mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 01:45:23 +07:00
a679f58d05
When we return pages to the system, we ensure that they are marked as being in the CPU domain since any external access is uncontrolled and we must assume the worst. This means that we need to always flush the pages on acquisition if we need to use them on the GPU, and from the beginning have used set-domain. Set-domain is overkill for the purpose as it is a general synchronisation barrier, but our intent is to only flush the pages being swapped in. If we move that flush into the pages acquisition phase, we know then that when we have obj->mm.pages, they are coherent with the GPU and need only maintain that status without resorting to heavy handed use of set-domain. The principle knock-on effect for userspace is through mmap-gtt pagefaulting. Our uAPI has always implied that the GTT mmap was async (especially as when any pagefault occurs is unpredicatable to userspace) and so userspace had to apply explicit domain control itself (set-domain). However, swapping is transparent to the kernel, and so on first fault we need to acquire the pages and make them coherent for access through the GTT. Our use of set-domain here leaks into the uABI that the first pagefault was synchronous. This is unintentional and baring a few igt should be unoticed, nevertheless we bump the uABI version for mmap-gtt to reflect the change in behaviour. Another implication of the change is that gem_create() is presumed to create an object that is coherent with the CPU and is in the CPU write domain, so a set-domain(CPU) following a gem_create() would be a minor operation that merely checked whether we could allocate all pages for the object. On applying this change, a set-domain(CPU) causes a clflush as we acquire the pages. This will have a small impact on mesa as we move the clflush here on !llc from execbuf time to create, but that should have minimal performance impact as the same clflush exists but is now done early and because of the clflush issue, userspace recycles bo and so should resist allocating fresh objects. Internally, the presumption that objects are created in the CPU write-domain and remain so through writes to obj->mm.mapping is more prevalent than I expected; but easy enough to catch and apply a manual flush. For the future, we should push the page flush from the central set_pages() into the callers so that we can more finely control when it is applied, but for now doing it one location is easier to validate, at the cost of sometimes flushing when there is no need. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Matthew Auld <matthew.william.auld@gmail.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190321161908.8007-1-chris@chris-wilson.co.uk
338 lines
8.6 KiB
C
338 lines
8.6 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 "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_flush_map(obj);
|
|
i915_gem_object_unpin_map(obj);
|
|
}
|
|
|
|
static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
struct page *page;
|
|
|
|
if (page_num >= obj->base.size >> PAGE_SHIFT)
|
|
return NULL;
|
|
|
|
if (!i915_gem_object_has_struct_page(obj))
|
|
return NULL;
|
|
|
|
if (i915_gem_object_pin_pages(obj))
|
|
return NULL;
|
|
|
|
/* Synchronisation is left to the caller (via .begin_cpu_access()) */
|
|
page = i915_gem_object_get_page(obj, page_num);
|
|
if (IS_ERR(page))
|
|
goto err_unpin;
|
|
|
|
return kmap(page);
|
|
|
|
err_unpin:
|
|
i915_gem_object_unpin_pages(obj);
|
|
return NULL;
|
|
}
|
|
|
|
static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
|
|
{
|
|
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
|
|
|
|
kunmap(virt_to_page(addr));
|
|
i915_gem_object_unpin_pages(obj);
|
|
}
|
|
|
|
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 = call_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,
|
|
.map = i915_gem_dmabuf_kmap,
|
|
.unmap = i915_gem_dmabuf_kunmap,
|
|
.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 int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
|
|
{
|
|
struct sg_table *pages;
|
|
unsigned int sg_page_sizes;
|
|
|
|
pages = dma_buf_map_attachment(obj->base.import_attach,
|
|
DMA_BIDIRECTIONAL);
|
|
if (IS_ERR(pages))
|
|
return PTR_ERR(pages);
|
|
|
|
sg_page_sizes = i915_sg_page_sizes(pages->sgl);
|
|
|
|
__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
|
|
|
|
return 0;
|
|
}
|
|
|
|
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();
|
|
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->read_domains = I915_GEM_DOMAIN_GTT;
|
|
obj->write_domain = 0;
|
|
|
|
return &obj->base;
|
|
|
|
fail_detach:
|
|
dma_buf_detach(dma_buf, attach);
|
|
dma_buf_put(dma_buf);
|
|
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
|
|
#include "selftests/mock_dmabuf.c"
|
|
#include "selftests/i915_gem_dmabuf.c"
|
|
#endif
|