Both busy_ioctl and the new wait_ioct need to do the same dance (or at
least should). Some slight changes:
- busy_ioctl now unconditionally checks for olr. Before emitting a
require flush would have prevent the olr check and hence required a
second call to the busy ioctl to really emit the request.
- the timeout wait now also retires request. Not really required for
abi-reasons, but makes a notch more sense imo.
I've tested this by pimping the i-g-t test some more and also checking
the polling behviour of the wait_rendering_timeout ioctl versus what
busy_ioctl returns.
v2: Too many people complained about unplug, new color is
flush_active.
v3: Kill the comment about the unplug moniker.
v4: s/un-active/inactive/
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need the latest dma-buf code from Dave Airlie so that we can pimp
the backing storage handling code in drm/i915 with Chris Wilson's
unbound tracking and stolen mem backed gem object code.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If any l3 rows have been previously remapped, we must remap them after
GPU reset/resume too.
v2: Just return (no warn) on remapping init if not IVB (Jesse)
Move the check of schizo userspace to i915_gem_l3_remap (Jesse)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
drm/i915: tune down the noise of the RP irq limit fail
drm/i915: Remove the error message for unbinding pinned buffers
drm/i915: Limit page allocations to lowmem (dma32) for i965
drm/i915: always use RPNSWREQ for turbo change requests
drm/i915: reject doubleclocked cea modes on dp
drm/i915: Adding TV Out Missing modes.
drm/i915: wait for a vblank to pass after tv detect
drm/i915: no lvds quirk for HP t5740e Thin Client
drm/i915: enable vdd when switching off the eDP panel
drm/i915: Fix PCH PLL assertions to not assume CRTC:PLL relationship
drm/i915: Always update RPS interrupts thresholds along with frequency
drm/i915: properly handle interlaced bit for sdvo dtd conversion
drm/i915: fix module unload since error_state rework
drm/i915: be more careful when returning -ENXIO in gmbus transfer
Wait request is poorly named IMO. After working with these functions for
some time, I feel it's much clearer to name the functions more
appropriately.
Of course we must update the callers to use the new name as well.
This leaves room within our namespace for a *real* wait request function
at some point.
Note to maintainer: this patch is optional.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This helps implement GL_ARB_sync but stops short of allowing full blown
sync objects. Finally we can use the new timed seqno waiting function
to allow userspace to wait on a buffer object with a timeout. This
implements that interface.
The IOCTL will take as input a buffer object handle, and a timeout in
nanoseconds (flags is currently optional but will likely be used for
permutations of flush operations). Users may specify 0 nanoseconds to
instantly check.
The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
non-zero timeout parameter the wait ioctl will wait for the given number
of nanoseconds on an object becoming unbusy. Since the wait itself does
so holding struct_mutex the object may become re-busied before this
completes. A similar but shorter race condition exists in the busy
ioctl.
v2: ETIME/ERESTARTSYS instead of changing to EBUSY, and EGAIN (Chris)
Flush the object from the gpu write domain (Chris + Daniel)
Fix leaked refcount in good case (Chris)
Naturally align ioctl struct (Chris)
v3: Drop lock after getting seqno to avoid ugly dance (Chris)
v4: check for 0 timeout after olr check to allow polling (Chris)
v5: Updated the comment. (Chris)
v6: Return -ETIME instead of -EBUSY when timeout_ns is 0 (Daniel)
Fix the commit message comment to be less ugly (Ben)
Add a warning to check the return timespec (Ben)
v7: Use DRM_AUTH for the ioctl. (Eugeni)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is now used intentionally to prevent proliferation of is-pinned
checks upon the inactive list following:
commit 1b50247a8d
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Apr 24 15:47:30 2012 +0100
drm/i915: Remove the list of pinned inactive objects
Reported-and-tested-by: guang.a.yang@intel.com
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50075
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Broadwater and Crestline share a limitation that prevent it from
relocating general surface state above 4GiB. The only recourse we have
since any buffer object may be used as a relocation target is then to
limit all object allocations on 965g[m] to DMA32.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Insert a wait parameter in the code so we can possibly timeout on a
seqno wait if need be. The code should be functionally the same as
before because all the callers will continue to retry if an arbitrary
timeout elapses.
We'd like to have nanosecond granularity, but the only way to do this is
with hrtimer, and that doesn't fit well with the needs of this code.
v2: Fix rebase error (Chris)
Return proper time even in wedged + signal case (Chris + Ben)
Use timespec constructs (Ben)
Didn't take Daniel's advice regarding the Frankenstein-ness of the
function. I did try his advice, but in the end I liked the way the
original code looked, better.
v3: Make wakeups far less frequent for infinite waits (Chris)
v4: Remove dummy_wait variable (Daniel)
Use raw monotonic time instead of jiffies (made the code a bit cleaner) (Ben)
Added a couple of warnings (Ben)
v5: Remove warnings (Daniel)
Use more accurate time diff for default case (Daniel)
Bikeshed for setting the return timespec in timeout case (Daniel)
s/jiffies/time in one of the comments
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This adds handle->fd and fd->handle support to i915, this is to allow
for offloading of rendering in one direction and outputs in the other.
v2 from Daniel Vetter:
- fixup conflicts with the prepare/finish gtt prep work.
- implement ppgtt binding support.
Note that we have squat i-g-t testcoverage for any of the lifetime and
access rules dma_buf/prime support brings along. And there are quite a
few intricate situations here.
Also note that the integration with the existing code is a bit
hackish, especially around get_gtt_pages and put_gtt_pages. It imo
would be easier with the prep code from Chris Wilson's unbound series,
but that is for 3.6.
Also note that I didn't bother to put the new prepare/finish gtt hooks
to good use by moving the dma_buf_map/unmap_attachment calls in there
(like we've originally planned for).
Last but not least this patch is only compile-tested, but I've changed
very little compared to Dave Airlie's version. So there's a decent
chance v2 on drm-next works as well as v1 on 3.4-rc.
v3: Right when I've hit sent I've noticed that I've screwed up one
obj->sg_list (for dmar support) and obj->sg_table (for prime support)
disdinction. We should be able to merge these 2 paths, but that's
material for another patch.
v4: fix the error reporting bugs pointed out by ickle.
v5: fix another error, and stop non-gtt mmaps on shared objects
stop pread/pwrite on imported objects, add fake kmap
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In many places we wish to iterate over the rings associated with the
GPU, so refactor them to use a common macro.
Along the way, there are a few code removals that should be side-effect
free and some rearrangement which should only have a cosmetic impact,
such as error-state.
Note that this slightly changes the semantics in the hangcheck code:
We now always cycle through all enabled rings instead of
short-circuiting the logic.
v2: Pull in a couple of suggestions from Ben and Daniel for
intel_ring_initialized() and not removing the warning (just moving them
to a new home, closer to the error).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Added note to commit message about the small behaviour
change, suggested by Ben Widawsky.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Backmerge of drm-next to resolve a few ugly conflicts and to get a few
fixes from 3.4-rc6 (which drm-next has already merged). Note that this
merge also restricts the stencil cache lra evict policy workaround to
snb (as it should) - I had to frob the code anyway because the
CM0_MASK_SHIFT define died in the masked bit cleanups.
We need the backmerge to get Paulo Zanoni's infoframe regression fix
for gm45 - further bugfixes from him touch the same area and would
needlessly conflict.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJPpvY9AAoJEHm+PkMAQRiGpEoIAJgbu+Y8gITnBK/wh9O6zy3S
5jie5KK4YWdbJsvO58WbNr3CyVIwGIqQ2dUZLiU59aBVLarlGw8xor0MmW+cZwhp
6fBHaf0qDYAV0MZjD+mnnExOiCRyISa2lPmsfu9dAWywh5KGe6/oAP6/qcXIyok3
KZyl3qQf4ENpaZPHwZPXCEkUvtuyHgNiszN+QXEadA3s19Ot4VGe9A3VGw+GNrSm
JqFIq3acQAbKa5BYaqf7TQC02v2FI7//eqt6QHxTqbE6a7LGbTvLfX3HlJ2mnfqa
1R6QHhM4y4OZDHbaMT2raHZ8WuLXzhehJzhP8Co7AHFOKwVKOb5XbcUr2RrukMU=
=HkMd
-----END PGP SIGNATURE-----
Merge tag 'v3.4-rc6' into drm-intel-next
Conflicts:
drivers/gpu/drm/i915/intel_display.c
Ok, this is a fun story of git totally messing things up. There
/shouldn't/ be any conflict in here, because the fixes in -rc6 do only
touch functions that have not been changed in -next.
The offending commits in drm-next are 14415745b2..1fa611065 which
simply move a few functions from intel_display.c to intel_pm.c. The
problem seems to be that git diff gets completely confused:
$ git diff 14415745b2..1fa611065
is a nice mess in intel_display.c, and the diff leaks into totally
unrelated functions, whereas
$git diff --minimal 14415745b2..1fa611065
is exactly what we want.
Unfortunately there seems to be no way to teach similar smarts to the
merge diff and conflict generation code, because with the minimal diff
there really shouldn't be any conflicts. For added hilarity, every
time something in that area changes the + and - lines in the diff move
around like crazy, again resulting in new conflicts. So I fear this
mess will stay with us for a little longer (and might result in
another backmerge down the road).
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The new wait_rendering ioctl also needs to check for an oustanding
lazy request, and we already duplicate that logic at three places. So
extract it.
While at it, also extract the code to check the gpu wedging state to
improve code flow.
v2: Don't use seqno as an outparam (Chris)
v3 by danvet: Kill stale comment and pimp commit message
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Even the horrible gen3 XvMC code has learned to do this
right by the time xf86-video-intel releases learned to do
kernel modesetting. So we can just disallow this.
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... and shove allow_batchbuffer in there. More dragons will
follow suit.
There's the curious case that we allow this for KMS ...
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It turns out throttle had an almost identical bit of code to do the
wait. Now we can call the new helper directly. This is just a bonus,
and not needed for the overall series.
v2: remove irq_get/put which is now in __wait_seqno (Ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's about to go away anyway. Just here to help bisection.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
i915_wait_request is actually a fairly large function encapsulating
quite a few different operations. Because being able to wait on seqnos
in various conditions is useful, extracting that bit of code to a helper
function seems useful
v2: pull the irq_get/put as well (Ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The only time irq_get should fail is during unload or suspend. Both of
these points should try to quiesce the GPU before disabling interrupts
and so the atomic polling should never occur.
This was recommended by Chris Wilson as a way of reducing added
complexity to the polled wait which I introduced in an RFC patch.
09:57 < ickle_> it's only there as a fudge for waiting after irqs
after uninstalled during s&r, we aren't actually meant to hit it
09:57 < ickle_> so maybe we should just kill the code there and fix the breakage
v2: return -ENODEV instead of -EBUSY when irq_get fails
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The waiting_seqno is not terribly useful, and as such we can remove it
so that we'll be able to extract lockless code.
v2: Keep the information for error_state (Chris)
Check if ring is initialized in hangcheck (Chris)
Capture the waiting ring (Chris)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: add some bikeshed to clarify a comment.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This extra bit of interrupt enabling code doesn't belong in the wait
seqno function. If anything we should pull it out to a helper so the
throttle code can also use it. The history is a bit vague, but I am
going to attempt to just dump it, unless someone can argue otherwise.
Removing this allows for a shared lock free wait seqno function. To keep
tabs on this issue though, the IER value is stored on error capture
(recommended by Chris Wilson)
v2: fixed typo EIR->IER (Ben)
Fix some white space (Ben)
Move IER capture to globally instead of per ring (Ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: ier is a 16 bit reg on gen2!]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This originates from a hack by me to quickly fix a bug in an earlier
patch where we needed control over whether or not waiting on a seqno
actually did any retire list processing. Since the two operations aren't
clearly related, we should pull the parameter out of the wait function,
and make the caller responsible for retiring if the action is desired.
The only function call site which did not get an explicit retire_request call
(on purpose) is i915_gem_inactive_shrink(). That code was already calling
retire_request a second time.
v2: don't modify any behavior excepit i915_gem_inactive_shrink(Daniel)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I've missed this one.
v2: Chris Wilson noticed another register.
v3: Color choice improvements.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We always set it so there's no point in checking. We could
instead add a bit that tells us whether gem is actually
initialized (i.e. either kms or gem_init_ioctl called), but
that's imho not worth it.
So just rip it out.
There's a little change in the wait_ring timeout, but we've never
run with anything else than the 60 second timeout, even on dri1
userspace.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This ioctl used in a kms driver is only useful to create massive
havoc.
v2: Bail out with -ENODEV as suggested by Chris Wilson.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The use of the mm_list by deferred-free breaks the following patches to
extend the range of objects tracked. We can simplify things if we just
make the unbind during free uninterrutible.
Note that unbinding should never fail, because we hold an additional
reference on every active object. Only the ilk vt-d workaround breaks
this, but already takes care of not failing by waiting for the gpu to
quiescent non-interruptible. But the existence of the deferred free
list casted some doubts on this theory, hence WARN if the unbind fails
and only then retry non-interruptible.
We can kill this additional code after a release in case the theory is
indeed right and no one has hit that WARN.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Simplify object tracking by removing the inactive but pinned list. The
only place where this was used is for counting the available memory,
which is just as easy performed by checking all objects on the rare
occasions it is required (application startup). For ease of debugging,
we keep the reporting of pinned objects through the error-state and
debugfs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This was only used by one external caller who would just be as happy
with evict-everything, so perform the replacement and make the function
private.
In the process we note that unbinding the inactive list should not fail,
and make it a warning instead.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently, we only bump the inactive LRU of an object when we bind
into the GTT for a page-fault. As the object may be used many times
before its mapping is zapped, we do not mark it as active as
frequently as we should. Userspace should be calling set-to-GTT-domain
before each pointer deference (for synchronous access) and so is a
good place to mark the buffer as active.
Marking the buffer as recently used places it at the end of the
inactive eviction queue, though still before anything with outstanding
rendering. This reduces the likelihood of evicting a buffer that is
going to be used again by the CPU in the near future. This way we can
hopefully avoid to kick out upload buffers right before we use them on
the gpu.
Note that we need to check that the object is not active or pinned,
for otherwise we create havoc on the active/pinned lists, which also
use obj->mm_list.
The active lists are sorted by and evicted in last GPU rendering
order, access by the CPU to a still active buffer therefore does not
affect its eviction ordering. Pinned objects are currently excluded
from eviction, therefore the only list that we need to bump for GTT
access by the CPU is the inactive list.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Added further explanations to the commit message as discussed
on irc.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... and put them to so good use.
Note that there's functional change in vlv clock gating code, we now
no longer spuriously read back the current value of the bit. According
to Bspec the high bits should always read zero, so ORing this in
should have no effect.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Rename obj->tiling_changed to obj->fence_dirty so that it is clear that
it flags when the parameters for an active fence (including the
no-fence) register are changed.
Also, do not set this flag when the object does not have a fence
register allocated currently and the gpu does not depend upon the
unfence. This case works exactly like when a tiled object lost its
fence and hence does not need additional handling for the tiling
change in the code.
v2: Use fence_dirty to better express what the flag tracks and add a few
more details to the comments to serve as a reminder of how the GPU also
uses the unfenced register slot.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add some bikeshed to the commit message about the stricter
use of fence_dirty.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As with one of the earlier patches in the series, we're forced to cast
for copy_[to|from]_user. Again because of the nature of the GEN x86
exclusivity, this should be safe.
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
[danvet: Added some bikeshed.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This continues the theme started with vm_brk() and vm_munmap():
vm_mmap() does the same thing as do_mmap(), but additionally does the
required VM locking.
This uninlines (and rewrites it to be clearer) do_mmap(), which sadly
duplicates it in mm/mmap.c and mm/nommu.c. But that way we don't have
to export our internal do_mmap_pgoff() function.
Some day we hopefully don't have to export do_mmap() either, if all
modular users can become the simpler vm_mmap() instead. We're actually
very close to that already, with the notable exception of the (broken)
use in i810, and a couple of stragglers in binfmt_elf.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We can also take advantage of the new 'no retire' mode for seqno waiting
to avoid having to take a reference on the old fence object whilst
flushing an existing fence.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we have a routine that is able to clear the fences as well as
setup up the register for a tiled object, remove the surplus routines to
clear the fences.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
One clarification that we make is to the existing semantics of
obj->tiling_changed to only mean that we need to update an associated
fence register (including the NO_FENCE when executing an untiled but
fenced GPU command). If we do not have a fence register or pending
fenced GPU access for the object (after put_fence() for example), then
we can clear the tiling_changed flag as any fence will necessarily be
rewritten upon acquisition.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Update the existing architecture specific fence writing routines to
either update the fence to point to a tiled object or to clear them in
preparation to remove the other fence writing routes.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As i915_wait_request() will first check for an already passed seqno,
doing it also in the caller is a waste of space for a cold path.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As the fences are stored in LRU order, we can simply reuse the oldest if
we do not have an unused register.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we now never pipeline a fence update, obj->last_fenced_ring is always
the same as the obj->ring whenever obj->last_fenced_seqno is active, so
remove it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we now no longer track a pipelined fence change, we never use
ring->setup_seqno and can kill it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Step 2 is then to replace the pipelined parameter with NULL and perform
constant folding to remove dead code.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We never succeeded in getting pipelined fencing to work (unresolved
spurious GPU hangs), so begin the process of dismantling and removal
the broken code.
Step 1 is the removal of the pipeline parameter to get_fence().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For some reason snb has 2 fields to set ppgtt cacheability. This one
here does not exist on gen7.
This might explain why ppgtt wasn't a win on snb like on ivb - not
enough pte caching.
v2: Fixup rebase fail.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Bspec says that we need to set this: vol1c.3 "Blitter Command
Streamer", Section 1.1.2.1 "GAB_CTL_REG - GAB Unit Control Register".
We don't really rely on pagefaults, but who knows what this all
affects.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEbBAABAgAGBQJPi3XOAAoJEHm+PkMAQRiGnsUH9RjHwH4YFVyuP/DKtKa6zs74
wqkpT15yITQ5WWMog4JaJFFg5rJCUd8QZr7AS/HSn0ijDyZX5VU7Rcs9cMudDzNR
H/5K/AscS4fjb0HwWVqoltTWHRb9QGSwVN3+E3VCDLt9P89YJ0o3QztkkuEX5dkZ
jc7reVXTfRnCcILEa9jleOzrn+OLM3j/jAjQ2hGunl8EDLzD4b17HHPoli4jEZ/5
5ibpSVsPD+AqzN+glbXvYjVItl12D0IQos/JdOwfuZriCVWLxysSSwHZTbPCyvBZ
LHH4HR5T+XLSXbjJeNkUFHLzqU+d5gVRadIoWtJCxqxFjKbOs2YtzJ5Ai0nDiw==
=kTkC
-----END PGP SIGNATURE-----
Merge tag 'v3.4-rc3' into drm-intel-next-queued
Backmerge Linux 3.4-rc3 into drm-intel-next to resolve a few things
that conflict/depend upon patches in -rc3:
- Second part of the Sandybridge workaround series - it changes some
of the same registers.
- Preparation for Chris Wilson's fencing cleanup - we need the fix
from -rc3 merged before we can move around all that code.
- Resolve the gmbus conflict - gmbus has been disabled in 3.4 again,
but should be enabled on all generations in 3.5.
Conflicts:
drivers/gpu/drm/i915/intel_i2c.c
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... we will botch up the bit17 swizzling. Furthermore tiled pwrite is
a (now) unused slowpath, so no one really cares.
This fixes the last swizzling issues I have with i-g-t on my bit17
swizzling i915G. No regression, it's been broken since the dawn of
gem, but it's nice for regression tracking when really _all_ i-g-t
tests work.
Actually this is not true, Chris Wilson noticed while reviewing this
patch that the commit
commit d9e86c0ee6
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed Nov 10 16:40:20 2010 +0000
drm/i915: Pipelined fencing [infrastructure]
contained a functional change that broke things.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Waiting for seqno-1 in our object synchronization code is an
implementation detail given how we've decided to do the waits within the
rest of our code.
Requested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This fixes a long standing issue where emitting the semaphore updates
may have failed, but we've already updated our internal data structure.
Reported-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When I extracted the synchronization code for implementing semaphorified
pageflips (74f5f6e0), I neglected the non pipelined case which also
calls this code. The modesetting code wants to make sure the object has
finished rendering to the frame before configuring the scanout (ie.
non-pipelined case).
As a result of a follow on discussion on IRC, I've decided to add a
comment about the function itself which received much inspiration from
Chris as well. So really, this patch was ghost-written by Chris :).
Reported-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Similar to allowing a buffer to be simultaneously read by the GPU and
through the GTT, we wish to allow readback of the pages through the CPU
domain whilst they are also being read by the GPU. Domain coherency
is managed by allowing multiple readers, but only a single writer.
This is used by mesa for its program cache which it may search for every
new program every frame and then renews should it need to add. During
renewal, mesa copies the program bo currently executing through a CPU
mapping onto the new bo. This patch allows the search and that copy to
proceed without causing a stall on the current batch.
Testcase: i-g-t/tests/gem_cpu_concurrent_blit
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In theory this will have performance and power improvements. Performance
because we don't need to stall when the scanout BO is busy, and power
because we don't have to stall when the BO is busy (and the ring can
even go to sleep if the HW supports it).
v2:
squash 2 patches into 1 (me)
un-inline the enable_semaphores function (Daniel)
remove comment about SNB hangs from i915_gem_object_sync (Chris)
rename intel_enable_semaphores to i915_semaphore_is_enabled (me)
removed page flip comment; "no why" (Chris)
To address other comments from Daniel (irc):
update the comment to say 'vt-d is crap, don't enable semaphores'
- I think you misinterpreted Chris' comment, it already exists.
checking out whether we can pageflip on the render ring on ivb (didn't
work on early silicon)
- We don't want to enable workarounds for early silicon unless we have
to.
- I can't find any references in the docs about this.
optionally use it if the fb is already busy on the render ring
- This should be how the code already worked, unless I am
misunderstanding your meaning.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By simplifying the rules to calling get_fence when writing to the
through the GTT in a tiled manner, and calling put_fence before writing
to the object through the GTT in a linear manner, the code becomes
clearer and there is less chance of making a mistake.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[danvet: fixed up conflict with ppgtt code and spelling in a new
comment.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel Vetter wrote
First pull request for 3.5-next, slightly large than usual because new
things kept coming in since the last pull for 3.4.
Highlights:
- first batch of hw enablement for vlv (Jesse et al) and hsw (Eugeni). pci
ids are not yet added, and there's still quite a few patches to merge
(mostly modesetting). To make QA easier I've decided to merge this stuff
in pieces.
- loads of cleanups and prep patches spurred by the above. Especially vlv
is a real frankenstein chip, but also hsw is stretching our driver's
code design. Expect more to come in this area for 3.5.
- more gmbus fixes, cleanups and improvements by Daniel Kurtz. Again,
there are more patches needed (and some already queued up), but I wanted
to split this a bit for better testing.
- pwrite/pread rework and retuning. This series has been in the works for
a few months already and a lot of i-g-t tests have been created for it.
Now it's finally ready to be merged. Note that one patch in this series
touches include/pagemap.h, that patch is acked-by akpm.
- reduce mappable pressure and relocation throughput improvements from
Chris.
- mmap offset exhaustion mitigation by Chris Wilson.
- a start at figuring out which codepaths in our messy dri1/ums+gem/kms
driver we actually need to support by bailing out of unsupported case.
The driver now refuses to load without kms on gen6+ and disallows a few
ioctls that userspace never used in certain cases. More of this will
definitely come.
- More decoupling of global gtt and ppgtt.
- Improved dual-link lvds detection by Takashi Iwai.
- Shut up the compiler + plus fix the fallout (Ben)
- Inverted panel brightness handling (mostly Acer manages to break things
in this way).
- Small fixlets and adjustements and some minor things to help debugging.
Regression-wise QA reported quite a few issues on ivb, but all of them
turned out to be hw stability issues which are already fixed in
drm-intel-fixes (QA runs the nightly regression tests on -next alone,
without -fixes automatically merged in). There's still one issue open on
snb, it looks like occlusion query writes are not quite as cache coherent
as we've expected. With some of the pwrite adjustements we can now
reliably hit this. Kernel workaround for it is in the works."
* 'drm-intel-next' of git://people.freedesktop.org/~danvet/drm-intel: (101 commits)
drm/i915: VCS is not the last ring
drm/i915: Add a dual link lvds quirk for MacBook Pro 8,2
drm/i915: make quirks more verbose
drm/i915: dump the DMA fetch addr register on pre-gen6
drm/i915/sdvo: Include YRPB as an additional TV output type
drm/i915: disallow gem init ioctl on ilk
drm/i915: refuse to load on gen6+ without kms
drm/i915: extract gt interrupt handler
drm/i915: use render gen to switch ring irq functions
drm/i915: rip out old HWSTAM missed irq WA for vlv
drm/i915: open code gen6+ ring irqs
drm/i915: ring irq cleanups
drm/i915: add SFUSE_STRAP registers for digital port detection
drm/i915: add WM_LINETIME registers
drm/i915: add WRPLL clocks
drm/i915: add LCPLL control registers
drm/i915: add SSC offsets for SBI access
drm/i915: add port clock selection support for HSW
drm/i915: add S PLL control
drm/i915: add PIXCLK_GATE register
...
Conflicts:
drivers/char/agp/intel-agp.h
drivers/char/agp/intel-gtt.c
drivers/gpu/drm/i915/i915_debugfs.c
This fixes a resume regression introduced in
commit 7dd4906586
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed Mar 21 10:48:18 2012 +0000
drm/i915: Mark untiled BLT commands as fenced on gen2/3
which fixed fencing tracking for untiled blt commands.
A side effect of that patch was that now also untiled objects have a
non-zero obj->last_fenced_seqno to track when a fence can be set up
after a pipelined tiling change. Unfortunately this was only cleared
by the fence setup and teardown code, resulting in tons of untiled but
inactive objects with non-zero last_fenced_seqno.
Now after resume we completely reset the seqno tracking, both on the
driver side (by setting dev_priv->next_seqno = 1) and on the hw side
(by allocating a new hws page, which contains the seqnos). Hilarity
and indefinite waits ensued from the stale seqnos in
obj->last_fenced_seqno from before the suspend.
The fix is to properly clear the fencing tracking state like we
already do for the normal gpu rendering while moving objects off the
active list.
Reported-and-tested-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Jiri Slaby <jslaby@suse.cz>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ums is already disabled, but on ilk we can additionally disable gem
initialization when using user mode setting. Upstream never support
ilk without kernel modesetting and not even the RHEL ilk ums backport
needs gem - that driver is based on xf86-video-intel version 2.2,
which is pre-gem.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The BLT commands on gen2/3 utilize the fence registers and so we cannot
modify any fences for the object whilst those commands are in flight.
Currently we marked tiled commands as occupying a fence, but forgot to
restrict the untiled commands from preventing a fence being assigned
before they were completed.
One side-effect is that we ten have to double check that a fence was
allocated for a fenced buffer during move-to-active.
Reported-by: Jiri Slaby <jirislaby@gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=43427
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=47990
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Testcase: i-g-t/tests/gem_tiled_after_untiled_blt
Tested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The ppgtt page directory lives in a snatched part of the gtt pte
range. Which naturally gets cleared on hibernate when we pull the
power. Suspend to ram (which is what I've tested) works because
despite the fact that this is a mmio region, it is actually back by
system ram.
Fix this by moving the page directory setup code to the ppgtt init
code (which gets called on resume).
This fixes hibernate on my ivb and snb.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Haven't seen this yet, but it doesn't hurt.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Beside helping the compiler untangle this maze they double-up as
documentation for which parts of the code aren't performance-critical
but just around to keep old (but already dead-slow) userspace from
breaking.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The issue is that with inline clflushing the clflushing isn't properly
swizzled. Fix this by
- always clflushing entire 128 byte chunks and
- unconditionally flush before writes when swizzling a given page.
We could be clever and check whether we pwrite a partial 128 byte
chunk instead of a partial cacheline, but I've figured that's not
worth it.
Now the usual approach is to fold this into the original patch series, but
I've opted against this because
- this fixes a corner case only very old userspace relies on and
- I'd like to not invalidate all the testing the pwrite rewrite has gotten.
This fixes the regression notice by tests/gem_tiled_partial_prite_pread
from i-g-t. Unfortunately it doesn't fix the issues with partial pwrites to
tiled buffers on bit17 swizzling machines. But that is also broken without
the pwrite patches, so likely a different issue (or a problem with the
testcase).
v2: Simplify the patch by dropping the overly clever partial write
logic for swizzled pages.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915 wants to read/write more than one page in its fastpath
and hence needs to prefault more than PAGE_SIZE bytes.
Add new functions in filemap.h to make that possible.
Also kill a copy&pasted spurious space in both functions while at it.
v2: As suggested by Andrew Morton, add a multipage parameter to both
functions to avoid the additional branch for the pagemap.c hotpath.
My gcc 4.6 here seems to dtrt and indeed reap these branches where not
needed.
v3: Becaus I couldn't find a way around adding a uaddr += PAGE_SIZE to
the filemap.c hotpaths (that the compiler couldn't remove again),
let's go with separate new functions for the multipage use-case.
v4: Adjust comment to CodingStlye and fix spelling.
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
While moving around things, this two functions slowly grew out of any
sane bounds. So extract a few lines that do the copying and
clflushing. Also add a few comments to explain what's going on.
v2: Again do s/needs_clflush/needs_clflush_after/ in the write paths
as suggested by Chris Wilson.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's around 20% faster.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's too expensive to move it around just for that pwrite, especially
when we're trashing on the mappable gtt part like crazy.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In micro-benchmarking of the usual pwrite use-pattern of alternating
pwrites with gtt domain reads from the gpu, this yields around 30%
improvement of pwrite throughput across all buffers size. The trick is
that we can avoid clflush cachelines that we will overwrite completely
anyway.
Furthermore for partial pwrites it gives a proportional speedup on top
of the 30% percent because we only clflush back the part of the buffer
we're actually writing.
v2: Simplify the clflush-before-write logic, as suggested by Chris
Wilson.
v3: Finishing touches suggested by Chris Wilson:
- add comment to needs_clflush_before and only set this if the bo is
uncached.
- s/needs_clflush/needs_clflush_after/ in the write paths to clearly
differentiate it from needs_clflush_before.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The pagemap.h prefault helpers do the prefaulting by simply writing
some data into every page. Hence we should not prefault when we're not
yet commited to to actually writing data to userspace. The problem is
now that
- we can't prefault while holding dev->struct_mutex for we could
deadlock with our own pagefault handler
- we need to grab dev->struct_mutex before copying to sync up with any
outsanding gpu writes.
Therefore only prefault when we're dropping the lock the first time in
the pread slowpath - at that point we're committed to the write, don't
wait on the gpu anymore and hence won't return early (with e.g.
-EINTR).
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the proper prefault, it's extremely unlikely that we fall back
to the gtt slowpath.
So just kill it and use the shmem_pwrite path as fallback.
To further clean up the code, move the preparatory gem calls into the
respective pwrite functions. This way the gtt_fast->shmem fallback
is much more obvious.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This speeds up pwrite and pread from ~120 µs ro ~100 µs for
reading/writing 1mb on my snb (if the backing storage pages
are already pinned, of course).
v2: Chris Wilson pointed out a glaring page reference bug - I've
unconditionally dropped the reference. With that fixed (and the
associated reduction of dirt in dmesg) it's now even a notch faster.
v3: Unconditionaly grab a page reference when dropping
dev->struct_mutex to simplify the code-flow.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
~120 µs instead fo ~210 µs to write 1mb on my snb. I like this.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
No longer needed.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is obviously gonna slow down pread. But for a half-way realistic
micro-benchmark, it doesn't matter: Non-broken userspace reads back
data from the gpu once before the gpu again dirties it.
So all this ranged clflush tracking is just a waste of time.
No pread performance change (neglecting the dumb benchmark of
constantly reading the same data) measured.
As an added bonus, this avoids clflush on read on coherent objects.
Which means that partial preads on snb are now roughly 4x as fast.
This will be usefull for e.g. the libva encoder - when I finally get
around to fix that up.
v2: Properly sync with the gpu on LLC machines.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the previous rewrite, they've become essential identical.
v2: Simplify the page_do_bit17_swizzling logic as suggested by Chris
Wilson.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the previous rewrite, they've become essential identical.
v2: Simplify the page_do_bit17_swizzling logic as suggested by Chris
Wilson.
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We try to avoid writing the relocations through the uncached GTT, if the
buffer is currently in the CPU write domain and so will be flushed out to
main memory afterwards anyway. Also on SandyBridge we can safely write
to the pages in cacheable memory, so long as the buffer is LLC mapped.
In either of these cases, we therefore do not need to force the
reallocation of the buffer into the mappable region of the GTT, reducing
the aperture pressure.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... because this is what it actually doesn now that we have the global
gtt vs. ppgtt split.
Also move it to the other global gtt functions in i915_gem_gtt.c
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we discard a buffer due to memory pressure, also release its alloted
mmap address space. As it may be sometime before userspace wakes up
and notices that it has buffers to purge from its cache, we may waste
valuable address space on unusable objects for a period of time.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=47738
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Introduced in commit 8461d226 and 8c59967c
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: s/fix/shut up/ in the commit msg.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that everything is in place, only bind to the global gtt
when actually required. Patch split-up suggested by Chris Wilson.
Reviewed-and-tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And track the existence of such a binding similar to the aliasing
ppgtt case. Speeds up binding/unbinding in the common case where we
only need a ppgtt binding (which is accessed in a cpu coherent fashion
by the gpu) and no gloabl gtt binding (which needs uc writes for the
ptes).
This patch just puts the required tracking in place.
v2: Check that global gtt mappings exist in the error_state capture
code (with Chris Wilson's llc reloc patches batchbuffers are no longer
relocated as mappable in all situations, so this matters). Suggested
by Chris Wilson.
v3: Adapted to Chris' latest llc-reloc patches.
v4: Fix a bug in the i915 error state capture code noticed by Chris
Wilson.
Reviewed-and-tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Note that there's a functional change buried in this patch wrt the ilk
dmar workaround: We now only idle the gpu while tearing down the dmar
mappings, not while clearing the gtt. Keeping the current semantics
would have made for some really ugly code and afaik the issue is only
with the dmar unmapping that needs a fully idle gpu.
Reviewed-and-tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This error message has since been superseded by the hangcheck, and does
not add any salient information beyond that already printed by hangcheck
discovering the GPU hang that lead to i915_wait_request() bombing out in
the first place.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By recording the location of every request in the ringbuffer, we know
that in order to retire the request the GPU must have finished reading
it and so the GPU head is now beyond the tail of the request. We can
therefore provide a conservative estimate of where the GPU is reading
from in order to avoid having to read back the ring buffer registers
when polling for space upon starting a new write into the ringbuffer.
A secondary effect is that this allows us to convert
intel_ring_buffer_wait() to use i915_wait_request() and so consolidate
upon the single function to handle the complicated task of waiting upon
the GPU. A necessary precaution is that we need to make that wait
uninterruptible to match the existing conditions as all the callers of
intel_ring_begin() have not been audited to handle ERESTARTSYS
correctly.
By using a conservative estimate for the head, and always processing all
outstanding requests first, we prevent a race condition between using
the estimate and direct reads of I915_RING_HEAD which could result in
the value of the head going backwards, and the tail overflowing once
again. We are also careful to mark any request that we skip over in
order to free space in ring as consumed which provides a
self-consistency check.
Given sufficient abuse, such as a set of unthrottled GPU bound
cairo-traces, avoiding the use of I915_RING_HEAD gives a 10-20% boost on
Sandy Bridge (i5-2520m):
firefox-paintball 18927ms -> 15646ms: 1.21x speedup
firefox-fishtank 12563ms -> 11278ms: 1.11x speedup
which is a mild consolation for the performance those traces achieved from
exploiting the buggy autoreported head.
v2: Add a few more comments and make request->tail a conservative
estimate as suggested by Daniel Vetter.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: resolve conflicts with retirement defering and the lack of
the autoreport head removal (that will go in through -fixes).]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently we reserve seqnos only when we emit the request to the ring
(by bumping dev_priv->next_seqno), but start using it much earlier for
ring->oustanding_lazy_request. When 2 threads compete for the gpu and
run on two different rings (e.g. ddx on blitter vs. compositor)
hilarity ensued, especially when we get constantly interrupted while
reserving buffers.
Breakage seems to have been introduced in
commit 6f392d5486
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat Aug 7 11:01:22 2010 +0100
drm/i915: Use a common seqno for all rings.
This patch fixes up the seqno reservation logic by moving it into
i915_gem_next_request_seqno. The ring->add_request functions now
superflously still return the new seqno through a pointer, that will
be refactored in the next patch.
Note that with this change we now unconditionally allocate a seqno,
even when ->add_request might fail because the rings are full and the
gpu died. But this does not open up a new can of worms because we can
already leave behind an outstanding_request_seqno if e.g. the caller
gets interrupted with a signal while stalling for the gpu in the
eviciton paths. And with the bugfix we only ever have one seqno
allocated per ring (and only that ring), so there are no ordering
issues with multiple outstanding seqnos on the same ring.
v2: Keep i915_gem_get_seqno (but move it to i915_gem.c) to make it
clear that we only have one seqno counter for all rings. Suggested by
Chris Wilson.
v3: As suggested by Chris Wilson use i915_gem_next_request_seqno
instead of ring->oustanding_lazy_request to make the follow-up
refactoring more clearly correct. Also improve the commit message
with issues discussed on irc.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45181
Tested-by: Nicolas Kalkhof nkalkhof()at()web.de
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We want to unconditionally enable ppgtt for two reasons:
- Windows uses this on snb and later.
- We need the basic hw support to work before we can think about real
per-process address spaces and other cool features we want.
But Chris Wilson was complaining all over irc and intel-gfx that this
will blow up if we don't have a module option to disable it. Hence add
one, to prevent this.
ppgtt support seems to slightly change the timings and make crashy
things slightly more or less crashy. Now in my testing and the testing
this got on troublesome snb machines, it seems to have improved things
only. But on ivb it makes quite a few crashes happen much more often,
see
https://bugs.freedesktop.org/show_bug.cgi?id=41353
Luckily Eugeni Dodonov seems to have a set of workarounds that fix
this issue.
v2: Don't try to enable ppgtt on pre-snb.
v3: Pimp commit message and make Chris Wilson less grumpy by adding a
module option.
v4: New try at making Chris Wilson happy.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This adds support to bind/unbind objects and wires it up. Objects are
only put into the ppgtt when necessary, i.e. at execbuf time.
Objects are still unconditionally put into the global gtt.
v2: Kill the quick hack and explicitly pass cache_level to ppgtt_bind
like for the global gtt function. Noticed by Chris Wilson.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On gen5 we also need to correctly set up swizzling in the display
scanout engine, but only there. Consolidate this into the same
function.
This has a small effect on ums setups - the kernel now also sets this
bit in addition to userspace setting it. Given that this code only
runs when userspace either can't (resume, gpu reset) or explicitly
won't(gem_init) touch the hw this shouldn't have an adverse effect.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We have to do this manually. Somebody had a Great Idea.
I've measured speed-ups just a few percent above the noise level
(below 5% for the best case), but no slowdows. Chris Wilson measured
quite a bit more (10-20% above the usual snb variance) on a more
recent and better tuned version of sna, but also recorded a few
slow-downs on benchmarks know for uglier amounts of snb-induced
variance.
v2: Incorporate Ben Widawsky's preliminary review comments and
elaborate a bit about the performance impact in the changelog.
v3: Add a comment as to why we don't need to check the 3rd memory
channel.
v4: Fixup whitespace.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like for shmem_pwrite_slow. The only difference is that because we
read data, we can leave the fetched cachelines in the cpu: In the case
that the object isn't in the cpu read domain anymore, the clflush for
the next cpu read domain invalidation will simply drop these
cachelines.
slow_shmem_bit17_copy is now ununsed, so kill it.
With this patch tests/gem_mmap_gtt now actually works.
v2: add __ to copy_to_user_swizzled as suggested by Chris Wilson.
v3: Fixup the swizzling logic, it swizzled the wrong pages.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=38115
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of get_user_pages, because that fails on non page-backed
user addresses like e.g. a gtt mapping of a bo.
To get there essentially copy the vfs read path into pagecache. We
can't call that right away because we have to take care of bit17
swizzling. To not deadlock with our own pagefault handler we need
to completely drop struct_mutex, reducing the atomicty-guarantees
of our userspace abi. Implications for racing with other gem ioctl:
- execbuf, pwrite, pread: Due to -EFAULT fallback to slow paths there's
already the risk of the pwrite call not being atomic, no degration.
- read/write access to mmaps: already fully racy, no degration.
- set_tiling: Calling set_tiling while reading/writing is already
pretty much undefined, now it just got a bit worse. set_tiling is
only called by libdrm on unused/new bos, so no problem.
- set_domain: When changing to the gtt domain while copying (without any
read/write access, e.g. for synchronization), we might leave unflushed
data in the cpu caches. The clflush_object at the end of pwrite_slow
takes care of this problem.
- truncating of purgeable objects: the shmem_read_mapping_page call could
reinstate backing storage for truncated objects. The check at the end
of pwrite_slow takes care of this.
v2:
- add missing intel_gtt_chipset_flush
- add __ to copy_from_user_swizzled as suggest by Chris Wilson.
v3: Fixup bit17 swizzling, it swizzled the wrong pages.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The gtt_pwrite slowpath grabs the userspace memory with
get_user_pages. This will not work for non-page backed memory, like a
gtt mmapped gem object. Hence fall throuh to the shmem paths if we hit
-EFAULT in the gtt paths.
Now the shmem paths have exactly the same problem, but this way we
only need to rearrange the code in one write path.
v2: v1 accidentaly falls back to shmem pwrite for phys objects. Fixed.
v3: Make the codeflow around phys_pwrite cleara as suggested by Chris
Wilson.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The original intention of comparing the bo against the mappable GTT
limits was to prevent a subsequent faulting of the bo into the GTT from
clearing the entire GTT in vain. However, that was clearly a cut'n'paste
mistake as a CPU mapping never binds the bo into the aperture. Whilst
there may be some merit to limiting the maximum size of the bo to
something that can be utilized by the GPU, that limit itself does not
belong as a safeguard to mmapping the bo, so remove the check entirely.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the fence accounting fixed up in the previous commit not finding
enough fences is a fatal error and userspace bug. Trashing the entire
gtt is not gonna turn up that missing fence, so don't to this by
returning another error thatn ENOSPC.
This has the added benefit that it's easier to distinguish fence
accounting errors from gtt space accounting issues.
TTM serves as precendence for the EDEADLK error code - it returns it
when the reservation code needs resources already blocked by the
current reservation.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order to correctly account for reserving space in the GTT and fences
for a batch buffer, we need to independently track whether the fence is
pinned due to a fenced GPU access in the batch or whether the buffer is
pinned in the aperture. Currently we count the fenced as pinned if the
buffer has already been seen in the execbuffer. This leads to a false
accounting of available fence registers, causing frequent mass evictions.
Worse, if coupled with the change to make i915_gem_object_get_fence()
report EDADLK upon fence starvation, the batchbuffer can fail with only
one fence required...
Fixes intel-gpu-tools/tests/gem_fenced_exec_thrash
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=38735
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Paul Neumann <paul104x@yahoo.de>
[danvet: Resolve the functional conflict with Jesse Barnes sprite
patches, acked by Chris Wilson on irc.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Sometimes it may be the case when we idle the gpu or wait on something
we don't actually want to process the retiring list. This patch allows
callers to choose the behavior.
Reviewed-by: Keith Packard <keithp@keithp.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
LLC is not SNB/IVB-specific, so we should check for it in a more generic
way.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The waits we do here are generally so short that sleeping is a bad
idea unless we have an IRQ to wake us up. Improves regression test
performance from 18 minutes to 3.5 minutes on gen7, which is now
consistent with the previous generation.
Signed-off-by: Eric Anholt <eric@anholt.net>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
As a workaround for IRQ synchronization issues in the gen7 BLT ring,
we want to turn the two wait functions into polling loops.
Signed-off-by: Eric Anholt <eric@anholt.net>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
This reverts commit eb1711bb94.
It blows up the i915 seqno tracking, resulting in the
BUG_ON(seqno == 0);
in i915_wait_request() triggering, which will cause lock-ups.
See for example
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/903010https://lkml.org/lkml/2011/12/14/395
Reported-requested-and-tested-by: Dirk Hohndel <dirk@hohndel.org>
Reported-by: Richard Eames <Richard.Eames@flinders.edu.au>
Reported-by: Rocko Requin <rockorequin@hotmail.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Keith Packard <keithp@keithp.com>
Cc: Eric Anholt <eric@anholt.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The recursion loop goes retire_requests->unbind->gpu_idle->retire_reqeusts.
Every time we go through this we need a
- active object that can be retired
- and there are no other references to that object than the one from
the active list, so that it gets unbound and freed immediately.
Otherwise the recursion stops. So the recursion is only limited by the
number of objects that fit these requirements sitting in the active list
any time retire_request is called.
Issue exercised by tests/gem_unref_active_buffers from i-g-t.
There's been a decent bikeshed discussion whether it wouldn't be
better to pass around a flag, but imo this is o.k. for such a limited
case that only supports a w/a.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=42180
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson>
[ickle- we built better bikesheds, but this keeps the rain off for now]
Tested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
A call to i915_add_request() has been made in function i915_gem_busy_ioctl(). i915_add_request can fail,
so in it's exit path previously allocated memory needs to be freed.
Signed-off-by: Rakib Mullick <rakib.mullick@gmail.com>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
IVB supports these bits as well.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
In preparation of to support 32 fences on Ivybdrigde.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
I've been seeing memory leaks on my system in the form of large
(300-400MB) GEM objects created by now-dead processes laying around
clogging up memory. I usually notice when it gets to about 1.2GB of
them. Hopefully this clears up the issue, but I just found this bug
by inspection.
Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: stable@kernel.org
Signed-off-by: Keith Packard <keithp@keithp.com>
[Description from: Daniel Vetter]
I've just discussed this quickly with Chris on irc and it's probably
best to just kill the list_empty early bailout. gpu_idle isn't a
fastpath, so who cares. One candidate where we emit commands to the ring
without adding anything onto these lists is e.g. pageflip. There are
probably more.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
We currently only round up the userspace size to the next page. We
assume that userspace hasn't made a mistake and requested a zero-length
gem object and all through our internal code we then presume that every
object is backed by at least a single page. Fix that oversight and
report EINVAL back to userspace if they try to create a zero length
object.
[danvet: This fixes tests/gem_bad_length]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Keith Packard <keithp@keithp.com>
Use the helper function already employed by the pwrite/pread
functions.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
Various issues involved with the space character were generating
warnings in the checkpatch.pl file. This patch removes most of those
warnings.
Signed-off-by: Akshay Joshi <me@akshayjoshi.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
Failing to pin a scanout buffer will most likely lead to a black
screen, so if the GPU is wedged, then just let the pin happen and hope
that things work out OK.
v2: Just ignore any error from i915_gem_object_wait_rendering, as
suggested by Chris Wilson
Signed-off-by: Keith Packard <keithp@keithp.com>
Align unfenced buffers on older hardware to the power-of-two object
size. The docs suggest that it should be possible to align only to a
power-of-two tile height, but using the already computed fence size is
easier and always correct. We also have to make sure that we unbind
misaligned buffers upon tiling changes.
In order to prevent a repetition of this bug, we change the interface
to the alignment computation routines to force the caller to provide
the requested alignment and size of the GTT binding rather than assume
the current values on the object.
Reported-and-tested-by: Sitosfe Wheeler <sitsofe@yahoo.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=36326
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
Provide a parameter to disable hanghcheck. This is useful mostly for
developers trying to debug known problems, and probably should not be
touched by normal users.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Keith Packard <keithp@keithp.com>
Konstantin Belousov pointed out that 4697995b98 replaced the generic
i915_driver_irq_*install() functions with chipset specific routines
accessible only through driver->irq_*install(). So update the sanity
check in i915_request_wait() to match.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
The interface to ->truncate_range is changing very slightly: once "tmpfs:
take control of its truncate_range" has been applied, this can be applied.
For now there is only a slight inefficiency while this remains unapplied,
but it will soon become essential for managing shmem's use of swap.
Change i915_gem_object_truncate() to use shmem_truncate_range() directly:
which should also spare i915 later change if we switch from
inode_operations->truncate_range to file_operations->fallocate.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Keith Packard <keithp@keithp.com>
Cc: Dave Airlie <airlied@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Soon tmpfs will stop supporting ->readpage and read_cache_page_gfp(): once
"tmpfs: add shmem_read_mapping_page_gfp" has been applied, this patch can
be applied to ease the transition.
Make i915_gem_object_get_pages_gtt() use shmem_read_mapping_page_gfp() in
the one place it's needed; elsewhere use shmem_read_mapping_page(), with
the mapping's gfp_mask properly initialized.
Forget about __GFP_COLD: since tmpfs initializes its pages with memset,
asking for a cold page is counter-productive.
Include linux/shmem_fs.h also in drm_gem.c: with shmem_file_setup() now
declared there too, we shall remove the prototype from linux/mm.h later.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Keith Packard <keithp@keithp.com>
Cc: Dave Airlie <airlied@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Even if the object is no longer in the GTT domain, there may still be
a user space mapping which needs to be released.
Without this fix, render-based text (mostly in firefox) would
occasionally get corrupted when the system was under load.
Signed-off-by: Keith Packard <keithp@keithp.com>
This reverts commit 4a684a4117.
Userland has always been required to set the object's domain to GTT
before using it through a GTT mapping, it's not something that the
kernel is supposed to enforce. (The pagefault support is so that we
can handle multiple mappings without userland having to pin across
them, not so that userland can use GTT after GPU domains without
telling the kernel).
Fixes 19.2% +/- 0.8% (n=6) performance regression in cairo-gl
firefox-talos-gfx on my T420 latop.
Signed-off-by: Keith Packard <keithp@keithp.com>
It seems to me that we are leaking 'user_pages' in
drivers/gpu/drm/i915/i915_gem.c::i915_gem_shmem_pread_slow() if
read_cache_page_gfp() fails.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Improves full-screen openarena on my laptop 20.3% +/- 4.0% (n=3)
Improves 800x600 nexuiz on my laptop 12.3% +/- 0.1% (n=3)
We have more room to improve with doing LLC caching for display using
GFDT, and in doing LLC+MLC caching, but this was an easy performance
win and incremental improvement toward those two.
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The simplest and common method for ensuring scanout coherency on all
chipsets is to mark the scanout buffers as uncached (and for
userspace to remember to flush the render cache every so often).
We can improve upon this for later generations by marking scanout
objects as GFDT and only flush those cachelines when required. However,
we start simple.
[v2: Move the set to uncached above the clflush. Otherwise, we'd skip
the clflush and try to scan out data that was still sitting in the
cache.]
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need to perform a few operations in order to move the object into the
display plane (where it can be accessed coherently by the display
engine) that are important for future safety to forbid whilst pinned. As a
result, we want to need to perform some of the operations before pinning,
but some are required once we have been bound into the GTT. So combine
the pinning performed by all the callers with set_to_display_plane(), so
this complication is contained within the single function.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[anholt v2: Don't forget that when going from cached to uncached, we
haven't been tracking the write domain from the CPU perspective, since
we haven't needed it for GPU coherency.]
[ickle v3: We also need to make sure we relinquish any fences on older
chipsets and clear the GTT for sane domain tracking.]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like its siblings finish_gpu(), this function clears the object from the
GTT domain forcing it to be trigger a domain invalidation should we ever
need to use via the GTT again.
Note that the most important side-effect of finishing the GTT domain
(aside from clearing the tracking read/write domains) is that it imposes
an memory barrier so that all accesses are complete before it returns,
which is important if you intend to be modifying translation tables
shortly afterwards. The second most important side-effect is that it
tears down the GTT mappings forcing a page-fault and invalidation on
next user access to the object.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... reincarnated from i915_gem_object_flush_gpu(). The semantic
difference is that after calling finish_gpu() the object no longer
resides in any GPU domain, and so will cause the GPU caches to be
invalidated if it is ever used again.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A tile on gen2 has a size of 2kb, stride of 128 bytes and 16 rows.
Userspace was broken and assumed 8 rows. Chris Wilson noted that the
kernel unfortunately can't reliable check that because libdrm rounds
up the size to the next bucket.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
Convert our open coded offset_in_page() to the common macro.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
Change each shrinker's API by consolidating the existing parameters into
shrink_control struct. This will simplify any further features added w/o
touching each file of shrinker.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: fix warning]
[kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API]
[akpm@linux-foundation.org: fix xfs warning]
[akpm@linux-foundation.org: update gfs2]
Signed-off-by: Ying Han <yinghan@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Pavel Emelyanov <xemul@openvz.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The registers are the same as on Sandybridge. Fixes scrambled display
in X when it does software drawing to the GTT, and scans the results
out as tiled.
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
This is once less place to miss a new INTEL_INFO(dev)->gen update now.
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
Rely on the GPU snooping into the CPU cache for appropriately bound
objects on MI_FLUSH. Or perhaps one day we will have a cache-coherent
CPU/GPU package...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
... to clarify just how we use it inside the driver and remove the
confusion of the poorly matching agp_type names. We still need to
translate through agp_type for interface into the fake AGP driver.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
We always skipped flushing the BLT ring if the request flush did not
include the RENDER domain. However, this neglects that we try to flush
the COMMAND domain after every batch and before the breadcrumb interrupt
(to make sure the batch is indeed completed prior to the interrupt
firing and so insuring CPU coherency). As a result of the missing flush,
incoherency did indeed creep in, most notable when using lots of command
buffers and so potentially rewritting an active command buffer (i.e.
the GPU was still executing from it even though the following interrupt
had already fired and the request/buffer retired).
As all ring->flush routines now have the same preconditions, de-duplicate
and move those checks up into i915_gem_flush_ring().
Fixes gem_linear_blit.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=35284
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: mengmeng.meng@intel.com
... even though it was disabled. A mistake in the handling of fence reuse
caused us to skip the vital delay of waiting for the object to finish
rendering before changing the register. This resulted in us changing the
fence register whilst the bo was active and so causing the blits to
complete using the wrong stride or even the wrong tiling. (Visually the
effect is that small blocks of the screen look like they have been
interlaced). The fix is to wait for the GPU to finish using the memory
region pointed to by the fence before changing it.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=34584
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[Note for 2.6.38-stable, we need to reintroduce the interruptible passing]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Dave Airlie <airlied@linux.ie>
When i915_gem_retire_requests_ring calls i915_gem_request_remove_from_client,
the client_list for that request may already be removed in i915_gem_release.
So we may call twice list_del(&request->client_list), resulting in an
oops like this report:
[126167.230394] BUG: unable to handle kernel paging request at 00100104
[126167.230699] IP: [<f8c2ce44>] i915_gem_retire_requests_ring+0xd4/0x240 [i915]
[126167.231042] *pdpt = 00000000314c1001 *pde = 0000000000000000
[126167.231314] Oops: 0002 [#1] SMP
[126167.231471] last sysfs file: /sys/devices/LNXSYSTM:00/device:00/PNP0C0A:00/power_supply/BAT1/current_now
[126167.231901] Modules linked in: snd_seq_dummy nls_utf8 isofs btrfs zlib_deflate libcrc32c ufs qnx4 hfsplus hfs minix ntfs vfat msdos fat jfs xfs exportfs reiserfs cryptd aes_i586 aes_generic binfmt_misc vboxnetadp vboxnetflt vboxdrv parport_pc ppdev snd_hda_codec_hdmi snd_hda_codec_conexant snd_hda_intel snd_hda_codec snd_hwdep arc4 snd_pcm snd_seq_midi snd_rawmidi snd_seq_midi_event snd_seq uvcvideo videodev snd_timer snd_seq_device joydev iwlagn iwlcore mac80211 snd cfg80211 soundcore i915 drm_kms_helper snd_page_alloc psmouse drm serio_raw i2c_algo_bit video lp parport usbhid hid sky2 sdhci_pci ahci sdhci libahci
[126167.232018]
[126167.232018] Pid: 1101, comm: Xorg Not tainted 2.6.38-6-generic-pae #34-Ubuntu Gateway MC7833U /
[126167.232018] EIP: 0060:[<f8c2ce44>] EFLAGS: 00213246 CPU: 0
[126167.232018] EIP is at i915_gem_retire_requests_ring+0xd4/0x240 [i915]
[126167.232018] EAX: 00200200 EBX: f1ac25b0 ECX: 00000040 EDX: 00100100
[126167.232018] ESI: f1a2801c EDI: e87fc060 EBP: ef4d7dd8 ESP: ef4d7db0
[126167.232018] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
[126167.232018] Process Xorg (pid: 1101, ti=ef4d6000 task=f1ba6500 task.ti=ef4d6000)
[126167.232018] Stack:
[126167.232018] f1a28000 f1a2809c f1a28094 0058bd97 f1aa2400 f1a2801c 0058bd7b 0058bd85
[126167.232018] f1a2801c f1a28000 ef4d7e38 f8c2e995 ef4d7e30 ef4d7e60 c14d1ebc f6b3a040
[126167.232018] f1522cc0 000000db 00000000 f1ba6500 ffffffa1 00000000 00000001 f1a29214
[126167.232018] Call Trace:
Unfortunately the call trace reported was cut, but looking at debug
symbols the crash is at __list_del, when probably list_del is called
twice on the same request->client_list, as the dereferenced value is
LIST_POISON1 + 4, and by looking more at the debug symbols before
list_del call it should have being called by
i915_gem_request_remove_from_client
And as I can see in the code, it seems we indeed have the possibility
to remove a request->client_list twice, which would cause the above,
because we do list_del(&request->client_list) on both
i915_gem_request_remove_from_client and i915_gem_release
As Chris Wilson pointed out, it's indeed the case:
"(...) I had thought that the actual insertion/deletion was serialised
under the struct mutex and the intention of the spinlock was to protect
the unlocked list traversal during throttling. However, I missed that
i915_gem_release() is also called without struct mutex and so we do need
the double check for i915_gem_request_remove_from_client()."
This change does the required check to avoid the duplicate remove of
request->client_list.
Bugzilla: http://bugs.launchpad.net/bugs/733780
Cc: stable@kernel.org # 2.6.38
Signed-off-by: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
* 'intel/drm-intel-next' of ../drm-next: (755 commits)
drm/i915: Only wait on a pending flip if we intend to write to the buffer
drm/i915/dp: Sanity check eDP existence
drm/i915: Rebind the buffer if its alignment constraints changes with tiling
drm/i915: Disable GPU semaphores by default
drm/i915: Do not overflow the MMADDR write FIFO
Revert "drm/i915: fix corruptions on i8xx due to relaxed fencing"
drm/i915: Don't save/restore hardware status page address register
drm/i915: don't store the reg value for HWS_PGA
drm/i915: fix memory corruption with GM965 and >4GB RAM
Linux 2.6.38-rc7
Revert "TPM: Long default timeout fix"
drm/i915: Re-enable GPU semaphores for SandyBridge mobile
drm/i915: Replace vblank PM QoS with "Interrupt-Based AGPBUSY#"
Revert "drm/i915: Use PM QoS to prevent C-State starvation of gen3 GPU"
drm/i915: Allow relocation deltas outside of target bo
drm/i915: Silence an innocuous compiler warning for an unused variable
fs/block_dev.c: fix new kernel-doc warning
ACPI: Fix build for CONFIG_NET unset
mm: <asm-generic/pgtable.h> must include <linux/mm_types.h>
x86: Use u32 instead of long to set reset vector back to 0
...
Conflicts:
drivers/gpu/drm/i915/i915_gem.c
Early gen3 and gen2 chipset do not have the relaxed per-surface tiling
constraints of the later chipsets, so we need to check that the GTT
alignment is correct for the new tiling. If it is not, we need to
rebind.
Reported-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The code paths for modesetting are growing in complexity as we may need
to move the buffers around in order to fit the scanout in the aperture.
Therefore we face a choice as to whether to thread the interruptible status
through the entire pinning and unbinding code paths or to add a flag to
the device when we may not be interrupted by a signal. This does the
latter and so fixes a few instances of modesetting failures under stress.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Dave Airlie spotted that we had a potential bug should we ever rearrange
the drm_i915_gem_object so not the base drm_gem_object was not its first
member. He noticed that we often convert the return of
drm_gem_object_lookup() immediately into drm_i915_gem_object and then
check the result for nullity. This is only valid when the base object is
the first member and so the superobject has the same address. Play safe
instead and use the compiler to convert back to the original return
address for sanity testing.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
... so we handle that for i915_gem_fault() in the same manner as
ERESTARTSYS, or we send a SIGBUS to the faulting application.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
A lot of minor tweaks to fix the tracepoints, improve the outputting for
ftrace, and to generally make the tracepoints useful again. It is a start
and enough to begin identifying performance issues and gaps in our
coverage.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
By returning EAGAIN upon a wedged GPU before attempting to wait, we
would hit an infinite loop of repeating operation without ever
progressing. Instead this needs to be EIO so that userspace knows that
the GPU is truly wedged and not in the process of error recovery.
Similarly, we need to handle the error recovery during i915_gem_fault.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This is just an idea that might or might not be a good idea,
it basically adds two ioctls to create a dumb and map a dumb buffer
suitable for scanout. The handle can be passed to the KMS ioctls to create
a framebuffer.
It looks to me like it would be useful in the following cases:
a) in development drivers - we can always provide a shadowfb fallback.
b) libkms users - we can clean up libkms a lot and avoid linking
to libdrm_*.
c) plymouth via libkms is a lot easier.
Userspace bits would be just calls + mmaps. We could probably
mark these handles somehow as not being suitable for acceleartion
so as top stop people who are dumber than dumb.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Instead of reporting EIO upfront in the entrance of an ioctl that may or
may not attempt to use the GPU, defer the actual detection of an invalid
ioctl to when we issue a GPU instruction. This allows us to continue to
use bo in video memory (via pread/pwrite and mmap) after the GPU has hung.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We can only utilize the stolen portion of the GTT if we are in sole
charge of the hardware. This is only true if using GEM and KMS,
otherwise VESA continues to access stolen memory.
Reported-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: Frederic Weisbecker <fweisbec@gmail.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
There are I915_NUM_RINGS-1 inter-ring synchronisation counters, but we
were clearing I915_NUM_RINGS of them. Oops.
Reported-by: Jiri Slaby <jirislaby@gmail.com>
Tested-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Rather than evicting an object at random, which is unlikely to alleviate
the memory pressure sufficient to allow us to continue, zap the entire
aperture. That should give the system long enough to recover and reap
some pages from the evicted objects, forestalling the allocation error
for the new object.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In order to retire active buffers whilst no client is active, we need to
insert our own flush requests onto the ring.
This is useful for servers that queue up some rendering and then go to
sleep as it allows us to the complete processing of those requests,
potentially making that memory available again much earlier.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We need to ensure that writes through the GTT land before any
modification to the MMIO registers and so must impose a mandatory write
barrier when flushing the GTT domain. This was revealed by relaxing the
write ordering by experimentally mapping the registers and the GATT as
write-combining.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The relative-to-general state default is useless as it means having to
rewrite the streaming kernels for each batch. Relative-to-surface is
more useful, as that stream usually needs to be rewritten for each
batch. And absolute addressing mode, vital if you start streaming
state, is also only available by adjusting the register...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In order to enforce the correct memory barriers for irq get/put, we need
to perform the actual counting using atomic operations.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
In order for bos to retire eventually, a request must be sent down the
ring. This is expected, for example, by occlusion queries for which mesa
will wait upon (whilst running glean) before issuing more batches and so
the normal activity upon the ring is suspended and we need to emit a
request to clear the idle ring.
Reported-by: Jinjin, Wang <jinjin.wang@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=30380
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
I'm still seeing tiling corruption of PutImage and CopyArea (I think)
under mutter on pnv, so obviously the pipelining logic is deeply flawed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The bulk of the change is to convert the growing list of rings into an
array so that the relationship between the rings and the semaphore sync
registers can be easily computed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As the tracepoint is now decoupled from when the actual register is
assigned and was never complemented by detailing when the object lost
its fence, it has outlived its limited usefulness. Profiling the actual
stalls is a far more profitable venture anyway.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As the userspace mappings are torn down on every GPU write, we prefer to
track when the buffer is activated (via a fresh i915_gem_fault). This
makes the LRU conceptually simpler. With coherent mappings, the
remaining use-case for set_domain_ioctl is GPU synchronisation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
With this change, every batchbuffer can use all available fences (save
pinned and scanout, of course) without ever stalling the gpu!
In theory. Currently the actual pipelined update of the register is
disabled due to some stability issues. However, just the deferred update
is a significant win.
Based on a series of patches by Daniel Vetter.
The premise is that before every access to a buffer through the GTT we
have to declare whether we need a register or not. If the access is by
the GPU, a pipelined update to the register is made via the ringbuffer,
and we track the last seqno of the batches that access it. If by the
CPU we wait for the last GPU access and update the register (either
to clear or to set it for the current buffer).
One advantage of being able to pipeline changes is that we can defer the
actual updating of the fence register until we first need to access the
object through the GTT, i.e. we can eliminate the stall on set_tiling.
This is important as the userspace bo cache does not track the tiling
status of active buffers which generate frequent stalls on gen3 when
enabling tiling for an already bound buffer.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... so that upon first use after resume we will reacquire the fence reg.
Reported-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We don't track gpu flush request in any special way. So even with
obj->write_domain == 0, a gpu flush might be outstanding but no
yet executed. Even worse, the latest request might use the object
only for reading. So and unconditional call to object_wait_rendering
is needed for !pipelined.
Hence revert that patch fully and untangle the flushing from the
synchronization again.
Reported-by: Keith Packard <keithp@keithp.com>
Tested-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Besides the minimal improvement in reducing the execbuffer overhead, the
real benefit is clarifying a few routines.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
A number of dragons have been seen lurking within the execbuffer code.
The first step is then to isolate them from the rest and begin to
scrutinise them in depth. Suggested by Daniel Vetter.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Simply remove our accounting of objects inside the aperture, keeping
only track of what is in the aperture and its current usage. This
removes the over-complication of BUGs that were attempting to keep the
accounting correct and also removes the overhead of the accounting on
the hot-paths.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
With KMS, we can simply relinquish the fence when we idle the GPU and
reassign it upon first use.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Avoid evicting buffers that will be used later in the batch in order to
make room for the initial buffers by pinning all bound buffers in a
single pass before binding (and evicting for) fresh buffer.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This used to check the precondition that all fences were to be located
in a mappable area, redundant now as those two parameters are combined
into one.
After pinning, we assert that the buffer is bound into the desired
region.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The pipe control object is allocated by the device for the sole use of the
render ringbuffer. Move this detail from the general code to the render
ring buffer initialisation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Combining map_and_fenceable revealed a bug in
i915_gem_object_gtt_size() in that it always computed the appropriate
fence size for the object regardless of tiling state which caused us to
over-allocate linear buffers when binding to the GTT.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This is required to restore gtt mappings on resume when agp is gone.
The right way to do this would be to make sturct drm_mm_node embeddable
and use the allocation list maintained by the drm memory manager. But
that's a bigger project. Getting rid of the per bo agp_mem will save
more memory than this wastes, anyway.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Daniel Vetter