If there is a separate stencil in use, the resource invalidation
flag was not being removed for the depth buffer as rsc was assigned
to the separate stencil.
Fixes: 6ff509593c ("v3d: Only apply TLB load invalidation on first job after FB state update")
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36030>
This workaround doesn't mitigate the issue reliably/completely. An
alternative (but complex) solution also exists.
This introduces a small option that allows to disable the current
workaround as preliminary work.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36110>
This exposes an experimental implementation of HIC with
RADV_PERFTEST=hic. It's passing 100% of VKCTS but it requires some
benchmarks first to verify if performance is acceptable or not.
No addrlib support for GFX6-9.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35974>
Because there is no surface<->surface helper in addrlib, this allocates
a temporary buffer on the CPU to do image->buffer->image. It's a naive
implementation which is probably not the best for performance, but it
works at least.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35974>
On GFX12, everything is compressed with DCC and it's completely
transparent to the userspace driver, so that should be optimal.
On older gens, using HIC disables compression which isn't optimal
for device access.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35974>
rustfmt would change not only lib.rs, which is output by this script,
but also all of the other files in the library. The problem is, those
other files are inputs to lib_rs_gen so the script was changing its own
inputs which meant ninja needed to be run twice before we reached a
fixed point. Remove rustfmt for now to prevent this issue.
Fixes: 591b5da4 ("nouveau/headers: Run rustfmt on generated files")
Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36121>
The unordered mode stored in dependencies might be a bitmask and not
only a single mode. In practice, only the "stronger" mode will stick.
Make sure that the code testing for the mode uses "&" instead of "==",
to avoid prevent some valid combinations to happen, e.g.
```
// ...
add(16) g104<1>F g94<1,1,0>F g34<1,1,0>F { align1 1H @7 $7.dst compacted };
```
which without the fix ends up as
```
// ...
sync nop(1) null<0,1,0>UB { align1 WE_all 1N F@7 };
add(16) g104<1>F g94<1,1,0>F g34<1,1,0>F { align1 1H $7.dst compacted };
```
Enables two tests for the scoreboard pass that illustrate this case.
For measuring the effect, re-enabled the sync.nop accounting on total of
instructions and got the following results.
```
Totals:
Instrs: 322041261 -> 321748285 (-0.09%)
Cycle count: 22864587567 -> 22863073741 (-0.01%)
Max dispatch width: 7989040 -> 7989024 (-0.00%); split: +0.00%, -0.00%
Totals from 88212 (9.78% of 902056) affected shaders:
Instrs: 102282050 -> 101989074 (-0.29%)
Cycle count: 12787629859 -> 12786116033 (-0.01%)
Max dispatch width: 525336 -> 525320 (-0.00%); split: +0.01%, -0.01%
```
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36096>
If the loader tells us to use zink, we use zink. This breaks the
Nouveau heuristic where we use Zink instead of the Nouveau GL driver on
Turing and later. The only reason why it works at all is because we
fail to load what the loader requests and then EGL goes "Oops. No
driver! Let's see if Zink works" and we pick it up on the fallback. We
shouldn't depend on those fallbacks if the loader explicitly says to use
Zink for some bit of hardware.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
This is exactly the same kopper check we had before, it's just moved to
the detect helper so we can do it dynamically in the future.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
Now that thes are only used if and only if we actually want kopper, we
don't need extra kopper checks in individual callbacks.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
Instead of duplicating half of the DRM path, just use the DRM path. The
only real functional change that I can see here is that we now advertise
WL_create_wayland_buffer_from_image on Zink, which should be fine. It
also fixes potential bugs where ForceSoftware && Zink could result in
getting visuals from DRM that don't actually work with wl_shm and then
trying to use them through wl_shm via the kopper path.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
No functional change. This just moves stuff around so it goes DRM then
kopper then swrast rather than having swrast and kopper mixed.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
This further detangles things so we just have a kopper initialization
helper that gets invoked whenever dri2_dpy->kopper is set.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
Otherwise we're sending lavapipe down the kopper path even though it's
not kopper which creates a mess in the code. Also, in spite of the fact
that there are comments claiming lavapipe hits these paths we also have
asserts that it doesn't. Make everything consistent.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
This moves the multibuffers check earlier to make it clear that this is
an early-exit. We also delete kopper_without_multibuffers in favor of a
local variable that doesn't leak all over everywhere. The new variable
is named force_zink because that's really what we're doing: force-enable
Zink even if the X11 checks fail.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
Before we were selecting Zink based on dri2_dpy->kopper which also takes
LIBGL_KOPPER_DISABLE into account which doesn't make any sense. This is
just selecting the driver, not selecting Kopper.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36014>
