Map the kernel alloc_flag AMDGPU_GEM_CREATE_DISCARDABLE to
RADEON_FLAG_DISCARDABLE in function radv_amdgpu_bo_get_flags_from_fd.
Signed-off-by: Julia Zhang <Julia.Zhang@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40879>
The new definitions have their numbers offset by 1 (e.g. S_580 -> S_581).
The remaining old definitions are adjusted to match that.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40588>
This would always wait on the queue syncobj if there was any other
wait syncobj, but it should only wait after zero submit.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39193>
Map the first page of the same BO as read-only after the BO itself
in order to pad each BO with an extra page. This doesn't require
us to allocate any memory.
This is going to be used for a HW bug mitigation.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38769>
DXVK's DXGI implementation can create extra instances used for
enumerating physical devices besides the games' instance. When reserving
VMIDs for SPM, the DXGI instances may snatch the VMID reservation early,
making VMID reservation for the instance that actually needs it fail.
This starts being a problem on kernels 6.18+ where only one user may
reserve a VMID at a time.
Move reserving VMIDs to SQTT initialization inside vkCreateDevice so
that only the instances that actually create logical devices try
reserving VMIDs.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38746>
RADEON_FLAG_VM_UPDATE_WAIT can be passed to wait for VM updates at
allocation time instead of delaying them at submit time. There is no
reason to delay the waiting when the memory is bound to images/buffers
because in DX12 ressources are allocated and bound immediately.
This flag will be used to workaround an use-before-alloc in FH5
(game bug) which causes GPU hangs.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38031>
vkd3d-proton (DX12) and Zink (GL) have always been enabling features
that require the global BO list to be enabled.
Since DXVK 2.7+ (August 2025), it's also always enabled by default for
DX9-11 games (because it requires BDA now).
The global BO list used to decrease performance in the past mostly
because of bad memory management in AMDGPU, but it seems the situation
slightly improved since. Though, there might still some workloads that
hit the issue, but I think it should be mostly good overall.
This introduces RADV_DEBUG=nobolist to disable the global BO list
when no features require it.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6957
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2331
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35075>
The primary CS doesn't need to use chaining in order to use IB2.
Allow using IB2 packets when chaining is disabled.
Rationale for this patch:
When chaining is enabled (the default), this patch removes a
useless check.
When chaining is disabled (by noibchaining), this patch allows us
to use IB2 without chaining.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37280>
All CS always use IBs, so the naming was confusing.
Rename these fields to chain_ib to better reflect
what it actually means, which is enabling chaining:
radv_amdgpu_winsys::use_ib_bos
radv_amdgpu_cs::chain_ib
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37280>
Based on a patch by llyyr <llyyr.public@gmail.com>:
!36827 added the copy_sync_payloads function, but didn't enable use of
it in radv. This commit mirrors similar MRs for anv/panvk/nvk and uses
the common vk_drm_syncobj_copy_payloads function for copy_sync_payloads.
I'm not too familiar with radv internals, so there's potentially a good
reason why this isn't a good change. However, I've personally been using
this patch locally for around a month and have experienced no
regressions and around 8% uplift on vkmark test scores with a 6600 XT.
[vertex] device-local=true: 45110 -> 48489 (+7.5%)
[vertex] device-local=false: 17529 -> 17488 (-0.2%)
[texture] anisotropy=0: 44768 -> 48679 (+8.7%)
[texture] anisotropy=16: 44920 -> 48572 (+8.1%)
[shading] shading=gouraud: 44931 -> 48467 (+7.9%)
[shading] shading=blinn-phong-inf: 44849 -> 48740 (+8.7%)
[shading] shading=phong: 44695 -> 48645 (+8.8%)
[shading] shading=cel: 44809 -> 47938 (+7.0%)
[effect2d] kernel=edge: 45185 -> 47837 (+5.9%)
[effect2d] kernel=blur: 26919 -> 26762 (-0.6%)
[desktop] <default>: 40974 -> 44034 (+7.5%)
[cube] <default>: 45090 -> 49270 (+9.3%)
[clear] <default>: 41102 -> 44375 (+8.0%)
(https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37606)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37640>
GFX6 actually supports IB2, but doesn't support chaining between
chunks inside the IB2. See WaCpIb2ChainingUnsupported in PAL.
Disable IB2 on GFX6 for now.
The proper fix will be to disable use_ib in just secondary
command buffers on GFX6 and emit multiple IB2 packets in the
main command buffer. This will be implemented later.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37121>
After a refactor last year, the noibs option stopped working
because it hits an assertion when empty IBs are submitted.
Emit a single large NOP packet to avoid submitting empty IBs.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37121>
Don't include amdgpu.h directly in AMDGPU/RADV code, the only libdrm
pieces that are needed are handled in src/amd/common/ac_linux_drm.h
which already includes amdgpu.h
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36932>
DRM syncobjs always let you wait repeatedly on them, so we can set the
flag in the core instead of having each driver override it once they try
to enable the emulated timeline semaphores.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36563>
This fixes an issue with Hellblade Senua's Sacrifice because
RADV_PERFTEST_RT_WAVE_64 is set using drirc, but if two devices are
created RADV_PERFTEST flags might differ.
The proposed solution is to filter out unused RADV_PERFTEST flags for
the winsys.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36727>
In the C23 standard unreachable() is now a predefined function-like
macro in <stddef.h>
See https://android.googlesource.com/platform/bionic/+/HEAD/docs/c23.md#is-now-a-predefined-function_like-macro-in
And this causes build errors when building for C23:
-----------------------------------------------------------------------
In file included from ../src/util/log.h:30,
from ../src/util/log.c:30:
../src/util/macros.h:123:9: warning: "unreachable" redefined
123 | #define unreachable(str) \
| ^~~~~~~~~~~
In file included from ../src/util/macros.h:31:
/usr/lib/gcc/x86_64-linux-gnu/14/include/stddef.h:456:9: note: this is the location of the previous definition
456 | #define unreachable() (__builtin_unreachable ())
| ^~~~~~~~~~~
-----------------------------------------------------------------------
So don't redefine it with the same name, but use the name UNREACHABLE()
to also signify it's a macro.
Using a different name also makes sense because the behavior of the
macro was extending the one of __builtin_unreachable() anyway, and it
also had a different signature, accepting one argument, compared to the
standard unreachable() with no arguments.
This change improves the chances of building mesa with the C23 standard,
which for instance is the default in recent AOSP versions.
All the instances of the macro, including the definition, were updated
with the following command line:
git grep -l '[^_]unreachable(' -- "src/**" | sort | uniq | \
while read file; \
do \
sed -e 's/\([^_]\)unreachable(/\1UNREACHABLE(/g' -i "$file"; \
done && \
sed -e 's/#undef unreachable/#undef UNREACHABLE/g' -i src/intel/isl/isl_aux_info.c
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36437>
Instead of assuming that VM_ALWAYS_VALID is always available,
make its use conditionnal on its support.
This allows to remove the virtio nctx special case (where
VM_ALWAYS_VALID is only possible with virtio for buffers that
also have the NO_CPU_ACCESS flag since CPU access is implemented
through dmabuf on the host).
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Rob Clark <robdclark@chromium.org>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34470>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Rob Clark <robdclark@chromium.org>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34470>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Rob Clark <robdclark@chromium.org>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34470>
