[RFC] ANDROID: GPU frequency tracing support

A periodic GPU frequency monitoring and tracing program for the
Xe driver. The implementation provides bothperiodic sampling and
event-driven frequency change notifications through the Linux
ftrace infrastructure.

Key features:
- Periodic GPU frequency sampling with configurable intervals
- Immediate frequency change reporting via tracepoints
- Integration with Linux ftrace subsystem under 'power' events
- Per-GT (Graphics Technology) monitoring support
- Dedicated workqueue for non-blocking frequency sampling
- Configurable via CONFIG_DRM_XE_GPUFREQTRACER kernel option
- The monitoring interval can be configured at runtime via the sysfs
  (default 5sec).

The sysfs entry is at:
/sys/module/xe/parameters/gpufreq_monitoring_interval_ms

The tracepoint is exposed at:
/sys/kernel/debug/tracing/events/power/gpu_frequency

Format: {unsigned int state, unsigned int gpu_id}
- state: GPU frequency in KHz
- gpu_id: GPU clock domain identifier

This enables userspace tools and system monitoring applications to track
GPU frequency changes for power management analysis, performance tuning,
and debugging purposes.

Bug: 388282937
Change-Id: I7e8025004abd4b3ffdfb4d7214a4b4896be95a64
Signed-off-by: S Sebinraj <s.sebinraj@intel.com>

Author: ssebinraj

drivers/gpu/drm/xe/Kconfig

@@ -86,6 +86,28 @@ config DRM_XE_FORCE_PROBE
 
 	  Use "!*" to block the probe of the driver for all known devices.
 
+config DRM_XE_GPUFREQTRACER
+	bool "Enable XE GPU frequency tracing"
+	depends on DRM_XE
+	default n
+	help
+	  Enable GPU frequency tracing support for Intel XE driver.
+	  This adds an ftrace tracepoint that reports GPU frequency changes
+	  at periodic boundaries (default 5 secs, configurable via the
+	  gpufreq_monitoring_interval_ms module parameter) and
+	  on direct frequency change events.
+
+	  The monitoring interval can be configured at runtime via the sysfs module parameter:
+	  /sys/module/xe/parameters/gpufreq_monitoring_interval_ms
+
+	  The tracepoint will be available at:
+	  /sys/kernel/debug/tracing/events/power/gpu_frequency
+
+	  Format: {unsigned int state, unsigned int gpu_id}
+	  Where state is the frequency in KHz and gpu_id is the GPU clock domain.
+
+	  If unsure, say N.
+
 menu "drm/Xe Debugging"
 depends on DRM_XE
 depends on EXPERT

drivers/gpu/drm/xe/Makefile

@@ -138,6 +138,9 @@ xe-$(CONFIG_PCI_IOV) += \
 	xe_pci_sriov.o \
 	xe_sriov_pf.o
 
+# GPU frequency tracer
+xe-$(CONFIG_DRM_XE_GPUFREQTRACER) += xe_gpufreqtracer/xe_gpufreqtracer.o
+
 # include helpers for tests even when XE is built-in
 ifdef CONFIG_DRM_XE_KUNIT_TEST
 xe-y += tests/xe_kunit_helpers.o

drivers/gpu/drm/xe/xe_device.c

@@ -31,6 +31,7 @@
 #include "xe_exec_queue.h"
 #include "xe_force_wake.h"
 #include "xe_ggtt.h"
+#include "xe_gpufreqtracer/xe_gpufreqtracer.h"
 #include "xe_gsc_proxy.h"
 #include "xe_gt.h"
 #include "xe_gt_mcr.h"
@@ -727,6 +728,21 @@ int xe_device_probe(struct xe_device *xe)
 
 	xe_heci_gsc_init(xe);
 
+#ifdef CONFIG_DRM_XE_GPUFREQTRACER
+	err = xe_gpufreqtracer_init(xe);
+	if (err)
+		goto err_fini_gt;
+
+	/* Start periodic monitoring on all GTs using global module parameter */
+	for_each_gt(gt, xe, id) {
+		err = xe_gpufreqtracer_start_monitoring(gt);
+		if (err) {
+			drm_err(&xe->drm, "xe_gpufreqtracer: failed to start monitoring for GT%u, err=%d\n",
+				gt->info.id, err);
+		}
+	}
+#endif
+
 	err = xe_oa_init(xe);
 	if (err)
 		goto err_fini_gt;
@@ -788,6 +804,10 @@ void xe_device_remove(struct xe_device *xe)
 
 	xe_device_remove_display(xe);
 
+#ifdef CONFIG_DRM_GPUFREQTRACER
+	xe_gpufreqtracer_fini(xe);
+#endif
+
 	xe_display_fini(xe);
 
 	xe_oa_fini(xe);

drivers/gpu/drm/xe/xe_device_types.h

@@ -33,6 +33,7 @@
 #endif
 
 struct xe_ggtt;
+struct xe_gpufreqtracer_data;
 struct xe_pat_ops;
 
 #define XE_BO_INVALID_OFFSET	LONG_MAX
@@ -496,6 +497,11 @@ struct xe_device {
 	/** @oa: oa observation subsystem */
 	struct xe_oa oa;
 
+#ifdef CONFIG_DRM_XE_GPUFREQTRACER
+	/** @gpufreqtracer_data: GPU frequency tracer data */
+	struct xe_gpufreqtracer_data *gpufreqtracer_data;
+#endif
+
 	/** @needs_flr_on_fini: requests function-reset on fini */
 	bool needs_flr_on_fini;