accel/amdxdna: Expose NPU device busy time via DRM fdinfo

Expose NPU device engine busy time through DRM fdinfo to enable
standardized userspace monitoring and profiling.

Add support for reporting per-engine busy time in nanoseconds via fdinfo
using the "drm-engine-npu" key. The value reflects the accumulated NPU
device execution time for a given process, allowing userspace tools to
observe NPU device utilization without driver-specific ioctls.

Signed-off-by: Max Zhen <max.zhen@amd.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20261012180808.2548697-1-max.zhen@amd.com

Documentation/accel/amdxdna/amdnpu.rst

@@ -289,6 +289,7 @@ Example of the output showing the implemented key value pairs:
         drm-driver:	amdxdna_accel_driver
         drm-client-id:	3219
         drm-pdev:	0000:c5:00.1
+        drm-engine-npu: 14003870 ns
         amdxdna_accel_driver-heap-alloc:	60 KiB
         amdxdna_accel_driver-internal-alloc:	67588 KiB
         amdxdna_accel_driver-external-alloc:	0

drivers/accel/amdxdna/aie.c

@@ -118,6 +118,45 @@ void amdxdna_vbnv_init(struct amdxdna_dev *xdna)
 	amdxdna_update_vbnv(xdna, info->rev_vbnv_tbl, rev);
 }
 
+void amdxdna_io_stats_job_start(struct amdxdna_client *client)
+{
+	int depth;
+
+	guard(spinlock)(&client->io_stats.lock);
+
+	depth = client->io_stats.job_depth++;
+	if (!depth)
+		client->io_stats.start_time = ktime_get_ns();
+}
+
+void amdxdna_io_stats_job_done(struct amdxdna_client *client)
+{
+	u64 busy_ns;
+	int depth;
+
+	guard(spinlock)(&client->io_stats.lock);
+
+	depth = --client->io_stats.job_depth;
+	if (!depth) {
+		busy_ns = ktime_get_ns() - client->io_stats.start_time;
+		client->io_stats.start_time = 0;
+		client->io_stats.busy_time += busy_ns;
+	}
+}
+
+u64 amdxdna_io_stats_busy_time_ns(struct amdxdna_client *client)
+{
+	u64 busy_ns;
+
+	guard(spinlock)(&client->io_stats.lock);
+
+	busy_ns = client->io_stats.busy_time;
+	if (client->io_stats.job_depth)
+		busy_ns += ktime_get_ns() - client->io_stats.start_time;
+
+	return busy_ns;
+}
+
 int amdxdna_get_metadata(struct aie_device *aie,
 			 struct amdxdna_client *client,
 			 struct amdxdna_drm_get_info *args)

drivers/accel/amdxdna/aie.h

@@ -117,4 +117,8 @@ void aie_smu_fini(struct smu_device *smu);
 int aie_smu_set_clocks(struct smu_device *smu, u32 *npuclk, u32 *hclk);
 int aie_smu_set_dpm(struct smu_device *smu, u32 dpm_level);
 
+void amdxdna_io_stats_job_start(struct amdxdna_client *client);
+void amdxdna_io_stats_job_done(struct amdxdna_client *client);
+u64 amdxdna_io_stats_busy_time_ns(struct amdxdna_client *client);
+
 #endif /* _AIE_H_ */

drivers/accel/amdxdna/aie2_ctx.c

@@ -290,6 +290,7 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
 	int ret = 0;
 	u32 status;
 
+	amdxdna_io_stats_job_done(job->hwctx->client);
 	cmd_abo = job->cmd_bo;
 
 	if (unlikely(job->job_timeout)) {
@@ -322,6 +323,8 @@ aie2_sched_drvcmd_resp_handler(void *handle, void __iomem *data, size_t size)
 	struct amdxdna_sched_job *job = handle;
 	int ret = 0;
 
+	amdxdna_io_stats_job_done(job->hwctx->client);
+
 	if (unlikely(!data || size != sizeof(u32))) {
 		job->drv_cmd->result = U32_MAX;
 		ret = -EINVAL;
@@ -344,6 +347,7 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size)
 	u32 cmd_status;
 	int ret = 0;
 
+	amdxdna_io_stats_job_done(job->hwctx->client);
 	cmd_abo = job->cmd_bo;
 
 	if (unlikely(job->job_timeout)) {
@@ -405,6 +409,7 @@ aie2_sched_job_run(struct drm_sched_job *sched_job)
 	kref_get(&job->refcnt);
 	fence = dma_fence_get(job->fence);
 
+	amdxdna_io_stats_job_start(job->hwctx->client);
 	if (job->drv_cmd) {
 		switch (job->drv_cmd->opcode) {
 		case SYNC_DEBUG_BO:
@@ -432,6 +437,7 @@ aie2_sched_job_run(struct drm_sched_job *sched_job)
 
 out:
 	if (ret) {
+		amdxdna_io_stats_job_done(job->hwctx->client);
 		dma_fence_put(job->fence);
 		aie2_job_put(job);
 		mmput(job->mm);

drivers/accel/amdxdna/amdxdna_pci_drv.c

@@ -14,6 +14,7 @@
 #include <linux/iommu.h>
 #include <linux/pci.h>
 
+#include "aie.h"
 #include "amdxdna_cbuf.h"
 #include "amdxdna_ctx.h"
 #include "amdxdna_debugfs.h"
@@ -151,6 +152,8 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp)
 	filp->driver_priv = client;
 	client->filp = filp;
 
+	spin_lock_init(&client->io_stats.lock);
+
 	XDNA_DBG(xdna, "pid %d opened", client->pid);
 	return 0;
 
@@ -287,6 +290,9 @@ static void amdxdna_show_fdinfo(struct drm_printer *p, struct drm_file *filp)
 	size_t heap_usage, external_usage, internal_usage;
 	char *drv_name = filp->minor->dev->driver->name;
 
+	drm_printf(p, "drm-engine-npu:\t%llu ns\n",
+		   amdxdna_io_stats_busy_time_ns(client));
+
 	mutex_lock(&client->mm_lock);
 
 	heap_usage = client->heap_usage;

drivers/accel/amdxdna/amdxdna_pci_drv.h

@@ -143,6 +143,13 @@ struct amdxdna_device_id {
 	const struct amdxdna_dev_info *dev_info;
 };
 
+struct amdxdna_io_stats {
+	spinlock_t			lock; /* protect io stats */
+	int				job_depth;
+	u64				start_time;
+	u64				busy_time;
+};
+
 /*
  * struct amdxdna_client - amdxdna client
  * A per fd data structure for managing context and other user process stuffs.
@@ -169,6 +176,8 @@ struct amdxdna_client {
 	size_t				heap_usage;
 	size_t				total_bo_usage;
 	size_t				total_int_bo_usage;
+
+	struct amdxdna_io_stats		io_stats;
 };
 
 #define amdxdna_for_each_hwctx(client, hwctx_id, entry)		\