}
}
+ /* 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;
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;
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);
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 */
* 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;
+ }
}
}
/* 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);
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:
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 */
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;
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
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)
*/
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;
#include "amdgpu_amdkfd.h"
#include "amdgpu_ras.h"
+#include "amdgpu_xgmi.h"
/*
* KMS wrapper.
int amdgpu_reset_method = -1; /* auto */
int amdgpu_num_kcq = -1;
+static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
+
struct amdgpu_mgpu_info mgpu_info = {
.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
+ .delayed_reset_work = __DELAYED_WORK_INITIALIZER(
+ mgpu_info.delayed_reset_work,
+ amdgpu_drv_delayed_reset_work_handler, 0),
};
int amdgpu_ras_enable = -1;
uint amdgpu_ras_mask = 0xffffffff;
adev->mp1_state = PP_MP1_STATE_NONE;
}
+/**
+ * amdgpu_drv_delayed_reset_work_handler - work handler for reset
+ *
+ * @work: work_struct.
+ */
+static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work)
+{
+ struct list_head device_list;
+ struct amdgpu_device *adev;
+ int i, r;
+ bool need_full_reset = true;
+
+ mutex_lock(&mgpu_info.mutex);
+ if (mgpu_info.pending_reset == true) {
+ mutex_unlock(&mgpu_info.mutex);
+ return;
+ }
+ mgpu_info.pending_reset = true;
+ mutex_unlock(&mgpu_info.mutex);
+
+ for (i = 0; i < mgpu_info.num_dgpu; i++) {
+ adev = mgpu_info.gpu_ins[i].adev;
+ r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset);
+ if (r) {
+ dev_err(adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
+ r, adev_to_drm(adev)->unique);
+ }
+ if (!queue_work(system_unbound_wq, &adev->xgmi_reset_work))
+ r = -EALREADY;
+ }
+ for (i = 0; i < mgpu_info.num_dgpu; i++) {
+ adev = mgpu_info.gpu_ins[i].adev;
+ adev->gmc.xgmi.pending_reset = false;
+ flush_work(&adev->xgmi_reset_work);
+ }
+
+ /* reset function will rebuild the xgmi hive info , clear it now */
+ for (i = 0; i < mgpu_info.num_dgpu; i++)
+ amdgpu_xgmi_remove_device(mgpu_info.gpu_ins[i].adev);
+
+ INIT_LIST_HEAD(&device_list);
+
+ for (i = 0; i < mgpu_info.num_dgpu; i++)
+ list_add_tail(&mgpu_info.gpu_ins[i].adev->reset_list, &device_list);
+
+ /* unregister the GPU first, reset function will add them back */
+ list_for_each_entry(adev, &device_list, reset_list)
+ amdgpu_unregister_gpu_instance(adev);
+
+ r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true);
+ if (r) {
+ DRM_ERROR("reinit gpus failure");
+ return;
+ }
+ for (i = 0; i < mgpu_info.num_dgpu; i++) {
+ adev = mgpu_info.gpu_ins[i].adev;
+ if (!adev->kfd.init_complete)
+ amdgpu_amdkfd_device_init(adev);
+ amdgpu_ttm_set_buffer_funcs_status(adev, true);
+ }
+ return;
+}
+
static int amdgpu_pmops_suspend(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);