[PATCH 33/34] drm/amdkfd: Add SVM API support capability bits

From: Philip Yang SVMAPISupported property added to HSA_CAPABILITY, the value match HSA_CAPABILITY defined in Thunk spec: SVMAPISupported: it will not be supported on older kernels that don't have HMM or on systems with GFXv8 or older GPUs without support for 48-bit virtual addresses.

[PATCH 34/34] drm/amdkfd: Add CONFIG_HSA_AMD_SVM

Control whether to build SVM support into amdgpu with a Kconfig option. This makes it easier to disable it in production kernels if this new feature causes problems in production environments. Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/Kconfig | 15 +++-

[PATCH 32/34] drm/amdkfd: multiple gpu migrate vram to vram

If prefetch range to gpu with acutal location is another gpu, or GPU retry fault restore pages to migrate the range with acutal location is gpu, then migrate from one gpu to another gpu. Use system memory as bridge because sdma engine may not able to access another gpu vram, use sdma of source

[PATCH 30/34] drm/amdkfd: refine migration policy with xnack on

With xnack on, GPU vm fault handler decide the best restore location, then migrate range to the best restore location and update GPU mapping to recover the GPU vm fault. Signed-off-by: Philip Yang Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling ---

[PATCH 31/34] drm/amdkfd: add svm range validate timestamp

With xnack on, add validate timestamp in order to handle GPU vm fault from multiple GPUs. If GPU retry fault need migrate the range to the best restore location, use range validate timestamp to record system timestamp after range is restored to update GPU page table. Because multiple pages of

[PATCH 29/34] drm/amdgpu: reserve fence slot to update page table

From: Philip Yang Forgot to reserve a fence slot to use sdma to update page table, cause below kernel BUG backtrace to handle vm retry fault while application is exiting. [ 133.048143] kernel BUG at /home/yangp/git/compute_staging/kernel/drivers/dma-buf/dma-resv.c:281! [ 133.048487]

[PATCH 26/34] drm/amdkfd: add svm_bo eviction mechanism support

svm_bo eviction mechanism is different from regular BOs. Every SVM_BO created contains one eviction fence and one worker item for eviction process. SVM_BOs can be attached to one or more pranges. For SVM_BO eviction mechanism, TTM will start to call enable_signal callback for every SVM_BO until

[PATCH 28/34] drm/amdgpu: add svm_bo eviction to enable_signal cb

From: Alex Sierra Add to amdgpu_amdkfd_fence.enable_signal callback, support for svm_bo fence eviction. Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c | 11 --- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git

[PATCH 27/34] drm/amdgpu: svm bo enable_signal call condition

From: Alex Sierra [why] To support svm bo eviction mechanism. [how] If the BO crated has AMDGPU_AMDKFD_CREATE_SVM_BO flag set, enable_signal callback will be called inside amdgpu_evict_flags. This also causes gutting of the BO by removing all placements, so that TTM won't actually do an

[PATCH 25/34] drm/amdgpu: add param bit flag to create SVM BOs

From: Alex Sierra Add CREATE_SVM_BO define bit for SVM BOs. Another define flag was moved to concentrate these KFD type flags in one include file. Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 7 ++-

[PATCH 24/34] drm/amdkfd: add svm_bo reference for eviction fence

From: Alex Sierra [why] As part of the SVM functionality, the eviction mechanism used for SVM_BOs is different. This mechanism uses one eviction fence per prange, instead of one fence per kfd_process. [how] A svm_bo reference to amdgpu_amdkfd_fence to allow differentiate between SVM_BO or

[PATCH 23/34] drm/amdkfd: SVM API call to restore page tables

From: Alex Sierra Use SVM API to restore page tables when retry fault and compute context are enabled. Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 20 +++- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git

[PATCH 22/34] drm/amdkfd: page table restore through svm API

Page table restore implementation in SVM API. This is called from the fault handler at amdgpu_vm. To update page tables through the page fault retry IH. Signed-off-by: Alex Sierra Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 59

[PATCH 20/34] drm/amdkfd: invalidate tables on page retry fault

GPU page tables are invalidated by unmapping prange directly at the mmu notifier, when page fault retry is enabled through amdgpu_noretry global parameter. The restore page table is performed at the page fault handler. If xnack is on, we update GPU mappings after migration to avoid unnecessary

[PATCH 21/34] drm/amdgpu: enable 48-bit IH timestamp counter

From: Alex Sierra By default this timestamp is 32 bit counter. It gets overflowed in around 10 minutes. Change-Id: I7c46604b0272dcfd1ce24351437c16fe53dca0ab Signed-off-by: Alex Sierra Signed-off-by: Philip Yang --- drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 1 + 1 file changed, 1 insertion(+)

[PATCH 19/34] drm/amdkfd: HMM migrate vram to ram

If CPU page fault happens, HMM pgmap_ops callback migrate_to_ram start migrate memory from vram to ram in steps: 1. migrate_vma_pages get vram pages, and notify HMM to invalidate the pages, HMM interval notifier callback evict process queues 2. Allocate system memory pages 3. Use svm copy memory

[PATCH 18/34] drm/amdkfd: HMM migrate ram to vram

Register svm range with same address and size but perferred_location is changed from CPU to GPU or from GPU to CPU, trigger migration the svm range from ram to vram or from vram to ram. If svm range prefetch location is GPU with flags KFD_IOCTL_SVM_FLAG_HOST_ACCESS, validate the svm range on ram

[PATCH 17/34] drm/amdkfd: copy memory through gart table

From: Philip Yang Use sdma linear copy to migrate data between ram and vram. The sdma linear copy command uses kernel buffer function queue to access system memory through gart table. Use reserved gart table window 0 to map system page address, and vram page address is direct mapping. Use the

[PATCH 16/34] drm/amdkfd: support xgmi same hive mapping

From: Philip Yang amdgpu_gmc_get_vm_pte use bo_va->is_xgmi same hive information to set pte flags to update GPU mapping. Add local structure variable bo_va, and update bo_va.is_xgmi, pass it to mapping->bo_va while mapping to GPU. Assuming xgmi pstate is hi after boot. Signed-off-by: Philip

[PATCH 13/34] drm/amdkfd: add ioctl to configure and query xnack retries

From: Alex Sierra Xnack retries are used for page fault recovery. Some AMD chip families support continuously retry while page table entries are invalid. The driver must handle the page fault interrupt and fill in a valid entry for the GPU to continue. This ioctl allows to enable/disable XNACK

[PATCH 15/34] drm/amdkfd: validate vram svm range from TTM

If svm range perfetch location is not zero, use TTM to alloc amdgpu_bo vram nodes to validate svm range, then map vram nodes to GPUs. Use offset to sub allocate from the same amdgpu_bo to handle overlap vram range while adding new range or unmapping range. svm_bo has ref count to trace the

[PATCH 14/34] drm/amdkfd: register HMM device private zone

From: Philip Yang Register vram memory as MEMORY_DEVICE_PRIVATE type resource, to allocate vram backing pages for page migration. Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/Kconfig | 1 + drivers/gpu/drm/amd/amdkfd/Makefile | 3 +-

[PATCH 12/34] drm/amdkfd: add xnack enabled flag to kfd_process

From: Alex Sierra XNACK mode controls the SQ RETRY_DISABLE setting that determines, whether recoverable page faults can be supported on GFXv9 hardware. Only on Aldebaran we can support different processes running with different XNACK modes. On older chips all processes must use the same

[PATCH 11/34] drm/amdgpu: Enable retry faults unconditionally on Aldebaran

This is needed to allow per-process XNACK mode selection in the SQ when booting with XNACK off by default. Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Tested-by: Alex Sierra --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++- drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 8 ++--

[PATCH 10/34] drm/amdkfd: svm range eviction and restore

HMM interval notifier callback notify CPU page table will be updated, stop process queues if the updated address belongs to svm range registered in process svms objects tree. Scheduled restore work to update GPU page table using new pages address in the updated svm range. The restore worker

[PATCH 09/34] drm/amdkfd: map svm range to GPUs

Use amdgpu_vm_bo_update_mapping to update GPU page table to map or unmap svm range system memory pages address to GPUs. Signed-off-by: Philip Yang Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 478 ++-

[PATCH 08/34] drm/amdgpu: export vm update mapping interface

From: Philip Yang It will be used by kfd to map svm range to GPU, because svm range does not have amdgpu_bo and bo_va, cannot use amdgpu_bo_update interface, use amdgpu vm update interface directly. Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling ---

[PATCH 07/34] drm/amdkfd: deregister svm range

From: Philip Yang When application explicitly call unmap or unmap from mmput when application exit, driver will receive MMU_NOTIFY_UNMAP event to remove svm range from process svms object tree and list first, unmap from GPUs (in the following patch). Split the svm ranges to handle partial

[PATCH 06/34] drm/amdkfd: validate svm range system memory

From: Philip Yang Use HMM to get system memory pages address, which will be used to map to GPUs or migrate to vram. Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 116 ++- drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 18

[PATCH 05/34] drm/amdgpu: add common HMM get pages function

From: Philip Yang Move the HMM get pages function from amdgpu_ttm and to amdgpu_mn. This common function will be used by new svm APIs. Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 83 +

[PATCH 04/34] drm/amdkfd: add svm ioctl GET_ATTR op

From: Philip Yang Get the intersection of attributes over all memory in the given range Signed-off-by: Philip Yang Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 164 +++ 1 file changed, 164 insertions(+) diff

[PATCH 03/34] drm/amdkfd: register svm range

From: Philip Yang svm range structure stores the range start address, size, attributes, flags, prefetch location and gpu bitmap which indicates which GPU this range maps to. Same virtual address is shared by CPU and GPUs. Process has svm range list which uses both interval tree and list to

[PATCH 02/34] drm/amdkfd: add svm ioctl API

From: Philip Yang Add svm (shared virtual memory) ioctl data structure and API definition. The svm ioctl API is designed to be extensible in the future. All operations are provided by a single IOCTL to preserve ioctl number space. The arguments structure ends with a variable size array of

[PATCH 01/34] drm/amdkfd: helper to convert gpu id and idx

From: Alex Sierra svm range uses gpu bitmap to store which GPU svm range maps to. Application pass driver gpu id to specify GPU, the helper is needed to convert gpu id to gpu bitmap idx. Access through kfd_process_device pointers array from kfd_process. Signed-off-by: Alex Sierra

[PATCH 00/34] Add HMM-based SVM memory manager to KFD v3

Since the last patch series on March 22, I integrated all fixes into the original patch series. An additonal fix was added for handling failed migrations during GPU page faults. (A bigger rework of migrations and VRAM mappings will come in the future.) Support for per-process XNACK mode selecation

[PATCH] drm/amdgpu: add DMUB outbox event IRQ source define/complete/debug flag

[Why & How] We use outbox interrupt that allows us to do the AUX via DMUB Therefore, we need to add some irq source related definition in the header files; Also, I added debug flag that allows us to turn it on/off for testing purpose. --- drivers/gpu/drm/amd/amdgpu/amdgpu.h

[pull] amdgpu, amdkfd drm-fixes-5.12

Hi Dave, Daniel, Fixes for 5.12. The following changes since commit 09d78dde88ef95a27b54a6e450ee700ccabdf39d: Merge tag 'drm-msm-fixes-2021-02-25' of https://gitlab.freedesktop.org/drm/msm into drm-fixes (2021-03-26 13:04:17 +1000) are available in the Git repository at:

Re: [pull] amdgpu, amdkfd, radeon drm-next-5.12

I think this is due to this pull, on arm32. /home/airlied/devel/kernel/dim/src/drivers/gpu/drm/amd/amdgpu/../display/dmub/src/dmub_srv.c: In function ‘dmub_srv_hw_init’: /home/airlied/devel/kernel/dim/src/drivers/gpu/drm/amd/amdgpu/../display/dmub/src/dmub_srv.c:519:44: warning: cast from pointer

Re: [PATCH 2/4] drm/amd/display: Add FPU event trace

Hi Rodrigo, I love your patch! Yet something to improve: [auto build test ERROR on next-20210331] [cannot apply to linus/master v5.12-rc5 v5.12-rc4 v5.12-rc3 v5.12-rc5] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base

Re: [PATCH 2/4] drm/amd/display: Add FPU event trace

Hi Rodrigo, I love your patch! Perhaps something to improve: [auto build test WARNING on next-20210331] [cannot apply to linus/master v5.12-rc5 v5.12-rc4 v5.12-rc3 v5.12-rc5] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use

Re: Interlaced resolutions hang the desktop

Does disabling pageflipping via the xorg.conf help? Alex On Wed, Mar 31, 2021 at 1:40 PM Christian König wrote: > > Yeah, agree that must be some kind of bug in the upper layer of the stack. > > Most likely some userspace component is not handling the specialties of > interlacing correctly

Re: Interlaced resolutions hang the desktop

Yeah, agree that must be some kind of bug in the upper layer of the stack. Most likely some userspace component is not handling the specialties of interlacing correctly (different vblank timing every other frame). It probably only works on Intel and after restarting the display manager by

Re: [PATCH 1/4] drm/amd/display: Introduce FPU directory inside DC

Hi Rodrigo, I love your patch! Perhaps something to improve: [auto build test WARNING on next-20210331] [also build test WARNING on v5.12-rc5] [cannot apply to linus/master v5.12-rc5 v5.12-rc4 v5.12-rc3] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting

Re: Interlaced resolutions hang the desktop

Well the hardware is working fine as far as I can see. Can you try to kill the X server over SSH and see if you then get some screen update? Regards, Christian. Am 31.03.21 um 16:52 schrieb Alberto Salvia Novella: Output

Re: Interlaced resolutions hang the desktop

Output . On Wed, 31 Mar 2021 at 16:36, Christian König wrote: > Mhm strange. > > Can you get me the output of "sudo cat > /sys/kernel/debug/dri/0/radeon_fence_info" when the problem happens? > > Thanks,

Re: Interlaced resolutions hang the desktop

- The computer still replies to *ping*. - The *journal* shows no errors, but a few warnings . - The *mouse* doesn't freeze. On Wed, 31 Mar 2021 at 10:09, Christian König wrote: > Can you access the

Re: Interlaced resolutions hang the desktop

Mhm strange. Can you get me the output of "sudo cat /sys/kernel/debug/dri/0/radeon_fence_info" when the problem happens? Thanks, Christian. Am 31.03.21 um 16:33 schrieb Alberto Salvia Novella: - The computer still replies to *ping*. - The *journal* shows no errors, but a few warnings

Re: [PATCH] drm/amdgpu: drop some unused atombios functions

Am 31.03.21 um 16:06 schrieb Alex Deucher: These were leftover from the old CI dpm code which was retired a while ago. Signed-off-by: Alex Deucher Acked-by: Christian König BTW: Wasn't there a way to get the linker to complain about unused symbols? E.g. unused function, global variables

[PATCH] drm/amdgpu: drop some unused atombios functions

These were leftover from the old CI dpm code which was retired a while ago. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 151 --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h | 12 -- 2 files changed, 163 deletions(-) diff --git

[PATCH][next] drm/amd/display: remove redundant initialization of variable status

From: Colin Ian King The variable status is being initialized with a value that is never read and it is being updated later with a new value. The initialization is redundant and can be removed. Also clean up an indentation. Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King ---

[PATCH] drm/amd: cleanup coding style a bit

Fix patch check warning: WARNING: suspect code indent for conditional statements (8, 17) + if (obj && obj->use < 0) { +DRM_ERROR("RAS ERROR: Unbalance obj(%s) use\n", obj->head.name); WARNING: braces {} are not necessary for single statement blocks + if (obj &&

[PATCH] amd/amdgpu: code refactoring to clean code style a bit

Fix checkpatch.pl warning: Too many leading tabs - consider code refactoring WARNING: Too many leading tabs - consider code refactoring + for (j = 0; j < profile->ucLeakageBinNum; j++) { WARNING: Too many leading tabs - consider code refactoring +

Re: Interlaced resolutions hang the desktop

What happens is this simple: after a few minutes, about 6 or so, the entire content of the screen stays still. In some minor situations only the applications panel of KDE Plasma. If music is playing it continues playing, so only graphics are hung. Yet in most cases the power button won't shut

[PATCH] drm/amd: use kmalloc_array over kmalloc with multiply

Fix patch check warning: WARNING: Prefer kmalloc_array over kmalloc with multiply + buf = kmalloc(MAX_KFIFO_SIZE * sizeof(*buf), GFP_KERNEL); Signed-off-by: Bernard Zhao --- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

Re: [PATCH 0/4] drm/amd/display: Base changes for isolating FPU operation in a single place

Hi Rodrigo, I'm not so happy about the whole recursion thing, but I think that is something which can be worked on later on. Apart from that the approach sounds solid to me. Regards, Christian. Am 31.03.21 um 14:24 schrieb Rodrigo Siqueira: Hi, In the display core, we utilize floats and

Re: [PATCH 4/4] drm/amd/display: Add DC_FP helper to check FPU state

Am 31.03.21 um 14:25 schrieb Rodrigo Siqueira: To fully isolate FPU operations in a single place, we must avoid situations where compilers spill FP values to registers due to FP enable in a specific C file. Note that even if we isolate all FPU functions in a single file and call its interface

Re: [PATCH 3/4] drm/amd/display: Add ref count control for FPU utilization

Am 31.03.21 um 14:25 schrieb Rodrigo Siqueira: DC invokes DC_FPU_START/END in multiple parts of the code; this can create a situation where we invoke this FPU operation in a nested way. For avoiding this situation, this commit adds a mechanism where dc_fpu_begin/end manages the access to

[PATCH 0/4] drm/amd/display: Base changes for isolating FPU operation in a single place

Hi, In the display core, we utilize floats and doubles units for calculating modesetting parameters. One side effect of our approach to use double-precision is the fact that we spread multiple FPU access across our driver, which means that we can accidentally clobber user space FPU state. #

[PATCH 4/4] drm/amd/display: Add DC_FP helper to check FPU state

To fully isolate FPU operations in a single place, we must avoid situations where compilers spill FP values to registers due to FP enable in a specific C file. Note that even if we isolate all FPU functions in a single file and call its interface from other files, the compiler might enable the use

[PATCH 2/4] drm/amd/display: Add FPU event trace

We don't have any mechanism for tracing FPU operations inside the display core, making the debug work a little bit tricky. For trying to alleviate this problem, this commit introduces a trace mechanism inside our DC_FP_START/END macros. Signed-off-by: Rodrigo Siqueira Acked-by: Rodrigo Siqueira

[PATCH 3/4] drm/amd/display: Add ref count control for FPU utilization

DC invokes DC_FPU_START/END in multiple parts of the code; this can create a situation where we invoke this FPU operation in a nested way. For avoiding this situation, this commit adds a mechanism where dc_fpu_begin/end manages the access to kernel_fpu_begin/end. Signed-off-by: Rodrigo Siqueira

[PATCH 1/4] drm/amd/display: Introduce FPU directory inside DC

The display core files rely on FPU operation, which requires to be compiled with special flags. Ideally, we don't want these FPU operations to get spread around the DC code; nevertheless, it happens in the current source. This commit introduces a new directory named fpu_operations that intends to

RE: [PATCH 2/2] drm/amdgpu: Revert "SWDEV-238407 Add clear vf fw support"

[AMD Official Use Only - Internal Distribution Only] Ping .. >-Original Message- >From: Emily Deng >Sent: Wednesday, March 31, 2021 2:34 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily >Subject: [PATCH 2/2] drm/amdgpu: Revert "SWDEV-238407 Add clear vf fw >support" > >As

RE: [PATCH] drm/amdgpu: Toggle msix after FLR for sriov

[AMD Official Use Only - Internal Distribution Only] Ping .. >-Original Message- >From: Emily Deng >Sent: Tuesday, March 30, 2021 5:43 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily >Subject: [PATCH] drm/amdgpu: Toggle msix after FLR for sriov > >From: "Emily.Deng" > >For

RE: [PATCH 4/6] drm/amdgpu: Disable fetch discovery data from vram for navi12 sriov

[AMD Official Use Only - Internal Distribution Only] Ping . >-Original Message- >From: Emily Deng >Sent: Tuesday, March 30, 2021 12:42 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily >Subject: [PATCH 4/6] drm/amdgpu: Disable fetch discovery data from vram for >navi12 sriov >

RE: [PATCH 2/6] drm/amdgpu: Correct the irq numbers for virtual ctrc

[AMD Official Use Only - Internal Distribution Only] Ping.. >-Original Message- >From: Emily Deng >Sent: Tuesday, March 30, 2021 12:42 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily >Subject: [PATCH 2/6] drm/amdgpu: Correct the irq numbers for virtual ctrc > >Set the

RE: [PATCH 1/6] drm/amdgpu: Disable vcn decode ring for sriov navi12

[AMD Official Use Only - Internal Distribution Only] Ping.. >-Original Message- >From: Emily Deng >Sent: Tuesday, March 30, 2021 12:42 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily ; Min, Frank >Subject: [PATCH 1/6] drm/amdgpu: Disable vcn decode ring for sriov navi12 >

[PATCH] [v2] amd: display: dc: struct dc_state is declared twice

struct dc_state is declared twice. One has been declared at 273rd line. Remove the duplicate. Signed-off-by: Wan Jiabing --- drivers/gpu/drm/amd/display/dc/dc.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index

Re: Interlaced resolutions hang the desktop

24fps is intended for video only. Anything interactive at 24fps, as just moving the mouse around, is extremely choppy. No way anyone would prefer that over an interlaced resolution or a lower resolution. That is, by far, the worst option. Just try it on your screen, set it to 24Hz or alike, and

Re: Interlaced resolutions hang the desktop

Can you access the system over the network and see if there is anything in the system log? It sounds like the display stack has crashed, but when the sound keeps playing the system is most likely still responsive over network. Thanks, Christian. Am 31.03.21 um 10:05 schrieb Alberto Salvia

Re: Interlaced resolutions hang the desktop

Correct, but a TV is intended for videos only. That's why it implements only the lower HDMI standard. Interlaced transmits only halve the lines with each frame, so a 60Hz mode effectively either becomes a 30Hz mode, halving the vertical resolution or adaptive motion compensated which the know

[PATCH] drm/amdgpu: change mmhub register access from mmio to rlcg

From: pengzhou change mmhub register access from mmio to rlcg if mmhub indirect access enabled, otherwise access these registers in the old path. Signed-off-by: pengzhou --- drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 12 ++-- drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 39

Re: Interlaced resolutions hang the desktop

Hi Alberto, well a frame rate of 24Hz is perfectly reasonable for a TV and desktop usage. This is probably caused by the TVs limited HDMI bandwidth and a refresh rate of 30/25 Hz for the interlaced mode isn't much better either. Regards, Christian. Am 30.03.21 um 22:59 schrieb Alberto

Re: [PATCH 1/4] drm/amdgpu: Macros for vram physical addr calculation

Hi Oak, have you seen my review comments on the patches? Regards, Christian. Am 30.03.21 um 21:35 schrieb Oak Zeng: Add one macro to calculate BO's GPU physical address. And another one to calculate BO's CPU physical address. Signed-off-by: Oak Zeng Suggested-by: Lijo Lazar ---

[PATCH 2/2] drm/amdgpu: Revert "SWDEV-238407 Add clear vf fw support"

As already moved the support to host driver, so revert this in guest driver. This reverts commit 8d5e6f45df5f9073760dea0ab94321615cea16ec. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 36 ++--- drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h | 8 -- 2

[PATCH 1/2] drm/amdgpu: Revert "SWDEV-238407 drm/amdgpu/sriov: Need to clear kiq position"

As already moved the implementation to host driver, so remove this from guest driver. This reverts commit 96f7d59858ada4a6372fcb249b04805d14482c49. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 6 -- 1 file changed, 6 deletions(-) diff --git