BACKPORT: accel/ivpu: Share NPU busy time in sysfs

The driver tracks the time spent by NPU executing jobs
and shares it through sysfs `npu_busy_time_us` file.
It can be then used by user space applications to monitor device
utilization.

NPU is considered 'busy' starting with a first job submitted
to firmware and ending when there is no more jobs pending/executing.

Tracked-On: OAM-128674
Signed-off-by: Tomasz Rusinowicz <[email protected]>
Signed-off-by: Jacek Lawrynowicz <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/drivers/accel/ivpu?id=0adff3b0ef12483a79dc8415b94547853d26d1f3
Signed-off-by: Zhao, Shirley <[email protected]>

drivers/accel/ivpu/Makefile

@@ -14,6 +14,7 @@ intel_vpu-y := \
 	ivpu_jsm_msg.o \
 	ivpu_mmu.o \
 	ivpu_mmu_context.o \
-	ivpu_pm.o
+	ivpu_pm.o \
+	ivpu_sysfs.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o

drivers/accel/ivpu/ivpu_drv.c

@@ -25,6 +25,7 @@
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
 #include "ivpu_pm.h"
+#include "ivpu_sysfs.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
@@ -661,6 +662,8 @@ static int ivpu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 	}
 
+	ivpu_sysfs_init(vdev);
+
 	ret = drm_dev_register(&vdev->drm, 0);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register DRM device: %d\n", ret);

drivers/accel/ivpu/ivpu_drv.h

@@ -118,6 +118,9 @@ struct ivpu_device {
 
 	atomic64_t unique_id_counter;
 
+	ktime_t busy_start_ts;
+	ktime_t busy_time;
+
 	struct {
 		int boot;
 		int jsm;

drivers/accel/ivpu/ivpu_job.c

@@ -323,11 +323,28 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 	return NULL;
 }
 
+static struct ivpu_job *ivpu_job_remove_from_submitted_jobs(struct ivpu_device *vdev, u32 job_id)
+{
+	struct ivpu_job *job;
+
+	xa_lock(&vdev->submitted_jobs_xa);
+	job = __xa_erase(&vdev->submitted_jobs_xa, job_id);
+
+	if (xa_empty(&vdev->submitted_jobs_xa) && job) {
+		vdev->busy_time = ktime_add(ktime_sub(ktime_get(), vdev->busy_start_ts),
+					    vdev->busy_time);
+	}
+
+	xa_unlock(&vdev->submitted_jobs_xa);
+
+	return job;
+}
+
 static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 {
 	struct ivpu_job *job;
 
-	job = xa_erase(&vdev->submitted_jobs_xa, job_id);
+	job = ivpu_job_remove_from_submitted_jobs(vdev, job_id);
 	if (!job)
 		return -ENOENT;
 
@@ -372,6 +389,7 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 	struct ivpu_device *vdev = job->vdev;
 	struct xa_limit job_id_range;
 	struct ivpu_cmdq *cmdq;
+	bool is_first_job;
 	int ret;
 
 	mutex_lock(&file_priv->lock);
@@ -388,6 +406,7 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 	job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK;
 
 	job_get(job, &job);
+	is_first_job = xa_empty(&vdev->submitted_jobs_xa);
 	ret = xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
 	if (ret) {
 		ivpu_warn_ratelimited(vdev, "Failed to allocate job id: %d\n", ret);
@@ -408,6 +427,8 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 		wmb(); /* Flush WC buffer for jobq header */
 	} else {
 		ivpu_cmdq_ring_db(vdev, cmdq);
+		if (is_first_job)
+			vdev->busy_start_ts = ktime_get();
 	}
 
 	mutex_unlock(&file_priv->lock);

drivers/accel/ivpu/ivpu_sysfs.c

@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+
+#include "ivpu_hw.h"
+#include "ivpu_sysfs.h"
+
+/*
+ * npu_busy_time_us is the time that the device spent executing jobs.
+ * The time is counted when and only when there are jobs submitted to firmware.
+ *
+ * This time can be used to measure the utilization of NPU, either by calculating
+ * npu_busy_time_us difference between two timepoints (i.e. measuring the time
+ * that the NPU was active during some workload) or monitoring utilization percentage
+ * by reading npu_busy_time_us periodically.
+ *
+ * When reading the value periodically, it shouldn't be read too often as it may have
+ * an impact on job submission performance. Recommended period is 1 second.
+ */
+static ssize_t
+npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	ktime_t total, now = 0;
+
+	xa_lock(&vdev->submitted_jobs_xa);
+	total = vdev->busy_time;
+	if (!xa_empty(&vdev->submitted_jobs_xa))
+		now = ktime_sub(ktime_get(), vdev->busy_start_ts);
+	xa_unlock(&vdev->submitted_jobs_xa);
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_us(ktime_add(total, now)));
+}
+
+static DEVICE_ATTR_RO(npu_busy_time_us);
+
+static struct attribute *ivpu_dev_attrs[] = {
+	&dev_attr_npu_busy_time_us.attr,
+	NULL,
+};
+
+static struct attribute_group ivpu_dev_attr_group = {
+	.attrs = ivpu_dev_attrs,
+};
+
+void ivpu_sysfs_init(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ret = devm_device_add_group(vdev->drm.dev, &ivpu_dev_attr_group);
+	if (ret)
+		ivpu_warn(vdev, "Failed to add group to device, ret %d", ret);
+}

drivers/accel/ivpu/ivpu_sysfs.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+
+#ifndef __IVPU_SYSFS_H__
+#define __IVPU_SYSFS_H__
+
+#include "ivpu_drv.h"
+
+void ivpu_sysfs_init(struct ivpu_device *vdev);
+
+#endif /* __IVPU_SYSFS_H__ */