summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c102
1 files changed, 75 insertions, 27 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 0b3db212b5a4..a7cd238654eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1224,6 +1224,10 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
}
}
+ /* Don't post if we need to reset whole hive on init */
+ if (adev->gmc.xgmi.pending_reset)
+ return false;
+
if (adev->has_hw_reset) {
adev->has_hw_reset = false;
return true;
@@ -2154,6 +2158,9 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_PSP)
continue;
+ if (!adev->ip_blocks[i].status.sw)
+ continue;
+
/* no need to do the fw loading again if already done*/
if (adev->ip_blocks[i].status.hw == true)
break;
@@ -2294,7 +2301,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
if (adev->gmc.xgmi.num_physical_nodes > 1)
amdgpu_xgmi_add_device(adev);
- amdgpu_amdkfd_device_init(adev);
+
+ /* Don't init kfd if whole hive need to be reset during init */
+ if (!adev->gmc.xgmi.pending_reset)
+ amdgpu_amdkfd_device_init(adev);
amdgpu_fru_get_product_info(adev);
@@ -2739,6 +2749,16 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
adev->ip_blocks[i].status.hw = false;
continue;
}
+
+ /* skip unnecessary suspend if we do not initialize them yet */
+ if (adev->gmc.xgmi.pending_reset &&
+ !(adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH)) {
+ adev->ip_blocks[i].status.hw = false;
+ continue;
+ }
/* XXX handle errors */
r = adev->ip_blocks[i].version->funcs->suspend(adev);
/* XXX handle errors */
@@ -3414,10 +3434,28 @@ int amdgpu_device_init(struct amdgpu_device *adev,
* E.g., driver was not cleanly unloaded previously, etc.
*/
if (!amdgpu_sriov_vf(adev) && amdgpu_asic_need_reset_on_init(adev)) {
- r = amdgpu_asic_reset(adev);
- if (r) {
- dev_err(adev->dev, "asic reset on init failed\n");
- goto failed;
+ if (adev->gmc.xgmi.num_physical_nodes) {
+ dev_info(adev->dev, "Pending hive reset.\n");
+ adev->gmc.xgmi.pending_reset = true;
+ /* Only need to init necessary block for SMU to handle the reset */
+ for (i = 0; i < adev->num_ip_blocks; i++) {
+ if (!adev->ip_blocks[i].status.valid)
+ continue;
+ if (!(adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC)) {
+ DRM_DEBUG("IP %s disabed for hw_init.\n",
+ adev->ip_blocks[i].version->funcs->name);
+ adev->ip_blocks[i].status.hw = true;
+ }
+ }
+ } else {
+ r = amdgpu_asic_reset(adev);
+ if (r) {
+ dev_err(adev->dev, "asic reset on init failed\n");
+ goto failed;
+ }
}
}
@@ -3548,19 +3586,19 @@ fence_driver_init:
/* enable clockgating, etc. after ib tests, etc. since some blocks require
* explicit gating rather than handling it automatically.
*/
- r = amdgpu_device_ip_late_init(adev);
- if (r) {
- dev_err(adev->dev, "amdgpu_device_ip_late_init failed\n");
- amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
- goto failed;
+ if (!adev->gmc.xgmi.pending_reset) {
+ r = amdgpu_device_ip_late_init(adev);
+ if (r) {
+ dev_err(adev->dev, "amdgpu_device_ip_late_init failed\n");
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
+ goto failed;
+ }
+ /* must succeed. */
+ amdgpu_ras_resume(adev);
+ queue_delayed_work(system_wq, &adev->delayed_init_work,
+ msecs_to_jiffies(AMDGPU_RESUME_MS));
}
- /* must succeed. */
- amdgpu_ras_resume(adev);
-
- queue_delayed_work(system_wq, &adev->delayed_init_work,
- msecs_to_jiffies(AMDGPU_RESUME_MS));
-
if (amdgpu_sriov_vf(adev))
flush_delayed_work(&adev->delayed_init_work);
@@ -3577,6 +3615,10 @@ fence_driver_init:
if (amdgpu_device_cache_pci_state(adev->pdev))
pci_restore_state(pdev);
+ if (adev->gmc.xgmi.pending_reset)
+ queue_delayed_work(system_wq, &mgpu_info.delayed_reset_work,
+ msecs_to_jiffies(AMDGPU_RESUME_MS));
+
return 0;
failed:
@@ -4287,14 +4329,16 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
return ret;
}
-static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
- struct amdgpu_job *job,
- bool *need_full_reset_arg)
+int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
+ struct amdgpu_job *job,
+ bool *need_full_reset_arg)
{
int i, r = 0;
bool need_full_reset = *need_full_reset_arg;
- amdgpu_debugfs_wait_dump(adev);
+ /* no need to dump if device is not in good state during probe period */
+ if (!adev->gmc.xgmi.pending_reset)
+ amdgpu_debugfs_wait_dump(adev);
if (amdgpu_sriov_vf(adev)) {
/* stop the data exchange thread */
@@ -4340,10 +4384,10 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
return r;
}
-static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
- struct list_head *device_list_handle,
- bool *need_full_reset_arg,
- bool skip_hw_reset)
+int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
+ struct list_head *device_list_handle,
+ bool *need_full_reset_arg,
+ bool skip_hw_reset)
{
struct amdgpu_device *tmp_adev = NULL;
bool need_full_reset = *need_full_reset_arg, vram_lost = false;
@@ -4357,6 +4401,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
/* For XGMI run all resets in parallel to speed up the process */
if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
+ tmp_adev->gmc.xgmi.pending_reset = false;
if (!queue_work(system_unbound_wq, &tmp_adev->xgmi_reset_work))
r = -EALREADY;
} else
@@ -4395,10 +4440,10 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
if (need_full_reset) {
/* post card */
- if (amdgpu_device_asic_init(tmp_adev))
+ r = amdgpu_device_asic_init(tmp_adev);
+ if (r) {
dev_warn(tmp_adev->dev, "asic atom init failed!");
-
- if (!r) {
+ } else {
dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
r = amdgpu_device_ip_resume_phase1(tmp_adev);
if (r)
@@ -4431,6 +4476,9 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
*/
amdgpu_register_gpu_instance(tmp_adev);
+ if (!hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1)
+ amdgpu_xgmi_add_device(tmp_adev);
+
r = amdgpu_device_ip_late_init(tmp_adev);
if (r)
goto out;
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-03-30 09:04:45 +0000