54fa32cdfe
[gem] Fix bad test for list_for_each completion.
...
Since it's a circular list, the entry won't be NULL at termination.
2008-05-21 15:15:58 -07:00
7078978db0
[gem] Hold a reference on the object in i915_gem_wait_space.
...
Otherwise, in the middle of the function called using it the last ref
might disappear.
2008-05-21 15:04:07 -07:00
f8e38e49dd
[intel-gem] invalidate ring locals for pin/unpin/set_domain/free functions
...
Ring locals must be reloaded from hardware in case the X server ran.
2008-05-21 15:00:16 -07:00
af8e087157
[gem] Use a separate sequence number field from classic/ttm
...
This lets us get some qualities we desire, such as using the full 32-bit
range (except zero), avoiding DRM_WAIT_ON, and a 1:1 mapping of active
sequence numbers to request structs, which will be used soon for throttling
and interrupt-driven list cleanup.
2008-05-20 14:16:26 -07:00
ab36a6f983
[gem] Rename sequence numbers from "cookie" to "seqno"
2008-05-20 10:53:10 -07:00
6c3ac484b0
[gem] Clean up active/inactive list handling using helper functions.
...
Additionally, a boolean active field is added to indicate which list an
object is on, rather than smashing last_rendering_cookie to 0 to show
inactive. This will help with flush-reduction later on, and makes the code
clearer.
2008-05-20 10:52:39 -07:00
7dced2f33a
[gem] Hold dev->struct_mutex to protect structure data.
2008-05-15 18:45:23 -07:00
3ab152da66
[gem] Rename the GTT LRU lists to active (executing) and inactive (idle).
2008-05-15 11:59:58 -07:00
aafafe507b
[gem] typo fix in comment.
2008-05-15 11:59:57 -07:00
a09c0bbe11
ati_pcigart: oops wrong way around not that it actually mattered
2008-05-14 22:48:12 +10:00
4c6ec02eb8
ati_pcigart: stop working in the evenings you mess up too often
2008-05-14 22:44:22 +10:00
2712cdeec3
Revert "ati_pcigart: fixup properly this version might even work"
...
This reverts commit bc0836e12a
2008-05-14 22:43:28 +10:00
bc0836e12a
ati_pcigart: fixup properly this version might even work
2008-05-14 22:42:21 +10:00
dd1f33f83c
ati_pcigart: fill out 40-bit gart table support properly
...
Thanks to Alex for supplying this info.
2008-05-14 22:35:32 +10:00
f650d7240a
[GEM] Typo (and thinking) fixes in drm-gem.txt and doxygen.
2008-05-12 13:17:01 -07:00
17e8000ac0
[intel] Minor kludge -- wait for the ring to be nearly empty before queuing
...
No need to fill the ring that much; wait for it to become nearly empty
before adding the execbuffer request. A better fix will involve scheduling
ring insertion in the irq handler.
2008-05-12 13:04:18 -07:00
6aeff6b9e3
[gem] Set write domain to CPU when doing pwrite.
...
Leave the flush call in place, which can fix domains up if necessary.
2008-05-12 13:01:57 -07:00
6950b7da71
[gem] Clarify use of explicit domain control. Remove Gen3 from I-cache usage.
2008-05-12 13:00:55 -07:00
ff39db099b
[GEM] Make pread/pwrite manage memory domains. No luck with movnti though.
...
pread and pwrite must update the memory domains to ensure consistency with
the GPU. At some point, it should be possible to avoid clflush through this
path, but that isn't working for me.
2008-05-11 00:10:16 -07:00
1b0bf30143
[intel-GEM] exec list can contain pinned, lru cannot.
...
The exec list contains all objects, in order of use. The lru list contains
only unpinned objects ready to be evicted. This required two changes -- the
first was to not migrate pinned objects from exec to lru, the second was to
search for the first unpinned object in the exec list when doing eviction.
2008-05-10 22:04:39 -07:00
1f9eaceb71
Merge commit 'anholt/drm-gem' into drm-gem
2008-05-10 21:05:25 -07:00
177b8b0703
[GEM] Add drm-gem.txt
...
Add some API and implementation documentation for GEM.
2008-05-10 21:04:42 -07:00
a37ac493da
[intel-GEM] Clean up GEM ioctl naming.
...
Rename 'validate_entry' to 'exec_object', then clean up some field names in
structures (renaming buffer_offset to just offset, for example).
2008-05-10 21:04:18 -07:00
48a8531aa4
GEM: Fix arguments to drm_memrange_init so we don't exceed our allocation.
...
It takes (offset, size), not (offset, end).
2008-05-09 18:23:51 -07:00
c5c59eab80
GEM: Separate the LRU into execution list and LRU list.
...
Now, the LRU list has objects that are completely done rendering and ready
to kick out, while the execution list has things with active rendering,
which have associated cookies and reference counts on them.
2008-05-09 17:38:32 -07:00
f56f2acb5a
GEM: Clear obj_priv->agp_mem when we free it.
...
Still managing to get something wrong with this, oopsing down in agp.
2008-05-09 15:07:49 -07:00
f0ae335cd7
GEM: Avoid leaking refs on target objects on presumed offset success.
2008-05-09 15:02:50 -07:00
1e26ca44c9
[gem] API cleanup. allocate->create unreference->close name->flink
...
Make the API names a bit more consistent.
2008-05-09 12:18:09 -07:00
ec75369b40
[i915] clean up whinging from checkpatch.pl
2008-05-08 13:09:17 -07:00
07ad5ce1e1
Clean up whinging from checkpatch.pl in drm_gem.c
...
Whitespace changes, a few too-long-lines and some extra braces.
2008-05-08 13:08:22 -07:00
2f573e6df4
GEM: Fix oops on NULL dereference when we try clflushing when we don't need to.
2008-05-08 12:46:02 -07:00
9af4c49743
[intel-gem] Move domains to relocation records. add set_domain ioctl.
...
Domain information is about buffer relationships, not buffer contents. That
means a relocation contains the domain information as it knows how the
source buffer references the target buffer.
This also adds the set_domain ioctl so that user space can move buffers to
the cpu domain.
2008-05-08 10:44:02 -07:00
aa0621a19f
Apply a few stylistic cleanups to match kernel code.
2008-05-07 15:54:53 -07:00
06e9761f94
GEM: Wait for existing rendering to complete before writing relocation data.
...
This should already have been generally safe since we don't change contents
and put in new relocations between execbufs, so if we were writing in a new
relocation then we'd already waited rendering to complete when we moved
the target of the relocation. However, doing the right thing will be required
if we do buffer reuse.
2008-05-07 14:10:04 -07:00
5f5f01ed91
GEM: Extend cache domain stuff for 965.
...
One of our MI_FLUSH bits is reserved on 965, being always implied, and there's
a vertex cache that was forgotten.
2008-05-07 12:46:06 -07:00
b44f2da380
drm: nopage compat fixup for drm_vm
...
The kernel has removed nopage so move the old nopage codepaths into a compat vm file and switch to using the fault paths.
nopfn is on its way out in the future also, so we should switch to using fault
for that path as well soon
2008-05-07 15:10:23 +10:00
6a6c37af9e
[intel-GEM] ref count objects in gtt-lru.
...
If objects on the lru aren't ref counted, they'll get pulled from the gtt as
soon as they are freed. This change does cause objects to get stuck in the
gtt until they're forced out by new requests. The lru should get cleaned
when the irq occurs.
2008-05-06 21:59:06 -07:00
61253f4f67
[intel-GEM] Add memory domain support.
...
Memory domains allow the kernel to track which caches to flush and how to
move objects before buffer execution.
2008-05-06 20:00:23 -07:00
2b9ef32669
Merge commit 'anholt/drm-gem' into drm-gem
2008-05-06 14:43:56 -07:00
631e86c5c4
Start coding up memory domains
2008-05-06 14:43:49 -07:00
d2373b2a34
GEM: Use irq-based fencing rather than syncing and evicting every exec.
2008-05-06 13:28:26 -07:00
dd6976c56f
GEM: Skip relocation if presumed offset matches.
2008-05-06 11:25:53 -07:00
8551bfc6db
GEM: Save the last ioremapped page for relocations in case we need it again.
2008-05-06 11:18:57 -07:00
91cba3ae17
Dump last batch buffer when hardware lockup is detected.
2008-05-05 22:10:02 -07:00
2c8f970baa
Unlock pages right after getting them.
...
pages come back from find_or_create_page locked, but must not stay locked
for long. Unlock them immediately instead of waiting until we're done with
them to avoid deadlock when applications try to touch them.
2008-05-05 17:17:19 -07:00
5b0d0fa7f8
Merge commit 'anholt/drm-gem' into drm-gem
...
Conflicts:
linux-core/i915_gem.c
2008-05-05 14:40:20 -07:00
dafe48e623
GEM: Replace drm_memrange_for_each with just evicting what we brought in.
...
I was wrong about how the data structure worked, and didn't care to fix it
to support debugging code.
2008-05-05 14:38:26 -07:00
d59a9300ec
Remove some debug messages.
2008-05-05 14:32:01 -07:00
f0bc796a02
Add object base to relocation store address.
...
The relocated value was being written to the wrong location, missing
the object base address.
2008-05-05 14:22:42 -07:00
4867780bd6
Emit clflush and chipset flush when mapping objects to gtt
2008-05-05 13:32:28 -07:00
4511e6cd80
Correct execbuffer offset. Add memory barrier and chipset flush.
2008-05-05 11:27:06 -07:00
b6f173c430
Add i915_dispatch_gem_execbuffer (broken).
...
This function submits a gem-based execbuffer to the ring.
It doesn't work yet.
2008-05-05 10:51:49 -07:00
166ff364fb
Don't forget to set the memrange private, and reset ring on kernel entry.
2008-05-02 17:50:46 -07:00
afe574f328
Don't include the tail guard memrange in foreach callbacking.
2008-05-02 17:49:52 -07:00
5f0614b86f
Check for do_mmap errors
2008-05-02 17:13:11 -07:00
ab3549d133
Add a bit of /proc/dri/*/gem support. Clean up some refcount/pagelock issues.
...
Track named objects in /proc/dri/0/gem_names.
Track total object count in /proc/dri/0/gem_objects.
Initialize device gem data.
return -ENODEV for gem ioctls if the driver doesn't support gem.
Call unlock_page when unbinding from gtt.
Add numerous misssing calls to drm_gem_object_unreference.
2008-05-02 16:34:16 -07:00
39e20bcd5f
Add name/open ioctls, separate handle and pointer ref counts.
...
Names are just another unique integer set (from another idr object).
Names are removed when the user refernces (handles) are all destroyed --
this required that handles for objects be counted separately from
internal kernel references (so that we can tell when the handles are all
gone).
2008-05-02 12:29:17 -07:00
49e8e3372a
Remove drm_driver argument to functions taking drm_gem_object.
...
Now that drm_gem_object has a drm_driver * in it, functions don't need both
parameters.
2008-05-02 10:36:00 -07:00
0d547c9ed9
Add alignment to all aperture allocation requests.
...
When pinning buffers, or using execbuffer, allow the application to specify
the necessary aperture allocation alignment constraints.
2008-05-01 20:41:55 -07:00
30efad5113
Fix gem ioctls to be 32/64-bit clean.
...
mixed 32/64 bit systems need 'special' help for ioctl where the user-space
and kernel-space datatypes differ. Fixing the datatypes to be the same size,
and align the same way for both 32 and 64-bit ppc and x86 environments will
elimiante the need to have magic 32/64-bit ioctl translation code.
2008-05-01 20:31:16 -07:00
abc896638f
Use krefs for refcounting.
...
krefs are way easier than a custom-coded spinlock+int combo.
2008-05-01 20:12:39 -07:00
c10695bb7a
Unbind objects when freeing, fix some error paths, and warn in others.
2008-05-01 17:31:57 -07:00
ddc80651d5
Fix offset passed to AGP to be pages instead of bytes.
...
Fix some utterly bonged loop while we were staring at it.
2008-05-01 17:31:29 -07:00
3f641b56c7
Fix missing member settings in obj/obj_priv, and some error paths.
2008-05-01 16:48:25 -07:00
7d5f783eca
Make GEM object handles be nonzero.
2008-05-01 16:38:37 -07:00
d2529d1396
Remove _args from gem ioctl argument structure tags.
2008-05-01 16:27:03 -07:00
793549116e
Add pin/unpin object ioctls for gem.
2008-05-01 15:40:02 -07:00
ccd1bae0f6
checkpoint: relocations support.
2008-05-01 15:22:21 -07:00
5af87acbc2
checkpoint: gtt binding written.
2008-05-01 14:20:44 -07:00
2140e102f9
checkpoint: rename to GEM and a few more i915 bits.
2008-05-01 11:39:20 -07:00
1a84067950
Hacking towards hooking up execbuffer.
2008-04-30 16:03:15 -07:00
81ba8ded7e
Remove the remainder of the mmfs device.
2008-04-29 13:48:51 -07:00
dabd056bf3
Move mmfs ioctls into the DRM. Untested.
2008-04-29 13:32:52 -07:00
cb33133ef3
i915: fix off by one in VGA save/restore of AR & CR regs
...
Turns out it's important to save/restore AR14 in particular.
2008-04-29 12:39:38 -07:00
3ad8db2071
Rename drm_mm.c and its fuctions to drm_memrange.
...
It's not really a graphics memory allocator, just something to track ranges
of address space. It doesn't involve actual allocation, and was consuming
some desired namespace.
2008-04-28 16:54:53 -07:00
7f8e406085
Use fixed sized types in new ioctls
...
Make both crtc and the command argument 32 bits to avoid any 32-on-64 compat
issues.
2008-04-27 09:42:17 -07:00
22877864c2
Add mmap ioctl to mmfs.
2008-04-23 16:22:09 -07:00
8c741ed54e
Add pread/pwrite ioctls to mmfs.
2008-04-23 14:25:54 -07:00
8665b666c7
Move mmfs.h userland interface to shared-core.
2008-04-23 11:23:40 -07:00
47a2b7dc03
Initial add of mmfs module.
2008-04-23 10:42:06 -07:00
c82894034f
Clarify that drm_agp_ttm_backend is associated with a drm_ttm.
...
On first looking at it I assumed it was an aspect of the ttm backend as a
whole rather than specific allocations from a backend.
2008-04-23 10:42:06 -07:00
10b9a116a7
Don't disable IRQs, just tasklets, when taking the drm lock spinlock.
2008-04-23 17:34:21 +02:00
9ba3aaaa1a
Fixed unlock check on EAGAIN
2008-04-23 12:43:45 +02:00
b3967765c0
linux-core Makefile: add GIT_REVISION
...
This tries to automatically fetch a git revision string and if succeeds,
it #defines GIT_REVISION string macro. Packagers can override it by
'make GIT_REVISION=foo'.
Update Nouveau to use GIT_REVISION, if defined, instead of DRIVER_DATE
in struct drm_driver.
Signed-off-by: Pekka Paalanen <pq@iki.fi>
2008-04-22 22:07:21 +03:00
1ad1bd5bd9
Fix buffer object map wait error.
...
Add some branch prediction hints.
2008-04-14 13:52:33 +02:00
c5955c6523
Fix buffer object creation validation.
...
BO lock fixes.
2008-04-14 12:14:20 +02:00
c9b73ef6da
Unlock the BO mutex while waiting for idle, unmapped, unfenced.
...
Move unfenced checking into idle checking.
Never time out while waiting for software events like unmapped or unfenced.
2008-04-14 12:13:33 +02:00
65dd0e68ff
Fix up buffer manager locking.
2008-04-14 12:13:17 +02:00
b986d7d2c9
Save and restore dsparb and d_state regs
2008-04-11 20:31:07 -07:00
db61f02bd7
Missing KERNEL_VERSION macro
2008-04-07 22:24:24 +02:00
dfa9f03992
nouveau: enable accelerated move to sysmem
2008-04-07 13:29:11 +10:00
c12b60b509
nouveau: enable m2mf for tt<->vram moves, fix fence_poll
2008-04-07 13:05:51 +10:00
e89710bef7
Place highmem pages last in the ttm page array.
2008-04-06 11:21:22 +02:00
c3888b97f6
Use clflush() when available for cache flushing.
2008-04-06 10:32:02 +02:00
51a0fdcf3f
[I915] Fix VRAM eviction.
2008-04-06 10:30:27 +02:00
87ae5b22e3
Fix emergency allocation accounting.
2008-04-06 10:30:27 +02:00
22d931f966
Initialize the fence::error member.
2008-03-30 21:30:43 +02:00
1f4ba62567
[i915] Report buffer state _after_ fence submission to user-space.
...
This fixes a problem where the wrong bo->fence_type was reported, and
also saves some memory space.
[bo core] export the drm_bo_fill_rep_arg function.
2008-03-30 15:14:45 +02:00
b8567bafff
Don't call fence::poll during irq if there are no waiters.
2008-03-30 15:11:47 +02:00
a244d29050
nouveau: silence warning
2008-03-24 03:26:37 +11:00
Eric Anholt
Keith Packard
Dave Airlie
Arjan van de Ven
Dave Airlie
Jesse Barnes
Jesse Barnes
Thomas Hellstrom
Jakob Bornecrantz
Pekka Paalanen
Patrice Mandin
Ben Skeggs
Thomas Hellström