From d65650a9d153c91f0cde0f5026268812e0b697f3 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Wed, 28 May 2025 11:00:21 +0200 Subject: [PATCH] drm/xe/guc: Resend potentially lost H2G MMIO request There could be a scenario where the VF driver is resuming faster than the driver PF is able to complete the VF FLR sequence which includes reset of the VF scratch registers. This may result in deletion of the ongoing HXG message (it could be either a host request or a GuC response). When we detect that HXG message was likey lost (scratch register with HXG header was zeroed) try to send this request once more before giving up. Signed-off-by: Michal Wajdeczko Cc: Satyanarayana K V P Reviewed-by: Satyanarayana K V P Link: https://lore.kernel.org/r/20250528090021.329-1-michal.wajdeczko@intel.com --- drivers/gpu/drm/xe/xe_guc.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 350434a8b9537..52453845d1bd3 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -1289,6 +1289,7 @@ int xe_guc_mmio_send_recv(struct xe_guc *guc, const u32 *request, struct xe_reg reply_reg = xe_gt_is_media_type(gt) ? MED_VF_SW_FLAG(0) : VF_SW_FLAG(0); const u32 LAST_INDEX = VF_SW_FLAG_COUNT - 1; + bool lost = false; int ret; int i; @@ -1322,6 +1323,12 @@ retry: FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_GUC), 50000, &reply, false); if (ret) { + /* scratch registers might be cleared during FLR, try once more */ + if (!reply && !lost) { + xe_gt_dbg(gt, "GuC mmio request %#x: lost, trying again\n", request[0]); + lost = true; + goto retry; + } timeout: xe_gt_err(gt, "GuC mmio request %#x: no reply %#x\n", request[0], reply); -- 2.47.2