This is a note to let you know that I've just added the patch titled
drm/amdgpu: Don't resume IOMMU after incomplete init
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdgpu-don-t-resume-iommu-after-incomplete-init.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From f3921a9a641483784448fb982b2eb738b383d9b9 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Date: Mon, 13 Mar 2023 20:03:08 -0400
Subject: drm/amdgpu: Don't resume IOMMU after incomplete init
From: Felix Kuehling <Felix.Kuehling@xxxxxxx>
commit f3921a9a641483784448fb982b2eb738b383d9b9 upstream.
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@xxxxxxxx>
Link: https://lore.kernel.org/r/4a3b225c-2ffd-e758-4de1-447375e34cad@xxxxxxxx/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217170
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2454
Cc: Vasant Hegde <vasant.hegde@xxxxxxx>
Cc: Linux regression tracking (Thorsten Leemhuis) <regressions@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Acked-by: Alex Deucher <alexander.deucher@xxxxxxx>
Tested-by: Matt Fagnani <matt.fagnani@xxxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
--- 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_de
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)
@@ -634,7 +635,7 @@ bool kgd2kfd_device_init(struct kfd_dev
svm_migrate_init(kfd->adev);
- if (kgd2kfd_resume_iommu(kfd))
+ if (kfd_resume_iommu(kfd))
goto device_iommu_error;
if (kfd_resume(kfd))
@@ -783,6 +784,14 @@ int kgd2kfd_resume(struct kfd_dev *kfd,
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;
err = kfd_iommu_resume(kfd);
Patches currently in stable-queue which might be from Felix.Kuehling@xxxxxxx are
queue-6.1/drm-ttm-fix-a-null-pointer-dereference.patch
queue-6.1/drm-amdgpu-don-t-resume-iommu-after-incomplete-init.patch
queue-6.1/drm-amdkfd-fix-an-illegal-memory-access.patch
