intel_glamor.c: In function 'intel_glamor_create_screen_image':
intel_glamor.c:192:12: warning: variable 'pixmap' set but not used
[-Wunused-but-set-variable]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As we now defer the allocation of pixel data until first use, it can
fail in the middle of a rendering routine. In order to prevent chasing
us passing a NULL pointer into the fallback routines, we need to propagate
the failure from the malloc and suppress the failure, discarding the
operation, which is less than ideal.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The cpu bo is only allocated on LLC systems, so do avoid the NULL deref on
debugging for others.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Since we can not keep an unlimited number of vma cached due to the hard
per-process limits on the number of mappings and recreating mappings is
slow due to excruciatingly slow GTT pagefaults, we need to compromise
and keep a small MRU cache of inactive mmaps.
This uses the new API in libdrm-2.4.29 to specify the limit upon the VMA
cache maintained by libdrm.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
libdrm expires its bo 2s after entry into the cache, but we need to free
a buffer to trigger the reaper. So schedule a timer event to trigger 3s
after the last rendering is submitted to free any resident bo during
long periods of idleness.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
A poor cousin to vmap is to instead allocate snooped bo and use a CPU
mapping for zero-copy uploads into GPU resident memory. For maximum
performance, we still need tiled GPU buffers so CPU bo are only useful
in situations where we are frequently migrating data.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In the happy scenario where the pixmap only resides upon the GPU we can
forgo the CPU allocation entirely. The goal is to reduce the number of
needless mmaps performed by the system memory allocator and reduce
overall memory consumption.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In benchmarking firefox this performs whose - it would appear the
sources are indeed used more often than not.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
For large render targets, we prefer to use tiled bo in order to avoid
severe performance degradation. However, if we don't have a GPU bo but
do have a CPU bo and the operation would be untiled, then simply use the
CPU bo.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In theory we should be able to disable dual-stream mode and so be
subject to much looser restrictions (such as the pitch need only be
dword aligned). However, achieving single-stream mode seems quite
difficult!
Reported-by: Paul Neumann <paul104x@yahoo.de>
References: https://bugs.freedesktop.org/show_bug.cgi?id=43706
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Our goal is to achieve "single-stream" rendering where the entire
RenderCache is allocated to the colour buffer (rather than split between
colour and depth). In theory all that is required is for the pipeline
not to reference the depth buffer at all, however it is not made clear
when that evaluation is made.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The binding table is intended to be after all the surface descriptions,
so make sure we write it with the appropriate offset into the buffer.
Fixes regression from 699888a64 (uxa/video: Use the common bo
allocations and upload)
Reported-by: Cyril Brulebois <kibi@debian.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=43704
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
A VMA cache appears unavoidable thanks to compiz and an excrutiatingly
slow GTT pagefault, though it does look like it will be ineffectual
during everyday usage. Compiz (and presumably other compositing
managers) appears to be undoing all the pagefault minimisation as
demonstrated on gen5 with large XPutImage. It also appears the CPU to
memory bandwidth ratio plays a crucial role in determining whether
going straight to GTT or through the CPU cache is a win - so no trivial
heuristic.
x11perf -putimage10 -putimage500 on i5-2467m:
Before:
bare: 1150,000 2,410
compiz: 438,000 2,670
After:
bare: 1190,000 2,730
compiz: 437,000 2,690
UXA:
bare: 658,000 2,670
compiz: 389,000 2,520
On i3-330m
Before:
bare: 537,000 1,080
compiz: 263,000 398
After:
bare: 606,000 1,360
compiz: 203,000 985
UXA:
bare: 294,000 1,070
compiz: 197,000 821
On pnv:
Before:
bare: 179,000 213
compiz: 106,000 123
After:
bare: 181,000 246
compiz: 103,000 197
UXA:
bare: 114,000 312
compiz: 75,700 191
Reported-by: Michael Larabel <Michael@phoronix.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
If we are copying over the entire source onto the destination,just copy
across the GPU bo. This is often used for caching images as pixmaps.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We have to be careful to assume bo via exposed are under our full
control, in particular not to assert their state. :(
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
gen2/3 have a restriction that the 3D pipeline cannot render to a pixmap
with a pitch less than 8/16 respectively. Rather than mandating all
pixmaps to be created with a stride greater than 16, fixup the bo for
the rare occasions when it is necessary.
Reported-by: Paul Neumann <paul104x@yahoo.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=43688
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
For the long interval events (such as expiring the caches), we do not
need precise timing and so can use a coarse timer to allow the system
to coalesce and reduce wakeup events.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
If a pixmap lies around for a couple of minutes not being used, it is
unlikely to be used again in the near future. Reap the GPU buffers of
any of those idle pixmaps (copying to a more compact buffer in system
memory) in order to free up resources for use elsewhere. Any object
that is exposed via DRI is obviously exempt from this reaping.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Chris Wilson