Re: [PATCH v6 2/3] drm/xe/sysctrl: Add system controller event support

["Tauro, Riana" <riana.tauro@intel.com>]

On 4/10/2026 3:57 PM, Raag Jadav wrote:
> System controller reports different types of events to GFX endpoint for
> different usecases, add initial support for them. This will be further
> extended to service those usecases.
>
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> ---
> v2: Handle unexpected response length (Mallesh)
> v3: Handle event flood (Mallesh)
> v6: Drop xe prefix from static functions (Riana)
>      Don't fail on unexpected event (Riana)
>      Move sysctrl commands to xe_sysctrl_mailbox_types.h (Riana)
>      Add kernel doc (Riana)
> ---
>   drivers/gpu/drm/xe/Makefile                   |  1 +
>   drivers/gpu/drm/xe/xe_sysctrl.c               | 11 +++
>   drivers/gpu/drm/xe/xe_sysctrl.h               |  1 +
>   drivers/gpu/drm/xe/xe_sysctrl_event.c         | 84 +++++++++++++++++++
>   drivers/gpu/drm/xe/xe_sysctrl_event_types.h   | 57 +++++++++++++
>   drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h | 18 ++++
>   drivers/gpu/drm/xe/xe_sysctrl_types.h         |  3 +
>   7 files changed, 175 insertions(+)
>   create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event.c
>   create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event_types.h
>
> diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
> index 7f03f06df186..9e6689c86797 100644
> --- a/drivers/gpu/drm/xe/Makefile
> +++ b/drivers/gpu/drm/xe/Makefile
> @@ -125,6 +125,7 @@ xe-y += xe_bb.o \
>   	xe_survivability_mode.o \
>   	xe_sync.o \
>   	xe_sysctrl.o \
> +	xe_sysctrl_event.o \
>   	xe_sysctrl_mailbox.o \
>   	xe_tile.o \
>   	xe_tile_sysfs.o \
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
> index 72ce0822cc6d..8fd791047f0a 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl.c
> +++ b/drivers/gpu/drm/xe/xe_sysctrl.c
> @@ -12,6 +12,7 @@
>   #include "regs/xe_sysctrl_regs.h"
>   #include "xe_device.h"
>   #include "xe_mmio.h"
> +#include "xe_pm.h"
>   #include "xe_soc_remapper.h"
>   #include "xe_sysctrl.h"
>   #include "xe_sysctrl_mailbox.h"
> @@ -39,6 +40,12 @@ static void sysctrl_fini(void *arg)
>   
>   static void xe_sysctrl_work(struct work_struct *work)
>   {
> +	struct xe_sysctrl *sc = container_of(work, struct xe_sysctrl, work);
> +	struct xe_device *xe = sc_to_xe(sc);
> +
> +	guard(xe_pm_runtime)(xe);
> +	guard(mutex)(&sc->work_lock);
> +	xe_sysctrl_event(sc);
>   }
>   
>   /**
> @@ -74,6 +81,10 @@ int xe_sysctrl_init(struct xe_device *xe)
>   	if (ret)
>   		return ret;
>   
> +	ret = devm_mutex_init(xe->drm.dev, &sc->work_lock);
> +	if (ret)
> +		return ret;
> +
>   	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
>   	xe_sysctrl_mailbox_init(sc);
>   	INIT_WORK(&sc->work, xe_sysctrl_work);
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl.h b/drivers/gpu/drm/xe/xe_sysctrl.h
> index f7469bfc9324..090dffb6d55f 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl.h
> @@ -16,6 +16,7 @@ static inline struct xe_device *sc_to_xe(struct xe_sysctrl *sc)
>   	return container_of(sc, struct xe_device, sc);
>   }
>   
> +void xe_sysctrl_event(struct xe_sysctrl *sc);
>   int xe_sysctrl_init(struct xe_device *xe);
>   void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl);
>   void xe_sysctrl_pm_resume(struct xe_device *xe);
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event.c b/drivers/gpu/drm/xe/xe_sysctrl_event.c
> new file mode 100644
> index 000000000000..3edde46a9711
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_event.c
> @@ -0,0 +1,84 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2026 Intel Corporation
> + */
> +
> +#include "xe_device.h"
> +#include "xe_irq.h"
> +#include "xe_printk.h"
> +#include "xe_sysctrl.h"
> +#include "xe_sysctrl_event_types.h"
> +#include "xe_sysctrl_mailbox.h"
> +#include "xe_sysctrl_mailbox_types.h"
> +
> +static void get_pending_event(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_command *command)
> +{
> +	struct xe_sysctrl_event_response *response = command->data_out;
> +	struct xe_device *xe = sc_to_xe(sc);
> +	u32 count = XE_SYSCTRL_EVENT_FLOOD;
> +	size_t len;
> +	int ret;
> +
> +	do {
> +		memset(response, 0, sizeof(*response));
> +
> +		ret = xe_sysctrl_send_command(sc, command, &len);
> +		if (ret) {
> +			xe_err(xe, "sysctrl: failed to get pending event %d\n", ret);
> +			return;
> +		}
> +
> +		if (len != sizeof(*response)) {
> +			xe_err(xe, "sysctrl: unexpected event response length %zu\n", len);

Let's keep error logs consistent across patches. Since multiple people 
are working on different patches
I found these logs better from the threshold series
[v1,08/11] drm/xe/ras: Get error threshold support - Patchwork 
<https://patchwork.freedesktop.org/patch/719221/?series=165091&rev=1>

Example:

xe_err(xe, "sysctrl: get threshold  failed %d\n", ret);

xe_err(xe, "sysctrl: unexpected get threshold response size%zu (expected 
%zu)\n",
            len, sizeof(response));

Let me know if this works. I'll incorporate the same in my patches

> +			return;
> +		}
> +
> +		if (response->event == XE_SYSCTRL_EVENT_THRESHOLD_CROSSED)
> +			xe_warn(xe, "[RAS]: counter threshold crossed\n");
> +		else
> +			xe_err(xe, "sysctrl: unexpected event %#x\n", response->event);
> +
> +		if (!--count) {
> +			xe_err(xe, "sysctrl: event flooding\n");
> +			return;
> +		}
> +
> +		xe_dbg(xe, "sysctrl: %u events pending\n", response->count);
> +	} while (response->count);
> +}
> +
> +static void event_request_prep(struct xe_device *xe, struct xe_sysctrl_app_msg_hdr *header,
> +			       struct xe_sysctrl_event_request *request)
> +{
> +	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> +
> +	header->data = REG_FIELD_PREP(APP_HDR_GROUP_ID_MASK, XE_SYSCTRL_GROUP_GFSP) |
> +		       REG_FIELD_PREP(APP_HDR_COMMAND_MASK, XE_SYSCTRL_CMD_GET_PENDING_EVENT);
> +
> +	request->vector = xe_device_has_msix(xe) ? XE_IRQ_DEFAULT_MSIX : 0;
> +	request->fn = PCI_FUNC(pdev->devfn);
> +}
> +
> +/**
> + * xe_sysctrl_event() - Handler for System Controller events
> + * @sc: System Controller instance
> + *
> + * Handle events generated by System Controller.
> + */
> +void xe_sysctrl_event(struct xe_sysctrl *sc)
> +{
> +	struct xe_sysctrl_mailbox_command command = {};
> +	struct xe_sysctrl_event_response response = {};
> +	struct xe_sysctrl_event_request request = {};
> +	struct xe_sysctrl_app_msg_hdr header = {};
> +
> +	event_request_prep(sc_to_xe(sc), &header, &request);
> +
> +	command.header = header;
> +	command.data_in = &request;
> +	command.data_in_len = sizeof(request);
> +	command.data_out = &response;
> +	command.data_out_len = sizeof(response);
> +
> +	get_pending_event(sc, &command);
> +}
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event_types.h b/drivers/gpu/drm/xe/xe_sysctrl_event_types.h
> new file mode 100644
> index 000000000000..7066d7979f4a
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_event_types.h
> @@ -0,0 +1,57 @@
> +/* SPDX-License-Identifier: MIT */
> +/*
> + * Copyright © 2026 Intel Corporation
> + */
> +
> +#ifndef _XE_SYSCTRL_EVENT_TYPES_H_
> +#define _XE_SYSCTRL_EVENT_TYPES_H_
> +
> +#include <linux/types.h>
> +
> +#define XE_SYSCTRL_EVENT_DATA_LEN		59
> +
> +/* Modify as needed */
> +#define XE_SYSCTRL_EVENT_FLOOD			16
> +
> +/**
> + * enum xe_sysctrl_event - Events reported by System Controller
> + *
> + * @XE_SYSCTRL_EVENT_THRESHOLD_CROSSED: Error counter threshold crossed
> + */
> +enum xe_sysctrl_event {
> +	XE_SYSCTRL_EVENT_THRESHOLD_CROSSED	= 0x01,
> +};
> +
> +/**
> + * struct xe_sysctrl_event_request - Request structure for pending event
> + */
> +struct xe_sysctrl_event_request {
> +	/** @vector: MSI-X vector that was triggered */
> +	u32 vector;
> +	/** @fn: Function index (0-7) of PCIe device */
> +	u32 fn:8;
> +	/** @reserved: Reserved for future use */
> +	u32 reserved:24;
> +	/** @reserved2: Reserved for future use */
> +	u32 reserved2[2];
Nit: reserved1?
> +} __packed;
> +
> +/**
> + * struct xe_sysctrl_event_response - Response structure for pending event
> + */
> +struct xe_sysctrl_event_response {
> +	/** @count: Pending event count, decremented by fw on each response */

Might not be decremented  everytime if there is a new event

Thanks
Riana

> +	u32 count;
> +	/** @event: Pending event */
> +	enum xe_sysctrl_event event;
> +	/** @timestamp: Timestamp of most recent event */
> +	u64 timestamp;
> +	/** @extended: Event has extended payload */
> +	u32 extended:1;
> +	/** @reserved: Reserved for future use */
> +	u32 reserved:31;
> +	/** @data: Generic event data */
> +	u32 data[XE_SYSCTRL_EVENT_DATA_LEN];
> +} __packed;
> +
> +#endif /* _XE_SYSCTRL_EVENT_TYPES_H_ */
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> index 89456aec6097..84d7c647e743 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> @@ -10,6 +10,24 @@
>   
>   #include "abi/xe_sysctrl_abi.h"
>   
> +/**
> + * enum xe_sysctrl_group - System Controller command groups
> + *
> + * @XE_SYSCTRL_GROUP_GFSP: GFSP group
> + */
> +enum xe_sysctrl_group {
> +	XE_SYSCTRL_GROUP_GFSP			= 0x01,
> +};
> +
> +/**
> + * enum xe_sysctrl_gfsp_cmd - Commands supported by GFSP group
> + *
> + * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
> + */
> +enum xe_sysctrl_gfsp_cmd {
> +	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
> +};
> +
>   /**
>    * struct xe_sysctrl_mailbox_command - System Controller mailbox command
>    */
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> index 5f408d6491ef..95359af691c9 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> @@ -31,6 +31,9 @@ struct xe_sysctrl {
>   
>   	/** @work: Pending events worker */
>   	struct work_struct work;
> +
> +	/** @work_lock: Mutex protecting pending events */
> +	struct mutex work_lock;
>   };
>   
>   #endif