Re: [PATCH v3 4/4] drm/xe/sysctrl: Add RAS error injection debugfs interface

[Anoop Vijay <anoop.c.vijay@intel.com>]

On 08-08-2026 00:19, Rodrigo Vivi wrote:
> On Fri, Aug 07, 2026 at 11:15:59AM -0400, Gupta, Anshuman wrote:
>>
>>> -----Original Message-----
>>> From: Vijay, Anoop C <anoop.c.vijay@intel.com>
>>> Sent: Friday, August 7, 2026 8:26 PM
>>> To: intel-xe@lists.freedesktop.org
>>> Cc: Nerlige Ramappa, Umesh <umesh.nerlige.ramappa@intel.com>; Nilawar,
>>> Badal <badal.nilawar@intel.com>; Vivi, Rodrigo <rodrigo.vivi@intel.com>;
>>> Iddamsetty, Aravind <aravind.iddamsetty@intel.com>; Tauro, Riana
>>> <riana.tauro@intel.com>; Gupta, Anshuman <anshuman.gupta@intel.com>;
>>> Roper, Matthew D <matthew.d.roper@intel.com>; Ruhl, Michael J
>>> <michael.j.ruhl@intel.com>; Luse, Paul E <paul.e.luse@intel.com>; V,
>>> Mohamed Mansoor <mohamed.mansoor.v@intel.com>; Nasim, Kam
>>> <kam.nasim@intel.com>; Vijay, Anoop C <anoop.c.vijay@intel.com>
>>> Subject: [PATCH v3 4/4] drm/xe/sysctrl: Add RAS error injection debugfs
>>> interface
>>>
>>> From: Anoop Vijay <anoop.c.vijay@intel.com>
>>>
>>> Add debugfs interface for exercising System Controller's RAS error injection
>>> command, used to validate RAS error detection and recovery paths.
>>>
>>> Command details:
>>> - Group ID: 0x02 (diag group)
>>> - Command ID: 0x7E (XE_SYSCTRL_CMD_DIAG_RAS_ERR_INJECT)
>>> - Usage: echo "<ras_block_id> <ras_sub_block_id> <err_type> [params]" \
>>>               > /sys/kernel/debug/dri/0/sc/ras_error_inject
>>>           cat /sys/kernel/debug/dri/0/sc/ras_error_inject
>>>
>>> This command requires the diag application to have completed firmware
>>> boot and initialization (late-bind loaded); writes are rejected with -ENODEV
>>> until xe_sysctrl_is_diag_fw_ready() reports the diag firmware as ready.
>>>
>>> Signed-off-by: Anoop Vijay <anoop.c.vijay@intel.com>
>>> ---
>>>   drivers/gpu/drm/xe/xe_sysctrl_debugfs.c       | 123 ++++++++++++++++++
>>>   drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |  31 +++++
>>>   drivers/gpu/drm/xe/xe_sysctrl_types.h         |   3 +
>>>   3 files changed, 157 insertions(+)
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
>>> b/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
>>> index 2144d9d43fba..7b8846d739cb 100644
>>> --- a/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
>>> +++ b/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
>>> @@ -10,6 +10,7 @@
>>>   #include <linux/seq_file.h>
>>>   #include <linux/slab.h>
>>>   #include <linux/string.h>
>>> +#include <linux/string_choices.h>
>>>   #include <linux/uaccess.h>
>>>
>>>   #include "xe_device.h"
>>> @@ -122,6 +123,124 @@ static const struct file_operations
>>> xe_sysctrl_loopback_fops = {
>>>   	.release = single_release,
>>>   };
>>>
>>> +static ssize_t xe_sysctrl_ras_error_inject_write(struct file *file, const char
>>> __user *ubuf,
>>> +						 size_t len, loff_t *offp)
>>> +{
>>> +	char *kbuf __free(kfree) = NULL;
>>> +	struct seq_file *m = file->private_data;
>>> +	struct xe_sysctrl_debugfs_entry *entry = m->private;
>>> +	struct xe_device *xe = sc_to_xe(entry->sc);
>>> +	struct xe_sysctrl_diag_ras_err_inj_req req = {};
>>> +	struct xe_sysctrl_mailbox_command cmd = {};
>>> +	u8 resp_hdr_only[sizeof(u32)];
>>> +	unsigned int nfields = 0;
>>> +	char *token, *tmp;
>>> +	unsigned long val;
>>> +	size_t out_len = 0;
>>> +
>>> +	if (!xe_sysctrl_is_diag_fw_ready(xe)) {
>>> +		xe_err(xe, "sysctrl: diag firmware not ready, cannot inject RAS
>>> error\n");
>> Wild thought,
>> How it would be register the debugfs only if  diag firmware is loaded ?
>> That way nobody will be having access to these debugfs ?
> I agree with this. It is better not even register the file if the
> firmware is not loaded. So it doesn't even appear in the filesystem.
Unlike oCode, diag firmware initialization is not driven by KMD and can 
complete asynchronously. We don't have a notification from SysCtrl when 
diag firmware app becomes ready.

Since xe_sysctrl_check_app_status() is a lightweight synchronous query 
that always reflects current firmware state, a possible middle ground 
would be to move the readiness check to .open() rather than .write(). 
This would cause both cat and echo to fail with -ENODEV until diag 
firmware is initialized.

The file would remain visible under sc/, but would be inaccessible until 
the firmware is ready.

Would that be an acceptable compromise, or would you still prefer the 
entry to remain hidden until diag firmware is loaded?
>> Thanks,
>> Anshuman.
>>
>>> +		return -ENODEV;
>>> +	}
>>> +
>>> +	if (len == 0 || len >= PAGE_SIZE)
>>> +		return -EINVAL;
>>> +
>>> +	kbuf = kmalloc(len + 1, GFP_KERNEL);
>>> +	if (!kbuf)
>>> +		return -ENOMEM;
>>> +
>>> +	if (copy_from_user(kbuf, ubuf, len))
>>> +		return -EFAULT;
>>> +	kbuf[len] = '\0';
>>> +
>>> +	tmp = kbuf;
>>> +	while ((token = strsep(&tmp, " \t\n")) != NULL) {
>>> +		if (*token == '\0')
>>> +			continue;
>>> +
>>> +		if (kstrtoul(token, 0, &val))
>>> +			goto inval;
>>> +
>>> +		switch (nfields) {
>>> +		case 0:
>>> +			if (val > U16_MAX)
>>> +				goto inval;
>>> +			req.ras_block_id = val;
>>> +			break;
>>> +		case 1:
>>> +			if (val > U16_MAX)
>>> +				goto inval;
>>> +			req.ras_sub_block_id = val;
>>> +			break;
>>> +		case 2:
>>> +			if (val > U16_MAX)
>>> +				goto inval;
>>> +			req.err_type = val;
>>> +			break;
>>> +		case 3:
>>> +			if (val > U32_MAX)
>>> +				goto inval;
>>> +			req.params = val;
>>> +			break;
>>> +		default:
>>> +			xe_err(xe, "sysctrl: too many ras_error_inject
>>> arguments\n");
>>> +			return -EINVAL;
>>> +		}
>>> +		nfields++;
>>> +	}
>>> +
>>> +	if (nfields < 3) {
>>> +		xe_err(xe,
>>> +		       "sysctrl: usage: <ras_block_id> <ras_sub_block_id>
>>> <err_type> [params]\n");
>>> +		return -EINVAL;
>>> +	}
>>> +
>>> +	xe_sysctrl_create_command(&cmd, entry->group, entry->command,
>>> +				  &req, sizeof(req), resp_hdr_only,
>>> +				  sizeof(resp_hdr_only));
>>> +
>>> +	guard(xe_pm_runtime)(xe);
>>> +	entry->status = xe_sysctrl_send_command(entry->sc, &cmd,
>>> &out_len);
>>> +
>>> +	return entry->status ? entry->status : len;
>>> +
>>> +inval:
>>> +	xe_err(xe, "sysctrl: invalid ras_error_inject token '%s'\n", token);
>>> +	return -EINVAL;
>>> +}
>>> +
>>> +static int xe_sysctrl_ras_error_inject_show(struct seq_file *m, void
>>> +*data) {
>>> +	struct xe_sysctrl_debugfs_entry *entry = m->private;
>>> +	struct xe_device *xe = sc_to_xe(entry->sc);
>>> +
>>> +	seq_printf(m, "Command: group=0x%02x cmd=0x%02x\n", entry-
>>>> group, entry->command);
>>> +	seq_printf(m, "Diag firmware ready: %s\n",
>>> +		   str_yes_no(xe_sysctrl_is_diag_fw_ready(xe)));
>>> +	seq_printf(m, "Status: %d (%s)\n", entry->status, entry->status ?
>>> +"FAILED" : "SUCCESS");
>>> +
>>> +	seq_puts(m, "\nUsage:\n");
>>> +	seq_puts(m, "  echo \"<ras_block_id> <ras_sub_block_id>
>>> <err_type> [params]\" > ras_error_inject\n");
>>> +	seq_puts(m, "  cat ras_error_inject\n");
>>> +
>>> +	return 0;
>>> +}
>>> +
>>> +static int xe_sysctrl_ras_error_inject_open(struct inode *inode, struct
>>> +file *file) {
>>> +	return single_open(file, xe_sysctrl_ras_error_inject_show,
>>> +inode->i_private); }
>>> +
>>> +static const struct file_operations xe_sysctrl_ras_error_inject_fops = {
>>> +	.owner = THIS_MODULE,
>>> +	.open = xe_sysctrl_ras_error_inject_open,
>>> +	.read = seq_read,
>>> +	.write = xe_sysctrl_ras_error_inject_write,
>>> +	.llseek = seq_lseek,
>>> +	.release = single_release,
>>> +};
>>> +
>>>   static void xe_sysctrl_register_entry(struct dentry *root, struct
>>> xe_sysctrl_debugfs_entry *entry,
>>>   				      struct xe_sysctrl *sc, const char *name,
>>>   				      u8 group, u8 command,
>>> @@ -154,4 +273,8 @@ void xe_sysctrl_debugfs_register(struct xe_sysctrl
>>> *sc, struct dentry *parent)
>>>   	xe_sysctrl_register_entry(root, &sc->debugfs.loopback, sc,
>>> "loopback",
>>>   				  XE_SYSCTRL_GROUP_CORE,
>>> XE_SYSCTRL_CMD_LOOPBACK,
>>>   				  &xe_sysctrl_loopback_fops);
>>> +
>>> +	xe_sysctrl_register_entry(root, &sc->debugfs.ras_error_inject, sc,
>>> "ras_error_inject",
>>> +				  XE_SYSCTRL_GROUP_DIAG,
>>> XE_SYSCTRL_CMD_DIAG_RAS_ERR_INJECT,
>>> +				  &xe_sysctrl_ras_error_inject_fops);
>>>   }
>>> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
>>> b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
>>> index ed80fe63e1c4..43ae0049b316 100644
>>> --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
>>> +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
>>> @@ -14,10 +14,12 @@
>>>    * enum xe_sysctrl_group - System Controller command groups
>>>    *
>>>    * @XE_SYSCTRL_GROUP_GFSP: GFSP group
>>> + * @XE_SYSCTRL_GROUP_DIAG: Diag group
>>>    * @XE_SYSCTRL_GROUP_CORE: Core group
>>>    */
>>>   enum xe_sysctrl_group {
>>>   	XE_SYSCTRL_GROUP_GFSP			= 0x01,
>>> +	XE_SYSCTRL_GROUP_DIAG			= 0x02,
>>>   	XE_SYSCTRL_GROUP_CORE			= 0xFF,
>>>   };
>>>
>>> @@ -51,6 +53,35 @@ enum xe_sysctrl_core_cmd {
>>>   	XE_SYSCTRL_CMD_GET_APP_STATUS_BY_ID		= 0x05,
>>>   };
>>>
>>> +/**
>>> + * enum xe_sysctrl_diag_cmd - Commands supported by Diag group
>>> + *
>>> + * @XE_SYSCTRL_CMD_DIAG_RAS_ERR_INJECT: RAS error injection  */
>>> enum
>>> +xe_sysctrl_diag_cmd {
>>> +	XE_SYSCTRL_CMD_DIAG_RAS_ERR_INJECT		= 0x7E,
>>> +};
>>> +
>>> +/**
>>> + * struct xe_sysctrl_diag_ras_err_inj_req - DIAG_RAS_ERR_INJECT request
>>> +payload
>>> + *
>>> + * Request payload for XE_SYSCTRL_CMD_DIAG_RAS_ERR_INJECT. The
>>> mailbox
>>> +layer
>>> + * prepends the application message header before sending.
>>> + *
>>> + * @ras_block_id: RAS block (subsystem) to inject the error into
>>> + * @ras_sub_block_id: RAS sub-block (IP) within @ras_block_id
>>> + * @err_type: Type of test error to inject
>>> + * @reserved: Must be zero
>>> + * @params: Optional injection parameters (default 0)  */ struct
>>> +xe_sysctrl_diag_ras_err_inj_req {
>>> +	u16 ras_block_id;
>>> +	u16 ras_sub_block_id;
>>> +	u16 err_type;
>>> +	u16 reserved;
>>> +	u32 params;
>>> +} __packed;
>>> +
>>>   /**
>>>    * struct xe_sysctrl_app_status_req - Get application status request
>>>    *
>>> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h
>>> b/drivers/gpu/drm/xe/xe_sysctrl_types.h
>>> index 53d82e61383a..3a97a10d1b7d 100644
>>> --- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
>>> +++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
>>> @@ -68,6 +68,9 @@ struct xe_sysctrl {
>>>
>>>   		/** @debugfs.loopback: Loopback test entry */
>>>   		struct xe_sysctrl_debugfs_entry loopback;
>>> +
>>> +		/** @debugfs.ras_error_inject: RAS error injection test entry
>>> */
>>> +		struct xe_sysctrl_debugfs_entry ras_error_inject;
>>>   	} debugfs;
>>>   };
>>>
>>> --
>>> 2.43.0