From: Jesse.Zhang <Jesse.Zhang@amd.com>
Date: Tue, 5 Aug 2025 04:23:18 +0000 (+0800)
Subject: drm/amdgpu: Switch user queues to use preempt/restore for eviction
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=bb1d7f157e3d2357daf3146f7bcd03bcdbcefd25;p=users%2Fhch%2Fmisc.git

drm/amdgpu: Switch user queues to use preempt/restore for eviction

This patch modifies the user queue management to use preempt/restore
operations instead of full map/unmap for queue eviction scenarios where
applicable. The changes include:

1. Introduces new helper functions:
   - amdgpu_userqueue_preempt_helper()
   - amdgpu_userqueue_restore_helper()

2. Updates queue state management to track PREEMPTED state

3. Modifies eviction handling to use preempt instead of unmap:
   - amdgpu_userq_evict_all() now uses preempt_helper
   - amdgpu_userq_restore_all() now uses restore_helper

The preempt/restore approach provides better performance during queue
eviction by avoiding the overhead of full queue teardown and setup.
Full map/unmap operations are still used for initial setup/teardown
and system suspend scenarios.

v2: rename amdgpu_userqueue_restore_helper/amdgpu_userqueue_preempt_helper to
amdgpu_userq_restore_helper/amdgpu_userq_preempt_helper for consistency. (Alex)

v3: amdgpu_userq_stop_sched_for_enforce_isolation() and
amdgpu_userq_start_sched_for_enforce_isolation() should use preempt and restore (Alex)

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index c3c1a714b06a..d2e59aecb3eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -77,7 +77,7 @@ out_err:
 }
 
 static int
-amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr,
+amdgpu_userq_preempt_helper(struct amdgpu_userq_mgr *uq_mgr,
 			  struct amdgpu_usermode_queue *queue)
 {
 	struct amdgpu_device *adev = uq_mgr->adev;
@@ -86,6 +86,49 @@ amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr,
 	int r = 0;
 
 	if (queue->state == AMDGPU_USERQ_STATE_MAPPED) {
+		r = userq_funcs->preempt(uq_mgr, queue);
+		if (r) {
+			queue->state = AMDGPU_USERQ_STATE_HUNG;
+		} else {
+			queue->state = AMDGPU_USERQ_STATE_PREEMPTED;
+		}
+	}
+
+	return r;
+}
+
+static int
+amdgpu_userq_restore_helper(struct amdgpu_userq_mgr *uq_mgr,
+			struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_device *adev = uq_mgr->adev;
+	const struct amdgpu_userq_funcs *userq_funcs =
+		adev->userq_funcs[queue->queue_type];
+	int r = 0;
+
+	if (queue->state == AMDGPU_USERQ_STATE_PREEMPTED) {
+		r = userq_funcs->restore(uq_mgr, queue);
+		if (r) {
+			queue->state = AMDGPU_USERQ_STATE_HUNG;
+		} else {
+			queue->state = AMDGPU_USERQ_STATE_MAPPED;
+		}
+	}
+
+	return r;
+}
+
+static int
+amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr,
+			  struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_device *adev = uq_mgr->adev;
+	const struct amdgpu_userq_funcs *userq_funcs =
+		adev->userq_funcs[queue->queue_type];
+	int r = 0;
+
+	if ((queue->state == AMDGPU_USERQ_STATE_MAPPED) ||
+		(queue->state == AMDGPU_USERQ_STATE_PREEMPTED)) {
 		r = userq_funcs->unmap(uq_mgr, queue);
 		if (r)
 			queue->state = AMDGPU_USERQ_STATE_HUNG;
@@ -653,7 +696,7 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 
 	/* Resume all the queues for this process */
 	idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) {
-		r = amdgpu_userq_map_helper(uq_mgr, queue);
+		r = amdgpu_userq_restore_helper(uq_mgr, queue);
 		if (r)
 			ret = r;
 	}
@@ -810,7 +853,7 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 
 	/* Try to unmap all the queues in this process ctx */
 	idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) {
-		r = amdgpu_userq_unmap_helper(uq_mgr, queue);
+		r = amdgpu_userq_preempt_helper(uq_mgr, queue);
 		if (r)
 			ret = r;
 	}
@@ -995,7 +1038,7 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev,
 			if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
 			     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
 			    (queue->xcp_id == idx)) {
-				r = amdgpu_userq_unmap_helper(uqm, queue);
+				r = amdgpu_userq_preempt_helper(uqm, queue);
 				if (r)
 					ret = r;
 			}
@@ -1029,7 +1072,7 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
 			if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
 			     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
 			    (queue->xcp_id == idx)) {
-				r = amdgpu_userq_map_helper(uqm, queue);
+				r = amdgpu_userq_restore_helper(uqm, queue);
 				if (r)
 					ret = r;
 			}