Signed-off-by: NRob Clark <robdclark@gmail.com>

This was only used for atomic commit these days.  So instead just give
atomic it's own work-queue where we can do a block on each bo in turn.
Simplifies things a whole bunch and makes the 'struct fence' conversion
easier.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Better encapsulate the per-timeline stuff into fence-context.  For now
there is just a single fence-context, but eventually we'll also have one
per-CRTC to enable fully explicit fencing.
Signed-off-by: NRob Clark <robdclark@gmail.com>

This was always the intention, but somehow it was never wired up
properly.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Signed-off-by: NRob Clark <robdclark@gmail.com>

Convert the raw unsigned long 'pfn' argument to pfn_t for the purpose of
evaluating the PFN_MAP and PFN_DEV flags.  When both are set it triggers
_PAGE_DEVMAP to be set in the resulting pte.

There are no functional changes to the gpu drivers as a result of this
conversion.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: David Airlie <airlied@linux.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The atomic commit cannot easily undo and return an error once the
state is swapped. Change to uninterruptible wait, and ignore the
timeout error.
Signed-off-by: NWentao Xu <wentaox@codeaurora.org>
Signed-off-by: NRob Clark <robdclark@gmail.com>

The atomic commit cannot easily undo and return an error once the
state is swapped. Change to uninterruptible wait, and ignore the
timeout error.
Signed-off-by: NWentao Xu <wentaox@codeaurora.org>
Signed-off-by: NRob Clark <robdclark@gmail.com>

The 'timeout' value comes from userspace (CLOCK_MONOTONIC), but
converting this directly to jiffies doesn't take into account the
initial jiffies count at boot, which may differ from the base time
of CLOCK_MONOTONIC.

TODO: add ktime_delta_jiffies() when rebasing on 4.1 and use that
instead of ktime_sub/ktime_to_timespec/timespec_to_jiffies combo (as
suggested by Arnd)

v2: switch over from 'struct timespec' to ktime_t throughout, since
'struct timespec' will be deprecated (as suggested by Arnd)
v3: minor cosmetic tweaks

Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: NRob Clark <robdclark@gmail.com>

If the GEM object is imported, drm_prime_gem_destroy needs to be
called to clean up dma buffer related information.
Signed-off-by: NJilai Wang <jilaiw@codeaurora.org>
Signed-off-by: NRob Clark <robdclark@gmail.com>

Avoid casts from pointers to fixed-size integers to prevent the compiler
from warning. Print virtual memory addresses using %p instead. Also turn
a couple of %d/%x specifiers into %zu/%zd/%zx to avoid further warnings
due to mismatched format strings.
Signed-off-by: NThierry Reding <treding@nvidia.com>
Reviewed-by: NRob Clark <robdclark@gmail.com>

Add support to use the VRAM carveout (if specified in dtb) for fbdev
scanout buffer.  This allows drm/msm to take over a bootloader splash-
screen, and avoids corruption on screen that results if the kernel uses
memory that is still being scanned out for itself.
Signed-off-by: NRob Clark <robdclark@gmail.com>

The functions framebuffer_release() and vunmap() perform also input
parameter validation. Thus the test around the call is not needed.

This issue was detected by using the Coccinelle software.
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Reviewed-by: NThierry Reding <treding@nvidia.com>
Signed-off-by: NRob Clark <robdclark@gmail.com>

Use pre-computed iova when unmapping, to reduce the places we assume iova
and mmap offset are (at the moment) the same.  And get rid of an extra
drm_gem_free_mmap_offset() call (since it is already called from
drm_gem_object_release())
Signed-off-by: NRob Clark <robdclark@gmail.com>

Atomic wants to split the prepare/pin from where we actually program the
scanout address (so that any part that can fail is done synchronously).
Add some fb/gem apis to make this easier to use from the kms parts.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Give ourselves a way to wait for certain fence #..  makes it easier to
wait on a set of bo's, which we'll need for atomic.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Signed-off-by: NRob Clark <robdclark@gmail.com>

drm_gem_get_pages() currently allows passing a 'gfp' parameter that is
passed to shmem combined with mapping_gfp_mask(). Given that the default
mapping_gfp_mask() is GFP_HIGHUSER, it is _very_ unlikely that anyone will
ever make use of that parameter. In fact, all drivers currently pass
redundant flags or 0.

This patch removes the 'gfp' parameter. The only reason to keep it is to
remove flags like __GFP_WAIT. But in its current form, it can only be used
to add flags. So to remove __GFP_WAIT, you'd have to drop it from the
mapping_gfp_mask, which again is stupid as this mask is used by shmem-core
for other allocations, too.

If any driver ever requires that parameter, we can introduce a new helper
that takes the raw 'gfp' parameter. The caller'd be responsible to combine
it with mapping_gfp_mask() in a suitable way. The current
drm_gem_get_pages() helper would then simply use mapping_gfp_mask() and
call the new helper. This is what shmem_read_mapping_pages{_gfp,} does
right now.

Moreover, the gfp-zone flag-usage is not obvious: If you pass a modified
zone, shmem core will WARN() or even BUG(). In other words, the following
must be true for 'gfp' passed to shmem_read_mapping_pages_gfp():
    gfp_zone(mapping_gfp_mask(mapping)) == gfp_zone(gfp)
Add a comment to drm_gem_read_pages() explaining that constraint.
Signed-off-by: NDavid Herrmann <dh.herrmann@gmail.com>

If probe fails after IOMMU is attached, we need to detach in order to
clean up properly.  Before this change, IOMMU faults would occur if the
probe failed (-EPROBE_DEFER).
Signed-off-by: NStephane Viau <sviau@codeaurora.org>
Signed-off-by: NRob Clark <robdclark@gmail.com>

Signed-off-by: NMicah Richert <richert@braincorporation.com>
Signed-off-by: NRob Clark <robdclark@gmail.com>

We already hold struct_mutex here.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Add a VRAM carveout that is used for systems which do not have an IOMMU.

The VRAM carveout uses CMA.  The arch code must setup a CMA pool for the
device (preferrably in highmem.. a 256m-512m VRAM pool in lowmem is not
cool).  The user can configure the VRAM pool size using msm.vram module
param.

Technically, the abstraction of IOMMU behind msm_mmu is not strictly
needed, but it simplifies the GEM code a bit, and will be useful later
when I add support for a2xx devices with GPUMMU, so I decided to keep
this part.

It appears to be possible to configure the GPU to restrict access to
addresses within the VRAM pool, but this is not done yet.  So for now
the GPU will refuse to load if there is no sort of mmu.  Once address
based limits are supported and tested to confirm that we aren't giving
the GPU access to arbitrary memory, this restriction can be lifted
Signed-off-by: NRob Clark <robdclark@gmail.com>

Subsequent threads returning EBUSY from vm_insert_pfn() was not
handled correctly. As a result concurrent access from new threads
to mmapped data caused SIGBUS.

See e79e0fe3Signed-off-by: NRob Clark <robdclark@gmail.com>
Acked-by: NDavid Brown <davidb@codeaurora.org>

Re-arrange things a bit so that we can get work requested after a bo
fence passes, like pageflip, done before retiring bo's.  Without any
sort of bo cache in userspace, some games can trigger hundred's of
transient bo's, which can cause retire to take a long time (5-10ms).
Obviously we want a bo cache.. but this cleanup will make things a
bit easier for atomic as well and makes things a bit cleaner.
Signed-off-by: NRob Clark <robdclark@gmail.com>
Acked-by: NDavid Brown <davidb@codeaurora.org>

Signed-off-by: NRob Clark <robdclark@gmail.com>
Acked-by: NDavid Brown <davidb@codeaurora.org>

Signed-off-by: NRob Clark <robdclark@gmail.com>

This was inherited from i915/udl, and not actually needed.
Signed-off-by: NRob Clark <robdclark@gmail.com>

When we CPU_PREP a bo with NOSYNC flag (for example, to implement
PIPE_TRANSFER_DISCARD_WHOLE_RESOURCE), an -EBUSY return indicates to
userspace that the bo is still busy.  Previously it was incorrectly
returning 0 in this case.

And while we're in there throw in an bit of extra sanity checking in
case userspace tries to wait for a bogus fence.
Signed-off-by: NRob Clark <robdclark@gmail.com>

In case of error, the function drm_prime_pages_to_sg() returns ERR_PTR()
and never returns NULL. The NULL test in the return value check should
be replaced with IS_ERR().
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>

The userspace API already had everything needed to handle read vs write
synchronization.  This patch actually bothers to hook it up properly, so
that we don't need to (for example) stall on userspace read access to a
buffer that gpu is also still reading.
Signed-off-by: NRob Clark <robdclark@gmail.com>

Add initial support for a3xx 3d core.

So far, with hardware that I've seen to date, we can have:
 + zero, one, or two z180 2d cores
 + a3xx or a2xx 3d core, which share a common CP (the firmware
   for the CP seems to implement some different PM4 packet types
   but the basics of cmdstream submission are the same)

Which means that the eventual complete "class" hierarchy, once
support for all past and present hw is in place, becomes:
 + msm_gpu
   + adreno_gpu
     + a3xx_gpu
     + a2xx_gpu
   + z180_gpu

This commit splits out the parts that will eventually be common
between a2xx/a3xx into adreno_gpu, and the parts that are even
common to z180 into msm_gpu.

Note that there is no cmdstream validation required.  All memory access
from the GPU is via IOMMU/MMU.  So as long as you don't map silly things
to the GPU, there isn't much damage that the GPU can do.
Signed-off-by: NRob Clark <robdclark@gmail.com>

The snapdragon chips have multiple different display controllers,
depending on which chip variant/version.  (As far as I can tell, current
devices have either MDP3 or MDP4, and upcoming devices have MDSS.)  And
then external to the display controller are HDMI, DSI, etc. blocks which
may be shared across devices which have different display controller
blocks.

To more easily add support for different display controller blocks, the
display controller specific bits are split out into a "kms" module,
which provides the kms plane/crtc/encoder objects.

The external HDMI, DSI, etc. blocks are part encoder, and part connector
currently.  But I think I will pull in the drm_bridge patches from
chromeos tree, and split them into a bridge+connector, with the
registers that need to be set in modeset handled by the bridge.  This
would remove the 'msm_connector' base class.  But some things need to be
double checked to make sure I could get the correct ON/OFF sequencing..

This patch adds support for mdp4 crtc (including hw cursor), dtv encoder
(part of MDP4 block), and hdmi.
Signed-off-by: NRob Clark <robdclark@gmail.com>