| Message ID | 20110714151044.44cb89ee@bike.lwn.net (mailing list archive) |
|---|---|
| State | Accepted |
| Headers | show |
Hello, On Thursday, July 14, 2011 11:11 PM Jonathan Corbet wrote: > 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@lwn.net> Acked-by: Marek Szyprowski <m.szyprowski@samsung.com> > --- > 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 Best regards
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:
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@lwn.net> --- drivers/media/video/videobuf2-dma-sg.c | 6 ------ 1 files changed, 0 insertions(+), 6 deletions(-)