[PATCH 9/9] drm/amdkfd: Validate queue cwsr area and eop buffer size
Philip Yang
Philip.Yang at amd.com
Mon Jul 15 12:35:02 UTC 2024
When creating KFD user compute queue, check if queue eop buffer size,
cwsr area size, ctl stack size equal to the size of KFD node
properities.
Check the entire cwsr area which may split into multiple svm ranges
aligned to gramularity boundary.
Signed-off-by: Philip Yang <Philip.Yang at amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling at amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 46 +++++++++++++++++++++++---
1 file changed, 42 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index adcda9730c9f..9807e8adf77d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -225,9 +225,15 @@ void kfd_queue_buffer_put(struct amdgpu_vm *vm, struct amdgpu_bo **bo)
int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_properties *properties)
{
+ struct kfd_topology_device *topo_dev;
struct amdgpu_vm *vm;
+ u32 total_cwsr_size;
int err;
+ topo_dev = kfd_topology_device_by_id(pdd->dev->id);
+ if (!topo_dev)
+ return -EINVAL;
+
vm = drm_priv_to_vm(pdd->drm_priv);
err = amdgpu_bo_reserve(vm->root.bo, false);
if (err)
@@ -252,6 +258,12 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
/* EOP buffer is not required for all ASICs */
if (properties->eop_ring_buffer_address) {
+ if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
+ pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
+ properties->eop_buf_bo->tbo.base.size,
+ topo_dev->node_props.eop_buffer_size);
+ goto out_err_unreserve;
+ }
err = kfd_queue_buffer_get(vm, (void *)properties->eop_ring_buffer_address,
&properties->eop_buf_bo,
properties->eop_ring_buffer_size);
@@ -259,15 +271,33 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
goto out_err_unreserve;
}
+ if (properties->ctl_stack_size != topo_dev->node_props.ctl_stack_size) {
+ pr_debug("queue ctl stack size 0x%x not equal to node ctl stack size 0x%x\n",
+ properties->ctl_stack_size,
+ topo_dev->node_props.ctl_stack_size);
+ goto out_err_unreserve;
+ }
+
+ if (properties->ctx_save_restore_area_size != topo_dev->node_props.cwsr_size) {
+ pr_debug("queue cwsr size 0x%x not equal to node cwsr size 0x%x\n",
+ properties->ctx_save_restore_area_size,
+ topo_dev->node_props.cwsr_size);
+ goto out_err_unreserve;
+ }
+
+ total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
+ * NUM_XCC(pdd->dev->xcc_mask);
+ total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
+
err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address,
- &properties->cwsr_bo, 0);
+ &properties->cwsr_bo, total_cwsr_size);
if (!err)
goto out_unreserve;
amdgpu_bo_unreserve(vm->root.bo);
err = kfd_queue_buffer_svm_get(pdd, properties->ctx_save_restore_area_address,
- properties->ctx_save_restore_area_size);
+ total_cwsr_size);
if (err)
goto out_err_release;
@@ -286,7 +316,9 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_properties *properties)
{
+ struct kfd_topology_device *topo_dev;
struct amdgpu_vm *vm;
+ u32 total_cwsr_size;
int err;
vm = drm_priv_to_vm(pdd->drm_priv);
@@ -302,8 +334,14 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope
amdgpu_bo_unreserve(vm->root.bo);
- kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address,
- properties->ctx_save_restore_area_size);
+ topo_dev = kfd_topology_device_by_id(pdd->dev->id);
+ if (!topo_dev)
+ return -EINVAL;
+ total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
+ * NUM_XCC(pdd->dev->xcc_mask);
+ total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
+
+ kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size);
return 0;
}
--
2.43.2
More information about the amd-gfx
mailing list