The one in-tree videobuf2-dma-sg driver (mmp-camera) has no need for a kernel-space mapping of the buffers; one suspects that most other drivers would not either. The videobuf2-dma-sg module does the right thing if buf->vaddr == NULL - it maps the buffer on demand if somebody needs it. So let's not map the buffer at allocation time; that will save a little CPU time and a lot of address space in the vmalloc range. Signed-off-by: Jonathan Corbet <corbet@xxxxxxx> --- drivers/media/video/videobuf2-dma-sg.c | 6 ------ 1 files changed, 0 insertions(+), 6 deletions(-) diff --git a/drivers/media/video/videobuf2-dma-sg.c b/drivers/media/video/videobuf2-dma-sg.c index b2d9485..0e8edc1 100644 --- a/drivers/media/video/videobuf2-dma-sg.c +++ b/drivers/media/video/videobuf2-dma-sg.c @@ -77,12 +77,6 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size) printk(KERN_DEBUG "%s: Allocated buffer of %d pages\n", __func__, buf->sg_desc.num_pages); - - if (!buf->vaddr) - buf->vaddr = vm_map_ram(buf->pages, - buf->sg_desc.num_pages, - -1, - PAGE_KERNEL); return buf; fail_pages_alloc: -- 1.7.6 -- To unsubscribe from this list: send the line "unsubscribe linux-media" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
