Re: [PATCH 3/6] drm/amdgpu: Rework coredump to use memory dynamically

Christian König <christian.koenig@xxxxxxx> · Wed, 12 Jul 2023 10:37:51 +0200

Am 11.07.23 um 23:34 schrieb André Almeida:
Instead of storing coredump information inside amdgpu_device struct,
move if to a proper separated struct and allocate it dynamically. This
will make it easier to further expand the logged information.

Verry big NAK to this. The problem is that memory allocation isn't 
allowed during a GPU reset.

What you could do is to allocate the memory with GFP_ATOMIC or similar, 
but for a large structure that might not be possible.

Regards,
Christian.


Signed-off-by: André Almeida <andrealmeid@xxxxxxxxxx>
---
  drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 14 +++--
  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 65 ++++++++++++++--------
  2 files changed, 51 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index dbe062a087c5..e1cc83a89d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1068,11 +1068,6 @@ struct amdgpu_device {
  	uint32_t                        *reset_dump_reg_list;
  	uint32_t			*reset_dump_reg_value;
  	int                             num_regs;
-#ifdef CONFIG_DEV_COREDUMP
-	struct amdgpu_task_info         reset_task_info;
-	bool                            reset_vram_lost;
-	struct timespec64               reset_time;
-#endif
  
  	bool                            scpm_enabled;
  	uint32_t                        scpm_status;
@@ -1085,6 +1080,15 @@ struct amdgpu_device {
  	uint32_t			aid_mask;
  };
  
+#ifdef CONFIG_DEV_COREDUMP
+struct amdgpu_coredump_info {
+	struct amdgpu_device		*adev;
+	struct amdgpu_task_info         reset_task_info;
+	struct timespec64               reset_time;
+	bool                            reset_vram_lost;
+};
+#endif
+
  static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
  {
  	return container_of(ddev, struct amdgpu_device, ddev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e25f085ee886..23b9784e9787 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4963,12 +4963,17 @@ static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
  	return 0;
  }
  
-#ifdef CONFIG_DEV_COREDUMP
+#ifndef CONFIG_DEV_COREDUMP
+static void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
+			    struct amdgpu_reset_context *reset_context)
+{
+}
+#else
  static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
  		size_t count, void *data, size_t datalen)
  {
  	struct drm_printer p;
-	struct amdgpu_device *adev = data;
+	struct amdgpu_coredump_info *coredump = data;
  	struct drm_print_iterator iter;
  	int i;
  
@@ -4982,21 +4987,21 @@ static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
  	drm_printf(&p, "**** AMDGPU Device Coredump ****\n");
  	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
  	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
-	drm_printf(&p, "time: %lld.%09ld\n", adev->reset_time.tv_sec, adev->reset_time.tv_nsec);
-	if (adev->reset_task_info.pid)
+	drm_printf(&p, "time: %lld.%09ld\n", coredump->reset_time.tv_sec, coredump->reset_time.tv_nsec);
+	if (coredump->reset_task_info.pid)
  		drm_printf(&p, "process_name: %s PID: %d\n",
-			   adev->reset_task_info.process_name,
-			   adev->reset_task_info.pid);
+			   coredump->reset_task_info.process_name,
+			   coredump->reset_task_info.pid);
  
-	if (adev->reset_vram_lost)
+	if (coredump->reset_vram_lost)
  		drm_printf(&p, "VRAM is lost due to GPU reset!\n");
-	if (adev->num_regs) {
+	if (coredump->adev->num_regs) {
  		drm_printf(&p, "AMDGPU register dumps:\nOffset:     Value:\n");
  
-		for (i = 0; i < adev->num_regs; i++)
+		for (i = 0; i < coredump->adev->num_regs; i++)
  			drm_printf(&p, "0x%08x: 0x%08x\n",
-				   adev->reset_dump_reg_list[i],
-				   adev->reset_dump_reg_value[i]);
+				   coredump->adev->reset_dump_reg_list[i],
+				   coredump->adev->reset_dump_reg_value[i]);
  	}
  
  	return count - iter.remain;
@@ -5004,14 +5009,34 @@ static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
  
  static void amdgpu_devcoredump_free(void *data)
  {
+	kfree(data);
  }
  
-static void amdgpu_reset_capture_coredumpm(struct amdgpu_device *adev)
+static void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
+			    struct amdgpu_reset_context *reset_context)
  {
+	struct amdgpu_coredump_info *coredump;
  	struct drm_device *dev = adev_to_drm(adev);
  
-	ktime_get_ts64(&adev->reset_time);
-	dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_KERNEL,
+	coredump = kmalloc(sizeof(*coredump), GFP_KERNEL);
+
+	if (!coredump) {
+		DRM_ERROR("%s: failed to allocate memory for coredump\n", __func__);
+		return;
+	}
+
+	memset(coredump, 0, sizeof(*coredump));
+
+	coredump->reset_vram_lost = vram_lost;
+
+	if (reset_context->job && reset_context->job->vm)
+		coredump->reset_task_info = reset_context->job->vm->task_info;
+
+	coredump->adev = adev;
+
+	ktime_get_ts64(&coredump->reset_time);
+
+	dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_KERNEL,
  		      amdgpu_devcoredump_read, amdgpu_devcoredump_free);
  }
  #endif
@@ -5119,15 +5144,9 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
  					goto out;
  
  				vram_lost = amdgpu_device_check_vram_lost(tmp_adev);
-#ifdef CONFIG_DEV_COREDUMP
-				tmp_adev->reset_vram_lost = vram_lost;
-				memset(&tmp_adev->reset_task_info, 0,
-						sizeof(tmp_adev->reset_task_info));
-				if (reset_context->job && reset_context->job->vm)
-					tmp_adev->reset_task_info =
-						reset_context->job->vm->task_info;
-				amdgpu_reset_capture_coredumpm(tmp_adev);
-#endif
+
+				amdgpu_coredump(tmp_adev, vram_lost, reset_context);
+
  				if (vram_lost) {
  					DRM_INFO("VRAM is lost due to GPU reset!\n");
  					amdgpu_inc_vram_lost(tmp_adev);







