aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2022-08-16drm/amdgpu: disable 3DCGCG/CGLS temporarily due to stability issueEvan Quan1-0/+2
Some stability issues were reported with these features. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: double free error and freeing uninitialized null pointerSebin Sebastian1-2/+3
Fix a double free and an uninitialized pointer read error. Both tmp and new are pointing at same address and both are freed which leads to double free. Adding a check to verify if new and tmp are free in the error_free label fixes the double free issue. new is not initialized to null which also leads to a free on an uninitialized pointer. Reviewed-by: André Almeida <[email protected]> Suggested by: S. Amaranath <[email protected]> Signed-off-by: Sebin Sebastian <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Only disable prefer_shadow on hawaiiAlex Deucher5-10/+9
We changed it for all asics due to a hibernation regression on hawaii, but the workaround breaks suspend on a polaris12. Just disable it for hawaii. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216119 Fixes: 3a4b1cc28fbd ("drm/amdgpu/display: disable prefer_shadow for generic fb helpers") Reviewed-and-tested-by: Mario Limonciello <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2022-08-10drm/amdgpu: add GFX Power Gating support for GC IP v11.0.1Tim Huang1-0/+1
Add AMD_PG_SUPPORT_GFX_PG support. Signed-off-by: Tim Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: enable GFX Power Gating for GC IP v11.0.1Tim Huang1-0/+38
Enable GFX Power Gating control for GC IP v11.0.1. Signed-off-by: Tim Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Avoid direct cast to amdgpu_ttm_ttRajneesh Bhardwaj1-16/+18
For typesafety, use container_of() instead of implicit cast from struct ttm_tt to struct amdgpu_ttm_tt. Reviewed-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Enable translate_further to extend UTCL2 reachJoseph Greathouse1-0/+3
Enable translate_further on Arcturus and Aldebaran server chips in order to increase the UTCL2 reach from 8 GiB to 64 GiB, which is more in line with the amount of framebuffer DRAM in the devices. Signed-off-by: Joseph Greathouse <[email protected]> Acked-by: Felix Kuehling <[email protected]> Acked-by: Kent Russell <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: enable GFX Clock Gating control for GC IP v11.0.1Tim Huang1-0/+1
Enable GFX CG gate/ungate control. Signed-off-by: Tim Huang <[email protected]> Reviewed-by: Yifan Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: add GFX Clock Gating support for GC IP v11.0.1Tim Huang1-0/+6
Add below GFX Clock Gating supports: 1. GFX Coarse Grain Clock Gating(CGCG) 2. GFX Coarse grain light sleep/deep sleep(CGLS) 3. GFX Medium Grain Clock Gating(MGCG) 4. GFX Fine Grain Clock Gating(FGCG) 5. Repeater Fine Grain Clock Gating 6. Perfmon Clock Gating Signed-off-by: Tim Huang <[email protected]> Reviewed-by: Yifan Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Remove redundant reference of header fileMa Jun1-1/+0
Remove redundant reference of header file dev_printk.h Signed-off-by: Ma Jun <[email protected]> Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Avoid another list of reset devicesLijo Lazar3-31/+17
A list of devices to be reset is already created in amdgpu_device_gpu_recover function. Creating another list with the same nodes is incorrect and not supported in list_head. Instead, pass the device list as part of reset context. Fixes: 9e08564727fc (drm/amdgpu: Refactor mode2 reset logic for v13.0.2) Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: change vram width algorithm for vram_info v3_0Likun Gao1-1/+1
Update the vram width algorithm for vram_info v3_0 to align with the changes of latest IFWI. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 5.19.x
2022-08-10drm/amdgpu: Pessimistic availability based on rounded up allocationsDaniel Phillips2-3/+8
Separately accumulate a statistic of rounded up allocations to use to report availability, with a view to increasing the likelihood a buffer object can be successfully allocated at exactly the size reported by the availability API. Signed-off-by: Daniel Phillips <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-10drm/amdgpu: Remove rounding from vram allocation pathDaniel Phillips1-6/+5
Rounding up allocations in the allocation path caused test regressions, so now just round in the availability path. Signed-off-by: Daniel Phillips <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-04drm/amd/amdgpu: fix build failure due to implicit declarationSudip Mukherjee1-0/+1
The builds for alpha and mips allmodconfig fails with the error: drivers/gpu/drm/amd/amdgpu/psp_v13_0.c:534:23: error: implicit declaration of function 'vmalloc'; did you mean 'kvmalloc'? [-Werror=implicit-function-declaration] drivers/gpu/drm/amd/amdgpu/psp_v13_0.c:534:21: error: assignment to 'void *' from 'int' makes pointer from integer without a cast [-Werror=int-conversion] drivers/gpu/drm/amd/amdgpu/psp_v13_0.c:545:33: error: implicit declaration of function 'vfree'; did you mean 'kvfree'? [-Werror=implicit-function-declaration] Add the header file for vmalloc and vfree. Reported-by: Sudip Mukherjee <[email protected]> Suggested-by: Linus Torvalds <[email protected]> Signed-off-by: Sudip Mukherjee <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2022-07-29drm/amdgpu: enable support for psp 13.0.4 blockXiaojian Du4-2/+19
This patch will enable support for psp 13.0.4 blcok. Signed-off-by: Xiaojian Du <[email protected]> Reviewed-by: Tim Huang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-29drm/amdgpu: add files for PSP 13.0.4Xiaojian Du2-0/+417
This patch will add files for PSP 13.0.4. Signed-off-by: Xiaojian Du <[email protected]> Reviewed-by: Tim Huang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-29drm/amdgpu: correct RLC_RLCS_BOOTLOAD_STATUS offset and indexYifan Zhang1-1/+9
This patch corrects RLC_RLCS_BOOTLOAD_STATUS offset and index for GC 11.0.1. Signed-off-by: Yifan Zhang <[email protected]> Reviewed-by: Tim Huang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: fix hive reference leak when reflecting psp topology infoJonathan Kim1-0/+2
Hives that require psp topology info to be reflected will leak hive reference so fix it. Signed-off-by: Jonathan Kim <[email protected]> Reviewed-by: Shaoyun Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: move mes self test after drm sched re-startedJack Xiao3-2/+7
mes self test rely on vm mapping, move it after drm sched re-started so that vm mapping can work during gpu reset. Signed-off-by: Jack Xiao <[email protected]> Acked-and-tested-by: Evan Quan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: drop non-necessary call trace dumpEvan Quan1-1/+0
This extra call trace dump comes out in every gpu reset. And it gives people a wrong impression that something went wrong. Although actually there was not. Signed-off-by: Evan Quan <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: enable VCN cg and JPEG cg/pgSonny Jiang1-2/+5
Not enable VCN pg because encode issue Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: vcn_4_0_2 video codec querySonny Jiang1-0/+1
Enable support for vcn_4_0_2 video codec Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: add VCN_4_0_2 firmware supportSonny Jiang1-0/+8
Add VCN_4_0_2 firmware support Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: add VCN function in NBIO v7.7Sonny Jiang1-0/+21
Add function to support VCN_4_0_2 doorbell Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: fix a vcn4 boot poll bug in emulation modeSonny Jiang1-0/+1
The return value should be set in vcn4 boot poll. Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amd/amdgpu: add memory training support for PSP_V13Chengming Gui1-0/+159
Add PSP_V13 memory training support funcs. v2: replace DRM_{DEBUG/ERROR} with dev_{dbg/err}. (Hawking) v3: fix checkpatch error (Alex) Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdkfd: remove an unnecessary amdgpu_bo_refLang Yu1-1/+0
No need to reference the BO here, dmabuf framework will handle that. Signed-off-by: Lang Yu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amd/amdgpu: add additional page fault settings for gfx11Chengming Gui1-4/+28
Add three additional page fault settings. V2: move reg offset definition to header file. (Alex) V3: add all shift/mask definitions of used reg. (Hawking) Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: fix i2s_pdata out of bound array accessVijendar Mukunda1-8/+0
Fixed following Smatch static checker warning: drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c:393 acp_hw_init() error: buffer overflow 'i2s_pdata' 3 <= 3 drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c:396 acp_hw_init() error: buffer overflow 'i2s_pdata' 3 <= 3 Fixes: 4c33e5179ff1 ("drm/amdgpu: create I2S platform devices for Jadeite platform") Reported-by: Dan Carpenter <[email protected]> Signed-off-by: Vijendar Mukunda <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdkfd: fix kgd_mem memory leak when importing dmabufLang Yu1-0/+8
The kgd_mem memory allocated in amdgpu_amdkfd_gpuvm_import_dmabuf() is not freed properly. Explicitly free it in amdgpu_amdkfd_gpuvm_free_memory_of_gpu() under condition "mem->bo->kfd_bo != mem". Suggested-by: Felix Kuehling <[email protected]> Signed-off-by: Lang Yu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: add debugfs for kfd system and ttm mem usedAlex Sierra2-0/+22
This keeps track of kfd system mem used and kfd ttm mem used. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Philip Yang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdkfd: track unified memory reservation with xnack offAlex Sierra2-9/+18
[WHY] Unified memory with xnack off should be tracked, as userptr mappings and legacy allocations do. To avoid oversuscribe system memory when xnack off. [How] Exposing functions reserve_mem_limit and unreserve_mem_limit to SVM API and call them on every prange creation and free. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: Allow TTM to evict svm bo from same processPhilip Yang1-3/+6
To support SVM range VRAM overcommitment, TTM should be able to evict svm bo of same process to system memory, to get space to alloc new svm bo. Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: Fix the incomplete product numberRoy Sun1-1/+1
The comments say that the product number is a 16-digit HEX string so the buffer needs to be at least 17 characters to hold the NUL terminator. Expand the buffer size to 20 to avoid the alignment issues. The comment:Product number should only be 16 characters. Any more,and something could be wrong. Cap it at 16 to be safe Signed-off-by: Roy Sun <[email protected]> Reviewed-by: André Almeida <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-28drm/amdgpu: use adev_to_drm for consistencyGuchun Chen1-1/+1
Keep code consistency when accessing drm_device from amdgpu driver. Signed-off-by: Guchun Chen <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-27Merge tag 'amd-drm-next-5.20-2022-07-26' of ↵Dave Airlie38-354/+1180
https://gitlab.freedesktop.org/agd5f/linux into drm-next amdgpu: - VCN4 fixes - RAS support for UMC 8.10 - ACP support for jadeite platforms - NBIO HDP flush fixes - Misc spelling and grammar fixes - Runtime PM fixes - Non-DC HPD fix - Clean up amdgpu DM code - DSC fixes - Expose some additional GFXOFF data via debugfs - More FP clean up for new DCN blocks - PPC DC FP fixes - DCN 3.1.4 fixes - DC DML stack usage fixes - GMC fixes - SPM fixes for RDNA2 amdkfd: - MMU notifier fix - Mutex fix UAPI: - Add a comment about VCN4 unified queues - IP version information for UMDs Proposed mesa change: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17411/diffs?commit_id=c8a63590dfd0d64e6e6a634dcfed993f135dd075 Signed-off-by: Dave Airlie <[email protected]> From: Alex Deucher <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2022-07-25drm/amdgpu: enable swiotlb for gmc 11.0Aaron Liu1-0/+5
Enable swiotlb for gmc 11.0. Signed-off-by: Aaron Liu <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: enable swiotlb for gmc 10.0 (V2)Aaron Liu1-0/+5
Enable swiotlb for gmc 10.0. v2: include drm_cache.h to use the function ‘drm_need_swiotlb’ Signed-off-by: Aaron Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amd: Fix typo 'the the' in commentSlark Xiao1-1/+1
Replace 'the the' with 'the' in the comment. Signed-off-by: Slark Xiao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: Refactor code to handle non coherent and uncachedRajneesh Bhardwaj1-27/+24
This simplifies existing coherence handling for Arcturus and Aldabaran to account for !coherent && uncached scenarios. Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amd/amdgpu: add TAP_DELAYS upload support for gfx10Chengming Gui6-1/+129
Support {GLOBAL/SE0/SE1/SE2/SE3}_TAP_DELAYS uploading. v2: upload TAP_DELAYS before RLC autoload was triggered. (Hawking) Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amd/display: Add visualconfirm module parameterLeo Li2-0/+5
[Why] Being able to configure visual confirm at boot or in cmdline is helpful when debugging. [How] Add a module parameter to configure DC visual confirm, which works the same way as the equivalent debugfs entry. Signed-off-by: Leo Li <[email protected]> Reviewed-by: Rodrigo Siqueira <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: bump driver version for IP discovery info in HW INFOAlex Deucher1-2/+3
So userspace knows when it is available. Proposed mesa patch: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17411/diffs?commit_id=c8a63590dfd0d64e6e6a634dcfed993f135dd075 Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: add the IP discovery IP versions for HW INFO dataAlex Deucher1-0/+24
Use the former pad element to store the IP versions from the IP discovery table. This allows userspace to get the IP version from the kernel to better align with hardware IP versions. Proposed mesa patch: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17411/diffs?commit_id=c8a63590dfd0d64e6e6a634dcfed993f135dd075 Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: Fix comment typoJason Wang1-1/+1
The double `to' is duplicated in the comment, remove one. Reviewed-by: Christian König <[email protected]> Signed-off-by: Jason Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amdgpu: add dm ip block for dcn 3.1.4Roman Li1-0/+1
Adding dm ip block to enable display on dcn 3.1.4. Signed-off-by: Roman Li <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-25drm/amd/debugfs: Expose GFXOFF state to userspaceAndré Almeida1-2/+47
GFXOFF has two different "state" values: one to define if the GPU is allowed/disallowed to enter GFXOFF, usually called state; and another one to define if currently GFXOFF is being used, usually called status. Even when GFXOFF is allowed, GPU firmware can decide to not used it accordingly to the GPU load. Userspace can allow/disallow GPUs to enter into GFXOFF via debugfs. The kernel maintains a counter of requests for GFXOFF (gfx_off_req_count) that should be decreased to allow GFXOFF and increased to disallow. The issue with this interface is that userspace can't be sure if GFXOFF is currently allowed. Even by checking amdgpu_gfxoff file, one might get an ambiguous 2, that means that GPU is currently out of GFXOFF, but that can be either because it's currently disallowed or because it's allowed but given the current GPU load it's enabled. Then, userspace needs to rely on the fact that GFXOFF is enabled by default on boot and to track this information. To make userspace life easier and GFXOFF more reliable, return the current state of GFXOFF to userspace when reading amdgpu_gfxoff with the same semantics of writing: 0 means not allowed, not 0 means allowed. Expose the current status of GFXOFF through a new file, amdgpu_gfxoff_status. Signed-off-by: André Almeida <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-07-22Merge tag 'drm-misc-next-fixes-2022-07-21' of ↵Dave Airlie2-9/+9
git://anongit.freedesktop.org/drm/drm-misc into drm-next Short summary of fixes pull: * amdgpu: Fix for drm buddy memory corruption * nouveau: PM fixes; DP fixes Signed-off-by: Dave Airlie <[email protected]> From: Thomas Zimmermann <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/Ytj65+PdAJs4jIEO@linux-uq9g
2022-07-20drm/amdgpu: Write masked value to control registerMaíra Canal2-2/+2
On the dce_v6_0 and dce_v8_0 hpd tear down callback, the tmp variable should be written into the control register instead of 0. Reviewed-by: André Almeida <[email protected]> Signed-off-by: Maíra Canal <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.