>-----Original Message-----
>From: Aravind Iddamsetty <aravind.iddamsetty@xxxxxxxxxxxxxxx>
>Sent: Friday, October 20, 2023 11:59 AM
>To: intel-xe@xxxxxxxxxxxxxxxxxxxxx; dri-devel@xxxxxxxxxxxxxxxxxxxxx;
>alexander.deucher@xxxxxxx; airlied@xxxxxxxxx; daniel@xxxxxxxx;
>joonas.lahtinen@xxxxxxxxxxxxxxx; ogabbay@xxxxxxxxxx; Tayar, Tomer (Habana)
><ttayar@xxxxxxxxx>; Hawking.Zhang@xxxxxxx;
>Harish.Kasiviswanathan@xxxxxxx; Felix.Kuehling@xxxxxxx;
>Luben.Tuikov@xxxxxxx; Ruhl, Michael J <michael.j.ruhl@xxxxxxxxx>
>Subject: [RFC v2 5/5] drm/xe/RAS: send multicast event on occurrence of an
>error
>
>Whenever a correctable or an uncorrectable error happens an event is sent
>to the corresponding listeners of these groups.
>
>v2: Rebase
Hi Aravind,
This looks reasonable to me.
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
M
>Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@xxxxxxxxxxxxxxx>
>---
> drivers/gpu/drm/xe/xe_hw_error.c | 33
>++++++++++++++++++++++++++++++++
> 1 file changed, 33 insertions(+)
>
>diff --git a/drivers/gpu/drm/xe/xe_hw_error.c
>b/drivers/gpu/drm/xe/xe_hw_error.c
>index bab6d4cf0b69..b0befb5e01cb 100644
>--- a/drivers/gpu/drm/xe/xe_hw_error.c
>+++ b/drivers/gpu/drm/xe/xe_hw_error.c
>@@ -786,6 +786,37 @@ xe_soc_hw_error_handler(struct xe_tile *tile, const
>enum hardware_error hw_err)
> (HARDWARE_ERROR_MAX << 1) + 1);
> }
>
>+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.module)
>+ 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);
>+ 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);
>+}
>+
> static void
> xe_hw_error_source_handler(struct xe_tile *tile, const enum hardware_error
>hw_err)
> {
>@@ -849,6 +880,8 @@ xe_hw_error_source_handler(struct xe_tile *tile, const
>enum hardware_error hw_er
> }
>
> xe_mmio_write32(gt, 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
