drm/i915: Expose per-engine client busynesscontext-stats-pphwsp

Expose per-client and per-engine busyness under the previously added sysfs
client root.

The new files are one per-engine instance and located under the 'busy'
directory. Each contains a monotonically increasing nano-second resolution
times each client's jobs were executing on the GPU.

This enables userspace to create a top-like tool for GPU utilization:

==========================================================================
intel-gpu-top -  935/ 935 MHz;    0% RC6; 14.73 Watts;     1097 irqs/s

      IMC reads:     1401 MiB/s
     IMC writes:        4 MiB/s

          ENGINE      BUSY                                 MI_SEMA MI_WAIT
     Render/3D/0   63.73% |███████████████████           |      3%      0%
       Blitter/0    9.53% |██▊                           |      6%      0%
         Video/0   39.32% |███████████▊                  |     16%      0%
         Video/1   15.62% |████▋                         |      0%      0%
  VideoEnhance/0    0.00% |                              |      0%      0%

  PID            NAME     RCS          BCS          VCS         VECS
 4084        gem_wsim |█████▌     ||█          ||           ||           |
 4086        gem_wsim |█▌         ||           ||███        ||           |
==========================================================================

v2: Use intel_context_engine_get_busy_time.
v3: New directory structure.
v4: Rebase.
v5: sysfs_attr_init.
v6: Small tidy in i915_gem_add_client.
v7: Rebase to be engine class based.
v8:
 * Always enable stats.
 * Walk all client contexts.
v9:
 * Skip unsupported engine classes. (Chris)
 * Use scheduler caps. (Chris)
v10:
 * Use pphwsp runtime only.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

2 files changed, 100 insertions, 1 deletions

diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 3e27c55f3eba..562553b60935 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -10,8 +10,13 @@
 
 #include <drm/drm_print.h>
 
+#include <uapi/drm/i915_drm.h>
+
 #include "i915_drv.h"
 #include "i915_drm_client.h"
+#include "gem/i915_gem_context.h"
+#include "gt/intel_engine_user.h"
+#include "i915_drv.h"
 #include "i915_gem.h"
 #include "i915_utils.h"
 
@@ -47,13 +52,61 @@ show_client_pid(struct device *kdev, struct device_attribute *attr, char *buf)
 	return ret;
 }
 
+static u64
+pphwsp_busy_add(struct i915_gem_context *ctx, unsigned int class)
+{
+	struct i915_gem_engines *engines = rcu_dereference(ctx->engines);
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
+	u64 total = 0;
+
+	for_each_gem_engine(ce, engines, it) {
+		if (ce->engine->uabi_class == class)
+			total += ce->runtime.total;
+	}
+
+	return total;
+}
+
+static ssize_t
+show_client_busy(struct device *kdev, struct device_attribute *attr, char *buf)
+{
+	struct i915_engine_busy_attribute *i915_attr =
+		container_of(attr, typeof(*i915_attr), attr);
+	unsigned int class = i915_attr->engine_class;
+	struct i915_drm_client *client = i915_attr->client;
+	u64 total = atomic64_read(&client->past_runtime[class]);
+	struct list_head *list = &client->ctx_list;
+	struct i915_gem_context *ctx;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, list, client_link) {
+		total += atomic64_read(&ctx->past_runtime[class]);
+		total += pphwsp_busy_add(ctx, class);
+	}
+	rcu_read_unlock();
+
+	total *= RUNTIME_INFO(i915_attr->i915)->cs_timestamp_period_ns;
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", total);
+}
+
+static const char *uabi_class_names[] = {
+	[I915_ENGINE_CLASS_RENDER] = "0",
+	[I915_ENGINE_CLASS_COPY] = "1",
+	[I915_ENGINE_CLASS_VIDEO] = "2",
+	[I915_ENGINE_CLASS_VIDEO_ENHANCE] = "3",
+};
+
 static int
 __i915_drm_client_register(struct i915_drm_client *client,
 			   struct task_struct *task)
 {
 	struct i915_drm_clients *clients = client->clients;
+	struct drm_i915_private *i915 =
+		container_of(clients, typeof(*i915), clients);
 	struct device_attribute *attr;
-	int ret = -ENOMEM;
+	int i, ret = -ENOMEM;
 	char idstr[32];
 	char *name;
 
@@ -92,8 +145,42 @@ __i915_drm_client_register(struct i915_drm_client *client,
 	if (ret)
 		goto err_attr;
 
+	if (HAS_LOGICAL_RING_CONTEXTS(i915)) {
+		client->busy_root =
+			kobject_create_and_add("busy", client->root);
+		if (!client->busy_root)
+			goto err_attr;
+
+		for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++) {
+			struct i915_engine_busy_attribute *i915_attr =
+				&client->attr.busy[i];
+
+			if (!intel_engine_lookup_user(i915, i, 0))
+				continue;
+
+			i915_attr->client = client;
+			i915_attr->i915 = i915;
+			i915_attr->engine_class = i;
+
+			attr = &i915_attr->attr;
+
+			sysfs_attr_init(&attr->attr);
+
+			attr->attr.name = uabi_class_names[i];
+			attr->attr.mode = 0444;
+			attr->show = show_client_busy;
+
+			ret = sysfs_create_file(client->busy_root,
+						(struct attribute *)attr);
+			if (ret)
+				goto err_busy;
+		}
+	}
+
 	return 0;
 
+err_busy:
+	kobject_put(client->busy_root);
 err_attr:
 	kobject_put(client->root);
 err_client:
@@ -113,6 +200,7 @@ __i915_drm_client_unregister(struct i915_drm_client *client)
 	if (!client->root)
 		return; /* fbdev client or error during drm open */
 
+	kobject_put(fetch_and_zero(&client->busy_root));
 	kobject_put(fetch_and_zero(&client->root));
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 55f559d86516..4701f620a805 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -25,6 +25,15 @@ struct i915_drm_clients {
 	struct kobject *root;
 };
 
+struct i915_drm_client;
+
+struct i915_engine_busy_attribute {
+	struct device_attribute attr;
+	struct drm_i915_private *i915;
+	struct i915_drm_client *client;
+	unsigned int engine_class;
+};
+
 struct i915_drm_client {
 	struct kref kref;
 
@@ -43,9 +52,11 @@ struct i915_drm_client {
 	struct i915_drm_clients *clients;
 
 	struct kobject *root;
+	struct kobject *busy_root;
 	struct {
 		struct device_attribute pid;
 		struct device_attribute name;
+		struct i915_engine_busy_attribute busy[MAX_ENGINE_CLASS + 1];
 	} attr;
 
 	/**