dmr/amdgpu: Add system auto reboot to RAS.

In case of RAS error allow user configure auto system
reboot through ras_ctrl.
This is also part of the temproray work around for the RAS
hang problem.

v4: Use latest kernel API for disk sync.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 98ff987..e89aa2d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -65,6 +65,8 @@
 #include "amdgpu_ras.h"
 #include "amdgpu_pmu.h"
 
+#include <linux/suspend.h>
+
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -3769,6 +3771,18 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
        int i, r = 0;
        bool in_ras_intr = amdgpu_ras_intr_triggered();
 
+       /*
+        * Flush RAM to disk so that after reboot
+        * the user can read log and see why the system rebooted.
+        */
+       if (in_ras_intr && amdgpu_ras_get_context(adev)->reboot) {
+
+               DRM_WARN("Emergency reboot.");
+
+               ksys_sync_helper();
+               emergency_restart();
+       }
+
        need_full_reset = job_signaled = false;
        INIT_LIST_HEAD(&device_list);
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index d7bf8fc..270110d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -156,6 +156,8 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
                op = 1;
        else if (sscanf(str, "inject %32s %8s", block_name, err) == 2)
                op = 2;
+       else if (sscanf(str, "reboot %32s", block_name) == 1)
+               op = 3;
        else if (str[0] && str[1] && str[2] && str[3])
                /* ascii string, but commands are not matched. */
                return -EINVAL;
@@ -289,6 +291,9 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
                /* data.inject.address is offset instead of absolute gpu address */
                ret = amdgpu_ras_error_inject(adev, &data.inject);
                break;
+       case 3:
+               amdgpu_ras_get_context(adev)->reboot = true;
+               break;
        default:
                ret = -EINVAL;
                break;
@@ -1746,6 +1751,8 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
 void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 {
        if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
-               DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected! Stopping all GPU jobs.\n");
+               DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected!\n");
+
+               amdgpu_ras_reset_gpu(adev, false);
        }
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 6fda96b..f487038 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -334,7 +334,7 @@ struct amdgpu_ras {
        struct mutex recovery_lock;
 
        uint32_t flags;
-
+       bool reboot;
        struct amdgpu_ras_eeprom_control eeprom_control;
 };