| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
| |
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103909
Signed-off-by: Vinson Lee <[email protected]>
Reviewed-by: Eric Engestrom <[email protected]>
|
|
|
|
|
| |
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Nanley Chery <[email protected]>
|
|
|
|
|
|
|
| |
While we're at it, we break it into two nicely named functions.
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Nanley Chery <[email protected]>
|
|
|
|
| |
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When the kernel support flagging our BO, let's mark batch &
instruction BOs for capture so then can be included in the error
state.
v2: Only add EXEC_CAPTURE if supported (Kristian)
v3: Fix operator precedence issue (Lionel)
Signed-off-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
|
|
|
|
|
|
|
| |
This will allow to set the flags on any anv_bo created/filled from a
state pool or block pool later.
Signed-off-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
|
|
|
|
|
|
|
| |
Otherwise, if the image is not bound to the start of the buffer, we're
going to be reading and writing its fast clear state in the wrong spot.
Reviewed-by: Lionel Landwerlin <[email protected]>
Cc: [email protected]
|
|
|
|
|
|
|
|
| |
Found by inspection
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Nanley Chery <[email protected]>
Cc: [email protected]
|
|
|
|
|
| |
Signed-off-by: Anuj Phogat <[email protected]>
Reviewed-by: Rafael Antognolli <[email protected]>
|
|
|
|
|
|
|
|
|
| |
We already have this workaround in OpenGL driver.
See Mesa commit 3cf4fe2219.
Signed-off-by: Anuj Phogat <[email protected]>
Cc: Nanley Chery <[email protected]>
Cc: Rafael Antognolli <[email protected]>
|
|
|
|
|
|
|
|
| |
This makes our MOCS settings significantly more flexible.
Cc: "17.3" <[email protected]>
Tested-by: Lyude Paul <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
|
|
|
|
|
| |
Cc: "17.3" <[email protected]>
Tested-by: Lyude Paul <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
I tested this in a setup where the builddir was outside of the srcdir.
Reviewed-by: Eric Engestrom <[email protected]>
Reviewed-by: Dylan Baker <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
Use the host arch, not the target arch. In Meson and in recent
Autotools, the host arch is where the binary will be used. The target
arch is useful only when compiling a compiler.
See: http://mesonbuild.com/Cross-compilation.html
See: https://www.gnu.org/software/automake/manual/html_node/Cross_002dCompilation.html
Reported-by: Eric Engestrom <[email protected]>
Reviewed-by: Dylan Baker <[email protected]>
|
|
|
|
|
|
|
|
| |
Its helper function, anv_surface_get_subresource_layout(), was not very
helpful. So fold it into the main function.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
Instead of choosing the tiling flags inside make_surface(), which is
called once per aspect in a loop, and which chooses the same tiling for
each aspect, choose the tiling flags exactly once before entering the
aspect loop.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
| |
The same local variable, 'plane_format', was returned on success *and*
failure. Be more explicit in distinguishing the two cases: return
'plane_format' on success and return 'unsupported' on failure.
This simplifies the diff in upcoming patches for
VK_EXT_image_drm_format_modifier.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
| |
Fold its body into its sole caller,
anv_GetPhysicalDeviceFormatProperties().
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Now that get_image_format_properties() returns the correct
VkFormatFeatureFlags, we can remove the unneeded if-branch and some
local variables.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Now that get_image_format_features() has a VkImageTiling parameter, we
can bypass anv_physical_device_get_format_properties() and call
get_image_format_features() directly.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The name is misleading. It looks like vkGetPhysicalDeviceImageFormatProperties(),
but it actually implement vkGetPhysicalDeviceFormatProperties. Let's
rename it to what it actually does, get_image_format_features(), because it
returns VkFormatFeatureFlags.
For consistency, also rename get_buffer_format_properties() to
get_buffer_format_features().
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Teach it to calculate the format features for YCbCr.
The goal (which is completed in this patch) is to incrementally fix
get_image_format_properties() to return a correct result. Previously,
it returned incorrect VkFormatFeatureFlags which the caller needed clean
up.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
Teach it to calculate the format features for 3-channel formats.
The goal is to incrementally fix get_image_format_properties() to return
a correct result. Currently, it returns incorrect VkFormatFeatureFlags
which the caller must clean up.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Replace parameters 'enum isl_format' and 'struct anv_format_plane' with
new parameter 'const struct anv_format *'.
The goal is to incrementally fix get_image_format_properties() to return
a correct result. Currently, it returns incorrect VkFormatFeatureFlags
which the caller must clean up.
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
| |
Rename parameter 'base' to 'base_isl_format'.
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
| |
Rename parameter 'format' to 'plane_format'.
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Teach it to calculate the format features for ASTC.
The goal is to incrementally fix get_image_format_properties() to return
a correct result. Currently, it returns incorrect VkFormatFeatureFlags
which the caller must clean up.
v2: New commit message
Reviewed-by: Jason Ekstrand <[email protected]> (v1)
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Teach it to calculate the features of depthstencil formats.
The goal is to incrementally fix get_image_format_properties() to return
a correct result. Currently, it returns incorrect VkFormatFeatureFlags
which the caller must clean up.
v2: New commit message
Reviewed-by: Jason Ekstrand <[email protected]> (v1)
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Some functions have a comment that says "Exactly one bit must be in
'aspect'". So change the type of their 'aspect' parameter from
VkImageAspectFlags to VkImageAspectFlagBits.
Reviewed-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
Make it a stand-alone function. Pre-patch, for some formats the function
returned incorrect VkFormatFeatureFlags which were cleaned up by the
caller.
This prepares for a cleaner implementation of
VK_EXT_image_drm_format_modifier.
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
| |
Fixes: e3a8013de8ca ("util/u_queue: add util_queue_fence_wait_timeout")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
While modern pthread mutexes are very fast, they still incur a call to an
external DSO and overhead of the generality and features of pthread mutexes.
Most mutexes in mesa only needs lock/unlock, and the idea here is that we can
inline the atomic operation and make the fast case just two intructions.
Mutexes are subtle and finicky to implement, so we carefully copy the
implementation from Ulrich Dreppers well-written and well-reviewed paper:
"Futexes Are Tricky"
http://www.akkadia.org/drepper/futex.pdf
We implement "mutex3", which gives us a mutex that has no syscalls on
uncontended lock or unlock. Further, the uncontended case boils down to a
cmpxchg and an untaken branch and the uncontended unlock is just a locked decr
and an untaken branch. We use __builtin_expect() to indicate that contention
is unlikely so that gcc will put the contention code out of the main code
flow.
A fast mutex only supports lock/unlock, can't be recursive or used with
condition variables. We keep the pthread mutex implementation around as
for the few places where we use condition variables or recursive locking.
For platforms or compilers where futex and atomics aren't available,
simple_mtx_t falls back to the pthread mutex.
The pthread mutex lock/unlock overhead shows up on benchmarks for CPU bound
applications. Most CPU bound cases are helped and some of our internal
bind_buffer_object heavy benchmarks gain up to 10%.
Signed-off-by: Kristian Høgsberg <[email protected]>
Signed-off-by: Timothy Arceri <[email protected]>
Reviewed-by: Nicolai Hähnle <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
We're going to want subgroup ID for SPIR-V subgroups eventually anyway.
We really only want to push one and calculate the other from it. It
makes a bit more sense to push the subgroup ID because it's simpler to
calculate and because it's a real API thing. The only advantage to
pushing the base thread ID is to avoid a single SHL in the shader.
Reviewed-by: Iago Toral Quiroga <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I saw VK_IMAGE_ASPECT_ANY_COLOR_BIT while hacking anv_formats.c and got
confused. "Huh? What extension added that?". No extension defines it;
anv_private.h defines it.
To remove confusion, rename the anv-private VK tokens as if they were
extension tokens with the ANV vendor suffix.
I found only two such tokens:
VK_IMAGE_ASPECT_ANY_COLOR_BIT
VK_IMAGE_ASPECT_PLANES_BITS
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
| |
In anv_physical_device_get_format_properties().
Reviewed-by: Jason Ekstrand <[email protected]>
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
| |
The caller can now use brw_stage_prog_data::program_size which is set
by the brw_compile_* functions.
Cc: Jason Ekstrand <[email protected]>
Signed-off-by: Jordan Justen <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Asserting slot >= 2 made sense when the URB read offset was always 1
(pair of slots). Commit 566a0c43f0b9fbf5106161471dd5061c7275f761 made
it possible to read from the VUE header in slot 0, by adjusting the
offset to be 0. So, this assert is now bogus. Use the one from GL.
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Commit 566a0c43f0b9fbf5106161471dd5061c7275f761 started setting the
3DSTATE_SBE bit to override these values with the one calculated there.
So, they're dead. Stop setting them.
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
| |
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
| |
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
We currently have a bug where nir_lower_system_values gets called before
nir_lower_var_copies so it will miss any system value uses which come
from a copy_var intrinsic. Moving it to after brw_preprocess_nir fixes
this problem.
Reviewed-by: Lionel Landwerlin <[email protected]>
Cc: [email protected]
|
|
|
|
|
|
| |
We already handle it in brw_preprocess_nir
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
| |
Reviewed-by: Lionel Landwerlin <[email protected]>
|
|
|
|
|
|
|
| |
v2: Warn that support is still in alpha (Jason)
Signed-off-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
| |
This workaround isn't listed on Gen10.
Signed-off-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
| |
It's redundant with nir_shader::info::stage.
Acked-by: Timothy Arceri <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Reviewed-by: Jordan Justen <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fix build error.
CC vulkan/vulkan_libvulkan_common_la-anv_device.lo
In file included from vulkan/anv_device.c:33:0:
vulkan/anv_device.c: In function ‘anv_AllocateMemory’:
vulkan/anv_device.c:1562:37: error: ‘struct anv_device’ has no member named ‘instace’; did you mean ‘instance’?
result = vk_errorf(device->instace, device,
^
vulkan/anv_private.h:317:17: note: in definition of macro ‘vk_errorf’
__vk_errorf(instance, obj, REPORT_OBJECT_TYPE(obj), error,\
^~~~~~~~
Fixes: 9775894f1025 ("anv: Move size check from anv_bo_cache_import() to caller (v2)")
Signed-off-by: Vinson Lee <[email protected]>
Reviewed-by: Eric Engestrom <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This implementation is correct (afaict), but takes two shortcuts
regarding the import/export of Android sync fds.
Shortcut 1. When Android calls vkAcquireImageANDROID to import a sync
fd into a VkSemaphore or VkFence, the driver instead simply blocks on
the sync fd, then puts the VkSemaphore or VkFence into the signalled
state. Thanks to implicit sync, this produces correct behavior (with
extra latency overhead, perhaps) despite its ugliness.
Shortcut 2. When Android calls vkQueueSignalReleaseImageANDROID to export
a collection of wait semaphores as a sync fd, the driver instead
submits the semaphores to the queue, then returns sync fd -1, which
informs the caller that no additional synchronization is needed.
Again, thanks to implicit sync, this produces correct behavior (with
extra batch submission overhead) despite its ugliness.
I chose to take the shortcuts instead of properly importing/exporting
the sync fds for two reasons:
Reason 1. I've already tested this patch with dEQP and with demos
apps. It works. I wanted to get the tested patches into the tree now,
and polish the implementation afterwards.
Reason 2. I want to run this on a 3.18 kernel (gasp!). In 3.18, i915
supports neither Android's sync_fence, nor upstream's sync_file, nor
drm_syncobj. Again, I tested these patches on Android with a 3.18
kernel and they work.
I plan to quickly follow-up with patches that remove the shortcuts and
properly import/export the sync fds.
Non-Testing
===========
I did not test at all using the Android.mk buildsystem. I may have broke
it. Please test and review that.
Testing
=======
I tested with 64-bit ARC++ on a Skylake Chromebook and a 3.18 kernel.
The following pass (as of patchset v9):
- a little spinning cube demo APK
- several Sascha demos
- dEQP-VK.info.*
- dEQP-VK.api.wsi.android.*
(except dEQP-VK.api.wsi.android.swapchain.*.image_usage, because
dEQP wants to create swapchains with VK_IMAGE_USAGE_STORAGE_BIT)
- dEQP-VK.api.smoke.*
- dEQP-VK.api.info.instance.*
- dEQP-VK.api.info.device.*
v2:
- Reject VkNativeBufferANDROID if the dma-buf's size is too small for
the VkImage.
- Stop abusing VkNativeBufferANDROID by passing it to vkAllocateMemory
during vkCreateImage. Instead, directly import its dma-buf during
vkCreateImage with anv_bo_cache_import(). [for jekstrand]
- Rebase onto Tapani's VK_EXT_debug_report changes.
- Drop `CPPFLAGS += $(top_srcdir)/include/android`. The dir does not
exist.
v3:
- Delete duplicate #include "anv_private.h". [per Tapani]
- Try to fix the Android-IA build in Android.vulkan.mk by following
Tapani's example.
v4:
- Unset EXEC_OBJECT_ASYNC and set EXEC_OBJECT_WRITE on the imported
gralloc buffer, just as we do for all other winsys buffers in
anv_wsi.c. [found by Tapani]
v5:
- Really fix the Android-IA build by ensuring that Android.vulkan.mk
uses Mesa' vulkan.h and not Android's. Insert -I$(MESA_TOP)/include
before -Iframeworks/native/vulkan/include. [for Tapani]
- In vkAcquireImageANDROID, submit signal operations to the
VkSemaphore and VkFence. [for zhou]
v6:
- Drop copy-paste duplication in vkGetSwapchainGrallocUsageANDROID().
[found by zhou]
- Improve comments in vkGetSwapchainGrallocUsageANDROID().
v7:
- Fix vkGetSwapchainGrallocUsageANDROID() to inspect its
VkImageUsageFlags parameter. [for tfiga]
- This fix regresses dEQP-VK.api.wsi.android.swapchain.*.image_usage
because dEQP wants to create swapchains with
VK_IMAGE_USAGE_STORAGE_BIT.
v8:
- Drop unneeded goto in vkAcquireImageANDROID. [for tfiga]
v8.1: (minor changes)
- Drop errant hunks added by rerere in anv_device.c.
- Drop explicit mention of VK_ANDROID_native_buffer in
anv_entrypoints_gen.py. [for jekstrand]
v9:
- Isolate as much Android code as possible, moving it from anv_image.c
to anv_android.c. Connect the files with anv_image_from_gralloc().
Remove VkNativeBufferANDROID params from all anv_image.c
funcs. [for krh]
- Replace some intel_loge() with vk_errorf() in anv_android.c.
- Use © in copyright line. [for krh]
Reviewed-by: Tapani Pälli <[email protected]> (v5)
Reviewed-by: Kristian H. Kristensen <[email protected]> (v9)
Reviewed-by: Jason Ekstrand <[email protected]> (v9)
Cc: zhoucm1 <[email protected]>
Cc: Tomasz Figa <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This change prepares for VK_ANDROID_native_buffer. When the user imports
a gralloc hande into a VkImage using VK_ANDROID_native_buffer, the user
provides no size. The driver must infer the size from the internals of
the gralloc buffer.
The patch is essentially a refactor patch, but it does change behavior
in some edge cases, described below. In what follows, the "nominal size"
of the bo refers to anv_bo::size, which may not match the bo's "actual
size" according to the kernel.
Post-patch, the nominal size of the bo returned from
anv_bo_cache_import() is always the size of imported dma-buf according
to lseek(). Pre-patch, the bo's nominal size was difficult to predict.
If the imported dma-buf's gem handle was not resident in the cache, then
the bo's nominal size was align(VkMemoryAllocateInfo::allocationSize,
4096). If it *was* resident, then the bo's nominal size was whatever
the cache returned. As a consequence, the first cache insert decided the
bo's nominal size, which could be significantly smaller compared to the
dma-buf's actual size, as the nominal size was determined by
VkMemoryAllocationInfo::allocationSize and not lseek().
I believe this patch cleans up that messy behavior. For an imported or
exported VkDeviceMemory, anv_bo::size should now be the true size of the
bo, if I correctly understand the problem (which I possibly don't).
v2:
- Preserve behavior of aligning size to 4096 before checking. [for
jekstrand]
- Check size with < instead of <=, to match behavior of commit c0a4f56
"anv: bo_cache: allow importing a BO larger than needed". [for
chadv]
|