OSDN Git Service
Likun Gao [Tue, 10 Jul 2018 12:20:16 +0000 (20:20 +0800)]
drm/amdgpu: add picasso support for vm
Add vm support for picasso.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Likun Gao [Tue, 10 Jul 2018 12:22:36 +0000 (20:22 +0800)]
drm/amdgpu: add soc15 support for picasso
Add the IP blocks, clock and powergating flags, and common clockgating support.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Likun Gao [Tue, 10 Jul 2018 12:10:05 +0000 (20:10 +0800)]
drm/amdgpu: add picasso to asic_type enum
Add picasso to amd_asic_type enum and amdgpu_asic_name[].
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 10 Sep 2018 18:02:46 +0000 (20:02 +0200)]
drm/amdgpu: use a single linked list for amdgpu_vm_bo_base
Instead of the double linked list. Gets the size of amdgpu_vm_pt down to
64 bytes again.
We could even reduce it down to 32 bytes, but that would require some
rather extreme hacks.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 10 Sep 2018 14:07:57 +0000 (16:07 +0200)]
drm/amdgpu: remove amdgpu_bo_list_entry.robj (v2)
We can get that just by casting tv.bo.
v2: squash in kfd fix (Alex)
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 12 Sep 2018 19:19:57 +0000 (21:19 +0200)]
drm/ttm: once more fix ttm_bo_bulk_move_lru_tail
While cutting the lists we sometimes accidentally added a list_head from
the stack to the LRUs, effectively corrupting the list.
Remove the list cutting and use explicit list manipulation instead.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-and-Tested: Huang Rui <ray.huang@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Andrey Grodzovsky [Wed, 12 Sep 2018 20:38:57 +0000 (16:38 -0400)]
drm/amd/display: Fix pflip IRQ status after gpu reset.
Problem:
After GPU reset pflip completion IRQ is disabled and hence
any subsequent mode set or plane update leads to hang.
Fix:
Unless acrtc->otg_inst is initialized to -1 during display
block initializtion then durng resume from GPU reset
amdgpu_irq_gpu_reset_resume_helper will override CRTC 0 pflip
IRQ value with whatever value was on every other unused CRTC because
dm_irq_state will do irq_source = dal_irq_type + acrtc->otg_inst
where acrtc->otg_inst will be 0 for every unused CRTC.
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 7 Sep 2018 18:34:17 +0000 (20:34 +0200)]
drm/amdgpu: allow fragment processing for invalid PTEs
That should improve the PRT performance on Vega quite a bit.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 7 Sep 2018 12:21:15 +0000 (14:21 +0200)]
drm/amdgpu: use the maximum possible fragment size on Vega/Raven
The fragment size controls only the L1 on Vega/Raven and we now don't
have any extra overhead any more because of larger fragments.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 6 Sep 2018 15:13:06 +0000 (17:13 +0200)]
drm/amdgpu: meld together VM fragment and huge page handling
This optimizes the generating of PTEs by walking the hierarchy only once
for a range and making changes as necessary.
It allows for both huge (2MB) as well giant (1GB) pages to be used on
Vega and Raven.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 3 Sep 2018 12:34:51 +0000 (14:34 +0200)]
drm/amdgpu: use leaf iterator for filling PTs
Less overhead and is the starting point for further cleanups and
improvements.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 8 Sep 2018 11:05:34 +0000 (13:05 +0200)]
drm/amdgpu: use the DFS iterator in amdgpu_vm_invalidate_pds v2
Less code and easier to maintain.
v2: rename the function as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 6 Sep 2018 13:35:13 +0000 (15:35 +0200)]
drm/amdgpu: use dfs iterator to free PDs/PTs
Allows us to free all PDs/PTs without recursion.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 1 Sep 2018 10:03:37 +0000 (12:03 +0200)]
drm/amdgpu: use leaf iterator for allocating PD/PT
Less code and allows for easier error handling.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 1 Sep 2018 08:36:48 +0000 (10:36 +0200)]
drm/amdgpu: add some VM PD/PT iterators v2
Both a leaf as well as dfs iterator to walk over all the PDs/PTs.
v2: update comments and fix for_each_amdgpu_vm_pt_dfs_safe
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 16:53:25 +0000 (12:53 -0400)]
drm/amdgpu:Add error message when register failed to reach expected value
Add error message when register failed to reach expected value, It will
help discover potential issue.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
kbuild test robot [Wed, 12 Sep 2018 00:59:07 +0000 (08:59 +0800)]
drm/amd/display: fix ptr_ret.cocci warnings
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c:771:1-3: WARNING: PTR_ERR_OR_ZERO can be used
Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR
Generated by: scripts/coccinelle/api/ptr_ret.cocci
Fixes:
e498eb713604 ("drm/amd/display: Add support for hw_state logging via debugfs")
CC: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Tue, 11 Sep 2018 17:49:49 +0000 (13:49 -0400)]
drm/amd: Add DM DMCU support
DMCU (Display Microcontroller Unit) is a GPU chip involved in
eDP features like Adaptive Backlight Modulation and Panel Self
Refresh.
DC is already fully equipped to initialize DMCU as long as the
firmware is loaded.
At the moment only the raven firmware is available.
A single .bin file is loaded by the kernel's loading mechanism
and split into two ucodes according to the header.
DMCU is optional, so if the firmware is not found, no error or
warning is raised.
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Tue, 11 Sep 2018 17:46:41 +0000 (13:46 -0400)]
drm/amd: Add PSP DMCU support
DMCU (Display Microcontroller Unit) is a GPU chip involved in
eDP features like Adaptive Backlight Modulation and Panel Self
Refresh.
PSP is already equipped to handle DMCU firmware loading, all
that is needed is to translate between the new DMCU ucode ID and
the equivalent psp_gfx_fw_type.
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Tue, 11 Sep 2018 17:41:01 +0000 (13:41 -0400)]
drm/amd: Add ucode DMCU support
DMCU (Display Microcontroller Unit) is a GPU chip involved in
eDP features like Adaptive Backlight Modulation and Panel Self
Refresh.
DMCU has two pieces of firmware: the ERAM and the interrupt
vectors, which must be loaded seperately.
To this end, the DMCU firmware has a custom header and parsing
logic similar to MEC, to extract the two ucodes from a single
struct firmware.
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Thu, 6 Sep 2018 03:51:23 +0000 (23:51 -0400)]
drm/amdgpu: Move fault hash table to amdgpu vm
In stead of share one fault hash table per device, make it
per vm. This can avoid inter-process lock issue when fault
hash table is full.
Change-Id: I5d1281b7c41eddc8e26113e010516557588d3708
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Suggested-by: Christian Konig <Christian.Koenig@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian Konig <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chunming Zhou [Tue, 11 Sep 2018 09:22:40 +0000 (17:22 +0800)]
drm/amdgpu: move cs dependencies front a bit
cs dependencies handling doesn't need in vm resv
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>
Christian König [Fri, 7 Sep 2018 12:27:05 +0000 (14:27 +0200)]
drm/amdgpu: try allocating VRAM as power of two
Try to allocate VRAM in power of two sizes and only fallback to vram
split sizes if that fails.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Andrey Grodzovsky [Mon, 10 Sep 2018 22:43:58 +0000 (18:43 -0400)]
drm/amdgpu: Fix SDMA TO after GPU reset v3
After GPU reset amdgpu_vm_clear_bo triggers VM flush
but job->vm_pd_addr is not set causing SDMA TO.
v2:
Per advise by Christian König avoid flushing VM for jobs where
job->vm_pd_addr wasn't explicitly set.
v3:
Shortcut vm_flush_needed early.
Fixes
cbd5285 drm/amdgpu: move setting the GART addr into TTM.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 30 Aug 2018 13:55:54 +0000 (15:55 +0200)]
drm/amdgpu: add amdgpu_vm_update_func
Add helper to call the update function for both BO and shadow.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 30 Aug 2018 13:55:54 +0000 (15:55 +0200)]
drm/amdgpu: add amdgpu_vm_pt_parent helper
Add a function to get the parent of a PD/PT.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 10 Sep 2018 13:52:55 +0000 (15:52 +0200)]
drm/amdgpu: fix error handling in amdgpu_cs_user_fence_chunk
Slowly leaking memory one page at a time :)
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
shaoyunl [Fri, 7 Sep 2018 16:00:07 +0000 (12:00 -0400)]
drm/amdkfd: Only add bi-directional iolink on GPU with XGMI or largebar (v2)
v2: compile fix
Signed-off-by: shaoyunl <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Mon, 13 Aug 2018 18:04:11 +0000 (14:04 -0400)]
drm/amdkfd: Generate xGMI direct iolink
Generate xGMI iolink for upper level usage
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Mon, 13 Aug 2018 18:02:17 +0000 (14:02 -0400)]
drm/amdkfd: Add new iolink type defines
Update the iolink type defines according to the new thunk spec
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Fri, 6 Jul 2018 15:32:42 +0000 (11:32 -0400)]
drm/amdkfd: kfd expose the hive_id of the device through its node properties
Thunk will generate the XGMI topology information when necessary with the hive_id
for each specified device
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Fri, 6 Jul 2018 15:28:23 +0000 (11:28 -0400)]
drm/amdgpu: get_hive_id from amdgpu side (v2)
Retrieve hive_id from amdgpu device
v2: compile fix
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Fri, 6 Jul 2018 15:26:08 +0000 (11:26 -0400)]
drm/amd/include: Add get_hive_id interface in kfd2kgd
KFD need to get hive id from amdgpu to build up the XGMI topology
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Wed, 27 Jun 2018 21:25:53 +0000 (17:25 -0400)]
drm/amdgpu : Generate XGMI topology info from driver level
Driver will save an array of XGMI hive info, each hive will have a list of devices
that have the same hive ID.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Tue, 14 Aug 2018 17:30:00 +0000 (13:30 -0400)]
drm/amdgpu: Add place holder functions for xgmi topology interface with psp
Add dummy function for xgmi function interface with psp
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Wed, 27 Jun 2018 21:24:46 +0000 (17:24 -0400)]
drm/amdgpu : Add psp function interfaces for XGMI support
Place holder for XGMI support
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 19 Jun 2018 21:11:56 +0000 (16:11 -0500)]
drm/amdgpu/gmc9: Adjust GART and AGP location with xgmi offset (v2)
On hives with xgmi enabled, the fb_location aperture is a size
which defines the total framebuffer size of all nodes in the
hive. Each GPU in the hive has the same view via the fb_location
aperture. GPU0 starts at offset (0 * segment size),
GPU1 starts at offset (1 * segment size), etc.
For access to local vram on each GPU, we need to take this offset into
account. This including on setting up GPUVM page table and GART table
v2: squash in "drm/amdgpu: Init correct fb region for none XGMI configuration"
Acked-by: Huang Rui <ray.huang@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Alex Deucher [Tue, 19 Jun 2018 22:03:27 +0000 (17:03 -0500)]
drm/amdgpu/gmc9: add a new gfxhub 1.1 helper for xgmi
Used to populate the xgmi info on vega20.
v2: PF_MAX_REGION is val - 1 (Ray)
Acked-by: Huang Rui <ray.huang@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Reviewed-by :Shaoyun liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by :Shaoyun liu <Shaoyun.liu@amd.com>
Alex Deucher [Tue, 19 Jun 2018 21:00:47 +0000 (16:00 -0500)]
drm/amdgpu/gmc: add initial xgmi structure to amdgpu_gmc structure
Initial pass at a structure to store xgmi info. xgmi is a high
speed cross gpu interconnect.
Acked-by: Huang Rui <ray.huang@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Reviewed-by :Shaoyun liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Shaoyun Liu [Tue, 7 Aug 2018 15:44:26 +0000 (11:44 -0400)]
drm/amd/include: update the bitfield define for PF_MAX_REGION
Correct the definition based on vega20 register spec
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Emily Deng [Mon, 10 Sep 2018 09:51:31 +0000 (17:51 +0800)]
drm/amdgpu: move PSP init prior to IH in gpu reset
since we use PSP to program IH regs now
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 5 Sep 2018 15:04:44 +0000 (17:04 +0200)]
drm/amdgpu: set bulk_moveable to false when a per VM is released
Otherwise we might run into a use after free during bulk move.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tao Zhou [Fri, 7 Sep 2018 05:50:31 +0000 (13:50 +0800)]
drm/amdgpu: Fix SDMA hang in prt mode v2
Fix SDMA hang in prt mode, clear XNACK_WATERMARK in reg SDMA0_UTCL1_WATERMK to avoid the issue
Affected ASICs: VEGA10 VEGA12 RV1 RV2
v2: add reg clear for SDMA1
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Tested-by: Yukun Li <yukun1.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Wed, 5 Sep 2018 02:03:13 +0000 (10:03 +0800)]
drm/amd/powerplay: fix compile warning for wrong data type V2
do_div expects the 1st argument in 64bit instead of 32bit.
Drop the usage of do_div as it seems unnecessary.
V2: drop usage of do_div completely
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Masanari Iida [Thu, 6 Sep 2018 02:10:57 +0000 (11:10 +0900)]
drm/amdgpu: Fix warnings while make xmldocs
This patch fixes following warnings.
./drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:3011:
warning: Excess function parameter 'dev' description
in 'amdgpu_vm_get_task_info'
./drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:3012:
warning: Function parameter or member 'adev' not
described in 'amdgpu_vm_get_task_info'
./drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:3012:
warning: Excess function parameter 'dev' description
in 'amdgpu_vm_get_task_info'
Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Thu, 6 Sep 2018 00:19:54 +0000 (20:19 -0400)]
drm/amdgpu: Fix compute VM BO params after rebase v2
The intent of two commits was lost in the last rebase:
810955b drm/amdgpu: Fix acquiring VM on large-BAR systems
b5d21aa drm/amdgpu: Don't use shadow BO for compute context
This commit restores the original behaviour:
* Don't set AMDGPU_GEM_CREATE_NO_CPU_ACCESS for page directories
to allow them to be reused for compute VMs
* Don't create shadow BOs for page tables in compute VMs
v2: move more logic into amdgpu_vm_bo_param
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Kent Russell <Kent.Russell@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 27 Aug 2018 16:23:11 +0000 (18:23 +0200)]
drm/amdgpu: enable AGP aperture for GMC9 v2
Enable the old AGP aperture to avoid GART mappings.
v2: don't enable it for SRIOV
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Fri, 31 Aug 2018 20:54:12 +0000 (16:54 -0400)]
drm/amdgpu: Clean up KFD init and fini
Only initialize KFD once by moving amdgpu_amdkfd_init from
amdgpu_pci_probe to amdgpu_init. This fixes kernel oopses and hangs
when booting multi-GPU systems.
Also removed some vestiges of KFD being its own module.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jun Lei [Wed, 22 Aug 2018 21:00:34 +0000 (17:00 -0400)]
drm/amd/display: Add invariant support instrumentation in driver
Existing debug dump are all invariant, new “low 32-bit of address”
dump is not invariant
Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chiawen Huang [Tue, 28 Aug 2018 05:38:34 +0000 (13:38 +0800)]
drm/amd/display: clean code for transition event log.
[Why]
There are same purpose transition events.
[How]
remove the redundant event log.
Signed-off-by: Chiawen Huang <chiawen.huang@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Fri, 17 Aug 2018 18:24:26 +0000 (14:24 -0400)]
drm/amd/display: Remove call to amdgpu_pm_compute_clocks
[Why]
The extraneous call to amdgpu_pm_compute_clocks is deprecated.
[How]
Remove it.
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Eric Yang [Fri, 24 Aug 2018 20:54:14 +0000 (16:54 -0400)]
drm/amd/display: use link type to decide stream enc acquisition
[Why]
Virtual sink is used when set mode happens on a disconnected display
to allow the mode set to proceed. This did not work with MST because
the logic for acquiring stream encoder uses stream signal to determine
the special handling is required, and stream signal is virtual instead
of DP in this case.
[How]
Use link type to decide instead.
Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tony Cheng [Mon, 27 Aug 2018 17:35:13 +0000 (13:35 -0400)]
drm/amd/display: dc 3.1.65
Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Steven Chiu <Steven.Chiu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Thu, 9 Aug 2018 14:05:10 +0000 (10:05 -0400)]
drm/amd/display: Reorder resource_pool to put i2c with aux
[Why]
The i2c and aux engines are similar, and should be placed
next to eachother for readability
[How]
Reorder the elements of the resource_pool struct
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Leo Li [Thu, 23 Aug 2018 19:28:08 +0000 (15:28 -0400)]
drm/amd/display: Use DRM helper for best_encoder
[Why]
Our implementation is functionally identical to DRM's
Note that instead of checking if the provided id is 0, the helper
follows through with the mode object search. However, It will still
return NULL, since 0 is not a valid object id, and missed searches
will return NULL.
[How]
Remove our implementation, and replace it with
drm_atomic_helper_best_encoder.
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Hersen Wu [Tue, 21 Aug 2018 13:35:47 +0000 (09:35 -0400)]
drm/amd/display: num of sw i2c/aux engines less than num of connectors
[why]
AMD Stoney reference board, there are only 2 pipes (not include
underlay), and 3 connectors. resource creation, only
2 I2C/AUX engines are created. Within dc_link_aux_transfer, when
pin_data_en =2, refer to enengines[ddc_pin->pin_data->en] = NULL.
NULL point is referred later causing system crash.
[how]
each asic design has fixed number of ddc engines at hw side.
for each ddc engine, create its i2x/aux engine at sw side.
Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chiawen Huang [Fri, 24 Aug 2018 09:45:28 +0000 (17:45 +0800)]
drm/amd/display: add aux transition event log.
[Why]
Enhance aux transition debugging information.
[How]
Added Aux request and reply event log.
Signed-off-by: Chiawen Huang <chiawen.huang@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Derek Lai [Thu, 23 Aug 2018 07:13:23 +0000 (15:13 +0800)]
drm/amd/display: add disconnect_delay to dc_panel_patch
Some display need disconnect delay. Adding this parameter for future use
Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dmytro Laktyushkin [Mon, 30 Jul 2018 18:45:42 +0000 (14:45 -0400)]
drm/amd/display: remove unused clk_src code
Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dmytro Laktyushkin [Tue, 14 Aug 2018 20:12:54 +0000 (16:12 -0400)]
drm/amd/display: remove dead dc vbios code
Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jun Lei [Mon, 13 Aug 2018 19:11:44 +0000 (15:11 -0400)]
drm/amd/display: Add driver-side parsing for CM
Although 4 unique register values exist for gamma modes, two are
actually the same (the two RAMs) It’s not possible for caller to
understand this HW specific behavior, so some parsing is necessary
in driver
Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Gary Kattan [Mon, 20 Aug 2018 22:12:14 +0000 (15:12 -0700)]
drm/amd/display: Fix DAL217 tests modify DTN logs for other tests
[Why]Update Code to get DTN golden log check to pass for tests run after
DAL217 tests.
[How]Change how dcn10_log_hw_state function prints HW state info
(CM_GAMUT_REMAP_Cx_Cx registers) when GAMUT REMAP is in bypass mode.
Signed-off-by: Gary Kattan <gary.kattan@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Eric Bernstein [Thu, 24 May 2018 19:50:27 +0000 (15:50 -0400)]
drm/amd/display: Add DP YCbCr 4:2:0 support
[Why]
For supporting DP YCbCr 4:2:0 output.
[How]
Update mod_build_vsc_infopacket to support Pixel
Encoding/Colorimetry Format indication for VSC SDP rev5.
Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Bhawanpreet Lakha [Mon, 20 Aug 2018 17:32:07 +0000 (13:32 -0400)]
drm/amd/display: Build stream update and plane updates in dm
[Why]
We currently lock modeset by setting a boolean in dm. We want to lock
Based on what DC tells us.
[How]
Build stream_updates and plane_update based on what changed. Then we
call check_update_surfaces_for_stream() to get the update type
We lock only if update_type is not fast
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tony Cheng [Thu, 19 Jul 2018 00:30:09 +0000 (20:30 -0400)]
drm/amd/display: dc 3.1.64
Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 29 Aug 2018 12:52:50 +0000 (14:52 +0200)]
drm/amdgpu: manually map the shadow BOs again
Otherwise we won't be able to use the AGP aperture.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 27 Aug 2018 16:19:48 +0000 (18:19 +0200)]
drm/amdgpu: use the AGP aperture for system memory access v2
Start to use the old AGP aperture for system memory access.
v2: Move that to amdgpu_ttm_alloc_gart
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 24 Aug 2018 10:08:06 +0000 (12:08 +0200)]
drm/amdgpu: add amdgpu_gmc_agp_location v3
Helper to figure out the location of the AGP BAR.
v2: fix a couple of bugs
v3: correctly add one to vram_end
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 27 Aug 2018 16:22:31 +0000 (18:22 +0200)]
drm/amdgpu: correctly sign extend 48bit addresses v3
Correct sign extend the GMC addresses to 48bit.
v2: sign extending turned out easier than thought.
v3: clean up the defines and move them into amdgpu_gmc.h as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 30 Aug 2018 08:27:15 +0000 (10:27 +0200)]
drm/amdgpu: improve VM state machine documentation v2
Since we have a lot of FAQ on the VM state machine try to improve the
documentation by adding functions for each state move.
v2: fix typo in amdgpu_vm_bo_invalidated, use amdgpu_vm_bo_relocated in
one more place as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 3 Sep 2018 08:51:51 +0000 (10:51 +0200)]
drm/amdgpu: fix amdgpu_mn_unlock() in the CS error path
Avoid unlocking a lock we never locked.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 1 Sep 2018 11:25:31 +0000 (13:25 +0200)]
drm/amdgpu: separate per VM BOs from normal in the moved state
Allows us to avoid taking the spinlock in more places.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 30 Aug 2018 08:31:52 +0000 (10:31 +0200)]
drm/amdgpu: move size calculations to the front of the file again
amdgpu_vm_bo_* functions should come much later.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Thu, 30 Aug 2018 04:38:45 +0000 (12:38 +0800)]
drm/amd/powerplay: correct data type to support under voltage
For under voltage, negative value will be applied to voltage
offset. Update the data type to cover this case.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Wed, 29 Aug 2018 06:38:50 +0000 (14:38 +0800)]
drm/amd/powerplay: added vega20 overdrive support V3
Added vega20 overdrive support based on existing OD sysfs
APIs. However, the OD logics are simplified on vega20. So,
the behavior will be a little different and works only on
some limited levels.
V2: fix typo
fix commit description
revise error logs
add support for clock OD
V3: separate clock from voltage OD settings
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 30 Aug 2018 14:46:27 +0000 (09:46 -0500)]
drm/amdgpu/gmc9: don't keep stolen memory on vega20
Vega20 does not appear to be affected by the same issue
as vega10. Enable the full stolen memory handling on
vega20. Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 30 Aug 2018 14:44:31 +0000 (09:44 -0500)]
drm/amdgpu/gmc9: don't keep stolen memory on vega12
vega12 does not appear to be affected by the same issue
as vega10. Enable the full stolen memory handling on
vega12. Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 30 Aug 2018 14:41:12 +0000 (09:41 -0500)]
drm/amdgpu/gmc9: don't keep stolen memory on Raven
Raven does not appear to be affected by the same issue
as vega10. Enable the full stolen memory handling on
Raven. Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Bug: https://bugs.freedesktop.org/show_bug.cgi?id=106639
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 30 Aug 2018 14:31:56 +0000 (09:31 -0500)]
drm/amdgpu/gmc9: rework stolen vga memory handling
No functional change, just rework it in order to adjust the
behavior on a per asic level. The problem is that on vega10,
something corrupts the lower 8 MB of vram on the second
resume from S3. This does not seem to affect Raven, other
gmc9 based asics need testing.
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 31 Aug 2018 09:08:06 +0000 (11:08 +0200)]
drm/amdgpu: fix idle state and bulk_moveable flag
Add BOs to the idle state again and correctly clear the flag when
new BOs are added.
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>
Christian König [Thu, 30 Aug 2018 08:04:53 +0000 (10:04 +0200)]
drm/amdgpu: fix "use bulk moves for efficient VM LRU handling" v2
First step to fix the LRU corruption, we accidentially tried to move things
on the LRU after dropping the lock.
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>
Christian König [Fri, 31 Aug 2018 13:06:35 +0000 (15:06 +0200)]
drm/ttm: fix ttm_bo_bulk_move_helper
Staring at the function for six hours, just to essentially move one line
of code. The problem was that the first list_cut_position call could result
in list2 pointing to la-la-land.
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>
Andrey Grodzovsky [Thu, 30 Aug 2018 15:24:17 +0000 (11:24 -0400)]
drm/amdgpu: Use drm_dev_unplug in PCI .remove
This at least allows to fail any subsequent IOCTLs with -ENODEV
after the device is gone.
Still this operation is not supported yet in graphic mode
and will lead at least to page faults and other issues.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 30 Aug 2018 07:45:07 +0000 (09:45 +0200)]
drm/amdgpu: Revert "kmap PDs/PTs in amdgpu_vm_update_directories"
This reverts commit
a7f91061c60ad9cac2e6a03b642be6a4f88b3662.
Felix pointed out that we need to have the BOs mapped even before
amdgpu_vm_update_directories is called.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 24 Aug 2018 08:48:12 +0000 (10:48 +0200)]
drm/amdgpu: put GART away from VRAM v2
Always try to put the GART away from where VRAM is.
v2: correctly handle the 4GB limitation
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 28 Aug 2018 19:16:23 +0000 (14:16 -0500)]
drm/amdgpu: add missing CHIP_HAINAN in amdgpu_ucode_get_load_type
This caused a confusing error message, but there is functionally
no problem since the default method is DIRECT.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Amber Lin [Wed, 29 Aug 2018 17:39:16 +0000 (12:39 -0500)]
drm/amdgpu: Relocate some definitions v2
Move some KFD-related (but used in amdgpu_drv.c) definitions from
kfd_priv.h to kgd_kfd_interface.h so we don't need to include kfd_priv.h
in amdgpu_drv.c. This fixes a build failure when AMDGPU is enabled but
MMU_NOTIFIER is not.
This patch also disables KFD-related module options when HSA_AMD is not
enabled.
v2: rebase (Alex)
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Wed, 29 Aug 2018 14:53:23 +0000 (10:53 -0400)]
drm/amdgpu: remove redundant memset
kvmalloc_array uses __GFP_ZERO flag ensures that the returned address
is zeroed already, memset it to zero again afterwards is unnecessary,
and in this case buggy because we only clear the first entry.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michel Dänzer [Tue, 28 Aug 2018 16:56:29 +0000 (18:56 +0200)]
drm/ttm: Initialize local lists in ttm_bo_bulk_move_helper
The first parameter of list_cut_position() must point to an initialized
list.
Noticed thanks to KASAN pointing out something's fishy here.
Fixes: "drm/ttm: add bulk move function on LRU"
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 24 Aug 2018 07:40:10 +0000 (09:40 +0200)]
drm/amdgpu: use the smaller hole for GART
Instead of the larger one use the smaller hole in the MC address
space for the GART mappings.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michel Dänzer [Wed, 29 Aug 2018 09:59:38 +0000 (11:59 +0200)]
Revert "drm/amdgpu: move PD/PT bos on LRU again"
This reverts commit
31625ccae4464b61ec8cdb9740df848bbc857a5b.
It triggered various badness on my development machine when running the
piglit gpu profile with radeonsi on Bonaire, looks like memory
corruption due to insufficiently protected list manipulations.
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 27 Aug 2018 11:51:27 +0000 (13:51 +0200)]
drm/amdgpu: distinct between allocated GART space and GMC addr
Most of the time we only need to know if the BO has a valid GMC addr.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 27 Aug 2018 11:12:19 +0000 (13:12 +0200)]
drm/amdgpu: stop using gart_start as offset for the GTT domain
Further separate GART and GTT domain.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 23 Aug 2018 18:38:52 +0000 (20:38 +0200)]
drm/amdgpu: fix amdgpu_gmc_gart_location a little bit
Improve the VCE limitation handling.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 23 Aug 2018 13:20:43 +0000 (15:20 +0200)]
drm/amdgpu: move amdgpu_device_(vram|gtt)_location
Move that into amdgpu_gmc.c since we are really deadling with GMC
address space here.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 28 Aug 2018 11:44:32 +0000 (13:44 +0200)]
drm/amdgpu: remove amdgpu_bo_gpu_accessible
Not used any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 27 Aug 2018 19:18:36 +0000 (15:18 -0400)]
drm/amdkfd: Release an acquired process vm
For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Wed, 29 Aug 2018 17:33:52 +0000 (12:33 -0500)]
drm/amdgpu: Set pasid for compute vm (v2)
To make a amdgpu vm to a compute vm, the old pasid will be freed and
replaced with a pasid managed by kfd. Kfd can't reuse original pasid
allocated by amdgpu because kfd uses different pasid policy with amdgpu.
For example, all graphic devices share one same pasid in a process.
v2: rebase (Alex)
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michel Dänzer [Tue, 28 Aug 2018 09:26:17 +0000 (11:26 +0200)]
drm/amdgpu: Only retrieve GPU address of GART table after pinning it
Doing it earlier hits a WARN_ON_ONCE in amdgpu_bo_gpu_offset.
Fixes: "drm/amdgpu: remove gart.table_addr"
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Emily Deng [Tue, 28 Aug 2018 12:52:40 +0000 (20:52 +0800)]
drm/amdgpu: Need to set moved to true when evict bo
Fix the VMC page fault when the running sequence is as below:
1.amdgpu_gem_create_ioctl
2.ttm_bo_swapout->amdgpu_vm_bo_invalidate, as not called
amdgpu_vm_bo_base_init, so won't called
list_add_tail(&base->bo_list, &bo->va). Even the bo was evicted,
it won't set the bo_base->moved.
3.drm_gem_open_ioctl->amdgpu_vm_bo_base_init, here only called
list_move_tail(&base->vm_status, &vm->evicted), but not set the
bo_base->moved.
4.amdgpu_vm_bo_map->amdgpu_vm_bo_insert_map, as the bo_base->moved is
not set true, the function amdgpu_vm_bo_insert_map will call
list_move(&bo_va->base.vm_status, &vm->moved)
5.amdgpu_cs_ioctl won't validate the swapout bo, as it is only in the
moved list, not in the evict list. So VMC page fault occurs.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>