Merge tag 'amd-drm-next-6.8-2024-01-05' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.8-2024-01-05:

amdgpu:
- VRR fixes
- PSR-SU fixes
- SubVP fixes
- DCN 3.5 fixes
- Documentation updates
- DMCUB fixes
- DML2 fixes
- UMC 12.0 updates
- GPUVM fix
- Misc code cleanups and whitespace cleanups
- DP MST fix
- Let KFD sync with GPUVM fences
- GFX11 reset fix
- SMU 13.0.6 fixes
- VSC fix for DP/eDP
- Navi12 display fix
- RN/CZN system aperture fix
- DCN 2.1 bandwidth validation fix
- DCN INIT cleanup

amdkfd:
- SVM fixes
- Revert TBA/TMA location change

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240105220522.4976-1-alexander.deucher@amd.com

Author: airlied

Documentation/gpu/amdgpu/apu-asic-info-table.csv

@@ -7,6 +7,7 @@ SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0
 Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1
 Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
 Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
-Ryzen 7x45 series (FL1), / Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
+Ryzen 7x45 series (FL1), Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
 Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8
-Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
+Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
+Ryzen 8x40 series, Hawk Point, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11

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

@@ -330,6 +330,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 {
 	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
+	struct amdgpu_ras *con;
 	int r;
 
 	if (reset_device_list == NULL)
@@ -355,7 +356,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		 */
 		amdgpu_register_gpu_instance(tmp_adev);
 
-		/* Resume RAS */
+		/* Resume RAS, ecc_irq */
+		con = amdgpu_ras_get_context(tmp_adev);
+		if (!amdgpu_sriov_vf(tmp_adev) && con) {
+			if (tmp_adev->sdma.ras &&
+				tmp_adev->sdma.ras->ras_block.ras_late_init) {
+				r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->sdma.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+
+			if (tmp_adev->gfx.ras &&
+				tmp_adev->gfx.ras->ras_block.ras_late_init) {
+				r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->gfx.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+		}
+
 		amdgpu_ras_resume(tmp_adev);
 
 		/* Update PSP FW topology after reset */

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

@@ -254,6 +254,8 @@ extern int amdgpu_agp;
 
 extern int amdgpu_wbrf;
 
+extern int fw_bo_location;
+
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000

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

@@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 		return NULL;
 
 	fence = container_of(f, struct amdgpu_amdkfd_fence, base);
-	if (fence && f->ops == &amdkfd_fence_ops)
+	if (f->ops == &amdkfd_fence_ops)
 		return fence;
 
 	return NULL;

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

@@ -1103,7 +1103,7 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 			 * DDC line.  The latter is more complex because with DVI<->HDMI adapters
 			 * you don't really know what's connected to which port as both are digital.
 			 */
-			 amdgpu_connector_shared_ddc(&ret, connector, amdgpu_connector);
+			amdgpu_connector_shared_ddc(&ret, connector, amdgpu_connector);
 		}
 	}
 

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

@@ -870,9 +870,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		struct amdgpu_bo *bo = e->bo;
 		int i;
 
-		e->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages,
-					sizeof(struct page *),
-					GFP_KERNEL | __GFP_ZERO);
+		e->user_pages = kvcalloc(bo->tbo.ttm->num_pages,
+					 sizeof(struct page *),
+					 GFP_KERNEL);
 		if (!e->user_pages) {
 			DRM_ERROR("kvmalloc_array failure\n");
 			r = -ENOMEM;

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

@@ -540,7 +540,11 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	while (size) {
 		uint32_t value;
 
-		value = RREG32_PCIE(*pos);
+		if (upper_32_bits(*pos))
+			value = RREG32_PCIE_EXT(*pos);
+		else
+			value = RREG32_PCIE(*pos);
+
 		r = put_user(value, (uint32_t *)buf);
 		if (r)
 			goto out;
@@ -600,7 +604,10 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 		if (r)
 			goto out;
 
-		WREG32_PCIE(*pos, value);
+		if (upper_32_bits(*pos))
+			WREG32_PCIE_EXT(*pos, value);
+		else
+			WREG32_PCIE(*pos, value);
 
 		result += 4;
 		buf += 4;

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

@@ -2251,15 +2251,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->mman.discovery_bin) {
-		/*
-		 * FIXME: The bounding box is still needed by Navi12, so
-		 * temporarily read it from gpu_info firmware. Should be dropped
-		 * when DAL no longer needs it.
-		 */
-		if (adev->asic_type != CHIP_NAVI12)
-			return 0;
-	}
+	if (adev->mman.discovery_bin)
+		return 0;
 
 	switch (adev->asic_type) {
 	default:

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

@@ -210,6 +210,7 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
+int fw_bo_location = -1;
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -989,6 +990,10 @@ MODULE_PARM_DESC(wbrf,
 	"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
 module_param_named(wbrf, amdgpu_wbrf, int, 0444);
 
+MODULE_PARM_DESC(fw_bo_location,
+	"location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
+module_param(fw_bo_location, int, 0644);
+
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */

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

@@ -218,6 +218,7 @@ static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, st
 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 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;
@@ -246,10 +247,18 @@ int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_blo
 		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, (uint64_t)count);
+			amdgpu_ras_error_statistic_ue_count(err_data,
+				&mcm_info, &err_addr, (uint64_t)count);
 		else
-			amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, (uint64_t)count);
+			amdgpu_ras_error_statistic_ce_count(err_data,
+				&mcm_info, &err_addr, (uint64_t)count);
 	}
 
 out_mca_release:
@@ -351,6 +360,9 @@ int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_err
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
 	int count;
 
+	if (!mca_funcs || !mca_funcs->mca_get_mca_entry)
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case AMDGPU_MCA_ERROR_TYPE_UE:
 		count = mca_funcs->max_ue_count;
@@ -365,10 +377,7 @@ int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_err
 	if (idx >= count)
 		return -EINVAL;
 
-	if (mca_funcs && mca_funcs->mca_get_mca_entry)
-		return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
-
-	return -EOPNOTSUPP;
+	return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
 }
 
 #if defined(CONFIG_DEBUG_FS)