* [PATCH 1/7] drm/i915: Explicitly track DRM clients
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 2/7] drm/i915: Make GEM contexts " Tvrtko Ursulin
` (5 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx; +Cc: dri-devel, Tvrtko Ursulin, Chris Wilson, Aravind Iddamsetty
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Tracking DRM clients more explicitly will allow later patches to
accumulate past and current GPU usage in a centralised place and also
consolidate access to owning task pid/name.
Unique client id is also assigned for the purpose of distinguishing/
consolidating between multiple file descriptors owned by the same process.
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)
v12:
* Do not fail client add on id wrap. (Maciej)
v13 (Lucas): Rebase.
v14:
* Dropped sysfs bits.
v15:
* Dropped tracking of pid/ and name.
* Dropped RCU freeing of the client object.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v11
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com> # v11
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/Makefile | 5 +-
drivers/gpu/drm/i915/i915_drm_client.c | 68 ++++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_drm_client.h | 50 +++++++++++++++++++
drivers/gpu/drm/i915/i915_drv.c | 6 +++
drivers/gpu/drm/i915/i915_drv.h | 5 ++
drivers/gpu/drm/i915/i915_gem.c | 21 ++++++--
6 files changed, 150 insertions(+), 5 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 335a8c668848..8187c9e52a79 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -32,8 +32,9 @@ subdir-ccflags-y += -I$(srctree)/$(src)
# Please keep these build lists sorted!
# core driver code
-i915-y += i915_drv.o \
- i915_config.o \
+i915-y += i915_config.o \
+ i915_drm_client.o \
+ i915_drv.o \
i915_irq.o \
i915_getparam.o \
i915_mitigations.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..e61e9ba15256
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -0,0 +1,68 @@
+// 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,
+ struct drm_i915_private *i915)
+{
+ clients->i915 = i915;
+ clients->next_id = 0;
+
+ xa_init_flags(&clients->xarray, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+}
+
+struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients)
+{
+ struct i915_drm_client *client;
+ struct xarray *xa = &clients->xarray;
+ int ret;
+
+ client = kzalloc(sizeof(*client), GFP_KERNEL);
+ if (!client)
+ return ERR_PTR(-ENOMEM);
+
+ xa_lock_irq(xa);
+ ret = __xa_alloc_cyclic(xa, &client->id, client, xa_limit_32b,
+ &clients->next_id, GFP_KERNEL);
+ xa_unlock_irq(xa);
+ if (ret < 0)
+ goto err;
+
+ kref_init(&client->kref);
+ client->clients = clients;
+
+ return client;
+
+err:
+ 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);
+ struct xarray *xa = &client->clients->xarray;
+ unsigned long flags;
+
+ xa_lock_irqsave(xa, flags);
+ __xa_erase(xa, client->id);
+ xa_unlock_irqrestore(xa, flags);
+ kfree(client);
+}
+
+void i915_drm_clients_fini(struct i915_drm_clients *clients)
+{
+ GEM_BUG_ON(!xa_empty(&clients->xarray));
+ xa_destroy(&clients->xarray);
+}
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..e8986ad51176
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __I915_DRM_CLIENT_H__
+#define __I915_DRM_CLIENT_H__
+
+#include <linux/kref.h>
+#include <linux/xarray.h>
+
+struct drm_i915_private;
+
+struct i915_drm_clients {
+ struct drm_i915_private *i915;
+
+ struct xarray xarray;
+ u32 next_id;
+};
+
+struct i915_drm_client {
+ struct kref kref;
+
+ unsigned int id;
+
+ struct i915_drm_clients *clients;
+};
+
+void i915_drm_clients_init(struct i915_drm_clients *clients,
+ struct drm_i915_private *i915);
+
+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);
+}
+
+struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients);
+
+void i915_drm_clients_fini(struct i915_drm_clients *clients);
+
+#endif /* !__I915_DRM_CLIENT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 3cf61bead2f6..6418f3dbdad0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -68,6 +68,7 @@
#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"
@@ -344,6 +345,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
intel_gt_init_early(&dev_priv->gt, dev_priv);
+ i915_drm_clients_init(&dev_priv->clients, dev_priv);
+
i915_gem_init_early(dev_priv);
/* This must be called before any calls to HAS_PCH_* */
@@ -363,6 +366,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
err_gem:
i915_gem_cleanup_early(dev_priv);
+ i915_drm_clients_fini(&dev_priv->clients);
intel_gt_driver_late_release(&dev_priv->gt);
intel_region_ttm_device_fini(dev_priv);
err_ttm:
@@ -382,6 +386,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv)
intel_irq_fini(dev_priv);
intel_power_domains_cleanup(dev_priv);
i915_gem_cleanup_early(dev_priv);
+ i915_drm_clients_fini(&dev_priv->clients);
intel_gt_driver_late_release(&dev_priv->gt);
intel_region_ttm_device_fini(dev_priv);
vlv_suspend_cleanup(dev_priv);
@@ -997,6 +1002,7 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
struct drm_i915_file_private *file_priv = file->driver_priv;
i915_gem_context_close(file);
+ i915_drm_client_put(file_priv->client);
kfree_rcu(file_priv, rcu);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cc355aa05dbf..2078e4776cdc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -96,6 +96,7 @@
#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"
@@ -284,6 +285,8 @@ 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:
@@ -1196,6 +1199,8 @@ 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 981e383d1a5d..3df78babe1a9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1177,25 +1177,40 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
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);
+ 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;
file_priv->bsd_engine = -1;
file_priv->hang_timestamp = jiffies;
ret = i915_gem_context_open(i915, file);
if (ret)
- kfree(file_priv);
+ goto err_context;
+
+ return 0;
+err_context:
+ i915_drm_client_put(client);
+err_client:
+ kfree(file_priv);
+err_alloc:
return ret;
}
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2/7] drm/i915: Make GEM contexts track DRM clients
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 1/7] drm/i915: Explicitly track DRM clients Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 3/7] drm/i915: Track runtime spent in closed and unreachable GEM contexts Tvrtko Ursulin
` (4 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx; +Cc: dri-devel, Tvrtko Ursulin, Chris Wilson, Aravind Iddamsetty
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Make GEM contexts keep a reference to i915_drm_client for the whole of
of their lifetime which will come handy in following patches.
v2: Don't bother supporting selftests contexts from debugfs. (Chris)
v3 (Lucas): Finish constructing ctx before adding it to the list
v4 (Ram): Rebase.
v5: Trivial rebase for proto ctx changes.
v6: Rebase after clients no longer track name and pid.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v5
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com> # v5
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 5 +++++
drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 3 +++
2 files changed, 8 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index c2ab0e22db0a..70340663136e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -956,6 +956,9 @@ static void i915_gem_context_release_work(struct work_struct *work)
if (vm)
i915_vm_put(vm);
+ if (ctx->client)
+ i915_drm_client_put(ctx->client);
+
mutex_destroy(&ctx->engines_mutex);
mutex_destroy(&ctx->lut_mutex);
@@ -1373,6 +1376,8 @@ static void gem_context_register(struct i915_gem_context *ctx,
ctx->file_priv = fpriv;
ctx->pid = get_task_pid(current, PIDTYPE_PID);
+ ctx->client = i915_drm_client_get(fpriv->client);
+
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
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 c4617e4d9fa9..598c57ac5cdf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -277,6 +277,9 @@ struct i915_gem_context {
/** @link: place with &drm_i915_private.context_list */
struct list_head link;
+ /** @client: struct i915_drm_client */
+ struct i915_drm_client *client;
+
/**
* @ref: reference count
*
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 3/7] drm/i915: Track runtime spent in closed and unreachable GEM contexts
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 1/7] drm/i915: Explicitly track DRM clients Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 2/7] drm/i915: Make GEM contexts " Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 4/7] drm/i915: Track all user contexts per client Tvrtko Ursulin
` (3 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx; +Cc: dri-devel, Tvrtko Ursulin, Aravind Iddamsetty, Chris Wilson
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.
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>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 25 +++++++++++++++++++--
drivers/gpu/drm/i915/i915_drm_client.h | 7 ++++++
2 files changed, 30 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 70340663136e..9b37723b70a9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -800,23 +800,44 @@ static void free_engines_rcu(struct rcu_head *rcu)
free_engines(engines);
}
+static void accumulate_runtime(struct i915_drm_client *client,
+ struct i915_gem_engines *engines)
+{
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+
+ if (!client)
+ return;
+
+ /* 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(client->past_runtime));
+ atomic64_add(intel_context_get_total_runtime_ns(ce),
+ &client->past_runtime[class]);
+ }
+}
+
static int __i915_sw_fence_call
engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
{
struct i915_gem_engines *engines =
container_of(fence, typeof(*engines), fence);
+ struct i915_gem_context *ctx = engines->ctx;
switch (state) {
case FENCE_COMPLETE:
if (!list_empty(&engines->link)) {
- struct i915_gem_context *ctx = engines->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->stale.lock, flags);
list_del(&engines->link);
spin_unlock_irqrestore(&ctx->stale.lock, flags);
}
- i915_gem_context_put(engines->ctx);
+ accumulate_runtime(ctx->client, engines);
+ i915_gem_context_put(ctx);
+
break;
case FENCE_FREE:
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index e8986ad51176..9d80d9f715ee 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -9,6 +9,8 @@
#include <linux/kref.h>
#include <linux/xarray.h>
+#include "gt/intel_engine_types.h"
+
struct drm_i915_private;
struct i915_drm_clients {
@@ -24,6 +26,11 @@ struct i915_drm_client {
unsigned int id;
struct i915_drm_clients *clients;
+
+ /**
+ * @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,
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 4/7] drm/i915: Track all user contexts per client
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
` (2 preceding siblings ...)
2021-09-22 15:51 ` [PATCH 3/7] drm/i915: Track runtime spent in closed and unreachable GEM contexts Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 5/7] drm/i915: Track context current active time Tvrtko Ursulin
` (2 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx; +Cc: dri-devel, Tvrtko Ursulin, Aravind Iddamsetty, Chris Wilson
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>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 12 ++++++++++++
drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 3 +++
drivers/gpu/drm/i915/i915_drm_client.c | 2 ++
drivers/gpu/drm/i915/i915_drm_client.h | 5 +++++
4 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9b37723b70a9..a1ef6be28899 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1190,6 +1190,7 @@ static void set_closed_name(struct i915_gem_context *ctx)
static void context_close(struct i915_gem_context *ctx)
{
+ struct i915_drm_client *client;
struct i915_address_space *vm;
/* Flush any concurrent set_engines() */
@@ -1226,6 +1227,13 @@ static void context_close(struct i915_gem_context *ctx)
list_del(&ctx->link);
spin_unlock(&ctx->i915->gem.contexts.lock);
+ client = ctx->client;
+ if (client) {
+ spin_lock(&client->ctx_lock);
+ list_del_rcu(&ctx->client_link);
+ spin_unlock(&client->ctx_lock);
+ }
+
mutex_unlock(&ctx->mutex);
/*
@@ -1406,6 +1414,10 @@ static void gem_context_register(struct i915_gem_context *ctx,
old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
WARN_ON(old);
+ spin_lock(&ctx->client->ctx_lock);
+ list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
+ spin_unlock(&ctx->client->ctx_lock);
+
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
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 598c57ac5cdf..b878e1b13b38 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -280,6 +280,9 @@ 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 e61e9ba15256..91a8559bebf7 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -38,6 +38,8 @@ struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients)
goto err;
kref_init(&client->kref);
+ spin_lock_init(&client->ctx_lock);
+ INIT_LIST_HEAD(&client->ctx_list);
client->clients = clients;
return client;
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 9d80d9f715ee..7416e18aa33c 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -7,6 +7,8 @@
#define __I915_DRM_CLIENT_H__
#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
#include <linux/xarray.h>
#include "gt/intel_engine_types.h"
@@ -25,6 +27,9 @@ struct i915_drm_client {
unsigned int id;
+ 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;
/**
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 5/7] drm/i915: Track context current active time
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
` (3 preceding siblings ...)
2021-09-22 15:51 ` [PATCH 4/7] drm/i915: Track all user contexts per client Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 6/7] drm: Document fdinfo format specification Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 7/7] drm/i915: Expose client engine utilisation via fdinfo Tvrtko Ursulin
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx; +Cc: dri-devel, Tvrtko Ursulin, Aravind Iddamsetty, Chris Wilson
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.
v2:
* Rename and make __intel_context_get_active_time unlocked.
v3:
* Use GRAPHICS_VER.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com> # v1
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gt/intel_context.c | 27 ++++++++++++++++++-
drivers/gpu/drm/i915/gt/intel_context.h | 15 ++++-------
drivers/gpu/drm/i915/gt/intel_context_types.h | 24 +++++++++++------
.../drm/i915/gt/intel_execlists_submission.c | 23 ++++++++++++----
.../gpu/drm/i915/gt/intel_gt_clock_utils.c | 4 +++
drivers/gpu/drm/i915/gt/intel_lrc.c | 27 ++++++++++---------
drivers/gpu/drm/i915/gt/intel_lrc.h | 24 +++++++++++++++++
drivers/gpu/drm/i915/gt/selftest_lrc.c | 10 +++----
drivers/gpu/drm/i915/i915_gpu_error.c | 9 +++----
drivers/gpu/drm/i915/i915_gpu_error.h | 2 +-
10 files changed, 116 insertions(+), 49 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ff637147b1a9..ae97c311d65b 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -382,7 +382,7 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
ce->ring = NULL;
ce->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);
@@ -532,6 +532,31 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
return active;
}
+u64 intel_context_get_total_runtime_ns(const struct intel_context *ce)
+{
+ u64 total, active;
+
+ total = ce->stats.runtime.total;
+ if (ce->ops->flags & COPS_RUNTIME_CYCLES)
+ total *= ce->engine->gt->clock_period_ns;
+
+ active = READ_ONCE(ce->stats.active);
+ if (active)
+ active = intel_context_clock() - active;
+
+ return total + active;
+}
+
+u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
+{
+ u64 avg = ewma_runtime_read(&ce->stats.runtime.avg);
+
+ if (ce->ops->flags & COPS_RUNTIME_CYCLES)
+ avg *= ce->engine->gt->clock_period_ns;
+
+ return avg;
+}
+
#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 c41098950746..2aaffe1bb388 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -296,18 +296,13 @@ intel_context_clear_nopreempt(struct intel_context *ce)
clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
}
-static inline u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
-{
- const u32 period = ce->engine->gt->clock_period_ns;
-
- return READ_ONCE(ce->runtime.total) * period;
-}
+u64 intel_context_get_total_runtime_ns(const struct intel_context *ce);
+u64 intel_context_get_avg_runtime_ns(struct intel_context *ce);
-static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
+static inline u64 intel_context_clock(void)
{
- const u32 period = ce->engine->gt->clock_period_ns;
-
- return mul_u32_u32(ewma_runtime_read(&ce->runtime.avg), period);
+ /* As we mix CS cycles with CPU clocks, use the raw monotonic clock. */
+ return ktime_get_raw_fast_ns();
}
#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 930569a1a01f..2a8a8d207691 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -35,6 +35,9 @@ struct intel_context_ops {
#define COPS_HAS_INFLIGHT_BIT 0
#define COPS_HAS_INFLIGHT BIT(COPS_HAS_INFLIGHT_BIT)
+#define COPS_RUNTIME_CYCLES_BIT 1
+#define COPS_RUNTIME_CYCLES BIT(COPS_RUNTIME_CYCLES_BIT)
+
int (*alloc)(struct intel_context *ce);
void (*ban)(struct intel_context *ce, struct i915_request *rq);
@@ -128,14 +131,19 @@ struct intel_context {
} lrc;
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 {
+ u64 active;
+
+ /* 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_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 87c595e4efe2..53529713eb50 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -621,8 +621,6 @@ static void __execlists_schedule_out(struct i915_request * const rq,
GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
__set_bit(ccid - 1, &engine->context_tag);
}
-
- lrc_update_runtime(ce);
intel_engine_context_out(engine);
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
if (engine->fw_domain && !--engine->fw_active)
@@ -2003,8 +2001,23 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
* and merits a fresh timeslice. We reinstall the timer after
* inspecting the queue to see if we need to resumbit.
*/
- if (*prev != *execlists->active) /* elide lite-restores */
+ if (*prev != *execlists->active) { /* elide lite-restores */
+ /*
+ * Note the inherent discrepancy between the HW runtime,
+ * recorded as part of the context switch, and the CPU
+ * adjustment for active contexts. We have to hope that
+ * the delay in processing the CS event is very small
+ * and consistent. It works to our advantage to have
+ * the CPU adjustment _undershoot_ (i.e. start later than)
+ * the CS timestamp so we never overreport the runtime
+ * and correct overselves later when updating from HW.
+ */
+ if (*prev)
+ lrc_runtime_stop((*prev)->context);
+ if (*execlists->active)
+ lrc_runtime_start((*execlists->active)->context);
new_timeslice(execlists);
+ }
return inactive;
}
@@ -2598,7 +2611,7 @@ static void execlists_context_cancel_request(struct intel_context *ce,
}
static const struct intel_context_ops execlists_context_ops = {
- .flags = COPS_HAS_INFLIGHT,
+ .flags = COPS_HAS_INFLIGHT | COPS_RUNTIME_CYCLES,
.alloc = execlists_context_alloc,
@@ -3616,7 +3629,7 @@ virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling)
}
static const struct intel_context_ops virtual_context_ops = {
- .flags = COPS_HAS_INFLIGHT,
+ .flags = COPS_HAS_INFLIGHT | COPS_RUNTIME_CYCLES,
.alloc = virtual_context_alloc,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 3513d6f90747..c5b561f71756 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -159,6 +159,10 @@ void intel_gt_init_clock_frequency(struct intel_gt *gt)
if (gt->clock_frequency)
gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1);
+ /* Icelake appears to use another fixed frequency for CTX_TIMESTAMP */
+ if (GRAPHICS_VER(gt->i915) == 11)
+ gt->clock_period_ns = NSEC_PER_SEC / 13750000;
+
GT_TRACE(gt,
"Using clock frequency: %dkHz, period: %dns, wrap: %lldms\n",
gt->clock_frequency / 1000,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 6ba8daea2f56..3f3f189b365a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -774,7 +774,7 @@ static void init_common_regs(u32 * const regs,
CTX_CTRL_RS_CTX_ENABLE);
regs[CTX_CONTEXT_CONTROL] = ctl;
- regs[CTX_TIMESTAMP] = ce->runtime.last;
+ regs[CTX_TIMESTAMP] = ce->stats.runtime.last;
}
static void init_wa_bb_regs(u32 * const regs,
@@ -1667,35 +1667,36 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine)
}
}
-static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
+static void st_runtime_underflow(struct intel_context_stats *stats, s32 dt)
{
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
- ce->runtime.num_underflow++;
- ce->runtime.max_underflow = max_t(u32, ce->runtime.max_underflow, -dt);
+ stats->runtime.num_underflow++;
+ stats->runtime.max_underflow =
+ max_t(u32, stats->runtime.max_underflow, -dt);
#endif
}
void lrc_update_runtime(struct intel_context *ce)
{
+ struct intel_context_stats *stats = &ce->stats;
u32 old;
s32 dt;
- if (intel_context_is_barrier(ce))
+ old = stats->runtime.last;
+ stats->runtime.last = lrc_get_runtime(ce);
+ dt = stats->runtime.last - old;
+ if (!dt)
return;
- old = ce->runtime.last;
- ce->runtime.last = lrc_get_runtime(ce);
- dt = ce->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_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;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 7f697845c4cf..8073674538d7 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -79,4 +79,28 @@ static inline u32 lrc_get_runtime(const struct intel_context *ce)
return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
}
+static inline void lrc_runtime_start(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+
+ if (intel_context_is_barrier(ce))
+ return;
+
+ if (stats->active)
+ return;
+
+ WRITE_ONCE(stats->active, intel_context_clock());
+}
+
+static inline void lrc_runtime_stop(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+
+ if (!stats->active)
+ return;
+
+ lrc_update_runtime(ce);
+ WRITE_ONCE(stats->active, 0);
+}
+
#endif /* __INTEL_LRC_H__ */
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index b0977a3b699b..9b9ee0fe1512 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1751,8 +1751,8 @@ 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;
@@ -1790,11 +1790,11 @@ 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_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2a2d7643b551..f812eabb474a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -504,13 +504,10 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
const char *header,
const struct i915_gem_context_coredump *ctx)
{
- const u32 period = m->i915->gt.clock_period_ns;
-
err_printf(m, "%s%s[%d] prio %d, guilty %d active %d, runtime total %lluns, avg %lluns\n",
header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
ctx->guilty, ctx->active,
- ctx->total_runtime * period,
- mul_u32_u32(ctx->avg_runtime, period));
+ ctx->total_runtime, ctx->avg_runtime);
}
static struct i915_vma_coredump *
@@ -1309,8 +1306,8 @@ 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 = intel_context_get_total_runtime_ns(rq->context);
+ e->avg_runtime = intel_context_get_avg_runtime_ns(rq->context);
simulated = i915_gem_context_no_error_capture(ctx);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index b98d8cdbe4f2..b11deb547672 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -90,7 +90,7 @@ struct intel_engine_coredump {
char comm[TASK_COMM_LEN];
u64 total_runtime;
- u32 avg_runtime;
+ u64 avg_runtime;
pid_t pid;
int active;
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 6/7] drm: Document fdinfo format specification
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
` (4 preceding siblings ...)
2021-09-22 15:51 ` [PATCH 5/7] drm/i915: Track context current active time Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
2021-09-22 15:51 ` [PATCH 7/7] drm/i915: Expose client engine utilisation via fdinfo Tvrtko Ursulin
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx
Cc: dri-devel, Tvrtko Ursulin, David M Nieto, Christian König,
Daniel Vetter, Daniel Stone
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Proposal to standardise the fdinfo text format as optionally output by DRM
drivers.
Idea is that a simple but, well defined, spec will enable generic
userspace tools to be written while at the same time avoiding a more heavy
handed approach of adding a mid-layer to DRM.
i915 implements a subset of the spec, everything apart from the memory
stats currently, and a matching intel_gpu_top tool exists.
Open is to see if AMD can migrate to using the proposed GPU utilisation
key-value pairs, or if they are not workable to see whether to go
vendor specific, or if a standardised alternative can be found which is
workable for both drivers.
Same for the memory utilisation key-value pairs proposal.
v2:
* Update for removal of name and pid.
v3:
* 'Drm-driver' tag will be obtained from struct drm_driver.name. (Daniel)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: David M Nieto <David.Nieto@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Daniel Stone <daniel@fooishbar.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
Documentation/gpu/drm-usage-stats.rst | 97 +++++++++++++++++++++++++++
Documentation/gpu/index.rst | 1 +
2 files changed, 98 insertions(+)
create mode 100644 Documentation/gpu/drm-usage-stats.rst
diff --git a/Documentation/gpu/drm-usage-stats.rst b/Documentation/gpu/drm-usage-stats.rst
new file mode 100644
index 000000000000..c669026be244
--- /dev/null
+++ b/Documentation/gpu/drm-usage-stats.rst
@@ -0,0 +1,97 @@
+.. _drm-client-usage-stats:
+
+======================
+DRM client usage stats
+======================
+
+DRM drivers can choose to export partly standardised text output via the
+`fops->show_fdinfo()` as part of the driver specific file operations registered
+in the `struct drm_driver` object registered with the DRM core.
+
+One purpose of this output is to enable writing as generic as practicaly
+feasible `top(1)` like userspace monitoring tools.
+
+Given the differences between various DRM drivers the specification of the
+output is split between common and driver specific parts. Having said that,
+wherever possible effort should still be made to standardise as much as
+possible.
+
+File format specification
+=========================
+
+- File shall contain one key value pair per one line of text.
+- Colon character (`:`) must be used to delimit keys and values.
+- All keys shall be prefixed with `drm-`.
+- Whitespace between the delimiter and first non-whitespace character shall be
+ ignored when parsing.
+- Neither keys or values are allowed to contain whitespace characters.
+- Numerical key value pairs can end with optional unit string.
+- Data type of the value is fixed as defined in the specification.
+
+Key types
+---------
+
+1. Mandatory, fully standardised.
+2. Optional, fully standardised.
+3. Driver specific.
+
+Data types
+----------
+
+- <uint> - Unsigned integer without defining the maximum value.
+- <str> - String excluding any above defined reserved characters or whitespace.
+
+Mandatory fully standardised keys
+---------------------------------
+
+- drm-driver: <str>
+
+String shall contain the name this driver registered as via the respective
+`struct drm_driver` data structure.
+
+Optional fully standardised keys
+--------------------------------
+
+- drm-pdev: <aaaa:bb.cc.d>
+
+For PCI devices this should contain the PCI slot address of the device in
+question.
+
+- drm-client-id: <uint>
+
+Unique value relating to the open DRM file descriptor used to distinguish
+duplicated and shared file descriptors. Conceptually the value should map 1:1
+to the in kernel representation of `struct drm_file` instances.
+
+Uniqueness of the value shall be either globally unique, or unique within the
+scope of each device, in which case `drm-pdev` shall be present as well.
+
+Userspace should make sure to not double account any usage statistics by using
+the above described criteria in order to associate data to individual clients.
+
+- drm-engine-<str>: <uint> ns
+
+GPUs usually contain multiple execution engines. Each shall be given a stable
+and unique name (str), with possible values documented in the driver specific
+documentation.
+
+Value shall be in specified time units which the respective GPU engine spent
+busy executing workloads belonging to this client.
+
+Values are not required to be constantly monotonic if it makes the driver
+implementation easier, but are required to catch up with the previously reported
+larger value within a reasonable period. Upon observing a value lower than what
+was previously read, userspace is expected to stay with that larger previous
+value until a monotonic update is seen.
+
+- drm-memory-<str>: <uint> [KiB|MiB]
+
+Each possible memory type which can be used to store buffer objects by the
+GPU in question shall be given a stable and unique name to be returned as the
+string here.
+
+Value shall reflect the amount of storage currently consumed by the buffer
+object belong to this client, in the respective memory region.
+
+Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
+indicating kibi- or mebi-bytes.
diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst
index b9c1214d8f23..b99dede9a5b1 100644
--- a/Documentation/gpu/index.rst
+++ b/Documentation/gpu/index.rst
@@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide
drm-kms
drm-kms-helpers
drm-uapi
+ drm-usage-stats
driver-uapi
drm-client
drivers
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 7/7] drm/i915: Expose client engine utilisation via fdinfo
2021-09-22 15:51 [PATCH 0/7] Per client GPU stats Tvrtko Ursulin
` (5 preceding siblings ...)
2021-09-22 15:51 ` [PATCH 6/7] drm: Document fdinfo format specification Tvrtko Ursulin
@ 2021-09-22 15:51 ` Tvrtko Ursulin
6 siblings, 0 replies; 10+ messages in thread
From: Tvrtko Ursulin @ 2021-09-22 15:51 UTC (permalink / raw)
To: Intel-gfx
Cc: dri-devel, Tvrtko Ursulin, David M Nieto, Christian König,
Daniel Vetter
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Similar to AMD commit
874442541133 ("drm/amdgpu: Add show_fdinfo() interface"), using the
infrastructure added in previous patches, we add basic client info
and GPU engine utilisation for i915.
Example of the output:
pos: 0
flags: 0100002
mnt_id: 21
drm-driver: i915
drm-pdev: 0000:00:02.0
drm-client-id: 7
drm-engine-render: 9288864723 ns
drm-engine-copy: 2035071108 ns
drm-engine-video: 0 ns
drm-engine-video-enhance: 0 ns
v2:
* Update for removal of name and pid.
v3:
* Use drm_driver.name.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: David M Nieto <David.Nieto@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Acked-by: Christian König <christian.koenig@amd.com>
---
Documentation/gpu/drm-usage-stats.rst | 6 +++
Documentation/gpu/i915.rst | 27 ++++++++++
drivers/gpu/drm/i915/i915_drm_client.c | 73 ++++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_drm_client.h | 4 ++
drivers/gpu/drm/i915/i915_drv.c | 3 ++
5 files changed, 113 insertions(+)
diff --git a/Documentation/gpu/drm-usage-stats.rst b/Documentation/gpu/drm-usage-stats.rst
index c669026be244..6952f8389d07 100644
--- a/Documentation/gpu/drm-usage-stats.rst
+++ b/Documentation/gpu/drm-usage-stats.rst
@@ -95,3 +95,9 @@ object belong to this client, in the respective memory region.
Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
indicating kibi- or mebi-bytes.
+
+===============================
+Driver specific implementations
+===============================
+
+:ref:`i915-usage-stats`
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 311e10400708..36cd6f74fb1b 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -700,3 +700,30 @@ The style guide for ``i915_reg.h``.
.. kernel-doc:: drivers/gpu/drm/i915/i915_reg.h
:doc: The i915 register macro definition style guide
+
+.. _i915-usage-stats:
+
+i915 DRM client usage stats implementation
+==========================================
+
+The drm/i915 driver implements the DRM client usage stats specification as
+documented in :ref:`drm-client-usage-stats`.
+
+Example of the output showing the implemented key value pairs and entirety of
+the currenly possible format options:
+
+::
+
+ pos: 0
+ flags: 0100002
+ mnt_id: 21
+ drm-driver: i915
+ drm-pdev: 0000:00:02.0
+ drm-client-id: 7
+ drm-engine-render: 9288864723 ns
+ drm-engine-copy: 2035071108 ns
+ drm-engine-video: 0 ns
+ drm-engine-video-enhance: 0 ns
+
+Possible `drm-engine-` key names are: `render`, `copy`, `video` and
+`video-enhance`.
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 91a8559bebf7..06dbd20ce763 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -7,6 +7,11 @@
#include <linux/slab.h>
#include <linux/types.h>
+#include <uapi/drm/i915_drm.h>
+
+#include <drm/drm_print.h>
+
+#include "gem/i915_gem_context.h"
#include "i915_drm_client.h"
#include "i915_gem.h"
#include "i915_utils.h"
@@ -68,3 +73,71 @@ void i915_drm_clients_fini(struct i915_drm_clients *clients)
GEM_BUG_ON(!xa_empty(&clients->xarray));
xa_destroy(&clients->xarray);
}
+
+#ifdef CONFIG_PROC_FS
+static const char * const uabi_class_names[] = {
+ [I915_ENGINE_CLASS_RENDER] = "render",
+ [I915_ENGINE_CLASS_COPY] = "copy",
+ [I915_ENGINE_CLASS_VIDEO] = "video",
+ [I915_ENGINE_CLASS_VIDEO_ENHANCE] = "video-enhance",
+};
+
+static u64 busy_add(struct i915_gem_context *ctx, unsigned int class)
+{
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+ u64 total = 0;
+
+ for_each_gem_engine(ce, rcu_dereference(ctx->engines), it) {
+ if (ce->engine->uabi_class != class)
+ continue;
+
+ total += intel_context_get_total_runtime_ns(ce);
+ }
+
+ return total;
+}
+
+static void
+show_client_class(struct seq_file *m,
+ struct i915_drm_client *client,
+ unsigned int class)
+{
+ const struct list_head *list = &client->ctx_list;
+ u64 total = atomic64_read(&client->past_runtime[class]);
+ struct i915_gem_context *ctx;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, list, client_link)
+ total += busy_add(ctx, class);
+ rcu_read_unlock();
+
+ return seq_printf(m, "drm-engine-%s:\t%llu ns\n",
+ uabi_class_names[class], total);
+}
+
+void i915_drm_client_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct drm_file *file = f->private_data;
+ struct drm_i915_file_private *file_priv = file->driver_priv;
+ struct drm_i915_private *i915 = file_priv->dev_priv;
+ struct i915_drm_client *client = file_priv->client;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ unsigned int i;
+
+ /*
+ * ******************************************************************
+ * For text output format description please see drm-usage-stats.rst!
+ * ******************************************************************
+ */
+
+ seq_printf(m, "drm-driver:\t%s\n", i915->drm.driver->name);
+ seq_printf(m, "drm-pdev:\t%04x:%02x:%02x.%d\n",
+ pci_domain_nr(pdev->bus), pdev->bus->number,
+ PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
+ seq_printf(m, "drm-client-id:\t%u\n", client->id);
+
+ for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++)
+ show_client_class(m, client, i);
+}
+#endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 7416e18aa33c..d96d6a06302e 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -57,6 +57,10 @@ static inline void i915_drm_client_put(struct i915_drm_client *client)
struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients);
+#ifdef CONFIG_PROC_FS
+void i915_drm_client_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
void i915_drm_clients_fini(struct i915_drm_clients *clients);
#endif /* !__I915_DRM_CLIENT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6418f3dbdad0..8ab0d49fd98a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1711,6 +1711,9 @@ static const struct file_operations i915_driver_fops = {
.read = drm_read,
.compat_ioctl = i915_ioc32_compat_ioctl,
.llseek = noop_llseek,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = i915_drm_client_fdinfo,
+#endif
};
static int
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread