Merge tag 'drm-next-2025-04-05' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly fixes, mostly from the end of last week, this week was very
  quiet, maybe you scared everyone away. It's mostly amdgpu, and xe,
  with some i915, adp and bridge bits, since I think this is overly
  quiet I'd expect rc2 to be a bit more lively.

  bridge:
   - tda998x: Select CONFIG_DRM_KMS_HELPER

  amdgpu:
   - Guard against potential division by 0 in fan code
   - Zero RPM support for SMU 14.0.2
   - Properly handle SI and CIK support being disabled
   - PSR fixes
   - DML2 fixes
   - DP Link training fix
   - Vblank fixes
   - RAS fixes
   - Partitioning fix
   - SDMA fix
   - SMU 13.0.x fixes
   - Rom fetching fix
   - MES fixes
   - Queue reset fix

  xe:
   - Fix NULL pointer dereference on error path
   - Add missing HW workaround for BMG
   - Fix survivability mode not triggering
   - Fix build warning when DRM_FBDEV_EMULATION is not set

  i915:
   - Bounds check for scalers in DSC prefill latency computation
   - Fix build by adding a missing include

  adp:
   - Fix error handling in plane setup"

  # -----BEGIN PGP SIGNATURE-----

* tag 'drm-next-2025-04-05' of https://gitlab.freedesktop.org/drm/kernel: (34 commits)
  drm/i2c: tda998x: select CONFIG_DRM_KMS_HELPER
  drm/amdgpu/gfx12: fix num_mec
  drm/amdgpu/gfx11: fix num_mec
  drm/amd/pm: Add gpu_metrics_v1_8
  drm/amdgpu: Prefer shadow rom when available
  drm/amd/pm: Update smu metrics table for smu_v13_0_6
  drm/amd/pm: Remove host limit metrics support
  Remove unnecessary firmware version check for gc v9_4_2
  drm/amdgpu: stop unmapping MQD for kernel queues v3
  Revert "drm/amdgpu/sdma_v4_4_2: update VM flush implementation for SDMA"
  drm/amdgpu: Parse all deferred errors with UMC aca handle
  drm/amdgpu: Update ta ras block
  drm/amdgpu: Add NPS2 to DPX compatible mode
  drm/amdgpu: Use correct gfx deferred error count
  drm/amd/display: Actually do immediate vblank disable
  drm/amd/display: prevent hang on link training fail
  Revert "drm/amd/display: dml2 soc dscclk use DPM table clk setting"
  drm/amd/display: Increase vblank offdelay for PSR panels
  drm/amd: Handle being compiled without SI or CIK support better
  drm/amd/pm: Add zero RPM enabled OD setting support for SMU14.0.2
  ...

Author: torvalds

drivers/gpu/drm/adp/adp_drv.c

@@ -232,9 +232,9 @@ static struct drm_plane *adp_plane_new(struct adp_drv_private *adp)
 					     ALL_CRTCS, &adp_plane_funcs,
 					     plane_formats, ARRAY_SIZE(plane_formats),
 					     NULL, DRM_PLANE_TYPE_PRIMARY, "plane");
-	if (!plane) {
+	if (IS_ERR(plane)) {
 		drm_err(drm, "failed to allocate plane");
-		return ERR_PTR(-ENOMEM);
+		return plane;
 	}
 
 	drm_plane_helper_add(plane, &adp_plane_helper_funcs);

drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c

@@ -195,6 +195,10 @@ static bool aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank,
 {
 	const struct aca_bank_ops *bank_ops = handle->bank_ops;
 
+	/* Parse all deferred errors with UMC aca handle */
+	if (ACA_BANK_ERR_IS_DEFFERED(bank))
+		return handle->hwip == ACA_HWIP_TYPE_UMC;
+
 	if (!aca_bank_hwip_is_matched(bank, handle->hwip))
 		return false;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h

@@ -80,14 +80,6 @@ struct ras_query_context;
 	(ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \
 	 ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS]))
 
-#define ACA_BANK_ERR_CE_DE_DECODE(bank)                             \
-	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
-					  ACA_ERROR_TYPE_CE)
-
-#define ACA_BANK_ERR_UE_DE_DECODE(bank)                             \
-	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
-					  ACA_ERROR_TYPE_UE)
-
 enum aca_reg_idx {
 	ACA_REG_IDX_CTL			= 0,
 	ACA_REG_IDX_STATUS		= 1,

drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c

@@ -447,6 +447,13 @@ static bool amdgpu_get_bios_apu(struct amdgpu_device *adev)
 	return true;
 }
 
+static bool amdgpu_prefer_rom_resource(struct amdgpu_device *adev)
+{
+	struct resource *res = &adev->pdev->resource[PCI_ROM_RESOURCE];
+
+	return (res->flags & IORESOURCE_ROM_SHADOW);
+}
+
 static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev)
 {
 	if (amdgpu_atrm_get_bios(adev)) {
@@ -465,14 +472,27 @@ static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev)
 		goto success;
 	}
 
-	if (amdgpu_read_platform_bios(adev)) {
-		dev_info(adev->dev, "Fetched VBIOS from platform\n");
-		goto success;
-	}
+	if (amdgpu_prefer_rom_resource(adev)) {
+		if (amdgpu_read_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
+			goto success;
+		}
 
-	if (amdgpu_read_bios(adev)) {
-		dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
-		goto success;
+		if (amdgpu_read_platform_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from platform\n");
+			goto success;
+		}
+
+	} else {
+		if (amdgpu_read_platform_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from platform\n");
+			goto success;
+		}
+
+		if (amdgpu_read_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
+			goto success;
+		}
 	}
 
 	if (amdgpu_read_bios_from_rom(adev)) {

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -1809,7 +1809,6 @@ static const u16 amdgpu_unsupported_pciidlist[] = {
 };
 
 static const struct pci_device_id pciidlist[] = {
-#ifdef CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
 	{0x1002, 0x6784, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
 	{0x1002, 0x6788, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -1882,8 +1881,6 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x6665, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
 	{0x1002, 0x6667, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
 	{0x1002, 0x666F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
 	{0x1002, 0x1304, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x1305, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|AMD_IS_APU},
@@ -1966,7 +1963,6 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x985D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x985E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
-#endif
 	/* topaz */
 	{0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ},
 	{0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ},
@@ -2313,40 +2309,48 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENOTSUPP;
 	}
 
+	switch (flags & AMD_ASIC_MASK) {
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+	case CHIP_HAINAN:
 #ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
+		if (!amdgpu_si_support) {
 			dev_info(&pdev->dev,
 				 "SI support provided by radeon.\n");
 			dev_info(&pdev->dev,
 				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
 				);
 			return -ENODEV;
 		}
-	}
+		break;
+#else
+		dev_info(&pdev->dev, "amdgpu is built without SI support.\n");
+		return -ENODEV;
 #endif
+	case CHIP_KAVERI:
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+	case CHIP_KABINI:
+	case CHIP_MULLINS:
 #ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
+		if (!amdgpu_cik_support) {
 			dev_info(&pdev->dev,
 				 "CIK support provided by radeon.\n");
 			dev_info(&pdev->dev,
 				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
 				);
 			return -ENODEV;
 		}
-	}
+		break;
+#else
+		dev_info(&pdev->dev, "amdgpu is built without CIK support.\n");
+		return -ENODEV;
 #endif
+	default:
+		break;
+	}
 
 	adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
 	if (IS_ERR(adev))

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -77,6 +77,7 @@ const char *ras_block_string[] = {
 	"jpeg",
 	"ih",
 	"mpio",
+	"mmsch",
 };
 
 const char *ras_mca_block_string[] = {

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h

@@ -98,6 +98,7 @@ enum amdgpu_ras_block {
 	AMDGPU_RAS_BLOCK__JPEG,
 	AMDGPU_RAS_BLOCK__IH,
 	AMDGPU_RAS_BLOCK__MPIO,
+	AMDGPU_RAS_BLOCK__MMSCH,
 
 	AMDGPU_RAS_BLOCK__LAST,
 	AMDGPU_RAS_BLOCK__ANY = -1
@@ -795,6 +796,12 @@ amdgpu_ras_block_to_ta(enum amdgpu_ras_block block) {
 		return TA_RAS_BLOCK__VCN;
 	case AMDGPU_RAS_BLOCK__JPEG:
 		return TA_RAS_BLOCK__JPEG;
+	case AMDGPU_RAS_BLOCK__IH:
+		return TA_RAS_BLOCK__IH;
+	case AMDGPU_RAS_BLOCK__MPIO:
+		return TA_RAS_BLOCK__MPIO;
+	case AMDGPU_RAS_BLOCK__MMSCH:
+		return TA_RAS_BLOCK__MMSCH;
 	default:
 		WARN_ONCE(1, "RAS ERROR: unexpected block id %d\n", block);
 		return TA_RAS_BLOCK__UMC;

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

@@ -608,59 +608,17 @@ static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf,
 				       size_t size, loff_t *pos)
 {
 	struct amdgpu_ring *ring = file_inode(f)->i_private;
-	volatile u32 *mqd;
-	u32 *kbuf;
-	int r, i;
-	uint32_t value, result;
+	ssize_t bytes = min_t(ssize_t, ring->mqd_size - *pos, size);
+	void *from = ((u8 *)ring->mqd_ptr) + *pos;
 
-	if (*pos & 3 || size & 3)
-		return -EINVAL;
-
-	kbuf = kmalloc(ring->mqd_size, GFP_KERNEL);
-	if (!kbuf)
-		return -ENOMEM;
-
-	r = amdgpu_bo_reserve(ring->mqd_obj, false);
-	if (unlikely(r != 0))
-		goto err_free;
-
-	r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd);
-	if (r)
-		goto err_unreserve;
-
-	/*
-	 * Copy to local buffer to avoid put_user(), which might fault
-	 * and acquire mmap_sem, under reservation_ww_class_mutex.
-	 */
-	for (i = 0; i < ring->mqd_size/sizeof(u32); i++)
-		kbuf[i] = mqd[i];
+	if (*pos > ring->mqd_size)
+		return 0;
 
-	amdgpu_bo_kunmap(ring->mqd_obj);
-	amdgpu_bo_unreserve(ring->mqd_obj);
+	if (copy_to_user(buf, from, bytes))
+		return -EFAULT;
 
-	result = 0;
-	while (size) {
-		if (*pos >= ring->mqd_size)
-			break;
-
-		value = kbuf[*pos/4];
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			goto err_free;
-		buf += 4;
-		result += 4;
-		size -= 4;
-		*pos += 4;
-	}
-
-	kfree(kbuf);
-	return result;
-
-err_unreserve:
-	amdgpu_bo_unreserve(ring->mqd_obj);
-err_free:
-	kfree(kbuf);
-	return r;
+	*pos += bytes;
+	return bytes;
 }
 
 static const struct file_operations amdgpu_debugfs_mqd_fops = {

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c

@@ -1172,7 +1172,7 @@ static int xgmi_v6_4_0_aca_bank_parser(struct aca_handle *handle, struct aca_ban
 		break;
 	case ACA_SMU_TYPE_CE:
 		count = ext_error_code == 6 ? count : 0ULL;
-		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		bank->aca_err_type = ACA_ERROR_TYPE_CE;
 		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, count);
 		break;
 	default:

drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c

@@ -473,7 +473,8 @@ static int aqua_vanjaram_get_xcp_res_info(struct amdgpu_xcp_mgr *xcp_mgr,
 		break;
 	case AMDGPU_DPX_PARTITION_MODE:
 		num_xcp = 2;
-		nps_modes = BIT(AMDGPU_NPS1_PARTITION_MODE);
+		nps_modes = BIT(AMDGPU_NPS1_PARTITION_MODE) |
+			    BIT(AMDGPU_NPS2_PARTITION_MODE);
 		break;
 	case AMDGPU_TPX_PARTITION_MODE:
 		num_xcp = 3;