summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJonathan Corbet <corbet@lwn.net>2011-07-14 18:10:44 -0300
committerMauro Carvalho Chehab <mchehab@redhat.com>2011-09-03 10:57:33 -0300
commit297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7 (patch)
treef9319522a8ffaa66312ebfbee37e35c54639eb5c
parent77b1e2fbbdfa0ee5cdf6c928b711493a3738468e (diff)
downloadtalos-obmc-linux-297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7.tar.gz
talos-obmc-linux-297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7.zip
[media] videobuf2: Do not unconditionally map S/G buffers into kernel space
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> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
-rw-r--r--drivers/media/video/videobuf2-dma-sg.c6
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 065f468faf8f..3bad8b105fea 100644
--- a/drivers/media/video/videobuf2-dma-sg.c
+++ b/drivers/media/video/videobuf2-dma-sg.c
@@ -75,12 +75,6 @@ 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:
OpenPOWER on IntegriCloud