| d4e8b7193d87d80f3364d7924692988c974780aa |
|
18-Apr-2012 |
Daniel Vetter <daniel.vetter@ffwll.ch> |
dma-buf: mmap support
Compared to Rob Clark's RFC I've ditched the prepare/finish hooks
and corresponding ioctls on the dma_buf file. The major reason for
that is that many people seem to be under the impression that this is
also for synchronization with outstanding asynchronous processsing.
I'm pretty massively opposed to this because:
- It boils down reinventing a new rather general-purpose userspace
synchronization interface. If we look at things like futexes, this
is hard to get right.
- Furthermore a lot of kernel code has to interact with this
synchronization primitive. This smells a look like the dri1 hw_lock,
a horror show I prefer not to reinvent.
- Even more fun is that multiple different subsystems would interact
here, so we have plenty of opportunities to create funny deadlock
scenarios.
I think synchronization is a wholesale different problem from data
sharing and should be tackled as an orthogonal problem.
Now we could demand that prepare/finish may only ensure cache
coherency (as Rob intended), but that runs up into the next problem:
We not only need mmap support to facilitate sw-only processing nodes
in a pipeline (without jumping through hoops by importing the dma_buf
into some sw-access only importer), which allows for a nicer
ION->dma-buf upgrade path for existing Android userspace. We also need
mmap support for existing importing subsystems to support existing
userspace libraries. And a loot of these subsystems are expected to
export coherent userspace mappings.
So prepare/finish can only ever be optional and the exporter /needs/
to support coherent mappings. Given that mmap access is always
somewhat fallback-y in nature I've decided to drop this optimization,
instead of just making it optional. If we demonstrate a clear need for
this, supported by benchmark results, we can always add it in again
later as an optional extension.
Other differences compared to Rob's RFC is the above mentioned support
for mapping a dma-buf through facilities provided by the importer.
Which results in mmap support no longer being optional.
Note that this dma-buf mmap patch does _not_ support every possible
insanity an existing subsystem could pull of with mmap: Because it
does not allow to intercept pagefaults and shoot down ptes importing
subsystems can't add some magic of their own at these points (e.g. to
automatically synchronize with outstanding rendering or set up some
special resources). I've done a cursory read through a few mmap
implementions of various subsytems and I'm hopeful that we can avoid
this (and the complexity it'd bring with it).
Additonally I've extended the documentation a bit to explain the hows
and whys of this mmap extension.
In case we ever want to add support for explicitly cache maneged
userspace mmap with a prepare/finish ioctl pair, we could specify that
userspace needs to mmap a different part of the dma_buf, e.g. the
range starting at dma_buf->size up to dma_buf->size*2. This works
because the size of a dma_buf is invariant over it's lifetime. The
exporter would obviously need to fall back to coherent mappings for
both ranges if a legacy clients maps the coherent range and the
architecture cannot suppor conflicting caching policies. Also, this
would obviously be optional and userspace needs to be able to fall
back to coherent mappings.
v2:
- Spelling fixes from Rob Clark.
- Compile fix for !DMA_BUF from Rob Clark.
- Extend commit message to explain how explicitly cache managed mmap
support could be added later.
- Extend the documentation with implementations notes for exporters
that need to manually fake coherency.
Change-Id: Ia8f2ae5d8a1b1c87ed12ca1c89d7bf2067239ee4
Cc: Rob Clark <rob.clark@linaro.org>
Cc: Rebecca Schultz Zavin <rebecca@android.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
/include/linux/dma-buf.h
|
| ed0bb8ea059764c3fc882fb135473afd347335e9 |
|
29-Mar-2012 |
Linus Torvalds <torvalds@linux-foundation.org> |
Merge branch 'for-linus-3.4' of git://git.linaro.org/people/sumitsemwal/linux-dma-buf
Pull dma-buf updates from Sumit Semwal:
"This includes the following key items:
- kernel cpu access support,
- flag-passing to dma_buf_fd,
- relevant Documentation updates, and
- some minor cleanups and fixes.
These changes are needed for the drm prime/dma-buf interface code that
Dave Airlie plans to submit in this merge window."
* 'for-linus-3.4' of git://git.linaro.org/people/sumitsemwal/linux-dma-buf:
dma-buf: correct dummy function declarations.
dma-buf: document fd flags and O_CLOEXEC requirement
dma_buf: Add documentation for the new cpu access support
dma-buf: add support for kernel cpu access
dma-buf: don't hold the mutex around map/unmap calls
dma-buf: add get_dma_buf()
dma-buf: pass flags into dma_buf_fd.
dma-buf: add dma_data_direction to unmap dma_buf_op
dma-buf: Move code out of mutex-protected section in dma_buf_attach()
dma-buf: Return error instead of using a goto statement when possible
dma-buf: Remove unneeded sanity checks
dma-buf: Constify ops argument to dma_buf_export()
|
| 3e0b2a1993c06e646d90d71e163d03869a211a4c |
|
26-Mar-2012 |
Sumit Semwal <sumit.semwal@ti.com> |
dma-buf: correct dummy function declarations.
Dummy functions for the newly added cpu access ops need variable names for
arguments.
Also, the introduction of flags in dma_buf_fd needs to be added to dummy
functions as well.
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| fc13020e086bfedf2afb95c91c026d5af1f80107 |
|
20-Mar-2012 |
Daniel Vetter <daniel.vetter@ffwll.ch> |
dma-buf: add support for kernel cpu access
Big differences to other contenders in the field (like ion) is
that this also supports highmem, so we have to split up the cpu
access from the kernel side into a prepare and a kmap step.
Prepare is allowed to fail and should do everything required so that
the kmap calls can succeed (like swapin/backing storage allocation,
flushing, ...).
More in-depth explanations will follow in the follow-up documentation
patch.
Changes in v2:
- Clear up begin_cpu_access confusion noticed by Sumit Semwal.
- Don't automatically fallback from the _atomic variants to the
non-atomic variants. The _atomic callbacks are not allowed to
sleep, so we want exporters to make this decision explicit. The
function signatures are explicit, so simpler exporters can still
use the same function for both.
- Make the unmap functions optional. Simpler exporters with permanent
mappings don't need to do anything at unmap time.
Changes in v3:
- Adjust the WARN_ON checks for the new ->ops functions as suggested
by Rob Clark and Sumit Semwal.
- Rebased on top of latest dma-buf-next git.
Changes in v4:
- Fixup a missing - in a return -EINVAL; statement.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rob Clark <rob@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| 6b607e3a658fee490bdabfdeb739a3eb498b1bff |
|
19-Mar-2012 |
Daniel Vetter <daniel.vetter@ffwll.ch> |
dma-buf: don't hold the mutex around map/unmap calls
The mutex protects the attachment list and hence needs to be held
around the callbakc to the exporters (optional) attach/detach
functions.
Holding the mutex around the map/unmap calls doesn't protect any
dma_buf state. Exporters need to properly protect any of their own
state anyway (to protect against calls from their own interfaces).
So this only makes the locking messier (and lockdep easier to anger).
Therefore let's just drop this.
v2: Rebased on top of latest dma-buf-next git.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Rob Clark <rob.clark@linaro.org>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| f9a24d1ac9cb82baf5ec5efdb6580a9ce0bd5bfc |
|
16-Mar-2012 |
Rob Clark <rob@ti.com> |
dma-buf: add get_dma_buf()
Works in a similar way to get_file(), and is needed in cases such as
when the exporter needs to also keep a reference to the dmabuf (that
is later released with a dma_buf_put()), and possibly other similar
cases.
Signed-off-by: Rob Clark <rob@ti.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| 55c1c4ca23d0f2736ef7c219d0fb005323ff8ee0 |
|
16-Mar-2012 |
Dave Airlie <airlied@redhat.com> |
dma-buf: pass flags into dma_buf_fd.
We need to pass the flags into dma_buf_fd at this point,
so the flags end up doing the right thing for O_CLOEXEC.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Rob Clark <rob@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| 33ea2dcb39ba50b0b69d1b1dc24702f084b46411 |
|
27-Jan-2012 |
Sumit Semwal <sumit.semwal@ti.com> |
dma-buf: add dma_data_direction to unmap dma_buf_op
Some exporters may use DMA map/unmap APIs in dma-buf ops, which require
enum dma_data_direction for both map and unmap operations.
Thus, the unmap dma_buf_op also needs to have enum dma_data_direction as
a parameter.
Reported-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| 5375764f9408b8ef1fb8d6cd1ed0efd97dce4824 |
|
26-Jan-2012 |
Laurent Pinchart <laurent.pinchart@ideasonboard.com> |
dma-buf: Constify ops argument to dma_buf_export()
This allows drivers to make the dma buf operations structure constant.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
/include/linux/dma-buf.h
|
| 313162d0b83836e2f57e51b9b8650fb4b9c396ea |
|
30-Jan-2012 |
Paul Gortmaker <paul.gortmaker@windriver.com> |
device.h: audit and cleanup users in main include dir
The <linux/device.h> header includes a lot of stuff, and
it in turn gets a lot of use just for the basic "struct device"
which appears so often.
Clean up the users as follows:
1) For those headers only needing "struct device" as a pointer
in fcn args, replace the include with exactly that.
2) For headers not really using anything from device.h, simply
delete the include altogether.
3) For headers relying on getting device.h implicitly before
being included themselves, now explicitly include device.h
4) For files in which doing #1 or #2 uncovers an implicit
dependency on some other header, fix by explicitly adding
the required header(s).
Any C files that were implicitly relying on device.h to be
present have already been dealt with in advance.
Total removals from #1 and #2: 51. Total additions coming
from #3: 9. Total other implicit dependencies from #4: 7.
As of 3.3-rc1, there were 110, so a net removal of 42 gives
about a 38% reduction in device.h presence in include/*
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
/include/linux/dma-buf.h
|
| d15bd7ee445d0702ad801fdaece348fdb79e6581 |
|
26-Dec-2011 |
Sumit Semwal <sumit.semwal@ti.com> |
dma-buf: Introduce dma buffer sharing mechanism
This is the first step in defining a dma buffer sharing mechanism.
A new buffer object dma_buf is added, with operations and API to allow easy
sharing of this buffer object across devices.
The framework allows:
- creation of a buffer object, its association with a file pointer, and
associated allocator-defined operations on that buffer. This operation is
called the 'export' operation.
- different devices to 'attach' themselves to this exported buffer object, to
facilitate backing storage negotiation, using dma_buf_attach() API.
- the exported buffer object to be shared with the other entity by asking for
its 'file-descriptor (fd)', and sharing the fd across.
- a received fd to get the buffer object back, where it can be accessed using
the associated exporter-defined operations.
- the exporter and user to share the scatterlist associated with this buffer
object using map_dma_buf and unmap_dma_buf operations.
Atleast one 'attach()' call is required to be made prior to calling the
map_dma_buf() operation.
Couple of building blocks in map_dma_buf() are added to ease introduction
of sync'ing across exporter and users, and late allocation by the exporter.
For this first version, this framework will work with certain conditions:
- *ONLY* exporter will be allowed to mmap to userspace (outside of this
framework - mmap is not a buffer object operation),
- currently, *ONLY* users that do not need CPU access to the buffer are
allowed.
More details are there in the documentation patch.
This is based on design suggestions from many people at the mini-summits[1],
most notably from Arnd Bergmann <arnd@arndb.de>, Rob Clark <rob@ti.com> and
Daniel Vetter <daniel@ffwll.ch>.
The implementation is inspired from proof-of-concept patch-set from
Tomasz Stanislawski <t.stanislaws@samsung.com>, who demonstrated buffer sharing
between two v4l2 devices. [2]
[1]: https://wiki.linaro.org/OfficeofCTO/MemoryManagement
[2]: http://lwn.net/Articles/454389
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-and-Tested-by: Rob Clark <rob.clark@linaro.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
/include/linux/dma-buf.h
|