amd-gfx  

Messages by Thread

• • [PATCH v3 04/14] drm/amdgpu: reserve SPM VMID on gfx7 Sunil Khatri
  • [PATCH v3 09/14] drm/amdgpu: reserve SPM VMID on gfx12 Sunil Khatri
  • [PATCH v3 08/14] drm/amdgpu: reserve SPM VMID on gfx11 Sunil Khatri
  • [PATCH v3 10/14] drm/amdgpu: use spm_vmid for the default RLC SPM VMID Sunil Khatri
  • [PATCH v3 12/14] drm/amdgpu: remove the unused ring parameter from update_spm_vmid() Sunil Khatri
  • [PATCH v3 07/14] drm/amdgpu: reserve SPM VMID on gfx10 Sunil Khatri
  • [PATCH v3 03/14] drm/amdgpu: use dedicated SPM VMID from the reserved path Sunil Khatri
  • [PATCH v3 14/14] drm/amdgpu: rename amdgpu_vmid_alloc/free_reserved to _spm Sunil Khatri
  • [PATCH v3 05/14] drm/amdgpu: reserve SPM VMID on gfx8 Sunil Khatri
  • [PATCH v3 02/14] drm/amdgpu: add spm_vmid and exclude it from the MES, KFD and kq pools Sunil Khatri
  • [PATCH v3 11/14] drm/amdgpu: remove the now-redundant runtime SPM VMID update Sunil Khatri
  • [PATCH v3 06/14] drm/amdgpu: reserve SPM VMID on gfx9 Sunil Khatri
  • [PATCH v3 13/14] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Sunil Khatri
  • Re: [PATCH v3 13/14] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Christian König
  • Re: [PATCH v3 13/14] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Khatri, Sunil
• [PATCH 1/9] drm/amdgpu: defer GPU recovery after userq eviction failure Prike Liang
  • [PATCH 2/9] drm/amdgpu: skip VKMS mode-config helpers during GPU reset Prike Liang
  • Re: [PATCH 2/9] drm/amdgpu: skip VKMS mode-config helpers during GPU reset Christian König
  • RE: [PATCH 2/9] drm/amdgpu: skip VKMS mode-config helpers during GPU reset Liang, Prike
  • Re: [PATCH 2/9] drm/amdgpu: skip VKMS mode-config helpers during GPU reset Christian König
  • [PATCH 3/9] drm/amdgpu: skip VMHUB fault handling while the device is inaccessible Prike Liang
  • [PATCH 6/9] drm/amdgpu: serialize JPEG and VCN idle work with GPU reset Prike Liang
  • Re: [PATCH 6/9] drm/amdgpu: serialize JPEG and VCN idle work with GPU reset Christian König
  • [PATCH 5/9] drm/amdgpu: finish GPU recovery callbacks before restarting schedulers Prike Liang
  • [PATCH 4/9] drm/amdgpu/userq: complete hung queue fences after successful removal Prike Liang
  • [PATCH 8/9] drm/amdgpu/userq: take reset_domain->sem before userq_mutex in create Prike Liang
  • [PATCH 9/9] drm/amdgpu/mes: skip unmap queue notification during GPU reset Prike Liang
  • [PATCH 7/9] drm/amdgpu/userq: take reset_domain->sem before userq_mutex in destroy Prike Liang
  • Re: [PATCH 7/9] drm/amdgpu/userq: take reset_domain->sem before userq_mutex in destroy Christian König
  • RE: [PATCH 7/9] drm/amdgpu/userq: take reset_domain->sem before userq_mutex in destroy Liang, Prike
  • Re: [PATCH 1/9] drm/amdgpu: defer GPU recovery after userq eviction failure Christian König
  • RE: [PATCH 1/9] drm/amdgpu: defer GPU recovery after userq eviction failure Liang, Prike
  • Re: [PATCH 1/9] drm/amdgpu: defer GPU recovery after userq eviction failure Christian König
• [PATCH v3 12/13] drm/amdgpu: remove the unused ring parameter from update_spm_vmid() Sunil Khatri
• [PATCH v3 01/13] drm/amdgpu: use the same naming scheme for kq and uq VMID masks Sunil Khatri
  • [PATCH v3 12/13] drm/amdgpu: remove the unused ring parameter from update_spm_vmid() Sunil Khatri
  • Re: [PATCH v3 12/13] drm/amdgpu: remove the unused ring parameter from update_spm_vmid() Christian König
  • [PATCH v3 02/13] drm/amdgpu: add spm_vmid and exclude it from the MES, KFD and kq pools Sunil Khatri
  • [PATCH v3 06/13] drm/amdgpu: reserve SPM VMID on gfx9 Sunil Khatri
  • [PATCH v3 04/13] drm/amdgpu: reserve SPM VMID on gfx7 Sunil Khatri
  • [PATCH v3 10/13] drm/amdgpu: use spm_vmid for the default RLC SPM VMID Sunil Khatri
  • [PATCH v3 11/13] drm/amdgpu: remove the now-redundant runtime SPM VMID update Sunil Khatri
  • [PATCH v3 13/13] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Sunil Khatri
  • Re: [PATCH v3 13/13] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Christian König
  • Re: [PATCH v3 13/13] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Khatri, Sunil
  • Re: [PATCH v3 13/13] drm/amdgpu: bind the SPM VMID's page table to the reserving VM Christian König
  • [PATCH v3 05/13] drm/amdgpu: reserve SPM VMID on gfx8 Sunil Khatri
  • [PATCH v3 09/13] drm/amdgpu: reserve SPM VMID on gfx12 Sunil Khatri
  • [PATCH v3 07/13] drm/amdgpu: reserve SPM VMID on gfx10 Sunil Khatri
  • [PATCH v3 08/13] drm/amdgpu: reserve SPM VMID on gfx11 Sunil Khatri
  • [PATCH v3 03/13] drm/amdgpu: use dedicated SPM VMID from the reserved path Sunil Khatri
  • Re: [PATCH v3 03/13] drm/amdgpu: use dedicated SPM VMID from the reserved path Christian König
• [PATCH v2 1/4] drm/amdgpu: undo the halted activities when the HW reset is skipped Jesse Zhang
  • [PATCH v2 2/4] drm/amdgpu: report the BO alignment in bytes in GEM_LIST_HANDLES Jesse Zhang
  • [PATCH v2 3/4] drm/amdgpu: keep the eviction fence until the last handle is closed Jesse Zhang
  • [PATCH v2 4/4] drm/amdgpu: reject unknown GEM_METADATA ops Jesse Zhang
  • Re: [PATCH v2 4/4] drm/amdgpu: reject unknown GEM_METADATA ops Christian König
• [PATCH] drm/radeon: fix wake event stealing in fence_is_signaled polling Bogdan Metla
• [PATCH 1/4] drm/amdgpu: undo the halted activities when the HW reset is skipped Jesse Zhang
  • [PATCH 4/4] drm/amdgpu: reject unknown GEM_METADATA ops Jesse Zhang
  • Re: [PATCH 4/4] drm/amdgpu: reject unknown GEM_METADATA ops Christian König
  • [PATCH 3/4] drm/amdgpu: keep the eviction fence until the last handle is closed Jesse Zhang
  • Re: [PATCH 3/4] drm/amdgpu: keep the eviction fence until the last handle is closed Christian König
  • [PATCH 2/4] drm/amdgpu: report the BO alignment in bytes in GEM_LIST_HANDLES Jesse Zhang
  • Re: [PATCH 2/4] drm/amdgpu: report the BO alignment in bytes in GEM_LIST_HANDLES Christian König
• [PATCH v2 01/11] drm/amdgpu: use the same naming scheme for kq and uq VMID masks Sunil Khatri
  • [PATCH v2 06/11] drm/amdgpu: reserve SPM VMID on gfx9 Sunil Khatri
  • [PATCH v2 09/11] drm/amdgpu: reserve SPM VMID on gfx12 Sunil Khatri
  • [PATCH v2 05/11] drm/amdgpu: reserve SPM VMID on gfx8 Sunil Khatri
  • [PATCH v2 10/11] drm/amdgpu: use spm_vmid for the default RLC SPM VMID Sunil Khatri
  • Re: [PATCH v2 10/11] drm/amdgpu: use spm_vmid for the default RLC SPM VMID Christian König
  • [PATCH v2 07/11] drm/amdgpu: reserve SPM VMID on gfx10 Sunil Khatri
  • [PATCH v2 03/11] drm/amdgpu: use dedicated SPM VMID from the reserved path Sunil Khatri
  • Re: [PATCH v2 03/11] drm/amdgpu: use dedicated SPM VMID from the reserved path Christian König
  • Re: [PATCH v2 03/11] drm/amdgpu: use dedicated SPM VMID from the reserved path Khatri, Sunil
  • [PATCH v2 11/11] drm/amdgpu: remove the now-redundant runtime SPM VMID update Sunil Khatri
  • Re: [PATCH v2 11/11] drm/amdgpu: remove the now-redundant runtime SPM VMID update Christian König
  • Re: [PATCH v2 11/11] drm/amdgpu: remove the now-redundant runtime SPM VMID update Khatri, Sunil
  • [PATCH v2 08/11] drm/amdgpu: reserve SPM VMID on gfx11 Sunil Khatri
  • [PATCH v2 02/11] drm/amdgpu: add spm_vmid and exclude it from the MES, KFD and kq pools Sunil Khatri
  • Re: [PATCH v2 02/11] drm/amdgpu: add spm_vmid and exclude it from the MES, KFD and kq pools Christian König
  • [PATCH v2 04/11] drm/amdgpu: reserve SPM VMID on gfx7 Sunil Khatri
  • Re: [PATCH v2 04/11] drm/amdgpu: reserve SPM VMID on gfx7 Christian König
  • Re: [PATCH v2 01/11] drm/amdgpu: use the same naming scheme for kq and uq VMID masks Christian König
• [PATCH] drm/amd/display: Initialize missing TD-LUT programming inputs Avi Weiss
• [PATCH for-linus] PCI/AER: Skip unmasking Advisory Non-Fatal Errors on T2 SEP Aditya Garg
  • Re: [PATCH for-linus] PCI/AER: Skip unmasking Advisory Non-Fatal Errors on T2 SEP Lukas Wunner
  • Re: [PATCH for-linus] PCI/AER: Skip unmasking Advisory Non-Fatal Errors on T2 SEP Bjorn Helgaas
  • Re: [PATCH for-linus] PCI/AER: Skip unmasking Advisory Non-Fatal Errors on T2 SEP Bjorn Helgaas
• [Phoenix / DCN 3.1.4] Regression in 7.2: 3840x2160@60 driven as RGB 594 MHz on an HDMI sink limited to 300 MHz TMDS (4:2:0-only mode) → black screen Tobias Johansson
  • Re: [Phoenix / DCN 3.1.4] Regression in 7.2: 3840x2160@60 driven as RGB 594 MHz on an HDMI sink limited to 300 MHz TMDS (4:2:0-only mode) → black screen Alex Deucher
• [PATCH v3] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Ce Sun
  • RE: [PATCH v3] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Zhang, Hawking
  • Re: [PATCH v3] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Lazar, Lijo
• [PATCH] drm/amd/pm: mark the current DPM clock level active Kevin Wang
  • RE: [PATCH] drm/amd/pm: mark the current DPM clock level active Feng, Kenneth
  • Re: [PATCH] drm/amd/pm: mark the current DPM clock level active Lazar, Lijo
  • RE: [PATCH] drm/amd/pm: mark the current DPM clock level active Wang, Kevin
  • Re: [PATCH] drm/amd/pm: mark the current DPM clock level active Lazar, Lijo
• [PATCH v2 1/2] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Ce Sun
  • RE: [PATCH v2 1/2] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Zhang, Hawking
  • Re: [PATCH v2 1/2] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Sun, Ce(Overlord)
  • RE: [PATCH v2 1/2] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Zhang, Hawking
• [PATCH v2 2/2] drm/amd/pm: move smu_feature_init to smu_early_init Ce Sun
• [PATCH] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Ce Sun
  • RE: [PATCH] drm/amd/ras: Use MP1 feature status to select fw-managed EEPROM Zhou1, Tao
• [PATCH v3] drm/amdgpu: preempt KFD queues before taking the reset domain lock William Palacek
  • Re: [PATCH v3] drm/amdgpu: preempt KFD queues before taking the reset domain lock Felix Kuehling
• [PATCH] drm/amd/pm: move smu_feature_init to smu_early_init Ce Sun
  • RE: [PATCH] drm/amd/pm: move smu_feature_init to smu_early_init Zhang, Hawking
• [PATCH v1] drm/amdkfd: Fix use-after-free in the process creation error path Binbin Deng
  • Re: [PATCH v1] drm/amdkfd: Fix use-after-free in the process creation error path Kuehling, Felix
• [amdgpu Picasso 1002:15d8] gfxhub UTCL2 SQC permission fault -> ring gfx timeout when DPM forced high (bug 222109, repro on LTS 6.18 too) Алексей
• [PATCH Review 1/1] drm/amd/ras: Add pci bif ras aca bank info Stanley . Yang
  • RE: [PATCH Review 1/1] drm/amd/ras: Add pci bif ras aca bank info Zhou1, Tao
• [PATCH] drm/amdgpu/userq: skip restoring guilty or VRAM-lost queues Prike Liang
• [PATCH v4 1/4] drm/amdgpu: add UAPI for user queue query status Prike Liang
  • [PATCH v4 3/4] drm/amdgpu/userq: report invalid VA through the broken status flag Prike Liang
  • [PATCH v4 4/4] drm/amdgpu/userq: report GPU reset in progress Prike Liang
  • [PATCH v4 2/4] drm/amdgpu/userq: implement support for query status Prike Liang
• [PATCH] drm/amdkfd: place GFX12 compute queue MQDs in CPU-visible VRAM Geramy Loveless
  • Re: [PATCH] drm/amdkfd: place GFX12 compute queue MQDs in CPU-visible VRAM Christian König
  • Re: [PATCH] drm/amdkfd: place GFX12 compute queue MQDs in CPU-visible VRAM Felix Kuehling
  • Re: [PATCH] drm/amdkfd: place GFX12 compute queue MQDs in CPU-visible VRAM Geramy Loveless
• [PATCH] drm/amdgpu: return error from gpu_recover_get() on runtime pm failure Haotian Zhang
• [PATCH] drm/amdgpu/ras: Use fw-managed EEPROM for MP1 IP_VERSION(13, 0, 12) Ce Sun
  • RE: [PATCH] drm/amdgpu/ras: Use fw-managed EEPROM for MP1 IP_VERSION(13,0,12) Zhou1, Tao
  • RE: [PATCH] drm/amdgpu/ras: Use fw-managed EEPROM for MP1 IP_VERSION(13,0,12) Zhou1, Tao
• [PATCH v2] drm/ttm: return an error when kmapping a BO without pages Jesse Zhang
  • Re: [PATCH v2] drm/ttm: return an error when kmapping a BO without pages Arunpravin Paneer Selvam
• [PATCH v4 1/3] gpu/buddy: restore two-pass clear/dirty guard for range-biased allocation Arunpravin Paneer Selvam
  • [PATCH v4 2/3] gpu/buddy: add range-restricted contiguous allocation fallback Arunpravin Paneer Selvam
  • [PATCH v4 3/3] gpu/buddy: search lower orders in contiguous try-harder fallback Arunpravin Paneer Selvam
  • Re: [PATCH v4 1/3] gpu/buddy: restore two-pass clear/dirty guard for range-biased allocation Arunpravin Paneer Selvam
  • Re: [PATCH v4 1/3] gpu/buddy: restore two-pass clear/dirty guard for range-biased allocation Matthew Auld
• [PATCH 1/4] drm/amdgpu: Use feedback buffer for VCE destroy message David Rosca
  • [PATCH 2/4] drm/amdgpu: Allow multiple VCE create commands with same handle David Rosca
  • [PATCH 4/4] drm/amdgpu: Allow VCE SEI command in IB David Rosca
  • [PATCH 3/4] drm/amdgpu: Fix VCE buffer size check for DPB and input surface David Rosca
• [GIT PULL] PCI fixes for v7.3 Bjorn Helgaas
  • Re: [GIT PULL] PCI fixes for v7.3 pr-tracker-bot
  • Re: [GIT PULL] PCI fixes for v7.3 Perlow, Jason
  • [GIT PULL] PCI fixes for v7.3 Bjorn Helgaas
  • Re: [GIT PULL] PCI fixes for v7.3 pr-tracker-bot
• [PATCH] drm/amdgpu/userq: actually invalidate userq BOs Benjamin Cheng
  • Re: [PATCH] drm/amdgpu/userq: actually invalidate userq BOs Christian König
  • [PATCH v2] drm/amdgpu/userq: actually validate userq BOs Benjamin Cheng
  • Re: [PATCH v2] drm/amdgpu/userq: actually validate userq BOs Christian König
• [PATCH] drm/amd/amdgpu: Add missing GC 11.0.0 registers Tom St Denis
  • Re: [PATCH] drm/amd/amdgpu: Add missing GC 11.0.0 registers Alex Deucher
• [PATCH] amdkfd: fix doorbell allocation race creating duplicate allocations Henry Martin
  • Re: [PATCH] amdkfd: fix doorbell allocation race creating duplicate allocations Kuehling, Felix
  • Re: [PATCH] amdkfd: fix doorbell allocation race creating duplicate allocations Kuehling, Felix
  • [PATCH v2] amdkfd: fix doorbell allocation race creating duplicate allocations Henry Martin
  • Re: [PATCH v2] amdkfd: fix doorbell allocation race creating duplicate allocations Felix Kuehling
  • Re: [PATCH v2] amdkfd: fix doorbell allocation race creating duplicate allocations henry martin
  • [PATCH v3] drm/amdkfd: fix doorbell allocation race creating duplicate allocations Felix Kuehling
  • [PATCH v4] drm/amdkfd: fix doorbell allocation race creating duplicate allocations Felix Kuehling
  • Re: [PATCH] amdkfd: fix doorbell allocation race creating duplicate allocations henry martin
• [PATCH v3 1/2] drm/amdgpu: store the user-queue VMID mask instead of first_kfd_vmid Sunil Khatri
  • [PATCH v3 2/2] drm/amdgpu: amdgpu_vmid_mgr_set_vmid_mask to set up both hubs at once Sunil Khatri
  • Re: [PATCH v3 2/2] drm/amdgpu: amdgpu_vmid_mgr_set_vmid_mask to set up both hubs at once Christian König
  • Re: [PATCH v3 1/2] drm/amdgpu: store the user-queue VMID mask instead of first_kfd_vmid Christian König
• [PATCH 1/3] drm/amdgpu: return -EFAULT from AMDGPU_INFO_UQ_FW_AREAS Jesse Zhang
  • [PATCH 3/3] drm/amdgpu: free the userptr ranges when a CS fails after parser_bos Jesse Zhang
  • Re: [PATCH 3/3] drm/amdgpu: free the userptr ranges when a CS fails after parser_bos Alex Deucher
  • [PATCH 2/3] drm/amdgpu: don't drop the runtime PM reference twice in amdgpu_gpr Jesse Zhang
  • Re: [PATCH 1/3] drm/amdgpu: return -EFAULT from AMDGPU_INFO_UQ_FW_AREAS Alex Deucher
• [PATCH] drm/amd/pm: add zero fan stop temperature support on smu 14.0.2 Kenneth Feng
  • RE: [PATCH] drm/amd/pm: add zero fan stop temperature support on smu 14.0.2 Wang, Kevin
• [PATCH v2 1/2] drm/amdgpu: store the user-queue VMID mask instead of first_kfd_vmid Sunil Khatri
  • Re: [PATCH v2 1/2] drm/amdgpu: store the user-queue VMID mask instead of first_kfd_vmid Christian König
  • Re: [PATCH v2 1/2] drm/amdgpu: store the user-queue VMID mask instead of first_kfd_vmid Khatri, Sunil
  • [PATCH v2 2/2] drm/amdgpu: amdgpu_vmid_mgr_set_vmid_mask to set up both hubs at once Sunil Khatri
  • Re: [PATCH v2 2/2] drm/amdgpu: amdgpu_vmid_mgr_set_vmid_mask to set up both hubs at once Christian König
• [PATCH] drm/amdgpu: fix NULL RAS context dereference in UMC page retirement Haotian Zhang
• [PATCH Review v2 1/1] drm/amd/ras: Support invoke ras command Stanley . Yang
  • RE: [PATCH Review v2 1/1] drm/amd/ras: Support invoke ras command Zhang, Hawking
• [PATCH 1/2] drm/amdgpu: fix the error path in amdgpu_vm_pt_alloc() Jesse Zhang
  • Re: [PATCH 1/2] drm/amdgpu: fix the error path in amdgpu_vm_pt_alloc() Christian König
• [PATCH] drm/ttm: return an error when kmapping a BO without pages Jesse Zhang
  • Re: [PATCH] drm/ttm: return an error when kmapping a BO without pages Christian König
• [PATCH] drm/amdgpu: UALink add debugfs selftest Philip Yang
• [PATCH v2] drm/amdgpu: wait for pending page table updates before switching a VM to CPU updates John Fisher
  • Re: [PATCH v2] drm/amdgpu: wait for pending page table updates before switching a VM to CPU updates Christian König
• [PATCH v5 0/3] drm/amdkfd: fix wedged teardown on surprise removal Olivier Kaloudoff
  • [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Kuehling, Felix
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Christian König
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Christian König
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Christian König
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • Re: [PATCH v5 3/3] drm/amdkfd: bound SVM migration fence wait and guard with drm_dev_enter Olivier Kaloudoff
  • [PATCH v5 1/3] drm/amdkfd: tear down KFD processes before early fini_sw on disconnect Olivier Kaloudoff
  • [PATCH v5 2/3] drm/amdkfd: stop restore retries on device unplug Olivier Kaloudoff
  • Re: [PATCH v5 0/3] drm/amdkfd: fix wedged teardown on surprise removal Kuehling, Felix

• Earlier messages
• Later messages