Previous reset code leaded to computer hard lockup (need to unplug
the power too reboot the computer) on various configuration. This
patch change the reset code to avoid hard lockup. The GPU reset
is failing most of the time but at least user can log in remotely
or properly shutdown the computer.
Two issues were leading to hard lockup :
- Writting to the scratch register lead to hard lockup most likely
because the write back mecanism is in fuzy state after GPU lockup.
- Resetting the GPU memory controller and not reinitializing it
after leaded to hard lockup. We did only reinitialize in case of
successfull reset thus unsuccessfull reset quickly leaded to hard
lockup.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
* 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
drm/radeon/kms: add FireMV 2400 PCI ID.
drm/radeon/kms: allow R500 regs VAP_ALT_NUM_VERTICES and VAP_INDEX_OFFSET
drivers/gpu/radeon: Add MSPOS regs to safe list.
drm/radeon/kms: disable the tv encoder when tv/cv is not in use
drm/radeon/kms: adjust pll settings for tv
drm/radeon/kms: fix tv dac conflict resolver
drm/radeon/kms/evergreen: don't enable hdmi audio stuff
drm/radeon/kms/atom: fix dual-link DVI on DCE3.2/4.0
drm/radeon/kms: fix rs600 tlb flush
drm/radeon/kms: print GPU family and device id when loading
drm/radeon/kms: fix calculation of mipmapped 3D texture sizes
drm/radeon/kms: only change mode when coherent value changes.
drm/radeon/kms: more atom parser fixes (v2)
[airlied: fix V_A_N_V to not be safe and fix check to make sure only r500
- bump userspace version]
Signed-off-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
* 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: (29 commits)
drm/nouveau: bail out of auxch transaction if we repeatedly recieve defers
drm/nv50: implement gpio set/get routines
drm/nv50: parse/use some more de-magiced parts of gpio table entries
drm/nouveau: store raw gpio table entry in bios gpio structs
drm/nv40: Init some tiling-related PGRAPH state.
drm/nv50: Add NVA3 support in ctxprog/ctxvals generator.
drm/nv50: another dodgy DP hack
drm/nv50: punt hotplug irq handling out to workqueue
drm/nv50: preserve an unknown SOR_MODECTRL value for DP encoders
drm/nv50: Allow using the NVA3 new compute class.
drm/nv50: cleanup properly if PDISPLAY init fails
drm/nouveau: fixup the init failure paths some more
drm/nv50: fix instmem init on IGPs if stolen mem crosses 4GiB mark
drm/nv40: add LVDS table quirk for Dell Latitude D620
drm/nv40: rework lvds table parsing
drm/nouveau: detect vram amount once, and save the value
drm/nouveau: remove some unused members from drm_nouveau_private
drm/nouveau: Make use of TTM busy_placements.
drm/nv50: add more 0x100c80 flushy magic
drm/nv50: fix fbcon when framebuffer above 4GiB mark
...
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>
This patch cleanup the fence code, it drops the timeout field of
fence as the time to complete each IB is unpredictable and shouldn't
be bound.
The fence cleanup lead to GPU lockup detection improvement, this
patch introduce a callback, allowing to do asic specific test for
lockup detection. In this patch the CP is use as a first indicator
of GPU lockup. If CP doesn't make progress during 1second we assume
we are facing a GPU lockup.
To avoid overhead of testing GPU lockup frequently due to fence
taking time to be signaled we query the lockup callback every
500msec. There is plenty code comment explaining the design & choise
inside the code.
This have been tested mostly on R3XX/R5XX hw, in normal running
destkop (compiz firefox, quake3 running) the lockup callback wasn't
call once (1 hour session). Also tested with forcing GPU lockup and
lockup was reported after the 1s CP activity timeout.
V2 switch to 500ms timeout so GPU lockup get call at least 2 times
in less than 2sec.
V3 store last jiffies in fence struct so on ERESTART, EBUSY we keep
track of how long we already wait for a given fence
V4 make sure we got up to date cp read pointer so we don't have
false positive
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>
- 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>
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>
Version 2 of memory controller did break the initialization for
R3XX/R4XX hardware. This patch fix it.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
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>
r200 cards have dma engine which can be used to tranfer data
between vram and system memory.
r300 dma engine registers match r200 dma engine. Enabling
dma copy for r200 is simple as hooking r200 asic to already
existing function r300_copy_dma.
Rename r300_dma_copy to r200_dma_copyto reflect that supports
starts from r200 cards.
v2: Created a new asic object for r200 cards.
Signed-off-by: Pauli Nieminen <suokkos@gmail.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>
Switch some magic numbers to their proper defines.
The register header madness needs to be cleaned up
at some point.
Signed-off-by: Alex Deucher <alexdeucher@gmail.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>
In some case we weren't releasing the AGP device at module unloading.
This leaded to unfunctional AGP at next module load. This patch make
sure we release the AGP bus if we acquire it.
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>
There are 2 formats:
ATI1N: 64 bits per 4x4 block, one-channel format
ATI2N: 128 bits per 4x4 block, two-channel format
Signed-off-by: Dave Airlie <airlied@redhat.com>
Because hardware cannot disable all colorbuffers directly to do depth-only
rendering, a user should:
- disable reading from a colorbuffer in blending
- disable fastfill
- set the color channel mask to 0 to prevent writing to a colorbuffer
Signed-off-by: Dave Airlie <airlied@redhat.com>
This adds support for compressed textures to the r100->r500 CS
checker, it lets me run openarena and the demos in mesa fine.
Thanks to Maciej Cencora for initial comments.
Changes since v1:
fix calculations with Maciej formulas
Reviewed-by: Maciej Cencora <m.cencora@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This adds the relocations for texture tiling for KMS.
Signed-off-by: Maciej Cencora <m.cencora@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 DDX and radeonfb always set these regs to a sane value.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
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 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>
This avoids needing to do a kmalloc > PAGE_SIZE for the main
indirect buffer chunk, it adds an accessor for all reads from
the chunk and caches a single page at a time for subsequent
reads.
changes since v1:
Use a two page pool which should be the most common case
a single packet spanning > PAGE_SIZE will be hit, but I'm
having trouble seeing anywhere we currently generate anything like that.
hopefully proper short page copying at end
added parser_error flag to set deep errors instead of having to test
every ib value fetch.
fixed bug in patch that went to list.
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>
This convert r4xx to new init path it also fix few bugs.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
R3XX/R4XX AGP asic use the old PCI GART block, not the new PCIE GART.
Make sure we pick the right GART when disabling AGP.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Acked-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This adds the r600 KMS + CS support to the Linux kernel.
The r600 TTM support is quite basic and still needs more
work esp around using interrupts, but the polled fencing
should work okay for now.
Also currently TTM is using memcpy to do VRAM moves,
the code is here to use a 3D blit to do this, but
isn't fully debugged yet.
Authors:
Alex Deucher <alexdeucher@gmail.com>
Dave Airlie <airlied@redhat.com>
Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This adds the command stream checker for the RN50, R100 and R200 cards.
It stops any access to 3D registers on RN50, and does checks
on buffer sizes on the r100/r200 cards. It also fixes some texture
sizing checks on r300.
Signed-off-by: Dave Airlie <airlied@redhat.com>
