drm/i915: Move GEM client throttling to its own file
Continuing the decluttering of i915_gem.c by moving the client self throttling into its own file. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190528092956.14910-13-chris@chris-wilson.co.uk
This commit is contained in:
parent
3f43c8767e
commit
446e2d16a1
|
@ -104,6 +104,7 @@ gem-y += \
|
|||
gem/i915_gem_shmem.o \
|
||||
gem/i915_gem_shrinker.o \
|
||||
gem/i915_gem_stolen.o \
|
||||
gem/i915_gem_throttle.o \
|
||||
gem/i915_gem_tiling.o \
|
||||
gem/i915_gem_userptr.o \
|
||||
gem/i915_gem_wait.o \
|
||||
|
|
|
@ -0,0 +1,73 @@
|
|||
/*
|
||||
* SPDX-License-Identifier: MIT
|
||||
*
|
||||
* Copyright © 2014-2016 Intel Corporation
|
||||
*/
|
||||
|
||||
#include <linux/jiffies.h>
|
||||
|
||||
#include <drm/drm_file.h>
|
||||
|
||||
#include "i915_drv.h"
|
||||
#include "i915_gem_ioctls.h"
|
||||
#include "i915_gem_object.h"
|
||||
|
||||
/*
|
||||
* 20ms is a fairly arbitrary limit (greater than the average frame time)
|
||||
* chosen to prevent the CPU getting more than a frame ahead of the GPU
|
||||
* (when using lax throttling for the frontbuffer). We also use it to
|
||||
* offer free GPU waitboosts for severely congested workloads.
|
||||
*/
|
||||
#define DRM_I915_THROTTLE_JIFFIES msecs_to_jiffies(20)
|
||||
|
||||
/*
|
||||
* Throttle our rendering by waiting until the ring has completed our requests
|
||||
* emitted over 20 msec ago.
|
||||
*
|
||||
* Note that if we were to use the current jiffies each time around the loop,
|
||||
* we wouldn't escape the function with any frames outstanding if the time to
|
||||
* render a frame was over 20ms.
|
||||
*
|
||||
* This should get us reasonable parallelism between CPU and GPU but also
|
||||
* relatively low latency when blocking on a particular request to finish.
|
||||
*/
|
||||
int
|
||||
i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
|
||||
struct drm_file *file)
|
||||
{
|
||||
struct drm_i915_file_private *file_priv = file->driver_priv;
|
||||
unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES;
|
||||
struct i915_request *request, *target = NULL;
|
||||
long ret;
|
||||
|
||||
/* ABI: return -EIO if already wedged */
|
||||
ret = i915_terminally_wedged(to_i915(dev));
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
spin_lock(&file_priv->mm.lock);
|
||||
list_for_each_entry(request, &file_priv->mm.request_list, client_link) {
|
||||
if (time_after_eq(request->emitted_jiffies, recent_enough))
|
||||
break;
|
||||
|
||||
if (target) {
|
||||
list_del(&target->client_link);
|
||||
target->file_priv = NULL;
|
||||
}
|
||||
|
||||
target = request;
|
||||
}
|
||||
if (target)
|
||||
i915_request_get(target);
|
||||
spin_unlock(&file_priv->mm.lock);
|
||||
|
||||
if (!target)
|
||||
return 0;
|
||||
|
||||
ret = i915_request_wait(target,
|
||||
I915_WAIT_INTERRUPTIBLE,
|
||||
MAX_SCHEDULE_TIMEOUT);
|
||||
i915_request_put(target);
|
||||
|
||||
return ret < 0 ? ret : 0;
|
||||
}
|
|
@ -213,12 +213,6 @@ struct drm_i915_file_private {
|
|||
struct {
|
||||
spinlock_t lock;
|
||||
struct list_head request_list;
|
||||
/* 20ms is a fairly arbitrary limit (greater than the average frame time)
|
||||
* chosen to prevent the CPU getting more than a frame ahead of the GPU
|
||||
* (when using lax throttling for the frontbuffer). We also use it to
|
||||
* offer free GPU waitboosts for severely congested workloads.
|
||||
*/
|
||||
#define DRM_I915_THROTTLE_JIFFIES msecs_to_jiffies(20)
|
||||
} mm;
|
||||
|
||||
struct idr context_idr;
|
||||
|
|
|
@ -1012,57 +1012,6 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915,
|
|||
return 0;
|
||||
}
|
||||
|
||||
/* Throttle our rendering by waiting until the ring has completed our requests
|
||||
* emitted over 20 msec ago.
|
||||
*
|
||||
* Note that if we were to use the current jiffies each time around the loop,
|
||||
* we wouldn't escape the function with any frames outstanding if the time to
|
||||
* render a frame was over 20ms.
|
||||
*
|
||||
* This should get us reasonable parallelism between CPU and GPU but also
|
||||
* relatively low latency when blocking on a particular request to finish.
|
||||
*/
|
||||
static int
|
||||
i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
|
||||
{
|
||||
struct drm_i915_private *dev_priv = to_i915(dev);
|
||||
struct drm_i915_file_private *file_priv = file->driver_priv;
|
||||
unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES;
|
||||
struct i915_request *request, *target = NULL;
|
||||
long ret;
|
||||
|
||||
/* ABI: return -EIO if already wedged */
|
||||
ret = i915_terminally_wedged(dev_priv);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
spin_lock(&file_priv->mm.lock);
|
||||
list_for_each_entry(request, &file_priv->mm.request_list, client_link) {
|
||||
if (time_after_eq(request->emitted_jiffies, recent_enough))
|
||||
break;
|
||||
|
||||
if (target) {
|
||||
list_del(&target->client_link);
|
||||
target->file_priv = NULL;
|
||||
}
|
||||
|
||||
target = request;
|
||||
}
|
||||
if (target)
|
||||
i915_request_get(target);
|
||||
spin_unlock(&file_priv->mm.lock);
|
||||
|
||||
if (target == NULL)
|
||||
return 0;
|
||||
|
||||
ret = i915_request_wait(target,
|
||||
I915_WAIT_INTERRUPTIBLE,
|
||||
MAX_SCHEDULE_TIMEOUT);
|
||||
i915_request_put(target);
|
||||
|
||||
return ret < 0 ? ret : 0;
|
||||
}
|
||||
|
||||
struct i915_vma *
|
||||
i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
|
||||
const struct i915_ggtt_view *view,
|
||||
|
@ -1142,13 +1091,6 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
|
|||
return vma;
|
||||
}
|
||||
|
||||
int
|
||||
i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
|
||||
struct drm_file *file_priv)
|
||||
{
|
||||
return i915_gem_ring_throttle(dev, file_priv);
|
||||
}
|
||||
|
||||
int
|
||||
i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
|
||||
struct drm_file *file_priv)
|
||||
|
|
Loading…
Reference in New Issue