drm/xe/pf: Reset GuC VF config when unprovisioning critical resource

GuC firmware counts received VF configuration KLVs and may start
validation of the complete VF config even if some resources where
unprovisioned in the meantime, leading to unexpected errors like:

 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/contexts_quota
 $ echo 0 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/contexts_quota
 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/doorbells_quota
 $ echo 0 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/doorbells_quota
 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/ggtt_quota
 tee: '/sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/ggtt_quota': Input/output error

To mitigate this problem trigger explicit VF config reset after
unprovisioning any of the critical resources (GGTT, context or
doorbell IDs) that GuC is monitoring.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250129195947.764-3-michal.wajdeczko@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index c219c55f23ab3d2d18a690a9aed02cdacee9601c..b1d994d65589639c15058ca40a96f981bfd5833b 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -338,6 +338,26 @@ static int pf_push_full_vf_config(struct xe_gt *gt, unsigned int vfid)
        return err;
 }
 
+static int pf_push_vf_cfg(struct xe_gt *gt, unsigned int vfid, bool reset)
+{
+       int err = 0;
+
+       xe_gt_assert(gt, vfid);
+       lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
+
+       if (reset)
+               err = pf_send_vf_cfg_reset(gt, vfid);
+       if (!err)
+               err = pf_push_full_vf_config(gt, vfid);
+
+       return err;
+}
+
+static int pf_refresh_vf_cfg(struct xe_gt *gt, unsigned int vfid)
+{
+       return pf_push_vf_cfg(gt, vfid, true);
+}
+
 static u64 pf_get_ggtt_alignment(struct xe_gt *gt)
 {
        struct xe_device *xe = gt_to_xe(gt);
@@ -434,6 +454,10 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
                        return err;
 
                pf_release_vf_config_ggtt(gt, config);
+
+               err = pf_refresh_vf_cfg(gt, vfid);
+               if (unlikely(err))
+                       return err;
        }
        xe_gt_assert(gt, !xe_ggtt_node_allocated(config->ggtt_region));
 
@@ -759,6 +783,10 @@ static int pf_provision_vf_ctxs(struct xe_gt *gt, unsigned int vfid, u32 num_ctx
                        return ret;
 
                pf_release_config_ctxs(gt, config);
+
+               ret = pf_refresh_vf_cfg(gt, vfid);
+               if (unlikely(ret))
+                       return ret;
        }
 
        if (!num_ctxs)
@@ -1056,6 +1084,10 @@ static int pf_provision_vf_dbs(struct xe_gt *gt, unsigned int vfid, u32 num_dbs)
                        return ret;
 
                pf_release_config_dbs(gt, config);
+
+               ret = pf_refresh_vf_cfg(gt, vfid);
+               if (unlikely(ret))
+                       return ret;
        }
 
        if (!num_dbs)
@@ -2087,10 +2119,7 @@ int xe_gt_sriov_pf_config_push(struct xe_gt *gt, unsigned int vfid, bool refresh
        xe_gt_assert(gt, vfid);
 
        mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
-       if (refresh)
-               err = pf_send_vf_cfg_reset(gt, vfid);
-       if (!err)
-               err = pf_push_full_vf_config(gt, vfid);
+       err = pf_push_vf_cfg(gt, vfid, refresh);
        mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
 
        if (unlikely(err)) {