This uses a stamp mechanisms to mark the DRI drawable as invalid.
Instead of immediately updating the buffers we just bump the drawable
stamp and call out to DRI2GetBuffers "later".
"Later" used to be at LOCK_HARDWARE time, and this patch brings back
callouts at the points where we used to call LOCK_HARDWARE. A new function,
intel_prepare_render(), is called where we used to call LOCK_HARDWARE,
and if the buffers are invalid, we call out to DRI2GetBuffers there.
This lets us invalidate buffers only when notified instead of on
every glViewport() call. If the loader calls the DRI invalidate
entrypoint, we disable viewport triggered buffer invalidation.
Additionally, we can clean up the old viewport mechanism a bit,
since we can just invalidate the buffers and not worry about
reentrancy and whatnot.
As part of the DRI driver interface rewrite I merged __DRIscreenPrivate
and __DRIscreen, and likewise for __DRIdrawablePrivate and
__DRIcontextPrivate. I left typedefs in place though, to avoid renaming
all the *Private use internal to the driver. That was probably a
mistake, and it turns out a one-line find+sed combo can do the mass
rename. Better late than never.
Wine's d3d9 visual.c testcase tries this a lot, so I've added some
piglit tests (fbo-nodepth-test, fbo-nostencil-test, fbo-stencil-only)
and enabled it.
This prevents the mystery blank window if, for example, glxgears is
resized larger than 2048 wide on 915. Since the Intel drivers in Mesa
7.6 lack GTT mapped fallbacks, the performance is a slideshow at
best. On Mesa 7.7 and later the performance is much better.
Before, if we just called glXMakeCurrent() and didn't render anything we'd
still trigger a flushFrontBuffer() call.
Now only set the intel->front_buffer_dirty field at state validation time
just before we draw something.
NOTE: additional calls to intel_check_front_buffer_rendering() might be
needed if I missed some rendering paths.
_ActualFormat is replaced by Format (MESA_FORMAT_x).
ColorEncoding, ComponentType, RedBits, GreenBits, BlueBits, etc. are
all replaced by MESA_FORMAT_x queries.
The _Enabled field isn't updated at the point that DrawBuffers is called,
and the Driver.Enable() function does the testing for stencil buffer
presence anyway.
bug #21608 for Radeon
Since GL_READ_BUFFER is historically part of the gl_pixel_attrib group
it made sense to signal changes with _NEW_PIXEL. But now with FBOs it's
also part of the framebuffer state.
Now _NEW_PIXEL strictly indicates pixels transfer state changes.
This change avoids framebuffer state validation when any random bit of
pixel-transfer state is set.
DRI drivers updated too: don't check _NEW_COLOR when updating framebuffer
state. I think that was just copied from the Xlib driver because we care
about dither enable/disable state there.
For non-stereo visuals, which is all we support, we treat
GL_FRONT_LEFT as GL_FRONT. However, they are technically different,
and they have different enum values. Test for either one to determine
if we're in front-buffer rendering mode.
This fix was suggested by Pierre Willenbrock.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
This interface gives the driver two important features. First, it can
allocate the (fake) front-buffer only when needed. Second, it can
tell the buffer allocator the format of buffers being allocated. This
enables support for back-buffer and depth-buffer with different bits
per pixel.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kristian Høgsberg <krh@redhat.com>
It is possible for ctx->DrawBuffer to be NULL, so don't fault when
that happens. This change is not being committed to master because it
doesn't appear to be necessary there.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Cherry picked from mesa_7_4_branch, commit 49e0c74ddd91900fc4effb6d305d56e0563b456d
Track two flags: whether or not front-buffer rendering is currently
enabled and whether or not front-buffer rendering has been enabled
since the last glFlush. If the second flag is set, the front-buffer
is flushed via a loader call back. If the first flag is cleared, the
second flag is cleared at this time.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kristian Høgsberg <krh@redhat.com>
On Mobile chipsets, we often enable PipeB instead of PipeA, but the test
in here was insufficient, falling back to pipe A if the area
intersection returned zero. Therefore, in the case where a window went
off to the top of the left of the screen, it would freeze, waiting on
the wrong vblank.
Fix this mess by checking the sarea for a crtc being zero sized, and in
that case always default to the other one.
intelMakeCurrent is called before intelWindowMoved (in fact, it calls
it), so calculation of the correct vblank crtc has not happened yet.
Fix this by making a function that fixes up a set of vblank flags and
call if from both functions.
We only allow combined depth+stencil renderbuffers so the complicated code
for splitting and combining separate depth and stencil buffers is no longer
needed.
The upstream linux kernel headers and libdrm kernel headers disagree on the
tag name for the sarea struct: _drm_i915_sarea vs drm_i915_sarea. They
both typedef it to drm_i915_sarea_t though, so just use that.
It's been broken and deprecated for a while, so it's time to die. This has the
wonderful benefit of cleaning up the code a fair amount; making it marginally
less twisty.
I'm unsure if the for loops in IntelWindowMoved are still needed.
This avoids issues with dereferencing stale cliprects around intel_draw_buffer
time. Additionally, take advantage of cliprects staying constant for FBOs and
DRI2, and emit cliprects in the batchbuffer instead of having to flush batch
each time they change.
This lets us short-circuit when we're leaving the same cliprects in place,
which becomes quite common with metaops clears, and may be useful for some of
our FBO paths.
Some buffer swap intel render buffer fields (pf_num_pages & vbl_pending) are
also used for page flipping, so enable the code that sets & updates them on
965. This allows buffer swaps and page flips to work on 965 and prevents hangs
in LOCK_HARDWARE in the buffer swap case due to an uninitialized vbl_pending
field.
Fixes FDO #16118.
Instead of passing in a fixed struct, the loader now passes in a list
of __DRIextension structs, to advertise the functionality it can provide
to the driver. Each extension is individually versioned and can be
extended or phased out as the interface develops.
