drm/xe: Hold a PM ref when GT TLB invalidations are inflight

Avoid GT TLB invalidation timeouts by holding a PM ref when
invalidations are inflight.

v2:
 - Drop PM ref before signaling fence (CI)
v3:
 - Move invalidation_fence_signal helper in tlb timeout to previous
   patch (Matthew Auld)

Fixes: dd08ebf ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-4-matthew.brost@intel.com
(cherry picked from commit 0a382f9)
Requires: 46209ce5287b ("drm/xe: Add xe_gt_tlb_invalidation_fence_init
helper")
Requires: 0e414ab036e0 ("drm/xe: Drop xe_gt_tlb_invalidation_wait")
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

Author: mbrost05

drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c

@@ -13,6 +13,7 @@
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_mmio.h"
+#include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_trace.h"
 #include "regs/xe_guc_regs.h"
@@ -41,6 +42,7 @@ __invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_
 	bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
 
 	trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
+	xe_gt_tlb_invalidation_fence_fini(fence);
 	dma_fence_signal(&fence->base);
 	if (!stack)
 		dma_fence_put(&fence->base);
@@ -263,8 +265,10 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 
 		xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
 		ret = xe_gt_tlb_invalidation_guc(gt, &fence);
-		if (ret < 0)
+		if (ret < 0) {
+			xe_gt_tlb_invalidation_fence_fini(&fence);
 			return ret;
+		}
 
 		xe_gt_tlb_invalidation_fence_wait(&fence);
 	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
@@ -489,12 +493,15 @@ static const struct dma_fence_ops invalidation_fence_ops = {
  * @fence: TLB invalidation fence to initialize
  * @stack: fence is stack variable
  *
- * Initialize TLB invalidation fence for use
+ * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
+ * must be called if fence is not signaled.
  */
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
 				       bool stack)
 {
+	xe_pm_runtime_get_noresume(gt_to_xe(gt));
+
 	spin_lock_irq(&gt->tlb_invalidation.lock);
 	dma_fence_init(&fence->base, &invalidation_fence_ops,
 		       &gt->tlb_invalidation.lock,
@@ -505,4 +512,16 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 		set_bit(FENCE_STACK_BIT, &fence->base.flags);
 	else
 		dma_fence_get(&fence->base);
+	fence->gt = gt;
+}
+
+/**
+ * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
+ * @fence: TLB invalidation fence to finalize
+ *
+ * Drop PM ref which fence took durinig init.
+ */
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+	xe_pm_runtime_put(gt_to_xe(fence->gt));
 }

drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h

@@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
 				       bool stack);
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
 
 static inline void
 xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)

drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h

@@ -8,6 +8,8 @@
 
 #include <linux/dma-fence.h>
 
+struct xe_gt;
+
 /**
  * struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence
  *
@@ -17,6 +19,8 @@
 struct xe_gt_tlb_invalidation_fence {
 	/** @base: dma fence base */
 	struct dma_fence base;
+	/** @gt: GT which fence belong to */
+	struct xe_gt *gt;
 	/** @link: link into list of pending tlb fences */
 	struct list_head link;
 	/** @seqno: seqno of TLB invalidation to signal fence one */

drivers/gpu/drm/xe/xe_vm.c

@@ -3379,8 +3379,10 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 			 */
 			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
 							 &fence[id], vma);
-			if (ret < 0)
+			if (ret < 0) {
+				xe_gt_tlb_invalidation_fence_fini(&fence[id]);
 				goto wait;
+			}
 
 			tile_needs_invalidate |= BIT(id);
 		}