From cbe006a6492c01a0058912ae15d473f4c149896c Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Tue, 29 Oct 2024 13:01:15 +0100
Subject: [PATCH] drm/xe: Move LNL scheduling WA to xe_device.h
Move LNL scheduling WA to xe_device.h so this can be used in other
places without needing keep the same comment about removal of this WA
in the future. The WA, which flushes work or workqueues, is now wrapped
in macros and can be reused wherever needed.
Cc: Badal Nilawar <badal.nilawar@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
cc: stable@vger.kernel.org # v6.11+
Suggested-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241029120117.449694-1-nirmoy.das@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
drivers/gpu/drm/xe/xe_device.h | 14 ++++++++++++++
drivers/gpu/drm/xe/xe_guc_ct.c | 11 +----------
2 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 4c3f0ebe78a90..f1fbfe9168678 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -191,4 +191,18 @@ void xe_device_declare_wedged(struct xe_device *xe);
struct xe_file *xe_file_get(struct xe_file *xef);
void xe_file_put(struct xe_file *xef);
+/*
+ * Occasionally it is seen that the G2H worker starts running after a delay of more than
+ * a second even after being queued and activated by the Linux workqueue subsystem. This
+ * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
+ * Lunarlake Hybrid CPU. Issue disappears if we disable Lunarlake atom cores from BIOS
+ * and this is beyond xe kmd.
+ *
+ * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
+ */
+#define LNL_FLUSH_WORKQUEUE(wq__) \
+ flush_workqueue(wq__)
+#define LNL_FLUSH_WORK(wrk__) \
+ flush_work(wrk__)
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 4870af1c5a900..8aeb1789805c5 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1018,17 +1018,8 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,
ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);
- /*
- * Occasionally it is seen that the G2H worker starts running after a delay of more than
- * a second even after being queued and activated by the Linux workqueue subsystem. This
- * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
- * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS
- * and this is beyond xe kmd.
- *
- * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
- */
if (!ret) {
- flush_work(&ct->g2h_worker);
+ LNL_FLUSH_WORK(&ct->g2h_worker);
if (g2h_fence.done) {
xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
g2h_fence.seqno, action[0]);
--
GitLab