drm/amdkfd: prepare per-process debug enable and disable

The ROCm debugger will attach to a process to debug by PTRACE and will
expect the KFD to prepare a process for the target PID, whether the
target PID has opened the KFD device or not.

This patch is to explicity handle this requirement.  Further HW mode
setting and runtime coordination requirements will be handled in
following patches.

In the case where the target process has not opened the KFD device,
a new KFD process must be created for the target PID.
The debugger as well as the target process for this case will have not
acquired any VMs so handle process restoration to correctly account for
this.

To coordinate with HSA runtime, the debugger must be aware of the target
process' runtime enablement status and will copy the runtime status
information into the debugged KFD process for later query.

On enablement, the debugger will subscribe to a set of exceptions where
each exception events will notify the debugger through a pollable FIFO
file descriptor that the debugger provides to the KFD to manage.

Finally on process termination of either the debugger or the target,
debugging must be disabled if it has not been done so.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 20 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 80cddb46657f..2baa0781eafc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1006,6 +1006,14 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 
 	pdd = qpd_to_pdd(qpd);
+
+	/* The debugger creates processes that temporarily have not acquired
+	 * all VMs for all devices and has no VMs itself.
+	 * Skip queue eviction on process eviction.
+	 */
+	if (!pdd->drm_priv)
+		goto out;
+
 	pr_debug_ratelimited("Evicting PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
@@ -1127,13 +1135,10 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 {
 	struct queue *q;
 	struct kfd_process_device *pdd;
-	uint64_t pd_base;
 	uint64_t eviction_duration;
 	int retval = 0;
 
 	pdd = qpd_to_pdd(qpd);
-	/* Retrieve PD base */
-	pd_base = amdgpu_amdkfd_gpuvm_get_process_page_dir(pdd->drm_priv);
 
 	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
@@ -1143,12 +1148,19 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 	}
 
+	/* The debugger creates processes that temporarily have not acquired
+	 * all VMs for all devices and has no VMs itself.
+	 * Skip queue restore on process restore.
+	 */
+	if (!pdd->drm_priv)
+		goto vm_not_acquired;
+
 	pr_debug_ratelimited("Restoring PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Update PD Base in QPD */
-	qpd->page_table_base = pd_base;
-	pr_debug("Updated PD address to 0x%llx\n", pd_base);
+	qpd->page_table_base = amdgpu_amdkfd_gpuvm_get_process_page_dir(pdd->drm_priv);
+	pr_debug("Updated PD address to 0x%llx\n", qpd->page_table_base);
 
 	/* activate all active queues on the qpd */
 	list_for_each_entry(q, &qpd->queues_list, list) {
@@ -1171,9 +1183,11 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	if (!dqm->dev->kfd->shared_resources.enable_mes)
 		retval = execute_queues_cpsch(dqm,
 					      KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	qpd->evicted = 0;
+
 	eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp;
 	atomic64_add(eviction_duration, &pdd->evict_duration_counter);
+vm_not_acquired:
+	qpd->evicted = 0;
 out:
 	dqm_unlock(dqm);
 	return retval;