Merge tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There's a lot of stuff in here, amd, i915 and xe have new platform
  work, lots of core rework around EDID handling, some new COMPILE_TEST
  options, maintainer changes and a lots of other stuff. Summary:

  core:
   - deprecate DRM data and return 0 date
   - connector: Create a set of helpers to help with HDMI support
   - Remove driver owner assignments
   - Allow more drivers to compile with COMPILE_TEST
   - Conversions to drm_edid
   - Sprinkle MODULE_DESCRIPTIONS everywhere they are missing
   - Remove drm_mm_replace_node
   - print: Add a drm prefix to warn level messages too, remove
            ___drm_dbg, consolidate prefix handling
   - New monochrome TV mode variant

  ttm:
   - improve number of page faults on some platforms
   - fix test builds under PREEMPT_RT
   - more test coverage

  ci:
   - Require a more recent version of mesa
   - improve farm setup and test generation

  dma-buf:
   - warn if reserving 0 fence slots
   - internal API heap enhancements

  fbdev:
   - Create memory manager optimized fbdev emulation

  panic:
   - Allow to select fonts
   - improve drm_fb_dma_get_scanout_buffer
   - Allow to dump kmsg to the screen

  bridge:
   - Remove redundant checks on bridge->encoder
   - Remove drm_bridge_chain_mode_fixup
   - bridge-connector: Plumb in the new HDMI helper
   - analogix_dp: Various improvements, handle AUX transfers timeout
   - samsung-dsim: Fix timings calculation
   - tc358767: Plenty of small fixes, fix no connector attach, fix
               clocks
   - sii902x: state validation improvements

  panels:
   - Switch panels from register table initialization to proper code
   - Now that the panel code tracks the panel state, remove every ad-hoc
     implementation in the panel drivers
   - More cleanup of prepare / enable state tracking in drivers
   - edp: Drop legacy panel compatibles
   - simple-bridge: Switch to devm_drm_bridge_add
   - New panels: Lincoln Tech Sol LCD185-101CT, Microtips Technology
                 13-101HIEBCAF0-C, Microtips Technology MF-103HIEB0GA0,
                 BOE nv110wum-l60, IVO t109nw41, WL-355608-A8, PrimeView
                 PM070WL4, Lincoln Technologies LCD197, Ortustech
                 COM35H3P70ULC, AUO G104STN01, K&d kd101ne3-40ti

  amdgpu:
   - DCN 4.0.x support
   - GC 12.0 support
   - GMC 12.0 support
   - SDMA 7.0 support
   - MES12 support
   - MMHUB 4.1 support
   - GFX12 modifier and DCC support
   - lots of IP fixes/updates

  amdkfd:
   - Contiguous VRAM allocations
   - GC 12.0 support
   - SDMA 7.0 support
   - SR-IOV fixes
   - KFD GFX ALU exceptions

  i915:
   - Battlemage Xe2 HPD display enablement
   - Panel Replay enabling
   - DP AUX-less ALPM/LOBF
   - Enable link training failure fallback for DP MST links
   - CMRR (Content Match Refresh Rate) enabling
   - Increase ADL-S/ADL-P/DG2+ max TMDS bitrate to 6 Gbps
   - Enable eDP AUX based HDR backlight
   - Support replaying GPU hangs with captured context image
   - Automate CCS Mode setting during engine resets
   - lots of refactoring
   - Support replaying GPU hangs with captured context image
   - Increase FLR timeout from 3s to 9s
   - Enable w/a 16021333562 for DG2, MTL and ARL [guc]

  xe:
   - update MAINATINERS
   - New uapi adding OA functionality to Xe
   - expose l3 bank mask
   - fix display detect on ADL-N
   - runtime PM Fixes
   - Fix silent backmerge issues
   - More prep for SR-IOV
   - HWmon additions
   - per client usage info
   - Rework GPU page fault handling
   - Drop EXEC_QUEUE_FLAG_BANNED
   - Add BMG PCI IDs
   - Scheduler fixes and improvements
   - Rename xe_exec_queue::compute to xe_exec_queue::lr
   - Use ttm_uncached for BO with NEEDS_UC flag
   - Rename xe perf layer as xe observation layer
   - lots of refactoring

  radeon:
   - Backlight workaround for iMac
   - Silence UBSAN flex array warnings

  msm:
   - Validate registers XML description against schema in CI
   - core/dpu: SM7150 support
   - mdp5: Add support for MSM8937
   - gpu: Add param for userspace to know if raytracing is supported
   - gpu: X185 support (aka gpu in X1 laptop chips)
   - gpu: a505 support

  ivpu:
   - hardware scheduler support
   - profiling support
   - improvements to the platform support layer
   - firmware handling improvements
   - clocks/power mgmt improvements
   - scheduler/logging improvements

  habanalabs:
   - Gradual sleep in polling memory macro
   - Reduce Gaudi2 MSI-X interrupt count to 128
   - Add Gaudi2-D revision support
   - Add timestamp to CPLD info
   - Gaudi2: Assume hard-reset by firmware upon MC SEI severe error
   - Align Gaudi2 interrupt names
   - Check for errors after preboot is ready
   - Change habanalabs maintainer and git repo path

  mgag200:
   - refactoring and improvements
   - Add BMC output
   - enable polling

  nouveau:
   - add registry command line

  v3d:
   - perf counters improvements

  zynqmp:
   - irq and debugfs improvements

  atmel-hlcdc:
   - Support XLCDC in sam9x7

  mipi-dbi:
   - Remove mipi_dbi_machine_little_endian
   - make SPI bits per word configurable
   - support RGB888
   - allow pixel formats to be specified in the DT

  sun4i:
   - Rework the blender setup for DE2

  panfrost:
   - Enable MT8188 support

  vc4:
   - Monochrome TV support

  exynos:
   - fix fallback mode regression
   - fix memory leak
   - Use drm_edid_duplicate() instead of kmemdup()

  etnaviv:
   - fix i.MX8MP NPU clock gating
   - workaround FE register cdc issues on some cores
   - fix DMA sync handling for cached buffers
   - fix job timeout handling
   - keep TS enabled on MMUv2 cores for improved performance

  mediatek:
   - Convert to platform remove callback returning void-
   - Drop chain_mode_fixup call in mode_valid()
   - Fixes the errors of MediaTek display driver found by IGT
   - Add display support for the MT8365-EVK board
   - Fix bit depth overwritten for mtk_ovl_set bit_depth()
   - Fix possible_crtcs calculation
   - Fix spurious kfree()

  ast:
   - refactor mode setting code

  stm:
   - Add LVDS support
   - DSI PHY updates"

* tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel: (2501 commits)
  drm/amdgpu/mes12: add missing opcode string
  drm/amdgpu/mes11: update opcode strings
  Revert "drm/amd/display: Reset freesync config before update new state"
  drm/omap: Restrict compile testing to PAGE_SIZE less than 64KB
  drm/xe: Drop trace_xe_hw_fence_free
  drm/xe/uapi: Rename xe perf layer as xe observation layer
  drm/amdgpu: remove exp hw support check for gfx12
  drm/amdgpu: timely save bad pages to eeprom after gpu ras reset is completed
  drm/amdgpu: flush all cached ras bad pages to eeprom
  drm/amdgpu: select compute ME engines dynamically
  drm/amd/display: Allow display DCC for DCN401
  drm/amdgpu: select compute ME engines dynamically
  drm/amdgpu/job: Replace DRM_INFO/ERROR logging
  drm/amdgpu: select compute ME engines dynamically
  drm/amd/pm: Ignore initial value in smu response register
  drm/amdgpu: Initialize VF partition mode
  drm/amd/amdgpu: fix SDMA IRQ client ID <-> req mapping
  MAINTAINERS: fix Xinhui's name
  MAINTAINERS: update powerplay and swsmu
  drm/qxl: Pin buffer objects for internal mappings
  ...

1 files changed, 239 insertions, 144 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index 0734490347db..2542bd7aa7c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -153,7 +153,7 @@ int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set)
+static void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set)
 {
 	if (!mca_set)
 		return;
@@ -162,7 +162,7 @@ void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set)
 	INIT_LIST_HEAD(&mca_set->list);
 }
 
-int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry)
+static int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry)
 {
 	struct mca_bank_node *node;
 
@@ -183,14 +183,36 @@ int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_
 	return 0;
 }
 
-void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set)
+static int amdgpu_mca_bank_set_merge(struct mca_bank_set *mca_set, struct mca_bank_set *new)
+{
+	struct mca_bank_node *node;
+
+	list_for_each_entry(node, &new->list, node)
+		amdgpu_mca_bank_set_add_entry(mca_set, &node->entry);
+
+	return 0;
+}
+
+static void amdgpu_mca_bank_set_remove_node(struct mca_bank_set *mca_set, struct mca_bank_node *node)
+{
+	if (!node)
+		return;
+
+	list_del(&node->node);
+	kvfree(node);
+
+	mca_set->nr_entries--;
+}
+
+static void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set)
 {
 	struct mca_bank_node *node, *tmp;
 
-	list_for_each_entry_safe(node, tmp, &mca_set->list, node) {
-		list_del(&node->node);
-		kvfree(node);
-	}
+	if (list_empty(&mca_set->list))
+		return;
+
+	list_for_each_entry_safe(node, tmp, &mca_set->list, node)
+		amdgpu_mca_bank_set_remove_node(mca_set, node);
 }
 
 void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs)
@@ -200,6 +222,45 @@ void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_m
 	mca->mca_funcs = mca_funcs;
 }
 
+int amdgpu_mca_init(struct amdgpu_device *adev)
+{
+	struct amdgpu_mca *mca = &adev->mca;
+	struct mca_bank_cache *mca_cache;
+	int i;
+
+	atomic_set(&mca->ue_update_flag, 0);
+
+	for (i = 0; i < ARRAY_SIZE(mca->mca_caches); i++) {
+		mca_cache = &mca->mca_caches[i];
+		mutex_init(&mca_cache->lock);
+		amdgpu_mca_bank_set_init(&mca_cache->mca_set);
+	}
+
+	return 0;
+}
+
+void amdgpu_mca_fini(struct amdgpu_device *adev)
+{
+	struct amdgpu_mca *mca = &adev->mca;
+	struct mca_bank_cache *mca_cache;
+	int i;
+
+	atomic_set(&mca->ue_update_flag, 0);
+
+	for (i = 0; i < ARRAY_SIZE(mca->mca_caches); i++) {
+		mca_cache = &mca->mca_caches[i];
+		amdgpu_mca_bank_set_release(&mca_cache->mca_set);
+		mutex_destroy(&mca_cache->lock);
+	}
+}
+
+int amdgpu_mca_reset(struct amdgpu_device *adev)
+{
+	amdgpu_mca_fini(adev);
+
+	return amdgpu_mca_init(adev);
+}
+
 int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 {
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
@@ -213,7 +274,7 @@ int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry,
 					 struct ras_query_context *qctx)
 {
-	u64 event_id = qctx->event_id;
+	u64 event_id = qctx ? qctx->evid.event_id : RAS_EVENT_INVALID_ID;
 
 	RAS_EVENT_LOG(adev, event_id, HW_ERR "Accelerator Check Architecture events logged\n");
 	RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].STATUS=0x%016llx\n",
@@ -228,175 +289,213 @@ static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, st
 		      idx, entry->regs[MCA_REG_IDX_SYND]);
 }
 
-int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
-				 struct ras_err_data *err_data, struct ras_query_context *qctx)
+static int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count)
 {
-	struct amdgpu_smuio_mcm_config_info mcm_info;
-	struct ras_err_addr err_addr = {0};
-	struct mca_bank_set mca_set;
-	struct mca_bank_node *node;
-	struct mca_bank_entry *entry;
-	uint32_t count;
-	int ret, i = 0;
-
-	amdgpu_mca_bank_set_init(&mca_set);
-
-	ret = amdgpu_mca_smu_get_mca_set(adev, blk, type, &mca_set);
-	if (ret)
-		goto out_mca_release;
-
-	list_for_each_entry(node, &mca_set.list, node) {
-		entry = &node->entry;
+	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
 
-		amdgpu_mca_smu_mca_bank_dump(adev, i++, entry, qctx);
+	if (!count)
+		return -EINVAL;
 
-		count = 0;
-		ret = amdgpu_mca_smu_parse_mca_error_count(adev, blk, type, entry, &count);
-		if (ret)
-			goto out_mca_release;
+	if (mca_funcs && mca_funcs->mca_get_valid_mca_count)
+		return mca_funcs->mca_get_valid_mca_count(adev, type, count);
 
-		if (!count)
-			continue;
+	return -EOPNOTSUPP;
+}
 
-		mcm_info.socket_id = entry->info.socket_id;
-		mcm_info.die_id = entry->info.aid;
+static int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
+					int idx, struct mca_bank_entry *entry)
+{
+	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+	int count;
 
-		if (blk == AMDGPU_RAS_BLOCK__UMC) {
-			err_addr.err_status = entry->regs[MCA_REG_IDX_STATUS];
-			err_addr.err_ipid = entry->regs[MCA_REG_IDX_IPID];
-			err_addr.err_addr = entry->regs[MCA_REG_IDX_ADDR];
-		}
+	if (!mca_funcs || !mca_funcs->mca_get_mca_entry)
+		return -EOPNOTSUPP;
 
-		if (type == AMDGPU_MCA_ERROR_TYPE_UE)
-			amdgpu_ras_error_statistic_ue_count(err_data,
-				&mcm_info, &err_addr, (uint64_t)count);
-		else {
-			if (amdgpu_mca_is_deferred_error(adev, entry->regs[MCA_REG_IDX_STATUS]))
-				amdgpu_ras_error_statistic_de_count(err_data,
-					&mcm_info, &err_addr, (uint64_t)count);
-			else
-				amdgpu_ras_error_statistic_ce_count(err_data,
-					&mcm_info, &err_addr, (uint64_t)count);
-		}
+	switch (type) {
+	case AMDGPU_MCA_ERROR_TYPE_UE:
+		count = mca_funcs->max_ue_count;
+		break;
+	case AMDGPU_MCA_ERROR_TYPE_CE:
+		count = mca_funcs->max_ce_count;
+		break;
+	default:
+		return -EINVAL;
 	}
 
-out_mca_release:
-	amdgpu_mca_bank_set_release(&mca_set);
+	if (idx >= count)
+		return -EINVAL;
 
-	return ret;
+	return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
 }
 
-
-int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count)
+static bool amdgpu_mca_bank_should_update(struct amdgpu_device *adev, enum amdgpu_mca_error_type type)
 {
-	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
-
-	if (!count)
-		return -EINVAL;
-
-	if (mca_funcs && mca_funcs->mca_get_valid_mca_count)
-		return mca_funcs->mca_get_valid_mca_count(adev, type, count);
+	struct amdgpu_mca *mca = &adev->mca;
+	bool ret = true;
+
+	/*
+	 * Because the UE Valid MCA count will only be cleared after reset,
+	 * in order to avoid repeated counting of the error count,
+	 * the aca bank is only updated once during the gpu recovery stage.
+	 */
+	if (type == AMDGPU_MCA_ERROR_TYPE_UE) {
+		if (amdgpu_ras_intr_triggered())
+			ret = atomic_cmpxchg(&mca->ue_update_flag, 0, 1) == 0;
+		else
+			atomic_set(&mca->ue_update_flag, 0);
+	}
 
-	return -EOPNOTSUPP;
+	return ret;
 }
 
-int amdgpu_mca_smu_get_mca_set_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-					    enum amdgpu_mca_error_type type, uint32_t *total)
+static int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set,
+				      struct ras_query_context *qctx)
 {
-	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
-	struct mca_bank_set mca_set;
-	struct mca_bank_node *node;
-	struct mca_bank_entry *entry;
-	uint32_t count;
+	struct mca_bank_entry entry;
+	uint32_t count = 0, i;
 	int ret;
 
-	if (!total)
+	if (!mca_set)
 		return -EINVAL;
 
-	if (!mca_funcs)
-		return -EOPNOTSUPP;
-
-	if (!mca_funcs->mca_get_ras_mca_set || !mca_funcs->mca_get_valid_mca_count)
-		return -EOPNOTSUPP;
-
-	amdgpu_mca_bank_set_init(&mca_set);
+	if (!amdgpu_mca_bank_should_update(adev, type))
+		return 0;
 
-	ret = mca_funcs->mca_get_ras_mca_set(adev, blk, type, &mca_set);
+	ret = amdgpu_mca_smu_get_valid_mca_count(adev, type, &count);
 	if (ret)
-		goto err_mca_set_release;
-
-	*total = 0;
-	list_for_each_entry(node, &mca_set.list, node) {
-		entry = &node->entry;
+		return ret;
 
-		count = 0;
-		ret = mca_funcs->mca_parse_mca_error_count(adev, blk, type, entry, &count);
+	for (i = 0; i < count; i++) {
+		memset(&entry, 0, sizeof(entry));
+		ret = amdgpu_mca_smu_get_mca_entry(adev, type, i, &entry);
 		if (ret)
-			goto err_mca_set_release;
+			return ret;
 
-		*total += count;
-	}
+		amdgpu_mca_bank_set_add_entry(mca_set, &entry);
 
-err_mca_set_release:
-	amdgpu_mca_bank_set_release(&mca_set);
+		amdgpu_mca_smu_mca_bank_dump(adev, i, &entry, qctx);
+	}
 
-	return ret;
+	return 0;
 }
 
-int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-					 enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
+static int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+						enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
 {
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+
 	if (!count || !entry)
 		return -EINVAL;
 
 	if (!mca_funcs || !mca_funcs->mca_parse_mca_error_count)
 		return -EOPNOTSUPP;
 
-
 	return mca_funcs->mca_parse_mca_error_count(adev, blk, type, entry, count);
 }
 
-int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-			       enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set)
+static int amdgpu_mca_dispatch_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
+				       struct mca_bank_set *mca_set, struct ras_err_data *err_data)
 {
-	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+	struct ras_err_addr err_addr;
+	struct amdgpu_smuio_mcm_config_info mcm_info;
+	struct mca_bank_node *node, *tmp;
+	struct mca_bank_entry *entry;
+	uint32_t count;
+	int ret;
 
 	if (!mca_set)
 		return -EINVAL;
 
-	if (!mca_funcs || !mca_funcs->mca_get_ras_mca_set)
-		return -EOPNOTSUPP;
+	if (!mca_set->nr_entries)
+		return 0;
 
-	WARN_ON(!list_empty(&mca_set->list));
+	list_for_each_entry_safe(node, tmp, &mca_set->list, node) {
+		entry = &node->entry;
+
+		count = 0;
+		ret = amdgpu_mca_smu_parse_mca_error_count(adev, blk, type, entry, &count);
+		if (ret && ret != -EOPNOTSUPP)
+			return ret;
+
+		if (!count)
+			continue;
+
+		memset(&mcm_info, 0, sizeof(mcm_info));
+		memset(&err_addr, 0, sizeof(err_addr));
+
+		mcm_info.socket_id = entry->info.socket_id;
+		mcm_info.die_id = entry->info.aid;
+
+		if (blk == AMDGPU_RAS_BLOCK__UMC) {
+			err_addr.err_status = entry->regs[MCA_REG_IDX_STATUS];
+			err_addr.err_ipid = entry->regs[MCA_REG_IDX_IPID];
+			err_addr.err_addr = entry->regs[MCA_REG_IDX_ADDR];
+		}
+
+		if (type == AMDGPU_MCA_ERROR_TYPE_UE) {
+			amdgpu_ras_error_statistic_ue_count(err_data,
+							    &mcm_info, &err_addr, (uint64_t)count);
+		} else {
+			if (amdgpu_mca_is_deferred_error(adev, entry->regs[MCA_REG_IDX_STATUS]))
+				amdgpu_ras_error_statistic_de_count(err_data,
+								    &mcm_info, &err_addr, (uint64_t)count);
+			else
+				amdgpu_ras_error_statistic_ce_count(err_data,
+								    &mcm_info, &err_addr, (uint64_t)count);
+		}
 
-	return mca_funcs->mca_get_ras_mca_set(adev, blk, type, mca_set);
+		amdgpu_mca_bank_set_remove_node(mca_set, node);
+	}
+
+	return 0;
 }
 
-int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
-				 int idx, struct mca_bank_entry *entry)
+static int amdgpu_mca_add_mca_set_to_cache(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, struct mca_bank_set *new)
 {
-	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
-	int count;
+	struct mca_bank_cache *mca_cache = &adev->mca.mca_caches[type];
+	int ret;
 
-	if (!mca_funcs || !mca_funcs->mca_get_mca_entry)
-		return -EOPNOTSUPP;
+	mutex_lock(&mca_cache->lock);
+	ret = amdgpu_mca_bank_set_merge(&mca_cache->mca_set, new);
+	mutex_unlock(&mca_cache->lock);
 
-	switch (type) {
-	case AMDGPU_MCA_ERROR_TYPE_UE:
-		count = mca_funcs->max_ue_count;
-		break;
-	case AMDGPU_MCA_ERROR_TYPE_CE:
-		count = mca_funcs->max_ce_count;
-		break;
-	default:
-		return -EINVAL;
+	return ret;
+}
+
+int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
+				 struct ras_err_data *err_data, struct ras_query_context *qctx)
+{
+	struct mca_bank_set mca_set;
+	struct mca_bank_cache *mca_cache = &adev->mca.mca_caches[type];
+	int ret;
+
+	amdgpu_mca_bank_set_init(&mca_set);
+
+	ret = amdgpu_mca_smu_get_mca_set(adev, type, &mca_set, qctx);
+	if (ret)
+		goto out_mca_release;
+
+	ret = amdgpu_mca_dispatch_mca_set(adev, blk, type, &mca_set, err_data);
+	if (ret)
+		goto out_mca_release;
+
+	/* add remain mca bank to mca cache */
+	if (mca_set.nr_entries) {
+		ret = amdgpu_mca_add_mca_set_to_cache(adev, type, &mca_set);
+		if (ret)
+			goto out_mca_release;
 	}
 
-	if (idx >= count)
-		return -EINVAL;
+	/* dispatch mca set again if mca cache has valid data */
+	mutex_lock(&mca_cache->lock);
+	if (mca_cache->mca_set.nr_entries)
+		ret = amdgpu_mca_dispatch_mca_set(adev, blk, type, &mca_cache->mca_set, err_data);
+	mutex_unlock(&mca_cache->lock);
 
-	return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
+out_mca_release:
+	amdgpu_mca_bank_set_release(&mca_set);
+
+	return ret;
 }
 
 #if defined(CONFIG_DEBUG_FS)
@@ -437,36 +536,32 @@ static void mca_dump_entry(struct seq_file *m, struct mca_bank_entry *entry)
 static int mca_dump_show(struct seq_file *m, enum amdgpu_mca_error_type type)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)m->private;
-	struct mca_bank_entry *entry;
-	uint32_t count = 0;
-	int i, ret;
+	struct mca_bank_node *node;
+	struct mca_bank_set mca_set;
+	struct ras_query_context qctx;
+	int ret;
 
-	ret = amdgpu_mca_smu_get_valid_mca_count(adev, type, &count);
+	amdgpu_mca_bank_set_init(&mca_set);
+
+	qctx.evid.event_id = RAS_EVENT_INVALID_ID;
+	ret = amdgpu_mca_smu_get_mca_set(adev, type, &mca_set, &qctx);
 	if (ret)
-		return ret;
+		goto err_free_mca_set;
 
 	seq_printf(m, "amdgpu smu %s valid mca count: %d\n",
-		   type == AMDGPU_MCA_ERROR_TYPE_UE ? "UE" : "CE", count);
-
-	if (!count)
-		return 0;
+		   type == AMDGPU_MCA_ERROR_TYPE_UE ? "UE" : "CE", mca_set.nr_entries);
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
+	if (!mca_set.nr_entries)
+		goto err_free_mca_set;
 
-	for (i = 0; i < count; i++) {
-		memset(entry, 0, sizeof(*entry));
+	list_for_each_entry(node, &mca_set.list, node)
+		mca_dump_entry(m, &node->entry);
 
-		ret = amdgpu_mca_smu_get_mca_entry(adev, type, i, entry);
-		if (ret)
-			goto err_free_entry;
+	/* add mca bank to mca bank cache */
+	ret = amdgpu_mca_add_mca_set_to_cache(adev, type, &mca_set);
 
-		mca_dump_entry(m, entry);
-	}
-
-err_free_entry:
-	kfree(entry);
+err_free_mca_set:
+	amdgpu_mca_bank_set_release(&mca_set);
 
 	return ret;
 }
@@ -513,7 +608,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(mca_debug_mode_fops, NULL, amdgpu_mca_smu_debug_mode_se
 void amdgpu_mca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root)
 {
 #if defined(CONFIG_DEBUG_FS)
-	if (!root || amdgpu_ip_version(adev, MP1_HWIP, 0) != IP_VERSION(13, 0, 6))
+	if (!root)
 		return;
 
 	debugfs_create_file("mca_debug_mode", 0200, root, adev, &mca_debug_mode_fops);