mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-20 02:34:23 +08:00
d07f0e59b2
In preparation to support many distinct timelines, we need to expand the activity tracking on the GEM object to handle more than just a request per engine. We already use the struct reservation_object on the dma-buf to handle many fence contexts, so integrating that into the GEM object itself is the preferred solution. (For example, we can now share the same reservation_object between every consumer/producer using this buffer and skip the manual import/export via dma-buf.) v2: Reimplement busy-ioctl (by walking the reservation object), postpone the ABI change for another day. Similarly use the reservation object to find the last_write request (if active and from i915) for choosing display CS flips. Caveats: * busy-ioctl: busy-ioctl only reports on the native fences, it will not warn of stalls (in set-domain-ioctl, pread/pwrite etc) if the object is being rendered to by external fences. It also will not report the same busy state as wait-ioctl (or polling on the dma-buf) in the same circumstances. On the plus side, it does retain reporting of which *i915* engines are engaged with this object. * non-blocking atomic modesets take a step backwards as the wait for render completion blocks the ioctl. This is fixed in a subsequent patch to use a fence instead for awaiting on the rendering, see "drm/i915: Restore nonblocking awaits for modesetting" * dynamic array manipulation for shared-fences in reservation is slower than the previous lockless static assignment (e.g. gem_exec_lut_handle runtime on ivb goes from 42s to 66s), mainly due to atomic operations (maintaining the fence refcounts). * loss of object-level retirement callbacks, emulated by VMA retirement tracking. * minor loss of object-level last activity information from debugfs, could be replaced with per-vma information if desired Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20161028125858.23563-21-chris@chris-wilson.co.uk
310 lines
8.0 KiB
C
310 lines
8.0 KiB
C
/*
|
|
* Copyright 2012 Red Hat Inc
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
* to deal in the Software without restriction, including without limitation
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice (including the next
|
|
* paragraph) shall be included in all copies or substantial portions of the
|
|
* Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
|
* DEALINGS IN THE SOFTWARE.
|
|
*
|
|
* Authors:
|
|
* Dave Airlie <airlied@redhat.com>
|
|
*/
|
|
|
|
#include <linux/dma-buf.h>
|
|
#include <linux/reservation.h>
|
|
|
|
#include <drm/drmP.h>
|
|
|
|
#include "i915_drv.h"
|
|
|
|
static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
|
|
{
|
|
return to_intel_bo(buf->priv);
|
|
}
|
|
|
|
static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment,
|
|
enum dma_data_direction dir)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
|
|
struct sg_table *st;
|
|
struct scatterlist *src, *dst;
|
|
int ret, i;
|
|
|
|
ret = i915_gem_object_pin_pages(obj);
|
|
if (ret)
|
|
goto err;
|
|
|
|
/* Copy sg so that we make an independent mapping */
|
|
st = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
|
|
if (st == NULL) {
|
|
ret = -ENOMEM;
|
|
goto err_unpin_pages;
|
|
}
|
|
|
|
ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL);
|
|
if (ret)
|
|
goto err_free;
|
|
|
|
src = obj->mm.pages->sgl;
|
|
dst = st->sgl;
|
|
for (i = 0; i < obj->mm.pages->nents; i++) {
|
|
sg_set_page(dst, sg_page(src), src->length, 0);
|
|
dst = sg_next(dst);
|
|
src = sg_next(src);
|
|
}
|
|
|
|
if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) {
|
|
ret = -ENOMEM;
|
|
goto err_free_sg;
|
|
}
|
|
|
|
return st;
|
|
|
|
err_free_sg:
|
|
sg_free_table(st);
|
|
err_free:
|
|
kfree(st);
|
|
err_unpin_pages:
|
|
i915_gem_object_unpin_pages(obj);
|
|
err:
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
|
|
struct sg_table *sg,
|
|
enum dma_data_direction dir)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
|
|
|
|
dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir);
|
|
sg_free_table(sg);
|
|
kfree(sg);
|
|
|
|
i915_gem_object_unpin_pages(obj);
|
|
}
|
|
|
|
static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
|
|
return i915_gem_object_pin_map(obj, I915_MAP_WB);
|
|
}
|
|
|
|
static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
|
|
i915_gem_object_unpin_map(obj);
|
|
}
|
|
|
|
static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
|
|
{
|
|
|
|
}
|
|
static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
|
|
{
|
|
|
|
}
|
|
|
|
static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
int ret;
|
|
|
|
if (obj->base.size < vma->vm_end - vma->vm_start)
|
|
return -EINVAL;
|
|
|
|
if (!obj->base.filp)
|
|
return -ENODEV;
|
|
|
|
ret = obj->base.filp->f_op->mmap(obj->base.filp, vma);
|
|
if (ret)
|
|
return ret;
|
|
|
|
fput(vma->vm_file);
|
|
vma->vm_file = get_file(obj->base.filp);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction direction)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
struct drm_device *dev = obj->base.dev;
|
|
bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE);
|
|
int err;
|
|
|
|
err = i915_gem_object_pin_pages(obj);
|
|
if (err)
|
|
return err;
|
|
|
|
err = i915_mutex_lock_interruptible(dev);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = i915_gem_object_set_to_cpu_domain(obj, write);
|
|
mutex_unlock(&dev->struct_mutex);
|
|
|
|
out:
|
|
i915_gem_object_unpin_pages(obj);
|
|
return err;
|
|
}
|
|
|
|
static int i915_gem_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction direction)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
struct drm_device *dev = obj->base.dev;
|
|
int err;
|
|
|
|
err = i915_gem_object_pin_pages(obj);
|
|
if (err)
|
|
return err;
|
|
|
|
err = i915_mutex_lock_interruptible(dev);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = i915_gem_object_set_to_gtt_domain(obj, false);
|
|
mutex_unlock(&dev->struct_mutex);
|
|
|
|
out:
|
|
i915_gem_object_unpin_pages(obj);
|
|
return err;
|
|
}
|
|
|
|
static const struct dma_buf_ops i915_dmabuf_ops = {
|
|
.map_dma_buf = i915_gem_map_dma_buf,
|
|
.unmap_dma_buf = i915_gem_unmap_dma_buf,
|
|
.release = drm_gem_dmabuf_release,
|
|
.kmap = i915_gem_dmabuf_kmap,
|
|
.kmap_atomic = i915_gem_dmabuf_kmap_atomic,
|
|
.kunmap = i915_gem_dmabuf_kunmap,
|
|
.kunmap_atomic = i915_gem_dmabuf_kunmap_atomic,
|
|
.mmap = i915_gem_dmabuf_mmap,
|
|
.vmap = i915_gem_dmabuf_vmap,
|
|
.vunmap = i915_gem_dmabuf_vunmap,
|
|
.begin_cpu_access = i915_gem_begin_cpu_access,
|
|
.end_cpu_access = i915_gem_end_cpu_access,
|
|
};
|
|
|
|
struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
|
|
struct drm_gem_object *gem_obj, int flags)
|
|
{
|
|
struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
|
|
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
|
|
|
|
exp_info.ops = &i915_dmabuf_ops;
|
|
exp_info.size = gem_obj->size;
|
|
exp_info.flags = flags;
|
|
exp_info.priv = gem_obj;
|
|
exp_info.resv = obj->resv;
|
|
|
|
if (obj->ops->dmabuf_export) {
|
|
int ret = obj->ops->dmabuf_export(obj);
|
|
if (ret)
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
return drm_gem_dmabuf_export(dev, &exp_info);
|
|
}
|
|
|
|
static struct sg_table *
|
|
i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
|
|
{
|
|
return dma_buf_map_attachment(obj->base.import_attach,
|
|
DMA_BIDIRECTIONAL);
|
|
}
|
|
|
|
static void i915_gem_object_put_pages_dmabuf(struct drm_i915_gem_object *obj,
|
|
struct sg_table *pages)
|
|
{
|
|
dma_buf_unmap_attachment(obj->base.import_attach, pages,
|
|
DMA_BIDIRECTIONAL);
|
|
}
|
|
|
|
static const struct drm_i915_gem_object_ops i915_gem_object_dmabuf_ops = {
|
|
.get_pages = i915_gem_object_get_pages_dmabuf,
|
|
.put_pages = i915_gem_object_put_pages_dmabuf,
|
|
};
|
|
|
|
struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
|
|
struct dma_buf *dma_buf)
|
|
{
|
|
struct dma_buf_attachment *attach;
|
|
struct drm_i915_gem_object *obj;
|
|
int ret;
|
|
|
|
/* is this one of own objects? */
|
|
if (dma_buf->ops == &i915_dmabuf_ops) {
|
|
obj = dma_buf_to_obj(dma_buf);
|
|
/* is it from our device? */
|
|
if (obj->base.dev == dev) {
|
|
/*
|
|
* Importing dmabuf exported from out own gem increases
|
|
* refcount on gem itself instead of f_count of dmabuf.
|
|
*/
|
|
return &i915_gem_object_get(obj)->base;
|
|
}
|
|
}
|
|
|
|
/* need to attach */
|
|
attach = dma_buf_attach(dma_buf, dev->dev);
|
|
if (IS_ERR(attach))
|
|
return ERR_CAST(attach);
|
|
|
|
get_dma_buf(dma_buf);
|
|
|
|
obj = i915_gem_object_alloc(dev);
|
|
if (obj == NULL) {
|
|
ret = -ENOMEM;
|
|
goto fail_detach;
|
|
}
|
|
|
|
drm_gem_private_object_init(dev, &obj->base, dma_buf->size);
|
|
i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops);
|
|
obj->base.import_attach = attach;
|
|
obj->resv = dma_buf->resv;
|
|
|
|
/* We use GTT as shorthand for a coherent domain, one that is
|
|
* neither in the GPU cache nor in the CPU cache, where all
|
|
* writes are immediately visible in memory. (That's not strictly
|
|
* true, but it's close! There are internal buffers such as the
|
|
* write-combined buffer or a delay through the chipset for GTT
|
|
* writes that do require us to treat GTT as a separate cache domain.)
|
|
*/
|
|
obj->base.read_domains = I915_GEM_DOMAIN_GTT;
|
|
obj->base.write_domain = 0;
|
|
|
|
return &obj->base;
|
|
|
|
fail_detach:
|
|
dma_buf_detach(dma_buf, attach);
|
|
dma_buf_put(dma_buf);
|
|
|
|
return ERR_PTR(ret);
|
|
}
|