In order to transition more of our code over to using a VMA instead of
an <OBJ, VM> pair - we must have the vma accessible at execbuf time. Up
until now, we've only had a VMA when actually binding an object.
The previous patch helped handle the distinction on bound vs. unbound.
This patch will help us catch leaks, and other issues before we actually
shuffle a bunch of stuff around.
This attempts to convert all the execbuf code to speak in vmas. Since
the execbuf code is very self contained it was a nice isolated
conversion.
The meat of the code is about turning eb_objects into eb_vma, and then
wiring up the rest of the code to use vmas instead of obj, vm pairs.
Unfortunately, to do this, we must move the exec_list link from the obj
structure. This list is reused in the eviction code, so we must also
modify the eviction code to make this work.
WARNING: This patch makes an already hotly profiled path slower. The cost is
unavoidable. In reply to this mail, I will attach the extra data.
v2: Release table lock early, and two a 2 phase vma lookup to avoid
having to use a GFP_ATOMIC. (Chris)
v3: s/obj_exec_list/obj_exec_link/
Updates to address
commit 6d2b888569
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed Aug 7 18:30:54 2013 +0100
drm/i915: List objects allocated from stolen memory in debugfs
v4: Use obj = vma->obj for neatness in some places (Chris)
need_reloc_mappable() should return false if ppgtt (Chris)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Split out prep patches. Also remove a FIXME comment which is
now taken care of.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Somehow we've lost the error handling in the patch split-up between
the internal and external patch. This regression has been introduced
in
commit 5032d871f7
Author: Rafael Barbalho <rafael.barbalho@intel.com>
Date: Wed Aug 21 17:10:51 2013 +0100
drm/i915: Cleaning up the relocate entry function
This bug is exercised by igt/gem_reloc_vs_gpu/interruptible.
Cc: Rafael Barbalho <rafael.barbalho@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As the relocate entry function was getting a bit too big I've moved
the code that used to use either the cpu or the gtt to for the
relocation into two separate functions.
Signed-off-by: Rafael Barbalho <rafael.barbalho@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we skip clflushes more often, return a boolean indicating
whether the clflush was actually performed, and only if it was do the
chipset flush. (Though on most of the architectures where the clflush will
be skipped, the chipset flush is a no-op!)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As mentioned in the previous commit, reads and writes from both the CPU
and GPU go through the LLC. This gives us coherency between the CPU and
GPU irrespective of the attribute settings either device sets. We can
use to avoid having to clflush even uncached memory.
Except for the scanout.
The scanout resides within another functional block that does not use
the LLC but reads directly from main memory. So in order to maintain
coherency with the scanout, writes to uncached memory must be flushed.
In order to optimize writes elsewhere, we start tracking whether an
framebuffer is attached to an object.
v2: Use pin_display tracking rather than fb_count (to ensure we flush
cursors as well etc) and only force the clflush along explicit writes to
the scanout paths (i.e. pin_to_display_plane and pwrite into scanout).
v3: Force the flush after hitting the slowpath in pwrite, as after
dropping the lock the object's cache domain may be invalidated. (Ville)
Based on a patch by Ville Syrjälä.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
formerly: "drm/i915: Create VMAs (part 5) - move mm_list"
The mm_list is used for the active/inactive LRUs. Since those LRUs are
per address space, the link should be per VMx .
Because we'll only ever have 1 VMA before this point, it's not incorrect
to defer this change until this point in the patch series, and doing it
here makes the change much easier to understand.
Shamelessly manipulated out of Daniel:
"active/inactive stuff is used by eviction when we run out of address
space, so needs to be per-vma and per-address space. Bound/unbound otoh
is used by the shrinker which only cares about the amount of memory used
and not one bit about in which address space this memory is all used in.
Of course to actual kick out an object we need to unbind it from every
address space, but for that we have the per-object list of vmas."
v2: only bump GGTT LRU in i915_gem_object_set_to_gtt_domain (Chris)
v3: Moved earlier in the series
v4: Add dropped message from v3
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Frob patch to apply and use vma->node.size directly as
discused with Ben. Also drop a needles BUG_ON before move_to_inactive,
the function itself has the same check.]
[danvet 2nd: Rebase on top of the lost "drm/i915: Cleanup more of VMA
in destroy", specifically unlink the vma from the mm_list in
vma_unbind (to keep it symmetric with bind_to_vm) instead of
vma_destroy.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In some places, we want to know if an object is bound in any address
space, and not just the global GTT. This often applies when there is a
single global resource (object, pages, etc.)
function | reason
--------------------------------------------------
i915_gem_object_is_inactive | global object
i915_gem_object_put_pages | object's pages
915_gem_object_unpin | global object
i915_gem_execbuffer_unreserve_object | temporary until we plumb vma
pread/pwrite | see the note below
Note: set_to_gtt_domain in pwrite/pread is abused as a wait_rendering
call - but that once only worked if the object is bound. We really
should replace this with a plain wait_rendering call, which would have
the upside that in pread it would be clearer that we actually only
wait for oustanding gpu writes.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Explain the set_to_gtt_domain in pwrite/pread and volunteer
Ben to replace those with wait_rendering calls.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As alluded to in several patches, and it will be reiterated later... A
VMA is an abstraction for a GEM BO bound into an address space.
Therefore it stands to reason, that the existing bind, and unbind are
the ones which will be the most impacted. This patch implements this,
and updates all callers which weren't already updated in the series
(because it was too messy).
This patch represents the bulk of an earlier, larger patch. I've pulled
out a bunch of things by the request of Daniel. The history is preserved
for posterity with the email convention of ">" One big change from the
original patch aside from a bunch of cropping is I've created an
i915_vma_unbind() function. That is because we always have the VMA
anyway, and doing an extra lookup is useful. There is a caveat, we
retain an i915_gem_object_ggtt_unbind, for the global cases which might
not talk in VMAs.
> drm/i915: plumb VM into object operations
>
> This patch was formerly known as:
> "drm/i915: Create VMAs (part 3) - plumbing"
>
> This patch adds a VM argument, bind/unbind, and the object
> offset/size/color getters/setters. It preserves the old ggtt helper
> functions because things still need, and will continue to need them.
>
> Some code will still need to be ported over after this.
>
> v2: Fix purge to pick an object and unbind all vmas
> This was doable because of the global bound list change.
>
> v3: With the commit to actually pin/unpin pages in place, there is no
> longer a need to check if unbind succeeded before calling put_pages().
> Make put_pages only BUG() after checking pin count.
>
> v4: Rebased on top of the new hangcheck work by Mika
> plumbed eb_destroy also
> Many checkpatch related fixes
>
> v5: Very large rebase
>
> v6:
> Change BUG_ON to WARN_ON (Daniel)
> Rename vm to ggtt in preallocate stolen, since it is always ggtt when
> dealing with stolen memory. (Daniel)
> list_for_each will short-circuit already (Daniel)
> remove superflous space (Daniel)
> Use per object list of vmas (Daniel)
> Make obj_bound_any() use obj_bound for each vm (Ben)
> s/bind_to_gtt/bind_to_vm/ (Ben)
>
> Fixed up the inactive shrinker. As Daniel noticed the code could
> potentially count the same object multiple times. While it's not
> possible in the current case, since 1 object can only ever be bound into
> 1 address space thus far - we may as well try to get something more
> future proof in place now. With a prep patch before this to switch over
> to using the bound list + inactive check, we're now able to carry that
> forward for every address space an object is bound into.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Rebase on top of the loss of "drm/i915: Cleanup more of VMA
in destroy".]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This represents the first half of hooking up VMs to execbuf. Here we
basically pass an address space all around to the different internal
functions. It should be much more readable, and have less risk than the
second half, which begins switching over to using VMAs instead of an
obj,vm.
The overall series echoes this style of, "add a VM, then make it smart
later"
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Switch a BUG_ON to WARN_ON.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
To verbalize it, one can say, "pin an object into the given address
space." The semantics of pinning remain the same otherwise.
Certain objects will always have to be bound into the global GTT.
Therefore, global GTT is a special case, and keep a special interface
around for it (i915_gem_obj_ggtt_pin).
v2: s/i915_gem_ggtt_pin/i915_gem_obj_ggtt_pin
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
prefault is stll enabled by default which prevent most of pwrite/pread/reloc
from running slow path, in order to verify these slow pathes, prefault need
to be disabled.
Signed-off-by: Xiong Zhang <xiong.y.zhang@intel.com>
[danvet: Make checkpatch happy and bikeshed the module option help
text a bit.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The intent of the check is made more clear if we use the proper name for
0 here.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In kernel modeset driver mode we're in full control of the chip,
always. So there's no need at all to set mm.suspended in
i915_gem_idle. Hence move that out into the leavevt ioctl. Since
i915_gem_idle doesn't suspend gem any more we can also drop the
re-enabling for KMS in the thaw function.
Also clean up the handling of mm.suspend at driver load by coalescing
all the assignments.
Stumbled over while reading through our resume code for unrelated
reasons.
v2: Shovel mm.suspended into the (newly created) ums dungeon as
suggested by Chris Wilson. The plan is that once we've completely
stopped relying on the register save/restore code we could shovel even
that in there.
v3: Improve the locking for the entervt/leavevt ioctls a bit by moving
the dev->struct_mutex locking outside of i915_gem_idle. Also don't
clear dev_priv->ums.mm_suspended for the kms case, we allocate it with
kzalloc. Both suggested by Chris Wilson.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> (v2)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Soon we want to gut a lot of our existing assumptions how many address
spaces an object can live in, and in doing so, embed the drm_mm_node in
the object (and later the VMA).
It's possible in the future we'll want to add more getter/setter
methods, but for now this is enough to enable the VMAs.
v2: Reworked commit message (Ben)
Added comments to the main functions (Ben)
sed -i "s/i915_gem_obj_set_color/i915_gem_obj_ggtt_set_color/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_bound/i915_gem_obj_ggtt_bound/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_size/i915_gem_obj_ggtt_size/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_offset/i915_gem_obj_ggtt_offset/" drivers/gpu/drm/i915/*.[ch]
(Daniel)
v3: Rebased on new reserve_node patch
Changed DRM_DEBUG_KMS to actually work (will need fixing later)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order to track down a batch buffer and context which
caused the ring to hang, store reference to bo into the request struct.
Request can also cause gpu to hang after the batch in the flush section
in the ring. To detect this add start of the flush portion offset into the
request.
v2: Included comment about request vs batch_obj lifetimes (Chris Wilson)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Only execbuffer needed all the parameters on i915_add_request().
By putting __i915_add_request behind macro, all current callsites
become cleaner. Following patch will introduce a new parameter
for __i915_add_request. With this patch, only the relevant callsite
will reflect the change making commit smaller and easier to understand.
v2: _i915_add_request as function name (Chris Wilson)
v3: change name __i915_add_request and fix ordering of params (Ben Widawsky)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is required for tracking render damage for use with FBC and will be
used in subsequent patches.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A user can run batchbuffer via VEBOX ring.
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
Highlights:
- Imre's for_each_sg_pages rework (now also with the stolen mem backed
case fixed with a hack) plus the drm prime sg list coalescing patch from
Rahul Sharma. I have some follow-up cleanups pending, already acked by
Andrew Morton.
- Some prep-work for the crazy no-pch/display-less platform by Ben.
- Some vlv patches, by far not all (Jesse et al).
- Clean up the HDMI/SDVO #define confusion (Paulo)
- gen2-4 vblank fixes from Ville.
- Unclaimed register warning fixes for hsw (Paulo). More still to come ...
- Complete pageflips which have been stuck in a gpu hang, should prevent
stuck gl compositors (Ville).
- pm patches for vt-switchless resume (Jesse). Note that the i915 enabling
is not (yet) included, that took a bit longer to settle. PM patches are
acked by Rafael Wysocki.
- Minor fixlets all over from various people.
* tag 'drm-intel-next-2013-03-23' of git://people.freedesktop.org/~danvet/drm-intel: (79 commits)
drm/i915: Implement WaSwitchSolVfFArbitrationPriority
drm/i915: Set the VIC in AVI infoframe for SDVO
drm/i915: Kill a strange comment about DPMS functions
drm/i915: Correct sandybrige overclocking
drm/i915: Introduce GEN7_FEATURES for device info
drm/i915: Move num_pipes to intel info
drm/i915: fixup pd vs pt confusion in gen6 ppgtt code
style nit: Align function parameter continuation properly.
drm/i915: VLV doesn't have HDMI on port C
drm/i915: DSPFW and BLC regs are in the display offset range
drm/i915: set conservative clock gating values on VLV v2
drm/i915: fix WaDisablePSDDualDispatchEnable on VLV v2
drm/i915: add more VLV IDs
drm/i915: use VLV DIP routines on VLV v2
drm/i915: add media well to VLV force wake routines v2
drm/i915: don't use plane pipe select on VLV
drm: modify pages_to_sg prime helper to create optimized SG table
drm/i915: use for_each_sg_page for setting up the gtt ptes
drm/i915: create compact dma scatter lists for gem objects
drm/i915: handle walking compact dma scatter lists
...
It is possible to wrap the counter used to allocate the buffer for
relocation copies. This could lead to heap writing overflows.
CVE-2013-0913
v3: collapse test, improve comment
v2: move check into validate_exec_list
Signed-off-by: Kees Cook <keescook@chromium.org>
Reported-by: Pinkie Pie
Cc: stable@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This clarifies the comment above the access_ok check so a missing
VERIFY_READ doesn't alarm anyone.
v2:
- rewrote comment, thanks to Chris Wilson
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
[danvet: add patch history log to commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
to_user_ptr() simply casts a pointer passed as u64 from user space
to void __user * correctly. Using this lets us get rid of all the
tiresome casts.
The idea came from Chris Wilson <chris@chris-wilson.co.uk>.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This pulls in most of Linus tree up to -rc6, this fixes the worst lockdep
reported issues and re-enables fbcon lockdep.
(not the fbcon maintainer)
* 'fbcon-locking-fixes' of ssh://people.freedesktop.org/~airlied/linux: (529 commits)
Revert "Revert "console: implement lockdep support for console_lock""
fbcon: fix locking harder
fb: Yet another band-aid for fixing lockdep mess
fb: rework locking to fix lock ordering on takeover
The purpose of the gtt structure is to help isolate our gtt specific
properties from the rest of the code (in doing so it help us finish the
isolation from the AGP connection).
The following members are pulled out (and renamed):
gtt_start
gtt_total
gtt_mappable_end
gtt_mappable
gtt_base_addr
gsm
The gtt structure will serve as a nice place to put gen specific gtt
routines in upcoming patches. As far as what else I feel belongs in this
structure: it is meant to encapsulate the GTT's physical properties.
This is why I've not added fields which track various drm_mm properties,
or things like gtt_mtrr (which is itself a pretty transient field).
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
[Ben modified commit messages]
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Using copywinwin10 as an example that is dependent upon emitting a lot
of relocations (2 per operation), we see improvements of:
c2d/gm45: 618000.0/sec to 623000.0/sec.
i3-330m: 748000.0/sec to 789000.0/sec.
(measured relative to a baseline with neither optimisations applied).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Userspace is able to hint to the kernel that its command stream and
auxiliary state buffers already hold the correct presumed addresses and
so the relocation process may be skipped if the kernel does not need to
move any buffers in preparation for the execbuffer. Thus for the common
case where the allotment of buffers is static between batches, we can
avoid the overhead of individually checking the relocation entries.
Note that this requires userspace to supply the domain tracking and
requests for workarounds itself that would otherwise be computed based
upon the relocation entries.
Using copywinwin10 as an example that is dependent upon emitting a lot
of relocations (2 per operation), we see improvements of:
c2d/gm45: 618000.0/sec to 632000.0/sec.
i3-330m: 748000.0/sec to 830000.0/sec.
(measured relative to a baseline with neither optimisations applied).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
[danvet: Fixup merge conflict in userspace header due to different
baseline trees.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of passing around the eb-objects hashtable and a separate object
list, we can include the object list into the eb-objects structure for
convenience.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The difference is that the kernel will then know that this memory will
be reclaimable in the near future.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
- seqno wrap fixes and debug infrastructure from Mika Kuoppala and Chris
Wilson
- some leftover kill-agp on gen6+ patches from Ben
- hotplug improvements from Damien
- clear fb when allocated from stolen, avoids dirt on the fbcon (Chris)
- Stolen mem support from Chris Wilson, one of the many steps to get to
real fastboot support.
- Some DDI code cleanups from Paulo.
- Some refactorings around lvds and dp code.
- some random little bits&pieces
* tag 'drm-intel-next-2012-12-21' of git://people.freedesktop.org/~danvet/drm-intel: (93 commits)
drm/i915: Return the real error code from intel_set_mode()
drm/i915: Make GSM void
drm/i915: Move GSM mapping into dev_priv
drm/i915: Move even more gtt code to i915_gem_gtt
drm/i915: Make next_seqno debugs entry to use i915_gem_set_seqno
drm/i915: Introduce i915_gem_set_seqno()
drm/i915: Always clear semaphore mboxes on seqno wrap
drm/i915: Initialize hardware semaphore state on ring init
drm/i915: Introduce ring set_seqno
drm/i915: Missed conversion to gtt_pte_t
drm/i915: Bug on unsupported swizzled platforms
drm/i915: BUG() if fences are used on unsupported platform
drm/i915: fixup overlay stolen memory leak
drm/i915: clean up PIPECONF bpc #defines
drm/i915: add intel_dp_set_signal_levels
drm/i915: remove leftover display.update_wm assignment
drm/i915: check for the PCH when setting pch_transcoder
drm/i915: Clear the stolen fb before enabling
drm/i915: Access to snooped system memory through the GTT is incoherent
drm/i915: Remove stale comment about intel_dp_detect()
...
Conflicts:
drivers/gpu/drm/i915/intel_display.c
In the slow path, we are forced to copy the relocations prior to
acquiring the struct mutex in order to handle pagefaults. We forgo
copying the new offsets back into the relocation entries in order to
prevent a recursive locking bug should we trigger a pagefault whilst
holding the mutex for the reservations of the execbuffer. Therefore, we
need to reset the presumed_offsets just in case the objects are rebound
back into their old locations after relocating for this exexbuffer - if
that were to happen we would assume the relocations were valid and leave
the actual pointers to the kernels dangling, instant hang.
Fixes regression from commit bcf50e2775
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun Nov 21 22:07:12 2010 +0000
drm/i915: Handle pagefaults in execbuffer user relocations
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=55984
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@fwll.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that Chris Wilson demonstrated that the key for stability on early
gen 2 is to simple _never_ exchange the physical backing storage of
batch buffers I've tried a stab at a kernel solution. Doesn't look too
nefarious imho, now that I don't try to be too clever for my own good
any more.
v2: After discussing the various techniques, we've decided to always blit
batches on the suspect devices, but allow userspace to opt out of the
kernel workaround assume full responsibility for providing coherent
batches. The principal reason is that avoiding the blit does improve
performance in a few key microbenchmarks and also in cairo-trace
replays.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet:
- Drop the hunk which uses HAS_BROKEN_CS_TLB to implement the ring
wrap w/a. Suggested by Chris Wilson.
- Also add the ACTHD check from Chris Wilson for the error state
dumping, so that we still catch batches when userspace opts out of
the w/a.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Simply use the last write-domain set for the object in the batch,
trusting userspace to have correctly flushed the caches between usage as
a write target. This check dates back from the golden age of having only
a single operation per batch with the kernel repeating it for each
cliprect, and conflicts both with userspace trying to efficiently batch
multiple operations and with reducing the kernel overhead of relocation
processing.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As per Chris Wilson's suggestion make
i915_gem_execbuffer_wait_for_flips() go away.
This was used to stall the GPU ring while there are pending
page flips involving the relevant BO. Ie. while the BO is still
being scanned out by the display controller.
The recommended alternative is to use the page flip events to
wait for the page flips to fully complete before reusing the BO
of the old front buffer. Or use more buffers.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Kristian Høgsberg <krh@bitplanet.net>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: don't remove obj->pending_flips, still required due to
reorder patches.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Based on the work by Mika Kuoppala, we realised that we need to handle
seqno wraparound prior to committing our changes to the ring. The most
obvious point then is to grab the seqno inside intel_ring_begin(), and
then to reuse that seqno for all ring operations until the next request.
As intel_ring_begin() can fail, the callers must already be prepared to
handle such failure and so we can safely add further checks.
This patch looks like it should be split up into the interface
changes and the tweaks to move seqno wrapping from the execbuffer into
the core seqno increment. However, I found no easy way to break it into
incremental steps without introducing further broken behaviour.
v2: Mika found a silly mistake and a subtle error in the existing code;
inside i915_gem_retire_requests() we were resetting the sync_seqno of
the target ring based on the seqno from this ring - which are only
related by the order of their allocation, not retirement. Hence we were
applying the optimisation that the rings were synchronised too early,
fortunately the only real casualty there is the handling of seqno
wrapping.
v3: Do not forget to reset the sync_seqno upon module reinitialisation,
ala resume.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=863861
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> [v2]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The intention of checking obj->gtt_offset!=0 is to verify that the
target object was listed in the execbuffer and had been bound into the
GTT. This is guarranteed by the earlier rearrangement to split the
execbuffer operation into reserve and relocation phases and then
verified by the check that the target handle had been processed during
the reservation phase.
However, the actual checking of obj->gtt_offset==0 is bogus as we can
indeed reference an object at offset 0. For instance, the framebuffer
installed by the BIOS often resides at offset 0 - causing EINVAL as we
legimately try to render using the stolen fb.
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>
As a quick hack we make the old intel_gtt structure mutable so we can
fool a bunch of the existing code which depends on elements in that data
structure. We can/should try to remove this in a subsequent patch.
This should preserve the old gtt init behavior which upon writing these
patches seems incorrect. The next patch will fix these things.
The one exception is VLV which doesn't have the preserved flush control
write behavior. Since we want to do that for all GEN6+ stuff, we'll
handle that in a later patch. Mainstream VLV support doesn't actually
exist yet anyway.
v2: Update the comment to remove the "voodoo"
Check that the last pte written matches what we readback
v3: actually kill cache_level_to_agp_type since most of the flags will
disappear in an upcoming patch
v4: v3 was actually not what we wanted (Daniel)
Make the ggtt bind assertions better and stricter (Chris)
Fix some uncaught errors at gtt init (Chris)
Some other random stuff that Chris wanted
v5: check for i==0 in gen6_ggtt_bind_object to shut up gcc (Ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by [v4]: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Make the cache_level -> agp_flags conversion for pre-gen6 a
tad more robust by mapping everything != CACHE_NONE to the cached agp
flag - we have a 1:1 uncached mapping, but different modes of
cacheable (at least on later generations). Suggested by Chris Wilson.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)
iQEcBAABAgAGBQJQgvdwAAoJEHm+PkMAQRiG+3AH/i2XsqqN3VctL0nnbWfvds+Q
aKulfIdJTjKiVAsawPUtRqReZ8ijiebrgA/53lZLlrFOoPPQ5+LHmnSyQF6gErOY
NuAE1lijXDRM1pwBlhvOBbAj26wUobGjqONFJ9OkKr758Ue8ds/Q7UdxyEgmYgmg
tvVMzfRcICzryUV3PcqL+3cNPpCUdT6wGGRJ9DCv/jvGiWKExWhOle5oltrmxk+D
NsqRcws5pEubfHE4J8BvNWr8lE1kHfYVhrJETiLJUiN2XAJcbI4Jy7rU/3EGteNS
0HMZdaPPjV874lohdM70X2225SbYrCVkAYB5hnZCTeC3tYyCawBBPMQoyAiOcmU=
=+861
-----END PGP SIGNATURE-----
Merge tag 'v3.7-rc2' into drm-intel-next-queued
Linux 3.7-rc2
Backmerge to solve two ugly conflicts:
- uapi. We've already added new ioctl definitions for -next. Do I need to say more?
- wc support gtt ptes. We've had to revert this for snb+ for 3.7 and
also fix a few other things in the code. Now we know how to make it
work on snb+, but to avoid losing the other fixes do the backmerge
first before re-enabling wc gtt ptes on snb+.
And a few other minor things, among them git getting confused in
intel_dp.c and seemingly causing a conflict out of nothing ...
Conflicts:
drivers/gpu/drm/i915/i915_reg.h
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/i915/intel_dp.c
drivers/gpu/drm/i915/intel_modes.c
include/drm/i915_drm.h
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the introduction of per-process GTT space, the hardware designers
thought it wise to also limit the ability to write to MMIO space to only
a "secure" batch buffer. The ability to rewrite registers is the only
way to program the hardware to perform certain operations like scanline
waits (required for tear-free windowed updates). So we either have a
choice of adding an interface to perform those synchronized updates
inside the kernel, or we permit certain processes the ability to write
to the "safe" registers from within its command stream. This patch
exposes the ability to submit a SECURE batch buffer to
DRM_ROOT_ONLY|DRM_MASTER processes.
v2: Haswell split up bit8 into a ppgtt bit (still bit8) and a security
bit (bit 13, accidentally not set). Also add a comment explaining why
secure batches need a global gtt binding.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> (v1)
[danvet: added hsw fixup.]
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Pull drm merge (part 1) from Dave Airlie:
"So first of all my tree and uapi stuff has a conflict mess, its my
fault as the nouveau stuff didn't hit -next as were trying to rebase
regressions out of it before we merged.
Highlights:
- SH mobile modesetting driver and associated helpers
- some DRM core documentation
- i915 modesetting rework, haswell hdmi, haswell and vlv fixes, write
combined pte writing, ilk rc6 support,
- nouveau: major driver rework into a hw core driver, makes features
like SLI a lot saner to implement,
- psb: add eDP/DP support for Cedarview
- radeon: 2 layer page tables, async VM pte updates, better PLL
selection for > 2 screens, better ACPI interactions
The rest is general grab bag of fixes.
So why part 1? well I have the exynos pull req which came in a bit
late but was waiting for me to do something they shouldn't have and it
looks fairly safe, and David Howells has some more header cleanups
he'd like me to pull, that seem like a good idea, but I'd like to get
this merge out of the way so -next dosen't get blocked."
Tons of conflicts mostly due to silly include line changes, but mostly
mindless. A few other small semantic conflicts too, noted from Dave's
pre-merged branch.
* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (447 commits)
drm/nv98/crypt: fix fuc build with latest envyas
drm/nouveau/devinit: fixup various issues with subdev ctor/init ordering
drm/nv41/vm: fix and enable use of "real" pciegart
drm/nv44/vm: fix and enable use of "real" pciegart
drm/nv04/dmaobj: fixup vm target handling in preparation for nv4x pcie
drm/nouveau: store supported dma mask in vmmgr
drm/nvc0/ibus: initial implementation of subdev
drm/nouveau/therm: add support for fan-control modes
drm/nouveau/hwmon: rename pwm0* to pmw1* to follow hwmon's rules
drm/nouveau/therm: calculate the pwm divisor on nv50+
drm/nouveau/fan: rewrite the fan tachometer driver to get more precision, faster
drm/nouveau/therm: move thermal-related functions to the therm subdev
drm/nouveau/bios: parse the pwm divisor from the perf table
drm/nouveau/therm: use the EXTDEV table to detect i2c monitoring devices
drm/nouveau/therm: rework thermal table parsing
drm/nouveau/gpio: expose the PWM/TOGGLE parameter found in the gpio vbios table
drm/nouveau: fix pm initialization order
drm/nouveau/bios: check that fixed tvdac gpio data is valid before using it
drm/nouveau: log channel debug/error messages from client object rather than drm client
drm/nouveau: have drm debugging macros build on top of core macros
...
Convert #include "..." to #include <path/...> in drivers/gpu/.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
Remove redundant DRM UAPI header #inclusions from drivers/gpu/.
Remove redundant #inclusions of core DRM UAPI headers (drm.h, drm_mode.h and
drm_sarea.h). They are now #included via drmP.h and drm_crtc.h via a preceding
patch.
Without this patch and the patch to make include the UAPI headers from the core
headers, after the UAPI split, the DRM C sources cannot find these UAPI headers
because the DRM code relies on specific -I flags to make #include "..." work
on headers in include/drm/ - but that does not work after the UAPI split without
adding more -I flags.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
As we make the simplification of using a power-of-two size for the
execbuffer handle-to-object TLB, we should validate that this is actually
true and so clarify that premise.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The exec_list is of type drm_i915_gem_exec_object2 and so casting it to
a drm_i915_gem_relocation_entry is very confusing!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Rather than have multiple data structures for describing our page layout
in conjunction with the array of pages, we can migrate all users over to
a scatterlist.
One major advantage, other than unifying the page tracking structures,
this offers is that we replace the vmalloc'ed array (which can be up to
a megabyte in size) with a chain of individual pages which helps reduce
memory pressure.
The disadvantage is that we then do not have a simple array to iterate,
or to access randomly. The common case for this is in the relocation
processing, which will typically fit within a single scatterlist page
and so be almost the same cost as the simple array. For iterating over
the array, the extra function call could be optimised away, but in
reality is an insignificant cost of either binding the pages, or
performing the pwrite/pread.
v2: Fix drm_clflush_sg() to not invoke wbinvd as well! And fix the
trivial compile error from rebasing.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we need to stall in order to complete the pin_and_fence operation
during execbuffer reservation, there is a high likelihood that the
operation will be interrupted by a signal (thanks X!). In order to
simplify the cleanup along that error path, the object was
unconditionally unbound and the error propagated. However, being
interrupted here is far more common than I would like and so we can
strive to avoid the extra work by eliminating the forced unbind.
v2: In discussion over the indecent colour of the new functions and
unwind path, we realised that we can use the new unreserve function to
clean up the code even further.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This prevents the case of unbinding the object in order to process the
relocations through the GTT and then rebinding it only to then proceed
to use cpu relocations as the object is now in the CPU write domain. By
choosing to use cpu relocations up front, we can therefore avoid the
rebind penalty.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Avoid stalling and waiting for the GPU by checking to see if there is
sufficient inactive space in the aperture for us to bind the buffer
prior to writing through the GTT. If there is inadequate space we will
have to stall waiting for the GPU, and incur overheads moving objects
about. Instead, only incur the clflush overhead on the target object by
writing through shmem.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When dealing with a working set larger than the GATT, or even the
mappable aperture when touching through the GTT, we end up with evicting
objects only to rebind them at a new offset again later. Moving an
object into and out of the GTT requires clflushing the pages, thus
causing a double-clflush penalty for rebinding.
To avoid having to clflush on rebinding, we can track the pages as they
are evicted from the GTT and only relinquish those pages on memory
pressure.
As usual, if it were not for the handling of out-of-memory condition and
having to manually shrink our own bo caches, it would be a net reduction
of code. Alas.
Note: The patch also contains a few changes to the last-hope
evict_everything logic in i916_gem_execbuffer.c - we no longer try to
only evict the purgeable stuff in a first try (since that's superflous
and only helps in OOM corner-cases, not fragmented-gtt trashing
situations).
Also, the extraction of the get_pages retry loop from bind_to_gtt (and
other callsites) to get_pages should imo have been a separate patch.
v2: Ditch the newly added put_pages (for unbound objects only) in
i915_gem_reset. A quick irc discussion hasn't revealed any important
reason for this, so if we need this, I'd like to have a git blame'able
explanation for it.
v3: Undo the s/drm_malloc_ab/kmalloc/ in get_pages that Chris noticed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Split out code movements and rant a bit in the commit message
with a few Notes. Done v2]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJQLWtvAAoJEHm+PkMAQRiG/DYH+wd0FqfEuYkYk4KPyAPuhKpX
zX7HYfLvyJE/ZYIdrhjq1E6Xm2KNr7gtX7/Rdzi2W38M9sjbYzwG1UGIw51qnxWy
yZJH9BGkfyQgQPeuDGohfB6DkDy2JWr2eqMDvakjOwgBsIzji0PQD/f3UvndhtUa
c+tTj/kjavHE1Yr2Wy6OnRZz3Uc0hIMn/Q0JqtbCs3LUgEV1KA4OEAe56XNz4Ku4
WE+FFaGFPvtriQsQON+ohPS5IC8jzQGK/0vbrJ4lWjFnZy4gvZXnborTOwD0WSQG
fbsNuxp1AaM2/pqfMwXm1w0ADvwOITHNiwwXf9id6DoK81QwTFpUdvKpn6yB6gQ=
=rurr
-----END PGP SIGNATURE-----
Merge tag 'v3.6-rc2' into drm-intel-next
Backmerge Linux 3.6-rc2 to resolve a few funny conflicts before we put
even more madness on top:
- drivers/gpu/drm/i915/i915_irq.c: Just a spurious WARN removed in
-fixes, that has been changed in a variable-rename in -next, too.
- drivers/gpu/drm/i915/intel_ringbuffer.c: -next remove scratch_addr
(since all their users have been extracted in another fucntion),
-fixes added another user for a hw workaroudn.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If a buffer that was the target of a PIPE_CONTROL from userland was a
reused one that hadn't been evicted which had not previously had this
workaround applied, then the early return for a correct
presumed_offset in this function meant we would not bind it into the
GTT and the write would land somewhere else.
Fixes reproducible failures with GL_EXT_timer_query usage in apitrace,
and I also expect it to fix the intermittent OQ issues on snb that
danvet's been working on.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=48019
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52932
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Carl Worth <cworth@cworth.org>
Tested-by: Carl Worth <cworth@cworth.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As suggested by Daniel, rip out the independent timers for device and
crtc busyness and integrate the manual powermanagement of the display
engine into the GEM core and its request tracking. The benefits are that
the code is a lot smaller, fewer moving parts and should fit more neatly
into the overall activity tracking of the driver.
v2: Complete overhaul and removal of the racy timers and workers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By moving the function to intel_ringbuffer and currying the appropriate
parameter, hopefully we make the callsites easier to read and
understand.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise once we use the buffer with a BLT command on gen2/3, we will
always regard future command submissions as continuing the fenced
access. However, now that we flush/invalidate between every batch we can
drop this pessimism.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we unconditionally flush and invalidate between every batch
buffer, we no longer need the complex logic to decide which domains
require flushing. Remove it and rejoice.
v2 (danvet): Keep around the flip waiting logic. It's gross and
broken, I know, but we can't just kill that thing ... even if we just
keep it around as a reminder that things are broken.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is now handled by a global flag to ensure we emit a flush before
the next serialisation point (if we failed to queue one previously).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we always flush the GPU cache prior to emitting the breadcrumb, we no
longer have to worry about the deferred flush causing the
pending_gpu_write to be delayed. So we can instead utilize the known
last_write_seqno to hopefully minimise the wait times.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Request preallocation was added to i915_add_request() in order to
support the overlay. However, not all users care and can quite happily
ignore the failure to allocate the request as they will simply repeat
the request in the future.
By pushing the allocation down into i915_add_request(), we can then
remove some rather ugly error handling in the callers.
v2: Nullify request->file_priv otherwise we chase a garbage pointer
when retiring requests.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Fixes failures in transform feedback on gen7 because our SOL_RESET
flag was setting the transform feedback offsets in the old context
(occasionally happened to be ours) instead of the new context.
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we drop the breadcrumb request after a batch due to a signal for
example we aim to fix it up at the next opportunity. In this case we
emit a second batchbuffer with no waits upon the first and so no
opportunity to insert the missing request, so we need to emit the
missing flush for coherency. (Note that that invalidating the render
cache is the same as flushing it, so there should have been no
observable corruption.)
Note that beside simply adding the missing flush, avoiding potential
render corruption, this will also fix at least parts of the problem
introduced by some funny interaction of these two commits:
commit de2b998552
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jul 4 22:52:50 2012 +0200
drm/i915: don't return a spurious -EIO from intel_ring_begin
which allowed intel_ring_begin to return -ERESTARTSYS and
commit cc889e0f6c
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jun 13 20:45:19 2012 +0200
drm/i915: disable flushing_list/gpu_write_list
which essentially disabled the flushing list.
The issue happens when we submit a batch & emit it, but get
interrupted (thanks to the first patch) while trying to emit the
flush. On the next batch we still assume that the full gpu domain
handling is in effect and hence compute the invalidate&flushing
domains. But thanks to the 2nd patch we totally ignore these and only
invalidate all gpu domains, presuming that any required flushes have
been issued already. Which is wrong and eventually results in us
updating the new write_domain values with the computed
pending_write_domain values, which leaves an object with write_domain
== 0 on the gpu_write_list.
As soon as we try to unbind that object, things blow up.
Fix this by emitting the missing flush according to the new
ring->gpu_caches_dirty flag.
Note that this does _not_ fix all the current cases where we end up
with an object on the flushing_list that can't be flushed.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52040
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add bug explanation to commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is just the minimal patch to disable all this code so that we can
do decent amounts of QA before we rip it all out.
The complicating thing is that we need to flush the gpu caches after
the batchbuffer is emitted. Which is past the point of no return where
execbuffer can't fail any more (otherwise we risk submitting the same
batch multiple times).
Hence we need to add a flag to track whether any caches associated
with that ring are dirty. And emit the flush in add_request if that's
the case.
Note that this has a quite a few behaviour changes:
- Caches get flushed/invalidated unconditionally.
- Invalidation now happens after potential inter-ring sync.
I've bantered around a bit with Chris on irc whether this fixes
anything, and it might or might not. The only thing clear is that with
these changes it's much easier to reason about correctness.
Also rip out a lone get_next_request_seqno in the execbuffer
retire_commands function. I've dug around and I couldn't figure out
why that is still there, with the outstanding lazy request stuff it
shouldn't be necessary.
v2: Chris Wilson complained that I also invalidate the read caches
when flushing after a batchbuffer. Now optimized.
v3: Added some comments to explain the new flushing behaviour.
Cc: Eric Anholt <eric@anholt.net>
Cc: 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>
Use the rsvd1 field in execbuf2 to specify the context ID associated
with the workload. This will allow the driver to do the proper context
switch when/if needed.
v2: Add checks for context switches on rings not supporting contexts.
Before the code would silently ignore such requests.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Rather than use the magic feature tests HAS_BLT/HAS_BSD just check
whether the ring we are about to dispatch the execbuffer on is
initialised.
v2: Use intel_ring_initialized()
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The principle of intel_mark_busy() is that we want to spot the
transition of when the display engine is being used in order to bump
powersaving modes and increase display clocks. As such it is only
important when the display is changing, i.e. when rendering to the
scanout or other sprite/plane, and these are characterised by being
pinned.
v2: Mark the whole device as busy on execbuffer and pageflips as well
and rebase against dinq for the minor bug fix to be immediately
applicable.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: fix compile fail.]
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>
Unfortunately there has been dri1 userspace that used gem to manage
the gtt and hence also needed cliprects in the execbuf ioctl. So
we can't ever remove that code without breaking the ioctl abi.
But at least we can disable it on gen5+, because these horrible
versions of mesa have not supported these chips.
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
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>
On 32-bit systems, a large args->num_cliprects from userspace via ioctl
may overflow the allocation size, leading to out-of-bounds access.
This vulnerability was introduced in commit 432e58ed ("drm/i915: Avoid
allocation for execbuffer object list").
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On 32-bit systems, a large args->buffer_count from userspace via ioctl
may overflow the allocation size, leading to out-of-bounds access.
This vulnerability was introduced in commit 8408c282 ("drm/i915:
First try a normal large kmalloc for the temporary exec buffers").
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
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>
As we defer updating the fence register from set-tiling to the point of
use, we need to declare every access through the GTT as either fenced or
unfenced.
This patches fixes an old bug in the execbuffer relocation processing
which could conceivably be hit by a pathological userspace.
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
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>
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>
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>
Originally the code tried to allocate a large enough array to perform
the copy using vmalloc, performance wasn't great and throughput was
improved by processing each individual relocation entry separately.
This too is not as efficient as one would desire. A compromise would be
to allocate a single page, or to allocate a few entries on the stack,
and process the copy in batches. The latter gives simpler code and more
consistent performance due to a lack of heuristic.
x11perf -copywinwin10: n450/pnv i3-330m i5-2520m (cpu)
before: 249000 785000 1280000 (80%)
page: 264000 896000 1280000 (65%)
on-stack: 264000 902000 1280000 (67%)
v2: Use 512-bytes of stack for batching rather than allocate a page.
v3: Tidy the code slightly with more descriptive variable names
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>
PIPE_CONTROL on snb needs global gtt mappings in place to workaround a
hw gotcha. No other commands need such a workaround. Luckily we can
detect a PIPE_CONTROL commands easily because they have a write_domain
= I915_GEM_DOMAIN_INSTRUCTION (and nothing else has that).
v2: Binding the target of such a reloc into the global gtt actually
works instead of binding the source, which is rather pointless ...
v3: Kill a superflous has_global_gtt_mapping assignement noticed by
Chris Wilson.
Reviewed-and-tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Back-merge from drm-fixes into drm-intel-next to sort out two things:
- interlaced support: -fixes contains a bugfix to correctly clear
interlaced configuration bits in case the bios sets up an interlaced
mode and we want to set up the progressive mode (current kernels
don't support interlaced). The actual feature work to support
interlaced depends upon (and conflicts with) this bugfix.
- forcewake voodoo to workaround missed IRQ issues: -fixes only enabled
this for ivybridge, but some recent bug reports indicate that we
need this on Sandybridge, too. But in a slightly different flavour
and with other fixes and reworks on top. Additionally there are some
forcewake cleanup patches heading to -next that would conflict with
currrent -fixes.
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>
These are all user-trigerable, so tune down their loudness a notch.
For some of these we have i-g-t tests (because they prevent
newly-discovered bugs), without this patches running the test suite
leaves behind a dirty dmesg.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This confuses our domain tracking and can (for gtt write domains) lead
to a subsequent oops.
Tested by tests/gem_exec_bad_domains from i-g-t.
Reviewed-by: Eric Anholt <eric@anholt.net>
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>
... and add a helpr function for the places where we want a flag.
This way we can use ring->id to index into arrays.
v2: Resurrect the missing beautification-space Chris Wilson noted.
I'm moving this space around because I'll reuse ring_str in the next
patch.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
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>
* 'drm-core-next' of git://people.freedesktop.org/~airlied/linux: (307 commits)
drm/nouveau/pm: fix build with HWMON off
gma500: silence gcc warnings in mid_get_vbt_data()
drm/ttm: fix condition (and vs or)
drm/radeon: double lock typo in radeon_vm_bo_rmv()
drm/radeon: use after free in radeon_vm_bo_add()
drm/sis|via: don't return stack garbage from free_mem ioctl
drm/radeon/kms: remove pointless CS flags priority struct
drm/radeon/kms: check if vm is supported in VA ioctl
drm: introduce drm_can_sleep and use in intel/radeon drivers. (v2)
radeon: Fix disabling PCI bus mastering on big endian hosts.
ttm: fix agp since ttm tt rework
agp: Fix multi-line warning message whitespace
drm/ttm/dma: Fix accounting error when calling ttm_mem_global_free_page and don't try to free freed pages.
drm/ttm/dma: Only call set_pages_array_wb when the page is not in WB pool.
drm/radeon/kms: sync across multiple rings when doing bo moves v3
drm/radeon/kms: Add support for multi-ring sync in CS ioctl (v2)
drm/radeon: GPU virtual memory support v22
drm: make DRM_UNLOCKED ioctls with their own mutex
drm: no need to hold global mutex for static data
drm/radeon/benchmark: common modes sweep ignores 640x480@32
...
Fix up trivial conflicts in radeon/evergreen.c and vmwgfx/vmwgfx_kms.c
These registers are automatically incremented by the hardware during
transform feedback to track where the next streamed vertex output
should go. Unlike the previous generation, which had a packet for
setting the corresponding registers to a defined value, gen7 only has
MI_LOAD_REGISTER_IMM to do so. That's a secure packet (since it loads
an arbitrary register), so we need to do it from the kernel, and it
needs to be settable atomically with the batchbuffer execution so that
two clients doing transform feedback don't stomp on each others'
state.
Instead of building a more complicated interface involcing setting the
registers to a specific value, just set them to 0 when asked and
userland can tweak its pointers accordingly.
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
The docs say this is required for Gen7, and since the bit was added for
Gen6, we are also setting it there pit pf paranoia. Particularly as
Chris points out, if PIPE_CONTROL counts as a 3d state packet.
This was found through doc inspection by Ken and applies to Gen6+;
Reported-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Keith Packard <keithp@keithp.com>
dev_priv keeps track of the current addressing mode that gets set at
execbuffer time. Unfortunately the existing code was doing this before
acquiring struct_mutex which leaves a race with another thread also
doing an execbuffer. If that wasn't bad enough, relocate_slow drops
struct_mutex which opens a much more likely error where another thread
comes in and modifies the state while relocate_slow is being slow.
The solution here is to just defer setting this state until we
absolutely need it, and we know we'll have struct_mutex for the
remainder of our code path.
v2: Keith noticed a bug in the original patch.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>
Semaphores still cause problems on some machines:
> From Udo Steinberg:
>
> With Linux-3.2-rc6 I'm frequently seeing GPU hangs when large amounts of
> text scroll in an xterm, such as when extracting a tar archive. Such as this
> one (note the timestamps):
>
> I can reproduce it fairly easily with something
> as simple as:
>
> while true; do dmesg; done
This patch turns them off on SNB while leaving them on for IVB.
Reported-by: Udo Steinberg <udo@hypervisor.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Eugeni Dodonov <eugeni@dodonov.net>
Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds a default setting for semaphores parameter, and enables
semaphores by default on IVB.
For now, as semaphores interaction with VTd causes random issues on
SNB, we do not enable them by default. But they can still be enabled
via the semaphores=1 kernel parameter.
v2: enables semaphores on SNB when IO remapping is disabled, with base
on Keith Packard patch.
CC: Daniel Vetter <daniel.vetter@ffwll.ch>
CC: Ben Widawsky <ben@bwidawsk.net>
CC: Keith Packard <keithp@keithp.com>
CC: Jesse Barnes <jbarnes@virtuousgeek.org>
CC: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=42696
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=40564
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=41353
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=38862
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
While I think the previous code is correct, it was hard to follow and
hard to debug. Since we already have a ring abstraction, might as well
use it to handle the semaphore updates and compares.
I don't expect this code to make semaphores better or worse, but you
never know...
v2:
Remove magic per Keith's suggestions.
Ran Daniel's gem_ring_sync_loop test on this.
v3:
Ignored one of Keith's suggestions.
v4:
Removed some bloat per Daniel's recommendation.
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
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>
Along the fast path for relocation handling, we attempt to copy directly
from the user data structures whilst holding our mutex. This causes
lockdep to warn about circular lock dependencies if we need to pagefault
the user pages. [Since when handling a page fault on a mmapped bo, we
need to acquire the struct mutex whilst already holding the mm
semaphore, it is then verboten to acquire the mm semaphore when already
holding the struct mutex. The likelihood of the user passing in the
relocations contained in a GTT mmaped bo is low, but conceivable for
extreme pathology.] In order to force the mm to return EFAULT rather
than handle the pagefault, we therefore need to disable pagefaults
across the relocation fast path.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Andi Kleen narrowed his GPU hangs on his Sugar Bay (SNB desktop) rev 09
down to the use of GPU semaphores, and we already know that they appear
broken up to Huron River (mobile) rev 08. (I'm optimistic that disabling
GPU semaphores is simply hiding another bug by the latency and
side-effects of the additional device interaction it introduces...)
However, use of semaphores is a massive performance improvement... Only
as long as the system remains stable. Enable at your peril.
Reported-by: Andi Kleen <andi-fd@firstfloor.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=33921
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This seems to be running stably on my test laptop, so hopefully the
reported hangs where just symptoms of other bugs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Userspace has a legitimate requirement to use a delta that points to
outside of the target bo, and so we need to enable this. (As this is an
abi break, albeit a relaxation of the current restrictions, mark the change
with a new flag.)
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>
As we just need a temporary array whilst performing the relocations for
the execbuffer, first attempt to allocate using kmalloc even if it is
not of order page-0. This avoids the overhead of remapping the
discontiguous array and so gives a moderate boost to execution
throughput.
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>
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>
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>
Move code around and invoke iomem annotation in a few more places in
order to silence sparse. Still a few more iomem annotations to go...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Hopefully, this is a temporary measure whilst the root cause is
understood. At the moment, we experience a hard hang whilst looping
urbanterror that has been identified as a result of the use of
semaphores, but so far only on SNB mobile.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=32752
Tested-by: mengmeng.meng@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
After reordering the sequence of relocating objects, commit 6fe4f1404,
we can no longer rely on seeing all reloc targets prior to performing
the relocation. As a result we were ignoring the need to flush objects
from the render cache and invalidate the sampler caches, resulting in
rendering glitches. So we need to clear the relocation domains earlier.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
On the fault path, commit 6fe4f140 introduction a regression whereby it
changed the sequence of the objects but continued to use the original
ordering of relocation entries. The result was that incorrect GTT offsets
were being fed into the execbuffer causing lots of misrendering and
potential hangs.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As the mappable portion of the aperture is always a small subset at the
start of the GTT, it is allocated preferentially by drm_mm. This is
useful in case we ever need to map an object later. However, if you have
a large object that can consume the entire mappable region of the
GTT this prevents the batchbuffer from fitting and so causing an error.
Instead allocate all those that require a mapping up front in order to
improve the likelihood of finding sufficient space to bind them.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Before releasing the lock in order to copy the relocation list from user
pages, we need to drop all the object references as another thread may
usurp and execute another batchbuffer before we reacquire the lock.
However, the code was buggy and failed to clear the list...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
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>
As we provide a list of all objects that will be accessed from the
batchbuffer, we can build a lut of the handles associated with those
objects for this invocation and use that to avoid the overhead of
looking up those objects again for every relocation.
The cost of building and searching a small hash table is much less than
that of acquiring a spinlock, searching a radix tree and manipulating an
atomic refcnt per relocation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Userspace should not have been declaring that it needed fenced GPU
access with gen4+ as those GPUs have no fenced commands, but to be on
the safe side it is easier to ignore userspace in case they did.
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>
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>
This makes the various rings more consistent by removing the anomalous
handing of the rendering ring execbuffer dispatch.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As the error occurred on the current object, it means that its state was
not changed and so it should be excluded from the unwind.
Reported-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>
Ben Widawsky