On 2022-09-07 14:36, Rajneesh Bhardwaj wrote:
Recently introduced change to allocate doorbells only when the first
queue is created or mapped for CPU / GPU access, did not consider
Checkpoint Restore scenario completely. This fix allows the CRIU restore
operation by extedning the doorbell optimization to CRIU restore
scenario.
typo: extending
A few more nit-picks inline.
Fixes: 'commit 15bcfbc55b57 ("drm/amdkfd: Allocate doorbells only when needed")'
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 8 ++++++++
drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 4 +++-
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 9 +++++++++
3 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 84da1a9ce37c..c476993e3927 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2153,6 +2153,13 @@ static int criu_restore_devices(struct kfd_process *p,
ret = PTR_ERR(pdd);
goto exit;
}
+
+ if (!pdd->doorbell_index &&
+ kfd_alloc_process_doorbells(pdd->dev, &pdd->doorbell_index) < 0) {
+ pr_err("Failed to allocate process doorbells\n");
+ ret = -ENOMEM;
+ goto err_alloc_doorbells;
+ }
Incorrect indentation. The closing brace should be indented one more
tab. And the if condition would be more readable if the second line was
aligned under the !pdd->doorbell_index.
You don't need a new err_alloc_doorbells label. Just goto exit.
}
/*
@@ -2161,6 +2168,7 @@ static int criu_restore_devices(struct kfd_process *p,
*/
*priv_offset += args->num_devices * sizeof(*device_privs);
+err_alloc_doorbells:
exit:
kfree(device_buckets);
return ret;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index b33798f89ef0..7690514c4eb3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -157,8 +157,10 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
/* Calculate physical address of doorbell */
address = kfd_get_process_doorbells(pdd);
- if (!address)
+ if (!address) {
+ pr_err("Failed to get physical address of process doorbell\n");
Please use the same error message as above for consistency. Or better
yet, move the error printing into kfd_alloc_process_doorbells, so you
don't have to duplicate the same error message in multiple places.
return -ENOMEM;
+ }
vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE |
VM_DONTDUMP | VM_PFNMAP;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 6e3e7f54381b..9f05f64c5af8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -857,6 +857,14 @@ int kfd_criu_restore_queue(struct kfd_process *p,
ret = -EINVAL;
goto exit;
}
+
+ if (!pdd->doorbell_index &&
+ kfd_alloc_process_doorbells(pdd->dev, &pdd->doorbell_index) < 0) {
+ pr_err("Failed to alloc process doorbells\n");
Same as above.
+ ret = -ENOMEM;
+ goto err_alloc_doorbells;
You don't need a new err_alloc_doorbells label. Just goto exit.
+ }
+
/* data stored in this order: mqd, ctl_stack */
mqd = q_extra_data;
ctl_stack = mqd + q_data->mqd_size;
@@ -876,6 +884,7 @@ int kfd_criu_restore_queue(struct kfd_process *p,
if (q_data->gws)
ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws);
+err_alloc_doorbells:
exit:
if (ret)
pr_err("Failed to restore queue (%d)\n", ret);