diff options
| author | Zhi Wang <zhi.a.wang@intel.com> | 2022-11-10 15:20:34 +0300 |
|---|---|---|
| committer | Zhenyu Wang <zhenyuw@linux.intel.com> | 2023-01-04 18:21:19 +0300 |
| commit | a06d4b9e15c0ea4e05b200cfb1f1050e785a5e87 (patch) | |
| tree | 938ffdc3fd9d95d703933c3387c471005a43a3d1 /drivers/gpu/drm/i915/gvt/gtt.c | |
| parent | 704f3384f322b40ba24d958473edfb1c9750c8fd (diff) | |
| download | linux-a06d4b9e15c0ea4e05b200cfb1f1050e785a5e87.tar.xz | |
drm/i915/gvt: use atomic operations to change the vGPU status
Several vGPU status are used to decide the availability of GVT-g core
logics when creating a vGPU. Use atomic operations on changing the vGPU
status to avoid the racing.
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: intel-gvt-dev@lists.freedesktop.org
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20221110122034.3382-2-zhi.a.wang@intel.com
Diffstat (limited to 'drivers/gpu/drm/i915/gvt/gtt.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/gtt.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 51e5e8fb505b..6b4039010cae 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -55,7 +55,7 @@ static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn) int idx; bool ret; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return false; idx = srcu_read_lock(&kvm->srcu); @@ -1178,7 +1178,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M)) return 0; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -EINVAL; pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry)); if (is_error_noslot_pfn(pfn)) |