[RFC,4/5] drm/i915: Expose per-engine client busyness
diff mbox series

Message ID 20191025142131.17378-5-tvrtko.ursulin@linux.intel.com
State New
Headers show
Series
  • Per client engine busyness (all aboard the sysfs train!)
Related show

Commit Message

Tvrtko Ursulin Oct. 25, 2019, 2:21 p.m. UTC
From: Tvrtko Ursulin <tvrtko.ursulin@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.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h |   8 +++
 drivers/gpu/drm/i915/i915_gem.c | 102 ++++++++++++++++++++++++++++++--
 2 files changed, 106 insertions(+), 4 deletions(-)

Comments

Chris Wilson Oct. 25, 2019, 2:42 p.m. UTC | #1
Quoting Tvrtko Ursulin (2019-10-25 15:21:30)
> +static int busy_add(int id, void *p, void *data)
> +{
> +       struct busy_ctx *bc = data;
> +       struct i915_gem_context *ctx = p;
> +       unsigned int engine_class = bc->engine_class;
> +       struct i915_gem_engines_iter it;
> +       struct intel_context *ce;
> +       uint64_t total = bc->total;
> +
> +       for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
> +               if (ce->engine->uabi_class == engine_class)
> +                       total += ktime_to_ns(intel_context_get_busy_time(ce));
> +       }
> +       i915_gem_context_unlock_engines(ctx);
> +
> +       bc->total = total;
> +
> +       return 0;
> +}
> +
> +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);
> +       struct drm_i915_file_private *file_priv = i915_attr->file_priv;
> +       struct busy_ctx bc = { .engine_class = i915_attr->engine_class };
> +       int ret;
> +
> +       ret = mutex_lock_interruptible(&file_priv->context_idr_lock);
> +       if (ret)
> +               return ret;
> +
> +       idr_for_each(&file_priv->context_idr, busy_add, &bc);

If you don a hard hat, this can all be done under rcu_read_lock().
-Chris

Patch
diff mbox series

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b8f7b0637224..45f0e2455322 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -186,6 +186,12 @@  struct drm_i915_private;
 struct i915_mm_struct;
 struct i915_mmu_object;
 
+struct i915_engine_busy_attribute {
+	struct device_attribute attr;
+	struct drm_i915_file_private *file_priv;
+	unsigned int engine_class;
+};
+
 struct drm_i915_file_private {
 	struct drm_i915_private *dev_priv;
 
@@ -230,10 +236,12 @@  struct drm_i915_file_private {
 		char *name;
 
 		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];
 		} attr;
 	} client;
 };
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 54a00c954066..b3d21b6b570c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1512,15 +1512,67 @@  show_client_pid(struct device *kdev, struct device_attribute *attr, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%u", file_priv->client.pid);
 }
 
+struct busy_ctx {
+	unsigned int engine_class;
+	u64 total;
+};
+
+static int busy_add(int id, void *p, void *data)
+{
+	struct busy_ctx *bc = data;
+	struct i915_gem_context *ctx = p;
+	unsigned int engine_class = bc->engine_class;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
+	uint64_t total = bc->total;
+
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		if (ce->engine->uabi_class == engine_class)
+			total += ktime_to_ns(intel_context_get_busy_time(ce));
+	}
+	i915_gem_context_unlock_engines(ctx);
+
+	bc->total = total;
+
+	return 0;
+}
+
+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);
+	struct drm_i915_file_private *file_priv = i915_attr->file_priv;
+	struct busy_ctx bc = { .engine_class = i915_attr->engine_class };
+	int ret;
+
+	ret = mutex_lock_interruptible(&file_priv->context_idr_lock);
+	if (ret)
+		return ret;
+
+	idr_for_each(&file_priv->context_idr, busy_add, &bc);
+
+	mutex_unlock(&file_priv->context_idr_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", bc.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",
+};
+
 int
 i915_gem_add_client(struct drm_i915_private *i915,
 		struct drm_i915_file_private *file_priv,
 		struct task_struct *task,
 		unsigned int serial)
 {
-	int ret = -ENOMEM;
+	int i, ret = -ENOMEM;
 	struct device_attribute *attr;
-	char id[32];
+	char idstr[32];
 
 	if (!i915->clients.root)
 		return 0; /* intel_fbdev_init registers a client before sysfs */
@@ -1529,8 +1581,8 @@  i915_gem_add_client(struct drm_i915_private *i915,
 	if (!file_priv->client.name)
 		goto err_name;
 
-	snprintf(id, sizeof(id), "%u", serial);
-	file_priv->client.root = kobject_create_and_add(id,
+	snprintf(idstr, sizeof(idstr), "%u", serial);
+	file_priv->client.root = kobject_create_and_add(idstr,
 							i915->clients.root);
 	if (!file_priv->client.root)
 		goto err_client;
@@ -1557,10 +1609,44 @@  i915_gem_add_client(struct drm_i915_private *i915,
 	if (ret)
 		goto err_attr_pid;
 
+	file_priv->client.busy_root =
+			kobject_create_and_add("busy", file_priv->client.root);
+	if (!file_priv->client.busy_root)
+		goto err_busy_root;
+
+	for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++) {
+		struct i915_engine_busy_attribute *i915_attr =
+			&file_priv->client.attr.busy[i];
+
+		i915_attr->file_priv = file_priv;
+		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(file_priv->client.busy_root,
+				        (struct attribute *)attr);
+		if (ret)
+			goto err_attr_busy;
+	}
+
 	file_priv->client.pid = pid_nr(get_task_pid(task, PIDTYPE_PID));
 
 	return 0;
 
+err_attr_busy:
+	for (--i; i >= 0; i--)
+		sysfs_remove_file(file_priv->client.busy_root,
+				  (struct attribute *)&file_priv->client.attr.busy[i]);
+	kobject_put(file_priv->client.busy_root);
+err_busy_root:
+	sysfs_remove_file(file_priv->client.root,
+			  (struct attribute *)&file_priv->client.attr.pid);
 err_attr_pid:
 	sysfs_remove_file(file_priv->client.root,
 			  (struct attribute *)&file_priv->client.attr.name);
@@ -1574,9 +1660,17 @@  i915_gem_add_client(struct drm_i915_private *i915,
 
 void i915_gem_remove_client(struct drm_i915_file_private *file_priv)
 {
+	unsigned int i;
+
 	if (!file_priv->client.name)
 		return; /* intel_fbdev_init registers a client before sysfs */
 
+	for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++)
+		sysfs_remove_file(file_priv->client.busy_root,
+				  (struct attribute *)&file_priv->client.attr.busy[i]);
+
+	kobject_put(file_priv->client.busy_root);
+
 	sysfs_remove_file(file_priv->client.root,
 			  (struct attribute *)&file_priv->client.attr.pid);
 	sysfs_remove_file(file_priv->client.root,