dma_buf_map_attachment and dma_buf_vmap can return NULL or
ERR_PTR on a error. This encourages a common buggy pattern in
callers:
sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
if (IS_ERR_OR_NULL(sgt))
return PTR_ERR(sgt);
This causes the caller to return 0 on an error. IS_ERR_OR_NULL
is almost always a sign of poorly-defined error handling.
This patch converts dma_buf_map_attachment to always return
ERR_PTR, and fixes the callers that incorrectly handled NULL.
There are a few more callers that were not checking for NULL
at all, which would have dereferenced a NULL pointer later.
There are also a few more callers that correctly handled NULL
and ERR_PTR differently, I left those alone but they could also
be modified to delete the NULL check.
This patch also converts dma_buf_vmap to always return NULL.
All the callers to dma_buf_vmap only check for NULL, and would
have dereferenced an ERR_PTR and panic'd if one was ever
returned. This is not consistent with the rest of the dma buf
APIs, but matches the expectations of all of the callers.
Signed-off-by: Colin Cross <ccross@android.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently it is not possible for userspace to map a DMABUF exported buffer
with write permissions. This patch allows to also pass O_RDONLY/O_RDWR when
exporting the buffer, so that userspace may map it with write permissions.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Earlier version of dma-contig allocator in user ptr mode assumed that in
all cases DMA address equals physical address. This was just a special case.
Commit e15dab752d introduced correct support
for converting userpage to dma address, but unfortunately it broke the
support for simple dma address = physical address for the case, when given
physical frame has no struct page associated with it (this happens if one
use for example dma_declare_coherent api or other reserved memory approach).
This commit restores support for such cases.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
[s.nawrocki@samsung.com: replaced #elsif with #elif]
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Memory maps typically require that the buffer size to be page
aligned. Currently, two memops drivers do such alignment
internally, but videobuf-vmalloc doesn't.
Also, the buffer overflow check doesn't take it into account.
So, instead of doing it at each memops driver, enforce it at
VB2 core.
Reported-by: Prabhakar lad <prabhakar.csengg@gmail.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Some drivers have special memory requirements for their buffers, usually
related to DMA (e.g. GFP_DMA or __GFP_DMA32). Make it possible to specify
additional GFP flags for those buffers by adding a gfp_flags field to
vb2_queue.
Note that this field will be replaced in the future with a different
mechanism, but that is still work in progress and we need this feature
now so we won't be able to convert drivers with such requirements to vb2.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Federico Vaga <federico.vaga@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
The right solution is to remove the architecture dependency on
dma_common_get_sgtable(). Revert this patch to apply the right one.
This reverts commit 93049b9368.
As reported by Stephen:
> After merging the v4l-dvb tree, today's linux-next build (x86_64
> allmodconfig) failed like this:
>
> ERROR: "dma_common_get_sgtable" [drivers/media/v4l2-core/videobuf2-dma-contig.ko] undefined!
>
> Caused by commit 9ef2cbeb81 ("[media] v4l: vb2-dma-contig: add support
> for DMABUF exporting"). dma_common_get_sgtable() is called from the
> inline dma_get_sgtable_attrs() and dma_get_sgtable_attrs() is "called
> from" dma_get_sgtable(). dma_common_get_sgtable() is only defined if
> ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY is set which depends on
> CONFIG_HAVE_GENERIC_DMA_COHERENT being set which it isn't for this build.
The simplest fix is to just not support DMABUF with vb2-contig, on archs
where this symbol doesn't exist. Some latter patch can rewrite it to
support this outside -arm.
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Most operations on DMA and DMABUF framework require the size of a buffer to be
page aligned. This patch guarantees the requirement is satisfied for all
vb2-dma-contig buffers.
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
The DMA transfer must be aligned to a specific value. If userptr is not aligned
to DMA requirements then unexpected corruptions of the memory may occur before
or after a buffer. To prevent such situations, all unligned userptr buffers
are rejected at VIDIOC_QBUF.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch adds taking reference to the device for MMAP buffers.
Such buffers, may be exported using DMABUF mechanism. If the driver that
created a queue is unloaded then the queue is released, the device might be
released too. However, buffers cannot be released if they are referenced by
DMABUF descriptor(s). The device pointer kept in a buffer must be valid for the
whole buffer's lifetime. Therefore MMAP buffers should take a reference to the
device to avoid risk of dangling pointers.
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch adds support for exporting a dma-contig buffer using
DMABUF interface.
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Let mmap method to use dma_mmap_coherent call. Moreover, this patch removes
vb2_mmap_pfn_range from videobuf2 helpers as it was suggested by Laurent
Pinchart. The function is no longer used in vb2 code.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch makes changes for adding dma-contig as a dma_buf user. It provides
function implementations for the {attach, detach, map, unmap}_dmabuf()
mem_ops of DMABUF memory type.
[author of the original patch]
[integration with refactored dma-contig allocator]
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch introduces usage of dma_map_sg to map memory behind
a userspace pointer to a device as dma-contiguous mapping.
This patch contains some of the code kindly provided by Marek Szyprowski
<m.szyprowski@samsung.com> and Kamil Debski <k.debski@samsung.com> and Andrzej
Pietrasiewicz <andrzej.p@samsung.com>. Kind thanks for bug reports from Laurent
Pinchart <laurent.pinchart@ideasonboard.com> and Seung-Woo Kim
<sw0312.kim@samsung.com>.
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch removes a reference to alloc_ctx from an instance of a DMA
contiguous buffer. It helps to avoid a risk of a dangling pointer if the
context is released while the buffer is still valid. Moreover it removes one
dereference step while accessing a device structure.
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Currently, the v4l2 core is mixed together with other non-core drivers.
Move them into a separate directory.
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Colin Cross