On Wed, Oct 7, 2020 at 10:33 PM John Hubbard jhubbard@nvidia.com wrote:
On 10/7/20 9:44 AM, Daniel Vetter wrote:
All we need are a pages array, pin_user_pages_fast can give us that directly. Plus this avoids the entire raw pfn side of get_vaddr_frames.
Signed-off-by: Daniel Vetter daniel.vetter@intel.com Cc: Jason Gunthorpe jgg@ziepe.ca Cc: Inki Dae inki.dae@samsung.com Cc: Joonyoung Shim jy0922.shim@samsung.com Cc: Seung-Woo Kim sw0312.kim@samsung.com Cc: Kyungmin Park kyungmin.park@samsung.com Cc: Kukjin Kim kgene@kernel.org Cc: Krzysztof Kozlowski krzk@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Cc: John Hubbard jhubbard@nvidia.com Cc: Jérôme Glisse jglisse@redhat.com Cc: Jan Kara jack@suse.cz Cc: Dan Williams dan.j.williams@intel.com Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org
drivers/gpu/drm/exynos/Kconfig | 1 - drivers/gpu/drm/exynos/exynos_drm_g2d.c | 48 ++++++++++++------------- 2 files changed, 22 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 6417f374b923..43257ef3c09d 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -88,7 +88,6 @@ comment "Sub-drivers" config DRM_EXYNOS_G2D bool "G2D" depends on VIDEO_SAMSUNG_S5P_G2D=n || COMPILE_TEST
select FRAME_VECTOR help Choose this option if you want to use Exynos G2D for DRM.diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 967a5cdc120e..c83f6faac9de 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -205,7 +205,8 @@ struct g2d_cmdlist_userptr { dma_addr_t dma_addr; unsigned long userptr; unsigned long size;
struct frame_vector *vec;
struct page **pages;unsigned int npages; struct sg_table *sgt; atomic_t refcount; bool in_pool;@@ -378,7 +379,7 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d, bool force) { struct g2d_cmdlist_userptr *g2d_userptr = obj;
struct page **pages;
int i;The above line can also be deleted, see below.
if (!obj) return;@@ -398,15 +399,11 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d, dma_unmap_sgtable(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt, DMA_BIDIRECTIONAL, 0);
pages = frame_vector_pages(g2d_userptr->vec);if (!IS_ERR(pages)) {int i;
for (i = 0; i < g2d_userptr->npages; i++)set_page_dirty_lock(g2d_userptr->pages[i]);
for (i = 0; i < frame_vector_count(g2d_userptr->vec); i++)set_page_dirty_lock(pages[i]);}put_vaddr_frames(g2d_userptr->vec);frame_vector_destroy(g2d_userptr->vec);
unpin_user_pages(g2d_userptr->pages, g2d_userptr->npages);kvfree(g2d_userptr->pages);You can avoid writing your own loop, and just simplify the whole thing down to two lines:
unpin_user_pages_dirty_lock(g2d_userptr->pages, g2d_userptr->npages, true); kvfree(g2d_userptr->pages);
Oh nice, this is neat. I'll also roll it out in the habanalabs patch, that has the same thing. Well almost, it only uses set_page_dirty, not the _lock variant. But I have no idea whether that matters or not? -Daniel
if (!g2d_userptr->out_of_list) list_del_init(&g2d_userptr->list);@@ -474,35 +471,34 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d, offset = userptr & ~PAGE_MASK; end = PAGE_ALIGN(userptr + size); npages = (end - start) >> PAGE_SHIFT;
g2d_userptr->vec = frame_vector_create(npages);if (!g2d_userptr->vec) {
g2d_userptr->pages = kvmalloc_array(npages, sizeof(*g2d_userptr->pages),GFP_KERNEL);if (!g2d_userptr->pages) { ret = -ENOMEM; goto err_free; }
ret = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,g2d_userptr->vec);
ret = pin_user_pages_fast(start, npages, FOLL_FORCE | FOLL_WRITE,g2d_userptr->pages); if (ret != npages) { DRM_DEV_ERROR(g2d->dev, "failed to get user pages from userptr.\n"); if (ret < 0)
goto err_destroy_framevec;ret = -EFAULT;goto err_put_framevec;}if (frame_vector_to_pages(g2d_userptr->vec) < 0) {
goto err_destroy_pages;npages = ret; ret = -EFAULT;
goto err_put_framevec;
goto err_unpin_pages; }g2d_userptr->npages = npages; sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); if (!sgt) { ret = -ENOMEM;
goto err_put_framevec;
goto err_unpin_pages; } ret = sg_alloc_table_from_pages(sgt,
frame_vector_pages(g2d_userptr->vec),
g2d_userptr->pages, npages, offset, size, GFP_KERNEL); if (ret < 0) { DRM_DEV_ERROR(g2d->dev, "failed to get sgt from pages.\n");@@ -538,11 +534,11 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d, err_free_sgt: kfree(sgt);
-err_put_framevec:
put_vaddr_frames(g2d_userptr->vec);+err_unpin_pages:
unpin_user_pages(g2d_userptr->pages, npages);-err_destroy_framevec:
frame_vector_destroy(g2d_userptr->vec);+err_destroy_pages:
kvfree(g2d_userptr->pages);err_free: kfree(g2d_userptr);
The rest all looks good, you've avoided the usual API pitfalls. :)
thanks,
John Hubbard NVIDIA