[PATCH 06/15] drm/i915: Expose per-engine client busyness

Chris Wilson chris at chris-wilson.co.uk
Tue Jan 19 00:31:15 UTC 2021


From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

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 at intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty at intel.com>
---
 drivers/gpu/drm/i915/i915_drm_client.c | 103 ++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_drm_client.h |  10 +++
 2 files changed, 112 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index b08c8d7def02..ce51a02bf33b 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -9,6 +9,11 @@
 
 #include <drm/drm_print.h>
 
+#include <uapi/drm/i915_drm.h>
+
+#include "gem/i915_gem_context.h"
+#include "gt/intel_engine_user.h"
+
 #include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_gem.h"
@@ -55,6 +60,97 @@ 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 += pphwsp_busy_add(ctx, class);
+	rcu_read_unlock();
+
+	total *= client->clients->i915->gt.clock_period_ns;
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", total);
+}
+
+static const char * const 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 __client_register_sysfs_busy(struct i915_drm_client *client)
+{
+	struct i915_drm_clients *clients = client->clients;
+	unsigned int i;
+	int ret = 0;
+
+	if (!HAS_LOGICAL_RING_CONTEXTS(clients->i915))
+		return 0;
+
+	client->busy_root = kobject_create_and_add("busy", client->root);
+	if (!client->busy_root)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++) {
+		struct i915_engine_busy_attribute *i915_attr =
+			&client->attr.busy[i];
+		struct device_attribute *attr = &i915_attr->attr;
+
+		if (!intel_engine_lookup_user(clients->i915, i, 0))
+			continue;
+
+		i915_attr->client = client;
+		i915_attr->engine_class = i;
+
+		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;
+	}
+
+	return 0;
+
+err:
+	kobject_put(client->busy_root);
+	return ret;
+}
+
+static void __client_unregister_sysfs_busy(struct i915_drm_client *client)
+{
+	kobject_put(fetch_and_zero(&client->busy_root));
+}
+
 static int __client_register_sysfs(struct i915_drm_client *client)
 {
 	const struct {
@@ -90,9 +186,12 @@ static int __client_register_sysfs(struct i915_drm_client *client)
 
 		ret = sysfs_create_file(client->root, (struct attribute *)attr);
 		if (ret)
-			break;
+			goto out;
 	}
 
+	ret = __client_register_sysfs_busy(client);
+
+out:
 	if (ret)
 		kobject_put(client->root);
 
@@ -101,6 +200,8 @@ static int __client_register_sysfs(struct i915_drm_client *client)
 
 static void __client_unregister_sysfs(struct i915_drm_client *client)
 {
+	__client_unregister_sysfs_busy(client);
+
 	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 b74565e0dee5..00e1b83b8ce4 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -30,6 +30,14 @@ struct i915_drm_clients {
 	struct kobject *root;
 };
 
+struct i915_drm_client;
+
+struct i915_engine_busy_attribute {
+	struct device_attribute attr;
+	struct i915_drm_client *client;
+	unsigned int engine_class;
+};
+
 struct i915_drm_client_name {
 	struct rcu_head rcu;
 	struct i915_drm_client *client;
@@ -54,9 +62,11 @@ 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;
 
 	/**
-- 
2.20.1



More information about the Intel-gfx-trybot mailing list