From a8901c9ece3c3cdfd2af6228b20e41542cf3d9c4 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Wed, 24 Nov 2021 08:49:15 -0500
Subject: drm/amdkfd: fix svm_bo release invalid wait context warning
Git-commit: 69879b3083cc5022585d1826c663c330efae4e63
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

Add svm_range_bo_unref_async to schedule work to wait for svm_bo
eviction work done and then free svm_bo. __do_munmap put_page
is atomic context, call svm_range_bo_unref_async to avoid warning
invalid wait context. Other non atomic context call svm_range_bo_unref.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 31 +++++++++++++++++++++---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.h     |  3 ++-
 3 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 48c2f2b6e217..ed5385137f48 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -549,7 +549,7 @@ static void svm_migrate_page_free(struct page *page)
 
 	if (svm_bo) {
 		pr_debug_ratelimited("ref: %d\n", kref_read(&svm_bo->kref));
-		svm_range_bo_unref(svm_bo);
+		svm_range_bo_unref_async(svm_bo);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 7e92dcea4ce8..cb73141cc460 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -332,6 +332,8 @@ static void svm_range_bo_release(struct kref *kref)
 	struct svm_range_bo *svm_bo;
 
 	svm_bo = container_of(kref, struct svm_range_bo, kref);
+	pr_debug("svm_bo 0x%p\n", svm_bo);
+
 	spin_lock(&svm_bo->list_lock);
 	while (!list_empty(&svm_bo->range_list)) {
 		struct svm_range *prange =
@@ -365,12 +367,33 @@ static void svm_range_bo_release(struct kref *kref)
 	kfree(svm_bo);
 }
 
-void svm_range_bo_unref(struct svm_range_bo *svm_bo)
+static void svm_range_bo_wq_release(struct work_struct *work)
 {
-	if (!svm_bo)
-		return;
+	struct svm_range_bo *svm_bo;
+
+	svm_bo = container_of(work, struct svm_range_bo, release_work);
+	svm_range_bo_release(&svm_bo->kref);
+}
+
+static void svm_range_bo_release_async(struct kref *kref)
+{
+	struct svm_range_bo *svm_bo;
+
+	svm_bo = container_of(kref, struct svm_range_bo, kref);
+	pr_debug("svm_bo 0x%p\n", svm_bo);
+	INIT_WORK(&svm_bo->release_work, svm_range_bo_wq_release);
+	schedule_work(&svm_bo->release_work);
+}
 
-	kref_put(&svm_bo->kref, svm_range_bo_release);
+void svm_range_bo_unref_async(struct svm_range_bo *svm_bo)
+{
+	kref_put(&svm_bo->kref, svm_range_bo_release_async);
+}
+
+static void svm_range_bo_unref(struct svm_range_bo *svm_bo)
+{
+	if (svm_bo)
+		kref_put(&svm_bo->kref, svm_range_bo_release);
 }
 
 static bool
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 6dc91c33e80f..2f8a95e86dcb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -48,6 +48,7 @@ struct svm_range_bo {
 	struct work_struct		eviction_work;
 	struct svm_range_list		*svms;
 	uint32_t			evicting;
+	struct work_struct		release_work;
 };
 
 enum svm_work_list_ops {
@@ -195,7 +196,7 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s
  */
 #define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0)
 
-void svm_range_bo_unref(struct svm_range_bo *svm_bo);
+void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
 #else
 
 struct kfd_process;
-- 
2.38.1