Commit Graph

3593 Commits

Author SHA1 Message Date
Francisco Jerez
38cf189fa1 drm/nv04-nv10: Don't re-enable FIFO access multiple times after IRQ dispatch.
nvxx_graph_isr is already taking care of it. In some cases this
could've made you miss PGRAPH interrupts (e.g. when you were supposed
to get several IRQs of the same kind in a row).

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08 03:00:20 +01:00
Francisco Jerez
ca130c2267 drm/nv04-nv40: Give "gpuobj->cinst" the same meaning as on nv50.
No functional changes, just simplify some code paths a bit.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08 03:00:09 +01:00
Francisco Jerez
2e5702aff3 drm/nouveau: fabricate DCB encoder table for iMac G4
In typical Apple fashion there's no standard information about what
encoders are present on this machine, this patch adds a quirk to
provide it.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:12:01 +10:00
Ben Skeggs
7f4a195fcb drm/nouveau: tidy up and extend dma object creation interfaces
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:59 +10:00
Ben Skeggs
6d6c5a157a drm/nouveau: remove some useless GETPARAMs
These have been unused since UMS support was ripped out, so lets remove
them completely.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:57 +10:00
Ben Skeggs
2cb3d3b6c6 drm/nv84: fix minor issues in PCRYPT implementation
Fix running of destroy_context() when create_context() has never been
called for the channel, and fill in engine's tlb_flush() function pointer.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:56 +10:00
Ben Skeggs
7b4808bb6e drm/nouveau: remove dummy page use from PCI(E)GART, use PTE present instead
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:54 +10:00
Ben Skeggs
9fea1bcbff drm/nv50: fix 0x100c90 init for NVAF
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:52 +10:00
Ben Skeggs
20f63afe98 drm/nv50: allocate page for unknown PFB object in nv50_fb.c
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:50 +10:00
Ben Skeggs
e41115d0ad drm/nouveau: rework gpu-specific instmem interfaces
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:48 +10:00
Ben Skeggs
dc1e5c0dbf drm/nouveau: simplify gpuobj suspend/resume
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:47 +10:00
Ben Skeggs
fce2bad0ee drm/nv50: rework PGPIO IRQ handling and hotplug detection
Allows callers to install their own handlers for when a GPIO line
changes state (such as for hotplug detect).

This also fixes a bug where we weren't acknowledging the GPIO IRQ
until after the bottom half had run, causing a severe IRQ storm
in some cases.

Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:45 +10:00
Ben Skeggs
e4cbadcaaa drm/nv04-nv40: unregister irq handler on destroy
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:43 +10:00
Ben Skeggs
274fec93cd drm/nouveau: tidy+move PGRAPH ISRs to their respective *_graph.c files
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:41 +10:00
Ben Skeggs
5178d40dff drm/nouveau: move PFIFO ISR into nv04_fifo.c
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:39 +10:00
Ben Skeggs
25b85783da drm/nv04-nv40: register vblank isr
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:38 +10:00
Ben Skeggs
8cbe71a6e7 drm/nouveau: move bitfield/enum helpers to nouveau_util.c
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:36 +10:00
Ben Skeggs
19b7fc7bf5 drm/nv50: use register/unregister functionality for PDISPLAY ISR
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:34 +10:00
Ben Skeggs
2cbd4c8185 drm/nv50: move GPIO ISR to nv50_gpio.c
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:32 +10:00
Ben Skeggs
d7facf9dc5 drm/nv84: move PCRYPT ISR out of nouveau_irq.c
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:30 +10:00
Ben Skeggs
8f8a54482b drm/nouveau: allow irq handlers to be installed by engine-specific code
Lets start to clean up this mess!

Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:29 +10:00
Ben Skeggs
a169f09b96 drm/nv50: 0x50c0 apparently works on NVA3+ too, so lets allow it
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:27 +10:00
Ben Skeggs
aa2c2e8039 drm/nv50: fix compute object class
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:25 +10:00
Francisco Jerez
23c45e8ed2 drm/nouveau: Fix sleep while atomic in nouveau_bo_fence().
Reported-by: Pekka Paalanen <pq@iki.fi>
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:23 +10:00
Francisco Jerez
87a326a385 drm/nv20: Add Z compression support.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Tested-by: Xavier Chantry <chantry.xavier@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:21 +10:00
Francisco Jerez
a5cf68b04b drm/nouveau: Rework tile region handling.
The point is to share more code between the PFB/PGRAPH tile region
hooks, and give the hardware specific functions a chance to allocate
per-region resources.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:20 +10:00
Francisco Jerez
e419cf0954 drm/nouveau: Add a separate class for the kernel channel mutex.
nouveau_bo_move_m2mf() needs to lock the kernel channel, and it may be
called from the pushbuf IOCTL with an user channel already locked. Use
a separate subclass for the kernel channel mutex because this is
legitimate mutex nesting.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:18 +10:00
Francisco Jerez
1f6d2de2c5 drm/nv50: Keep track of the head a channel is vsync'ing to.
In a multihead setup vblank interrupts may end up enabled in both
heads. In that case we want to ignore the vblank interrupts coming
from the wrong CRTC to avoid tearing and unbalanced calls to
drm_vblank_get/put (fdo bug 31074).

Reported-by: Felix Leimbach <felix.leimbach@gmx.net>
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:16 +10:00
Francisco Jerez
1c180fa5bd drm/nouveau: Call drm_vblank_pre/post_modeset() around mode setting.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:14 +10:00
Francisco Jerez
332b242f47 drm/nouveau: Implement the pageflip ioctl.
nv0x-nv4x should be mostly fine, nv50 doesn't work yet.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:12 +10:00
Francisco Jerez
042206c0cd drm/nouveau: Implement the vblank DRM hooks.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:11 +10:00
Francisco Jerez
63f7fcfebd drm/nv04: Make CRTC base changes effective in the next hsync.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:09 +10:00
Marcin Slusarz
382d62e524 drm/nouveau: fix annoying nouveau_fence type issue
nouveau_fence_* functions are not type safe, which could lead to bugs.
Additionally every use of nouveau_fence_unref had to cast struct
nouveau_fence to void **.
Fix it by renaming old functions and creating static inline functions with
new prototypes. We still need old functions, because we pass function
pointers to ttm.
As we are wrapping functions, drop unused "void *arg" parameter where possible.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:07 +10:00
Ben Skeggs
5f80198e43 drm/nv50: regression fix, point NVAA/NVAC at correct PM functions
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:05 +10:00
Ben Skeggs
35fa2f2ad1 drm/nouveau: add support for MSI
Only supported on NV50+ so far, and disabled by default currently.  The
module parameter "msi=1" will enable it.

There's a kernel bug which will cause this to fail if the module (or the
NVIDIA binary driver) has ever been loaded before loading nouveau with
MSI enabled.  As such, this is only safe to enable if you have nouveau
load on boot, and don't wish to ever reload it.

The workaround is to "echo 0 > /sys/bus/pci/devices/<device>/enable"
until the enable count reads 0.  Then you should be able to load nouveau
with MSI enabled.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:03 +10:00
Ben Skeggs
01d63187d1 drm/nv10: fix thinko and let nv17 do 3d again :)
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:11:01 +10:00
Ben Skeggs
8888cb18ff drm/nv50: fix evo instmem alignment
Not an issue right now, we're forced to 64k size/alignment by the BO
allocator anyway.  This won't be the case soon.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:59 +10:00
Ben Skeggs
97e2000f75 drm/nv50: improve evo error handler when more than just channel 0 active
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:58 +10:00
Ben Skeggs
43ce028ff2 drm/nv50: rework evo init to match nvidia more closely
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:56 +10:00
Ben Skeggs
1e96268aca drm/nv50: initial work to allow multiple evo channels
This doesn't work yet for unknown reasons.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:54 +10:00
Ben Skeggs
b7bc613a4c drm/nv50: move evo handling to nv50_evo.c
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:52 +10:00
Ben Skeggs
106ddad5aa drm/nv50: clearer separation of the stages of evo init
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:50 +10:00
Ben Skeggs
f4512e6579 drm/nv50: create graph and crypt contexts on demand
This really needs cleaning up somehow, and probably investigate what's
needed to do this on earlier generations.  NVIDIA do something similar
there too.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:10:44 +10:00
Ben Skeggs
3052be2cea drm/nv50: remove excessive alignment of graph/crypt contexts
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:07:00 +10:00
Ben Skeggs
bd2e597de8 drm/nv84: add support for the PCRYPT engine
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:58 +10:00
Ben Skeggs
b8c157d3a9 drm/nouveau: only expose the object classes that are supported by the chipset
We previously added all the available classes for the entire generation,
even though the objects wouldn't work on the hardware.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:56 +10:00
Ben Skeggs
a6a1a38075 drm/nouveau: use object class structs more extensively
The structs themselves, as well as the non-sw object creation function are
probably very misnamed now.  That's a problem for later :)

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:54 +10:00
Ben Skeggs
50536946fa drm/nouveau: store engine type in gpuobj class structs
We will eventually want to address hw engines other than PGRAPH.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:52 +10:00
Ben Skeggs
9100468d1b drm/nouveau: pass gpuobj alignment request down into backing allocator
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:51 +10:00
Francisco Jerez
0541324abc drm/nv40: Ignore sync-to-vblank active when waiting for idle.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:49 +10:00
Francisco Jerez
889fa93dc0 drm/nouveau: Take fence spinlock in nouveau_fence_channel_fini().
Without it there's a potential race with nouveau_fence_update().

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:47 +10:00
Francisco Jerez
2b478addc0 drm/nouveau: Avoid race in the interchannel sync code.
It needs a "strong" channel reference because it actually writes to
the channel pushbuf, otherwise the corresponding FIFO context could
get kicked off in the middle of nouveau_fence_sync().

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:45 +10:00
Francisco Jerez
2a6789ae5e drm/nouveau: Make fences take a weak channel reference.
Fences didn't increment the channel reference count, and the fenced
channel could go away at any time. Fixes a potential race in
nouveau_fence_update().

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:43 +10:00
Francisco Jerez
f091a3d403 drm/nouveau: Implement weak channel references.
nouveau_channel_ref() takes a "weak" channel reference that doesn't
prevent the hardware channel resources from being released, it just
keeps the channel data structure alive.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:42 +10:00
Francisco Jerez
36c952e8b3 drm/nouveau: Fix lock unbalance on card take down.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:40 +10:00
Francisco Jerez
feeb0aecfb drm/nouveau: Add unlocked variants of nouveau_channel_get/put.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:38 +10:00
Francisco Jerez
f175b745b5 drm/nouveau: Fix race condition in channel refcount handling.
nouveau_channel_put() can be executed after the 'refcount == 0' check
in nouveau_channel_get() and before the channel reference count is
incremented. In that case CPU0 will take the context down while CPU1
thinks it owns the channel and 'refcount == 1'.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:36 +10:00
Francisco Jerez
3945e47543 drm/nouveau: Refactor context destruction to avoid a lock ordering issue.
The destroy_context() engine hooks call gpuobj management functions to
release the channel resources, these functions use HARDIRQ-unsafe locks
whereas destroy_context() is called with the HARDIRQ-safe
context_switch_lock held, that's a lock ordering violation.

Push the engine-specific channel destruction logic into destroy_context()
and let the hardware-specific code lock and unlock when it's actually
needed. Change the engine destruction order to avoid a race in the small
gap between pgraph and pfifo context uninitialization.

Reported-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:35 +10:00
Francisco Jerez
fcccab2e4e drm/nouveau: Use lazy fence waits when doing software interchannel sync.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:33 +10:00
Francisco Jerez
aa5ac7358c drm/nouveau: Leave BO eviction synchronization for later.
The pushbuf ioctl syncs after validation, no need for this anymore.

Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:31 +10:00
Ben Skeggs
cbb4b608b6 drm/nv50: remove some unnecessary PDISPLAY init
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:29 +10:00
Ben Skeggs
9acc8100cb drm/nouveau: fallback to sw fbcon if we can't get mutex immediately
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:06:23 +10:00
Ben Skeggs
6032649df9 drm/nouveau: hook up acpi power supply change tracking
Not used at all yet, but lets hook it up now anyway.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:29 +10:00
Ben Skeggs
18a16a768c drm/nouveau: return error from nouveau_ramht_remove() if not found
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:27 +10:00
Ben Skeggs
938c40ed69 drm/nouveau: use interruptible waits during pushbuf validation
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:26 +10:00
Ben Skeggs
08cd3d4311 drm/nouveau: fix thinko in channel locking in semaphore path
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:24 +10:00
Ben Skeggs
21e86c1c8a drm/nouveau: remove cpu_writers lock
No other driver uses this, and userspace should be responsible for handling
locking between them if they share BOs.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:22 +10:00
Ben Skeggs
b12120a58e drm/nouveau: switch to unlocked ioctls
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:20 +10:00
Ben Skeggs
cff5c13324 drm/nouveau: add more fine-grained locking to channel list + structures
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:18 +10:00
Ben Skeggs
6a6b73f254 drm/nouveau: add per-channel mutex, use to lock access to drm's channel
This fixes a race condition between fbcon acceleration and TTM buffer
moves.  To reproduce:

- start X
- switch to vt and "while (true); do dmesg; done"
- switch to another vt and "sleep 2 && cat /path/to/debugfs/dri/0/evict_vram"
- switch back to vt running dmesg

We don't make use of this on any other channel yet, they're currently
protected by drm_global_mutex.  This will change in the near future.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:05:10 +10:00
Ben Skeggs
ceed5f30bf drm/nouveau: disallow fbcon accel if running in interrupt context
A future commit will add locking to the DRM's channel, and there's numerous
problems that come up if we allow printk from an interrupt context to be
accelerated.  It seems saner to just disallow it completely.

As a nice side-effect, all the "to accel or not to accel" logic gets moved
out of the chipset-specific code.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 15:04:20 +10:00
Ben Skeggs
7c74cbd01b drm/nouveau: tidy fifo swmthd handler a little
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03 14:18:39 +10:00
Dave Airlie
f7eb0c5541 Merge branch 'drm-radeon-fusion' of ../drm-radeon-next into drm-core-next
* 'drm-radeon-fusion' of ../drm-radeon-next:
  drm/radeon/kms: add Ontario APU ucode loading support
  drm/radeon/kms: add Ontario Fusion APU pci ids
  drm/radeon/kms: enable MSIs on fusion APUs
  drm/radeon/kms: add power table parsing support for Ontario fusion APUs
  drm/radeon/kms: refactor atombios power state fetching
  drm/radeon/kms: add bo blit support for Ontario fusion APUs
  drm/radeon/kms: add thermal sensor support for fusion APUs
  drm/radeon/kms: fill in GPU init for AMD Ontario Fusion APUs
  drm/radeon/kms: add radeon_asic struct for AMD Ontario fusion APUs
  drm/radeon/kms: evergreen.c updates for fusion
  drm/radeon/kms: MC setup changes for fusion APUs
  drm/radeon/kms: move r7xx/evergreen to its own vram_gtt setup function
  drm/radeon/kms: add support for ss overrides on Fusion APUs
  drm/radeon/kms: Add support for external encoders on fusion APUs
  drm/radeon/kms: atom changes for DCE4.1 devices
  drm/radeon/kms: add new family id for AMD Ontario APUs
  drm/radeon/kms: upstream power table updates
  drm/radeon/kms: upstream atombios.h updates
  drm/radeon/kms: upstream ObjectID.h updates
  drm/radeon/kms: setup mc chremap properly on r7xx/evergreen
2010-12-03 14:01:08 +10:00
Dave Airlie
7e76c5cf6f Merge branch 'drm-radeon-next' of ../drm-radeon-next into drm-core-next
* 'drm-radeon-next' of ../drm-radeon-next:
  drm/radeon/kms: improve pflip precision on r1xx-r4xx
  drm/kms/radeon: Use high precision timestamps for pageflip completion events.
  drm/kms/radeon: Reorder vblank and pageflip interrupt handling.
  drm/radeon/kms: add pageflip ioctl support (v3)
  drm/kms/radeon: Add support for precise vblank timestamping.
2010-12-03 14:00:52 +10:00
Alex Deucher
acb325062a drm/radeon/kms: improve pflip precision on r1xx-r4xx
The update pending bit has a separate enable bit.

Cc: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-26 10:42:05 +10:00
Alex Deucher
439bd6cde4 drm/radeon/kms: add Ontario APU ucode loading support
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:35 +10:00
Alex Deucher
bbbf9b7b02 drm/radeon/kms: enable MSIs on fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:33 +10:00
Alex Deucher
b0e664140a drm/radeon/kms: add power table parsing support for Ontario fusion APUs
The vbios power tables on my inagua board seem a bit funky...

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:32 +10:00
Alex Deucher
560154e9a2 drm/radeon/kms: refactor atombios power state fetching
The function was getting too large.  Rework it to share
more state better handle new power table formats.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:31 +10:00
Alex Deucher
e719ebd916 drm/radeon/kms: add bo blit support for Ontario fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:30 +10:00
Alex Deucher
e33df25fec drm/radeon/kms: add thermal sensor support for fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:29 +10:00
Alex Deucher
d5e455e48b drm/radeon/kms: fill in GPU init for AMD Ontario Fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:28 +10:00
Alex Deucher
958261d1e8 drm/radeon/kms: add radeon_asic struct for AMD Ontario fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:27 +10:00
Alex Deucher
180074010c drm/radeon/kms: evergreen.c updates for fusion
fusion chips only have 2 crtcs.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:26 +10:00
Alex Deucher
6eb18f8b60 drm/radeon/kms: MC setup changes for fusion APUs
- CONFIG_MEMSIZE is in bytes on fusion.
- FB_BASE and FB_TOP are finer grained.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:24 +10:00
Alex Deucher
0ef0c1f734 drm/radeon/kms: move r7xx/evergreen to its own vram_gtt setup function
MC_VM_FB_LOCATION is at a different offset between r6xx and r7xx/evergreen.
The location is needed for vram setup on fusion chips.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:23 +10:00
Alex Deucher
4339c442c0 drm/radeon/kms: add support for ss overrides on Fusion APUs
System specific spread spectrum overrides can be specified in
the integrated system info table for Fusion APUs.  This adds
support for using those overrides.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:22 +10:00
Alex Deucher
bf982ebf22 drm/radeon/kms: Add support for external encoders on fusion APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:21 +10:00
Alex Deucher
4e8c65a1f9 drm/radeon/kms: atom changes for DCE4.1 devices
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:20 +10:00
Alex Deucher
2f062fda4f drm/radeon/kms: add new family id for AMD Ontario APUs
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:19 +10:00
Alex Deucher
603a9da37b drm/radeon/kms: upstream power table updates
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:17 +10:00
Alex Deucher
1422ef52ef drm/radeon/kms: upstream atombios.h updates
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:16 +10:00
Alex Deucher
5d68e501bf drm/radeon/kms: upstream ObjectID.h updates
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:14 +10:00
Alex Deucher
9535ab7323 drm/radeon/kms: setup mc chremap properly on r7xx/evergreen
Should improve performance slightly and possibly fix some
issues.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-23 09:23:09 +10:00
Thomas Hellstrom
147666fb3b drm/radeon: Use the ttm execbuf utilities
Rather than re-implementing in the Radeon driver,
Use the execbuf / cs / pushbuf utilities that comes with TTM.
This comes with an even greater benefit now that many spinlocks have been
optimized away...

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:23 +10:00
Thomas Hellstrom
eba67093f5 drm/ttm: Fix up io_mem_reserve / io_mem_free calling
This patch attempts to fix up shortcomings with the current calling
sequences.

1) There's a fastpath where no locking occurs and only io_mem_reserved is
   called to obtain needed info for mapping. The fastpath is set per
   memory type manager.
2) If the fastpath is disabled, io_mem_reserve and io_mem_free will be exactly
   balanced and not called recursively for the same struct ttm_mem_reg.
3) Optionally the driver can choose to enable a per memory type manager LRU
   eviction mechanism that, when io_mem_reserve returns -EAGAIN will attempt
   to kill user-space mappings of memory in that manager to free up needed
   resources

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:22 +10:00
Thomas Hellstrom
6570596202 drm/ttm/vmwgfx: Have TTM manage the validation sequence.
Rather than having the driver supply the validation sequence, leave that
responsibility to TTM. This saves some confusion and a function argument.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:21 +10:00
Thomas Hellstrom
95762c2b34 drm/ttm: Improved fencing of buffer object lists
Drastically reduce the number of spin lock / unlock operations by performing
unreserving and fencing under global locks.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jerome Glisse <j.glisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:20 +10:00
Thomas Hellstrom
702adba224 drm/ttm/radeon/nouveau: Kill the bo lock in favour of a bo device fence_lock
The bo lock used only to protect the bo sync object members, and since it
is a per bo lock, fencing a buffer list will see a lot of locks and unlocks.
Replace it with a per-device lock that protects the sync object members on
*all* bos. Reading and setting these members will always be very quick, so
the risc of heavy lock contention is microscopic. Note that waiting for
sync objects will always take place outside of this lock.

The bo device fence lock will eventually be replaced with a seqlock /
rcu mechanism so we can determine that a bo is idle under a
rcu / read seqlock.

However this change will allow us to batch fencing and unreserving of
buffers with a minimal amount of locking.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jerome Glisse <j.glisse@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:18 +10:00
Thomas Hellstrom
96726fe50f drm/ttm: Don't deadlock on recursive multi-bo reservations
Add an aid for the driver to detect deadlocks on multi-bo reservations
Update documentation.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jerome Glisse <j.glisse@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-11-22 13:25:17 +10:00