diff options
| author | Jonathan Corbet <corbet@lwn.net> | 2011-07-14 18:10:44 -0300 |
|---|---|---|
| committer | Mauro Carvalho Chehab <mchehab@redhat.com> | 2011-09-03 10:57:33 -0300 |
| commit | 297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7 (patch) | |
| tree | f9319522a8ffaa66312ebfbee37e35c54639eb5c /drivers | |
| parent | 77b1e2fbbdfa0ee5cdf6c928b711493a3738468e (diff) | |
| download | linux-stable-297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7.tar.gz linux-stable-297875b6a1f3910c883e4b00bb9bc3e6c3aa6ab7.tar.bz2 linux-stable-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>
Diffstat (limited to 'drivers')
| -rw-r--r-- | 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 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: |