On 6/22/20 9:18 AM, Christian König wrote:
Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
Will be used to reroute CPU mapped BO's page faults once
device is removed.
Signed-off-by: Andrey Grodzovsky <andrey.grodzov...@amd.com>
---
drivers/gpu/drm/drm_file.c | 8 ++++++++
drivers/gpu/drm/drm_prime.c | 10 ++++++++++
include/drm/drm_file.h | 2 ++
include/drm/drm_gem.h | 2 ++
4 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c4c704e..67c0770 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct drm_minor
*minor)
goto out_prime_destroy;
}
+ file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!file->dummy_page) {
+ ret = -ENOMEM;
+ goto out_prime_destroy;
+ }
+
return file;
out_prime_destroy:
@@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
if (dev->driver->postclose)
dev->driver->postclose(dev, file);
+ __free_page(file->dummy_page);
+
drm_prime_destroy_file_private(&file->prime);
WARN_ON(!list_empty(&file->event_list));
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 1de2cde..c482e9c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct drm_device
*dev,
ret = drm_prime_add_buf_handle(&file_priv->prime,
dma_buf, *handle);
+
+ if (!ret) {
+ obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!obj->dummy_page)
+ ret = -ENOMEM;
+ }
+
While the per file case still looks acceptable this is a clear NAK
since it will massively increase the memory needed for a prime
exported object.
I think that this is quite overkill in the first place and for the hot
unplug case we can just use the global dummy page as well.
Christian.
Global dummy page is good for read access, what do you do on write
access ? My first approach was indeed to map at first global dummy page
as read only and mark the vma->vm_flags as !VM_SHARED assuming that this
would trigger Copy On Write flow in core mm
(https://elixir.bootlin.com/linux/v5.7-rc7/source/mm/memory.c#L3977) on
the next page fault to same address triggered by a write access but then
i realized a new COW page will be allocated for each such mapping and
this is much more wasteful then having a dedicated page per GEM object.
We can indeed optimize by allocating this dummy page on the first page
fault after device disconnect instead on GEM object creation.
Andrey
mutex_unlock(&file_priv->prime.lock);
if (ret)
goto fail;
@@ -1006,6 +1013,9 @@ void drm_prime_gem_destroy(struct
drm_gem_object *obj, struct sg_table *sg)
dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL);
dma_buf = attach->dmabuf;
dma_buf_detach(attach->dmabuf, attach);
+
+ __free_page(obj->dummy_page);
+
/* remove the reference */
dma_buf_put(dma_buf);
}
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 19df802..349a658 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -335,6 +335,8 @@ struct drm_file {
*/
struct drm_prime_file_private prime;
+ struct page *dummy_page;
+
/* private: */
#if IS_ENABLED(CONFIG_DRM_LEGACY)
unsigned long lock_count; /* DRI1 legacy lock count */
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 0b37506..47460d1 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -310,6 +310,8 @@ struct drm_gem_object {
*
*/
const struct drm_gem_object_funcs *funcs;
+
+ struct page *dummy_page;
};
/**
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
