Blob Blame History Raw
From 51524f428ed9c4a27bd264f9c9eb10eaff7763ef Mon Sep 17 00:00:00 2001
From: Jack Zhang <Jack.Zhang1@amd.com>
Date: Thu, 2 Apr 2020 15:10:24 +0800
Subject: drm/amdgpu/sriov add amdgpu_amdkfd_pre_reset in gpu reset
Git-commit: 04bef61e5da18c2b301c629a209ccdba4d4c6fbb
Patch-mainline: v5.8-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322

kfd_pre_reset will free mem_objs allocated by kfd_gtt_sa_allocate

Without this change, sriov tdr code path will never free those allocated
memories and get memory leak.

v2:add a bugfix for kiq ring test fail

Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c  | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c         | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 4ec6d0c03201..bdc1f5a532f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -543,6 +543,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v10_compute_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 #if 0
 	unsigned long flags;
 	int retry;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index df841c2ac5e7..c2562d65e0b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -541,6 +541,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 	if (adev->in_gpu_reset)
 		return -EIO;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index aa1785113fdf..a1e7c887d9a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3868,6 +3868,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
-- 
2.28.0