* [Intel-gfx] [PATCH 01/10] drm/i915: Expose list of clients in sysfs
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 02/10] drm/i915: Update client name on context create Tvrtko Ursulin
` (7 subsequent siblings)
8 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Expose a list of clients with open file handles in sysfs.
This will be a basis for a top-like utility showing per-client and per-
engine GPU load.
Currently we only expose each client's pid and name under opaque numbered
directories in /sys/class/drm/card0/clients/.
For instance:
/sys/class/drm/card0/clients/3/name: Xorg
/sys/class/drm/card0/clients/3/pid: 5664
v2:
Chris Wilson:
* Enclose new members into dedicated structs.
* Protect against failed sysfs registration.
v3:
* sysfs_attr_init.
v4:
* Fix for internal clients.
v5:
* Use cyclic ida for client id. (Chris)
* Do not leak pid reference. (Chris)
* Tidy code with some locals.
v6:
* Use xa_alloc_cyclic to simplify locking. (Chris)
* No need to unregister individial sysfs files. (Chris)
* Rebase on top of fpriv kref.
* Track client closed status and reflect in sysfs.
v7:
* Make drm_client more standalone concept.
v8:
* Simplify sysfs show. (Chris)
* Always track name and pid.
v9:
* Fix cyclic id assignment.
v10:
* No need for a mutex around xa_alloc_cyclic.
* Refactor sysfs into own function.
* Unregister sysfs before freeing pid and name.
* Move clients setup into own function.
v11:
* Call clients init directly from driver init. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915_drm_client.c | 179 +++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_drm_client.h | 64 +++++++++
drivers/gpu/drm/i915/i915_drv.c | 3 +
drivers/gpu/drm/i915/i915_drv.h | 5 +
drivers/gpu/drm/i915/i915_gem.c | 25 +++-
drivers/gpu/drm/i915/i915_sysfs.c | 8 ++
7 files changed, 283 insertions(+), 4 deletions(-)
create mode 100644 drivers/gpu/drm/i915/i915_drm_client.c
create mode 100644 drivers/gpu/drm/i915/i915_drm_client.h
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 99cd3d25f816..d183cc490a94 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -36,7 +36,8 @@ subdir-ccflags-y += -I$(srctree)/$(src)
# Please keep these build lists sorted!
# core driver code
-i915-y += i915_drv.o \
+i915-y += i915_drm_client.o \
+ i915_drv.o \
i915_irq.o \
i915_getparam.o \
i915_params.o \
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
new file mode 100644
index 000000000000..2067fbcdb795
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "i915_drm_client.h"
+#include "i915_gem.h"
+#include "i915_utils.h"
+
+void i915_drm_clients_init(struct i915_drm_clients *clients)
+{
+ clients->next_id = 0;
+ xa_init_flags(&clients->xarray, XA_FLAGS_ALLOC);
+}
+
+static ssize_t
+show_client_name(struct device *kdev, struct device_attribute *attr, char *buf)
+{
+ struct i915_drm_client *client =
+ container_of(attr, typeof(*client), attr.name);
+
+ return snprintf(buf, PAGE_SIZE,
+ READ_ONCE(client->closed) ? "<%s>" : "%s",
+ client->name);
+}
+
+static ssize_t
+show_client_pid(struct device *kdev, struct device_attribute *attr, char *buf)
+{
+ struct i915_drm_client *client =
+ container_of(attr, typeof(*client), attr.pid);
+
+ return snprintf(buf, PAGE_SIZE,
+ READ_ONCE(client->closed) ? "<%u>" : "%u",
+ pid_nr(client->pid));
+}
+
+static int
+__client_register_sysfs(struct i915_drm_client *client)
+{
+ const struct {
+ const char *name;
+ struct device_attribute *attr;
+ ssize_t (*show)(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+ } files[] = {
+ { "name", &client->attr.name, show_client_name },
+ { "pid", &client->attr.pid, show_client_pid },
+ };
+ unsigned int i;
+ char buf[16];
+ int ret;
+
+ ret = scnprintf(buf, sizeof(buf), "%u", client->id);
+ if (ret == sizeof(buf))
+ return -EINVAL;
+
+ client->root = kobject_create_and_add(buf, client->clients->root);
+ if (!client->root)
+ return -ENOMEM;
+
+ for (i = 0; i < ARRAY_SIZE(files); i++) {
+ struct device_attribute *attr = files[i].attr;
+
+ sysfs_attr_init(&attr->attr);
+
+ attr->attr.name = files[i].name;
+ attr->attr.mode = 0444;
+ attr->show = files[i].show;
+
+ ret = sysfs_create_file(client->root, (struct attribute *)attr);
+ if (ret)
+ break;
+ }
+
+ if (ret)
+ kobject_put(client->root);
+
+ return ret;
+}
+
+static void __client_unregister_sysfs(struct i915_drm_client *client)
+{
+ kobject_put(fetch_and_zero(&client->root));
+}
+
+static int
+__i915_drm_client_register(struct i915_drm_client *client,
+ struct task_struct *task)
+{
+ struct i915_drm_clients *clients = client->clients;
+ char *name;
+ int ret;
+
+ name = kstrdup(task->comm, GFP_KERNEL);
+ if (!name)
+ return -ENOMEM;
+
+ client->pid = get_task_pid(task, PIDTYPE_PID);
+ client->name = name;
+
+ if (!clients->root)
+ return 0; /* intel_fbdev_init registers a client before sysfs */
+
+ ret = __client_register_sysfs(client);
+ if (ret)
+ goto err_sysfs;
+
+ return 0;
+
+err_sysfs:
+ put_pid(client->pid);
+ kfree(client->name);
+
+ return ret;
+}
+
+static void
+__i915_drm_client_unregister(struct i915_drm_client *client)
+{
+ __client_unregister_sysfs(client);
+
+ put_pid(fetch_and_zero(&client->pid));
+ kfree(fetch_and_zero(&client->name));
+}
+
+struct i915_drm_client *
+i915_drm_client_add(struct i915_drm_clients *clients, struct task_struct *task)
+{
+ struct i915_drm_client *client;
+ int ret;
+
+ client = kzalloc(sizeof(*client), GFP_KERNEL);
+ if (!client)
+ return ERR_PTR(-ENOMEM);
+
+ kref_init(&client->kref);
+ client->clients = clients;
+
+ ret = xa_alloc_cyclic(&clients->xarray, &client->id, client,
+ xa_limit_32b, &clients->next_id, GFP_KERNEL);
+ if (ret)
+ goto err_id;
+
+ ret = __i915_drm_client_register(client, task);
+ if (ret)
+ goto err_register;
+
+ return client;
+
+err_register:
+ xa_erase(&clients->xarray, client->id);
+err_id:
+ kfree(client);
+
+ return ERR_PTR(ret);
+}
+
+void __i915_drm_client_free(struct kref *kref)
+{
+ struct i915_drm_client *client =
+ container_of(kref, typeof(*client), kref);
+
+ __i915_drm_client_unregister(client);
+ xa_erase(&client->clients->xarray, client->id);
+ kfree_rcu(client, rcu);
+}
+
+void i915_drm_client_close(struct i915_drm_client *client)
+{
+ GEM_BUG_ON(READ_ONCE(client->closed));
+ WRITE_ONCE(client->closed, true);
+ i915_drm_client_put(client);
+}
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
new file mode 100644
index 000000000000..af6998c74d4c
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __I915_DRM_CLIENT_H__
+#define __I915_DRM_CLIENT_H__
+
+#include <linux/device.h>
+#include <linux/kobject.h>
+#include <linux/kref.h>
+#include <linux/pid.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/xarray.h>
+
+struct i915_drm_clients {
+ struct xarray xarray;
+ u32 next_id;
+
+ struct kobject *root;
+};
+
+struct i915_drm_client {
+ struct kref kref;
+
+ struct rcu_head rcu;
+
+ unsigned int id;
+ struct pid *pid;
+ char *name;
+ bool closed;
+
+ struct i915_drm_clients *clients;
+
+ struct kobject *root;
+ struct {
+ struct device_attribute pid;
+ struct device_attribute name;
+ } attr;
+};
+
+void i915_drm_clients_init(struct i915_drm_clients *clients);
+
+static inline struct i915_drm_client *
+i915_drm_client_get(struct i915_drm_client *client)
+{
+ kref_get(&client->kref);
+ return client;
+}
+
+void __i915_drm_client_free(struct kref *kref);
+
+static inline void i915_drm_client_put(struct i915_drm_client *client)
+{
+ kref_put(&client->kref, __i915_drm_client_free);
+}
+
+void i915_drm_client_close(struct i915_drm_client *client);
+
+struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients,
+ struct task_struct *task);
+
+#endif /* !__I915_DRM_CLIENT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 48ba37e35bea..02d38024e3d7 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -69,6 +69,7 @@
#include "gt/intel_rc6.h"
#include "i915_debugfs.h"
+#include "i915_drm_client.h"
#include "i915_drv.h"
#include "i915_ioc32.h"
#include "i915_irq.h"
@@ -456,6 +457,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
i915_gem_init_early(dev_priv);
+ i915_drm_clients_init(&dev_priv->clients);
+
/* This must be called before any calls to HAS_PCH_* */
intel_detect_pch(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a7ea1d855359..d805120785c3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -91,6 +91,7 @@
#include "intel_wakeref.h"
#include "intel_wopcm.h"
+#include "i915_drm_client.h"
#include "i915_gem.h"
#include "i915_gem_gtt.h"
#include "i915_gpu_error.h"
@@ -226,6 +227,8 @@ struct drm_i915_file_private {
/** ban_score: Accumulated score of all ctx bans and fast hangs. */
atomic_t ban_score;
unsigned long hang_timestamp;
+
+ struct i915_drm_client *client;
};
/* Interface history:
@@ -1198,6 +1201,8 @@ struct drm_i915_private {
struct i915_pmu pmu;
+ struct i915_drm_clients clients;
+
struct i915_hdcp_comp_master *hdcp_master;
bool hdcp_comp_added;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 762b50b08d73..24348df7b231 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1231,6 +1231,8 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list));
GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
drm_WARN_ON(&dev_priv->drm, dev_priv->mm.shrink_count);
+ drm_WARN_ON(&dev_priv->drm, !xa_empty(&dev_priv->clients.xarray));
+ xa_destroy(&dev_priv->clients.xarray);
}
int i915_gem_freeze(struct drm_i915_private *dev_priv)
@@ -1285,6 +1287,8 @@ void i915_gem_release(struct drm_device *dev, struct drm_file *file)
struct drm_i915_file_private *file_priv = file->driver_priv;
struct i915_request *request;
+ i915_drm_client_close(file_priv->client);
+
/* Clean up our request list when the client is going away, so that
* later retire_requests won't dereference our soon-to-be-gone
* file_priv.
@@ -1298,17 +1302,25 @@ void i915_gem_release(struct drm_device *dev, struct drm_file *file)
int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
{
struct drm_i915_file_private *file_priv;
- int ret;
+ struct i915_drm_client *client;
+ int ret = -ENOMEM;
DRM_DEBUG("\n");
file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
if (!file_priv)
- return -ENOMEM;
+ goto err_alloc;
+
+ client = i915_drm_client_add(&i915->clients, current);
+ if (IS_ERR(client)) {
+ ret = PTR_ERR(client);
+ goto err_client;
+ }
file->driver_priv = file_priv;
file_priv->dev_priv = i915;
file_priv->file = file;
+ file_priv->client = client;
spin_lock_init(&file_priv->mm.lock);
INIT_LIST_HEAD(&file_priv->mm.request_list);
@@ -1318,8 +1330,15 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
ret = i915_gem_context_open(i915, file);
if (ret)
- kfree(file_priv);
+ goto err_context;
+
+ return 0;
+err_context:
+ i915_drm_client_close(client);
+err_client:
+ kfree(file_priv);
+err_alloc:
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 45d32ef42787..b7d4a6d2dd5c 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -560,6 +560,11 @@ void i915_setup_sysfs(struct drm_i915_private *dev_priv)
struct device *kdev = dev_priv->drm.primary->kdev;
int ret;
+ dev_priv->clients.root =
+ kobject_create_and_add("clients", &kdev->kobj);
+ if (!dev_priv->clients.root)
+ DRM_ERROR("Per-client sysfs setup failed\n");
+
#ifdef CONFIG_PM
if (HAS_RC6(dev_priv)) {
ret = sysfs_merge_group(&kdev->kobj,
@@ -627,4 +632,7 @@ void i915_teardown_sysfs(struct drm_i915_private *dev_priv)
sysfs_unmerge_group(&kdev->kobj, &rc6_attr_group);
sysfs_unmerge_group(&kdev->kobj, &rc6p_attr_group);
#endif
+
+ if (dev_priv->clients.root)
+ kobject_put(dev_priv->clients.root);
}
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* [Intel-gfx] [PATCH 02/10] drm/i915: Update client name on context create
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 01/10] drm/i915: Expose list of clients in sysfs Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 03/10] drm/i915: Make GEM contexts track DRM clients Tvrtko Ursulin
` (6 subsequent siblings)
8 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Some clients have the DRM fd passed to them over a socket by the X server.
Grab the real client and pid when they create their first context and
update the exposed data for more useful enumeration.
To enable lockless access to client name and pid data from the following
patches, we also make these fields rcu protected. In this way asynchronous
code paths where both contexts which remain after the client exit, and
access to client name and pid as they are getting updated due context
creation running in parallel with name/pid queries.
v2:
* Do not leak the pid reference and borrow context idr_lock. (Chris)
v3:
* More avoiding leaks. (Chris)
v4:
* Move update completely to drm client. (Chris)
* Do not lose previous client data on failure to re-register and simplify
update to only touch what it needs.
v5:
* Reuse ext_data local. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 5 +
drivers/gpu/drm/i915/i915_drm_client.c | 103 ++++++++++++++++++--
drivers/gpu/drm/i915/i915_drm_client.h | 10 +-
3 files changed, 106 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index c0e476fcd1fa..841838d6c1dd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -74,6 +74,7 @@
#include "gt/intel_engine_user.h"
#include "gt/intel_ring.h"
+#include "i915_drm_client.h"
#include "i915_gem_context.h"
#include "i915_globals.h"
#include "i915_trace.h"
@@ -2357,6 +2358,10 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
return -EIO;
}
+ ret = i915_drm_client_update(ext_data.fpriv->client, current);
+ if (ret)
+ return ret;
+
ext_data.ctx = i915_gem_create_context(i915, args->flags);
if (IS_ERR(ext_data.ctx))
return PTR_ERR(ext_data.ctx);
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2067fbcdb795..342a11554573 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -7,6 +7,9 @@
#include <linux/slab.h>
#include <linux/types.h>
+#include <drm/drm_print.h>
+
+#include "i915_drv.h"
#include "i915_drm_client.h"
#include "i915_gem.h"
#include "i915_utils.h"
@@ -22,10 +25,15 @@ show_client_name(struct device *kdev, struct device_attribute *attr, char *buf)
{
struct i915_drm_client *client =
container_of(attr, typeof(*client), attr.name);
+ int ret;
+
+ rcu_read_lock();
+ ret = snprintf(buf, PAGE_SIZE,
+ READ_ONCE(client->closed) ? "<%s>" : "%s",
+ rcu_dereference(client->name));
+ rcu_read_unlock();
- return snprintf(buf, PAGE_SIZE,
- READ_ONCE(client->closed) ? "<%s>" : "%s",
- client->name);
+ return ret;
}
static ssize_t
@@ -33,10 +41,15 @@ show_client_pid(struct device *kdev, struct device_attribute *attr, char *buf)
{
struct i915_drm_client *client =
container_of(attr, typeof(*client), attr.pid);
+ int ret;
- return snprintf(buf, PAGE_SIZE,
- READ_ONCE(client->closed) ? "<%u>" : "%u",
- pid_nr(client->pid));
+ rcu_read_lock();
+ ret = snprintf(buf, PAGE_SIZE,
+ READ_ONCE(client->closed) ? "<%u>" : "%u",
+ pid_nr(rcu_dereference(client->pid)));
+ rcu_read_unlock();
+
+ return ret;
}
static int
@@ -101,8 +114,8 @@ __i915_drm_client_register(struct i915_drm_client *client,
if (!name)
return -ENOMEM;
- client->pid = get_task_pid(task, PIDTYPE_PID);
- client->name = name;
+ rcu_assign_pointer(client->pid, get_task_pid(task, PIDTYPE_PID));
+ rcu_assign_pointer(client->name, name);
if (!clients->root)
return 0; /* intel_fbdev_init registers a client before sysfs */
@@ -125,8 +138,8 @@ __i915_drm_client_unregister(struct i915_drm_client *client)
{
__client_unregister_sysfs(client);
- put_pid(fetch_and_zero(&client->pid));
- kfree(fetch_and_zero(&client->name));
+ put_pid(rcu_replace_pointer(client->pid, NULL, true));
+ kfree(rcu_replace_pointer(client->name, NULL, true));
}
struct i915_drm_client *
@@ -140,6 +153,7 @@ i915_drm_client_add(struct i915_drm_clients *clients, struct task_struct *task)
return ERR_PTR(-ENOMEM);
kref_init(&client->kref);
+ mutex_init(&client->update_lock);
client->clients = clients;
ret = xa_alloc_cyclic(&clients->xarray, &client->id, client,
@@ -177,3 +191,72 @@ void i915_drm_client_close(struct i915_drm_client *client)
WRITE_ONCE(client->closed, true);
i915_drm_client_put(client);
}
+
+struct client_update_free {
+ struct rcu_head rcu;
+ struct pid *pid;
+ char *name;
+};
+
+static void __client_update_free(struct rcu_head *rcu)
+{
+ struct client_update_free *old = container_of(rcu, typeof(*old), rcu);
+
+ put_pid(old->pid);
+ kfree(old->name);
+ kfree(old);
+}
+
+int
+i915_drm_client_update(struct i915_drm_client *client,
+ struct task_struct *task)
+{
+ struct drm_i915_private *i915 =
+ container_of(client->clients, typeof(*i915), clients);
+ struct client_update_free *old;
+ struct pid *pid;
+ char *name;
+ int ret;
+
+ old = kmalloc(sizeof(*old), GFP_KERNEL);
+ if (!old)
+ return -ENOMEM;
+
+ ret = mutex_lock_interruptible(&client->update_lock);
+ if (ret)
+ goto out_free;
+
+ pid = get_task_pid(task, PIDTYPE_PID);
+ if (!pid)
+ goto out_pid;
+ if (pid == client->pid)
+ goto out_name;
+
+ name = kstrdup(task->comm, GFP_KERNEL);
+ if (!name) {
+ drm_notice(&i915->drm,
+ "Failed to update client id=%u,name=%s,pid=%u! (%d)\n",
+ client->id, client->name, pid_nr(client->pid), ret);
+ goto out_name;
+ }
+
+ init_rcu_head(&old->rcu);
+
+ old->pid = rcu_replace_pointer(client->pid, pid, true);
+ old->name = rcu_replace_pointer(client->name, name, true);
+
+ mutex_unlock(&client->update_lock);
+
+ call_rcu(&old->rcu, __client_update_free);
+
+ return 0;
+
+out_name:
+ put_pid(pid);
+out_pid:
+ mutex_unlock(&client->update_lock);
+out_free:
+ kfree(old);
+
+ return ret;
+}
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index af6998c74d4c..11b48383881d 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -9,6 +9,7 @@
#include <linux/device.h>
#include <linux/kobject.h>
#include <linux/kref.h>
+#include <linux/mutex.h>
#include <linux/pid.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
@@ -26,9 +27,11 @@ struct i915_drm_client {
struct rcu_head rcu;
+ struct mutex update_lock; /* Serializes name and pid updates. */
+
unsigned int id;
- struct pid *pid;
- char *name;
+ struct pid __rcu *pid;
+ char __rcu *name;
bool closed;
struct i915_drm_clients *clients;
@@ -61,4 +64,7 @@ void i915_drm_client_close(struct i915_drm_client *client);
struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients,
struct task_struct *task);
+int i915_drm_client_update(struct i915_drm_client *client,
+ struct task_struct *task);
+
#endif /* !__I915_DRM_CLIENT_H__ */
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* [Intel-gfx] [PATCH 03/10] drm/i915: Make GEM contexts track DRM clients
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 01/10] drm/i915: Expose list of clients in sysfs Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 02/10] drm/i915: Update client name on context create Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 13:47 ` Chris Wilson
2020-03-18 12:11 ` [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context Tvrtko Ursulin
` (5 subsequent siblings)
8 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
If we make GEM contexts keep a reference to i915_drm_client for the whole
of their lifetime, we can consolidate the current task pid and name usage
by getting it from the client.
v2:
* Don't bother supporting selftests contexts from debugfs. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 23 ++++++++++++---
.../gpu/drm/i915/gem/i915_gem_context_types.h | 13 ++-------
drivers/gpu/drm/i915/i915_debugfs.c | 29 +++++++------------
drivers/gpu/drm/i915/i915_gpu_error.c | 21 ++++++++------
4 files changed, 44 insertions(+), 42 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 841838d6c1dd..9afc60ab95e0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -340,8 +340,13 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
static void i915_gem_context_free(struct i915_gem_context *ctx)
{
+ struct i915_drm_client *client = ctx->client;
+
GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
+ if (client)
+ i915_drm_client_put(client);
+
spin_lock(&ctx->i915->gem.contexts.lock);
list_del(&ctx->link);
spin_unlock(&ctx->i915->gem.contexts.lock);
@@ -351,7 +356,6 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
if (ctx->timeline)
intel_timeline_put(ctx->timeline);
- put_pid(ctx->pid);
mutex_destroy(&ctx->mutex);
kfree_rcu(ctx, rcu);
@@ -911,6 +915,7 @@ static int gem_context_register(struct i915_gem_context *ctx,
struct drm_i915_file_private *fpriv,
u32 *id)
{
+ struct i915_drm_client *client;
struct i915_address_space *vm;
int ret;
@@ -922,15 +927,25 @@ static int gem_context_register(struct i915_gem_context *ctx,
WRITE_ONCE(vm->file, fpriv); /* XXX */
mutex_unlock(&ctx->mutex);
- ctx->pid = get_task_pid(current, PIDTYPE_PID);
+ client = i915_drm_client_get(fpriv->client);
+
+ rcu_read_lock();
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
- current->comm, pid_nr(ctx->pid));
+ rcu_dereference(client->name),
+ pid_nr(rcu_dereference(client->pid)));
+ rcu_read_unlock();
/* And finally expose ourselves to userspace via the idr */
ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
if (ret)
- put_pid(fetch_and_zero(&ctx->pid));
+ goto err;
+
+ ctx->client = client;
+ return 0;
+
+err:
+ i915_drm_client_put(client);
return ret;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 28760bd03265..b0e03380c690 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -96,20 +96,13 @@ struct i915_gem_context {
*/
struct i915_address_space __rcu *vm;
- /**
- * @pid: process id of creator
- *
- * Note that who created the context may not be the principle user,
- * as the context may be shared across a local socket. However,
- * that should only affect the default context, all contexts created
- * explicitly by the client are expected to be isolated.
- */
- struct pid *pid;
-
/** link: place with &drm_i915_private.context_list */
struct list_head link;
struct llist_node free_link;
+ /** client: struct i915_drm_client */
+ struct i915_drm_client *client;
+
/**
* @ref: reference count
*
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6ca797128aa1..03018a108916 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -330,17 +330,15 @@ static void print_context_stats(struct seq_file *m,
.vm = rcu_access_pointer(ctx->vm),
};
struct drm_file *file = ctx->file_priv->file;
- struct task_struct *task;
char name[80];
rcu_read_lock();
+
idr_for_each(&file->object_idr, per_file_stats, &stats);
- rcu_read_unlock();
- rcu_read_lock();
- task = pid_task(ctx->pid ?: file->pid, PIDTYPE_PID);
snprintf(name, sizeof(name), "%s",
- task ? task->comm : "<unknown>");
+ rcu_dereference(ctx->client->name));
+
rcu_read_unlock();
print_file_stats(m, name, stats);
@@ -1059,20 +1057,13 @@ static int i915_context_status(struct seq_file *m, void *unused)
spin_unlock(&i915->gem.contexts.lock);
seq_puts(m, "HW context ");
- if (ctx->pid) {
- struct task_struct *task;
-
- task = get_pid_task(ctx->pid, PIDTYPE_PID);
- if (task) {
- seq_printf(m, "(%s [%d]) ",
- task->comm, task->pid);
- put_task_struct(task);
- }
- } else if (IS_ERR(ctx->file_priv)) {
- seq_puts(m, "(deleted) ");
- } else {
- seq_puts(m, "(kernel) ");
- }
+
+ rcu_read_lock();
+ seq_printf(m, "(%s [%d]) %s",
+ rcu_dereference(ctx->client->name),
+ pid_nr(rcu_dereference(ctx->client->pid)),
+ ctx->client->closed ? "(closed) " : "");
+ rcu_read_unlock();
seq_putc(m, ctx->remap_slice ? 'R' : 'r');
seq_putc(m, '\n');
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2a4cd0ba5464..653e1bc5050e 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1221,7 +1221,8 @@ static void record_request(const struct i915_request *request,
rcu_read_lock();
ctx = rcu_dereference(request->context->gem_context);
if (ctx)
- erq->pid = pid_nr(ctx->pid);
+ erq->pid = I915_SELFTEST_ONLY(!ctx->client) ?
+ 0 : pid_nr(rcu_dereference(ctx->client->pid));
rcu_read_unlock();
}
@@ -1241,23 +1242,25 @@ static bool record_context(struct i915_gem_context_coredump *e,
const struct i915_request *rq)
{
struct i915_gem_context *ctx;
- struct task_struct *task;
bool simulated;
rcu_read_lock();
+
ctx = rcu_dereference(rq->context->gem_context);
if (ctx && !kref_get_unless_zero(&ctx->ref))
ctx = NULL;
- rcu_read_unlock();
- if (!ctx)
+ if (!ctx) {
+ rcu_read_unlock();
return true;
+ }
- rcu_read_lock();
- task = pid_task(ctx->pid, PIDTYPE_PID);
- if (task) {
- strcpy(e->comm, task->comm);
- e->pid = task->pid;
+ if (I915_SELFTEST_ONLY(!ctx->client)) {
+ strcpy(e->comm, "[kernel]");
+ } else {
+ strcpy(e->comm, rcu_dereference(ctx->client->name));
+ e->pid = pid_nr(rcu_dereference(ctx->client->pid));
}
+
rcu_read_unlock();
e->sched_attr = ctx->sched;
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (2 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 03/10] drm/i915: Make GEM contexts track DRM clients Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 13:49 ` Chris Wilson
2020-03-18 12:11 ` [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts Tvrtko Ursulin
` (4 subsequent siblings)
8 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
I need to keep the GEM context around a bit longer so adding an explicit
flag for syncing execbuf with closed/abandonded contexts.
v2:
* Use already available context flags. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 ++-
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/gt/intel_context_types.h | 1 +
3 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9afc60ab95e0..7c119a3a2cbd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -579,7 +579,8 @@ static void engines_idle_release(struct i915_gem_context *ctx,
int err = 0;
/* serialises with execbuf */
- RCU_INIT_POINTER(ce->gem_context, NULL);
+ set_bit(INTEL_CONTEXT_CLOSED, &ce->flags);
+
if (!intel_context_pin_if_active(ce))
continue;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d3f4f28e9468..875da020d6c8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2316,7 +2316,7 @@ static void eb_request_add(struct i915_execbuffer *eb)
prev = __i915_request_commit(rq);
/* Check that the context wasn't destroyed before submission */
- if (likely(rcu_access_pointer(eb->context->gem_context))) {
+ if (likely(!test_bit(INTEL_CONTEXT_CLOSED, &eb->context->flags))) {
attr = eb->gem_context->sched;
/*
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 0f3b68b95c56..d5925c25f109 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -66,6 +66,7 @@ struct intel_context {
#define CONTEXT_BANNED 4
#define CONTEXT_FORCE_SINGLE_SUBMISSION 5
#define CONTEXT_NOPREEMPT 6
+#define INTEL_CONTEXT_CLOSED 7
u32 *lrc_reg_state;
u64 lrc_desc;
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context
2020-03-18 12:11 ` [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context Tvrtko Ursulin
@ 2020-03-18 13:49 ` Chris Wilson
2020-03-18 13:55 ` Tvrtko Ursulin
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 13:49 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 12:11:33)
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> I need to keep the GEM context around a bit longer so adding an explicit
> flag for syncing execbuf with closed/abandonded contexts.
>
> v2:
> * Use already available context flags. (Chris)
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
> drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 ++-
> drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
> drivers/gpu/drm/i915/gt/intel_context_types.h | 1 +
> 3 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index 9afc60ab95e0..7c119a3a2cbd 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -579,7 +579,8 @@ static void engines_idle_release(struct i915_gem_context *ctx,
> int err = 0;
>
> /* serialises with execbuf */
> - RCU_INIT_POINTER(ce->gem_context, NULL);
> + set_bit(INTEL_CONTEXT_CLOSED, &ce->flags);
> +
> if (!intel_context_pin_if_active(ce))
> continue;
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> index d3f4f28e9468..875da020d6c8 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> @@ -2316,7 +2316,7 @@ static void eb_request_add(struct i915_execbuffer *eb)
> prev = __i915_request_commit(rq);
>
> /* Check that the context wasn't destroyed before submission */
> - if (likely(rcu_access_pointer(eb->context->gem_context))) {
> + if (likely(!test_bit(INTEL_CONTEXT_CLOSED, &eb->context->flags))) {
> attr = eb->gem_context->sched;
>
> /*
> diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
> index 0f3b68b95c56..d5925c25f109 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
> @@ -66,6 +66,7 @@ struct intel_context {
> #define CONTEXT_BANNED 4
> #define CONTEXT_FORCE_SINGLE_SUBMISSION 5
> #define CONTEXT_NOPREEMPT 6
> +#define INTEL_CONTEXT_CLOSED 7
Trying to start a flame war? :)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
With this flag, we can start banning contexts after a GPU hang on a
closed context _again_. That might justify applying immediately.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context
2020-03-18 13:49 ` Chris Wilson
@ 2020-03-18 13:55 ` Tvrtko Ursulin
0 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 13:55 UTC (permalink / raw)
To: Chris Wilson, Intel-gfx
On 18/03/2020 13:49, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-03-18 12:11:33)
>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>
>> I need to keep the GEM context around a bit longer so adding an explicit
>> flag for syncing execbuf with closed/abandonded contexts.
>>
>> v2:
>> * Use already available context flags. (Chris)
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> ---
>> drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 ++-
>> drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
>> drivers/gpu/drm/i915/gt/intel_context_types.h | 1 +
>> 3 files changed, 4 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> index 9afc60ab95e0..7c119a3a2cbd 100644
>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> @@ -579,7 +579,8 @@ static void engines_idle_release(struct i915_gem_context *ctx,
>> int err = 0;
>>
>> /* serialises with execbuf */
>> - RCU_INIT_POINTER(ce->gem_context, NULL);
>> + set_bit(INTEL_CONTEXT_CLOSED, &ce->flags);
>> +
>> if (!intel_context_pin_if_active(ce))
>> continue;
>>
>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
>> index d3f4f28e9468..875da020d6c8 100644
>> --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
>> @@ -2316,7 +2316,7 @@ static void eb_request_add(struct i915_execbuffer *eb)
>> prev = __i915_request_commit(rq);
>>
>> /* Check that the context wasn't destroyed before submission */
>> - if (likely(rcu_access_pointer(eb->context->gem_context))) {
>> + if (likely(!test_bit(INTEL_CONTEXT_CLOSED, &eb->context->flags))) {
>> attr = eb->gem_context->sched;
>>
>> /*
>> diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
>> index 0f3b68b95c56..d5925c25f109 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h
>> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
>> @@ -66,6 +66,7 @@ struct intel_context {
>> #define CONTEXT_BANNED 4
>> #define CONTEXT_FORCE_SINGLE_SUBMISSION 5
>> #define CONTEXT_NOPREEMPT 6
>> +#define INTEL_CONTEXT_CLOSED 7
>
> Trying to start a flame war? :)
No, but CONTEXT_ namespace is overloaded between here and GEM context. I
propose we prefix one of them all with something.
> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
>
> With this flag, we can start banning contexts after a GPU hang on a
> closed context _again_. That might justify applying immediately.
Hm okay.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread
* [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (3 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 04/10] drm/i915: Use explicit flag to mark unreachable intel_context Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 13:55 ` Chris Wilson
2020-03-18 12:11 ` [Intel-gfx] [PATCH 06/10] drm/i915: Track runtime spent in closed GEM contexts Tvrtko Ursulin
` (3 subsequent siblings)
8 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
As contexts are abandoned we want to remember how much GPU time they used
(per class) so later we can used it for smarter purposes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 7c119a3a2cbd..5edf79ed6247 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
{
struct i915_gem_engines *engines =
container_of(rcu, struct i915_gem_engines, rcu);
+ struct i915_gem_context *ctx = engines->ctx;
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+
+ /* Transfer accumulated runtime to the parent GEM context. */
+ for_each_gem_engine(ce, engines, it) {
+ unsigned int class = ce->engine->uabi_class;
+ GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
+ atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
+ }
+
+ i915_gem_context_put(ctx);
i915_sw_fence_fini(&engines->fence);
free_engines(engines);
}
@@ -278,7 +290,6 @@ engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
list_del(&engines->link);
spin_unlock_irqrestore(&ctx->stale.lock, flags);
}
- i915_gem_context_put(engines->ctx);
break;
case FENCE_FREE:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index b0e03380c690..f0d7441aafc8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -177,6 +177,11 @@ struct i915_gem_context {
spinlock_t lock;
struct list_head engines;
} stale;
+
+ /**
+ * @past_runtime: Accumulation of freed intel_context pphwsp runtimes.
+ */
+ atomic64_t past_runtime[MAX_ENGINE_CLASS + 1];
};
#endif /* __I915_GEM_CONTEXT_TYPES_H__ */
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 12:11 ` [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts Tvrtko Ursulin
@ 2020-03-18 13:55 ` Chris Wilson
2020-03-18 14:13 ` Tvrtko Ursulin
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 13:55 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 12:11:34)
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> As contexts are abandoned we want to remember how much GPU time they used
> (per class) so later we can used it for smarter purposes.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
> drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
> drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
> 2 files changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index 7c119a3a2cbd..5edf79ed6247 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
> {
> struct i915_gem_engines *engines =
> container_of(rcu, struct i915_gem_engines, rcu);
> + struct i915_gem_context *ctx = engines->ctx;
> + struct i915_gem_engines_iter it;
> + struct intel_context *ce;
> +
> + /* Transfer accumulated runtime to the parent GEM context. */
> + for_each_gem_engine(ce, engines, it) {
> + unsigned int class = ce->engine->uabi_class;
>
> + GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
> + atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
Hmm, there's an odd situation where the free_engines_rcu could fire
before we do the final schedule_out of the context.
GEM_BUG_ON(intel_context_inflight(ce)) to see if that's being too
paranoid.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 13:55 ` Chris Wilson
@ 2020-03-18 14:13 ` Tvrtko Ursulin
2020-03-18 14:32 ` Chris Wilson
0 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 14:13 UTC (permalink / raw)
To: Chris Wilson, Intel-gfx
On 18/03/2020 13:55, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-03-18 12:11:34)
>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>
>> As contexts are abandoned we want to remember how much GPU time they used
>> (per class) so later we can used it for smarter purposes.
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> ---
>> drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
>> drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
>> 2 files changed, 17 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> index 7c119a3a2cbd..5edf79ed6247 100644
>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>> @@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
>> {
>> struct i915_gem_engines *engines =
>> container_of(rcu, struct i915_gem_engines, rcu);
>> + struct i915_gem_context *ctx = engines->ctx;
>> + struct i915_gem_engines_iter it;
>> + struct intel_context *ce;
>> +
>> + /* Transfer accumulated runtime to the parent GEM context. */
>> + for_each_gem_engine(ce, engines, it) {
>> + unsigned int class = ce->engine->uabi_class;
>>
>> + GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
>> + atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
>
> Hmm, there's an odd situation where the free_engines_rcu could fire
> before we do the final schedule_out of the context.
>
> GEM_BUG_ON(intel_context_inflight(ce)) to see if that's being too
> paranoid.
Deja vu.. have I forgotten to move this into intel_context_free while
the purpose of keeping ce->gem_context valid was exactly to enable that.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 14:13 ` Tvrtko Ursulin
@ 2020-03-18 14:32 ` Chris Wilson
2020-03-18 14:38 ` Tvrtko Ursulin
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 14:32 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 14:13:14)
>
> On 18/03/2020 13:55, Chris Wilson wrote:
> > Quoting Tvrtko Ursulin (2020-03-18 12:11:34)
> >> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> >>
> >> As contexts are abandoned we want to remember how much GPU time they used
> >> (per class) so later we can used it for smarter purposes.
> >>
> >> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> >> ---
> >> drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
> >> drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
> >> 2 files changed, 17 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >> index 7c119a3a2cbd..5edf79ed6247 100644
> >> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >> @@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
> >> {
> >> struct i915_gem_engines *engines =
> >> container_of(rcu, struct i915_gem_engines, rcu);
> >> + struct i915_gem_context *ctx = engines->ctx;
> >> + struct i915_gem_engines_iter it;
> >> + struct intel_context *ce;
> >> +
> >> + /* Transfer accumulated runtime to the parent GEM context. */
> >> + for_each_gem_engine(ce, engines, it) {
> >> + unsigned int class = ce->engine->uabi_class;
> >>
> >> + GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
> >> + atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
> >
> > Hmm, there's an odd situation where the free_engines_rcu could fire
> > before we do the final schedule_out of the context.
> >
> > GEM_BUG_ON(intel_context_inflight(ce)) to see if that's being too
> > paranoid.
>
> Deja vu.. have I forgotten to move this into intel_context_free while
> the purpose of keeping ce->gem_context valid was exactly to enable that.
I would rather not have it in gt/ if possible. The delay should be
nominal at worst.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 14:32 ` Chris Wilson
@ 2020-03-18 14:38 ` Tvrtko Ursulin
2020-03-18 14:48 ` Chris Wilson
0 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 14:38 UTC (permalink / raw)
To: Chris Wilson, Intel-gfx
On 18/03/2020 14:32, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-03-18 14:13:14)
>>
>> On 18/03/2020 13:55, Chris Wilson wrote:
>>> Quoting Tvrtko Ursulin (2020-03-18 12:11:34)
>>>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>>>
>>>> As contexts are abandoned we want to remember how much GPU time they used
>>>> (per class) so later we can used it for smarter purposes.
>>>>
>>>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>>> ---
>>>> drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
>>>> drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
>>>> 2 files changed, 17 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>>> index 7c119a3a2cbd..5edf79ed6247 100644
>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>>> @@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
>>>> {
>>>> struct i915_gem_engines *engines =
>>>> container_of(rcu, struct i915_gem_engines, rcu);
>>>> + struct i915_gem_context *ctx = engines->ctx;
>>>> + struct i915_gem_engines_iter it;
>>>> + struct intel_context *ce;
>>>> +
>>>> + /* Transfer accumulated runtime to the parent GEM context. */
>>>> + for_each_gem_engine(ce, engines, it) {
>>>> + unsigned int class = ce->engine->uabi_class;
>>>>
>>>> + GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
>>>> + atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
>>>
>>> Hmm, there's an odd situation where the free_engines_rcu could fire
>>> before we do the final schedule_out of the context.
>>>
>>> GEM_BUG_ON(intel_context_inflight(ce)) to see if that's being too
>>> paranoid.
>>
>> Deja vu.. have I forgotten to move this into intel_context_free while
>> the purpose of keeping ce->gem_context valid was exactly to enable that.
>
> I would rather not have it in gt/ if possible. The delay should be
> nominal at worst.
But I thought your concern was this can miss the accumulation of the
last active period due active tracker triggering the rcu cleanup before
last context save. What do you then recommend?
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 14:38 ` Tvrtko Ursulin
@ 2020-03-18 14:48 ` Chris Wilson
2020-03-18 15:07 ` Chris Wilson
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 14:48 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 14:38:53)
>
> On 18/03/2020 14:32, Chris Wilson wrote:
> > Quoting Tvrtko Ursulin (2020-03-18 14:13:14)
> >>
> >> On 18/03/2020 13:55, Chris Wilson wrote:
> >>> Quoting Tvrtko Ursulin (2020-03-18 12:11:34)
> >>>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> >>>>
> >>>> As contexts are abandoned we want to remember how much GPU time they used
> >>>> (per class) so later we can used it for smarter purposes.
> >>>>
> >>>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> >>>> ---
> >>>> drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
> >>>> drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
> >>>> 2 files changed, 17 insertions(+), 1 deletion(-)
> >>>>
> >>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >>>> index 7c119a3a2cbd..5edf79ed6247 100644
> >>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> >>>> @@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
> >>>> {
> >>>> struct i915_gem_engines *engines =
> >>>> container_of(rcu, struct i915_gem_engines, rcu);
> >>>> + struct i915_gem_context *ctx = engines->ctx;
> >>>> + struct i915_gem_engines_iter it;
> >>>> + struct intel_context *ce;
> >>>> +
> >>>> + /* Transfer accumulated runtime to the parent GEM context. */
> >>>> + for_each_gem_engine(ce, engines, it) {
> >>>> + unsigned int class = ce->engine->uabi_class;
> >>>>
> >>>> + GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
> >>>> + atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
> >>>
> >>> Hmm, there's an odd situation where the free_engines_rcu could fire
> >>> before we do the final schedule_out of the context.
> >>>
> >>> GEM_BUG_ON(intel_context_inflight(ce)) to see if that's being too
> >>> paranoid.
> >>
> >> Deja vu.. have I forgotten to move this into intel_context_free while
> >> the purpose of keeping ce->gem_context valid was exactly to enable that.
> >
> > I would rather not have it in gt/ if possible. The delay should be
> > nominal at worst.
>
> But I thought your concern was this can miss the accumulation of the
> last active period due active tracker triggering the rcu cleanup before
> last context save. What do you then recommend?
That is the concern, but it's not a huge concern for me :)
I was tempted just to put a busywait here, rather than couple up a
notification scheme. Although...
We do have a notification here for the context_retire we could listen to
instead of listening to the request idling. If we use
i915_sw_fence_await_active(&engines->fence,
&ce->active,
I915_ACTIVE_AWAIT_ALL);
instead, then the fence will not fire until the final barrier has
executed.
Tada!
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
2020-03-18 14:48 ` Chris Wilson
@ 2020-03-18 15:07 ` Chris Wilson
0 siblings, 0 replies; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 15:07 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Chris Wilson (2020-03-18 14:48:05)
> We do have a notification here for the context_retire we could listen to
> instead of listening to the request idling. If we use
>
> i915_sw_fence_await_active(&engines->fence,
> &ce->active,
> I915_ACTIVE_AWAIT_ALL);
>
> instead, then the fence will not fire until the final barrier has
> executed.
>
> Tada!
It's close. It's still strictly firing on the pulse request signaling,
which is currently not guaranteed to be after after the context_out.
Although we can arrange that with a sentinel.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread
* [Intel-gfx] [PATCH 06/10] drm/i915: Track runtime spent in closed GEM contexts
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (4 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 05/10] drm/i915: Track runtime spent in unreachable intel_contexts Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 13:57 ` Chris Wilson
2020-03-18 12:11 ` [Intel-gfx] [PATCH 07/10] drm/i915: Track all user contexts per client Tvrtko Ursulin
` (2 subsequent siblings)
8 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
As GEM contexts are closed we want to have the DRM client remember how
much GPU time they used (per class) so later we can used it for smarter
purposes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 12 +++++++++++-
drivers/gpu/drm/i915/i915_drm_client.h | 7 +++++++
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 5edf79ed6247..912375fb8a3b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -355,8 +355,18 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
- if (client)
+ if (client) {
+ unsigned int i;
+
+ /* Transfer accumulated runtime to the parent drm client. */
+ BUILD_BUG_ON(ARRAY_SIZE(client->past_runtime) !=
+ ARRAY_SIZE(ctx->past_runtime));
+ for (i = 0; i < ARRAY_SIZE(client->past_runtime); i++)
+ atomic64_add(atomic64_read(&ctx->past_runtime[i]),
+ &client->past_runtime[i]);
+
i915_drm_client_put(client);
+ }
spin_lock(&ctx->i915->gem.contexts.lock);
list_del(&ctx->link);
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 11b48383881d..29b116606596 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -15,6 +15,8 @@
#include <linux/sched.h>
#include <linux/xarray.h>
+#include "gt/intel_engine_types.h"
+
struct i915_drm_clients {
struct xarray xarray;
u32 next_id;
@@ -41,6 +43,11 @@ struct i915_drm_client {
struct device_attribute pid;
struct device_attribute name;
} attr;
+
+ /**
+ * @past_runtime: Accumulation of pphwsp runtimes from closed contexts.
+ */
+ atomic64_t past_runtime[MAX_ENGINE_CLASS + 1];
};
void i915_drm_clients_init(struct i915_drm_clients *clients);
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 06/10] drm/i915: Track runtime spent in closed GEM contexts
2020-03-18 12:11 ` [Intel-gfx] [PATCH 06/10] drm/i915: Track runtime spent in closed GEM contexts Tvrtko Ursulin
@ 2020-03-18 13:57 ` Chris Wilson
0 siblings, 0 replies; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 13:57 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 12:11:35)
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> As GEM contexts are closed we want to have the DRM client remember how
> much GPU time they used (per class) so later we can used it for smarter
> purposes.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
> drivers/gpu/drm/i915/gem/i915_gem_context.c | 12 +++++++++++-
> drivers/gpu/drm/i915/i915_drm_client.h | 7 +++++++
> 2 files changed, 18 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index 5edf79ed6247..912375fb8a3b 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -355,8 +355,18 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
>
> GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
>
> - if (client)
> + if (client) {
> + unsigned int i;
> +
> + /* Transfer accumulated runtime to the parent drm client. */
> + BUILD_BUG_ON(ARRAY_SIZE(client->past_runtime) !=
> + ARRAY_SIZE(ctx->past_runtime));
> + for (i = 0; i < ARRAY_SIZE(client->past_runtime); i++)
> + atomic64_add(atomic64_read(&ctx->past_runtime[i]),
> + &client->past_runtime[i]);
> +
> i915_drm_client_put(client);
> + }
Ok, order looks good.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread
* [Intel-gfx] [PATCH 07/10] drm/i915: Track all user contexts per client
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (5 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 06/10] drm/i915: Track runtime spent in closed GEM contexts Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness Tvrtko Ursulin
2020-03-18 12:11 ` [Intel-gfx] [PATCH 09/10] drm/i915: Track context current active time Tvrtko Ursulin
8 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
We soon want to start answering questions like how much GPU time is the
context belonging to a client which exited still using.
To enable this we start tracking all context belonging to a client on a
separate list.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 ++++++++
drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 3 +++
drivers/gpu/drm/i915/i915_drm_client.c | 3 +++
drivers/gpu/drm/i915/i915_drm_client.h | 5 +++++
4 files changed, 19 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 912375fb8a3b..9654f0ab3f45 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -358,6 +358,10 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
if (client) {
unsigned int i;
+ spin_lock(&client->ctx_lock);
+ list_del_rcu(&ctx->client_link);
+ spin_unlock(&client->ctx_lock);
+
/* Transfer accumulated runtime to the parent drm client. */
BUILD_BUG_ON(ARRAY_SIZE(client->past_runtime) !=
ARRAY_SIZE(ctx->past_runtime));
@@ -964,6 +968,10 @@ static int gem_context_register(struct i915_gem_context *ctx,
ctx->client = client;
+ spin_lock(&client->ctx_lock);
+ list_add_tail_rcu(&ctx->client_link, &client->ctx_list);
+ spin_unlock(&client->ctx_lock);
+
return 0;
err:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index f0d7441aafc8..255fcc469d9b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -103,6 +103,9 @@ struct i915_gem_context {
/** client: struct i915_drm_client */
struct i915_drm_client *client;
+ /** link: &drm_client.context_list */
+ struct list_head client_link;
+
/**
* @ref: reference count
*
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 342a11554573..c88d9ff448e0 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -154,6 +154,9 @@ i915_drm_client_add(struct i915_drm_clients *clients, struct task_struct *task)
kref_init(&client->kref);
mutex_init(&client->update_lock);
+ spin_lock_init(&client->ctx_lock);
+ INIT_LIST_HEAD(&client->ctx_list);
+
client->clients = clients;
ret = xa_alloc_cyclic(&clients->xarray, &client->id, client,
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 29b116606596..0be27aa9bbda 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -9,10 +9,12 @@
#include <linux/device.h>
#include <linux/kobject.h>
#include <linux/kref.h>
+#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/pid.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
+#include <linux/spinlock.h>
#include <linux/xarray.h>
#include "gt/intel_engine_types.h"
@@ -36,6 +38,9 @@ struct i915_drm_client {
char __rcu *name;
bool closed;
+ spinlock_t ctx_lock; /* For add/remove from ctx_list. */
+ struct list_head ctx_list; /* List of contexts belonging to client. */
+
struct i915_drm_clients *clients;
struct kobject *root;
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (6 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 07/10] drm/i915: Track all user contexts per client Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
2020-03-18 14:00 ` Chris Wilson
2020-03-18 12:11 ` [Intel-gfx] [PATCH 09/10] drm/i915: Track context current active time Tvrtko Ursulin
8 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
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.
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>
---
drivers/gpu/drm/i915/i915_drm_client.c | 110 ++++++++++++++++++++++++-
drivers/gpu/drm/i915/i915_drm_client.h | 11 +++
2 files changed, 120 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index c88d9ff448e0..0a2d933fe83c 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -9,8 +9,13 @@
#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"
@@ -52,6 +57,104 @@ 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 * 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;
+ struct drm_i915_private *i915 =
+ container_of(clients, typeof(*i915), clients);
+ unsigned int i;
+ int ret = 0;
+
+ if (!HAS_LOGICAL_RING_CONTEXTS(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(i915, i, 0))
+ continue;
+
+ i915_attr->client = client;
+ i915_attr->i915 = i915;
+ 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)
{
@@ -88,9 +191,12 @@ __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);
@@ -99,6 +205,8 @@ __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 0be27aa9bbda..98c5fc24fcb4 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -26,6 +26,15 @@ 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;
@@ -44,9 +53,11 @@ 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
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness
2020-03-18 12:11 ` [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness Tvrtko Ursulin
@ 2020-03-18 14:00 ` Chris Wilson
2020-03-18 14:15 ` Tvrtko Ursulin
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 14:00 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 12:11:37)
> +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);
Hmm. I would like to have some GEM context agnosticism here. At the
moment, all I have to offer is
struct client_runtime {
struct list_head client_link;
atomic64_t past_runtime;
u64 (*cur_runtime)(struct client_runtime *);
};
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness
2020-03-18 14:00 ` Chris Wilson
@ 2020-03-18 14:15 ` Tvrtko Ursulin
2020-03-18 14:34 ` Chris Wilson
0 siblings, 1 reply; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 14:15 UTC (permalink / raw)
To: Chris Wilson, Intel-gfx
On 18/03/2020 14:00, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-03-18 12:11:37)
>> +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);
>
> Hmm. I would like to have some GEM context agnosticism here. At the
> moment, all I have to offer is
>
> struct client_runtime {
> struct list_head client_link;
> atomic64_t past_runtime;
> u64 (*cur_runtime)(struct client_runtime *);
> };
What exactly do you mean here? Who keeps a list and of what and what
does the vfunc do?
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness
2020-03-18 14:15 ` Tvrtko Ursulin
@ 2020-03-18 14:34 ` Chris Wilson
2020-04-15 10:19 ` Tvrtko Ursulin
0 siblings, 1 reply; 24+ messages in thread
From: Chris Wilson @ 2020-03-18 14:34 UTC (permalink / raw)
To: Intel-gfx, Tvrtko Ursulin
Quoting Tvrtko Ursulin (2020-03-18 14:15:31)
>
> On 18/03/2020 14:00, Chris Wilson wrote:
> > Quoting Tvrtko Ursulin (2020-03-18 12:11:37)
> >> +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);
> >
> > Hmm. I would like to have some GEM context agnosticism here. At the
> > moment, all I have to offer is
> >
> > struct client_runtime {
> > struct list_head client_link;
> > atomic64_t past_runtime;
> > u64 (*cur_runtime)(struct client_runtime *);
> > };
>
> What exactly do you mean here? Who keeps a list and of what and what
> does the vfunc do?
This is what you've added to GEM context. Here in i915/i915_drm_client.c
we shouldn't have to know about i915/gem/i915_gem_context internals. So
the GEM context registers its client_runtime (by coupling that into the
list).
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread* Re: [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness
2020-03-18 14:34 ` Chris Wilson
@ 2020-04-15 10:19 ` Tvrtko Ursulin
0 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-04-15 10:19 UTC (permalink / raw)
To: Chris Wilson, Intel-gfx
On 18/03/2020 14:34, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-03-18 14:15:31)
>>
>> On 18/03/2020 14:00, Chris Wilson wrote:
>>> Quoting Tvrtko Ursulin (2020-03-18 12:11:37)
>>>> +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);
>>>
>>> Hmm. I would like to have some GEM context agnosticism here. At the
>>> moment, all I have to offer is
>>>
>>> struct client_runtime {
>>> struct list_head client_link;
>>> atomic64_t past_runtime;
>>> u64 (*cur_runtime)(struct client_runtime *);
>>> };
>>
>> What exactly do you mean here? Who keeps a list and of what and what
>> does the vfunc do?
>
> This is what you've added to GEM context. Here in i915/i915_drm_client.c
> we shouldn't have to know about i915/gem/i915_gem_context internals. So
> the GEM context registers its client_runtime (by coupling that into the
> list).
I've ignored this for now as it was feeling a bit too much for too
little benefit and just decided to send out another simple rebase, given
that there seems to be some urgency around this work now.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 24+ messages in thread
* [Intel-gfx] [PATCH 09/10] drm/i915: Track context current active time
2020-03-18 12:11 [Intel-gfx] [PATCH 00/10] Per client engine busyness Tvrtko Ursulin
` (7 preceding siblings ...)
2020-03-18 12:11 ` [Intel-gfx] [PATCH 08/10] drm/i915: Expose per-engine client busyness Tvrtko Ursulin
@ 2020-03-18 12:11 ` Tvrtko Ursulin
8 siblings, 0 replies; 24+ messages in thread
From: Tvrtko Ursulin @ 2020-03-18 12:11 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Track context active (on hardware) status together with the start
timestamp.
This will be used to provide better granularity of context
runtime reporting in conjunction with already tracked pphwsp accumulated
runtime.
The latter is only updated on context save so does not give us visibility
to any currently executing work.
As part of the patch the existing runtime tracking data is moved under the
new ce->stats member and updated under the seqlock. This provides the
ability to atomically read out accumulated plus active runtime.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 +-
drivers/gpu/drm/i915/gt/intel_context.c | 18 +++++-
drivers/gpu/drm/i915/gt/intel_context.h | 6 +-
drivers/gpu/drm/i915/gt/intel_context_types.h | 24 +++++---
drivers/gpu/drm/i915/gt/intel_lrc.c | 55 +++++++++++++++----
drivers/gpu/drm/i915/gt/selftest_lrc.c | 10 ++--
drivers/gpu/drm/i915/i915_drm_client.c | 2 +-
drivers/gpu/drm/i915/i915_gpu_error.c | 4 +-
8 files changed, 90 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9654f0ab3f45..8c67a1269142 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -266,7 +266,8 @@ static void free_engines_rcu(struct rcu_head *rcu)
unsigned int class = ce->engine->uabi_class;
GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
- atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
+ atomic64_add(ce->stats.runtime.total,
+ &ctx->past_runtime[class]);
}
i915_gem_context_put(ctx);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 01474d3a558b..1f371f8b202a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -288,7 +288,7 @@ intel_context_init(struct intel_context *ce,
ce->sseu = engine->sseu;
ce->ring = __intel_context_ring_size(SZ_4K);
- ewma_runtime_init(&ce->runtime.avg);
+ ewma_runtime_init(&ce->stats.runtime.avg);
ce->vm = i915_vm_get(engine->gt->vm);
@@ -296,6 +296,7 @@ intel_context_init(struct intel_context *ce,
INIT_LIST_HEAD(&ce->signals);
mutex_init(&ce->pin_mutex);
+ seqlock_init(&ce->stats.lock);
i915_active_init(&ce->active,
__intel_context_active, __intel_context_retire);
@@ -390,6 +391,21 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
return rq;
}
+ktime_t intel_context_get_active_time(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned int seq;
+ ktime_t total = 0;
+
+ do {
+ seq = read_seqbegin(&stats->lock);
+ if (stats->active)
+ total = ktime_sub(ktime_get(), stats->start);
+ } while (read_seqretry(&stats->lock, seq));
+
+ return total;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_context.c"
#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 18efad255124..1f8b6e0bbfaf 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -233,7 +233,7 @@ static inline u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
const u32 period =
RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
- return READ_ONCE(ce->runtime.total) * period;
+ return READ_ONCE(ce->stats.runtime.total) * period;
}
static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
@@ -241,7 +241,9 @@ static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
const u32 period =
RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
- return mul_u32_u32(ewma_runtime_read(&ce->runtime.avg), period);
+ return mul_u32_u32(ewma_runtime_read(&ce->stats.runtime.avg), period);
}
+ktime_t intel_context_get_active_time(struct intel_context *ce);
+
#endif /* __INTEL_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index d5925c25f109..fe85a3b0b7f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/types.h>
+#include <linux/seqlock.h>
#include "i915_active_types.h"
#include "i915_utils.h"
@@ -72,14 +73,21 @@ struct intel_context {
u64 lrc_desc;
u32 tag; /* cookie passed to HW to track this context on submission */
- /* Time on GPU as tracked by the hw. */
- struct {
- struct ewma_runtime avg;
- u64 total;
- u32 last;
- I915_SELFTEST_DECLARE(u32 num_underflow);
- I915_SELFTEST_DECLARE(u32 max_underflow);
- } runtime;
+ /** stats: Context GPU engine busyness tracking. */
+ struct intel_context_stats {
+ seqlock_t lock;
+ bool active;
+ ktime_t start;
+
+ /* Time on GPU as tracked by the hw. */
+ struct {
+ struct ewma_runtime avg;
+ u64 total;
+ u32 last;
+ I915_SELFTEST_DECLARE(u32 num_underflow);
+ I915_SELFTEST_DECLARE(u32 max_underflow);
+ } runtime;
+ } stats;
unsigned int active_count; /* protected by timeline->mutex */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 112531b29f59..6143c6a9dea4 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1206,35 +1206,61 @@ static u32 intel_context_get_runtime(const struct intel_context *ce)
return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
}
-static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
+static void
+st_update_runtime_underflow(struct intel_context_stats *stats, s32 dt)
{
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
- ce->runtime.num_underflow += dt < 0;
- ce->runtime.max_underflow = max_t(u32, ce->runtime.max_underflow, -dt);
+ stats->runtime.num_underflow += dt < 0;
+ stats->runtime.max_underflow =
+ max_t(u32, stats->runtime.max_underflow, -dt);
#endif
}
static void intel_context_update_runtime(struct intel_context *ce)
{
+ struct intel_context_stats *stats = &ce->stats;
u32 old;
s32 dt;
if (intel_context_is_barrier(ce))
return;
- old = ce->runtime.last;
- ce->runtime.last = intel_context_get_runtime(ce);
- dt = ce->runtime.last - old;
+ old = stats->runtime.last;
+ stats->runtime.last = intel_context_get_runtime(ce);
+ dt = stats->runtime.last - old;
if (unlikely(dt <= 0)) {
CE_TRACE(ce, "runtime underflow: last=%u, new=%u, delta=%d\n",
- old, ce->runtime.last, dt);
- st_update_runtime_underflow(ce, dt);
+ old, stats->runtime.last, dt);
+ st_update_runtime_underflow(stats, dt);
return;
}
- ewma_runtime_add(&ce->runtime.avg, dt);
- ce->runtime.total += dt;
+ ewma_runtime_add(&stats->runtime.avg, dt);
+ stats->runtime.total += dt;
+}
+
+static void intel_context_stats_start(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned long flags;
+
+ write_seqlock_irqsave(&stats->lock, flags);
+ stats->start = ktime_get();
+ stats->active = true;
+ write_sequnlock_irqrestore(&stats->lock, flags);
+}
+
+static void intel_context_stats_stop(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned long flags;
+
+ write_seqlock_irqsave(&stats->lock, flags);
+ stats->active = false;
+ stats->start = 0;
+ intel_context_update_runtime(ce);
+ write_sequnlock_irqrestore(&stats->lock, flags);
}
static inline struct intel_engine_cs *
@@ -1304,7 +1330,7 @@ static inline void
__execlists_schedule_out(struct i915_request *rq,
struct intel_engine_cs * const engine)
{
- struct intel_context * const ce = rq->context;
+ struct intel_context *ce = rq->context;
/*
* NB process_csb() is not under the engine->active.lock and hence
@@ -1320,8 +1346,8 @@ __execlists_schedule_out(struct i915_request *rq,
i915_request_completed(rq))
intel_engine_add_retire(engine, ce->timeline);
- intel_context_update_runtime(ce);
intel_engine_context_out(engine);
+ intel_context_stats_stop(ce);
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
intel_gt_pm_put_async(engine->gt);
@@ -1790,6 +1816,11 @@ active_timeslice(const struct intel_engine_cs *engine)
static void set_timeslice(struct intel_engine_cs *engine)
{
+ struct intel_engine_execlists * const execlists = &engine->execlists;
+
+ if (*execlists->active)
+ intel_context_stats_start((*execlists->active)->context);
+
if (!intel_engine_has_timeslices(engine))
return;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 6f06ba750a0a..6a51e7fa03ca 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -5479,8 +5479,8 @@ static int __live_pphwsp_runtime(struct intel_engine_cs *engine)
if (IS_ERR(ce))
return PTR_ERR(ce);
- ce->runtime.num_underflow = 0;
- ce->runtime.max_underflow = 0;
+ ce->stats.runtime.num_underflow = 0;
+ ce->stats.runtime.max_underflow = 0;
do {
unsigned int loop = 1024;
@@ -5518,11 +5518,11 @@ static int __live_pphwsp_runtime(struct intel_engine_cs *engine)
intel_context_get_avg_runtime_ns(ce));
err = 0;
- if (ce->runtime.num_underflow) {
+ if (ce->stats.runtime.num_underflow) {
pr_err("%s: pphwsp underflow %u time(s), max %u cycles!\n",
engine->name,
- ce->runtime.num_underflow,
- ce->runtime.max_underflow);
+ ce->stats.runtime.num_underflow,
+ ce->stats.runtime.max_underflow);
GEM_TRACE_DUMP();
err = -EOVERFLOW;
}
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 0a2d933fe83c..485a2b75d3e1 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -67,7 +67,7 @@ pphwsp_busy_add(struct i915_gem_context *ctx, unsigned int class)
for_each_gem_engine(ce, engines, it) {
if (ce->engine->uabi_class == class)
- total += ce->runtime.total;
+ total += ce->stats.runtime.total;
}
return total;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 653e1bc5050e..ce752572c38f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1267,8 +1267,8 @@ static bool record_context(struct i915_gem_context_coredump *e,
e->guilty = atomic_read(&ctx->guilty_count);
e->active = atomic_read(&ctx->active_count);
- e->total_runtime = rq->context->runtime.total;
- e->avg_runtime = ewma_runtime_read(&rq->context->runtime.avg);
+ e->total_runtime = rq->context->stats.runtime.total;
+ e->avg_runtime = ewma_runtime_read(&rq->context->stats.runtime.avg);
simulated = i915_gem_context_no_error_capture(ctx);
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 24+ messages in thread