Commit Graph

32 Commits

Author SHA1 Message Date
Dave Airlie
484048db6b Merge branch 'drm-next-3.18' of git://people.freedesktop.org/~agd5f/linux into drm-next
radeon userptr support.

* 'drm-next-3.18' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: allow userptr write access under certain conditions
  drm/radeon: add userptr flag to register MMU notifier v3
  drm/radeon: add userptr flag to directly validate the BO to GTT
  drm/radeon: add userptr flag to limit it to anonymous memory v2
  drm/radeon: add userptr support v8

Conflicts:
	drivers/gpu/drm/radeon/radeon_prime.c
2014-08-26 09:05:14 +10:00
Alex Deucher
cd1c9c1a4b drm/radeon: re-enable selective GPUVM flushing
Now that the PFP and ME synchronization is fixed, we
can enable this again reliably.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
2014-08-19 11:48:30 -04:00
Michel Dänzer
1538a9e0e0 drm/radeon: Only flush HDP cache for indirect buffers from userspace
It isn't necessary for command streams generated by the kernel (at least
not while we aren't storing ring or indirect buffers in VRAM).

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-18 17:09:44 -04:00
Michel Dänzer
6f28ef4797 drm/radeon: Always flush VM again on < CIK
Not doing this causes piglit hangs[0] on my Cape Verde card. No issues on
Bonaire and Kaveri though.

[0] Same symptoms as those fixed on CIK by 'drm/radeon: set VM base addr
using the PFP v2'.

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:17 -04:00
Dan Carpenter
68b1ea30e4 drm/radeon: add a check for allocation failure (v2)
We can easily return -ENOMEM here if kzalloc() fails.

v2: agd5f: drop the vm mutex

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:17 -04:00
Christian König
f72a113a71 drm/radeon: add userptr support v8
This patch adds an IOCTL for turning a pointer supplied by
userspace into a buffer object.

It imposes several restrictions upon the memory being mapped:

1. It must be page aligned (both start/end addresses, i.e ptr and size).

2. It must be normal system memory, not a pointer into another map of IO
space (e.g. it must not be a GTT mmapping of another object).

3. The BO is mapped into GTT, so the maximum amount of memory mapped at
all times is still the GTT limit.

4. The BO is only mapped readonly for now, so no write support.

5. List of backing pages is only acquired once, so they represent a
snapshot of the first use.

Exporting and sharing as well as mapping of buffer objects created by
this function is forbidden and results in an -EPERM.

v2: squash all previous changes into first public version
v3: fix tabs, map readonly, don't use MM callback any more
v4: set TTM_PAGE_FLAG_SG so that TTM never messes with the pages,
    pin/unpin pages on bind/unbind instead of populate/unpopulate
v5: rebased on 3.17-wip, IOCTL renamed to userptr, reject any unknown
    flags, better handle READONLY flag, improve permission check
v6: fix ptr cast warning, use set_page_dirty/mark_page_accessed on unpin
v7: add warning about it's availability in the API definition
v8: drop access_ok check, fix VM mapping bits

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v4)
Reviewed-by: Jérôme Glisse <jglisse@redhat.com> (v4)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-11 11:04:23 -04:00
Christian König
cc6f353625 drm/radeon: update IB size estimation for VM
That should allow us to allocate bigger BOs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:56 -04:00
Christian König
03f62abd11 drm/radeon: split PT setup in more functions
Move the decision what to use into the common VM code.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:55 -04:00
Christian König
ee26d83ff0 drm/radeon: take a BO reference on VM cleanup
This closes a small window where the GPU might have accessed freed up memory.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:54 -04:00
Christian König
f77c4f0223 drm/radeon: try to enable VM flushing once more
Let's try to fix bugs related to this instead of just disabling it.

Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:51 -04:00
Alex Deucher
0aea5e4aa2 drm/radeon: use an intervall tree to manage the VMA v2
Scales much better than scanning the address range linearly.

v2: store pfn instead of address

Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:51 -04:00
Christian König
e31ad969bb drm/radeon: invalidate moved BOs in the VM (v2)
Don't wait for the BO to be used again, just
update the PT on the next VM use.

v2: remove stray semicolon.

Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:49 -04:00
Christian König
a3a9226d29 drm/radeon: add trace_radeon_vm_flush
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:38 -04:00
Michel Dänzer
02376d8282 drm/radeon: Allow write-combined CPU mappings of BOs in GTT (v2)
v2: fix rebase onto drm-fixes

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-05 08:53:33 -04:00
Christian König
5b75327563 drm/radeon: fix error handling in radeon_vm_bo_set_addr
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-07-22 12:21:58 -04:00
Christian König
cc9e67e3d7 drm/radeon: fix VM IB handling
Calling radeon_vm_bo_find on the IB BO during CS
is illegal and can lead to an crash.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-07-21 13:17:38 -04:00
Christian König
036bf46a39 drm/radeon: fix handling of radeon_vm_bo_rmv v3
v3: completely rewritten. We now just remember which areas
    of the PT to clear and do so on the next command submission.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=79980

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-07-21 13:17:38 -04:00
Christian König
7dae77f880 drm/radeon: page table BOs are kernel allocations
Userspace shouldn't be able to access them.

Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-07-02 15:52:21 -04:00
Christian König
4510fb985d drm/radeon: make vm_block_size a module parameter
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-06-09 22:06:54 -04:00
Christian König
ce6758c8bd drm/radeon: rename alt_domain to allowed_domains
And also domain to prefered_domains. That matches better
what those values represent.

Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-06-09 22:06:52 -04:00
Dave Airlie
8d4ad9d4bb Merge commit '9e9a928eed8796a0a1aaed7e0b676db86ba84594' into drm-next
Merge drm-fixes into drm-next.

Both i915 and radeon need this done for later patches.

Conflicts:
	drivers/gpu/drm/drm_crtc_helper.c
	drivers/gpu/drm/i915/i915_drv.h
	drivers/gpu/drm/i915/i915_gem.c
	drivers/gpu/drm/i915/i915_gem_execbuffer.c
	drivers/gpu/drm/i915/i915_gem_gtt.c
2014-06-05 20:28:59 +10:00
Christian König
1c89d27fb9 drm/radeon: add proper support for RADEON_VM_BLOCK_SIZE v2
This patch makes it possible to decide how many address
bits are spend on the page directory vs the page tables.

v2: remove unintended change

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-06-02 10:25:03 -04:00
Christian König
ec3dbbcbd7 drm/radeon: add large PTE support for NI, SI and CIK v5
This patch implements support for VRAM page table entry compression.
PTE construction is enhanced to identify physically contiguous page
ranges and mark them in the PTE fragment field. L1/L2 TLB support is
enabled for 64KB (SI/CIK) and 256KB (NI) PTE fragments, significantly
improving TLB utilization for VRAM allocations.

Linear store bandwidth is improved from 60GB/s to 125GB/s on Pitcairn.
Unigine Heaven 3.0 sees an average improvement from 24.7 to 27.7 FPS
on default settings at 1920x1200 resolution with vsync disabled.

See main comment in radeon_vm.c for a technical description.

v2 (chk): rebased and simplified.
v3 (chk): add missing hw setup
v4 (chk): rebased on current drm-fixes-3.15
v5 (chk): fix comments and commit text

Signed-off-by: Jay Cornwall <jay@jcornwall.me>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-06-02 10:25:02 -04:00
Christian König
37903b5e08 drm/radeon: sync page table updates
Only necessary if we don't use the same engine for buffer moves and table updates.

Signed-off-by: Christian König <christian.koenig@amd.com>
2014-06-02 10:56:21 +02:00
Christian König
2f93dc32b0 drm/radeon: fix vm buffer size estimation
Only relevant if we got VM_BLOCK_SIZE>9, but better save than sorry.

Signed-off-by: Christian König <christian.koenig@amd.com>
2014-06-02 10:54:02 +02:00
Christian König
7d95f6cc4e drm/radeon: only allocate necessary size for vm bo list
No need to always allocate the theoretical maximum here.

Signed-off-by: Christian König <christian.koenig@amd.com>
2014-05-30 14:21:54 +02:00
Christian König
4906f6891e drm/radeon: fix page directory update size estimation
Take padding into account as well.

Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=75651

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-05-20 14:42:01 +02:00
Christian König
df0af4403a drm/radeon: remove struct radeon_bo_list
Just move all fields into radeon_cs_reloc, removing unused/duplicated fields.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-03-04 14:34:34 +01:00
Christian König
529364e05b drm/radeon: remove global vm lock
Not needed any more.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-03-03 11:26:27 +01:00
Christian König
6d2f2944e9 drm/radeon: use normal BOs for the page tables v4
No need to make it more complicated than necessary,
just allocate the page tables as normal BO and
flush whenever the address change.

v2: update comments and function name
v3: squash bug fixes, page directory and tables patch
v4: rebased on Mareks changes

Signed-off-by: Christian König <christian.koenig@amd.com>
2014-03-03 11:26:08 +01:00
Christian König
fa68834342 drm/radeon: further cleanup vm flushing & fencing
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-03-03 11:03:35 +01:00
Christian König
2280ab57b6 drm/radeon: separate gart and vm functions
Both are complex enough on their own.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-03-03 11:03:34 +01:00