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
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>
Let's allow GCC to optimize better.
This exposed some five unused functions, but this patch doesn't remove them.
Signed-off-by: Lauri Kasanen <cand@gmx.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Making it easier to control when it is executed.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
The IB pool is in gart memory, so it is completely
superfluous to unpin / repin it on suspend / resume.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Removing all the different error messages and
having just one standard behaviour over all
chipset generations.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Each ring type may need a different variant.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König<christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Required for future functionality.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
If accel is not working many subsystem such as the ib pool might not be
initialized properly that can lead to segfault inside kernel when cs
ioctl is call with non working acceleration. To avoid this make sure
the accel working flag is false when an error in GPU startup happen and
return EBUSY from cs ioctl if accel is not working.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Somewhat specializaed sub-allocator designed to perform sub-allocation
for command buffer not only for current cs ioctl but for future command
submission ioctl as well. Patch also convert current ib pool to use
the sub allocator. Idea is that ib poll buffer can be share with other
command buffer submission not having 64K granularity.
v2 Harmonize pool handling and add suspend/resume callback to pin/unpin
sa bo (tested on rv280, rv370, r420, rv515, rv610, rv710, redwood, cayman,
rs480, rs690, rs880)
v3 Simplify allocator
v4 Fix radeon_ib_get error path to properly free fence
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Add a start fence driver helper function which will be call
once for each ring and will compute cpu/gpu addr for fence
depending on wether to use wb buffer or scratch reg.
This patch replace initialize fence driver separately which
was broken in regard of GPU lockup. The fence list for created,
emited, signaled must be initialize once and only from the
asic init callback not from the startup call back which is
call from the gpu reset.
v2: With this in place we no longer need to know the number of
rings in fence_driver_init, also writing to the scratch reg
before knowing its offset is a bad idea.
v3: rebase on top of change to previous patch in the serie
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
For supporting multiple CP ring buffers, async DMA
engines and UVD. We still need a way to synchronize
between engines.
v2 initialize unused fence driver ring to avoid issue in
suspend/unload
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
When writeback is enabled, the GPU shadows writes to certain
registers into a buffer in memory. The driver can then read
the values from the shadow rather than reading back from the
register across the bus. Writeback can be disabled by setting
the no_wb module param to 1.
On r6xx/r7xx/evergreen, the following registers are shadowed:
- CP scratch registers
- CP read pointer
- IH write pointer
On r1xx-rr5xx, the following registers are shadowed:
- CP scratch registers
- CP read pointer
v2:
- Combine wb patches for r6xx-evergreen and r1xx-r5xx
- Writeback is disabled on AGP boards since it tends to be
unreliable on AGP using the gart.
- Check radeon_wb_init return values properly.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
On systems using kexec, the new kernel is booted straight from the old kernel, without any warning to the graphics driver. So the GPU is basically left as-is in a running state, however the CPU side is completly reset.
Without stating the saneness of anyone using kexec on live systems, we should at least try not to crash the GPU. This patch resets 3 registers to 0 that could cause bad things to happen to the running system.
This allows kexec to work on a Power6/RN50 system.
Signed-off-by: Dave Airlie <airlied@redhat.com>
The asics in question have the following requirements with regard to
their gart setups:
1. The GART aperture size has to be in the form of 2^X bytes, where X is from 25 to 31
2. The GART aperture MC base has to be aligned to a boundary equal to the size of the
aperture.
3. The GART page table has to be aligned to the boundary equal to the size of the table.
4. The GART page table size is: table_entry_size * (aperture_size / page_size)
5. The GART page table has to be allocated in non-paged, non-cached, contiguous system
memory.
This patch takes care 2. The rest should already be handled properly.
This fixes a regression noticed by: Torsten Kaiser <just.for.lkml@googlemail.com>
Tested-by: Torsten Kaiser <just.for.lkml@googlemail.com>
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
- Separate dynpm and profile based power management methods. You can select the pm method
by echoing the selected method ("dynpm" or "profile") to power_method in sysfs.
- Expose basic 4 profile in profile method
"default" - default clocks
"auto" - select between low and high based on ac/dc state
"low" - DC, low power mode
"high" - AC, performance mode
The current base profile is "default", but it should switched to "auto" once we've tested
on more systems. Switching the state is a matter of echoing the requested profile to
power_profile in sysfs. The lowest power states are selected automatically when dpms turns
the monitors off in all states but default.
- Remove dynamic fence-based reclocking for the moment. We can revisit this later once we
have basic pm in.
- Move pm init/fini to modesetting path. pm is tightly coupled with display state. Make sure
display side is initialized before pm.
- Add pm suspend/resume functions to make sure pm state is properly reinitialized on resume.
- Remove dynpm module option. It's now selectable via sysfs.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This simplify and improve GPU reset for R1XX-R6XX hw, it's
not 100% reliable here are result:
- R1XX/R2XX works bunch of time in a row, sometimes it
seems it can work indifinitly
- R3XX/R3XX the most unreliable one, sometimes you will be
able to reset few times, sometimes not even once
- R5XX more reliable than previous hw, seems to work most
of the times but once in a while it fails for no obvious
reasons (same status than previous reset just no same
happy ending)
- R6XX/R7XX are lot more reliable with this patch, still
it seems that it can fail after a bunch (reset every
2sec for 3hour bring down the GPU & computer)
This have been tested on various hw, for some odd reasons
i wasn't able to lockup RS480/RS690 (while they use to
love locking up).
Note that on R1XX-R5XX the cursor will disapear after
lockup haven't checked why, switch to console and back
to X will restore cursor.
Next step is to record the bogus command that leaded to
the lockup.
V2 Fix r6xx resume path to avoid reinitializing blit
module, use the gpu_lockup boolean to avoid entering
inifinite waiting loop on fence while reiniting the GPU
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Patch rename gpu_reset to asic_reset in prevision of having
gpu_reset doing more stuff than just basic asic reset.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
- rs780/880 were using the wrong bandwidth functions
- convert r1xx-r4xx to use the same pm sclk/mclk structs as
r5xx+
- move bandwidth setup to a common function
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
In essence this creates a home for all asic specific declarations in
radeon_asic.h
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Get rid of _location and use _start/_end also simplify the
computation of vram_start|end & gtt_start|end. For R1XX-R2XX
we place VRAM at the same address of PCI aperture, those GPU
shouldn't have much memory and seems to behave better when
setup that way. For R3XX and newer we place VRAM at 0. For
R6XX-R7XX AGP we place VRAM before or after AGP aperture this
might limit to limit the VRAM size but it's very unlikely.
For IGP we don't change the VRAM placement.
Tested on (compiz,quake3,suspend/resume):
PCI/PCIE:RV280,R420,RV515,RV570,RV610,RV710
AGP:RV100,RV280,R420,RV350,RV620(RPB*),RV730
IGP:RS480(RPB*),RS690,RS780(RPB*),RS880
RPB: resume previously broken
V2 correct commit message to reflect more accurately the bug
and move VRAM placement to 0 for most of the GPU to avoid
limiting VRAM.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
In suspend path we unmap the GART table while in cleaning up
path we will unbind buffer and thus try to write to unmapped
GART leading to oops. In order to avoid this we don't call the
suspend path in cleanup path. Cleanup path is clever enough
to desactive GPU like the suspend path is doing, thus this was
redondant.
Tested on: RV370, R420, RV515, RV570, RV610, RV770 (all PCIE)
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
R300 family will hard lockup if host path read cache flush is
done through MMIO to HOST_PATH_CNTL. But scheduling same flush
through ring seems harmless. This patch remove the hdp_flush
callback and add a flush after each fence emission which means
a flush after each IB schedule. Thus we should have same behavior
without the hard lockup.
Tested on R100,R200,R300,R400,R500,R600,R700 family.
V2: Adjust fence counts in r600_blit_prepare_copy()
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
On resume on my rv530 laptop surface cntl was left disabled, so
wierd stuff would happen with rendering to a tiled front buffer.
This checks if the surface regs are assigned to bos and reprograms
the surface registers on resume using the same path that clears
them all on init.
Signed-off-by: Dave Airlie <airlied@redhat.com>
The locking & protection of radeon object was somewhat messy.
This patch completely rework it to now use ttm reserve as a
protection for the radeon object structure member. It also
shrink down the various radeon object structure by removing
field which were redondant with the ttm information. Last it
converts few simple functions to inline which should with
performances.
airlied: rebase on top of r600 and other changes.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
We really don't need to process every irq that comes in, we only
really want to do SW irq processing when we are actually waiting for
a fence to pass. I'm not 100% sure this is race free esp on non-MSI systems
so it needs some testing.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Avivo hw have vblank interrupt in different place, fixes
irq handling (especialy irq disabling while suspending or
shuting down the module).
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This remove old init path and allow code cleanup, now all hw
use the new init path, see top of radeon.h for description of
this.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Convert the r520 asic support to new init path, change are smaller than
previous one as most of the architecture is now in place and more code
sharing can happen btw various asics.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@linux.ie>
Convert the rv515 asic support to new init path also add an explanation
in radeon.h about the new init path. There is also few cleanups
associated with this change (others asic calling rv515 helper
functions).
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@linux.ie>
GART static one time initialization was mixed up with GART
enabling/disabling which could happen several time for instance
during suspend/resume cycles. This patch splits all GART
handling into 4 differents function. gart_init is for one
time initialization, gart_deinit is called upon module unload
to free resources allocated by gart_init, gart_enable enable
the GART and is intented to be call after first initialization
and at each resume cycle or reset cycle. Finaly gart_disable
stop the GART and is intended to be call at suspend time or
when unloading the module.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
radeon_share.h was begining to give problem with include order in
respect of radeon.h. It's easier and also i think cleaner to move
what was in radeon_share.h into radeon.h. At the same time use the
extern keyword for function shared accross the module.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
If an rn50/r100/m6/m7 GPU has < 64MB RAM, i.e. 8/16/32, the
aperture used to calculate the MC_FB_LOCATION needs to be worked
out from the CONFIG_APER_SIZE register, and not the actual vram size.
TTM VRAM size was also being initialised wrong, use actual vram size
to initialise it.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Fix bandwidth computation and crtc priority in memory controller
so that crtc memory request are fullfill in time to avoid display
artifact.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Doing this like the DDX seems like the most sure fire way to avoid
having to reinvent it slowly and painfully. At the moment we keep
getting things wrong with aper vs vram, so we know the DDX does it right.
booted on PCI r100, PCIE rv370, IGP rs400.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Add kernel modesetting support to radeon driver, use the ttm memory
manager to manage memory and DRM/GEM to provide userspace API.
In order to avoid backward compatibility issue and to allow clean
design and code the radeon kernel modesetting use different code path
than old radeon/drm driver.
When kernel modesetting is enabled the IOCTL of radeon/drm
driver are considered as invalid and an error message is printed
in the log and they return failure.
KMS enabled userspace will use new API to talk with the radeon/drm
driver. The new API provide functions to create/destroy/share/mmap
buffer object which are then managed by the kernel memory manager
(here TTM). In order to submit command to the GPU the userspace
provide a buffer holding the command stream, along this buffer
userspace have to provide a list of buffer object used by the
command stream. The kernel radeon driver will then place buffer
in GPU accessible memory and will update command stream to reflect
the position of the different buffers.
The kernel will also perform security check on command stream
provided by the user, we want to catch and forbid any illegal use
of the GPU such as DMA into random system memory or into memory
not owned by the process supplying the command stream. This part
of the code is still incomplete and this why we propose that patch
as a staging driver addition, future security might forbid current
experimental userspace to run.
This code support the following hardware : R1XX,R2XX,R3XX,R4XX,R5XX
(radeon up to X1950). Works is underway to provide support for R6XX,
R7XX and newer hardware (radeon from HD2XXX to HD4XXX).
Authors:
Jerome Glisse <jglisse@redhat.com>
Dave Airlie <airlied@redhat.com>
Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Adis Hamzić