From 2506af5f8109a387a5e8e9e3d7c498480b8033db Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Thu, 4 Sep 2025 00:33:30 +0200 Subject: [PATCH] drm/xe/guc: Set upper limit of H2G retries over CTB The GuC communication protocol allows GuC to send NO_RESPONSE_RETRY reply message to indicate that due to some interim condition it can not handle incoming H2G request and the host shall resend it. But in some cases, due to errors, this unsatisfied condition might be final and this could lead to endless retries as it was recently seen on the CI: [drm] GT0: PF: VF1 FLR didn't finish in 5000 ms (-ETIMEDOUT) [drm] GT0: PF: VF1 resource sanitizing failed (-ETIMEDOUT) [drm] GT0: PF: VF1 FLR failed! [drm:guc_ct_send_recv [xe]] GT0: H2G action 0x5503 retrying: reason 0x0 [drm:guc_ct_send_recv [xe]] GT0: H2G action 0x5503 retrying: reason 0x0 [drm:guc_ct_send_recv [xe]] GT0: H2G action 0x5503 retrying: reason 0x0 [drm:guc_ct_send_recv [xe]] GT0: H2G action 0x5503 retrying: reason 0x0 To avoid such dangerous loops allow only limited number of retries (for now 50) and add some delays (n * 5ms) to slow down the rate of resending this repeated request. Signed-off-by: Michal Wajdeczko Cc: John Harrison Cc: Matthew Brost Reviewed-by: Stuart Summers Reviewed-by: Julia Filipchuk Link: https://lore.kernel.org/r/20250903223330.6408-1-michal.wajdeczko@intel.com --- drivers/gpu/drm/xe/xe_guc_ct.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index e431ff73227cc..f40543b040d6a 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1079,11 +1079,15 @@ static bool retry_failure(struct xe_guc_ct *ct, int ret) return true; } +#define GUC_SEND_RETRY_LIMIT 50 +#define GUC_SEND_RETRY_MSLEEP 5 + static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len, u32 *response_buffer, bool no_fail) { struct xe_gt *gt = ct_to_gt(ct); struct g2h_fence g2h_fence; + unsigned int retries = 0; int ret = 0; /* @@ -1148,6 +1152,12 @@ retry_same_fence: xe_gt_dbg(gt, "H2G action %#x retrying: reason %#x\n", action[0], g2h_fence.reason); mutex_unlock(&ct->lock); + if (++retries > GUC_SEND_RETRY_LIMIT) { + xe_gt_err(gt, "H2G action %#x reached retry limit=%u, aborting\n", + action[0], GUC_SEND_RETRY_LIMIT); + return -ELOOP; + } + msleep(GUC_SEND_RETRY_MSLEEP * retries); goto retry; } if (g2h_fence.fail) { -- 2.47.3