Felix Kuehling [Wed, 21 Nov 2018 02:00:29 +0000 (21:00 -0500)]
drm/amdkfd: Add DMABuf import functionality
This is used for interoperability between ROCm compute and graphics
APIs. It allows importing graphics driver BOs into the ROCm SVM
address space for zero-copy GPU access.
The API is split into two steps (query and import) to allow user mode
to manage the virtual address space allocation for the imported buffer.
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Wed, 21 Nov 2018 01:52:37 +0000 (20:52 -0500)]
drm/amdkfd: Add NULL-pointer check
top_dev->gpu is NULL for CPUs. Avoid dereferencing it if NULL.
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Tue, 20 Nov 2018 01:05:54 +0000 (20:05 -0500)]
drm/amdgpu: Add KFD VRAM limit checking
We don't want KFD processes evicting each other over VRAM usage.
Therefore prevent overcommitting VRAM among KFD applications with
a per-GPU limit. Also leave enough room for page tables on top
of the application memory usage.
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kuehling, Felix [Fri, 7 Dec 2018 22:07:20 +0000 (22:07 +0000)]
drm/amdgpu: Workaround build failure due to trace conflict
Avoid including mmu_context.h in amdgpu_amdkfd.h since that may be
included in other header files that define traces. This leads to
conflicts due to traces defined in other headers included via
mmu_context.h.
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
hersen wu [Wed, 28 Nov 2018 21:55:47 +0000 (16:55 -0500)]
drm/amd/powerplay: rv dal-pplib interface refactor powerplay part
[WHY] clarify dal input parameters to pplib interface, remove
un-used parameters. dal knows exactly which parameters needed
and their effects at pplib and smu sides.
current dal sequence for dcn1_update_clock to pplib:
1.smu10_display_clock_voltage_request for dcefclk
2.smu10_display_clock_voltage_request for fclk
3.phm_store_dal_configuration_data {
set_min_deep_sleep_dcfclk
set_active_display_count
store_cc6_data --- this data never be referenced
new sequence will be:
1. set_display_count --- need add new pplib interface
2. set_min_deep_sleep_dcfclk -- new pplib interface
3. set_hard_min_dcfclk_by_freq
4. set_hard_min_fclk_by_freq
after this code refactor, smu10_display_clock_voltage_request,
phm_store_dal_configuration_data will not be needed for rv.
[HOW] step 1: add new functions at pplib interface
step 2: add new functions at amdgpu dm and dc
Signed-off-by: hersen wu <hersenxs.wu@amd.com> Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
wentalou [Thu, 6 Dec 2018 02:29:52 +0000 (10:29 +0800)]
drm/amdgpu: Skip ring soft recovery when fence was NULL
amdgpu_ring_soft_recovery would have Call-Trace,
when s_fence->parent was NULL inside amdgpu_job_timedout.
Check fence first, as drm_sched_hw_job_reset did.
Signed-off-by: Wentao Lou <Wentao.Lou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Xiangliang Yu [Wed, 5 Dec 2018 06:36:33 +0000 (14:36 +0800)]
drm/amdgpu/psp: Destroy psp ring when doing gpu reset
PSP ring need to be destroy before starting reinit for vf.
This patche move it from hypervisor driver into guest.
Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Frank Min <Frank.Min@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Xiangliang Yu [Tue, 4 Dec 2018 07:13:28 +0000 (15:13 +0800)]
drm/amdgpu/psp: Get psp fw version through reading register
If PSP FW is running already, driver will not load PSP FW again and skip
it. So psp fw version is not correct if reading it from FW binary file,
need to get right version from register.
Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 24 Sep 2018 11:35:08 +0000 (13:35 +0200)]
drm/amdgpu: always reserve one more shared slot for pipelined BO moves
This allows us to drop the extra reserve in TTM.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@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 [Fri, 21 Sep 2018 16:09:59 +0000 (18:09 +0200)]
drm/amdgpu: always reserve two slots for the VM
And drop the now superflous extra reservations.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@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 [Wed, 19 Sep 2018 14:54:35 +0000 (16:54 +0200)]
drm/amdgpu: fix using shared fence for exported BOs v2
It is perfectly possible that the BO list is created before the BO is
exported. While at it clean up setting shared to one instead of true.
v2: add comment and simplify logic
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@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 [Wed, 19 Sep 2018 14:25:08 +0000 (16:25 +0200)]
drm/ttm: allow reserving more than one shared slot v3
Let's support simultaneous submissions to multiple engines.
v2: rename the field to num_shared and fix up all users
v3: rebased
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@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>
Signed-off-by: Aaron Liu <aaron.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher at amd.com> Reviewed-by: Huang Rui <ray.huang at amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch adds two new functions to help client drivers suspend and
resume the scheduler job timeout. This can be useful in cases where the
hardware has preemption support enabled. Using this, it is possible to have
the timeout active only for the ring which is active on the ringbuffer.
This patch also makes the job_list_lock IRQ safe.
Suggested-by: Christian Koenig <Christian.Koenig@amd.com> Signed-off-by: Sharat Masetty <smasetty@codeaurora.org> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Sharat Masetty [Thu, 29 Nov 2018 10:05:19 +0000 (15:35 +0530)]
drm/scheduler: Set sched->thread to NULL on failure
In cases where the scheduler instance is used as a base object of another
driver object, it's not clear if the driver can call scheduler cleanup on the
fail path. So, Set the sched->thread to NULL, so that the driver can safely
call drm_sched_fini() during cleanup.
Signed-off-by: Sharat Masetty <smasetty@codeaurora.org> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Leo Li [Thu, 22 Nov 2018 14:39:17 +0000 (09:39 -0500)]
drm/amd/include: Add mmhub 9.4 reg offsets and shift-mask
In particular, we need the mmMC_VM_XGMI_LFB_CNTL register, for
determining if xGMI is enabled on VG20. This will be used by DC to
determine the correct spread spectrum adjustment for display and audio
clocks.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Mon, 3 Dec 2018 02:47:42 +0000 (21:47 -0500)]
drm/amdgpu/si: fix SI after doorbell rework
SI does not use doorbells, move asic doorbell init later
asic check.
Fixes: https://bugs.freedesktop.org/show_bug.cgi?id=108920 Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Fri, 30 Nov 2018 14:57:06 +0000 (09:57 -0500)]
drm/amd/display: Add tracing to dc
[Why]
Tracing is a useful and cheap debug functionality
[How]
This creates a new trace system amdgpu_dm, currently with
three trace events
amdgpu_dc_rreg and amdgpu_dc_wreg report the address and value
of any dc register reads and writes
amdgpu_dc_performance requires at least one of those two to be
enabled. It counts the register reads and writes since the
last entry
v2: Don't check for NULL before kfree
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_xgmi_update_topology is called both on device registration
and reset. Fix misleading print since the device is added only once to
the hive on registration and not on reset.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Implement concurrent asic reset for XGMI.
Use per hive wq to concurrently send reset commands to all nodes
in the hive.
v2:
Switch to system_highpri_wq after dropping dedicated queue.
Fix non XGMI code path KASAN error.
Stop the hive reset for each node loop if there
is a reset failure on any of the nodes.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/psp: Update waiting in psp mode1 reset.
No point in use mdelay unless running from interrupt context (which we are not)
This is busy wait which will block the CPU for the entirety of the wait time.
Also, reduce wait time to 500ms as it is done in refernce code because
1s might cause PSP FW TO issues during XGMI hive reset.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 26 Sep 2018 12:17:03 +0000 (14:17 +0200)]
drm/amdgpu: add missing error handling
We ignored the return code here.
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>
Christian König [Wed, 7 Nov 2018 08:23:26 +0000 (09:23 +0100)]
drm/amdgpu: remove amdgpu_bo_backup_to_shadow
It is unused.
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>
drm/amd/display: Clean up for DCN1 clock debug logging
[Why]
To prepare for clock debug logging. With the exception of removing
max_supported_dppclk_khz from logs, there are no functional changes.
[How]
Add clk_bypass struct and clean up buffer logic
Signed-off-by: Fatemeh Darbehani <fatemeh.darbehani@amd.com> Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com> Acked-by: Su Chung <Su.Chung@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Steven Chiu [Mon, 12 Nov 2018 18:22:36 +0000 (13:22 -0500)]
drm/amd/display: 3.2.08
Signed-off-by: Steven Chiu <steven.chiu@amd.com> Reviewed-by: Fatemeh Darbehani <Fatemeh.Darbehani@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Fri, 9 Nov 2018 16:50:18 +0000 (11:50 -0500)]
drm/amd/display: Allow clock lower on dce100
dce100 was set to always pass safe_to_lower = false
to the clock manager
Thus, on suspend the clocks were not being set to 0
which is incorrect behaviour
This was causing s3 resume to blackscreen on intel
CPUs with dce100 GPUs attached
(Note that the hash in this Fixes: tag is the hash on Alex's tree) Fixes: ae7d8aeb38d7 ("drm/amd/display: remove safe_to_lower flag from dc, use 2 functions instead") Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dithering needs to be enabled or disabled as requested. If
dc_stream_update->dither_option is non-null, program the FMT blocks.
Signed-off-by: SivapiriyanKumarasamy <sivapiriyan.kumarasamy@amd.com> Reviewed-by: Anthony Koo <Anthony.Koo@amd.com> Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Copy crc_enabled when duplicating dm_crtc_state
[Why]
When running igt@kms_plane@pixel-format-pipe-* tests the CRC read will
time out and the test will fail.
This is because the CRTC is duplicated but the crc_enabled parameter
isn't copied over to the new dm_crtc_state. CRC reads will time out
because amdgpu_dm_crtc_handle_crc_irq will no longer call
drm_crtc_add_crc_entry.
[How]
Copy crc_enabled when duplicating the state.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: David Francis <David.Francis@amd.com> Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chiawen Huang [Fri, 9 Nov 2018 03:44:38 +0000 (11:44 +0800)]
drm/amd/display: Add customizable tracing event
[why]
add customizable log with a message input, which is for adding
test log in debugging as printf function in ETW.
[Usage]
EVENT_LOG_CUST_MSG1("TestLog","Hello World %d=0x%x", 123, pDC);
Signed-off-by: Chiawen Huang <chiawen.huang@amd.com> Reviewed-by: Tony Cheng <Tony.Cheng@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Nevenko Stupar [Fri, 9 Nov 2018 00:20:11 +0000 (19:20 -0500)]
drm/amd/display: Re-arrange GFX9 fields
For more clear usage in future
Signed-off-by: Nevenko Stupar <Nevenko.Stupar@amd.com> Reviewed-by: Tony Cheng <Tony.Cheng@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
hersen wu [Tue, 30 Oct 2018 20:39:15 +0000 (16:39 -0400)]
drm/amd/display: fbc state could not reach while enable fbc
[WHY] fbc is within the data path from memory to dce. while
re-configure mc dmif, fbc should be enabled. otherwise, fbc
may not be enabled properly.
[HOW] before re-configure mc dmif, disable fbc, only after
dmif re-configuration fully done, enable fbc again.
Signed-off-by: hersen wu <hersenxs.wu@amd.com> Reviewed-by: Roman Li <Roman.Li@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* Use provided infopacket in stream (if valid) instead of reconstructing
in set_vendor_info_packet()
* Use proper format for enums
* Use dc info packet struct instead
Signed-off-by: Harmanprit Tatla <Harmanprit.Tatla@amd.com> Reviewed-by: Anthony Koo <Anthony.Koo@amd.com> Acked-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: abdoulaye berthe <abdoulaye.berthe@amd.com> Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Krunoslav Kovac [Wed, 24 Oct 2018 19:33:50 +0000 (15:33 -0400)]
drm/amd/display: Fix spelling of axis in modules/color/color_gamma.c
Use axis instead of axix
Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com> Reviewed-by: Aric Cyr <Aric.Cyr@amd.com> Acked-by: Anthony Koo <Anthony.Koo@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
This patch is for use by dm, no need for it in dc.
Signed-off-by: Joshua Aberback <joshua.aberback@amd.com> Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Tue, 9 Oct 2018 13:45:28 +0000 (09:45 -0400)]
drm/amd/display: Start documentation of DC
[Why]
There are a lot of unintuitive parts of the dm-dc interface.
It would help us if these were documented to provide
a common understanding of what they are supposed to do
[How]
Most of this documentation is stubs, to be filled out more
thoroughly by the experts
Not every dm-accessible function and struct is mentioned.
Simple functions like getters, setters, retain, release,
create, destroy can be left unadorned.
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Steven Chiu [Mon, 5 Nov 2018 16:42:19 +0000 (11:42 -0500)]
drm/amd/display: 3.2.07
Signed-off-by: Steven Chiu <steven.chiu@amd.com> Reviewed-by: Shahin Khayyer <Shahin.Khayyer@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: fix sporadic multiple aux transaction failure
[why]
When there are multiple aux transaction in parallel, it is sometime
sporadically the aux transaction starts to continuously fail. The
aux transaction was failing because the busy bit for the given gpio
pin was always set. The busy bit was alway set because the
programming sequence to read, modify and write busy bit was not
atomic. Due to which when multiple threads are trying to modify the
busy bits for their gpio pins in the same integer variable sometimes
the busy bits integer variable is written with old data causing
failure.
[how]
Instead of using individual bits to track gpio pins and grouping
them to integers, one byte will be allcoated for each gpio pin.
Now whenever a gpio pin needs to be set to mark being used, only
writing a value of one to that byte is sufficient, other bytes
are not impacted. Also no need to have atomicity with bytes unlike
with bits.
Signed-off-by: Yogesh Mohan Marimuthu <yogesh.mohanmarimuthu@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Fri, 30 Nov 2018 15:33:02 +0000 (09:33 -0600)]
drm/amdgpu: Fix num_doorbell calculation issue
When paging queue is enabled, it use the second page of doorbell.
The AMDGPU_DOORBELL64_MAX_ASSIGNMENT definition assumes all the
kernel doorbells are in the first page. So with paging queue enabled,
the total kernel doorbell range should be original num_doorbell plus
one page (0x400 in dword), not *2.
Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 29 Nov 2018 15:25:10 +0000 (16:25 +0100)]
drm/ttm: fix LRU handling in ttm_buffer_object_transfer
We need to set the NO_EVICT flag on the ghost object or otherwise we are
adding it to the LRU.
When it is added to the LRU we can run into a race between destroying
and evicting it again.
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>
drm/amd/display: Fix NULL ptr deref for commit_planes_to_stream
[Why]
With scaling, underscan and abm changes we can end up calling
commit_planes_to_stream in commit_tail. This call uses dm_state->context
which can be NULL if the commit was a fast update.
[How]
Use dc_state instead since that can't be NULL unless the system ran
out of memory.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108912 Fixes: e64abff2f133 ("drm/amd/display: Use private obj helpers for dm_atomic_state") Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Roman Li [Tue, 27 Nov 2018 22:16:37 +0000 (17:16 -0500)]
drm/amd/display: Fix 6x4K displays light-up on Vega20
[Why]
More than 4x4K didn't lightup on Vega20 due to low dcfclk value.
Powerplay expects valid min requirement for dcfclk from DC.
[How]
Update min_dcfclock_khz based on min_engine_clock value.
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com> Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Reviewed-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Roman Li <Roman.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Young Xiao [Tue, 27 Nov 2018 11:50:17 +0000 (11:50 +0000)]
drm: radeon: fix overflow on 32bit systems
the type mem->start is unsigned long, so this can overflow on
32bit system, since the type addr is uint64_t.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Young Xiao <YangX92@hotmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108709 Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For XGMI hive case do reset in steps where each step iterates over
all devs in hive. This especially important for asic reset
since all PSP FW in hive must come up within a limited time
(around 1 sec) to properply negotiate the link.
Do this by refactoring amdgpu_device_gpu_recover and amdgpu_device_reset
into pre_asic_reset, asic_reset and post_asic_reset functions where is part
is exectued for all the GPUs in the hive before going to the next step.
v2: Update names for amdgpu_device_lock/unlock functions.
v3: Introduce per hive locking to avoid multiple resets for GPUs
in same hive.
v4:
Remove delayed_workqueue()/ttm_bo_unlock_delayed_workqueue() - they
are copy & pasted over from radeon and on amdgpu there isn't
any reason for that any more.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v3:
Add per hive lock to allow avoiding duplicate resets triggered by
multiple members of same hive.
Expose amdgpu_hive_info instead of adding getter functions.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This is prep work for updating each PSP FW in hive after
GPU reset.
Split into build topology SW state and update each PSP FW in the hive.
Save topology and count of XGMI devices for reuse.
v2: Create seperate header for XGMI.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Set FreeSync state using drm VRR properties
Support for AMDGPU specific FreeSync properties and ioctls are dropped
from amdgpu_dm in favor of supporting drm variable refresh rate
properties.
The notify_freesync and set_freesync_property functions are dropped
from amdgpu_display_funcs.
The drm vrr_capable property is now attached to any DP/HDMI connector.
Its value is updated accordingly to the connector's FreeSync capabiltiy.
The freesync_enable logic and ioctl control has has been dropped in
favor of utilizing the vrr_enabled on the drm CRTC. This allows for more
fine grained atomic control over which CRTCs should support variable
refresh rate.
To handle state changes for vrr_enabled it was easiest to drop the
forced modeset on freesync_enabled change. This patch now performs the
required stream updates when planes are flipped.
This is done for a few reasons:
(1) VRR stream updates can be done in the fast update path
(2) amdgpu_dm_atomic_check would need to be hacked apart to check
desired variable refresh state and capability before the CRTC
disable pass.
(3) Performing VRR stream updates on-flip is needed for enabling BTR
support.
VRR packets and timing adjustments are now tracked and compared to
previous values sent to the hardware.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Correct get_crtc_scanoutpos behavior when vpos >= vtotal
When variable refresh rate is active the hardware counter can return
a position >= vtotal. This results in a vpos being returned from
amdgpu_display_get_crtc_scanoutpos that's a positive value. The
positive value indicates to the caller that the display is
currently in scanout when the display is actually still in vblank.
This is because the vfront porch duration is unknown with variable
refresh active and will end when either a page flip occurs or the
timeout specified by the driver/display is reached.
The behavior of the amdgpu_display_get_crtc_scanoutpos remains the
same when the position is below vtotal. When the position is above
vtotal the function will return a value that is effectively -vbl_end,
the size of the vback porch.
The only caller affected by this change is the DRM helper for
calculating vblank timestamps. This change corrects behavior for
calculating the page flip timestamp from being the previous timestamp
to the calculation to the next timestamp when position >= vtotal.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
These include the drm_connector 'vrr_capable' and the drm_crtc
'vrr_enabled' properties.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Acked-by: Pekka Paalanen <pekka.paalanen@collabora.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch introduces the 'vrr_enabled' CRTC property to allow
dynamic control over variable refresh rate support for a CRTC.
This property should be treated like a content hint to the driver -
if the hardware or driver is not capable of driving variable refresh
timings then this is not considered an error.
Capability for variable refresh rate support should be determined
by querying the vrr_capable drm connector property.
It is worth noting that while the property is intended for atomic use
it isn't filtered from legacy userspace queries. This allows for Xorg
userspace drivers to implement support.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm: Add vrr_capable property to the drm connector
Modern display hardware is capable of supporting variable refresh rates.
This patch introduces the "vrr_capable" property on the connector to
allow userspace to query support for variable refresh rates.
Atomic drivers should attach this property to connectors that are
capable of driving variable refresh rates using
drm_connector_attach_vrr_capable_property().
The value should be updated based on driver and hardware capability
by using drm_connector_set_vrr_capable_property().
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Manasi Navare <manasi.d.navare@intel.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Fri, 23 Nov 2018 19:48:27 +0000 (13:48 -0600)]
drm/amdgpu: Move doorbell structures to seperate file
Move doorbell structures, enum definitions and helper functions
from amdgpu.h to amdgpu_doorbell.h. No functional change
Signed-off-by: Oak Zeng <ozeng@amd.com> Proposed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 19 Nov 2018 21:20:07 +0000 (15:20 -0600)]
drm/amdgpu: Use asic specific doorbell index instead of macro definition
ASIC specific doorbell layout is used instead of enum definition
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 19 Nov 2018 20:36:09 +0000 (14:36 -0600)]
drm/amdgpu: Call doorbell index init on device initialization
Also call functioin amdgpu_device_doorbell_init after
amdgpu_device_ip_early_init because the former depends
on the later to set up asic-specific init_doorbell_index
function
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 19 Nov 2018 21:59:53 +0000 (15:59 -0600)]
drm/amdgpu: Doorbell layout for vega20 and future asic
This introduces new doorbell layout for vega20 and future asics
v2: Use enum definition instead of hardcoded value
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 19 Nov 2018 15:51:20 +0000 (09:51 -0600)]
drm/amdgpu: Doorbell index initialization for ASICs before vega10
Initialize doorbell index for asics vi and cik
v2: Use enum definition instead of hardcoded number
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 19 Nov 2018 15:25:37 +0000 (09:25 -0600)]
drm/amdgpu: Vega10 doorbell index initialization
v2: Use enum definition instead of hardcoded value
v3: Remove unused enum definition
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Mon, 26 Nov 2018 16:41:23 +0000 (10:41 -0600)]
drm/amdgpu: Add asic func interface to init doorbell index
This is preparation to move doorbell index initialization
to amdgpu_asic_funcs
Signed-off-by: Oak Zeng <ozeng@amd.com> Proposed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Oak Zeng [Sat, 17 Nov 2018 01:23:44 +0000 (19:23 -0600)]
drm/amdgpu: Add field in amdgpu_dev to hold reserved doorbell index
This is a preparation work to make reserved doorbell index per device,
instead of using a global macro definition. By doing this, we can easily
change doorbell layout for future ASICs while not affecting ASICs in
production.
Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Tue, 27 Nov 2018 16:10:07 +0000 (11:10 -0500)]
drm/amd/display: Fix compile error with ACPI disabled
The fallback code for getting default backlight caps was using
the wrong variable name. Fix it.
Fixes: https://lists.freedesktop.org/archives/dri-devel/2018-November/197752.html Signed-off-by: David Francis <David.Francis@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Use private obj helpers for dm_atomic_state
[Why]
Two non-blocking commits in succession can result in a sequence where
the same dc->current_state is queried for both commits.
1. 1st commit -> check -> commit -> swaps atomic state -> queues work
2. 2nd commit -> check -> commit -> swaps atomic state -> queues work
3. 1st commit work finishes
The issue with this sequence is that the same dc->current_state is
read in both atomic checks. If the first commit modifies streams or
planes those will be missing from the dc->current_state for the
second atomic check. This result in many stream and plane errors in
atomic commit tail.
[How]
The driver still needs to track old to new state to determine if the
commit in its current implementation. Updating the dc_state in
atomic tail is wrong since the dc_state swap should be happening as
part of drm_atomic_helper_swap_state *before* the worker queue kicks
its work off.
The simplest replacement for the subclassing (which doesn't properly
manage the old to new atomic state swap) is to use the drm private
object helpers. While some of the dc_state members could be merged
into dm_crtc_state or dm_plane_state and copied over that way it is
easier for now to just treat the whole dc_state structure as a single
private object.
This allows amdgpu_dm to drop the dc->current_state copy from within
atomic check. It's replaced by a copy from the current atomic state
which is propagated correctly for the sequence described above.
Since access to the dm_state private object is now locked this should
also fix issues that could arise if submitting non-blocking commits
from different threads.
Cc: Harry Wentland <harry.wentland@amd.com> Cc: Leo Li <sunpeng.li@amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
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>
David Francis [Mon, 26 Nov 2018 16:44:06 +0000 (11:44 -0500)]
drm/amd: Query and use ACPI backlight caps
ACPI ATIF has a function called query
backlight transfer characteristics. Among the
information returned by this function is
the minimum and maximum input signals for the
backlight
Call that function on ACPI init. When DM
backlight device is updated, copy over the
backlight caps into DM, but only once. Use
the backlight caps in the backlight-to-dc
calculation
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Mon, 26 Nov 2018 18:14:14 +0000 (13:14 -0500)]
drm/amd: update ATIF functions in AMD ACPI header
The ACPI interface in AMD was a few years out of date
and contained some unused and deprecated functions
Remove functions: Select Active Displays, Get Lid State,
Get TV Standard, Set TV Standard, Get Panel Expansion Mode,
Set Panel Expansion Mode, Get Graphics Device Types
Add functions: Query Backlight Transfer Characteristics,
Ready To Undock Notification
Changed functions: Get System Parameters,
Get System BIOS Requests
All changes are right from the standard
ATI ACPI Control Methods V0.44
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Mon, 26 Nov 2018 20:51:09 +0000 (15:51 -0500)]
drm/amd: Add abm level drm property
Adaptive Backlight Management (ABM) is a feature
that reduces backlight level to save power, while
increasing pixel contrast and pixel luminance
to maintain readability and image quality.
ABM will adjust in response to the
pixel luminance of the displayed content.
ABM is made available as a drm property on eDP
monitors called "abm level", which ranges from 0 to 4.
When this property is set to 0, ABM is off. Levels 1
to 4 represent different ranges of backlight reduction.
At higher levels both the backlight reduction and pixel
adjustment will be greater.
ABM requires DMCU firmware, which is currently available for
Raven ASICs only. If the feature does not work, please
ensure your firmware is up to date.
v2:
Fix commit message, only attach property if DMCU loaded
v3:
Store ABM level in crtc state to accommodate dc
v4:
Fix ABM saving on dpms cycle
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
David Francis [Mon, 26 Nov 2018 16:38:33 +0000 (11:38 -0500)]
drm/amd/display: Load DMCU IRAM
DMCU IRAM must be loaded by the driver before DMCU
can function.
Move the IRAM code out of the shadows and into a new file
modules/power/power_helpers.c
The IRAM table contains the backlight curve and ABM parameters
Add this new file to the Makefiles
Call dmcu_load_iram in late init of DM
Move struct dmcu_version from dc.h to dmcu.h to allow
dmcu to be included on its own
Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rex Zhu [Fri, 23 Nov 2018 10:52:21 +0000 (18:52 +0800)]
drm/amdgpu: Fix static checker warning
drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c:49 amdgpu_allocate_static_csa()
error: uninitialized symbol 'ptr'.
the test if (!bo) doesn't work, as the bo is a pointer to a pointer.
if bo create failed, the *bo will be set to NULL.
so change to test *bo.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Guttula, Suresh [Fri, 16 Nov 2018 06:50:37 +0000 (06:50 +0000)]
drm/amd:Enable/Disable NBPSTATE on On/OFF of UVD
We observe black lines (underflow) on display when playing a
4K video with UVD. On Disabling Low memory P state this issue is
not seen.
In this patch ,disabling low memory P state only when video
size >= 4k.
Multiple runs of power measurement shows no impact
Signed-off-by: suresh guttula <suresh.guttula@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reason for revert:
This patch sends msg PPSMC_MSG_DisableLowMemoryPstate(0x002e)
in wrong of sequence to SMU which is before PPSMC_MSG_UVDPowerON (0x0008).
This leads to SMU failing to service the request as it is
dependent on UVD to be powered ON, since it accesses UVD
registers.
This msg should ideally be sent only when the UVD is about to decode
a 4k video.
Signed-off-by: Shirish S <shirish.s@amd.com> Signed-off-by: suresh guttula <suresh.guttula@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Fix Scaling (RMX_*) for DC driver
Before:
We use drm_match_cea_mode() to get the vic for any mode we
want to set, most of the time vic will be different for the new mode.
DC uses memcmp to check if timing changed, in this case DC will
say timing changed and we endup doing a full modeset.
Current:
Now we check if !RMX_OFF and old_refresh == new_refresh if so
we copy the vic from old timing. In a case where we are currently on
a lower timing and want to change to higher mode, stream->dst will be
different and cause us to do a full modeset, which is what we want.
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Setting this allows for display scaling by default
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Colin Ian King [Tue, 20 Nov 2018 17:17:45 +0000 (17:17 +0000)]
drm/amd/display: fix dereference of pointer fs_params before it is null checked
Currently there are several instances of pointer fs_params being
dereferenced before fs_params is being null checked. Fix this by
only dereferencing fs_params after the null check.
Detected by CoverityScan, CID#1475565 ("Dereference before null check")
Fixes: e1e8a020c6b8 ("drm/amd/display: Add support for Freesync 2 HDR and Content to Display Mapping") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Mon, 19 Nov 2018 14:53:43 +0000 (09:53 -0500)]
drm/amdgpu: enable paging queue based on FW version (v2)
Based SDMA fw version to enable has_page_queue support. Have to move
sdma_v4_0_init_microcode from sw_init to early_init, to load firmware
and init fw_version before set_ring/buffer/vm_pte_funcs use it.
v2: don't enable on vega12, 20 until confirmed
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Mon, 19 Nov 2018 15:36:02 +0000 (10:36 -0500)]
drm/amdgpu: enable paging queue doorbell support v4
Because increase SDMA_DOORBELL_RANGE to add new SDMA doorbell for paging queue will
break SRIOV, instead we can reserve and map two doorbell pages for amdgpu, paging
queues doorbell index use same index as SDMA gfx queues index but on second page.
For Vega20, after we change doorbell layout to increase SDMA doorbell for 8 SDMA RLC
queues later, we could use new doorbell index for paging queue.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@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>
Philip Yang [Mon, 19 Nov 2018 15:37:08 +0000 (10:37 -0500)]
drm/amdgpu: fix typo in function sdma_v4_0_page_resume
This looks like copy paste typo
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>
Rex Zhu [Mon, 19 Nov 2018 10:59:53 +0000 (18:59 +0800)]
drm/amdgpu: Remove dead static variable
The static struct drm_driver *driver was
not used because drm_pci_init was deprecated
v2: Remove static pointer pdriver(Christian)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Eric Huang [Wed, 5 Sep 2018 15:46:14 +0000 (11:46 -0400)]
drm/amdkfd: change system memory overcommit limit
It is to improve system limit by:
1. replacing userptrlimit with a total memory limit that
conunts TTM memory usage and userptr usage.
2. counting acc size for all BOs.
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Thu, 3 May 2018 21:37:56 +0000 (17:37 -0400)]
drm/amdgpu: Fix KFD doorbell SG BO mapping
This change prepares for adding SG BOs that will be used for mapping
doorbells into GPUVM address space.
This type of BO would be mistaken for an invalid userptr BO. Improve
that check to test that it's actually a userptr BO so that SG BOs that
are still in the CPU domain can be validated and mapped correctly.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>