[PATCH v12 1/2] drm/amdgpu: add debugfs for reset registers list

[Christian König]

Am 22.02.22 um 16:34 schrieb Somalapuram Amaranath:
> List of register populated for dump collection during the GPU reset.
>
> Signed-off-by: Somalapuram Amaranath <Amaranath.Somalapuram at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h         |  4 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 83 +++++++++++++++++++++
>   2 files changed, 87 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index b85b67a88a3d..6e35f2c4c869 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1097,6 +1097,10 @@ struct amdgpu_device {
>   
>   	struct amdgpu_reset_control     *reset_cntl;
>   	uint32_t                        ip_versions[HW_ID_MAX][HWIP_MAX_INSTANCE];
> +
> +	/* reset dump register */
> +	uint32_t			*reset_dump_reg_list;
> +	int                             num_regs;
>   };
>   
>   static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> index 164d6a9e9fbb..0cc80aa1b5ec 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -1609,6 +1609,87 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_ib_preempt, NULL,
>   DEFINE_DEBUGFS_ATTRIBUTE(fops_sclk_set, NULL,
>   			amdgpu_debugfs_sclk_set, "%llu\n");
>   
> +static ssize_t amdgpu_reset_dump_register_list_read(struct file *f,
> +				char __user *buf, size_t size, loff_t *pos)
> +{
> +	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
> +	char reg_offset[11];
> +	int i, ret, len = 0;
> +
> +	if (*pos)
> +		return 0;
> +
> +	ret = down_read_killable(&adev->reset_sem);
> +	if (ret)
> +		return ret;
> +
> +	for (i = 0; i < adev->num_regs; i++) {
> +		sprintf(reg_offset, "0x%x\n", adev->reset_dump_reg_list[i]);
> +		up_read(&adev->reset_sem);
> +		ret = copy_to_user(buf + len, reg_offset, strlen(reg_offset));
> +		if (ret)
> +			return -EFAULT;
> +
> +		len += strlen(reg_offset);
> +		ret = down_read_killable(&adev->reset_sem);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	up_read(&adev->reset_sem);
> +	if (ret)
> +		return ret;

That if and return now looks superfluous.

> +
> +	*pos += len;
> +
> +	return len;
> +}
> +
> +static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
> +			const char __user *buf, size_t size, loff_t *pos)
> +{
> +	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
> +	char reg_offset[12];
> +	uint32_t *tmp;
> +	int ret, i = 0, len = 0;
> +
> +	do {
> +		memset(reg_offset, 0, 12);
> +		if (copy_from_user(reg_offset, buf + len,
> +					min(11, ((int)size-len)))) {
> +			ret = -EFAULT;
> +			goto error_free;
> +		}
> +
> +		tmp = krealloc_array(tmp, i + 1, sizeof(uint32_t), GFP_KERNEL);
> +		if (sscanf(reg_offset, "%X %n", &tmp[i], &ret) != 1)

Does this also work when we write the registers separated with newlines 
into the debugfs file?

Regards,
Christian.

> +			goto error_free;
> +
> +		len += ret;
> +		i++;
> +	} while (len < size);
> +
> +	ret = down_write_killable(&adev->reset_sem);
> +	if (ret)
> +		goto error_free;
> +
> +	swap(adev->reset_dump_reg_list, tmp);
> +	adev->num_regs = i;
> +	up_write(&adev->reset_sem);
> +	ret = size;
> +
> +error_free:
> +	kfree(tmp);
> +	return ret;
> +}
> +
> +static const struct file_operations amdgpu_reset_dump_register_list = {
> +	.owner = THIS_MODULE,
> +	.read = amdgpu_reset_dump_register_list_read,
> +	.write = amdgpu_reset_dump_register_list_write,
> +	.llseek = default_llseek
> +};
> +
>   int amdgpu_debugfs_init(struct amdgpu_device *adev)
>   {
>   	struct dentry *root = adev_to_drm(adev)->primary->debugfs_root;
> @@ -1672,6 +1753,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
>   			    &amdgpu_debugfs_test_ib_fops);
>   	debugfs_create_file("amdgpu_vm_info", 0444, root, adev,
>   			    &amdgpu_debugfs_vm_info_fops);
> +	debugfs_create_file("amdgpu_reset_dump_register_list", 0644, root, adev,
> +			    &amdgpu_reset_dump_register_list);
>   
>   	adev->debugfs_vbios_blob.data = adev->bios;
>   	adev->debugfs_vbios_blob.size = adev->bios_size;