From: Xiaogang Chen <xiaogang.chen@amd.com>
Date: Wed, 27 Sep 2023 16:20:28 +0000 (-0500)
Subject: drm/amdkfd: Fix a race condition of vram buffer unref in svm code
X-Git-Tag: v6.6.3~472
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=fc0210720127cc6302e6d6f3de48f49c3fcf5659;p=thirdparty%2Fkernel%2Fstable.git

drm/amdkfd: Fix a race condition of vram buffer unref in svm code

[ Upstream commit 709c348261618da7ed89d6c303e2ceb9e453ba74 ]

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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 2a42fbddcb7ae..2591bdfcc2289 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -628,8 +628,15 @@ 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 kfd_node *