drm/amdgpu: Don't resume IOMMU after incomplete init

Check kfd->init_complete in kgd2kfd_iommu_resume, consistent with other
kgd2kfd calls. This should fix IOMMU errors on resume from suspend when
KFD IOMMU initialization failed.

Reported-by: Matt Fagnani <matt.fagnani@bell.net>
Link: https://lore.kernel.org/r/4a3b225c-2ffd-e758-4de1-447375e34cad@bell.net/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217170
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2454
Cc: Vasant Hegde <vasant.hegde@amd.com>
Cc: Linux regression tracking (Thorsten Leemhuis) <regressions@leemhuis.info>
Cc: stable@vger.kernel.org
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Matt Fagnani <matt.fagnani@bell.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 3de7f616a001cf6a8be622f87db2bb286c7e1c3d..ec70a1658dc3871c1dd960af26586a76dbb847a8 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -59,6 +59,7 @@ static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
                                unsigned int chunk_size);
 static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
 
+static int kfd_resume_iommu(struct kfd_dev *kfd);
 static int kfd_resume(struct kfd_dev *kfd);
 
 static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
@@ -624,7 +625,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
        svm_migrate_init(kfd->adev);
 
-       if (kgd2kfd_resume_iommu(kfd))
+       if (kfd_resume_iommu(kfd))
                goto device_iommu_error;
 
        if (kfd_resume(kfd))
@@ -772,6 +773,14 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 }
 
 int kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+       if (!kfd->init_complete)
+               return 0;
+
+       return kfd_resume_iommu(kfd);
+}
+
+static int kfd_resume_iommu(struct kfd_dev *kfd)
 {
        int err = 0;