drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register

The only case where the GuC submission backend cannot reason 100%
correctly is when a GuC context is registered during VF post-migration
recovery. In this scenario, it's possible that the GuC context register
H2G is processed, but the immediately following schedule-enable H2G gets
lost. The schedule-enable G2H "done" response is how the GuC state machine
determines whether context registration has completed.

A double register is harmless when using `GUC_HXG_TYPE_EVENT`, as GuC
simply drops the duplicate H2G. To keep things simple, use
`GUC_HXG_TYPE_EVENT` for all context registrations on VFs.

v5:
 - Check for xe_sriov_vf_migration_supported (Tomasz)
v7:
 - Add comment about subsequent protocol failures (Tomasz)
 - Modify commit message (Michal)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-20-matthew.brost@intel.com

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 9f0090ae64a60fe69ccad7d04c231462ee47bd7a..f63ce0cec3575ab1260fc4344bb3630510868537 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -32,6 +32,7 @@
 #include "xe_guc_tlb_inval.h"
 #include "xe_map.h"
 #include "xe_pm.h"
+#include "xe_sriov_vf.h"
 #include "xe_trace_guc.h"
 
 static void receive_g2h(struct xe_guc_ct *ct);
@@ -736,6 +737,28 @@ static u16 next_ct_seqno(struct xe_guc_ct *ct, bool is_g2h_fence)
        return seqno;
 }
 
+#define MAKE_ACTION(type, __action)                            \
+({                                                             \
+       FIELD_PREP(GUC_HXG_MSG_0_TYPE, type) |                  \
+       FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |                 \
+                  GUC_HXG_EVENT_MSG_0_DATA0, __action);        \
+})
+
+static bool vf_action_can_safely_fail(struct xe_device *xe, u32 action)
+{
+       /*
+        * When resuming a VF, we can't reliably track whether context
+        * registration has completed in the GuC state machine. It is harmless
+        * to resend the request, as it will fail silently if GUC_HXG_TYPE_EVENT
+        * is used. Additionally, if there is an H2G protocol issue on a VF,
+        * subsequent H2G messages sent as GUC_HXG_TYPE_FAST_REQUEST will likely
+        * fail.
+        */
+       return IS_SRIOV_VF(xe) && xe_sriov_vf_migration_supported(xe) &&
+               (action == XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC ||
+                action == XE_GUC_ACTION_REGISTER_CONTEXT);
+}
+
 #define H2G_CT_HEADERS (GUC_CTB_HDR_LEN + 1) /* one DW CTB header and one DW HxG header */
 
 static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
@@ -807,18 +830,14 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
                FIELD_PREP(GUC_CTB_MSG_0_NUM_DWORDS, len) |
                FIELD_PREP(GUC_CTB_MSG_0_FENCE, ct_fence_value);
        if (want_response) {
-               cmd[1] =
-                       FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
-                       FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
-                                  GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
+               cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_REQUEST, action[0]);
+       } else if (vf_action_can_safely_fail(xe, action[0])) {
+               cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_EVENT, action[0]);
        } else {
                fast_req_track(ct, ct_fence_value,
                               FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, action[0]));
 
-               cmd[1] =
-                       FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_FAST_REQUEST) |
-                       FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
-                                  GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
+               cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_FAST_REQUEST, action[0]);
        }
 
        /* H2G header in cmd[1] replaces action[0] so: */