Amber Lin [Fri, 24 Sep 2021 16:15:48 +0000 (12:15 -0400)]
drm/amdkfd: Enable HW_UPDATE_RPTR on GC 9.4.3
GC 9.4.3 uses the hardware to update AQL queues read pointer, so
remove CP_HQD_PQ_CONTROL__NO_UPDATE_RPTR_MASK flag from MQD if it's
GC 9.4.3, and keep it for other existing gfx9 ASICs.
Signed-off-by: Amber Lin <Amber.Lin@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aaron Liu [Wed, 5 Apr 2023 11:22:20 +0000 (19:22 +0800)]
drm/amdgpu: skip kfd-iommu suspend/resume for S0ix
GFX is in gfxoff mode during s0ix so we shouldn't need to
actually execute kfd_iommu_suspend/kfd_iommu_resume operation.
Signed-off-by: Aaron Liu <aaron.liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
all the gc v9_4_3 registers fall in gc_rlcpdec address range
have different relative offsets and base_idx from the ones
defined in gc v9_0 ip headers. gc_v9_0_rlc_funcs can not be
reused anymore for gc v9_4_3
v2: drop unused handshake function (Alex)
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Le Ma <Le.Ma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shashank Sharma [Fri, 24 Feb 2023 20:27:57 +0000 (21:27 +0100)]
drm/amdgpu: include protection for doorbell.h
This patch adds double include protection for doorbell.h
Cc: Christian Koenig <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian Koenig <christian.koenig@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shashank Sharma [Fri, 24 Feb 2023 10:25:07 +0000 (11:25 +0100)]
drm/amdgpu: rename num_doorbells
Rename doorbell.num_doorbells to doorbell.num_kernel_doorbells to
make it more readable.
Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian Koenig <christian.koenig@amd.com> Acked-by: Christian Koenig <christian.koenig@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: switch to golden tsc registers for raven/raven2
Due to raven/raven2 maybe enable sclk slow down,
they cannot get clock count by the RLC at the auto level of dpm performance.
So switch to golden tsc register.
Suggested-by: shanshengwang <shansheng.wang@amd.com> Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Jesse Zhang <jesse.zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Fri, 7 Apr 2023 09:12:15 +0000 (17:12 +0800)]
drm/amd/pm: correct the pcie link state check for SMU13
Update the driver implementations to fit those data exposed
by PMFW.
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>
Rework retry fault removal from the software filter by
storing an expired timestamp for a fault that is being removed.
When a new fault comes, and it matches an entry in the sw filter,
it will be added as a new fault only when its timestamp is greater
than the timestamp expiry of the fault in the sw filter.
This helps in avoiding stale faults being added back into the
filter and preventing legitimate faults from being handled.
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch enables the IH retry CAM on GFX9 series cards. This
retry filter is used to prevent sending lots of retry interrupts
in a short span of time and overflowing the IH ring buffer. This
will also help reduce CPU interrupt workload.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
clang with W=1 reports
drivers/gpu/drm/amd/amdgpu/../pm/swsmu/amdgpu_smu.c:1700:6: error: variable
'num_of_active_display' set but not used [-Werror,-Wunused-but-set-variable]
int num_of_active_display = 0;
^
This variable is not used so remove it.
Fixes: 75145aab7a0d ("drm/amdgpu/swsmu: clean up a bunch of stale interfaces") Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 28 Mar 2023 00:09:08 +0000 (20:09 -0400)]
drm/amdgpu: simplify amdgpu_ras_eeprom.c
All chips that support RAS also support IP discovery, so
use the IP versions rather than a mix of IP versions and
asic types. Checking the validity of the atom_ctx pointer
is not required as the vbios is already fetched at this
point.
v2: add comments to id asic types based on feedback from Luben
Enable SDMA queue empty context switching. SDMA context switch due to
quantum programming no longer done here (as of sdma v6), so re-name
sdma_v6_0_ctx_switch_enable to sdma_v6_0_ctxempty_int_enable to reflect
this.
Also program SDMAx_QUEUEx_SCHEDULE_CNTL for context switch due to
quantum in KFD. Set to amdgpu_sdma_phase_quantum (defaults to 32 i.e.
3200us).
Signed-off-by: Graham Sider <Graham.Sider@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Stanley Yang <Stanley.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Sreekant Somasekharan [Mon, 13 Mar 2023 22:05:41 +0000 (18:05 -0400)]
drm/amdkfd: Check PCIe atomics support on GFX11 to set CP_HQD_HQ_STATUS0[29]
CP_HQD_HQ_STATUS0[29] bit will be used by CPFW to acknowledge whether
PCIe atomics are supported. The default value of this bit is set
to 0. Driver will check whether PCIe atomics are supported and set the
bit to 1 if supported. This will force CPFW to use real atomic ops.
If the bit is not set, CPFW will default to read/modify/write using the
firmware itself.
This is applicable only to GFX11 RS64 CP with MEC FW >= 509. If MEC
FW < 509 and for all GFX11 F32 CP, PCIe atomics needs to be supported
else it will skip the device.
This commit also involves moving amdgpu_amdkfd_device_probe() function
call after per-IP early_init loop in amdgpu_device_ip_early_init()
function so as to check for RS64 enabled device.
Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com> Reviewed-by: Graham Sider <Graham.Sider@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aldebaran supports VCN and JPEG RAS, it reports unexpected
block id message during VCN and JPEG RAS initialization if VCN
and JPEG block id not defined.
drm/amdgpu: use sdma_v6 single packet invalidation
This achieves the same result as the sequence used in emit_flush_gpu_tlb
but the invalidation is now a single packet instead of the 3 packets
required to implement reg_write_reg_wait.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display : Log DP link training downspread info
Update the existing log with DP LT downspread info:
[Downstream devices shall support down spreading of the link clock.
The down-spread amplitude shall either be disabled (0.0%) or up to 0.5%,
as written by the upstream device to the DOWNSPREAD_CTRL register
(DPCD 00107h). The modulation frequency range shall be 30 to 33 kHz]
Besides, fix checkpatch warning:
CHECK: Alignment should match open parenthesis
Cc: Mario Limonciello <mario.limonciello@amd.com> Cc: Harry Wentland <harry.wentland@amd.com> Cc: Leo Li <sunpeng.li@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
clang with W=1 reports
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_enc_cfg.c:625:6: error:
variable 'matching_stream_ptrs' set but not used [-Werror,-Wunused-but-set-variable]
int matching_stream_ptrs = 0;
^
This variable is not used so remove it.
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom Rix [Sat, 8 Apr 2023 13:43:48 +0000 (09:43 -0400)]
drm/amd/display: set variables dml*_funcs storage-class-specifier to static
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:44:24: warning: symbol
'dml20_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:51:24: warning: symbol
'dml20v2_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:58:24: warning: symbol
'dml21_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:65:24: warning: symbol
'dml30_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:72:24: warning: symbol
'dml31_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:79:24: warning: symbol
'dml314_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:86:24: warning: symbol
'dml32_funcs' was not declared. Should it be static?
These variables are only used in one file so should be static.
Cleanup whitespace, use tabs consistently for indents.
Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom Rix [Thu, 6 Apr 2023 19:58:18 +0000 (15:58 -0400)]
drm/amd/display: set variables aperture_default_system and context0_default_system storage-class-specifier to static
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:758:10: warning: symbol
'aperture_default_system' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:759:10: warning: symbol
'context0_default_system' was not declared. Should it be static?
These variables are only used in one file so should be static.
Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom Rix [Thu, 6 Apr 2023 18:44:34 +0000 (14:44 -0400)]
drm/amd/display: set variable dcn3_14_soc storage-class-specifier to static
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn314/dcn314_fpu.c:100:37: warning: symbol
'dcn3_14_soc' was not declared. Should it be static?
This variable is only used in one file so should be static.
Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
regGOLDEN_TSC_COUNT_LOWER/regGOLDEN_TSC_COUNT_UPPER are protected and
unaccessible under sriov.
The clock counter high bit may update during reading process.
[How]
Replace regGOLDEN_TSC_COUNT_LOWER/regGOLDEN_TSC_COUNT_UPPER with
regCP_MES_MTIME_LO/regCP_MES_MTIME_HI to get gpu clock under sriov.
Refine get gpu clock counter method to make the result more precise.
Guilherme G. Piccoli [Thu, 30 Mar 2023 14:40:45 +0000 (11:40 -0300)]
drm/amd/pm: Fix incorrect comment about Vangogh power cap support
The comment mentions that power1 cap attributes are not supported on
Vangogh, but the opposite is indeed valid: for APUs, only Vangogh is
supported. While at it, also fixed the Renoir comment below (thanks
Melissa for noticing that!).
Cc: Lijo Lazar <lijo.lazar@amd.com> Cc: Melissa Wen <mwen@igalia.com> Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add userptr bo support for mGPUs when iommu is on
For userptr bo with iommu on, multiple GPUs use same system
memory dma mapping address when both adev and bo_adev are in
identity mode or in the same iommu group.
If RAM direct map to one GPU, other GPUs can share the original
BO in order to reduce dma address array usage when RAM can
direct map to these GPUs. However, we should explicit check
whether RAM can direct map to all these GPUs.
This patch fixes a potential issue that where RAM is
direct mapped on some but not all GPUs.
v2:
1. Update comment
2. Add helper function reuse_dmamap
Signed-off-by: Shane Xiao <shane.xiao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The driver doesn't resubmit jobs on hangs any more, hence drop
the hang limit parameter - amdgpu_job_hang_limit, wherever it is used.
Suggested-by: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Mario Limonciello <mario.limonciello@amd.com> Cc: Kent Russell <kent.russell@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Igor Artemiev [Mon, 3 Apr 2023 13:10:37 +0000 (16:10 +0300)]
drm/amd/display: Fix potential null dereference
The adev->dm.dc pointer can be NULL and dereferenced in amdgpu_dm_fini()
without checking.
Add a NULL pointer check before calling dc_dmub_srv_destroy().
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: 9a71c7d31734 ("drm/amd/display: Register DMUB service with DC") Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Mario Limonciello [Thu, 23 Mar 2023 19:07:06 +0000 (14:07 -0500)]
drm/amd: Fix an out of bounds error in BIOS parser
The array is hardcoded to 8 in atomfirmware.h, but firmware provides
a bigger one sometimes. Deferencing the larger array causes an out
of bounds error.
commit 4fc1ba4aa589 ("drm/amd/display: fix array index out of bound error
in bios parser") fixed some of this, but there are two other cases
not covered by it. Fix those as well.
Anthony Koo [Sat, 25 Mar 2023 13:55:13 +0000 (09:55 -0400)]
drm/amd/display: [FW Promotion] Release 0.0.161.0
- Add command to idle opt.
- Rename d3 entry event and add idle trigger param on
notify event.
- Add bit to fw boot status to notify status when hardware
is powered up.
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by: Anthony Koo <Anthony.Koo@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michael Strauss [Fri, 24 Mar 2023 14:48:37 +0000 (10:48 -0400)]
drm/amd/display: Improve robustness of FIXED_VS link training at DP1 rates
[WHY]
New sequence for transparent mode DP1.x link training was provided by LTTPR
vendor
[HOW]
Implement new FIXED_VS sequence, increase LT retry count to minimize
any potential intermittent lightup failures
Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by: Michael Strauss <michael.strauss@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Charlene Liu [Fri, 24 Mar 2023 16:31:07 +0000 (12:31 -0400)]
drm/amd/display: add dscclk instance offset check
[why]
based on dscclk instance offset check conditiona program dscclk
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by: Charlene Liu <Charlene.Liu@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alvin Lee [Fri, 24 Mar 2023 16:01:09 +0000 (12:01 -0400)]
drm/amd/display: On clock init, maintain DISPCLK freq
[Description]
- On init if a display is connected, we need to maintain the DISPCLK
frequency
- Even though DPG_EN=1, the display still requires the correct
timing or it could cause audio corruption (if DISPCLK freq
is reduced)
- Read the current DISPCLK freq and request the same value to ensure
the timing is valid and unchanged
- However, add option to do a full pipe power down (including link)
which will also avoid audio related issues
- Disabled for the time being on dcn32
Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@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>
Alvin Lee [Thu, 23 Mar 2023 19:48:41 +0000 (15:48 -0400)]
drm/amd/display: Add FPO + VActive support
[Description]
- When determining FPO support, include FPO + VActive support
- Support FPO + VActive if one display meets regular requirements
for FPO and the second display is able to switch in VACTIVE with
a given amount of margin
Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@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>
Paul Hsieh [Wed, 22 Mar 2023 09:46:31 +0000 (17:46 +0800)]
drm/amd/display: Correct DML calculation to follow HW SPEC
[Why]
In 2560x1600@240p eDP panel, driver use lowest voltage level
to play 1080p video cause underflow. According to HW SPEC,
the senario should use high voltage level.
[How]
ChromaPre value is zero when bandwidth validation.
Correct ChromaPre calculation.
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com> Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by: Paul Hsieh <Paul.Hsieh@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Hamza Mahfooz [Tue, 21 Mar 2023 20:35:28 +0000 (16:35 -0400)]
drm/amd/display: prep work for root clock optimization enablement for DCN314
To enable root clock optimizations, we need a number of
register writes and need to account for the difference
in DPSTREAMCLK between DCN31 and DCN314. To prevent
issues, add a number of register writes to
DCCG_MASK_SH_LIST_DCN314_COMMON(), and define dccg314_init()
which is mostly in alignment with dccg31_init() but
accounts for the new DPSTREAMCLK sequence.
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Tested-by: Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alvin Lee [Tue, 21 Mar 2023 17:35:44 +0000 (13:35 -0400)]
drm/amd/display: Clear FAMS flag if FAMS doesn't reduce vlevel
[Description]
- If we find that applying FAMS doesn't reduce the voltage level,
we will not use it
- Ensure to clear the stream flags indicating FAMS if we hit this
case
Reviewed-by: Jun Lei <Jun.Lei@amd.com> Acked-by: Qingqing Zhuo <qingqing.zhuo@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>
Tom Rix [Fri, 31 Mar 2023 00:10:32 +0000 (20:10 -0400)]
drm/amd/display: remove unused average_render_time_in_us and i variables
clang with W=1 reports
drivers/gpu/drm/amd/amdgpu/../display/modules/freesync/freesync.c:1132:15: error: variable
'average_render_time_in_us' set but not used [-Werror,-Wunused-but-set-variable]
unsigned int average_render_time_in_us = 0;
^
This variable is not used so remove it, which caused i to be unused so remove that as well.
Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jack Xiao [Fri, 24 Mar 2023 08:55:15 +0000 (16:55 +0800)]
drm/amd/amdgpu: introduce gc_*_mes_2.bin v2
To avoid new mes fw running with old driver, rename
mes schq fw to gc_*_mes_2.bin.
v2: add MODULE_FIRMWARE declaration
v3: squash in fixup patch
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tim Huang [Thu, 30 Mar 2023 02:33:02 +0000 (10:33 +0800)]
drm/amdgpu: allow more APUs to do mode2 reset when go to S4
Skip mode2 reset only for IMU enabled APUs when do S4.
This patch is to fix the regression issue
https://gitlab.freedesktop.org/drm/amd/-/issues/2483
It is generated by commit b589626674de ("drm/amdgpu: skip ASIC reset
for APUs when go to S4").
Fixes: b589626674de ("drm/amdgpu: skip ASIC reset for APUs when go to S4") Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2483 Tested-by: Yuan Perry <Perry.Yuan@amd.com> Signed-off-by: Tim Huang <tim.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Daniel Vetter [Tue, 11 Apr 2023 10:28:09 +0000 (12:28 +0200)]
Merge tag 'mediatek-drm-next-6.4' of https://git.kernel.org/pub/scm/linux/kernel/git/chunkuang.hu/linux into drm-next
Mediatek DRM Next for Linux 6.4
1. Add support for 10-bit overlays
2. Add MediaTek SoC DRM (vdosys1) support for mt8195
3. Change mmsys compatible for mt8195 mediatek-drm
4. Only trigger DRM HPD events if bridge is attached
5. Change the aux retries times when receiving AUX_DEFER
Daniel Vetter [Tue, 11 Apr 2023 10:11:32 +0000 (12:11 +0200)]
Merge tag 'drm-msm-next-2023-04-10' of https://gitlab.freedesktop.org/drm/msm into drm-next
main pull request for v6.4
Core Display:
============
* Bugfixes for error handling during probe
* rework UBWC decoder programming
* prepare_commit cleanup
* bindings for SM8550 (MDSS, DPU), SM8450 (DP)
* timeout calculation fixup
* atomic: use drm_crtc_next_vblank_start() instead of our own
custom thing to calculate the start of next vblank
DP:
==
* interrupts cleanup
DPU:
===
* DSPP sub-block flush on sc7280
* support AR30 in addition to XR30 format
* Allow using REC_0 and REC_1 to handle wide (4k) RGB planes
* Split the HW catalog into individual per-SoC files
DSI:
===
* rework DSI instance ID detection on obscure platforms
GPU:
===
* uapi C++ compatibility fix
* a6xx: More robust gdsc reset
* a3xx and a4xx devfreq support
* update generated headers
* various cleanups and fixes
* GPU and GEM updates to avoid allocations which could trigger
reclaim (shrinker) in fence signaling path
* dma-fence deadline hint support and wait-boost
* a640 speedbin support
* a650 speedbin support
Conflicts in drivers/gpu/drm/msm/adreno/adreno_gpu.c:
Conflict between the 7fa5047a436b ("drm: Use of_property_present() for
testing DT property presence") and 9f251f934012 ("drm/msm/adreno: Use
OPP for every GPU generation"). The latter removed the of_ function
call outright, so I went with what's in the PR unchanged.
Daniel Vetter [Tue, 11 Apr 2023 10:02:38 +0000 (12:02 +0200)]
Merge tag 'drm-habanalabs-next-2023-04-10' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into drm-next
This tag contains additional habanalabs driver changes for v6.4:
- uAPI changes:
- Add a definition of a new Gaudi2 server type. This is used by userspace
to know what is the connectivity between the accelerators inside the
server
- New features and improvements:
- speedup h/w queues test in Gaudi2 to reduce device initialization times.
- Firmware related fixes:
- Fixes to the handshake protocol during f/w initialization.
- Sync f/w events interrupt in hard reset to avoid warning message.
- Improvements to extraction of the firmware version.
- Misc bug fixes and code cleanups. Notable fixes are:
- Multiple fixes for interrupt handling in Gaudi2.
- Unmap mapped memory in case TLB invalidation fails.
accel/habanalabs: add missing error flow in hl_sysfs_init()
hl_sysfs_fini() is called only if hl_sysfs_init() completes
successfully. Therefore if hl_sysfs_init() fails, need to remove any
sysfs group that was added until that point.
Moti Haimovski [Mon, 20 Mar 2023 20:59:11 +0000 (22:59 +0200)]
accel/habanalabs: speedup h/w queues test in Gaudi2
HW queues testing at driver load and after reset takes a substantial
amount of time.
This commit reduces the queues test time in Gaudi2 devices by running
all the tests in parallel instead of one after the other.
Time measurements on tests duration shows that the new method is almost
x100 faster than the serial approach.
Dani Liberman [Tue, 28 Mar 2023 17:41:35 +0000 (20:41 +0300)]
accel/habanalabs: fix handling of arc farm sei event
There is only single eq entry for arc farm sei event which aggregates
events from the four arc farms.
Fix the code to handle this event according to this behavior.
Ofir Bitton [Mon, 27 Mar 2023 10:40:56 +0000 (13:40 +0300)]
accel/habanalabs: remove Gaudi1 multi MSI code
Multi MSI interrupts aren't working in Gaudi1 and because of that,
we are only using a single MSI interrupt. Therefore, let's remove this
dead code in order to avoid confusion.
Koby Elbaz [Sun, 26 Mar 2023 15:22:57 +0000 (18:22 +0300)]
accel/habanalabs: don't wait for STS_OK after sending COMMS WFE
Sending COMMS_GOTO_WFE instructs the FW's CPU to halt (WFE state).
Once sent, FW's CPU isn't expected to continue communicating with LKD.
Therefore, the stage of waiting for COMMS_STS_OK should be skipped or
else waiting for COMMS_STS_OK will simply timeout, which will trigger
unexpected behavior.
Tal Cohen [Tue, 21 Mar 2023 08:59:28 +0000 (10:59 +0200)]
accel/habanalabs: sync f/w events interrupt in hard reset
Receiving events from FW, while the device is in hard reset, causes
a warning message in Driver log. The message may point to a
problem in the Driver or FW. But It also can appear as a result
of events that have been sent from FW just before the hard reset.
In order to avoid receiving events from FW while the device is in reset
and is already in 'disabled' mode, sync the f/w events interrupt right
before setting the device to 'disabled'.
Tomer Tayar [Sun, 26 Mar 2023 21:08:45 +0000 (00:08 +0300)]
accel/habanalabs: fix events mask of decoder abnormal interrupts
The decoder IRQ status register may have several set bits upon an
abnormal interrupt. Therefore, when setting the events mask, need to
check all bits and not using if-else.
Ofir Bitton [Wed, 15 Mar 2023 08:36:41 +0000 (10:36 +0200)]
accel/habanalabs: fix HBM MMU interrupt handling
Current mapping between HMMU event and HMMU block is wrong.
In addition the captured address in case of a page fault or
an access error is scrambled, Hence we must call the descramble
function.
Tal Cohen [Wed, 22 Mar 2023 09:20:05 +0000 (11:20 +0200)]
accel/habanalabs: send disable pci when compute ctx is active
Fix an issue in hard reset flow in which the driver didn't send a
disable pci message if there was an active compute context.
In hard reset, disable pci message should be sent no matter if
a compute context exists or not.
The disable pci message is sent in reset device. It informs the FW not
to raise more EQs. The Driver may ignore received EQs, when the device
is in disabled mode.
The duplication happens when hard reset is scheduled during compute
reset and also performs 'escalate_reset_flow'.
Koby Elbaz [Tue, 21 Mar 2023 14:03:07 +0000 (16:03 +0200)]
accel/habanalabs: change COMMS warning messages to error level
COMMS protocol is used for LKD <--> FW communication, and any
communication failure between the two might turn out to be
destructive, hence, it should be well emphasized.
Tal Cohen [Thu, 16 Mar 2023 15:30:46 +0000 (17:30 +0200)]
accel/habanalabs: print event type when device is disabled
When the device is in disabled state, the driver isn't suppose to
receive any events from FW. Printing the event type, as part of the
message that was already printed, shall help to get more info if this
unexpected message is received.
Koby Elbaz [Wed, 8 Mar 2023 15:53:39 +0000 (17:53 +0200)]
accel/habanalabs: unmap mapped memory when TLB inv fails
Once a memory mapping is added to the page tables, it's followed by
a TLB invalidation request which could potentially fail (HW failure).
Removing the mapping is simply a part of this failure handling routine.
TLB invalidation failure prints were updated to be more accurate.
Remove pci_clear_master to simplify the code,
the bus-mastering is also cleared in do_pci_disable_device,
like this:
./drivers/pci/pci.c:2197
static void do_pci_disable_device(struct pci_dev *dev)
{
u16 pci_command;
drm/msm/dpu: fetch DPU configuration from match data
In email discussion it was noted that there can be different SoC device
having slightly different SoC features, but sharing the same DPU hw
revision. Stop fetching catalog data using core_rev and use platform's
match data instead.
For sm8150+ the DPU_CTL_SPLIT_DISPLAY should be replaced with
DPU_CTL_ACTIVE_CFG support (which supports having a single CTL for both
interfaces in a split). Add comments where this conversion is required.
projects / users / dwmw2 / linux.git / log