Commit 297875b6 authored by Jonathan Corbet's avatar Jonathan Corbet Committed by Mauro Carvalho Chehab

[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: default avatarJonathan Corbet <corbet@lwn.net>
Acked-by: default avatarMarek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: default avatarMauro Carvalho Chehab <mchehab@redhat.com>
parent 77b1e2fb
...@@ -75,12 +75,6 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size) ...@@ -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", printk(KERN_DEBUG "%s: Allocated buffer of %d pages\n",
__func__, buf->sg_desc.num_pages); __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; return buf;
fail_pages_alloc: fail_pages_alloc:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment