5e662f90d1
[gem] Release GEM buffers from work task scheduled from IRQ.
...
There are now 3 lists. Active is buffers currently in the ringbuffer.
Flushing is not in the ringbuffer, but needs a flush before unbinding.
Inactive is as before. This prevents object_free → unbind →
wait_rendering → object_reference and a kernel oops about weird refcounting.
This also avoids an synchronous extra flush and wait when freeing a buffer
which had a write_domain set (such as a temporary rendered to and then from
using the 2d engine). It will sit around on the flushing list until the
appropriate flush gets emitted, or we need the GTT space for another
operation.
2008-05-22 22:00:21 -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
3ab152da66
[gem] Rename the GTT LRU lists to active (executing) and inactive (idle).
2008-05-15 11:59:58 -07:00
e4f29968f4
Merge branch 'modesetting-101' of ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
2008-05-13 14:47:17 -07:00
ee631e1b86
i915: register definition & header file cleanup
...
It would be nice if one day the DRM driver was the canonical source for
register definitions and core macros. To that end, this patch cleans
things up quite a bit, removing redundant definitions (some with
different names referring to the same register) and generally tidying up
the header file.
2008-05-13 14:44:17 -07:00
5be53a0881
i915: execbuf now works without i915_dma_init being called
2008-05-13 09:26:26 +02:00
7e7ea313c4
[intel] When polling for ring space, sleep for a lot longer (10ms)
...
If the ring is full, the engine will surely be running for more than 10ms.
2008-05-12 13:03:16 -07:00
af60d87869
fix G33 hardware status page in modeset
...
We need to alloc a hw status page bo for G33 if modeset is enabled since the 2D
driver can't alloc gfx memory when working in drm modeset.
2008-05-12 12:04:02 -07:00
3f66a0005c
drm: remove root only from a lot of drm ioctls to get stuff running as non-root
2008-05-12 16:29:22 +10:00
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
d2373b2a34
GEM: Use irq-based fencing rather than syncing and evicting every exec.
2008-05-06 13:28:26 -07:00
ed6657fa8e
Monitor ACTHD register while polling for idle ring.
...
When batch buffers are executing, the ring may be stuck for a long time.
Monitor the ACTHD pointer which will show if the execution engine is
actually hung.
2008-05-05 22:09:34 -07:00
d59a9300ec
Remove some debug messages.
2008-05-05 14:32:01 -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
793549116e
Add pin/unpin object ioctls for gem.
2008-05-01 15:40:02 -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
7f269bec7e
Merge branch 'master' into modesetting-101
...
Conflicts:
linux-core/Makefile.kernel
linux-core/drm_compat.c
linux-core/drm_fops.c
linux-core/drm_lock.c
shared-core/drm.h
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
2008-04-28 12:10:44 +02:00
ce8c842518
i915: gfx hw and i945gme fixes from upstream
...
From Jesse and Zhenyu originally.
2008-04-22 16:08:17 +10:00
b0817a42e7
i915: fix oops on agp=off
...
Kernel bug 10289.
2008-03-24 18:52:26 +10:00
88bd1e4a35
Merge branch 'intel-post-reloc'
...
Conflicts:
linux-core/drm_compat.c
linux-core/drm_compat.h
linux-core/drm_ttm.c
shared-core/i915_dma.c
Bump driver minor to 13 due to introduction of new
relocation type.
2008-03-12 11:34:29 +01:00
b6dc381fab
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
2008-03-12 10:18:33 +00:00
8a18d123f5
Avoid large kmallocs.
2008-03-12 09:49:27 +01:00
e00dea812d
Merge branch 'master' of ../../drm into modesetting-101
...
Conflicts:
linux-core/drmP.h
linux-core/drm_drv.c
linux-core/drm_proc.c
linux-core/drm_stub.c
linux-core/drm_sysfs.c
2008-03-06 05:26:23 +10:00
12574590cd
drm: reorganise minor number handling using code from modesetting branch
...
Rip out the whole head thing and replace it with an idr and drm_minor
structure.
2008-03-06 05:21:50 +10:00
638353103d
i915: Evict if relocatee buffer is CACHED_MAPPED before
...
writting relocations, otherwise the GPU probably sees some
inconsistent data. Fix fd.o bug#14656
2008-03-05 15:09:17 +08:00
43891ff2d0
Merge remote branch 'origin/master' into modesetting-101
...
Conflicts:
linux-core/drm_compat.c
2008-03-05 10:37:02 +10:00
9c5ba9f5d1
Add FENCE registers to MMIO list
2008-03-02 21:48:40 +00:00
2305100c0f
More post-ioctl work.
2008-02-29 13:25:55 +01:00
01dcc47d89
drm: add modesetting as a driver feature.
...
This change adds a driver feature that for i915 is controlled by a module
parameter. You now need to do insmod i915.ko modeset=1 to enable it the
modesetting paths.
It also fixes up lots of X paths. I can run my new DDX driver on this code
with and without modesetting enabled
2008-02-28 16:24:17 +10:00
fd595fa4dc
Reinstate buffer idle before applying relocations.
2008-02-27 21:44:40 +01:00
72983ff301
Don't wait for buffer idle before applying relocations.
2008-02-27 19:46:28 +01:00
1e66322633
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
shared-core/i915_dma.c
2008-02-26 15:42:41 +00:00
e87cec1968
[i915] Relocation fixes.
2008-02-26 10:47:05 +01:00
b92e343dc4
i915: fix typos
2008-02-26 16:20:27 +10:00
35d1b13b4a
i915_mmio: add overlay regs
2008-02-26 16:13:06 +10:00
56bb29cf37
Make the execbuffer code reasonably safe against errors.
...
In particular -EAGAINs, which should be common during Xserver operation.
Also handle the fence creation failure case.
2008-02-26 00:05:26 +01:00
b7086e6ae5
Fix one last occurance of struct _drm_i915_batchbuffer.
...
Thanks to Todd Merrill for pointing it out.
2008-02-22 11:22:52 -05:00
8caf6e9571
Fix up conflicts for DRI2 (untested)
2008-02-19 15:17:24 +00:00
f24ed2ad6c
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
linux-core/i915_fence.c
linux-core/via_fence.c
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
2008-02-18 22:35:46 +00:00
8bf8cd63bb
missing bits
2008-02-14 07:37:34 +10:00
373dbcf8b2
i915: Add a dri2 init path that gets the lock from the dri2 sarea.
2008-02-13 13:34:02 -05:00
db3f03ae35
i915: Only look up dev_priv->mmio_map if it's not already set up
2008-02-13 13:34:02 -05:00
ee15459483
i915: Add I915_PARAM_CHIPSET_ID param to get chipset ID.
2008-02-13 13:34:02 -05:00
4feb0638f1
i915: Make sarea_priv setup optional.
2008-02-13 13:34:02 -05:00
76748efae2
i915: Re-report breadcrumbs on poll to the fence manager,
...
since a breadcrumb may actually turn up before a corresponding fence object
has been placed on the fence ring.
2008-02-05 10:36:49 +01:00
47ee6237fe
i915: Avoid calling drm_fence_flush_old excessively.
2008-01-30 22:14:02 +01:00
f1edb7ad91
Simplify the fencing code and differentiate between flushes and
...
waiting types.
Add a "command_stream_barrier" method to the bo driver.
2008-01-30 22:06:02 +01:00
fa7b779c91
don't reinit ring if already initialised
2008-01-25 16:32:09 +10:00
e7a41d7f5b
Merge remote branch 'origin/master' into modesetting-101
...
Conflicts:
linux-core/drm_bo.c
linux-core/drm_drv.c
shared-core/drm.h
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
shared-core/radeon_irq.c
2008-01-25 15:27:53 +10:00
5b99306452
i915: fix missing header when copying data from userspace
2008-01-24 15:18:09 +10:00
34b71eb451
i915 make relocs use copy from user
...
Switch relocs to using copy from user and remove index and pass buffer
handles in instead.
2008-01-24 14:37:40 +10:00
88c511e49d
Properly propagate the user-space fence flags.
...
This avoids a sync flush when user-space has already programmed
and MI_FLUSH in the batchbuffer.
2008-01-15 10:03:41 +01:00
10937cf20b
drm: move drm_head to drm_minor and fix up users
2008-01-04 16:12:24 +11:00
9ab620d661
drm: cleanup DRM_DEBUG() parameters
...
As DRM_DEBUG macro already prints out the __FUNCTION__ string (see
drivers/char/drm/drmP.h), it is not worth doing this again. At some
other places the ending "\n" was added.
airlied:- I cleaned up a few that this patch missed also
2008-01-03 16:56:04 +10:00
5f23519b14
Document drm_bo_handle_validate. Match drm_bo_do_validate parameter order.
...
Document parameters and usage for drm_bo_handle_validate. Change parameter
order to match drm_bo_do_validate (fence_class has been moved to after
flags, hint and mask values). Existing users of this function have been
changed, but out-of-tree users must be modified separately.
2007-12-15 12:10:42 -08:00
f62a300547
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
2007-12-13 10:41:23 +00:00
7dcaf0cdbb
Make relocation validate client computed values when debugging
2007-12-11 20:23:00 -08:00
4ec8f58d04
i915: wait for buffer idle before writing relocations
...
When writing a relocation entry, make sure the target buffer is idle,
otherwise the GPU may see inconsistent data.
2007-12-11 20:23:00 -08:00
57b9a54eb6
Allow relocation to be skipped when buffers don't move.
...
One of the costs of superioctl has been the need to perform relocations
inside the kernel. The cost of mapping the buffers to the CPU and writing
data is fairly high, especially if those buffers have been mapped and read
by the GPU.
If we assume that buffers don't move around very often, we can have the
client compute the relocations itself using the previous GPU address. When
that object doesn't move, the kernel can skip computing and writing the
updated data.
Here's a patch which adds a new field to struct drm_bo_info_req called
'presumed_offset', and a new DRM_BO_HINT_PRESUMED_OFFSET that is set when
this field has been filled in by the client.
There are two separate optimizations performed when the presumed_offset is
correct:
1. i915_exec_reloc checks to see if all previous buffer offsets were guessed
correctly. If so, there's no need for it to look at *any* of the
relocations for a buffer. When this happens, it skips the whole
relocation process, simply returning success.
2. i915_apply_reloc checks to see if the target buffer offset was guessed
correctly. If so, it skips mapping the relocatee, computing the
relocation and writing the value. If no relocations are needed, the
relocatee should never be mapped to the CPU, and so the kernel shouldn't
need to wait for any fences to pass.
2007-12-11 20:23:00 -08:00
8d2da20233
Merge branch 'master' of ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
linux-core/drm_drv.c
shared-core/drm.h
shared-core/i915_dma.c
2007-12-11 16:58:00 +10:00
e38749ebe5
Remove references to the sarea_priv perf_boxes field.
...
This field isn't touched or read by any other code in the stack so it's
time to retire these last few references.
2007-12-05 14:43:22 -05:00
b2f8368b57
Clarify order of operations
2007-12-01 14:44:30 -05:00
453a295c82
DRM_DEBUG already prints the function name.
2007-12-01 14:44:29 -05:00
d6295cc9ff
drm: Add _DRM_DRIVER map flag.
...
This flag indicates that the driver is responsible for the map.
2007-12-01 02:40:13 -05:00
309b2c4c05
Beside the emitted warning, the added cast (u64 -> unsigned) strips out
...
part of address on 64 bit. Cast to unsigned long instead.
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
2007-11-29 09:55:38 +10:00
dc338921f9
drm: more cleanups
2007-11-29 09:38:21 +10:00
e9fa8fe734
i965: oops force mi batchbuffer start
2007-11-28 22:46:06 +10:00
a20587e395
Merge branch 'origin' into modesetting-101
...
Conflicts:
linux-core/drmP.h
shared-core/i915_dma.c
shared-core/i915_drm.h
shared-core/radeon_drv.h
2007-11-22 17:17:06 +11:00
5dc5c36e62
drm: major whitespace/coding style realignment with kernel
2007-11-22 16:10:36 +10:00
3fc3fc082a
Fix capitalization of __linux__ define.
2007-11-19 08:41:23 -08:00
a74181ddb2
Bug #13233 : Fix build on FreeBSD.
2007-11-18 22:42:40 -08:00
2eee33ace5
intel: add flushing for i8xx chipsets.
...
Add a nut vs hammer style chipset flush for the i8xx chipsets - reenable TTM
code paths
2007-11-15 13:29:55 +11:00
d983ed90cb
i915: cleanup pageflip derefs sarea even if no sarea exists
2007-11-09 11:30:50 +10:00
47497abc1e
i915: oops disable TTM is backwards
2007-11-07 23:10:24 +10:00
c07dd80269
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
linux-core/Makefile.kernel
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
2007-11-06 10:01:52 +01:00
9280076b67
i915: disable TTM on 8xx chips for now until flushing is solved
2007-11-06 18:13:46 +11:00
5ce43a346c
Merge branch 'master' into modesetting-101
...
Conflicts:
linux-core/drm_bufs.c
shared-core/i915_dma.c
shared-core/i915_drv.h
shared-core/i915_irq.c
2007-11-05 13:46:06 +01:00
7f6bf84c23
drm: remove lots of spurious whitespace.
...
Kernel "cleanfile" script run.
2007-11-05 12:42:22 +10:00
629c8b0dbf
Merge branch 'master' into modesetting-101
...
Conflicts:
linux-core/Makefile.kernel
linux-core/drm_stub.c
linux-core/i915_drv.c
shared-core/i915_dma.c
shared-core/i915_drv.h
Fixup suspend/resume conflicts (basically use what's in DRM master for now).
Also fix up a few other conflicts that snuck in (i915_dma changes etc.).
2007-11-01 15:27:55 -07:00
17f0882d50
drm: add chipset flushing via agp support
2007-10-31 11:33:34 +11:00
2489062a33
i915: add backwards compat chipset flushing code
2007-10-31 11:27:44 +11:00
1e2a2babab
i915: suspend/resume support
...
Add suspend/resume support to the i915 driver. Moves some of the
initialization into the driver load routine, and fixes up places where we
assumed no dev_private existed in some of the cleanup paths. This allows
us to suspend/resume properly even if X isn't running.
2007-10-26 16:10:02 -07:00
9adf8c0256
Merge branch 'master' into modesetting-101
...
Conflicts:
linux-core/Makefile.kernel
linux-core/drm_bo.c
linux-core/drm_objects.h
2007-10-25 11:00:45 +02:00
07706c9b79
Merge branch 'master' into drm-ttm-finalize
2007-10-25 09:24:45 +02:00
a70fe82baf
i915: relocate buffers before validation add memory barrier between two
2007-10-25 16:53:18 +10:00
c5f158abbe
i915: remove relocatee kernel mapping sooner stops mutex taking during sleep
2007-10-25 16:52:33 +10:00
83199c257e
Fix missing \n on some DRM_ERROR in i915_dma.c
2007-10-24 16:27:51 -07:00
fd7c24753c
i915: use a drm memory barrier define
2007-10-24 11:13:15 +11:00
d5f2b4b411
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
2007-10-23 15:34:12 +01:00
a294aa724a
i915: require mfence before submitting batchbuffer
2007-10-23 17:54:07 +10:00
919c886b2b
A cmdbuf mutex to implement validate-submit-fence atomicity in the absence
...
of a hardware lock.
2007-10-22 18:59:37 +02:00
22883ff26b
i915: split reloc execution into separate function
2007-10-22 11:54:41 +11:00
9ddff6d15f
Adapt i915 super-ioctl for lock-free operation.
2007-10-21 12:26:26 +02:00
48b5eaf303
Simple replacement for hardware lock in some cases.
...
Fix i915 since last commit.
2007-10-20 16:49:43 +02:00
be2d68914d
Fix a crash on X startup
2007-10-17 09:35:44 +01:00
ec1162b212
i915: lock struct mutex about buffer object lookups
2007-10-17 15:36:14 +10:00
90bfc8e611
Merge branch 'master' of git+ssh://git.freedesktop.org/git/mesa/drm into modesetting-101
...
Conflicts:
linux-core/drm_bo.c
linux-core/drm_objects.h
shared-core/i915_dma.c
shared-core/i915_drv.h
2007-10-16 15:28:33 +01:00
74001c34e5
i915: add superioctl support to i915
...
This adds the initial i915 superioctl interface. The interface should be
sufficent even if the implementation may needs fixes/optimisations internally
in the drm wrt caching etc.
2007-10-12 10:54:38 +10:00
Eric Anholt
Jesse Barnes
Jakob Bornecrantz
Keith Packard
Hong Liu
Dave Airlie
Thomas Hellstrom
Dave Airlie
Alan Hourihane
Xiang, Haihao
Dave Airlie
Alan Hourihane
Kristian Høgsberg
Márton Németh
Robert Noland
Robert Noland
Jiri Slaby
Dave Airlie
Robert Noland
Jesse Barnes
Dave Airlie