summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c37
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c17
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c12
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c14
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c22
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v10_0.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v11_0.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v12_0.c4
17 files changed, 103 insertions, 44 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d58e37fd01f4..b85b67a88a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -205,6 +205,7 @@ extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
extern int amdgpu_bad_page_threshold;
+extern bool amdgpu_ignore_bad_page_threshold;
extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer;
extern int amdgpu_async_gfx_ring;
extern int amdgpu_mcbp;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 69de31754907..751557af09bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -279,6 +279,8 @@ int amdgpu_amdkfd_gpuvm_sync_memory(
struct kgd_dev *kgd, struct kgd_mem *mem, bool intr);
int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
struct kgd_mem *mem, void **kptr, uint64_t *size);
+void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem);
+
int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
struct dma_fence **ef);
int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index cdf46bd0d8d5..0e9cfe99ae9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1871,6 +1871,16 @@ bo_reserve_failed:
return ret;
}
+void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem)
+{
+ struct amdgpu_bo *bo = mem->bo;
+
+ amdgpu_bo_reserve(bo, true);
+ amdgpu_bo_kunmap(bo);
+ amdgpu_bo_unpin(bo);
+ amdgpu_bo_unreserve(bo);
+}
+
int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
struct kfd_vm_fault_info *mem)
{
@@ -2041,19 +2051,26 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
/* Get updated user pages */
ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
if (ret) {
- pr_debug("%s: Failed to get user pages: %d\n",
- __func__, ret);
+ pr_debug("Failed %d to get user pages\n", ret);
+
+ /* Return -EFAULT bad address error as success. It will
+ * fail later with a VM fault if the GPU tries to access
+ * it. Better than hanging indefinitely with stalled
+ * user mode queues.
+ *
+ * Return other error -EBUSY or -ENOMEM to retry restore
+ */
+ if (ret != -EFAULT)
+ return ret;
+ } else {
- /* Return error -EBUSY or -ENOMEM, retry restore */
- return ret;
+ /*
+ * FIXME: Cannot ignore the return code, must hold
+ * notifier_lock
+ */
+ amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
}
- /*
- * FIXME: Cannot ignore the return code, must hold
- * notifier_lock
- */
- amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
-
/* Mark the BO as valid unless it was invalidated
* again concurrently.
*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c218d53a031d..6e40cc1bc6dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3852,8 +3852,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
void amdgpu_device_fini_sw(struct amdgpu_device *adev)
{
- amdgpu_device_ip_fini(adev);
amdgpu_fence_driver_sw_fini(adev);
+ amdgpu_device_ip_fini(adev);
release_firmware(adev->firmware.gpu_info_fw);
adev->firmware.gpu_info_fw = NULL;
adev->accel_working = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 208a784475bd..d7c8d9e3c203 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -931,6 +931,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 0);
adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 0);
adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 0);
+ adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 0);
adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 0);
adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 1, 0);
adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 0, 0);
@@ -951,6 +952,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 1);
adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 1);
adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 1);
+ adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 1);
adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 5, 0);
adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 2, 0);
adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 0);
@@ -1009,6 +1011,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 0);
adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 0);
adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 0);
+ adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 0);
adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 0);
adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 0);
adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 1);
@@ -1018,6 +1021,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 2);
adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 0);
adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 2, 0);
+ adev->ip_versions[UVD_HWIP][1] = IP_VERSION(7, 2, 0);
adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 1, 0);
adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0);
break;
@@ -1030,6 +1034,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 1);
adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 1);
adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][1] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][2] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][3] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][4] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][5] = IP_VERSION(4, 2, 2);
+ adev->ip_versions[SDMA1_HWIP][6] = IP_VERSION(4, 2, 2);
adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 1);
adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 1);
adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 2);
@@ -1039,6 +1050,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 3);
adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 1);
adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 5, 0);
+ adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0);
break;
case CHIP_ALDEBARAN:
aldebaran_reg_base_init(adev);
@@ -1049,6 +1061,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 4, 0);
adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 4, 0);
adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 4, 0);
+ adev->ip_versions[SDMA0_HWIP][1] = IP_VERSION(4, 4, 0);
+ adev->ip_versions[SDMA0_HWIP][2] = IP_VERSION(4, 4, 0);
+ adev->ip_versions[SDMA0_HWIP][3] = IP_VERSION(4, 4, 0);
+ adev->ip_versions[SDMA0_HWIP][4] = IP_VERSION(4, 4, 0);
adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 2);
adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 4);
adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 7, 0);
@@ -1058,6 +1074,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(13, 0, 2);
adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 2);
adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 6, 0);
+ adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 6, 0);
adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
break;
default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index c718fb5f3f8a..4cefe867ccf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -877,7 +877,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444);
* result in the GPU entering bad status when the number of total
* faulty pages by ECC exceeds the threshold value.
*/
-MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)");
module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index d2955ea4a62b..dfe667ea8b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -340,32 +340,32 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
case AMDGPU_INFO_FW_TA:
switch (query_fw->index) {
case TA_FW_TYPE_PSP_XGMI:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.xgmi_context.context.bin_desc.fw_version;
fw_info->feature = adev->psp.xgmi_context.context
.bin_desc.feature_version;
break;
case TA_FW_TYPE_PSP_RAS:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.ras_context.context.bin_desc.fw_version;
fw_info->feature = adev->psp.ras_context.context
.bin_desc.feature_version;
break;
case TA_FW_TYPE_PSP_HDCP:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.hdcp_context.context.bin_desc.fw_version;
fw_info->feature = adev->psp.hdcp_context.context
.bin_desc.feature_version;
break;
case TA_FW_TYPE_PSP_DTM:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.dtm_context.context.bin_desc.fw_version;
fw_info->feature = adev->psp.dtm_context.context
.bin_desc.feature_version;
break;
case TA_FW_TYPE_PSP_RAP:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.rap_context.context.bin_desc.fw_version;
fw_info->feature = adev->psp.rap_context.context
.bin_desc.feature_version;
break;
case TA_FW_TYPE_PSP_SECUREDISPLAY:
- fw_info->ver = adev->psp.ta_fw_version;
+ fw_info->ver = adev->psp.securedisplay_context.context.bin_desc.fw_version;
fw_info->feature =
adev->psp.securedisplay_context.context.bin_desc
.feature_version;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index fd04e83031d6..c641f84649d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1115,7 +1115,7 @@ int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id)
static bool psp_xgmi_peer_link_info_supported(struct psp_context *psp)
{
return psp->adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 2) &&
- psp->xgmi_context.context.bin_desc.feature_version >= 0x2000000b;
+ psp->xgmi_context.context.bin_desc.fw_version >= 0x2000000b;
}
/*
@@ -3108,32 +3108,32 @@ static int parse_ta_bin_descriptor(struct psp_context *psp,
psp->asd_context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_XGMI:
- psp->xgmi_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version);
+ psp->xgmi_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version);
psp->xgmi_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes);
psp->xgmi_context.context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_RAS:
- psp->ras_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version);
+ psp->ras_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version);
psp->ras_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes);
psp->ras_context.context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_HDCP:
- psp->hdcp_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version);
+ psp->hdcp_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version);
psp->hdcp_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes);
psp->hdcp_context.context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_DTM:
- psp->dtm_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version);
+ psp->dtm_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version);
psp->dtm_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes);
psp->dtm_context.context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_RAP:
- psp->rap_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version);
+ psp->rap_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version);
psp->rap_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes);
psp->rap_context.context.bin_desc.start_addr = ucode_start_addr;
break;
case TA_FW_TYPE_PSP_SECUREDISPLAY:
- psp->securedisplay_context.context.bin_desc.feature_version =
+ psp->securedisplay_context.context.bin_desc.fw_version =
le32_to_cpu(desc->fw_version);
psp->securedisplay_context.context.bin_desc.size_bytes =
le32_to_cpu(desc->size_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index f4c05ff4b26c..05117eda105b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1077,6 +1077,13 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
if (res)
DRM_ERROR("RAS table incorrect checksum or error:%d\n",
res);
+
+ /* Warn if we are at 90% of the threshold or above
+ */
+ if (10 * control->ras_num_recs >= 9 * ras->bad_page_cnt_threshold)
+ dev_warn(adev->dev, "RAS records:%u exceeds 90%% of threshold:%d",
+ control->ras_num_recs,
+ ras->bad_page_cnt_threshold);
} else if (hdr->header == RAS_TABLE_HDR_BAD &&
amdgpu_bad_page_threshold != 0) {
res = __verify_ras_table_checksum(control);
@@ -1098,11 +1105,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
res = amdgpu_ras_eeprom_correct_header_tag(control,
RAS_TABLE_HDR_VAL);
} else {
- *exceed_err_limit = true;
- dev_err(adev->dev,
- "RAS records:%d exceed threshold:%d, "
- "GPU will not be initialized. Replace this GPU or increase the threshold",
+ dev_err(adev->dev, "RAS records:%d exceed threshold:%d",
control->ras_num_recs, ras->bad_page_cnt_threshold);
+ if (amdgpu_bad_page_threshold == -2) {
+ dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2.");
+ res = 0;
+ } else {
+ *exceed_err_limit = true;
+ dev_err(adev->dev,
+ "RAS records:%d exceed threshold:%d, "
+ "GPU will not be initialized. Replace this GPU or increase the threshold",
+ control->ras_num_recs, ras->bad_page_cnt_threshold);
+ }
}
} else {
DRM_INFO("Creating a new EEPROM table");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 590537b62a0a..17b5dd6adf8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -696,6 +696,9 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
true, NULL);
out_unlock:
mmap_read_unlock(mm);
+ if (r)
+ pr_debug("failed %d to get user pages 0x%lx\n", r, start);
+
mmput(mm);
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 920c4f6ac914..ca3350502618 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -527,8 +527,8 @@ FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version);
FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version);
FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version);
FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version);
-FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.feature_version);
-FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.xgmi_context.context.bin_desc.feature_version);
+FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version);
+FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.xgmi_context.context.bin_desc.fw_version);
FW_VERSION_ATTR(smc_fw_version, 0444, pm.fw_version);
FW_VERSION_ATTR(sdma_fw_version, 0444, sdma.instance[0].fw_version);
FW_VERSION_ATTR(sdma2_fw_version, 0444, sdma.instance[1].fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 99c149397aae..04cf9b207e62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -535,9 +535,9 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,
adev->psp.asd_context.bin_desc.fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS,
- adev->psp.ras_context.context.bin_desc.feature_version);
+ adev->psp.ras_context.context.bin_desc.fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI,
- adev->psp.xgmi_context.context.bin_desc.feature_version);
+ adev->psp.xgmi_context.context.bin_desc.fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SMC, adev->pm.fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA, adev->sdma.instance[0].fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA2, adev->sdma.instance[1].fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
index 00a2b36a24b3..c4f37a161875 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
@@ -706,6 +706,11 @@ int gfx_v9_4_2_do_edc_gpr_workarounds(struct amdgpu_device *adev)
if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
return 0;
+ /* Workaround for ALDEBARAN, skip GPRs init in GPU reset.
+ Will remove it once GPRs init algorithm works for all CU settings. */
+ if (amdgpu_in_reset(adev))
+ return 0;
+
gfx_v9_4_2_do_sgprs_init(adev);
gfx_v9_4_2_do_vgprs_init(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 0e81e03e9b49..0fe714f54cca 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -841,12 +841,12 @@ static int gmc_v6_0_sw_init(void *handle)
adev->gmc.mc_mask = 0xffffffffffULL;
- r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(44));
+ r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(40));
if (r) {
dev_warn(adev->dev, "No suitable DMA available.\n");
return r;
}
- adev->need_swiotlb = drm_need_swiotlb(44);
+ adev->need_swiotlb = drm_need_swiotlb(40);
r = gmc_v6_0_init_microcode(adev);
if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 59644015dfc3..ed2293686f0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -84,7 +84,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
ta_hdr = (const struct ta_firmware_header_v1_0 *)
adev->psp.ta_fw->data;
- adev->psp.hdcp_context.context.bin_desc.feature_version =
+ adev->psp.hdcp_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->hdcp.fw_version);
adev->psp.hdcp_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->hdcp.size_bytes);
@@ -92,7 +92,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
(uint8_t *)ta_hdr +
le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
- adev->psp.dtm_context.context.bin_desc.feature_version =
+ adev->psp.dtm_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->dtm.fw_version);
adev->psp.dtm_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->dtm.size_bytes);
@@ -100,7 +100,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
le32_to_cpu(ta_hdr->dtm.offset_bytes);
- adev->psp.securedisplay_context.context.bin_desc.feature_version =
+ adev->psp.securedisplay_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->securedisplay.fw_version);
adev->psp.securedisplay_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->securedisplay.size_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 21a325ea49cb..2176ef85f137 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -151,7 +151,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
goto out2;
ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
- adev->psp.xgmi_context.context.bin_desc.feature_version =
+ adev->psp.xgmi_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->xgmi.fw_version);
adev->psp.xgmi_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->xgmi.size_bytes);
@@ -159,7 +159,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
(uint8_t *)ta_hdr +
le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
- adev->psp.ras_context.context.bin_desc.feature_version =
+ adev->psp.ras_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->ras.fw_version);
adev->psp.ras_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->ras.size_bytes);
@@ -192,7 +192,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
goto out2;
ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
- adev->psp.hdcp_context.context.bin_desc.feature_version =
+ adev->psp.hdcp_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->hdcp.fw_version);
adev->psp.hdcp_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->hdcp.size_bytes);
@@ -203,7 +203,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
- adev->psp.dtm_context.context.bin_desc.feature_version =
+ adev->psp.dtm_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->dtm.fw_version);
adev->psp.dtm_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->dtm.size_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 281bc4d7f0a1..a2588200ea58 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -84,7 +84,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
ta_hdr = (const struct ta_firmware_header_v1_0 *)
adev->psp.ta_fw->data;
- adev->psp.hdcp_context.context.bin_desc.feature_version =
+ adev->psp.hdcp_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->hdcp.fw_version);
adev->psp.hdcp_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->hdcp.size_bytes);
@@ -94,7 +94,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
- adev->psp.dtm_context.context.bin_desc.feature_version =
+ adev->psp.dtm_context.context.bin_desc.fw_version =
le32_to_cpu(ta_hdr->dtm.fw_version);
adev->psp.dtm_context.context.bin_desc.size_bytes =
le32_to_cpu(ta_hdr->dtm.size_bytes);