From 709c348261618da7ed89d6c303e2ceb9e453ba74 Mon Sep 17 00:00:00 2001
From: Xiaogang Chen <xiaogang.chen@amd.com>
Date: Wed, 27 Sep 2023 11:20:28 -0500
Subject: [PATCH] drm/amdkfd: Fix a race condition of vram buffer unref in svm code
Git-commit: 709c348261618da7ed89d6c303e2ceb9e453ba74
Patch-mainline: v6.7-rc1
References: git-fixes

prange->svm_bo unref can happen in both mmu callback and a callback after
migrate to system ram. Both are async call in different tasks. Sync svm_bo
unref operation to avoid random "use-after-free".

Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Tested-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -550,8 +550,15 @@ create_bo_failed:
 
 void svm_range_vram_node_free(struct svm_range *prange)
 {
-	svm_range_bo_unref(prange->svm_bo);
-	prange->ttm_res = NULL;
+	/* serialize prange->svm_bo unref */
+	mutex_lock(&prange->lock);
+	/* prange->svm_bo has not been unref */
+	if (prange->ttm_res) {
+		prange->ttm_res = NULL;
+		mutex_unlock(&prange->lock);
+		svm_range_bo_unref(prange->svm_bo);
+	} else
+		mutex_unlock(&prange->lock);
 }
 
 struct amdgpu_device *