Merge tag 'amd-drm-next-6.2-2022-11-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-18:

amdgpu:
- SR-IOV fixes
- Clean up DC checks
- DCN 3.2.x fixes
- DCN 3.1.x fixes
- Don't enable degamma on asics which don't support it
- IP discovery fixes
- BACO fixes
- Fix vbios allocation handling when vkms is enabled
- Drop buggy tdr advanced mode GPU reset handling
- Fix the build when DCN is not set in kconfig
- MST DSC fixes
- Userptr fixes
- FRU and RAS EEPROM fixes
- VCN 4.x RAS support
- Aldrebaran CU occupancy reporting fix
- PSP ring cleanup

amdkfd:
- Memory limit fix
- Enable cooperative launch on gfx 10.3

amd-drm-next-6.2-2022-11-11:

amdgpu:
- SMU 13.x updates
- GPUVM TLB race fix
- DCN 3.1.4 updates
- DCN 3.2.x updates
- PSR fixes
- Kerneldoc fix
- Vega10 fan fix
- GPUVM locking fixes in error pathes
- BACO fix for Beige Goby
- EEPROM I2C address cleanup
- GFXOFF fix
- Fix DC memory leak in error pathes
- Flexible array updates
- Mtype fix for GPUVM PTEs
- Move Kconfig into amdgpu directory
- SR-IOV updates
- Fix possible memory leak in CS IOCTL error path

amdkfd:
- Fix possible memory overrun
- CRIU fixes

radeon:
- ACPI ref count fix
- HDA audio notifier support
- Move Kconfig into radeon directory

UAPI:
- Add new GEM_CREATE flags to help to transition more KFD functionality to the DRM UAPI.
  These are used internally in the driver to align location based memory coherency
  requirements from memory allocated in the KFD with how we manage GPUVM PTEs.  They
  are currently blocked in the GEM_CREATE IOCTL as we don't have a user right now.
  They are just used internally in the kernel driver for now for existing KFD memory
  allocations. So a change to the UAPI header, but no functional change in the UAPI.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221118170807.6505-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 15 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 5feaba6a77de..6d291aa6386b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1950,7 +1950,7 @@ static int criu_checkpoint(struct file *filep,
 {
 	int ret;
 	uint32_t num_devices, num_bos, num_objects;
-	uint64_t priv_size, priv_offset = 0;
+	uint64_t priv_size, priv_offset = 0, bo_priv_offset;
 
 	if (!args->devices || !args->bos || !args->priv_data)
 		return -EINVAL;
@@ -1994,38 +1994,34 @@ static int criu_checkpoint(struct file *filep,
 	if (ret)
 		goto exit_unlock;
 
-	ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos,
-			    (uint8_t __user *)args->priv_data, &priv_offset);
-	if (ret)
-		goto exit_unlock;
+	/* Leave room for BOs in the private data. They need to be restored
+	 * before events, but we checkpoint them last to simplify the error
+	 * handling.
+	 */
+	bo_priv_offset = priv_offset;
+	priv_offset += num_bos * sizeof(struct kfd_criu_bo_priv_data);
 
 	if (num_objects) {
 		ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data,
 						 &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 
 		ret = kfd_criu_checkpoint_events(p, (uint8_t __user *)args->priv_data,
 						 &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 
 		ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 	}
 
-close_bo_fds:
-	if (ret) {
-		/* If IOCTL returns err, user assumes all FDs opened in criu_dump_bos are closed */
-		uint32_t i;
-		struct kfd_criu_bo_bucket *bo_buckets = (struct kfd_criu_bo_bucket *) args->bos;
-
-		for (i = 0; i < num_bos; i++) {
-			if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)
-				close_fd(bo_buckets[i].dmabuf_fd);
-		}
-	}
+	/* This must be the last thing in this function that can fail.
+	 * Otherwise we leak dmabuf file descriptors.
+	 */
+	ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos,
+			   (uint8_t __user *)args->priv_data, &bo_priv_offset);
 
 exit_unlock:
 	mutex_unlock(&p->mutex);