This fixes a problem with GPU resets and TLB flushes on SI/CIK.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It isn't necessary for command streams generated by the kernel (at least
not while we aren't storing ring or indirect buffers in VRAM).
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Doesn't seem necessary, the GART table memory should be persistent.
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Replace occurrences of "v & 0xffffffff" with lower_32_bits(v)
when it's next to an upper_32_bits(v). Also remove unnecessary
"upper_32_bits(v) & 0xffffffff" code snippets.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch makes it possible to decide how many address
bits are spend on the page directory vs the page tables.
v2: remove unintended change
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch implements support for VRAM page table entry compression.
PTE construction is enhanced to identify physically contiguous page
ranges and mark them in the PTE fragment field. L1/L2 TLB support is
enabled for 64KB (SI/CIK) and 256KB (NI) PTE fragments, significantly
improving TLB utilization for VRAM allocations.
Linear store bandwidth is improved from 60GB/s to 125GB/s on Pitcairn.
Unigine Heaven 3.0 sees an average improvement from 24.7 to 27.7 FPS
on default settings at 1920x1200 resolution with vsync disabled.
See main comment in radeon_vm.c for a technical description.
v2 (chk): rebased and simplified.
v3 (chk): add missing hw setup
v4 (chk): rebased on current drm-fixes-3.15
v5 (chk): fix comments and commit text
Signed-off-by: Jay Cornwall <jay@jcornwall.me>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTJlUvAAoJEHm+PkMAQRiGOhYH/1I+Bc7N7Rjr6QQAtBIy0GPC
XMqSE/gpgxlvRneQbQsvTUlPnWRhgzLGendT9HFKawkaQ0UNuZdRVyBHGFmpuED8
RlbicVVuuEZabrxEnCd7UPvYvEyK5pLIFpCRs5B+ManB1qLki2Ar03ymH1NRxOde
edmPbSUFo2aONITrEBm7tqT3cShTmBaDGP/zU0TNDMNrpVVDbHZolSNu2z4xOTa5
GqAOEbluLQ6jP3yxWur/V3Lk3W7pB6TabfX4o6UZu0F3iFnJxRMIzHXrI3o4yLTj
HEwmB3npfc8DIUk4oik7RkN+aqxDcdg/rBLQD63+xxt6zCkP+0q16brC0R67qWE=
=n9Ml
-----END PGP SIGNATURE-----
Merge tag 'v3.14-rc7' into drm-next
Linux 3.14-rc7
Backmerge to help out Intel guys.
Moving the pm resume up in the init order to fix
dpm seems to have regressed somes cases with the old
pm code. Move it back to late resume.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The reason for the false positives was fixed quite some time ago and since
most engines can still execute NOPs while being locked up it leads to false
negatives.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
In all cases where it really matters we are using the read functions anyway.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
If we are not able to properly initialize one of the gpu
engines for buffer paging, we limit vram to the size of
the cpu visible aperture. We generally either use the gfx
or dma engine to do this. Clean up the size limiting code
to only adjust the size based on what ring is selected
for buffer paging rather than making assumptions about which
engine is selected for paging.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
We need to set the engine bit to select the ME and
also set the full cache bit. Should help stability
on TN and cayman.
V2: fix up surface sync in ib execute as well
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
drm-intel-next-2014-01-10:
- final bits for runtime D3 on Haswell from Paul (now enabled fully)
- parse the backlight modulation freq information in the VBT from Jani
(but not yet used)
- more watermark improvements from Ville for ilk-ivb and bdw
- bugfixes for fastboot from Jesse
- watermark fix for i830M (but not yet everything)
- vlv vga hotplug w/a (Imre)
- piles of other small improvements, cleanups and fixes all over
Note that the pull request includes a backmerge of the last drm-fixes
pulled into Linus' tree - things where getting a bit too messy. So the
shortlog also contains a bunch of patches from Linus tree. Please yell if
you want me to frob it for you a bit.
* 'drm-intel-next' of git://people.freedesktop.org/~danvet/drm-intel: (609 commits)
drm/i915/bdw: make sure south port interrupts are enabled properly v2
drm/i915: Include more information in disabled hotplug interrupt warning
drm/i915: Only complain about a rogue hotplug IRQ after disabling
drm/i915: Only WARN about a stuck hotplug irq ONCE
drm/i915: s/hotplugt_status_gen4/hotplug_status_g4x/
pci config reset is a low level reset that resets
the entire chip from the bus interface. It can
be more reliable if soft reset fails.
v2: put behind module parameter
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fill in asic family specific versions rather than
using the generic version. This lets us handle asic
specific differences more easily. In this case, we
disable sw swapping of the rtpr writeback value on
r6xx+ since the hw does it for us. Fixes bogus
rptr readback on BE systems.
v2: remove missed cpu_to_le32(), add comments
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We need more control over the ordering of dpm init with
respect to the rest of the asic. Specifically, the SMC
has to be initialized before the rlc and cg/pg. The pm
code currently initializes late in the driver, but we need
it to happen much earlier so move pm handling into the asic
specific callbacks.
This makes dpm more reliable and makes clockgating work
properly on CIK parts and should help on SI parts as well.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We need to reorder the driver init sequence to better accomodate
dpm which needs to be loaded earlier in the init sequence. Move
fw init up so that it's available for dpm init.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Bit a bit -fixes pull request in the merge window than usual dua to two
feauture-y things:
- Display CRCs are now enabled on all platforms, including the odd DP case
on gm45/vlv. Since this is a testing-only feature it should ever hurt,
but I figured it'll help with regression-testing -fixes. So I left it
in and didn't postpone it to 3.14.
- Display power well refactoring from Imre. Would have caused major pain
conflict with the bdw stage 1 patches if I'd postpone this to -next.
It's only an relatively small interface rework, so shouldn't cause pain.
It's also been in my tree since almost 3 weeks already.
That accounts for about two thirds of the pull, otherwise just bugfixes:
- vlv backlight fix from Jesse/Jani
- vlv vblank timestamp fix from Jesse
- improved edp detection through vbt from Ville (fixes a vlv issue)
- eDP vdd fix from Paulo
- fixes for dvo lvds on i830M
- a few smaller things all over
Note: This contains a backmerge of v3.12. Since the -internal branch
always applied on top of -nightly I need that unified base to merge bdw
patches. So you'll get a conflict with radeon connector props when pulling
this (and nouveau/master will also conflict a bit when Ben doesn't
rebase). The backmerge itself only had conflicts in drm/i915.
There's also a tiny conflict between Jani's backlight fix and your sysfs
lifetime fix in drm-next.
* tag 'drm-intel-fixes-2013-11-07' of git://people.freedesktop.org/~danvet/drm-intel: (940 commits)
drm/i915/vlv: use per-pipe backlight controls v2
drm/i915: make backlight functions take a connector
drm/i915: move opregion asle request handling to a work queue
drm/i915/vlv: use PIPE_START_VBLANK interrupts on VLV
drm/i915: Make intel_dp_is_edp() less specific
drm/i915: Give names to the VBT child device type bits
drm/i915/vlv: enable HDA display audio for Valleyview2
drm/i915/dvo: call ->mode_set callback only when the port is running
drm/i915: avoid unclaimed registers when capturing the error state
drm/i915: Enable DP port CRC for the "auto" source on g4x/vlv
drm/i915: scramble reset support for DP port CRC on vlv
drm/i915: scramble reset support for DP port CRC on g4x
drm/i916: add "auto" pipe CRC source
...
Conflicts:
MAINTAINERS
drivers/gpu/drm/i915/intel_panel.c
drivers/gpu/drm/nouveau/core/subdev/mc/base.c
drivers/gpu/drm/radeon/atombios_encoders.c
drivers/gpu/drm/radeon/radeon_connectors.c
The DMA ring seems to be stable now.
v2: remove pt_ring_index as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex writes:
This is the radeon drm-next request. Big changes include:
- support for dpm on CIK parts
- support for ASPM on CIK parts
- support for berlin GPUs
- major ring handling cleanup
- remove the old 3D blit code for bo moves in favor of CP DMA or sDMA
- lots of bug fixes
[airlied: fix up a bunch of conflicts from drm_order removal]
* 'drm-next-3.12' of git://people.freedesktop.org/~agd5f/linux: (898 commits)
drm/radeon/dpm: make sure dc performance level limits are valid (CI)
drm/radeon/dpm: make sure dc performance level limits are valid (BTC-SI) (v2)
drm/radeon: gcc fixes for extended dpm tables
drm/radeon: gcc fixes for kb/kv dpm
drm/radeon: gcc fixes for ci dpm
drm/radeon: gcc fixes for si dpm
drm/radeon: gcc fixes for ni dpm
drm/radeon: gcc fixes for trinity dpm
drm/radeon: gcc fixes for sumo dpm
drm/radeonn: gcc fixes for rv7xx/eg/btc dpm
drm/radeon: gcc fixes for rv6xx dpm
drm/radeon: gcc fixes for radeon_atombios.c
drm/radeon: enable UVD interrupts on CIK
drm/radeon: fix init ordering for r600+
drm/radeon/dpm: only need to reprogram uvd if uvd pg is enabled
drm/radeon: check the return value of uvd_v1_0_start in uvd_v1_0_init
drm/radeon: split out radeon_uvd_resume from uvd_v4_2_resume
radeon kms: fix uninitialised hotplug work usage in r100_irq_process()
drm/radeon/audio: set up the sads on DCE3.2 asics
drm/radeon: fix handling of variable sized arrays for router objects
...
Conflicts:
drivers/gpu/drm/i915/i915_dma.c
drivers/gpu/drm/i915/i915_gem_dmabuf.c
drivers/gpu/drm/i915/intel_pm.c
drivers/gpu/drm/radeon/cik.c
drivers/gpu/drm/radeon/ni.c
drivers/gpu/drm/radeon/r600.c
The vram scratch buffer needs to be initialized
before the mc is programmed otherwise we program
0 as the GPU address of the default GPU fault
page. In most cases we put vram at zero anyway and
reserve a page for the legacy vga buffer so in practice
this shouldn't cause any problems, but better to make
it correct.
Was changed in:
6fab3febf6
Reported-by: FrankR Huang <FrankR.Huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Similar to DCE4/5, but supports multiple audio pins
which can be assigned per afmt block.
v2: rework the driver to handle more than one audio
pin.
v3: try different dto reg
v4: properly program dto
v5 (ck): change dto programming order
v6: program speaker allocation block
v7: rebase
v8: rebase on Rafał's changes
v9: integrated Rafał's comments, update to latest
drm_edid_to_speaker_allocation API
v10: add missing line break in error message
v11: add back audio enabled messages
v12: fix copy paste typo in r600_audio_enable
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Rafał Miłecki <zajec5@gmail.com>
Similar to separating the UVD code, just put the DMA
functions into separate files.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Our different hardware blocks are actually completely
separated, so it doesn't make much sense any more to
structure the code by pure chipset generations.
Start restructuring the code by separating our the UVD block.
v2: updated commit message
v3: rebased and restructurized start/stop functions for kv dpm.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Now that we have callbacks for [rw]ptr handling we can
remove the special handling for the DMA rings and use
the callbacks instead.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The hardware just doesn't support this correctly.
Disable it before we accidentally write anywhere we shouldn't.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When we PG (powergate) UVD, we need to re-initialize it
before we can use it again.
v2: rebase on UVD stop fixes
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The smc ucode is required for dpm (dynamic power
management), but if it's missing just skip dpm setup
and don't disable acceleration.
Should fix:
https://bugs.freedesktop.org/show_bug.cgi?id=67876
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For r6xx+ asics. This mirrors the behavior of pre-r6xx
asics. We need to program the MC even if something
else in startup() fails. Failure to do so results in
an unusable GPU.
Based on a fix from: Mark Kettenis <kettenis@openbsd.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Removing the clock/power or resetting the VCPU can cause
hangs if that happens in the middle of a register write.
Stall the memory and register bus before putting the VCPU
into reset. Keep it in reset when unloading the module or
suspending.
Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Last driver and pretty obviously a major user of this little function.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@gmail.com>
Helpful for debugging GPUVM errors as we can see what
hw block and page generated the fault in the log.
v2: simplify fault decoding
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Avoid creating temporary platform device that will lead to issue
when several radeon gpu are in same computer. Instead directly use
the radeon device for requesting firmware.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This adds dpm support for cayman asics. This includes:
- clockgating
- dynamic engine clock scaling
- dynamic memory clock scaling
- dynamic voltage scaling
- dynamic pcie gen1/gen2 switching (requires additional acpi support)
- power containment
- shader power scaling
Set radeon.dpm=1 to enable.
v2: fold in tdp fix
v3: fix indentation
v4: fix 64 bit div
v5: attempt to fix state enable
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
This is required for certain advanced functionality.
v2: save/restore list takes dword offsets
v3: rebase on gpu reset changes
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The current radeon driver initialization routines, when using KMS, are written
so that the IRQ installation routine is called before initializing the WB buffer
and the CP rings. With some ASICs, though, the IRQ routine tries to access the
GFX_INDEX ring causing a call to RREG32 with the value of -1 in
radeon_fence_read. This, in turn causes the system to completely hang with some
cards, requiring a hard reset.
A call stack that can cause such a hang looks like this (using rv515 ASIC for the
example here):
* rv515_init (rv515.c)
* radeon_irq_kms_init (radeon_irq_kms.c)
* drm_irq_install (drm_irq.c)
* radeon_driver_irq_preinstall_kms (radeon_irq_kms.c)
* rs600_irq_process (rs600.c)
* radeon_fence_process - due to SW interrupt (radeon_fence.c)
* radeon_fence_read (radeon_fence.c)
* hang due to RREG32(-1)
The patch moves the IRQ installation to the card startup routine, after the ring
has been initialized, but before the IRQ has been set. This fixes the issue, but
requires a check to see if the IRQ is already installed, as is the case in the
system resume codepath.
I have tested the patch on three machines using the rv515, the rv770 and the
evergreen ASIC. They worked without issues.
This seems to be a known issue and has been reported on several bug tracking
sites by various distributions (see links below). Most of reports recommend
booting the system with KMS disabled and then enabling KMS by reloading the
radeon module. For some reason, this was indeed a usable workaround, however,
UMS is now deprecated and disabled by default.
Bug reports:
https://bugzilla.redhat.com/show_bug.cgi?id=845745https://bugs.launchpad.net/ubuntu/+source/linux/+bug/561789https://bbs.archlinux.org/viewtopic.php?id=156964
Signed-off-by: Adis Hamzić <adis@hamzadis.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
PTE/PDE doesn't support a single update (count = 1). We had
previously disabled it since it we were hitting that case which
let to hangs. The PTE/PDE packet is much more efficient for VM
updates where it can be used.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König