- 15 Jan, 2024 2 commits
-
-
Alex Deucher authored
Hawaii, Bonaire, Fiji, and Tonga support average power, the others support current power. Reviewed-by:
Yang Wang <kevinyang.wang@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Dafna Hirschfeld authored
Fix err return value and reset pgmap->type after checking it. Fixes: c83dee9b ("drm/amdkfd: add SPM support for SVM") Reviewed-by:
Felix Kuehling <felix.kuehling@amd.com> Signed-off-by:
Dafna Hirschfeld <dhirschfeld@habana.ai> Signed-off-by:
-
- 09 Jan, 2024 19 commits
-
-
Melissa Wen authored
smatch warnings: amdgpu_dm_update_plane_color_mgmt() warn: inconsistent indenting Reported-by:
kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202401051643.PPdbmG1U-lkp@intel.com/Signed-off-by:
Melissa Wen <mwen@igalia.com> Reviewed-by:
Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Signed-off-by:
-
James Zhu authored
Use a generic comment for AMDGPU_VM_RESERVED_VRAM size. Signed-off-by:
James Zhu <James.Zhu@amd.com> Reviewed-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
-
Ivan Lipski authored
This commit causes dmesg-warn on several IGT tests on DCN 3.1.6: *ERROR* link_enc_cfg_validate: Invalid link encoder assignments - 0x1c Affected IGT tests include: - amdgpu/[amd_assr|amd_plane|amd_hotplug] - kms_atomic - kms_color - kms_flip - kms_properties - kms_universal_plane and some other tests This reverts commit 3a0fa3bc. Cc: Melissa Wen <mwen@igalia.com> Cc: Hamza Mahfooz <hamza.mahfooz@amd.com> Reviewed-by:
Ivan Lipski <ivlipski@amd.com> Signed-off-by:
-
Felix Kuehling authored
Properly mark kfd_process->ef as __rcu and consistently use the right accessor functions. Reported-by:
-
Philip Yang authored
====================================================== WARNING: possible circular locking dependency detected 6.5.0-kfd-yangp #2289 Not tainted ------------------------------------------------------ kworker/0:2/996 is trying to acquire lock: (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0 but task is already holding lock: ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at: process_one_work+0x211/0x560 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu] svm_range_set_attr+0xd6/0x14c0 [amdgpu] kfd_ioctl+0x1d1/0x630 [amdgpu] __x64_sys_ioctl+0x88/0xc0 -> #2 (&info->lock#2){+.+.}-{3:3}: __mutex_lock+0x99/0xc70 amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu] restore_process_helper+0x22/0x80 [amdgpu] restore_process_worker+0x2d/0xa0 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 -> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 __cancel_work_timer+0x12c/0x1c0 kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu] __mmu_notifier_release+0xad/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 do_exit+0x322/0xb90 do_group_exit+0x37/0xa0 __x64_sys_exit_group+0x18/0x20 do_syscall_64+0x38/0x80 -> #0 (srcu){.+.+}-{0:0}: __lock_acquire+0x1521/0x2510 lock_sync+0x5f/0x90 __synchronize_srcu+0x4f/0x1a0 __mmu_notifier_release+0x128/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 svm_range_deferred_list_work+0x19f/0x350 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 other info that might help us debug this: Chain exists of: srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&svms->deferred_list_work)); lock(&info->lock#2); lock((work_completion)(&svms->deferred_list_work)); sync(srcu); Signed-off-by:Philip Yang <Philip.Yang@amd.com> Reviewed-by:
-
Hawking Zhang authored
Initialize RAS feature mask bit[31:29] with socket_id. Signed-off-by:
Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by:
Tao Zhou <tao.zhou1@amd.com> Signed-off-by:
-
Candice Li authored
Support poison error injection. Signed-off-by:
Candice Li <candice.li@amd.com> Reviewed-by:
-
Likun Gao authored
Correct the algorithm of active CU to skip disabled sa for gfx v11. Signed-off-by:
Likun Gao <Likun.Gao@amd.com> Reviewed-by:
-
Candice Li authored
Remove "no user action is needed" for correctable and deferred error to avoid confusion. Signed-off-by:
-
Aric Cyr authored
This version brings along following fixes: - Improve z8/z10 support. - Revert some of the VRR optimization. - Improve usb4 when using MST. Acked-by:
Aric Cyr <aric.cyr@amd.com> Tested-by:
Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by:
-
Meenakshikumar Somasundaram authored
[Why] Dpia hpd status not in sync causing driver not enabling BW Alloc after S4. [How] Update hpd_status of the link when querying hpd state from dmub in dpia_query_hpd_status(). Reviewed-by:
Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Acked-by:
Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com> Tested-by:
-
Charlene Liu authored
Adjust z8 latency for performance. Reviewed-by:
Muhammad Ahmed <ahmed.ahmed@amd.com> Acked-by:
Charlene Liu <charlene.liu@amd.com> Tested-by:
-
Daniel Miess authored
This reverts commit d0f639c5. The previous commit causes failure to light up for 1080p eDP + 8k HDMI panel combo. Reviewed-by:
Daniel Miess <daniel.miess@amd.com> Tested-by:
-
Peichen Huang authored
[WHY] When usb4 bandwidth allocation mode is enabled, driver need to request bandwidth from connection manager. For mst link, the requested bandwidth should be big enough for all remote streams. [HOW] - If mst link, the requested bandwidth should be the sum of all mst streams bandwidth added with dp MTPH overhead. - Allocate/deallcate usb4 bandwidth when setting dpms on/off. - When doing display mode validation, driver also need to consider total bandwidth of all mst streams for mst link. Reviewed-by:
Cruise Hung <cruise.hung@amd.com> Acked-by:
Peichen Huang <peichen.huang@amd.com> Tested-by:
-
Martin Leung authored
This reverts commit 6e4337f6. The original commit causes regression in corner case with HDMI at specific timings. Reverting from staging to get the full suite to retest. Reviewed-by:
Martin Leung <martin.leung@amd.com> Tested-by:
-
Martin Leung authored
This reverts commit 6b2b782a. The original commit causes issues with certain features when DRR is disabled, need to revisit this change later after resolving issues with new DRR policy. Reviewed-by:
-
George Shen authored
[Why] If an OPP is used for a different OPTC without first being disconnected from the previous OPTC, unexpected behaviour can occur. This also applies to phantom pipes, which is what the current logic missed. [How] Disconnect OPPs from OPTC for phantom pipes before disabling OTG master. Also move the disconnection to before the OTG master disable, since the register is double buffered. Reviewed-by:
Dillon Varone <dillon.varone@amd.com> Acked-by:
George Shen <george.shen@amd.com> Tested-by:
-
Martin Tsai authored
[Why] Panels show corruption with high refresh rate timings when ssc is enabled. [How] Read down-spread percentage from lut to adjust dprefclk. Issues come from S0i3 with this commit has been fixed by SMU. Reviewed-by:
Martin Tsai <martin.tsai@amd.com> Tested-by:
-
Felix Kuehling authored
====================================================== WARNING: possible circular locking dependency detected 6.5.0-kfd-fkuehlin #276 Not tainted ------------------------------------------------------ kworker/8:2/2676 is trying to acquire lock: ffff9435aae95c88 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}, at: __flush_work+0x52/0x550 but task is already holding lock: ffff9435cd8e1720 (&svms->lock){+.+.}-{3:3}, at: svm_range_deferred_list_work+0xe8/0x340 [amdgpu] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&svms->lock){+.+.}-{3:3}: __mutex_lock+0x97/0xd30 kfd_ioctl_alloc_memory_of_gpu+0x6d/0x3c0 [amdgpu] kfd_ioctl+0x1b2/0x5d0 [amdgpu] __x64_sys_ioctl+0x86/0xc0 do_syscall_64+0x39/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #1 (&mm->mmap_lock){++++}-{3:3}: down_read+0x42/0x160 svm_range_evict_svm_bo_worker+0x8b/0x340 [amdgpu] process_one_work+0x27a/0x540 worker_thread+0x53/0x3e0 kthread+0xeb/0x120 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x11/0x20 -> #0 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}: __lock_acquire+0x1426/0x2200 lock_acquire+0xc1/0x2b0 __flush_work+0x80/0x550 __cancel_work_timer+0x109/0x190 svm_range_bo_release+0xdc/0x1c0 [amdgpu] svm_range_free+0x175/0x180 [amdgpu] svm_range_deferred_list_work+0x15d/0x340 [amdgpu] process_one_work+0x27a/0x540 worker_thread+0x53/0x3e0 kthread+0xeb/0x120 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x11/0x20 other info that might help us debug this: Chain exists of: (work_completion)(&svm_bo->eviction_work) --> &mm->mmap_lock --> &svms->lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&svms->lock); lock(&mm->mmap_lock); lock(&svms->lock); lock((work_completion)(&svm_bo->eviction_work)); I believe this cannot really lead to a deadlock in practice, because svm_range_evict_svm_bo_worker only takes the mmap_read_lock if the BO refcount is non-0. That means it's impossible that svm_range_bo_release is running concurrently. However, there is no good way to annotate this. To avoid the problem, take a BO reference in svm_range_schedule_evict_svm_bo instead of in the worker. That way it's impossible for a BO to get freed while eviction work is pending and the cancel_work_sync call in svm_range_bo_release can be eliminated. v2: Use svm_bo_ref_unless_zero and explained why that's safe. Also removed redundant checks that are already done in amdkfd_fence_enable_signaling. Signed-off-by:
-
- 08 Jan, 2024 1 commit
-
-
https://gitlab.freedesktop.org/agd5f/linuxDave Airlie authored
amd-drm-next-6.8-2024-01-05: amdgpu: - VRR fixes - PSR-SU fixes - SubVP fixes - DCN 3.5 fixes - Documentation updates - DMCUB fixes - DML2 fixes - UMC 12.0 updates - GPUVM fix - Misc code cleanups and whitespace cleanups - DP MST fix - Let KFD sync with GPUVM fences - GFX11 reset fix - SMU 13.0.6 fixes - VSC fix for DP/eDP - Navi12 display fix - RN/CZN system aperture fix - DCN 2.1 bandwidth validation fix - DCN INIT cleanup amdkfd: - SVM fixes - Revert TBA/TMA location change Signed-off-by:
Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240105220522.4976-1-alexander.deucher@amd.com
-
- 05 Jan, 2024 18 commits
-
-
Charlene Liu authored
Copy StutterPeriod from DML2 into DML1 StutterPeriod parameter. Tested-by:
-
Melissa Wen authored
IGT `amdgpu/amd_color/crtc-lut-accuracy` fails right at the beginning of the test execution, during atomic check, because DC rejects the bandwidth state for a fb sizing 64x64. The test was previously working with the deprecated dc_commit_state(). Now using dc_validate_with_context() approach, the atomic check needs to perform a full state validation. Therefore, set fast_validation to false in the dc_validate_global_state call for atomic check. Cc: stable@vger.kernel.org Fixes: b8272241 ("drm/amd/display: Drop dc_commit_state in favor of dc_commit_streams") Signed-off-by:
Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by:
-
Alex Deucher authored
These chips needs the same fix. This was previously not seen on then since the AGP aperture expanded the system aperture, but this showed up again when AGP was disabled. Reviewed-and-tested-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Signed-off-by:
-
Harry Wentland authored
Other environments don't like the unary minus operator on an unsigned value. Signed-off-by:
Harry Wentland <harry.wentland@amd.com> Acked-by:
-
Harry Wentland authored
- Use tabs, not spaces. - Brace and parentheses placement Signed-off-by:
-
Kaibo Ma authored
That commit causes NULL pointer dereferences in dmesgs when running applications using ROCm, including clinfo, blender, and PyTorch, since v6.6.1. Revert it to fix blender again. This reverts commit 96c211f1. Closes: https://github.com/ROCm/ROCm/issues/2596 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2991Reviewed-by:
Jay Cornwall <jay.cornwall@amd.com> Signed-off-by:
Kaibo Ma <ent3rm4n@gmail.com> Signed-off-by:
-
Arnd Bergmann authored
gcc prints a warning about a possible array overflow for a couple of callers of dp_decide_lane_settings() after commit 1b56c90018f0 ("Makefile: Enable -Wstringop-overflow globally"): drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c: In function 'dp_perform_fixed_vs_pe_training_sequence_legacy': drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c:426:25: error: 'dp_decide_lane_settings' accessing 4 bytes in a region of size 1 [-Werror=stringop-overflow=] 426 | dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 427 | lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c:426:25: note: referencing argument 4 of type 'union dpcd_training_lane[4]' I'm not entirely sure what caused this, but changing the prototype to expect a pointer instead of an array avoids the warnings. Fixes: 7727e7b6 ("drm/amd/display: Improve robustness of FIXED_VS link training at DP1 rates") Acked-by:Randy Dunlap <rdunlap@infradead.org> Tested-by: Randy Dunlap <rdunlap@infradead.org> # build-tested Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Place define macro expression inside () in power_helpers.c file Signed-off-by:
Marcelo Mendes Spessoto Junior <marcelomspessoto@gmail.com> Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Place HDCP_EVENT_TRACE(hdcp, event) macro content inside do while loop to avoid if-else issues in hdcp_log.h file v2: fix up build (Alex) Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Remove braces for single statement if expressions and change comparison order for hdcp2_execution.c file Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Fix identation inside enum and place expressions in define macros inside () for hdcp_psp.h file Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Remove braces for single statement if expression for freesync.c file Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Fix identation for hdcp_psp.c file Signed-off-by:
-
Marcelo Mendes Spessoto Junior authored
Remove braces from single statement if expression in hdcp1_execution.c file Signed-off-by:
-
Zhipeng Lu authored
The hwmgr->backend, (i.e. data) allocated by kzalloc is not freed in the error-handling paths of smu7_get_evv_voltages and smu7_update_edc_leakage_table. However, it did be freed in the error-handling of phm_initializa_dynamic_state_adjustment_rule_settings, by smu7_hwmgr_backend_fini. So the lack of free in smu7_get_evv_voltages and smu7_update_edc_leakage_table is considered a memleak in this patch. Fixes: 599a7e9f ("drm/amd/powerplay: implement smu7 hwmgr to manager asics with smu ip version 7.") Fixes: 8f0804c6 ("drm/amd/pm: add edc leakage controller setting") Signed-off-by:
Zhipeng Lu <alexious@zju.edu.cn> Signed-off-by:
-
Srinivasan Shanmugam authored
Fix the following about iterator use: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1456 kfd_add_peer_prop() warn: iterator used outside loop: 'iolink3' Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by:
-
Srinivasan Shanmugam authored
Return value of container_of(...) can't be null, so null check is not required for 'fence'. Hence drop its NULL check. Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c:93 to_amdgpu_amdkfd_fence() warn: can 'fence' even be NULL? Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
-
Srinivasan Shanmugam authored
Before using list_first_entry, make sure to check that list is not empty, if list is empty return -ENODATA. Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1347 kfd_create_indirect_link_prop() warn: can 'gpu_link' even be NULL? drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1428 kfd_add_peer_prop() warn: can 'iolink1' even be NULL? drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1433 kfd_add_peer_prop() warn: can 'iolink2' even be NULL? Fixes: 0f28cca8 ("drm/amdkfd: Extend KFD device topology to surface peer-to-peer links") Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Lijo Lazar <lijo.lazar@amd.com> Reviewed-by:
-
