u32 *count)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	const struct aca_smu_funcs *smu_funcs = aca->smu_funcs;
+
+	if (!count)
+		return -EINVAL;
+
+	if (!smu_funcs || !smu_funcs->get_valid_aca_count)
+		return -EOPNOTSUPP;
+
+	return smu_funcs->get_valid_aca_count(adev, type, count);
+}
+
+static struct aca_regs_dump {
+	const char *name;
+	int reg_idx;
+} aca_regs[] = {
+	{"CONTROL",		ACA_REG_IDX_CTL},
+	{"STATUS",		ACA_REG_IDX_STATUS},
+	{"ADDR",		ACA_REG_IDX_ADDR},
+	{"MISC",		ACA_REG_IDX_MISC0},
+	{"CONFIG",		ACA_REG_IDX_CONFG},
+	{"IPID",		ACA_REG_IDX_IPID},
+	{"SYND",		ACA_REG_IDX_SYND},
+	{"DESTAT",		ACA_REG_IDX_DESTAT},
+	{"DEADDR",		ACA_REG_IDX_DEADDR},
+	{"CONTROL_MASK",	ACA_REG_IDX_CTL_MASK},
+};
+
+static void aca_smu_bank_dump(struct amdgpu_device *adev, int idx, int total, struct aca_bank *bank)
+{
+	int i;
+
+	dev_info(adev->dev, HW_ERR "Accelerator Check Architecture events logged\n");
+	/* plus 1 for output format, e.g: ACA[08/08]: xxxx */
+	for (i = 0; i < ARRAY_SIZE(aca_regs); i++)
+		dev_info(adev->dev, HW_ERR "ACA[%02d/%02d].%s=0x%016llx\n",
+			 idx + 1, total, aca_regs[i].name, bank->regs[aca_regs[i].reg_idx]);
+}
+
+static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_error_type type,
+				       int start, int count,
+				       struct aca_banks *banks)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	const struct aca_smu_funcs *smu_funcs = aca->smu_funcs;
+	struct aca_bank bank;
+	int i, max_count, ret;
+
+	if (!count)
+		return 0;
+
+	if (!smu_funcs || !smu_funcs->get_valid_aca_bank)
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACA_ERROR_TYPE_UE:
+		max_count = smu_funcs->max_ue_bank_count;
+		break;
+	case ACA_ERROR_TYPE_CE:
+		max_count = smu_funcs->max_ce_bank_count;
+		break;
+	case ACA_ERROR_TYPE_DEFERRED:
+	default:
+		return -EINVAL;
+	}
+
+	if (start + count >= max_count)
+		return -EINVAL;
+
+	count = min_t(int, count, max_count);
+	for (i = 0; i < count; i++) {
+		memset(&bank, 0, sizeof(bank));
+		ret = smu_funcs->get_valid_aca_bank(adev, type, start + i, &bank);
+		if (ret)
+			return ret;
+
+		aca_smu_bank_dump(adev, i, count, &bank);
+
+		ret = aca_banks_add_bank(banks, &bank);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
+{
+
+	struct aca_hwip *hwip;
+	int hwid, mcatype;
+	u64 ipid;
+
+	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
+		return false;
+
+	hwip = &aca_hwid_mcatypes[type];
+	if (!hwip->hwid)
+		return false;
+
+	ipid = bank->regs[ACA_REG_IDX_IPID];
+	hwid = ACA_REG__IPID__HARDWAREID(ipid);
+	mcatype = ACA_REG__IPID__MCATYPE(ipid);
+
+	return hwip->hwid == hwid && hwip->mcatype == mcatype;
+}
+
+static bool aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank, enum aca_error_type type)
+{
+	const struct aca_bank_ops *bank_ops = handle->bank_ops;
+
+	if (!aca_bank_hwip_is_matched(bank, handle->hwip))
+		return false;
+
+	if (!bank_ops->aca_bank_is_valid)
+		return true;
+
+	return bank_ops->aca_bank_is_valid(handle, bank, type, handle->data);
+}
+
+static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_bank_info *info)
+{
+	struct aca_bank_error *bank_error;
+
+	bank_error = kvzalloc(sizeof(*bank_error), GFP_KERNEL);
+	if (!bank_error)
+		return NULL;
+
+	INIT_LIST_HEAD(&bank_error->node);
+	memcpy(&bank_error->info, info, sizeof(*info));
+
+	mutex_lock(&aerr->lock);
+	list_add_tail(&bank_error->node, &aerr->list);
+	mutex_unlock(&aerr->lock);
+
+	return bank_error;
+}
+
+static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca_bank_info *info)
+{
+	struct aca_bank_error *bank_error = NULL;
+	struct aca_bank_info *tmp_info;
+	bool found = false;
+
+	mutex_lock(&aerr->lock);
+	list_for_each_entry(bank_error, &aerr->list, node) {
+		tmp_info = &bank_error->info;
+		if (tmp_info->socket_id == info->socket_id &&
+		    tmp_info->die_id == info->die_id) {
+			found = true;
+			goto out_unlock;
+		}
+	}
+
+out_unlock:
+	mutex_unlock(&aerr->lock);
+
+	return found ? bank_error : NULL;
+}
+
+static void aca_bank_error_remove(struct aca_error *aerr, struct aca_bank_error *bank_error)
+{
+	if (!aerr || !bank_error)
+		return;
+
+	list_del(&bank_error->node);
+	aerr->nr_errors--;
+
+	kvfree(bank_error);
+}
+
+static struct aca_bank_error *get_bank_error(struct aca_error *aerr, struct aca_bank_info *info)
+{
+	struct aca_bank_error *bank_error;
+
+	if (!aerr || !info)
+		return NULL;
+
+	bank_error = find_bank_error(aerr, info);
+	if (bank_error)
+		return bank_error;
+
+	return new_bank_error(aerr, info);
+}
+
+static int aca_log_errors(struct aca_handle *handle, enum aca_error_type type,
+			  struct aca_bank_report *report)
+{
+	struct aca_error_cache *error_cache = &handle->error_cache;
+	struct aca_bank_error *bank_error;
+	struct aca_error *aerr;
+
+	if (!handle || !report)
+		return -EINVAL;
+
+	if (!report->count[type])
+		return 0;
+
+	aerr = &error_cache->errors[type];
+	bank_error = get_bank_error(aerr, &report->info);
+	if (!bank_error)
+		return -ENOMEM;
+
+	bank_error->count[type] += report->count[type];
+
+	return 0;
+}
+
+static int aca_generate_bank_report(struct aca_handle *handle, struct aca_bank *bank,
+				    enum aca_error_type type, struct aca_bank_report *report)
+{
+	const struct aca_bank_ops *bank_ops = handle->bank_ops;
+
+	if (!bank || !report)
+		return -EINVAL;
+
+	if (!bank_ops->aca_bank_generate_report)
+		return -EOPNOTSUPP;
+
+	memset(report, 0, sizeof(*report));
+	return bank_ops->aca_bank_generate_report(handle, bank, type,
+						  report, handle->data);
+}
+
+static int handler_aca_log_bank_error(struct aca_handle *handle, struct aca_bank *bank,
+				      enum aca_error_type type, void *data)
+{
+	struct aca_bank_report report;
+	int ret;
+
+	ret = aca_generate_bank_report(handle, bank, type, &report);
+	if (ret)
+		return ret;
+
+	if (!report.count[type])
+		return 0;
+
+	ret = aca_log_errors(handle, type, &report);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int aca_dispatch_bank(struct aca_handle_manager *mgr, struct aca_bank *bank,
+			     enum aca_error_type type, bank_handler_t handler, void *data)
+{
+	struct aca_handle *handle;
+	int ret;
+
+	if (list_empty(&mgr->list))
+		return 0;
+
+	list_for_each_entry(handle, &mgr->list, node) {
+		if (!aca_bank_is_valid(handle, bank, type))
+			continue;
+
+		ret = handler(handle, bank, type, data);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int aca_dispatch_banks(struct aca_handle_manager *mgr, struct aca_banks *banks,
+			      enum aca_error_type type, bank_handler_t handler, void *data)
+{
+	struct aca_bank_node *node;
+	struct aca_bank *bank;
+	int ret;
+
+	if (!mgr || !banks)
+		return -EINVAL;
+
+	/* pre check to avoid unnecessary operations */
+	if (list_empty(&mgr->list) || list_empty(&banks->list))
+		return 0;
+
+	list_for_each_entry(node, &banks->list, node) {
+		bank = &node->bank;
+
+		ret = aca_dispatch_bank(mgr, bank, type, handler, data);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int aca_banks_update(struct amdgpu_device *adev, enum aca_error_type type,
+			    bank_handler_t handler, void *data)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	struct aca_banks banks;
+	u32 count = 0;
+	int ret;
+
+	if (list_empty(&aca->mgr.list))
+		return 0;
+
+	/* NOTE: pmfw is only support UE and CE */
+	if (type == ACA_ERROR_TYPE_DEFERRED)
+		type = ACA_ERROR_TYPE_CE;
+
+	ret = aca_smu_get_valid_aca_count(adev, type, &count);
+	if (ret)
+		return ret;
+
+	if (!count)
+		return 0;
+
+	aca_banks_init(&banks);
+
+	ret = aca_smu_get_valid_aca_banks(adev, type, 0, count, &banks);
+	if (ret)
+		goto err_release_banks;
+
+	if (list_empty(&banks.list)) {
+		ret = 0;
+		goto err_release_banks;
+	}
+
+	ret = aca_dispatch_banks(&aca->mgr, &banks, type,
+				 handler, data);
+	if (ret)
+		goto err_release_banks;
+
+err_release_banks:
+	aca_banks_release(&banks);
+
+	return ret;
+}
+
+static int aca_log_aca_error_data(struct aca_bank_error *bank_error, enum aca_error_type type, struct ras_err_data *err_data)
+{
+	struct aca_bank_info *info;
+	struct amdgpu_smuio_mcm_config_info mcm_info;
+	u64 count;
+
+	if (type >= ACA_ERROR_TYPE_COUNT)
+		return -EINVAL;
+
+	count = bank_error->count[type];
+	if (!count)
+		return 0;
+
+	info = &bank_error->info;
+	mcm_info.die_id = info->die_id;
+	mcm_info.socket_id = info->socket_id;
+
+	switch (type) {
+	case ACA_ERROR_TYPE_UE:
+		amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, NULL, count);
+		break;
+	case ACA_ERROR_TYPE_CE:
+		amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, NULL, count);
+		break;
+	case ACA_ERROR_TYPE_DEFERRED:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int aca_log_aca_error(struct aca_handle *handle, enum aca_error_type type, struct ras_err_data *err_data)
+{
+	struct aca_error_cache *error_cache = &handle->error_cache;
+	struct aca_error *aerr = &error_cache->errors[type];
+	struct aca_bank_error *bank_error, *tmp;
+
+	mutex_lock(&aerr->lock);
+
+	if (list_empty(&aerr->list))
+		goto out_unlock;
+
+	list_for_each_entry_safe(bank_error, tmp, &aerr->list, node) {
+		aca_log_aca_error_data(bank_error, type, err_data);
+		aca_bank_error_remove(aerr, bank_error);
+	}
+
+out_unlock:
+	mutex_unlock(&aerr->lock);
+
+	return 0;
+}
+
+static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *handle, enum aca_error_type type,
+				struct ras_err_data *err_data)
+{
+	int ret;
+
+	/* udpate aca bank to aca source error_cache first */
+	ret = aca_banks_update(adev, type, handler_aca_log_bank_error, NULL);
+	if (ret)
+		return ret;
+
+	return aca_log_aca_error(handle, type, err_data);
+}
+
+static bool aca_handle_is_valid(struct aca_handle *handle)
+{
+	if (!handle->mask || !list_empty(&handle->node))
+		return false;
+
+	return true;
+}
+
+int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *handle,
+			      enum aca_error_type type, void *data)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)data;
+
+	if (!handle || !err_data)
+		return -EINVAL;
+
+	if (aca_handle_is_valid(handle))
+		return -EOPNOTSUPP;
+
+	if (!(BIT(type) & handle->mask))
+		return  0;
+
+	return __aca_get_error_data(adev, handle, type, err_data);
+}
+
+static void aca_error_init(struct aca_error *aerr, enum aca_error_type type)
+{
+	mutex_init(&aerr->lock);
+	INIT_LIST_HEAD(&aerr->list);
+	aerr->type = type;
+	aerr->nr_errors = 0;
+}
+
+static void aca_init_error_cache(struct aca_handle *handle)
+{
+	struct aca_error_cache *error_cache = &handle->error_cache;
+	int type;
+
+	for (type = ACA_ERROR_TYPE_UE; type < ACA_ERROR_TYPE_COUNT; type++)
+		aca_error_init(&error_cache->errors[type], type);
+}
+
+static void aca_error_fini(struct aca_error *aerr)
+{
+	struct aca_bank_error *bank_error, *tmp;
+
+	mutex_lock(&aerr->lock);
+	list_for_each_entry_safe(bank_error, tmp, &aerr->list, node)
+		aca_bank_error_remove(aerr, bank_error);
+
+	mutex_destroy(&aerr->lock);
+}
+
+static void aca_fini_error_cache(struct aca_handle *handle)
+{
+	struct aca_error_cache *error_cache = &handle->error_cache;
+	int type;
+
+	for (type = ACA_ERROR_TYPE_UE; type < ACA_ERROR_TYPE_COUNT; type++)
+		aca_error_fini(&error_cache->errors[type]);
+}
+
+static int add_aca_handle(struct amdgpu_device *adev, struct aca_handle_manager *mgr, struct aca_handle *handle,
+			  const char *name, const struct aca_info *ras_info, void *data)
+{
+	memset(handle, 0, sizeof(*handle));
+
+	handle->adev = adev;
+	handle->mgr = mgr;
+	handle->name = name;
+	handle->hwip = ras_info->hwip;
+	handle->mask = ras_info->mask;
+	handle->bank_ops = ras_info->bank_ops;
+	handle->data = data;
+	aca_init_error_cache(handle);
+
+	INIT_LIST_HEAD(&handle->node);
+	list_add_tail(&handle->node, &mgr->list);
+	mgr->nr_handles++;
+
+	return 0;
+}
+
+static ssize_t aca_sysfs_read(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct aca_handle *handle = container_of(attr, struct aca_handle, aca_attr);
+
+	/* NOTE: the aca cache will be auto cleared once read,
+	 * So the driver should unify the query entry point, forward request to ras query interface directly */
+	return amdgpu_ras_aca_sysfs_read(dev, attr, handle, buf, handle->data);
+}
+
+static int add_aca_sysfs(struct amdgpu_device *adev, struct aca_handle *handle)
+{
+	struct device_attribute *aca_attr = &handle->aca_attr;
+
+	snprintf(handle->attr_name, sizeof(handle->attr_name) - 1, "aca_%s", handle->name);
+	aca_attr->show = aca_sysfs_read;
+	aca_attr->attr.name = handle->attr_name;
+	aca_attr->attr.mode = S_IRUGO;
+	sysfs_attr_init(&aca_attr->attr);
+
+	return sysfs_add_file_to_group(&adev->dev->kobj,
+				       &aca_attr->attr,
+				       "ras");
+}
+
+int amdgpu_aca_add_handle(struct amdgpu_device *adev, struct aca_handle *handle,
+			  const char *name, const struct aca_info *ras_info, void *data)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	int ret;
+
+	if (!amdgpu_aca_is_enabled(adev))
+		return 0;
+
+	ret = add_aca_handle(adev, &aca->mgr, handle, name, ras_info, data);
+	if (ret)
+		return ret;
+
+	return add_aca_sysfs(adev, handle);
+}
+
+static void remove_aca_handle(struct aca_handle *handle)
+{
+	struct aca_handle_manager *mgr = handle->mgr;
+
+	aca_fini_error_cache(handle);
+	list_del(&handle->node);
+	mgr->nr_handles--;
+}
+
+static void remove_aca_sysfs(struct aca_handle *handle)
+{
+	struct amdgpu_device *adev = handle->adev;
+	struct device_attribute *aca_attr = &handle->aca_attr;
+
+	if (adev->dev->kobj.sd)
+		sysfs_remove_file_from_group(&adev->dev->kobj,
+					     &aca_attr->attr,
+					     "ras");
+}
+
+void amdgpu_aca_remove_handle(struct aca_handle *handle)
+{
+	if (!handle || list_empty(&handle->node))
+		return;
+
+	remove_aca_sysfs(handle);
+	remove_aca_handle(handle);
+}
+
+static int aca_manager_init(struct aca_handle_manager *mgr)
+{
+	INIT_LIST_HEAD(&mgr->list);
+	mgr->nr_handles = 0;
+
+	return 0;
+}
+
+static void aca_manager_fini(struct aca_handle_manager *mgr)
+{
+	struct aca_handle *handle, *tmp;
+
+	list_for_each_entry_safe(handle, tmp, &mgr->list, node)
+		amdgpu_aca_remove_handle(handle);
+}
+
+bool amdgpu_aca_is_enabled(struct amdgpu_device *adev)
+{
+	return adev->aca.is_enabled;
+}
+
+int amdgpu_aca_init(struct amdgpu_device *adev)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	int ret;
+
+	ret = aca_manager_init(&aca->mgr);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void amdgpu_aca_fini(struct amdgpu_device *adev)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+
+	aca_manager_fini(&aca->mgr);
+}
+
+int amdgpu_aca_reset(struct amdgpu_device *adev)
+{
+	amdgpu_aca_fini(adev);
+
+	return amdgpu_aca_init(adev);
+}
+
+void amdgpu_aca_set_smu_funcs(struct amdgpu_device *adev, const struct aca_smu_funcs *smu_funcs)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+
+	WARN_ON(aca->smu_funcs);
+	aca->smu_funcs = smu_funcs;
+}
+
+int aca_bank_info_decode(struct aca_bank *bank, struct aca_bank_info *info)
+{
+	u64 ipid;
+	u32 instidhi, instidlo;
+
+	if (!bank || !info)
+		return -EINVAL;
+
+	ipid = bank->regs[ACA_REG_IDX_IPID];
+	info->hwid = ACA_REG__IPID__HARDWAREID(ipid);
+	info->mcatype = ACA_REG__IPID__MCATYPE(ipid);
+	/*
+	 * Unfied DieID Format: SAASS. A:AID, S:Socket.
+	 * Unfied DieID[4:4] = InstanceId[0:0]
+	 * Unfied DieID[0:3] = InstanceIdHi[0:3]
+	 */
+	instidhi = ACA_REG__IPID__INSTANCEIDHI(ipid);
+	instidlo = ACA_REG__IPID__INSTANCEIDLO(ipid);
+	info->die_id = ((instidhi >> 2) & 0x03);
+	info->socket_id = ((instidlo & 0x1) << 2) | (instidhi & 0x03);
+
+	return 0;
+}
+
+static int aca_bank_get_error_code(struct amdgpu_device *adev, struct aca_bank *bank)
+{
+	int error_code;
+
+	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
+	case IP_VERSION(13, 0, 6):
+		if (!(adev->flags & AMD_IS_APU) && adev->pm.fw_version >= 0x00555600) {
+			error_code = ACA_REG__SYND__ERRORINFORMATION(bank->regs[ACA_REG_IDX_SYND]);
+			return error_code & 0xff;
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* NOTE: the true error code is encoded in status.errorcode[0:7] */
+	error_code = ACA_REG__STATUS__ERRORCODE(bank->regs[ACA_REG_IDX_STATUS]);
+
+	return error_code & 0xff;
+}
+
+int aca_bank_check_error_codes(struct amdgpu_device *adev, struct aca_bank *bank, int *err_codes, int size)
+{
+	int i, error_code;
+
+	if (!bank || !err_codes)
+		return -EINVAL;
+
+	error_code = aca_bank_get_error_code(adev, bank);
+	for (i = 0; i < size; i++) {
+		if (err_codes[i] == error_code)
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+int amdgpu_aca_smu_set_debug_mode(struct amdgpu_device *adev, bool en)
+{
+	struct amdgpu_aca *aca = &adev->aca;
+	const struct aca_smu_funcs *smu_funcs = aca->smu_funcs;
+
+	if (!smu_funcs || !smu_funcs->set_debug_mode)
+		return -EOPNOTSUPP;
+
+	return smu_funcs->set_debug_mode(adev, en);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+static int amdgpu_aca_smu_debug_mode_set(void *data, u64 val)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)data;
+	int ret;
+
+	ret = amdgpu_ras_set_aca_debug_mode(adev, val ? true : false);
+	if (ret)
+		return ret;
+
+	dev_info(adev->dev, "amdgpu set smu aca debug mode %s success\n", val ? "on" : "off");
+
+	return 0;
+}
+
+static void aca_dump_entry(struct seq_file *m, struct aca_bank *bank, enum aca_error_type type, int idx)
+{
+	struct aca_bank_info info;
+	int i, ret;
+
+	ret = aca_bank_info_decode(bank, &info);
+	if (ret)
+		return;
+
+	seq_printf(m, "aca entry[%d].type: %s\n", idx, type ==  ACA_ERROR_TYPE_UE ? "UE" : "CE");
+	seq_printf(m, "aca entry[%d].info: socketid:%d aid:%d hwid:0x%03x mcatype:0x%04x\n",
+		   idx, info.socket_id, info.die_id, info.hwid, info.mcatype);
+
+	for (i = 0; i < ARRAY_SIZE(aca_regs); i++)
+		seq_printf(m, "aca entry[%d].regs[%d]: 0x%016llx\n", idx, aca_regs[i].reg_idx, bank->regs[aca_regs[i].reg_idx]);
+}
+
+struct aca_dump_context {
+	struct seq_file *m;
+	int idx;
+};
+
+static int handler_aca_bank_dump(struct aca_handle *handle, struct aca_bank *bank,
+				 enum aca_error_type type, void *data)
+{
+	struct aca_dump_context *ctx = (struct aca_dump_context *)data;
+
+	aca_dump_entry(ctx->m, bank, type, ctx->idx++);
+
+	return handler_aca_log_bank_error(handle, bank, type, NULL);
+}
+
+static int aca_dump_show(struct seq_file *m, enum aca_error_type type)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)m->private;
+	struct aca_dump_context context = {
+		.m = m,
+		.idx = 0,
+	};
+
+	return aca_banks_update(adev, type, handler_aca_bank_dump, (void *)&context);
+}
+
+static int aca_dump_ce_show(struct seq_file *m, void *unused)
+{
+	return aca_dump_show(m, ACA_ERROR_TYPE_CE);
+}
+
+static int aca_dump_ce_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aca_dump_ce_show, inode->i_private);
+}
+
+static const struct file_operations aca_ce_dump_debug_fops = {
+	.owner = THIS_MODULE,
+	.open = aca_dump_ce_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int aca_dump_ue_show(struct seq_file *m, void *unused)
+{
+	return aca_dump_show(m, ACA_ERROR_TYPE_UE);
+}
+
+static int aca_dump_ue_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aca_dump_ue_show, inode->i_private);
+}
+
+static const struct file_operations aca_ue_dump_debug_fops = {
+	.owner = THIS_MODULE,
+	.open = aca_dump_ue_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+DEFINE_DEBUGFS_ATTRIBUTE(aca_debug_mode_fops, NULL, amdgpu_aca_smu_debug_mode_set, "%llu\n");
+#endif
+
+void amdgpu_aca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root)
+{
+#if defined(CONFIG_DEBUG_FS)
+	if (!root || adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 6))
+		return;
+
+	debugfs_create_file("aca_debug_mode", 0200, root, adev, &aca_debug_mode_fops);
+	debugfs_create_file("aca_ue_dump", 0400, root, adev, &aca_ue_dump_debug_fops);
+	debugfs_create_file("aca_ce_dump", 0400, root, adev, &aca_ce_dump_debug_fops);
+#endif
+}