[PATCH] drm/amdgpu: refine reboot debugfs operation in ras case

Deucher, Alexander Alexander.Deucher at amd.com
Mon Oct 21 15:40:52 UTC 2019


> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of
> Chen, Guchun
> Sent: Monday, October 21, 2019 5:33 AM
> To: amd-gfx at lists.freedesktop.org; Koenig, Christian
> <Christian.Koenig at amd.com>; Zhang, Hawking
> <Hawking.Zhang at amd.com>; Li, Dennis <Dennis.Li at amd.com>;
> Grodzovsky, Andrey <Andrey.Grodzovsky at amd.com>; Zhou1, Tao
> <Tao.Zhou1 at amd.com>
> Cc: Li, Candice <Candice.Li at amd.com>; Chen, Guchun
> <Guchun.Chen at amd.com>
> Subject: [PATCH] drm/amdgpu: refine reboot debugfs operation in ras case
> 
> Ras reboot debugfs node allows user one easy control to avoid gpu recovery
> hang problem and directly reboot system per card basis, after ras
> uncorrectable error happens. However, it is one common entry, which
> should get rid of ras_ctrl node and remove ip dependence when inputting by
> user. So add one new auto_reboot node in ras debugfs dir to achieve this.
> 
> v2: in commit mssage, add justification why ras reboot debugfs node is
> needed.
> 
> Signed-off-by: Guchun Chen <guchun.chen at amd.com>

Reviewed-by: Alex Deucher <alexander.deucher at amd.com>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 57
> ++++++++++++++++++++++---
>  1 file changed, 50 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 6220394521e4..6450065b88de 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -153,8 +153,6 @@ 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;
> @@ -218,12 +216,11 @@ static struct ras_manager
> *amdgpu_ras_find_obj(struct amdgpu_device *adev,
>   * value to the address.
>   *
>   * Second member: struct ras_debug_if::op.
> - * It has four kinds of operations.
> + * It has three kinds of operations.
>   *
>   * - 0: disable RAS on the block. Take ::head as its data.
>   * - 1: enable RAS on the block. Take ::head as its data.
>   * - 2: inject errors on the block. Take ::inject as its data.
> - * - 3: reboot on unrecoverable error
>   *
>   * How to use the interface?
>   * programs:
> @@ -305,9 +302,6 @@ 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;
> @@ -346,6 +340,46 @@ static ssize_t
> amdgpu_ras_debugfs_eeprom_write(struct file *f, const char __user
>  	return ret == 1 ? size : -EIO;
>  }
> 
> +/**
> + * DOC: AMDGPU RAS debugfs auto reboot interface
> + *
> + * After one uncorrectable error happens, GPU recovery will be scheduled.
> + * Due to the known problem in GPU recovery failing to bring GPU back,
> +this
> + * interface provides one direct way to user to reboot system
> +automatically
> + * in such case within ERREVENT_ATHUB_INTERRUPT generated. Normal
> GPU
> +recovery
> + * routine will never be called.
> + *
> + * Enable auto_reboot:
> + *
> + *	echo 1 > /sys/kernel/debug/dri/x/ras/auto_reboot
> + *
> + * Revert auto_reboot:
> + *
> + * 	echo 0 > /sys/kernel/debug/dri/x/ras/auto_reboot
> + *
> + */
> +static ssize_t amdgpu_ras_debugfs_reboot_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 tmp[8] = {0};
> +	int value = -1;
> +
> +	if (size != simple_write_to_buffer(tmp, sizeof(tmp), pos, buf, size))
> +		return -EINVAL;
> +
> +	if (kstrtoint(tmp, 10, &value))
> +		return -EINVAL;
> +
> +	if (value == 1)
> +		amdgpu_ras_get_context(adev)->reboot = true;
> +	else if (value == 0)
> +		amdgpu_ras_get_context(adev)->reboot = false;
> +
> +	return size;
> +}
> +
>  static const struct file_operations amdgpu_ras_debugfs_ctrl_ops = {
>  	.owner = THIS_MODULE,
>  	.read = NULL,
> @@ -360,6 +394,13 @@ static const struct file_operations
> amdgpu_ras_debugfs_eeprom_ops = {
>  	.llseek = default_llseek
>  };
> 
> +static const struct file_operations amdgpu_ras_debugfs_reboot_ops = {
> +	.owner = THIS_MODULE,
> +	.read = NULL,
> +	.write = amdgpu_ras_debugfs_reboot_write,
> +	.llseek = default_llseek
> +};
> +
>  /**
>   * DOC: AMDGPU RAS sysfs Error Count Interface
>   *
> @@ -1037,6 +1078,8 @@ static void
> amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
>  				adev, &amdgpu_ras_debugfs_ctrl_ops);
>  	debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO,
> con->dir,
>  				adev, &amdgpu_ras_debugfs_eeprom_ops);
> +	debugfs_create_file("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
> +				adev, &amdgpu_ras_debugfs_reboot_ops);
>  }
> 
>  void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
> --
> 2.17.1
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx


More information about the amd-gfx mailing list