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
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>
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>
After GPU lockup VRAM gart table is unpinned and thus its pointer
becomes unvalid. This patch move the unpin code to a common helper
function and set pointer to NULL so that page update code can check
if it should update GPU page table or not. That way bo still bound
to GART can be unbound (pci_unmap_page for all there page) properly
while there is no need to update the GPU page table.
V2 move the test for null gart out of the loop, small optimization
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This was previously done for r300 only. Use %016llX instead of %08X for
printing the table address.
Also fix typos in gart warning messages.
Signed-off-by: Tormod Volden <debian.tormod@gmail.com>
Reviewed-by: Michel Dänzer <michel@daenzer.net>
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>
We used to limit the rs4xx gart aperture to 32 MB, but I suspect
that was due to not meeting the alignment requirements of the
aperture. This patch should only be applied after:
"drm/radeon/kms: fix gtt MC base alignment on rs4xx/rs690/rs740 asics"
has been applied.
This patch should probably soak for a bit in d-r-t.
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>
radeon_gart_fini might call GART unbind callback function which
might try to access GART table but if gart_disable is call first
the GART table will be unmapped so any access to it will oops.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
I missed rs4xx in 7f1e613daf0fdd0884316ab25a749db3c671329e
Fixes fdo bug 27219.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Look up i2c bus in the power table and expose it.
You'll need to load a hwmon driver for any chips
on the bus, this patch just exposes the bus.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.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>
this uses a new entrypoint to invalidate gart entries instead of using 0.
Changed to rather than pointing to 0 address point empty entry to dummy
page. This might help to avoid hard lockup if for some wrong
reasons GPU try to access unmapped GART entry.
I'm not 100% sure this is going to work, we probably need to allocate
a dummy page and point all the GTT entries at it similiar to what AGP does.
but we can test this first I suppose.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Boot testing on my rs480 laptop found the MC idle never happened
on startup, a quick check with AMD found the idle bit is in a different
place on the rs4xx than r300.
Implement a new rs400 mc idle function to fix this.
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>
This detects if the sideport memory is enabled and
if it is VRAM is evicted on suspend/resume.
This should fix s/r issues on some IGPs.
Signed-off-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>
We might not hit this yet, but when if we do any sort of writeback
we really need to enable PCI bus mastering on these systems from
what I can see.
This enables PCI BM on all radeons that require it.
Signed-off-by: Dave Airlie <airlied@redhat.com>
This fixes suspend/resume on my rc410 motherboard, it restores
the memory controller setup before posting the GPU, since it seems
to need the MC_FB_LOCATION setup correctly.
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>
Also cleanup register specific to RS400/RS480. This patch also fix
legacy VGA register used to disable VGA access we were programming
wrong register. Now we should properly disable VGA on r100 up to
rs400 asics. Note that RS400/RS480 resume is broken, it hangs the
computer while reprogramming dynamic clock, doesn't work either
without that patch. We need to spend more time investigating this
issue. Version 2 of the patch remove dead code that was left
commented out in the previous version. Version 3 correct the
placement on IGP of the VRAM inside GPU address space to match the
stollen RAM placement of IGP.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
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>
Adis Hamzić