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 <[email protected]> From: Alex Deucher <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
NeroReflex · Jan 8, 2024 · e54478f · e54478f
2 parents 3c064ae + 754d349
commit e54478f
Show file tree

Hide file tree

Showing 198 changed files with 4,093 additions and 2,111 deletions.
diff --git a/Documentation/gpu/amdgpu/apu-asic-info-table.csv b/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
diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/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 */

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/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

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/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;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/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);
 		}
 	}
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/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;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/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;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/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:

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/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
  */

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/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)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      amdgpu_sriov_vf(adev) ?
+				      (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
 				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1156,8 +1156,10 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s
 		for_each_ras_error(err_node, err_data) {
 			err_info = &err_node->err_info;
 
-			amdgpu_ras_error_statistic_ce_count(&obj->err_data, &err_info->mcm_info, err_info->ce_count);
-			amdgpu_ras_error_statistic_ue_count(&obj->err_data, &err_info->mcm_info, err_info->ue_count);
+			amdgpu_ras_error_statistic_ce_count(&obj->err_data,
+					&err_info->mcm_info, NULL, err_info->ce_count);
+			amdgpu_ras_error_statistic_ue_count(&obj->err_data,
+					&err_info->mcm_info, NULL, err_info->ue_count);
 		}
 	} else {
 		/* for legacy asic path which doesn't has error source info */
@@ -1174,6 +1176,9 @@ static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev,
 	enum amdgpu_ras_block blk = info ? info->head.block : AMDGPU_RAS_BLOCK_COUNT;
 	struct amdgpu_ras_block_object *block_obj = NULL;
 
+	if (blk == AMDGPU_RAS_BLOCK_COUNT)
+		return -EINVAL;
+
 	if (error_query_mode == AMDGPU_RAS_INVALID_ERROR_QUERY)
 		return -EINVAL;
 
@@ -2538,7 +2543,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 		return 0;
 
 	data = &con->eh_data;
-	*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
+	*data = kzalloc(sizeof(**data), GFP_KERNEL);
 	if (!*data) {
 		ret = -ENOMEM;
 		goto out;
@@ -2825,10 +2830,10 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	if (con)
 		return 0;
 
-	con = kmalloc(sizeof(struct amdgpu_ras) +
+	con = kzalloc(sizeof(*con) +
 			sizeof(struct ras_manager) * AMDGPU_RAS_BLOCK_COUNT +
 			sizeof(struct ras_manager) * AMDGPU_RAS_MCA_BLOCK_COUNT,
-			GFP_KERNEL|__GFP_ZERO);
+			GFP_KERNEL);
 	if (!con)
 		return -ENOMEM;
 
@@ -3133,8 +3138,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	/* enable MCA debug on APU device */
-	amdgpu_ras_set_mca_debug_mode(adev, !!(adev->flags & AMD_IS_APU));
+	amdgpu_ras_set_mca_debug_mode(adev, false);
 
 	list_for_each_entry_safe(node, tmp, &adev->ras_list, node) {
 		if (!node->ras_obj) {
@@ -3691,7 +3695,8 @@ static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct
 }
 
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
-						      struct amdgpu_smuio_mcm_config_info *mcm_info)
+				struct amdgpu_smuio_mcm_config_info *mcm_info,
+				struct ras_err_addr *err_addr)
 {
 	struct ras_err_node *err_node;
 
@@ -3705,6 +3710,9 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	memcpy(&err_node->err_info.mcm_info, mcm_info, sizeof(*mcm_info));
 
+	if (err_addr)
+		memcpy(&err_node->err_info.err_addr, err_addr, sizeof(*err_addr));
+
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
 	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
@@ -3713,7 +3721,8 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 }
 
 int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count)
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -3723,7 +3732,7 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 	if (!count)
 		return 0;
 
-	err_info = amdgpu_ras_error_get_info(err_data, mcm_info);
+	err_info = amdgpu_ras_error_get_info(err_data, mcm_info, err_addr);
 	if (!err_info)
 		return -EINVAL;
 
@@ -3734,7 +3743,8 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 }
 
 int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count)
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -3744,7 +3754,7 @@ int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
 	if (!count)
 		return 0;
 
-	err_info = amdgpu_ras_error_get_info(err_data, mcm_info);
+	err_info = amdgpu_ras_error_get_info(err_data, mcm_info, err_addr);
 	if (!err_info)
 		return -EINVAL;
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -452,10 +452,17 @@ struct ras_fs_data {
 	char debugfs_name[32];
 };
 
+struct ras_err_addr {
+	uint64_t err_status;
+	uint64_t err_ipid;
+	uint64_t err_addr;
+};
+
 struct ras_err_info {
 	struct amdgpu_smuio_mcm_config_info mcm_info;
 	u64 ce_count;
 	u64 ue_count;
+	struct ras_err_addr err_addr;
 };
 
 struct ras_err_node {
@@ -806,8 +813,10 @@ void amdgpu_ras_inst_reset_ras_error_count(struct amdgpu_device *adev,
 int amdgpu_ras_error_data_init(struct ras_err_data *err_data);
 void amdgpu_ras_error_data_fini(struct ras_err_data *err_data);
 int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count);
 int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -531,13 +531,12 @@ int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
 	if (version_major == 2 && version_minor == 1)
 		adev->gfx.rlc.is_rlc_v2_1 = true;
 
-	if (version_minor >= 0) {
-		err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
-		if (err) {
-			dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
-			return err;
-		}
+	err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
+	if (err) {
+		dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
+		return err;
 	}
+
 	if (version_minor >= 1)
 		amdgpu_gfx_rlc_init_microcode_v2_1(adev);
 	if (version_minor >= 2)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -191,7 +191,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
 
 	/* Never sync to VM updates either. */
 	if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
-	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED &&
+	    owner != AMDGPU_FENCE_OWNER_KFD)
 		return false;
 
 	/* Ignore fences depending on the sync mode */