[RFC v5 5/5] drm/xe/RAS: send multicast event on occurrence of an error

[Rodrigo Vivi]

On Wed, Jul 30, 2025 at 12:19:56PM +0530, Aravind Iddamsetty wrote:
> Whenever a correctable or an uncorrectable error happens an event is sent
> to the corresponding listeners of these groups.
> 
> v2: Rebase
> v3: protect with CONFIG_NET define.
> 
> Reviewed-by: Michael J. Ruhl <michael.j.ruhl at intel.com> #v2
> Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty at linux.intel.com>
> ---
>  drivers/gpu/drm/xe/xe_hw_error.c | 41 ++++++++++++++++++++++++++++++++
>  1 file changed, 41 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
> index bdd9c88674b2..e6e2e6250b70 100644
> --- a/drivers/gpu/drm/xe/xe_hw_error.c
> +++ b/drivers/gpu/drm/xe/xe_hw_error.c
> @@ -2,6 +2,8 @@
>  /*
>   * Copyright © 2023 Intel Corporation
>   */
> +#include <net/genetlink.h>
> +#include <uapi/drm/drm_netlink.h>
>  
>  #include "xe_gt_printk.h"
>  #include "xe_hw_error.h"
> @@ -776,6 +778,43 @@ xe_soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
>  				(HARDWARE_ERROR_MAX << 1) + 1);
>  }
>  
> +#ifdef CONFIG_NET
> +static void
> +generate_netlink_event(struct xe_device *xe, const enum hardware_error hw_err)
> +{
> +	struct sk_buff *msg;
> +	void *hdr;
> +
> +	if (!xe->drm.drm_genl_family)
> +		return;
> +
> +	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
> +	if (!msg) {
> +		drm_dbg_driver(&xe->drm, "couldn't allocate memory for error multicast event\n");
> +		return;
> +	}
> +
> +	hdr = genlmsg_put(msg, 0, 0, xe->drm.drm_genl_family, 0, DRM_RAS_CMD_ERROR_EVENT);

this is something that could be wrapped up in the drm_ras

> +	if (!hdr) {
> +		drm_dbg_driver(&xe->drm, "mutlicast msg buffer is small\n");
> +		nlmsg_free(msg);
> +		return;
> +	}
> +
> +	genlmsg_end(msg, hdr);
> +
> +	genlmsg_multicast(xe->drm.drm_genl_family, msg, 0,
> +			  hw_err ?
> +			  DRM_GENL_MCAST_UNCORR_ERR
> +			  : DRM_GENL_MCAST_CORR_ERR,
> +			  GFP_ATOMIC);
> +}
> +#else
> +static void
> +generate_netlink_event(struct xe_device *xe, const enum hardware_error hw_err)
> +{}
> +#endif
> +
>  static void
>  xe_hw_error_source_handler(struct xe_tile *tile, const enum hardware_error hw_err)
>  {
> @@ -837,6 +876,8 @@ xe_hw_error_source_handler(struct xe_tile *tile, const enum hardware_error hw_er
>  	}
>  
>  	xe_mmio_write32(&tile->mmio, DEV_ERR_STAT_REG(hw_err), errsrc);
> +
> +	generate_netlink_event(tile_to_xe(tile), hw_err);
>  unlock:
>  	spin_unlock_irqrestore(&tile_to_xe(tile)->irq.lock, flags);
>  }
> -- 
> 2.25.1
>