drm/amdkfd: Add debugfs interface to trigger HWS hang

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

5 files changed, 113 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 4bd6ebfaf425..ab37d36d9cd6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
 #include "kfd_priv.h"
 
 static struct dentry *debugfs_root;
@@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, show, NULL);
 }
 
+static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
+	const char __user *user_buf, size_t size, loff_t *ppos)
+{
+	struct kfd_dev *dev;
+	char tmp[16];
+	uint32_t gpu_id;
+	int ret = -EINVAL;
+
+	memset(tmp, 0, 16);
+	if (size >= 16) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	if (copy_from_user(tmp, user_buf, size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (kstrtoint(tmp, 10, &gpu_id)) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	dev = kfd_device_by_id(gpu_id);
+	if (dev) {
+		kfd_debugfs_hang_hws(dev);
+		ret = size;
+	} else
+		pr_err("Cannot find device %d.\n", gpu_id);
+
+out:
+	return ret;
+}
+
 static const struct file_operations kfd_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = kfd_debugfs_open,
@@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = {
 	.release = single_release,
 };
 
+static const struct file_operations kfd_debugfs_hang_hws_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.write = kfd_debugfs_hang_hws_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void kfd_debugfs_init(void)
 {
 	struct dentry *ent;
@@ -65,6 +108,11 @@ void kfd_debugfs_init(void)
 	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
+
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+				  NULL,
+				  &kfd_debugfs_hang_hws_fops);
+
 	if (!ent)
 		pr_warn("Failed to create rls in kfd debugfs\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9f63ac366284..8faa8db3eba5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -914,3 +914,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
 	kfree(mem_obj);
 	return 0;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+/* This function will send a package to HIQ to hang the HWS
+ * which will trigger a GPU reset and bring the HWS back to normal state
+ */
+int kfd_debugfs_hang_hws(struct kfd_dev *dev)
+{
+	int r = 0;
+
+	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
+		pr_err("HWS is not enabled");
+		return -EINVAL;
+	}
+
+	r = pm_debugfs_hang_hws(&dev->dqm->packets);
+	if (!r)
+		r = dqm_debugfs_execute_queues(dev->dqm);
+
+	return r;
+}
+
+#endif
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 6b59eab39fbe..32e93b53e7e8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1801,4 +1801,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+{
+	int r = 0;
+
+	dqm_lock(dqm);
+	dqm->active_runlist = true;
+	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	dqm_unlock(dqm);
+
+	return r;
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index c317feb43f69..1092631765cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -418,4 +418,30 @@ out:
 	return 0;
 }
 
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+
+	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
+		buffer[0], buffer[1], buffer[2], buffer[3],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 2e03d6c80aa0..d9bf70b52857 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -995,6 +995,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data);
 int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
 int pm_debugfs_runlist(struct seq_file *m, void *data);
 
+int kfd_debugfs_hang_hws(struct kfd_dev *dev);
+int pm_debugfs_hang_hws(struct packet_manager *pm);
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+
 #else
 
 static inline void kfd_debugfs_init(void) {}