aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2021-10-04drm/amdgpu/gfxhub2.1: convert to IP version checkingAlex Deucher1-3/+3
Use IP versions rather than asic_type to differentiate IP version specific features. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: drive nav10 from the IP discovery tableAlex Deucher1-1/+0
Rather than hardcoding based on asic_type, use the IP discovery table to configure the driver. Only tested on Navi10 so far. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: Use IP discovery to drive setting IP blocks by defaultAlex Deucher1-2/+4
Drive the asic setup from the IP discovery table rather than hardcoded settings based on asic type. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/gmc10.0: convert to IP version checkingAlex Deucher1-61/+30
Use IP versions rather than asic_type to differentiate IP version specific features. v2: squash in gmc fixes v3: rebase Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: bind to any 0x1002 PCI diplay class deviceAlex Deucher1-0/+15
Bind to all 0x1002 GPU devices. For now we explicitly return -ENODEV for generic bindings. Remove this check once IP discovery based checking is in place. v2: rebase (Alex) Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: filter out radeon PCI device IDsAlex Deucher1-1/+637
Once we claim all 0x1002 PCI display class devices, we will need to filter out devices owned by radeon. v2: rename radeon id array to make it more clear that the devices are not supported by amdgpu. add r128, mach64 pci ids as well Acked-by: Christian König <[email protected]> (v1) Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/gfx10: convert to IP version checkingAlex Deucher1-190/+190
Use IP versions rather than asic_type to differentiate IP version specific features. v2: rebase, squash in navi10 fixes (Alex) Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/sdma5.2: convert to IP version checkingAlex Deucher1-24/+24
Use IP versions rather than asic_type to differentiate IP version specific features. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/sdma5.0: convert to IP version checkingAlex Deucher1-15/+15
Use IP versions rather than asic_type to differentiate IP version specific features. v2: rebase Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: add initial IP enumeration via IP discovery tableAlex Deucher2-0/+334
Add initial support for all navi based parts. v2: rebase Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/nv: export common IP functionsAlex Deucher2-1/+3
So they can be driven by IP dicovery table. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: add XGMI HWIPAlex Deucher2-0/+2
So we can track grab the appropriate XGMI info out of the IP discovery table. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: fill in IP versions from IP discovery tableAlex Deucher1-1/+2
Prerequisite for using IP versions in the driver rather than asic type. v2: Use IP_VERSION() macro instead of new function Reviewed-by: Christian König <[email protected]> (v1) Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: store HW IP versions in the driver structureAlex Deucher2-1/+4
So we can check the IP versions directly rather than using asic type. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: add debugfs access to the IP discovery tableAlex Deucher2-0/+6
Useful for debugging and new asic validation. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: move headless sku check into harvest functionAlex Deucher2-14/+7
Consolidate harvesting information. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: resolve RAS query bugJohn Clements1-0/+3
clear error count when persistant harvesting is not enabled Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04amd/amdkfd: add ras page retirement handling for sq/sdma (v3)Tao Zhou2-0/+15
In ras poison mode, page retirement will be handled by the irq handler of the module which consumes corrupted data. v2: rename ras_process_cb to ras_poison_consumption_handler. move the handler's implementation from ASIC specific file to common file. v3: call gpu reset for xGMI connected mode. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: force exit gfxoff on sdma resume for rmb s0ixPrike Liang1-0/+8
In the s2idle stress test sdma resume fail occasionally,in the failed case GPU is in the gfxoff state.This issue may introduce by firmware miss handle doorbell S/R and now temporary fix the issue by forcing exit gfxoff for sdma resume. Signed-off-by: Prike Liang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amd/display: add cyan_skillfish display supportZhan Liu2-0/+5
[Why] add display related cyan_skillfish files in. makefile controlled by CONFIG_DRM_AMD_DC_DCN201 flag. v2: squash in clang fixes from Harry, Nathan v3: squash in missing CONFIG_DRM_AMD_DC check (Alex) Signed-off-by: Charlene Liu <[email protected]> Signed-off-by: Zhan Liu <[email protected]> Reviewed-by: Charlene Liu <[email protected]> Acked-by: Jun Lei <[email protected]> Acked-by: Harry Wentland <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04Revert "drm/amd: cleanup: drm_modeset_lock_all() --> ↵Sean Paul1-14/+7
DRM_MODESET_LOCK_ALL_BEGIN()" This reverts commit 299f040e855b69c29522cde446777902381a07f5. This patchset breaks on intel platforms and was previously NACK'd by Ville. Cc: Ville Syrjälä <[email protected]> Cc: Fernando Ramos <[email protected]> Acked-by: Ville Syrjälä <[email protected]> Signed-off-by: Sean Paul <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2021-10-04treewide: Replace the use of mem_encrypt_active() with cc_platform_has()Tom Lendacky1-1/+3
Replace uses of mem_encrypt_active() with calls to cc_platform_has() with the CC_ATTR_MEM_ENCRYPT attribute. Remove the implementation of mem_encrypt_active() across all arches. For s390, since the default implementation of the cc_platform_has() matches the s390 implementation of mem_encrypt_active(), cc_platform_has() does not need to be implemented in s390 (the config option ARCH_HAS_CC_PLATFORM is not set). Signed-off-by: Tom Lendacky <[email protected]> Signed-off-by: Borislav Petkov <[email protected]> Link: https://lkml.kernel.org/r/[email protected]
2021-10-01drm/amd: cleanup: drm_modeset_lock_all() --> DRM_MODESET_LOCK_ALL_BEGIN()Fernando Ramos1-7/+14
As requested in Documentation/gpu/todo.rst, replace driver calls to drm_modeset_lock_all() with DRM_MODESET_LOCK_ALL_BEGIN() and DRM_MODESET_LOCK_ALL_END() Signed-off-by: Fernando Ramos <[email protected]> Signed-off-by: Sean Paul <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2021-09-29drm/amdgpu: Add a UAPI flag for hot plug/unplugAndrey Grodzovsky1-1/+2
To support libdrm tests. Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-29drm/amdgpu: drm/amdgpu: Handle IOMMU enabled caseAndrey Grodzovsky1-0/+2
Handle all DMA IOMMU group related dependencies before the group is removed and we try to access it after free. v2: Move the actul handling function to TTM Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-29drm/amd/amdgpu: Validate ip discovery blobErnst Sjöstrand1-0/+21
We use the number_instance index that we get from the fw discovery blob to index into an array for example. Update error messages (Alex) Signed-off-by: Ernst Sjöstrand <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-29drm/amdgpu: fix warning for overflow checkArnd Bergmann2-2/+2
The overflow check in amdgpu_bo_list_create() causes a warning with clang-14 on 64-bit architectures, since the limit can never be exceeded. drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c:74:18: error: result of comparison of constant 256204778801521549 with expression of type 'unsigned int' is always false [-Werror,-Wtautological-constant-out-of-range-compare] if (num_entries > (SIZE_MAX - sizeof(struct amdgpu_bo_list)) ~~~~~~~~~~~ ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The check remains useful for 32-bit architectures, so just avoid the warning by using size_t as the type for the count. Fixes: 920990cb080a ("drm/amdgpu: allocate the bo_list array after the list") Reviewed-by: Christian König <[email protected]> Signed-off-by: Arnd Bergmann <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-29drm/amdgpu: check tiling flags when creating FB on GFX8-Simon Ser1-0/+31
On GFX9+, format modifiers are always enabled and ensure the frame-buffers can be scanned out at ADDFB2 time. On GFX8-, format modifiers are not supported and no other check is performed. This means ADDFB2 IOCTLs will succeed even if the tiling isn't supported for scan-out, and will result in garbage displayed on screen [1]. Fix this by adding a check for tiling flags for GFX8 and older. The check is taken from radeonsi in Mesa (see how is_displayable is populated in gfx6_compute_surface). Changes in v2: use drm_WARN_ONCE instead of drm_WARN (Michel) [1]: https://github.com/swaywm/wlroots/issues/3185 Signed-off-by: Simon Ser <[email protected]> Acked-by: Michel Dänzer <[email protected]> Cc: Alex Deucher <[email protected]> Cc: Harry Wentland <[email protected]> Cc: Nicholas Kazlauskas <[email protected]> Cc: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-29drm/ttm: s/FLAG_SG/FLAG_EXTERNAL/Matthew Auld1-5/+5
It covers more than just ttm_bo_type_sg usage, like with say dma-buf, since one other user is userptr in amdgpu, and in the future we might have some more. Hence EXTERNAL is likely a more suitable name. v2(Christian): - Rename these to TTM_TT_FLAGS_* - Fix up all the holes in the flag values Suggested-by: Christian König <[email protected]> Signed-off-by: Matthew Auld <[email protected]> Cc: Thomas Hellström <[email protected]> Cc: Christian König <[email protected]> Acked-by: Christian König <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Signed-off-by: Christian König <[email protected]>
2021-09-29drm/ttm: move ttm_tt_{add, clear}_mapping into amdgpuMatthew Auld1-1/+14
Now that setting page->index shouldn't be needed anymore, we are just left with setting page->mapping, and here it looks like amdgpu is the only user, where pointing the page->mapping at the dev_mapping is used to verify that the pages do indeed belong to the device, if userspace later tries to touch them. v2(Christian): - Drop the functions altogether and just inline modifying the page->mapping Signed-off-by: Matthew Auld <[email protected]> Cc: Thomas Hellström <[email protected]> Cc: Christian König <[email protected]> Reviewed-by: Christian König <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Signed-off-by: Christian König <[email protected]>
2021-09-28drm/amdgpu: force exit gfxoff on sdma resume for rmb s0ixPrike Liang1-0/+8
In the s2idle stress test sdma resume fail occasionally,in the failed case GPU is in the gfxoff state.This issue may introduce by firmware miss handle doorbell S/R and now temporary fix the issue by forcing exit gfxoff for sdma resume. Signed-off-by: Prike Liang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2021-09-28drm/amdgpu: check tiling flags when creating FB on GFX8-Simon Ser1-0/+31
On GFX9+, format modifiers are always enabled and ensure the frame-buffers can be scanned out at ADDFB2 time. On GFX8-, format modifiers are not supported and no other check is performed. This means ADDFB2 IOCTLs will succeed even if the tiling isn't supported for scan-out, and will result in garbage displayed on screen [1]. Fix this by adding a check for tiling flags for GFX8 and older. The check is taken from radeonsi in Mesa (see how is_displayable is populated in gfx6_compute_surface). Changes in v2: use drm_WARN_ONCE instead of drm_WARN (Michel) [1]: https://github.com/swaywm/wlroots/issues/3185 Signed-off-by: Simon Ser <[email protected]> Acked-by: Michel Dänzer <[email protected]> Cc: Alex Deucher <[email protected]> Cc: Harry Wentland <[email protected]> Cc: Nicholas Kazlauskas <[email protected]> Cc: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2021-09-28drm/amdgpu: correct initial cp_hqd_quantum for gfx9Hawking Zhang1-1/+1
didn't read the value of mmCP_HQD_QUANTUM from correct register offset Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Le Ma <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2021-09-28drm/amdgpu: fix gart.bo pin_count leakLeslie Shi2-2/+4
gmc_v{9,10}_0_gart_disable() isn't called matched with correspoding gart_enbale function in SRIOV case. This will lead to gart.bo pin_count leak on driver unload. Cc: Hawking Zhang <[email protected]> Signed-off-by: Leslie Shi <[email protected]> Signed-off-by: Guchun Chen <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: correct initial cp_hqd_quantum for gfx9Hawking Zhang1-1/+1
didn't read the value of mmCP_HQD_QUANTUM from correct register offset Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Le Ma <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: skip umc ras irq handling in poison mode (v2)Tao Zhou1-14/+20
In ras poison mode, umc uncorrectable error will be ignored until the corrupted data consumed by another ras module (such as gfx, sdma). v2: update the debug message and replace dev_warn with dev_info. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: set poison supported flag for RAS (v2)Tao Zhou3-4/+37
Add RAS poison supported flag and tell PSP RAS TA about the info. v2: rename poison mode to poison supported, we can also disable poison mode even we support it. print value of poison supported if ras feature enablement fails. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: add poison mode query for UMCTao Zhou2-0/+35
Add ras poison mode query interface for UMC. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: add poison mode query for DF (v2)Tao Zhou2-0/+32
Add ras poison mode query interface for DF. v2: replace RREG32_PCIE with RREG32_SOC15. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: Update PSP TA Invoke to use common TA context as inputCandice Li1-8/+8
Updated invoke to use new common TA structure similarily to load/unload. Signed-off-by: Candice Li <[email protected]> Reviewed-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28drm/amdgpu: fix gart.bo pin_count leakLeslie Shi2-2/+4
gmc_v{9,10}_0_gart_disable() isn't called matched with correspoding gart_enbale function in SRIOV case. This will lead to gart.bo pin_count leak on driver unload. Cc: Hawking Zhang <[email protected]> Signed-off-by: Leslie Shi <[email protected]> Signed-off-by: Guchun Chen <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-28Merge tag 'amd-drm-next-5.16-2021-09-27' of ↵Dave Airlie55-1094/+1281
https://gitlab.freedesktop.org/agd5f/linux into drm-next amd-drm-next-5.16-2021-09-27: amdgpu: - RAS improvements - BACO fixes - Yellow Carp updates - Misc code cleanups - Initial DP 2.0 support - VCN priority handling - Cyan Skillfish updates - Rework IB handling for multimedia engine tests - Backlight fixes - DCN 3.1 power saving improvements - Runtime PM fixes - Modifier support for DCC image stores for gfx 10.3 - Hotplug fixes - Clean up stack related warnings in display code - DP alt mode fixes - Display rework for better handling FP code - Debugfs fixes amdkfd: - SVM fixes - DMA map fixes radeon: - AGP fix From: Alex Deucher <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Signed-off-by: Dave Airlie <[email protected]>
2021-09-23drm/amdgpu: make soc15_common_ip_funcs staticAlex Deucher2-3/+3
It's not used outside of soc15.c Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Remove all code paths under the EAGAIN path in RAS late initCandice Li2-35/+1
All code paths under the EAGAIN path in RAS late init are unused. Signed-off-by: Candice Li <[email protected]> Reviewed-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Consolidate RAS cmd warning messagesJohn Clements2-26/+26
Explicity post warning if cmd is issued against unsupported IP Update to latest RAS TA interface Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Updated RAS infrastructureJohn Clements7-52/+146
Update RAS infrastructure to support RAS query for MCA subblocks Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: move amdgpu_virt_release_full_gpu to fini_early stageGuchun Chen1-4/+5
adev->rmmio is set to be NULL in amdgpu_device_unmap_mmio to prevent access after pci_remove, however, in SRIOV case, amdgpu_virt_release_full_gpu will still use adev->rmmio for access after amdgpu_device_unmap_mmio. The patch is to move such SRIOV calling earlier to fini_early stage. Fixes: 07775fc13878 ("drm/amdgpu: Unmap all MMIO mappings") Cc: Andrey Grodzovsky <[email protected]> Signed-off-by: Leslie Shi <[email protected]> Signed-off-by: Guchun Chen <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Fix resume failures when device is goneAndrey Grodzovsky1-0/+4
Problem: When device goes into suspend and unplugged during it then all HW programming during resume fails leading to a bad SW during pci remove handling which follows. Because device is first resumed and only later removed we cannot rely on drm_dev_enter/exit here. Fix: Use a flag we use for PCIe error recovery to avoid accessing registres. This allows to successfully complete pm resume sequence and finish pci remove. Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Fix MMIO access page faultAndrey Grodzovsky2-8/+17
Add more guards to MMIO access post device unbind/unplug Bug: https://bugs.archlinux.org/task/72092?project=1&order=dateopened&sort=desc&pagenum=1 Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-09-23drm/amdgpu: Fix crash on device remove/driver unloadAndrey Grodzovsky7-90/+105
Crash: BUG: unable to handle page fault for address: 00000000000010e1 RIP: 0010:vega10_power_gate_vce+0x26/0x50 [amdgpu] Call Trace: pp_set_powergating_by_smu+0x16a/0x2b0 [amdgpu] amdgpu_dpm_set_powergating_by_smu+0x92/0xf0 [amdgpu] amdgpu_dpm_enable_vce+0x2e/0xc0 [amdgpu] vce_v4_0_hw_fini+0x95/0xa0 [amdgpu] amdgpu_device_fini_hw+0x232/0x30d [amdgpu] amdgpu_driver_unload_kms+0x5c/0x80 [amdgpu] amdgpu_pci_remove+0x27/0x40 [amdgpu] pci_device_remove+0x3e/0xb0 device_release_driver_internal+0x103/0x1d0 device_release_driver+0x12/0x20 pci_stop_bus_device+0x79/0xa0 pci_stop_and_remove_bus_device_locked+0x1b/0x30 remove_store+0x7b/0x90 dev_attr_store+0x17/0x30 sysfs_kf_write+0x4b/0x60 kernfs_fop_write_iter+0x151/0x1e0 Why: VCE/UVD had dependency on SMC block for their suspend but SMC block is the first to do HW fini due to some constraints How: Since the original patch was dealing with suspend issues move the SMC block dependency back into suspend hooks as was done in V1 of the original patches. Keep flushing idle work both in suspend and HW fini seuqnces since it's essential in both cases. Fixes: 859e4659273f1d ("drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend") Fixes: bf756fb833cbe8 ("drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend") Signed-off-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.