[PATCH 1/1] drm/xe: Avoid serializing unbind jobs on prior TLB invalidations

[Matthew Brost <matthew.brost@intel.com>]

When a burst of unbind jobs is issued, a dependency chain can form
between the TLB invalidation of a previous unbind job and the current
one. This leads to undesirable serialization, causing current jobs to
wait unnecessarily for prior TLB invalidations, execute on the GPU when
not needed, and significantly slow down the unbind burst—resulting in up
to a 4× slowdown.

To break this chain, mask the last bind queue dependency if the last
fence's DMA context matches the TLB invalidation context. This allows
full pipelining of unbinds and TLB invalidations while preserving
correct dma-fence signaling semantics.

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/6047
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c          |  3 +-
 drivers/gpu/drm/xe/xe_exec_queue.c    | 18 +++++++++--
 drivers/gpu/drm/xe/xe_exec_queue.h    |  3 +-
 drivers/gpu/drm/xe/xe_pt.c            | 15 +++++++--
 drivers/gpu/drm/xe/xe_sched_job.c     | 44 ++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_sched_job.h     |  7 ++++-
 drivers/gpu/drm/xe/xe_tlb_inval_job.c | 14 +++++++++
 drivers/gpu/drm/xe/xe_tlb_inval_job.h |  2 ++
 8 files changed, 98 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 0dc27476832b..6034cfc8be06 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -294,7 +294,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto err_put_job;
 
 	if (!xe_vm_in_lr_mode(vm)) {
-		err = xe_sched_job_last_fence_add_dep(job, vm);
+		err = xe_sched_job_last_fence_add_dep(job, vm, NO_MASK_DEP,
+						      NO_MASK_DEP);
 		if (err)
 			goto err_put_job;
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 90cbc95f8e2e..d6f69d9bccba 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -25,6 +25,7 @@
 #include "xe_migrate.h"
 #include "xe_pm.h"
 #include "xe_ring_ops_types.h"
+#include "xe_sched_job.h"
 #include "xe_trace.h"
 #include "xe_vm.h"
 #include "xe_pxp.h"
@@ -1106,11 +1107,17 @@ void xe_exec_queue_last_fence_set(struct xe_exec_queue *q, struct xe_vm *vm,
  * xe_exec_queue_last_fence_test_dep - Test last fence dependency of queue
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
+ * @mask_ctx0: Mask dma-fence context0
+ * @mask_ctx1: Mask dma-fence context1
+ *
+ * Test last fence dependency of queue, skipping masked dma fence contexts.
  *
  * Returns:
- * -ETIME if there exists an unsignalled last fence dependency, zero otherwise.
+ * -ETIME if there exists an unsignalled and unmasked last fence dependency,
+ * zero otherwise.
  */
-int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm)
+int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm,
+				      u64 mask_ctx0, u64 mask_ctx1)
 {
 	struct dma_fence *fence;
 	int err = 0;
@@ -1119,6 +1126,13 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm)
 	if (fence) {
 		err = test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) ?
 			0 : -ETIME;
+
+		if (err == -ETIME) {
+			if (xe_sched_job_mask_dependency(fence, mask_ctx0,
+							 mask_ctx1))
+				err = 0;
+		}
+
 		dma_fence_put(fence);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index a4dfbe858bda..99a35b22a46c 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -85,7 +85,8 @@ struct dma_fence *xe_exec_queue_last_fence_get_for_resume(struct xe_exec_queue *
 void xe_exec_queue_last_fence_set(struct xe_exec_queue *e, struct xe_vm *vm,
 				  struct dma_fence *fence);
 int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
-				      struct xe_vm *vm);
+				      struct xe_vm *vm, u64 mask_ctx0,
+				      u64 mask_ctx1);
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q);
 
 int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index d22fd1ccc0ba..bba9ae559f57 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1341,10 +1341,21 @@ static int xe_pt_vm_dependencies(struct xe_sched_job *job,
 	}
 
 	if (!(pt_update_ops->q->flags & EXEC_QUEUE_FLAG_KERNEL)) {
+		u64 mask_ctx0 = NO_MASK_DEP, mask_ctx1 = NO_MASK_DEP;
+
+		if (ijob)
+			mask_ctx0 = xe_tlb_inval_job_fence_context(ijob);
+		if (mjob)
+			mask_ctx1 = xe_tlb_inval_job_fence_context(mjob);
+
 		if (job)
-			err = xe_sched_job_last_fence_add_dep(job, vm);
+			err = xe_sched_job_last_fence_add_dep(job, vm,
+							      mask_ctx0,
+							      mask_ctx1);
 		else
-			err = xe_exec_queue_last_fence_test_dep(pt_update_ops->q, vm);
+			err = xe_exec_queue_last_fence_test_dep(pt_update_ops->q,
+								vm, mask_ctx0,
+								mask_ctx1);
 	}
 
 	for (i = 0; job && !err && i < vops->num_syncs; i++)
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index d21bf8f26964..7cbdd87904c6 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -6,6 +6,7 @@
 #include "xe_sched_job.h"
 
 #include <uapi/drm/xe_drm.h>
+#include <linux/dma-fence-array.h>
 #include <linux/dma-fence-chain.h>
 #include <linux/slab.h>
 
@@ -295,19 +296,60 @@ void xe_sched_job_push(struct xe_sched_job *job)
 	xe_sched_job_put(job);
 }
 
+/**
+ * xe_sched_job_mask_dependency() - Determine if a dma-fence dependency can be masked
+ * @fence: The dma-fence to check
+ * @mask_ctx0: First context to compare against the fence's context
+ * @mask_ctx1: Second context to compare against the fence's context
+ *
+ * This function checks whether the context of the given dma-fence matches
+ * either of the provided mask contexts. If a match is found, the dependency
+ * represented by the fence can be skipped. If the fence is a dma-fence-array,
+ * its individual fences are unwound and checked.
+ *
+ * Return: true if the fence can be masked (i.e., skipped), false otherwise.
+ */
+bool xe_sched_job_mask_dependency(struct dma_fence *fence, u64 mask_ctx0,
+				  u64 mask_ctx1)
+{
+	if (dma_fence_is_array(fence)) {
+		struct dma_fence *__fence;
+		int index;
+
+		dma_fence_array_for_each(__fence, index, fence)
+			if (__fence->context == mask_ctx0 ||
+			    __fence->context == mask_ctx1)
+				return true;
+	} else if (fence->context == mask_ctx0 ||
+		   fence->context == mask_ctx1) {
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * xe_sched_job_last_fence_add_dep - Add last fence dependency to job
  * @job:job to add the last fence dependency to
  * @vm: virtual memory job belongs to
+ * @mask_ctx0: Mask dma-fence context0
+ * @mask_ctx1: Mask dma-fence context1
+ *
+ * Add last fence dependency to job, skipping masked dma fence contexts.
  *
  * Returns:
  * 0 on success, or an error on failing to expand the array.
  */
-int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
+int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm,
+				    u64 mask_ctx0, u64 mask_ctx1)
 {
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
+	if (xe_sched_job_mask_dependency(fence, mask_ctx0, mask_ctx1)) {
+		dma_fence_put(fence);
+		return 0;
+	}
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sched_job.h b/drivers/gpu/drm/xe/xe_sched_job.h
index 3dc72c5c1f13..81d8e848e605 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.h
+++ b/drivers/gpu/drm/xe/xe_sched_job.h
@@ -58,7 +58,8 @@ bool xe_sched_job_completed(struct xe_sched_job *job);
 void xe_sched_job_arm(struct xe_sched_job *job);
 void xe_sched_job_push(struct xe_sched_job *job);
 
-int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm);
+int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm,
+				    u64 mask_ctx0, u64 mask_ctx1);
 void xe_sched_job_init_user_fence(struct xe_sched_job *job,
 				  struct xe_sync_entry *sync);
 
@@ -93,4 +94,8 @@ void xe_sched_job_snapshot_print(struct xe_sched_job_snapshot *snapshot, struct
 int xe_sched_job_add_deps(struct xe_sched_job *job, struct dma_resv *resv,
 			  enum dma_resv_usage usage);
 
+#define NO_MASK_DEP	(~0x0ull)
+bool xe_sched_job_mask_dependency(struct dma_fence *fence, u64 mask_ctx0,
+				  u64 mask_ctx1);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
index 492def04a559..f2fe7f9fbb22 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_job.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
@@ -32,6 +32,8 @@ struct xe_tlb_inval_job {
 	u64 start;
 	/** @end: End address to invalidate */
 	u64 end;
+	/** @fence_context: Fence context for job */
+	u64 fence_context;
 	/** @asid: Address space ID to invalidate */
 	u32 asid;
 	/** @fence_armed: Fence has been armed */
@@ -101,6 +103,7 @@ xe_tlb_inval_job_create(struct xe_exec_queue *q, struct xe_tlb_inval *tlb_inval,
 	job->asid = asid;
 	job->fence_armed = false;
 	job->dep.ops = &dep_job_ops;
+	job->fence_context = entity->fence_context + 1;
 	kref_init(&job->refcount);
 	xe_exec_queue_get(q);	/* Pairs with put in xe_tlb_inval_job_destroy */
 
@@ -266,3 +269,14 @@ void xe_tlb_inval_job_put(struct xe_tlb_inval_job *job)
 	if (!IS_ERR_OR_NULL(job))
 		kref_put(&job->refcount, xe_tlb_inval_job_destroy);
 }
+
+/**
+ * xe_tlb_inval_job_fence_context() - TLB invalidation job fence context
+ * @job: TLB invalidation job object
+ *
+ * Return: TLB invalidation job fence context
+ */
+u64 xe_tlb_inval_job_fence_context(struct xe_tlb_inval_job *job)
+{
+	return job->fence_context;
+}
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_job.h b/drivers/gpu/drm/xe/xe_tlb_inval_job.h
index e63edcb26b50..2576165c2228 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_job.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.h
@@ -30,4 +30,6 @@ void xe_tlb_inval_job_get(struct xe_tlb_inval_job *job);
 
 void xe_tlb_inval_job_put(struct xe_tlb_inval_job *job);
 
+u64 xe_tlb_inval_job_fence_context(struct xe_tlb_inval_job *job);
+
 #endif
-- 
2.34.1