drm/amdgpu/sriov add amdgpu_amdkfd_pre_reset in gpu reset

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>

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 4ec6d0c0320107489a4b7072d68f056b48da915a..bdc1f5a532f3f570b2d7dc290d0adcb68cee97f4 100644 (file)
--- 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 df841c2ac5e741a5a4c8aa530f7b7d8c9c8ac8a2..c2562d65e0b54aa85def614a38960c3a9275abf1 100644 (file)
--- 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 90601966c52475bfc57fdc5f7e7e31af2ac8ae56..626b46fa1a63ec935082391554500206ee501db7 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3852,6 +3852,8 @@ 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)