Alvin Lee [Mon, 2 May 2022 19:04:31 +0000 (15:04 -0400)]
drm/amd/display: Add SubVP required code
This commit enables the SubVP feature. To achieve that, we need to:
- Don't force p-state disallow on SubVP (can't block dummy p-state)
- Send calculated watermark to DMCUB for SubVP
- Adjust CAB mode message to PMFW
- Add a proper locking sequence for SubVP
- Various fixes to SubVP static analysis and determining SubVP config
- Currently SubVP not supported with pipe split so merge all pipes
before setting up SubVp
Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Wed, 29 Jun 2022 11:33:05 +0000 (19:33 +0800)]
drm/amd/pm: update SMU 13.0.0 driver_if header
And bump the version to 0x2A.
Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Lang Yu [Tue, 7 Jun 2022 07:58:23 +0000 (15:58 +0800)]
drm/amdkfd: simplify vm_validate_pt_pd_bos
We don't need to validate and map root PD specially here,
it would be validated and mapped by amdgpu_vm_validate_pt_bos
if it is evicted.
The special case is when turning a GFX VM to a compute VM,
if vm_update_mode changed, we should make sure root PD gets
mapped. So just map root PD after updating vm->update_funcs
in amdgpu_vm_make_compute whether the vm_update_mode changed
or not.
v3:
- Add some comments suggested by Christian.
v2:
- Don't rename vm_validate_pt_pd_bos and make it public.
Signed-off-by: Lang Yu <Lang.Yu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rodrigo Siqueira [Thu, 30 Jun 2022 18:46:20 +0000 (14:46 -0400)]
drm/amd/display: Fix __muldf3 undefined for 32 bit compilation
Sometimes when trying to enable some feature, we have to define some
values with educated guesses, but we mark those values as TBD, which
means "To Be Determined". However, the correct way to approach it is by
loading that information from the firmware. Anyway, some of the values
that we were experimenting with caused this issue:
This was caused because we were trying to assign an unsigned int to a
double value which causes issues for 32-bit architecture. This issue can
be fixed by changing the value type.
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com> Cc: Harry Wentland <harry.wentland@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Randy Dunlap <rdunlap@infradead.org> Fixes: 265280b99822 ("drm/amd/display: add CLKMGR changes for DCN32/321") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Randy Dunlap <rdunlap@infradead.org> Tested-by: Randy Dunlap <rdunlap@infradead.org> # build-tested Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Wed, 19 Jan 2022 17:57:26 +0000 (12:57 -0500)]
drm/amdkfd: Bump KFD API version for SMI profiling event
Indicate SMI profiling events available.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Fri, 8 Apr 2022 14:25:11 +0000 (10:25 -0400)]
drm/amdkfd: Asynchronously free smi_client
The synchronize_rcu may take several ms, which noticeably slows down
applications close SMI event handle. Use call_rcu to free client->fifo
and client asynchronously and eliminate the synchronize_rcu call in the
user thread.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Thu, 20 Jan 2022 21:43:42 +0000 (16:43 -0500)]
drm/amdkfd: Add unmap from GPU SMI event
SVM range unmapped from GPUs when range is unmapped from CPU, or with
xnack on from MMU notifier when range is evicted or migrated.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Fri, 14 Jan 2022 02:24:20 +0000 (21:24 -0500)]
drm/amdkfd: Add user queue eviction restore SMI event
Output user queue eviction and restore event. User queue eviction may be
triggered by svm or userptr MMU notifier, TTM eviction, device suspend
and CRIU checkpoint and restore.
User queue restore may be rescheduled if eviction happens again while
restore.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Fri, 14 Jan 2022 00:28:13 +0000 (19:28 -0500)]
drm/amdkfd: Add migration SMI event
For migration start and end event, output timestamp when migration
starts, ends, svm range address and size, GPU id of migration source and
destination and svm range attributes,
Migration trigger could be prefetch, CPU or GPU page fault and TTM
eviction.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Fri, 14 Jan 2022 00:22:54 +0000 (19:22 -0500)]
drm/amdkfd: Add GPU recoverable fault SMI event
Use ktime_get_boottime_ns() as timestamp to correlate with other
APIs. Output timestamp when GPU recoverable fault starts and ends to
recover the fault, if migration happened or only GPU page table is
updated to recover, fault address, if read or write fault.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Thu, 13 Jan 2022 23:59:02 +0000 (18:59 -0500)]
drm/amdkfd: Enable per process SMI event
Process receive event from same process by default. Add a flag to be
able to receive event from all processes, this requires super user
permission.
Event using pid 0 to send the event to all processes, to keep the
default behavior of existing SMI events.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Thu, 20 Jan 2022 20:06:30 +0000 (15:06 -0500)]
drm/amdkfd: Add KFD SMI event IDs and triggers
Define new system management interface event IDs for migration, GPU
recoverable page fault, user queues eviction, restore and unmap from
GPU events and corresponding event triggers, those will be implemented
in the following patches.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jonathan Kim [Mon, 27 Jun 2022 01:35:10 +0000 (21:35 -0400)]
drm/amdkfd: fix cu mask for asics with wgps
GFX10 and up have work group processors (WGP) and WGP mode is the native
compile mode.
KFD and ROCr have no visibility into whether a dispatch is operating
in CU or WGP mode.
Enforce CU masking to be pairwise continguous in enablement and
round robin distribute CUs across the SEs in a pairwise manner to
assume WGP mode at all times.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 23 Jun 2022 16:37:40 +0000 (12:37 -0400)]
drm/amdgpu: fix documentation warning
Fixes this issue:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:5094: warning: expecting prototype for amdgpu_device_gpu_recover_imp(). Prototype was for amdgpu_device_gpu_recover() instead
Fixes: cf727044144d ("drm/amdgpu: Rename amdgpu_device_gpu_recover_imp back to amdgpu_device_gpu_recover") Reviewed-by: Kent Russell <kent.russell@amd.com> Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Re-org and cleanup the redundant code
[Why]
Redundant if-else cases for repeater and non-repeater checks
[How]
Without changing the core logic, rearranged the code by removing
redundant checks
Signed-off-by: Chandan Vurdigere Nataraj <chandan.vurdigerenataraj@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aurabindo Pillai [Tue, 28 Jun 2022 20:25:28 +0000 (16:25 -0400)]
drm/amd/display: expose additional modifier for DCN32/321
[Why&How]
Some userspace expect a backwards compatible modifier on DCN32/321. For
hardware with num_pipes more than 16, we expose the most efficient
modifier first. As a fall back method, we need to expose slightly inefficient
modifier AMD_FMT_MOD_TILE_GFX9_64K_R_X after the best option.
Also set the number of packers to fixed value as required per hardware
documentation. This value is cached during hardware initialization and
can be read through the base driver.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There are 4 undocumented fields at struct amdgpu_display_manager.
Add documentation for them, fixing those warnings:
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'dmub_outbox_params' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'num_of_edps' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'disable_hpd_irq' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'dmub_aux_transfer_done' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'delayed_hpd_wq' not described in 'amdgpu_display_manager'
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom Rix [Sun, 26 Jun 2022 14:46:15 +0000 (10:46 -0400)]
drm/amd/display: change to_dal_irq_source_dnc32() storage class specifier to static
sparse reports
drivers/gpu/drm/amd/amdgpu/../display/dc/irq/dcn32/irq_service_dcn32.c:39:20: warning: symbol 'to_dal_irq_source_dcn32' was not declared. Should it be static?
to_dal_irq_source_dnc32() is only referenced in irq_service_dnc32.c, so change its
storage class specifier to static.
Fixes: 0efd4374f6b4 ("drm/amd/display: add dcn32 IRQ changes") Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom Rix [Sun, 26 Jun 2022 14:20:53 +0000 (10:20 -0400)]
drm/amd/display: Remove unused globals FORCE_RATE and FORCE_LANE_COUNT
sparse reports
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_dp.c:3885:6: warning: symbol 'FORCE_RATE' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_dp.c:3886:10: warning: symbol 'FORCE_LANE_COUNT' was not declared. Should it be static?
Neither of thse variables is used in dc_link_dp.c. Reviewing the commit listed in
the fixes tag shows neither was used in the original patch. So remove them.
Fixes: 265280b99822 ("drm/amd/display: add CLKMGR changes for DCN32/321") Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Thu, 23 Jun 2022 16:34:18 +0000 (12:34 -0400)]
drm/amdgpu/display: drop set but unused variable
No longer used so drop it.
Fixes: ec457f837890 ("drm/amd/display: Drop unnecessary detect link code") Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kent Russell [Tue, 28 Jun 2022 14:40:59 +0000 (10:40 -0400)]
drm/amdgpu: Fix typos in amdgpu_stop_pending_resets
Change amdggpu to amdgpu and pedning to pending
Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link.c:
In function 'dc_link_reduce_mst_payload':
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link.c:3782:32:
warning: variable 'ret' set but not used [-Wunused-but-set-variable]
3782 | enum act_return_status ret;
Removed the unused ret variable.
Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Souptick Joarder (HPE) <jrdr.linux@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This causes KFDTest KFDMemoryTest.MemoryRegister test failed on gfx9.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Follow up change to previous drm scheduler change.
Align refcount behaviour for amdgpu_job embedded HW fence with
classic pointer style HW fences by increasing refcount each
time emit is called so amdgpu code doesn't need to make workarounds
using amdgpu_job.job_run_counter to keep the HW fence refcount balanced.
Also since in the previous patch we resumed setting s_fence->parent to NULL
in drm_sched_stop switch to directly checking if job->hw_fence is
signaled to short circuit reset if already signed.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Tested-by: Yiqing Yao <yiqing.yao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/sched: Partial revert of 'drm/sched: Keep s_fence->parent pointer'
Problem:
This patch caused negative refcount as described in [1] because
for that case parent fence did not signal by the time of drm_sched_stop and hence
kept in pending list the assumption was they will not signal and
so fence was put to account for the s_fence->parent refcount but for
amdgpu which has embedded HW fence (always same parent fence)
drm_sched_fence_release_scheduled was always called and would
still drop the count for parent fence once more. For jobs that
never signaled this imbalance was masked by refcount bug in
amdgpu_fence_driver_clear_job_fences that would not drop
refcount on the fences that were removed from fence drive
fences array (against prevois insertion into the array in
get in amdgpu_fence_emit).
Fix:
Revert this patch and by setting s_job->s_fence->parent to NULL
as before prevent the extra refcount drop in amdgpu when
drm_sched_fence_release_scheduled is called on job release.
Also - align behaviour in drm_sched_resubmit_jobs_ext with that of
drm_sched_main when submitting jobs - take a refcount for the
new parent fence pointer and drop refcount for original kref_init
for new HW fence creation (or fake new HW fence in amdgpu - see next patch).
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Tested-by: Yiqing Yao <yiqing.yao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Prevent race between late signaled fences and GPU reset.
Problem:
After we start handling timed out jobs we assume there fences won't be
signaled but we cannot be sure and sometimes they fire late. We need
to prevent concurrent accesses to fence array from
amdgpu_fence_driver_clear_job_fences during GPU reset and amdgpu_fence_process
from a late EOP interrupt.
Fix:
Before accessing fence array in GPU disable EOP interrupt and flush
all pending interrupt handlers for amdgpu device's interrupt line.
v2: Switch from irq_get/put to full enable/disable_irq for amdgpu
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: Add put fence in amdgpu_fence_driver_clear_job_fences
This function should drop the fence refcount when it extracts the
fence from the fence array, just as it's done in amdgpu_fence_process.
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>
[How]
Update the existing log with DP LT failure reason
Signed-off-by: Chandan Vurdigere Nataraj <chandan.vurdigerenataraj@amd.com> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Tue, 14 Jun 2022 07:21:48 +0000 (15:21 +0800)]
drm/amd/pm: enable VR0 HOT support for SMU 13.0.0
Enable VR0 Hot support for SMU 13.0.0.
Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Thu, 3 Mar 2022 06:39:22 +0000 (14:39 +0800)]
drm/amdgpu: update GFX11 cs settings
Update GFX11 cs related settings.
Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Wed, 22 Jun 2022 14:36:58 +0000 (10:36 -0400)]
drm/amdgpu/display: reduce stack size in dml32_ModeSupportAndSystemConfigurationFull()
Move more stack variable in to dummy vars structure on the heap.
Fixes stack frame size errors:
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/display_mode_vba_32.c: In function 'dml32_ModeSupportAndSystemConfigurationFull':
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/display_mode_vba_32.c:3833:1: error: the frame size of 2720 bytes is larger than 2048 bytes [-Werror=frame-larger-than=]
3833 | } // ModeSupportAndSystemConfigurationFull
| ^
Fixes: dda4fb85e433 ("drm/amd/display: DML changes for DCN32/321") Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Aurabindo Pillai <aurabindo.pillai@amd.com> Cc: Rodrigo Siqueira Jordao <Rodrigo.Siqueira@amd.com> Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This breaks validation and enumeration of display capable modifiers.
The early return true means the rest of the validation code never gets
executed, and we need that to enumerate the right modifiers to userspace
for the format.
The modifiers that are in the initial list generated for a plane are the
superset for all formats and we need the proper checks in this function
to filter some of them out for formats with which they're invalid to be
used.
Furthermore, the safety contract here is that we validate the incoming
modifiers to ensure the kernel can handle them and the display hardware
can handle them. This includes e.g. rejecting multi-plane images with DCC.
Note that the legacy swizzle mechanism allows encoding more swizzles, and
at fb creation time we convert them to modifiers and reject those with
no corresponding modifiers. If we are seeing rejections I'm happy to
help define modifiers that correspond to those, or if absolutely needed
implement a fallback path to allow for less strict validation of the
legacy path.
However, I'd like to revert this patch, since any of these is going to
be a significant rework of the patch, and I'd rather not the regression
gets into a release or forgotten in the meantime.
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is a spelling mistake in a dml_print message. Fix it.
Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Colin Ian King <colin.i.king@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This causes stuttering and timeouts with DMCUB for some users
so revert it until we understand why and safely enable it
to save power.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1887 Acked-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
drm/amd/display: Fix indentation in dcn32_get_vco_frequency_from_reg()
Clang warns:
drivers/gpu/drm/amd/amdgpu/../display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c:549:4: warning: misleading indentation; statement is not part of the previous 'else' [-Wmisleading-indentation]
pll_req = dc_fixpt_from_int(pll_req_reg & clk_mgr->clk_mgr_mask->FbMult_int);
^
drivers/gpu/drm/amd/amdgpu/../display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c:542:3: note: previous statement is here
else
^
1 warning generated.
Indent this statement to the left, as it was clearly intended to be
called unconditionally, which will fix the warning.
Link: https://github.com/ClangBuiltLinux/linux/issues/1655 Fixes: 3e838f7ccf64 ("drm/amd/display: Get VCO frequency from registers") Signed-off-by: Nathan Chancellor <nathan@kernel.org> Reviewed-by: Leo Li <sunpeng.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Graham Sider [Thu, 28 Apr 2022 14:16:16 +0000 (10:16 -0400)]
drm/amdgpu: Update mes_v11_api_def.h
Update MES API to support oversubscription without aggregated doorbell
for usermode queues.
v2: Change oversubscription_no_aggregated_en to is_kfd_process (align
with MES)
Signed-off-by: Graham Sider <Graham.Sider@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Starting with GFX11, MES requires wptr BOs to be GTT allocated/mapped to
GART for usermode queues in order to support oversubscription. In the
case that work is submitted to an unmapped queue, MES must have a GART
wptr address to determine whether the queue should be mapped.
This change is accompanied with changes in MES and is applicable for
MES_API_VERSION >= 2.
v3:
- Use amdgpu_vm_bo_lookup_mapping for wptr_bo mapping lookup
- Move wptr_bo refcount increment to amdgpu_amdkfd_map_gtt_bo_to_gart
- Remove list_del_init from amdgpu_amdkfd_map_gtt_bo_to_gart
- Cleanup/fix create_queue wptr_bo error handling
v4:
- Add MES version shift/mask defines to amdgpu_mes.h
- Change version check from MES_VERSION to MES_API_VERSION
- Add check in kfd_ioctl_create_queue before wptr bo pin/GART map to
ensure bo is a single page.
Signed-off-by: Graham Sider <Graham.Sider@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Graham Sider [Fri, 3 Jun 2022 13:53:54 +0000 (09:53 -0400)]
drm/amdgpu: Fetch MES scheduler/KIQ versions
Store MES scheduler and MES KIQ version numbers in amdgpu_mes for GFX11.
Signed-off-by: Graham Sider <Graham.Sider@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Ruili Ji [Wed, 22 Jun 2022 06:20:22 +0000 (14:20 +0800)]
drm/amdgpu: To flush tlb for MMHUB of RAVEN series
amdgpu: [mmhub0] no-retry page fault (src_id:0 ring:40 vmid:8 pasid:32769, for process test_basic pid 3305 thread test_basic pid 3305)
amdgpu: in page starting at address 0x00007ff990003000 from IH client 0x12 (VMC)
amdgpu: VM_L2_PROTECTION_FAULT_STATUS:0x00840051
amdgpu: Faulty UTCL2 client ID: MP1 (0x0)
amdgpu: MORE_FAULTS: 0x1
amdgpu: WALKER_ERROR: 0x0
amdgpu: PERMISSION_FAULTS: 0x5
amdgpu: MAPPING_ERROR: 0x0
amdgpu: RW: 0x1
When memory is allocated by kfd, no one triggers the tlb flush for MMHUB0.
There is page fault from MMHUB0.
v2:fix indentation
v3:change subject and fix indentation
Signed-off-by: Ruili Ji <ruiliji2@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Reviewed-by: Aaron Liu <aaron.liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Carlos Llamas [Tue, 21 Jun 2022 20:39:21 +0000 (20:39 +0000)]
drm/fourcc: fix integer type usage in uapi header
Kernel uapi headers are supposed to use __[us]{8,16,32,64} types defined
by <linux/types.h> as opposed to 'uint32_t' and similar. See [1] for the
relevant discussion about this topic. In this particular case, the usage
of 'uint64_t' escaped headers_check as these macros are not being called
here. However, the following program triggers a compilation error:
#include <drm/drm_fourcc.h>
int main()
{
unsigned long x = AMD_FMT_MOD_CLEAR(RB);
return 0;
}
gcc error:
drm.c:5:27: error: ‘uint64_t’ undeclared (first use in this function)
5 | unsigned long x = AMD_FMT_MOD_CLEAR(RB);
| ^~~~~~~~~~~~~~~~~
This patch changes AMD_FMT_MOD_{SET,CLEAR} macros to use the correct
integer types, which fixes the above issue.
[1] https://lkml.org/lkml/2019/6/5/18
Fixes: 8ba16d599374 ("drm/fourcc: Add AMD DRM modifiers.") Signed-off-by: Carlos Llamas <cmllamas@google.com> Reviewed-by: Simon Ser <contact@emersion.fr> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Darren Powell [Wed, 11 May 2022 05:07:04 +0000 (01:07 -0400)]
amdgpu/pm: Fix possible array out-of-bounds if SCLK levels != 2
[v2]
simplified fix after Lijo's feedback
removed clocks.num_levels from calculation of loop count
removed unsafe accesses to shim table freq_values
retained corner case output only min,now if
clocks.num_levels == 1 && now > min
[v1]
added a check to populate and use SCLK shim table freq_values only
if using dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL or
AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM
removed clocks.num_levels from calculation of shim table size
removed unsafe accesses to shim table freq_values
output gfx_table values if using other dpm levels
added check for freq_match when using freq_values for when now == min_clk
Darren Powell [Sat, 30 Apr 2022 01:20:52 +0000 (21:20 -0400)]
amdgpu/pm: Fix incorrect variable for size of clocks array
[v2]
No Changes, added RB
[v1]
Size of pp_clock_levels_with_latency is PP_MAX_CLOCK_LEVELS, not MAX_NUM_CLOCKS.
Both are currently defined as 16, modifying in case one value is modified in future
Changed code in both arcturus and aldabaran.
Also removed unneeded var count, and used min_t function
Signed-off-by: Darren Powell <darren.powell@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Sat, 11 Jun 2022 00:15:29 +0000 (20:15 -0400)]
drm/amdkfd: Free queue after unmap queue success
After queue unmap or remove from MES successfully, free queue sysfs
entries, doorbell and remove from queue list. Otherwise, application may
destroy queue again, cause below kernel warning or crash backtrace.
For outstanding queues, either application forget to destroy or failed
to destroy, kfd_process_notifier_release will remove queue sysfs
entries, kfd_process_wq_release will free queue doorbell.
general protection fault, probably for non-canonical address
0xdead000000000108:
Call Trace:
pqm_destroy_queue+0xf0/0x200 [amdgpu]
kfd_ioctl_destroy_queue+0x2f/0x60 [amdgpu]
kfd_ioctl+0x19b/0x600 [amdgpu]
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Graham Sider <Graham.Sider@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Philip Yang [Wed, 15 Jun 2022 20:26:35 +0000 (16:26 -0400)]
drm/amdkfd: Add queue to MES if it becomes active
We remove the user queue from MES scheduler to update queue properties.
If the queue becomes active after updating, add the user queue to MES
scheduler, to be able to handle command packet submission.
v2: don't break pqm_set_gws
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Graham Sider <Graham.Sider@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aurabindo Pillai [Tue, 21 Jun 2022 15:23:40 +0000 (11:23 -0400)]
drm/amd/display: fix incorrect comparison in DML
[Why&How]
GCC 12 catches the following incorrect comparison in the if arm
drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c: In function ‘dml32_ModeSupportAndSystemConfigurationFull’:
drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c:3740:33: error: the comparison will always evaluate as ‘true’ for the address of ‘USRRetrainingSupport’ will never be NULL [-Werror=address]
3740 | || &mode_lib->vba.USRRetrainingSupport[i][j])) {
| ^~
In file included from ./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/display_mode_lib.h:32,
from ./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dc.h:45,
from drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c:30:
./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/display_mode_vba.h:1175:14: note: ‘USRRetrainingSupport’ declared here
1175 | bool USRRetrainingSupport[DC__VOLTAGE_STATES][2];
|
Fix this by remove preceding & so that value is compared instead of
address
Fixes: dda4fb85e433 ("drm/amd/display: DML changes for DCN32/321") Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aurabindo Pillai [Tue, 21 Jun 2022 15:23:39 +0000 (11:23 -0400)]
drm/amd/display: fix array index in DML
[Why&How]
When the a 3d array is used by indexing with only one dimension in an if
condition, the addresses get compared instead of the intended value stored in the
array. GCC 12.1 caught this error:
drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c: In function ‘DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation’:
drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c:1007:45: error: the comparison will always evaluate as ‘true’ for the address of ‘use_one_row_for_frame_flip’ will never be NULL [-Werror=address]
1007 | if (v->use_one_row_for_frame_flip[k]) {
| ^
In file included from ./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/display_mode_lib.h:32,
from ./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dc.h:45,
from drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/dcn32/display_mode_vba_32.c:30:
./drivers/gpu/drm/amd/amdgpu/../dal-dev/dc/dml/display_mode_vba.h:605:14: note: ‘use_one_row_for_frame_flip’ declared here
605 | bool use_one_row_for_frame_flip[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX];
|
Fix this by explicitly specifying the last two indices.
Fixes: dda4fb85e433 ("drm/amd/display: DML changes for DCN32/321") Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jiang Jian [Tue, 21 Jun 2022 13:10:41 +0000 (21:10 +0800)]
drm/amdgpu: vm - drop unexpected word "the" in the comments
there is an unexpected word "the" in the comments that need to be dropped
file: drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
line: 57
* the kernel tells the the ring what VMID to use for that command
changed to
* the kernel tells the ring what VMID to use for that command
Signed-off-by: Jiang Jian <jiangjian@cdjrlc.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Joshua Ashton [Thu, 16 Jun 2022 01:21:27 +0000 (01:21 +0000)]
amd/display/dc: Fix COLOR_ENCODING and COLOR_RANGE doing nothing for DCN20+
For DCN20 and above, the code that actually hooks up the provided
input_color_space got lost at some point.
Fixes COLOR_ENCODING and COLOR_RANGE doing nothing on DCN20+.
Tested using Steam Remote Play Together + gamescope.
Update other DCNs the same wasy DCN1.x was updates in
commit a1e07ba89d49 ("drm/amd/display: Use plane->color_space for dpp if specified")
Fixes: a1e07ba89d49 ("drm/amd/display: Use plane->color_space for dpp if specified") Signed-off-by: Joshua Ashton <joshua@froggi.es> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rodrigo Siqueira [Tue, 14 Jun 2022 14:11:47 +0000 (10:11 -0400)]
drm/amd/display: Update hook dcn32_funcs
In DCN32 clk hook functions, we are using the wrong reference for
get_dp_ref_clk_frequency and missing the get_dtb_ref_clk_frequency
reference. This commit adds those references.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Implement a pme workaround function
[Why]
For DCN32 we do not have a pme workaround function defined that sends a
BacoAudio message. Default code had uses the DCN30 function for pme
workaround. PMFW headers are inconsistent with their message ID
definitions which cause ID's to clash leading to inconsistent system
behaviour. There is a clash with FCLK message due to inconsitent PMFW
headers.
[How]
Implement a new BacoAudio function to workaround the problem of
inconsistent PMFW headers in order to avoid BacoAudio message clasing
with FCLK Enable message.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Chaitanya Dhere <chaitanya.dhere@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
George Shen [Fri, 20 May 2022 15:55:10 +0000 (11:55 -0400)]
drm/amd/display: Fix divide-by-zero in DPPCLK and DISPCLK calculation
[Why]
Certain use cases will pass in zero in the new_clocks parameter for all
clocks. This results in a divide-by-zero error when attempting to round
up the new clock.
When new_clocks are zero, no rounding is required, so we can skip it.
[How]
Guard the division calculation with a check to make sure clocks are not
zero.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: George Shen <george.shen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Description]
- When lowering DPPCLK, we want to program the DPP DTO before updating
the DPP refclk.
- Also update DPPCLK to the exact frequency that will be set after clock
divider has been programmed. This will prevent rounding errors when
making the request to PMFW (we need DPP DTO to match exactly with the
exact DPP refclk).
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rodrigo Siqueira [Tue, 14 Jun 2022 13:04:53 +0000 (09:04 -0400)]
drm/amd/display: Check minimum disp_clk and dpp_clk debug option
Our debug struct has the min_disp_clk_khz and min_dpp_clk_khz options,
which we ignore in the DCN32. This commit introduces those checks and
the necessary calculation.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Aurabindo Jayamohanan Pillai <Aurabindo.Pillai@amd.com> Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Fix in dp link-training when updating payload allocation table
[Why & How]
Check if aux is not accessible before updating payload allocation table.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Wenjing Liu [Fri, 25 Mar 2022 20:12:14 +0000 (16:12 -0400)]
drm/amd/display: extract update stream allocation to link_hwss
[Why & How]
Extract update stream allocation table into link hwss as part of the
link hwss refactor work.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: George Shen <George.Shen@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Wenjing Liu <wenjing.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
George Shen [Fri, 11 Feb 2022 19:13:01 +0000 (14:13 -0500)]
drm/amd/display: Remove unused vendor specific w/a
[Why & How]
Old vendor specific w/a are no longer needed and unused. Clean up
codebase by removing them.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: George Shen <george.shen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
George Shen [Mon, 31 Jan 2022 19:31:14 +0000 (14:31 -0500)]
drm/amd/display: Handle downstream LTTPR with fixed VS sequence
[Why]
Several issues were discovered that caused link
training to fail when an LTTPR device is
connected downstream for the fixed VS sequence.
[How]
The following were added:
- workaround to configure AUX timeout
for fixed VS sequence
- additional delay before disabling
fixed VS intercept
- detection of fixed VS deadlock state and
performing DPCD sequence to recover
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Meenakshikumar Somasundaram <Meenakshikumar.Somasundaram@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: George Shen <George.Shen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
George Shen [Thu, 7 Oct 2021 19:59:44 +0000 (15:59 -0400)]
drm/amd/display: Fix typo in override_lane_settings
[Why]
The function currently skips overriding the drive
settings of the first lane.
[How]
Change for loop to start at 0 instead of 1.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: George Shen <george.shen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aric Cyr [Sat, 2 Oct 2021 13:44:08 +0000 (09:44 -0400)]
drm/amd/display: Change initializer to single brace
[Why & How]
Change struct initializer from multiple brace to single brace.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Aric Cyr <aric.cyr@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Wenjing Liu [Sun, 12 Sep 2021 03:06:31 +0000 (23:06 -0400)]
drm/amd/display: rename lane_settings to hw_lane_settings
[why]
This is one of the major steps to decouple hw lane settings
from dpcd lane settings.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Wenjing Liu <wenjing.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
George Shen [Wed, 6 Oct 2021 19:47:37 +0000 (15:47 -0400)]
drm/amd/display: Fix in overriding DP drive settings
[Why & How]
Check always_match_dpcd_with_hw_lane_settings bit before
overriding the DP drive settings
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: George Shen <george.shen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Wenjing Liu [Tue, 6 Oct 2020 20:22:40 +0000 (16:22 -0400)]
drm/amd/display: Enrich the log in MST payload update
[Why & How]
Enrich the log to provide more informatio in MST payload update.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Ariel Bernstein <Eric.Bernstein@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: Wenjing Liu <wenjing.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why & How]
Use dc_is_hdmi_signal to determine signal type.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Acked-by: Alan Liu <HaoPing.Liu@amd.com> Signed-off-by: JinZe.Xu <JinZe.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Saaem Rizvi [Thu, 9 Jun 2022 19:34:43 +0000 (15:34 -0400)]
drm/amd/display: Add SMU logging code
[WHY]
Logging for SMU response value after the wait allows us to know
immediately what the response value was. Makes it easier to debug should
the value be anything other than OK.
[HOW]
Using the the already available DC SMU logging functions.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Charlene Liu <Charlene.Liu@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Saaem Rizvi <SyedSaaem.Rizvi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Sung Joon Kim [Tue, 7 Jun 2022 15:36:29 +0000 (11:36 -0400)]
drm/amd/display: Fix eDP not light up on resume
[why]
Only on VG, if external display is disconnected during S3 suspend, the
internal panel doesn't light up on resume because we set the power state
using an unsupported DPCD register SET_POWER. To check the register is
supported, we need to check SET_POWER_CAPABLE first which is
eDP-specific DPCD register field.
[how]
Check the SET_POWER_CAPABLE register field and decide the control of the
eDP power state based on the read register value.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Agustin Gutierrez <Agustin.Gutierrez@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Sung Joon Kim <sungkim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
hersen wu [Sun, 29 May 2022 16:12:32 +0000 (12:12 -0400)]
drm/amd/display: add mst port output bw check
[Why]
when connect one 4k@144hz dp to dsc mst hub, 4k@144hz mode is in valid
mode list. but some mst hub port output bandwidth does not support
4k@144hz.
[How]
add mst port output bandwidth checks, include full_pbn, branch max
throughput mps.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Jerry Zuo <Jerry.Zuo@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: hersen wu <hersenxs.wu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Ian Chen [Mon, 16 May 2022 07:35:34 +0000 (15:35 +0800)]
drm/amd/display: Drop unnecessary detect link code
Delete unnecessary codes in detect_link_and_local_sink. We already have
correct stop logic in dc_link_detect.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com> Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by: Ian Chen <ian.chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
projects / mirror_ubuntu-kernels.git / log