A user can run batchbuffer via VEBOX ring.
Signed-off-by: NXiang, Haihao <haihao.xiang@intel.com>
Reviewed-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Using copywinwin10 as an example that is dependent upon emitting a lot
of relocations (2 per operation), we see improvements of:

c2d/gm45: 618000.0/sec to 623000.0/sec.
i3-330m: 748000.0/sec to 789000.0/sec.

(measured relative to a baseline with neither optimisations applied).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NImre Deak <imre.deak@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Userspace is able to hint to the kernel that its command stream and
auxiliary state buffers already hold the correct presumed addresses and
so the relocation process may be skipped if the kernel does not need to
move any buffers in preparation for the execbuffer. Thus for the common
case where the allotment of buffers is static between batches, we can
avoid the overhead of individually checking the relocation entries.

Note that this requires userspace to supply the domain tracking and
requests for workarounds itself that would otherwise be computed based
upon the relocation entries.

Using copywinwin10 as an example that is dependent upon emitting a lot
of relocations (2 per operation), we see improvements of:

c2d/gm45: 618000.0/sec to 632000.0/sec.
i3-330m: 748000.0/sec to 830000.0/sec.

(measured relative to a baseline with neither optimisations applied).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NImre Deak <imre.deak@intel.com>
[danvet: Fixup merge conflict in userspace header due to different
baseline trees.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Now that Chris Wilson demonstrated that the key for stability on early
gen 2 is to simple _never_ exchange the physical backing storage of
batch buffers I've tried a stab at a kernel solution. Doesn't look too
nefarious imho, now that I don't try to be too clever for my own good
any more.

v2: After discussing the various techniques, we've decided to always blit
batches on the suspect devices, but allow userspace to opt out of the
kernel workaround assume full responsibility for providing coherent
batches. The principal reason is that avoiding the blit does improve
performance in a few key microbenchmarks and also in cairo-trace
replays.
Signed-Off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
[danvet:
- Drop the hunk which uses HAS_BROKEN_CS_TLB to implement the ring
  wrap w/a. Suggested by Chris Wilson.
- Also add the ACTHD check from Chris Wilson for the error state
  dumping, so that we still catch batches when userspace opts out of
  the w/a.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NMichael Kerrisk <mtk.manpages@gmail.com>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: NDave Jones <davej@redhat.com>

Convert #include "..." to #include <path/...> in kernel system headers.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: NDave Jones <davej@redhat.com>

Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

There are internal patches for a feature which require a parameter to
query whether support exists . These patches cannot be made external
yet. In order to keep existing tests and userspace happy and free from
conflicts, reserve a number for it.
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

In order for udl vmap to work properly, we need to push the object
into the CPU domain before we start copying the data to the USB device.

This along with the udl change avoids userspace explicit mapping to
be used.

v2: add a flag for userspace to query to know if Intel kernel driver can
deal with the vmap flushing properly. In theory udl would need a flag also,
but I intend to push the patches very close to each other and other drivers
should do the right thing from the start.

I've added a test to my intel-gpu-tools prime branch, however testing
this is a bit messy since the only way to get udl to vmap is to rendering
something. I've tested this with real code as well to make sure it works.
Signed-off-by: NDave Airlie <airlied@redhat.com>
[danvet: resolved conflict, which required reallocating the PARAM
number to 21.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Userspace tries to estimate the cost of ring switching based on whether
the GPU and GEM supports semaphores. (If we have multiple rings and no
semaphores, userspace assumes that the cost of switching rings between
batches is exorbitant and will endeavour to keep the next batch on the
active ring - as a coarse approximation to tracking both destination and
source surfaces.) Currently userspace has to guess whether semaphores
exist based on the chipset generation and the module parameter,
i915.semaphores. This is a crude and inaccurate guess as the defaults
internally depend upon other chipset features being enabled or disabled,
nor does it extend well into the future. By exporting a HAS_SEMAPHORES
parameter, we can easily query the driver and obtain an accurate answer.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

By selecting the cache level (essentially whether or not the CPU snoops
any updates to the bo, and on more recent machines whether it resides
inside the CPU's last-level-cache) a userspace driver is able to then
manage all of its memory within buffer objects, if it so desires. This
enables the userspace driver to accelerate uploads and more importantly
downloads from the GPU and to able to mix CPU and GPU rendering/activity
efficiently.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
[danvet: Added code comment about where we plan to stuff platform
specific cacheing control bits in the ioctl struct.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

The intention is to help select which engine to use for copies with
interoperating clients - such as a GL client making a request to the X
server to perform a SwapBuffers, which may require copying from the
active GL back buffer to the X front buffer.

We choose to report a mask of the active rings to future proof the
interface against any changes which may allow for the object to reside
upon multiple rings.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
[danvet: bikeshed away the write ring mask and add the explanation
Chris sent in a follow-up mail why we decided to use masks.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

The interface's immediate purpose is to do synchronous timestamp queries
as required by GL_TIMESTAMP. The GPU has a register for reading the
timestamp but because that would normally require root access through
libpciaccess, the IOCTL can provide this service instead.

Currently the implementation whitelists only the render ring timestamp
register, because that is the only thing we need to expose at this time.

v2: make size implicit based on the register offset
Add a generation check
Reviewed-by: NEric Anholt <eric@anholt.net>
Cc: Jacek Lawrynowicz <jacek.lawrynowicz@intel.com>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
[danvet: fixup the ioctl numerb:]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

I'm planing to merge this next week for 3.7, but I'd like to avoid
stupid conflicts with the exsting userspace when merging the new
reg_read ioctl (which doesn't have userspace yet, but this caching
interface has).

Header extracted from Chris Wilson's patch, but fix up the copy&pasted
comment in the interface struct.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Use the rsvd1 field in execbuf2 to specify the context ID associated
with the workload. This will allow the driver to do the proper context
switch when/if needed.

v2: Add checks for context switches on rings not supporting contexts.
Before the code would silently ignore such requests.
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>

Add the interfaces to allow user space to create and destroy contexts.
Contexts are destroyed automatically if the file descriptor for the dri
device is closed.

Following convention as usual here causes checkpatch warnings.

v2: with is_initialized, no longer need to init at create
drop the context switch on create (daniel)

v3: Use interruptible lock (Chris)
return -ENODEV in !GEM case (Chris)
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>

Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Change the ns_timeout parameter of the wait ioctl to a signed value.
Doing this allows the kernel to provide an infinite wait when a timeout
of less than 0 is provided. This mimics select/poll.

Initially the parameter was meant to match up with the GL spec 1:1, but
after being made aware of how much 2^64 - 1 nanoseconds actually is, I
do not think anyone will ever notice the loss of 1 bit.

The infinite timeout on waiting is similar to the existing i915
userspace interface with the exception that struct_mutex is dropped
while doing the wait in this ioctl.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This helps implement GL_ARB_sync but stops short of allowing full blown
sync objects. Finally we can use the new timed seqno waiting function
to allow userspace to wait on a buffer object with a timeout. This
implements that interface.

The IOCTL will take as input a buffer object handle, and a timeout in
nanoseconds (flags is currently optional but will likely be used for
permutations of flush operations). Users may specify 0 nanoseconds to
instantly check.

The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
non-zero timeout parameter the wait ioctl will wait for the given number
of nanoseconds on an object becoming unbusy. Since the wait itself does
so holding struct_mutex the object may become re-busied before this
completes. A similar but shorter race condition exists in the busy
ioctl.

v2: ETIME/ERESTARTSYS instead of changing to EBUSY, and EGAIN (Chris)
Flush the object from the gpu write domain (Chris + Daniel)
Fix leaked refcount in good case (Chris)
Naturally align ioctl struct (Chris)

v3: Drop lock after getting seqno to avoid ugly dance (Chris)

v4: check for 0 timeout after olr check to allow polling (Chris)

v5: Updated the comment. (Chris)

v6: Return -ETIME instead of -EBUSY when timeout_ns is 0 (Daniel)
Fix the commit message comment to be less ugly (Ben)
Add a warning to check the return timespec (Ben)

v7: Use DRM_AUTH for the ioctl. (Eugeni)
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

On Sanybridge a few MI read/write commands only work when ppgtt is
enabled.  Userspace therefore needs to be able to check whether ppgtt
is enabled. For added hilarity, you need to reset the "use global GTT"
bit on snb when ppgtt is enabled, otherwise it won't work.  Despite
what bspec says about automatically using ppgtt ...

Luckily PIPE_CONTROL (the only write cmd current userspace uses) is
not affected by all this, as tested by tests/gem_pipe_control_store_loop.
Reviewed-and-tested-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

LLC is not SNB/IVB-specific, so we should check for it in a more generic
way.
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NEric Anholt <eric@anholt.net>
Reviewed-by: NKenneth Graunke <kenneth@whitecape.org>
Signed-off-by: NEugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

These registers are automatically incremented by the hardware during
transform feedback to track where the next streamed vertex output
should go.  Unlike the previous generation, which had a packet for
setting the corresponding registers to a defined value, gen7 only has
MI_LOAD_REGISTER_IMM to do so.  That's a secure packet (since it loads
an arbitrary register), so we need to do it from the kernel, and it
needs to be settable atomically with the batchbuffer execution so that
two clients doing transform feedback don't stomp on each others'
state.

Instead of building a more complicated interface involcing setting the
registers to a specific value, just set them to 0 when asked and
userland can tweak its pointers accordingly.
Signed-off-by: NEric Anholt <eric@anholt.net>
Reviewed-by: NEugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: NKenneth Graunke <kenneth@whitecape.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Add new ioctls for getting and setting the current destination color
key.  This allows for simple overlay display control by matching a color
key value in the primary plane before blending the overlay on top.

v2: remove unnecessary mutex acquire/release around reg accesses
v3: add support for full color key management
v4: fix copy & paste bug in snb_get_colorkey
    don't bother checking min/max values against docs as the docs are likely
    wrong (how could we handle 10bpc surface formats?)
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Because of a typo, calling ioctl with DRM_IOCTL_I915_OVERLAY_PUT_IMAGE
is broken if the macro is used directly. When using libdrm the bug is
not hit, since libdrm handles the ioctl encoding internally.

The typo also leads to the .cmd and .cmd_drv fields of the drm_ioctl
structure for DRM_I915_OVERLAY_PUT_IMAGE having inconsistent content.
Signed-off-by: NOle Henrik Jahren <olehenja@alumni.ntnu.no>
Acked-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@kernel.org
Signed-off-by: NKeith Packard <keithp@keithp.com>

Userspace has a legitimate requirement to use a delta that points to
outside of the target bo, and so we need to enable this. (As this is an
abi break, albeit a relaxation of the current restrictions, mark the change
with a new flag.)
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

The relative-to-general state default is useless as it means having to
rewrite the streaming kernels for each batch. Relative-to-surface is
more useful, as that stream usually needs to be rewritten for each
batch. And absolute addressing mode, vital if you start streaming
state, is also only available by adjusting the register...
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Otherwise we can't really fix the abi-braindeadness of forcing
libva to manually wait for rendering when switching rings. Which
in turn makes implementing hw semaphores a pointless exercise
(at least for ironlake).

[Also added the relaxed fencing param to explain the jump in
numbering - relaxed fencing is in -next.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

So long as we adhere to the fence registers rules for alignment and no
overlaps (including with unfenced accesses to linear memory) and account
for the tiled access in our size allocation, we do not have to allocate
the full fenced region for the object. This allows us to fight the bloat
tiling imposed on pre-i965 chipsets and frees up RAM for real use. [Inside
the GTT we still suffer the additional alignment constraints, so it doesn't
magic allow us to render larger scenes without stalls -- we need the
expanded GTT and fence pipelining to overcome those...]
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Based on an original patch by Zhenyu Wang, this initializes the BLT ring for
SandyBridge and enables support for user execbuffers.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

With the current screwed but its ABI, ioctls for the drm, Linus pointed out that we could allow userspace to specify the allocation size, but we pass it to the driver which then uses it blindly to store a struct. Now if userspace specifies the allocation size as smaller than the driver needs, the driver can possibly overwrite memory.

This patch restructures the driver ioctls so we store the structure size we are expecting, and make sure we allocate at least that size. The copy from/to userspace are still restricted to the size the user specifies, this allows ioctl structs to grow on both sides of the equation.

Up until now we didn't really use the DRM_IOCTL defines in the kernel, so this cleans them up and adds them for nouveau.

v2:
fix nouveau pushbuf arg (thanks to Ben for pointing it out)
Reported-by: NLinus Torvalds <torvalds@linuxfoundation.org>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Intel Core i3/5 platforms with integrated graphics support both CPU and
GPU turbo mode.  CPU turbo mode is opportunistic: the CPU will use any
available power to increase core frequencies if thermal headroom is
available.  The GPU side is more manual however; the graphics driver
must monitor GPU power and temperature and coordinate with a core
thermal driver to take advantage of available thermal and power headroom
in the package.

The intelligent power sharing (IPS) driver is intended to coordinate
this activity by monitoring MCP (multi-chip package) temperature and
power, allowing the CPU and/or GPU to increase their power consumption,
and thus performance, when possible.  The goal is to maximize
performance within a given platform's TDP (thermal design point).
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NMatthew Garrett <mjg@redhat.com>

This will let userland only try to use the new media decode
functionality when the appropriate kernel is present.
Signed-off-by: NZou Nan hai <nanhai.zou@intel.com>
Signed-off-by: NEric Anholt <eric@anholt.net>

Introduces a more complete intel_ring_buffer structure with callbacks
for setup and management of a particular ringbuffer, and converts the
render ring buffer consumers to use it.
Signed-off-by: NZou Nan hai <nanhai.zou@intel.com>
Signed-off-by: NXiang Hai hao <haihao.xiang@intel.com>
[anholt: Fixed up whitespace fail and rebased against prep patches]
Signed-off-by: NEric Anholt <eric@anholt.net>

This patch adds a new execbuf ioctl, execbuf2, for use by clients that
want to control fence register allocation more finely.  The buffer
passed in to the new ioctl includes a new relocation type to indicate
whether a given object needs a fence register assigned for the command
buffer in question.

Compatibility with the existing execbuf ioctl is implemented in terms
of the new code, preserving the assumption that fence registers are
required for pre-965 rendering commands.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
[ickle: Remove pre-emptive clear_fence_reg()]
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKristian Høgsberg <krh@bitplanet.net>
[anholt: Removed dmesg spam]
Signed-off-by: NEric Anholt <eric@anholt.net>

This let's use use the linux drm headers as the canonical source for
libdrm on all platforms.
Signed-off-by: NKristian Høgsberg <krh@bitplanet.net>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NKristian Høgsberg <krh@bitplanet.net>
Signed-off-by: NEric Anholt <eric@anholt.net>

Add a GETPARAM request for checking if page flipping is supported.
Useful for the 2D driver to enable the flipping path.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NEric Anholt <eric@anholt.net>

This implements intel overlay support for kms via a device-specific
ioctl. Thomas Hellstrom brought up the idea of a general ioctl (on
dri-devel). We've reached the conclusion that such an infrastructure
only makes sense when multiple kms overlay implementations exists,
which atm don't (and it doesn't look like this is gonna change).

Open issues:
- Runs in sync with the gpu, i.e. unnecessary waiting. I've decided
  to wait on this because the hw tends to hang when changing something
  in this area. I left some dummy functions as infrastructure.
- polyphase filtering uses a static table.
- uses uninterruptible sleeps. Unfortunately the alternatives may
  unnecessarily wedged the hw if/when we timeout too early (and
  userspace only overloaded the batch buffers with stuff worth a few
  secs of gpu time).

Changes since v1:
- fix off-by-one misconception on my side. This fixes fullscreen
  playback.
Changes since v2:
- add underrun detection as spec'ed for i965.
- flush caches properly, fixing visual corruptions.
Changes since v4:
- fix up cache flushing of overlay memory regs.
- killed require_pipe_a logic - it hangs the chip.

Tested-By: diego.abelenda@gmail.com (on a 865G)
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
[anholt: Resolved against the MADVISE ioctl going in before this one]
Signed-off-by: NEric Anholt <eric@anholt.net>

In order to correctly prevent the invalid reuse of a purged buffer, we
need to track such events and warn the user before something bad
happens.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Similar to the madvise() concept, the application may wish to mark some
data as volatile. That is in the event of memory pressure the kernel is
free to discard such buffers safe in the knowledge that the application
can recreate them on demand, and is simply using these as a cache.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>