Add two new sysfs attributes:
- dynpm
- power_state

Echoing 0/1 to dynpm disables/enables dynamic power management.
The driver scales the sclk dynamically based on the number of
queued fences.  dynpm only scales sclk dynamically in single head
mode.

Echoing x.y to power_state selects a static power state (x) and clock
mode (y).  This allows you to statically select a power state and clock
mode.  Selecting a static clock mode will disable dynpm.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

- pm_misc() - handles voltage, pcie lanes, and other non
clock related power mode settings.  Currently disabled.
Needs further debugging

- pm_prepare() - disables crtc mem requests right now.
All memory clients need to be disabled when changing
memory clocks.  This function can be expanded to include
disabling fb access as well.

- pm_finish() - enable active memory clients.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

- remove non_clock_info struct
- track power state misc flags
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

This also simplifies the code and enables reclocking with multiple heads
active by tracking whether the power states are single or multi-head
capable.

Eventually, we will want to select a power state based on external
factors (AC/DC state, user selection, etc.).

(v2) Update for evergreen
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

(v2) Add evergreen vbl checks
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Useful for certain power management operations.  You
need to wait for the GUI engine (2D, 3D, CP, etc.) to be
idle before changing clocks or adjusting engine parameters.

(v2) Fix gui idle enable on pre-r6xx asics

(v3) The gui idle interrrupt status bit is permanently asserted
on pre-r6xx chips, but the interrrupt is still generated.
workaround it in the driver.

(v4) Add support for evergreen
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Check to see if the GUI engine and related blocks
(2D, 3D, CP, etc) are idle or not.  There are a number
of cases when we need to know if the drawing engine
is busy.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

This patch enable the use of unmappable VRAM thanks to
previous TTM infrastructure change.

V2 update after io_mem_reserve/io_mem_free callback balancing
Signed-off-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

[airlied: fix V_A_N_V to not be safe and fix check to make sure only r500
 - bump userspace version]
Signed-off-by: NMarek Olšák <maraeo@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

The 3rd dimension should be minified too.
Signed-off-by: NMarek Olšák <maraeo@gmail.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Some GPUs have an APM/ACPI PM mode selection switch and some BIOSes
set this to APM. We really want this in ACPI mode for Linux.
Signed-off-by: NDave Airlie <airlied@redhat.com>

If we resume in a bad way, we'll get 0xffffffff in wptr, and then
oops with no console. This just adds a sanity check so that we can
avoid the oops and hopefully get more details out of people's systems.
Signed-off-by: NDave Airlie <airlied@redhat.com>

- Add module option to force the display priority
  0 = auto, 1 = normal, 2 = high
- Default to high on r3xx/r4xx/rv515 chips
  Fixes flickering problems during heavy acceleration
  due to underflow to the display controllers
- Fill in minimal support for RS600

v2 - update display priority when bandwidth is updated
so the user can change the parameter at runtime and it
will take affect on the next modeset.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave 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: NAlex Deucher <alexdeucher@gmail.com>

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h

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: NTejun Heo <tj@kernel.org>
Guess-its-ok-by: NChristoph 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: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NDave Airlie <airlied@redhat.com>

We tried to implement interruptible waiting with timeout (it was broken
anyway) which was not a good idea as explained by Andrew. It's possible
to avoid using additional variable but actually it inroduces using more
complex in-kernel tools. So simply add one variable for condition.
Signed-off-by: NRafał Miłecki <zajec5@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

This patch properly set visible VRAM and enforce any pinned buffer
to be into visible VRAM. We might later add a flag to release this
constraint for some newer hw more clever than previous.
Signed-off-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

This already simplifies code significally and makes it maintaible
in case of adding memory reclocking plus voltage changing in future.
Signed-off-by: NRafał Miłecki <zajec5@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

V2: reorganize functions, fix modesetting calls
V3: rebase patch, use radeon's workqueue
V4: enable on tested chipsets only, request VBLANK IRQs
V5: enable PM on older hardware (IRQs, mode_fixup, dpms)
V6: use separate dynpm module parameter
V7: drop RADEON_ prefix, set minimum mode for dpms off
V8: update legacy encoder call, fix order in rs600 IRQ
V9: update compute_clocks call in legacy, not only DPMS_OFF
Signed-off-by: NRafał Miłecki <zajec5@gmail.com>
Signed-off-by: NDave 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: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Some servers have two VGA ports but only report
one in the bios connector tables.  On these systems
always set up the TV DAC so that it displays properly
even if the bios is wrong.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Cache flush is required in case CPU is accessing rendered data.

This fixes glean/readPixSanity test case and random rendering
errors in sauerbraten and warzone2100.

v2 Fix comment ordering in r100_fence_ring_emit and remove extra
   defines added in first version.
Signed-off-by: NPauli Nieminen <suokkos@gmail.com>
Reviewed-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

The first dword of PACKET3_3D_DRAW_IMMD maps to
SE_VTX_FMT so the vertex size is part of the draw
packet.

This patch fixes a possible case where you have a
command buffer that does not contain SE_VTX_FMT
register write, but does contain PACKET3_3D_DRAW_IMMD.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@linux.ie>

Use same common function to disable agp so we replace the GART
callback by the proper one when we do so. This fix oops if
radeon_agp_init report failure.

This patch also move radeon_agp_init out of *_mc_init for r600
& rv770 so that we can have a similar behavior than for previous
hw, ie if agp_init fails it will fallback to GPU GART and disable
AGP.
Signed-off-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

If for any reason we haven't installed handler we shouldn't try to
enable IRQ/MSI on the hw so we don't get unhandled IRQ/MSI which
makes the kernel sad.
Signed-off-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave 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: NJerome Glisse <jglisse@redhat.com>
Reviewed-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave 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: NDave 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: NMaciej Cencora <m.cencora@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NRafał Miłecki <zajec5@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>