Commit Graph

50 Commits

Author SHA1 Message Date
Monk Liu
505dfe76cd drm/amdgpu: modify sdma start sequence
should fist halt engine, and then doing the register
programing, and later unhalt engine, and finally run
ring_test.

this help fix reloading driver hang issue of SDMA
ring

original sequence is wrong for it programing engine
after unhalt, which will lead to fault behavior when
doing driver reloading after unloaded.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-06-09 10:48:59 -04:00
Monk Liu
d72f7c0685 drm/amdgpu: init more register for sdma
This help fix reloading driver hang issue of SDMA
ring

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-06-09 10:48:58 -04:00
Christian König
d88bf583bd drm/amdgpu: move VM fields into job
They are the same for all IBs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-11 13:30:31 -04:00
Christian König
f153d2867b drm/amdgpu: move context switch handling into common code v2
It was a source of bugs to repeat that in each IP version.

v2: rename parameter

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-11 13:30:30 -04:00
Tom St Denis
88a907d67c drm/amd/amdgpu: Add name field to amd_ip_funcs (v2)
Add name that we can print out in kernel messages
to aid in debugging.

v2: drop DAL changes for upstream

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-11 12:31:26 -04:00
Monk Liu
c5637837ba drm/amdgpu: keep vm in job instead of ib (v2)
ib.vm is a legacy way to get vm, after scheduler
implemented vm should be get from job, and all ibs
from one job share the same vm, no need to keep ib.vm
just move vm field to job.

this patch as well add job as paramter to ib_schedule
so it can get vm from job->vm.

v2: agd: sqaush in:
drm/amdgpu: check if ring emit_vm_flush exists in vm flush

No vm flush on engines that don't support VM.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=95195

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-11 12:31:16 -04:00
Tom St Denis
16a7989ac6 drm/amd/amdgpu: Drop print_status callbacks.
First patch in series to move to user mode
debug tools we're removing the print_status callbacks.

These functions were unused at the moment anyway.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-04 20:30:06 -04:00
Christian König
b38d99c4f4 drm/amdgpu: reduce the ring size for SDMA
Those are way too large.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-04 20:20:58 -04:00
Christian König
a3f1cf355e drm/amdgpu: use max_dw in ring_init
Instead of specifying the total ring size calculate that from the maximum
number of dw a submission can have and the number of concurrent submissions.

This fixes UVD with 8 concurrent submissions or more.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-04 20:20:50 -04:00
Monk Liu
73cfa5f5ce drm/amdgpu: move ib.fence to job.fence
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-17 11:54:11 -04:00
Monk Liu
cc55c45db5 drm/amdgpu: give a fence param to ib_free
thus amdgpu_ib_free() can hook sched fence to SA manager
in later patches.

BTW:
for amdgpu_free_job(), it should only fence_put() the
fence of the last ib once, so fix it as well in this patch.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-17 11:53:34 -04:00
Ken Wang
16a8a49be1 drm/amdgpu: include the right version of gmc header files for iceland
Signed-off-by: Ken Wang <Qingqing.Wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2016-03-17 11:52:03 -04:00
Christian König
00b7c4ff7d drm/amdgpu: split pipeline sync out of SDMA vm_flush() as well
Code it similar to how we did it for the gfx and compute engines.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-10 10:36:13 -05:00
Christian König
336d1f5efe drm/amdgpu: remove HW fence owner
Not used any more since we now always use the sheduler.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2016-03-08 11:01:47 -05:00
Chunming Zhou
6ad550c35d drm/amdgpu: add hdp invalidation for sdma v2_4
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-08 11:01:43 -05:00
Chunming Zhou
5c55db83b7 drm/amdgpu: wait engine idle before vm flush for sdma
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-08 11:01:40 -05:00
Christian König
4ff37a83f1 drm/amdgpu: fix VM faults caused by vm_grab_id() v4
The owner must be per ring as long as we don't
support sharing VMIDs per process. Also move the
assigned VMID and page directory address into the
IB structure.

v3: assign the VMID to all IBs, not just the first one.
v4: use correct pointer for owner

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-29 11:33:46 -05:00
Alex Deucher
c458fe9425 drm/amdgpu/vi: move sdma tiling config setup into sdma code
Split sdma and gfx programming.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-12 15:53:04 -05:00
Christian König
2d55e45a03 drm/amdgpu: use SDMA round robin for VM updates v3
Distribute the load on both rings.

v2: use a loop for the initialization
v3: agd: rebase on upstream

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-12 15:38:16 -05:00
Christian König
3ee94136b4 drm/amdgpu: remove is_pte_ring
Not used for anything.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-12 15:35:54 -05:00
Christian König
e86f9ceee1 drm/amdgpu: move sync into job object
No need to keep that for every IB.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:17:24 -05:00
Christian König
a0332b56f6 drm/amdgpu: send SDMA/GFX IB tests directly to the ring again
There is no point in sending them through the scheduler.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:17:22 -05:00
Christian König
b07c60c065 drm/amdgpu: move ring from IBs into job
We can't submit to multiple rings at the same time anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:17:20 -05:00
Christian König
9e5d53094c drm/amdgpu: make pad_ib a ring function v3
The padding depends on the firmware version and we need that for BO moves as
well, not only for VM updates.

v2: new approach of making pad_ib a ring function
v3: fix typo in macro name

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:17:20 -05:00
Christian König
b07c9d2a73 drm/amdgpu: move more logic into amdgpu_vm_map_gart v3
No need to duplicate that code over and over again. Also stop using the
flags to determine if we need to map the addresses.

v2: constify the pages_addr
v3: rebased, fix typo in commit message

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:17:04 -05:00
Christian König
a27de35caa drm/amdgpu: remove the ring lock v2
It's not needed any more because all access goes through the scheduler now.

v2: Update commit message.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:16:58 -05:00
Alex Deucher
ea5e4c8731 drm/amdgpu: remove some more semaphore leftovers
No longer needed since semaphores were removed.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <David1.Zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:16:51 -05:00
Chunming Zhou
2f4b940033 drm/amdgpu: clean up hw semaphore support in driver
No longer used.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Ken Wang  <Qingqing.Wang@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-02-10 14:16:49 -05:00
Christian König
b7e4dad3e1 drm/amdgpu: remove old lockup detection infrastructure
It didn't worked to well anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
2015-10-21 11:35:12 -04:00
Alex Deucher
c113ea1c4f drm/amdgpu: rework sdma structures
Rework the sdma structures in the driver to
consolidate all of the sdma info into a single
structure and allow for asics that may have
different numbers of sdma instances.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-10-14 16:16:36 -04:00
Jammy Zhou
ac01db3dd5 drm/amdgpu: implement burst NOP for SDMA
Customize the insert_nop func for SDMA rings, and use burst NOP for
ring/IB submissions in other places as well

Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-02 12:35:39 -04:00
Jammy Zhou
edff0e2826 drm/amdgpu: add insert_nop ring func and default implementation
The insert_nop function is added to amdgpu_ring_funcs structure as
well as the default implementation

Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-02 12:24:43 -04:00
Jammy Zhou
18111de0df drm/amdgpu: add burst_nop flag for sdma
The burst NOP is supported for SDMA when feature_version is >= 20.

Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-02 12:22:28 -04:00
Chunming Zhou
6e7a384074 drm/amdgpu: use IB for fill_buffer instead of direct command
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-28 15:04:19 -04:00
Chunming Zhou
c7ae72c01b drm/amdgpu: use IB for copy buffer of eviction
This aids handling buffers moves with the scheduler.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-26 17:50:42 -04:00
Christian König
b203dd9594 drm/amdgpu: fix zeroing all IB fields manually v2
The problem now is that we don't necessarily call amdgpu_ib_get()
in some error paths and so work with uninitialized data.

Better require that the memory is already zeroed.

v2: better commit message

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-20 17:05:34 -04:00
Chunming Zhou
281b422301 drm/amdgpu: add reference for **fence
fix fence is released when pass to **fence sometimes.
add reference for it.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17 16:51:17 -04:00
Chunming Zhou
1763552ee8 drm/amdgpu: add kernel fence in ib_submit_kernel_helper
every sbumission should be able to get a fence.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
2015-08-17 16:50:54 -04:00
Chunming Zhou
ed88a0ee7f drm/amdgpu: use kernel fence for sdma ib test
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
2015-08-17 16:50:54 -04:00
Chunming Zhou
0011fdaa4d drm/amdgpu: use gpu scheduler for sdma ib test
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17 16:50:45 -04:00
Chunming Zhou
4274f5d45c drm/amdgpu: prepare job before push to sw queue for pte ring
user mode will still use pte ring as a normal ring.
if the prepare job generates another command(update pte) on its ring in scheduler,
then will kill scheduler which is going to waiting later job but pending running job.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Christian K?nig <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
2015-08-17 16:50:36 -04:00
Jammy Zhou
595fd013f7 drm/amdgpu: set fw_version and feature_version for smu fw loading
The fw_version and feature_verion should be set correctly when the
firmwares are loaded by SMU on Tonga/Carrzio/Iceland

Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
2015-08-05 14:26:50 -04:00
Jammy Zhou
cfa2104fbc drm/amdgpu: add feature version for SDMA ucode
Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
2015-08-05 14:26:50 -04:00
Chunming Zhou
890ee23fc6 drm/amdgpu: disable user fence interrupt (v2)
amdgpu submits both kernel and user fences, but just need one interrupt,
disable user fence interrupt and don't effect user fence.

v2: fix merge error

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-06-05 11:02:06 -04:00
monk.liu
b9a7faaeb2 drm/amdgpu: remove all sh mem register modification in vm flush
Leave that at the values set during init.  No need to update
them repeatedly.

Signed-off-by: monk.liu <monk.liu@amd.com>
Signed-off-by: David Zhang <david1.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
2015-06-03 21:03:56 -04:00
yanyang1
5fc3aeeb9e drm/amdgpu: rename amdgpu_ip_funcs to amd_ip_funcs (v2)
The structure is renamed and moved to amd_shared.h to make
the component independent.  This makes it easier to add
new components in the future.

v2: fix include path

Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Signed-off-by: yanyang1 <young.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-06-03 21:03:51 -04:00
Jammy Zhou
c65444fe05 drm/amdgpu: switch to amdgpu folder for firmware files v2
v2: keep using radeon folder for CIK

Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
2015-06-03 21:03:36 -04:00
Christian König
d2edb07b10 drm/amdgpu: cleanup HDP flush handling
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
2015-06-03 21:03:32 -04:00
Jack Xiao
74a5d1656e drm/amdgpu: allow unaligned memory access (v2)
Set up the CP and SDMA for proper unaligned memory access.
Required for OpenCL 2.x

v2: udpate commit message

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
2015-06-03 21:03:28 -04:00
Alex Deucher
aaa36a976b drm/amdgpu: Add initial VI support
This adds initial support for VI asics.  This
includes Iceland, Tonga, and Carrizo.  Our inital
focus as been Carrizo, so there are still gaps in
support for Tonga and Iceland, notably power
management.

Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Jammy Zhou <Jammy.Zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-06-03 21:03:17 -04:00