[PATCH v2] drm/xe/guc/tlb: Flush g2h worker in case of tlb timeout
Nirmoy Das
nirmoy.das at intel.com
Thu Oct 24 15:37:39 UTC 2024
Flush the g2h worker explicitly if TLB timeout happens which is
observed on LNL and that points to the recent scheduling issue with
E-cores on LNL.
This is similar to the recent fix:
commit e51527233804 ("drm/xe/guc/ct: Flush g2h worker in case of g2h
response timeout") and should be removed once there is E core
scheduling fix.
v2: Add platform check(Himal)
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2687
Cc: Badal Nilawar <badal.nilawar at intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
Cc: Matthew Auld <matthew.auld at intel.com>
Cc: John Harrison <John.C.Harrison at Intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
Cc: Lucas De Marchi <lucas.demarchi at intel.com>
Cc: <stable at vger.kernel.org> # v6.11+
Signed-off-by: Nirmoy Das <nirmoy.das at intel.com>
Reviewed-by: Matthew Brost <matthew.brost at intel.com>
Acked-by: Badal Nilawar <badal.nilawar at intel.com>
---
drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 773de1f08db9..5aba6ed950b7 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -6,6 +6,7 @@
#include "xe_gt_tlb_invalidation.h"
#include "abi/guc_actions_abi.h"
+#include "compat-i915-headers/i915_drv.h"
#include "xe_device.h"
#include "xe_force_wake.h"
#include "xe_gt.h"
@@ -72,6 +73,16 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
struct xe_device *xe = gt_to_xe(gt);
struct xe_gt_tlb_invalidation_fence *fence, *next;
+ /*
+ * This is analogous to e51527233804 ("drm/xe/guc/ct: Flush g2h worker
+ * in case of g2h response timeout")
+ *
+ * TODO: Drop this change once workqueue scheduling delay issue is
+ * fixed on LNL Hybrid CPU.
+ */
+ if (IS_LUNARLAKE(xe))
+ flush_work(>->uc.guc.ct.g2h_worker);
+
spin_lock_irq(>->tlb_invalidation.pending_lock);
list_for_each_entry_safe(fence, next,
>->tlb_invalidation.pending_fences, link) {
--
2.46.0
More information about the Intel-xe
mailing list