#
5869b32b |
|
31-Jan-2024 |
Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> |
drm/amdkfd: update SIMD distribution algo for GFXIP 9.4.2 onwards In certain cooperative group dispatch scenarios the default SPI resource allocation may cause reduced per-CU workgroup occupancy. Set COMPUTE_RESOURCE_LIMITS.FORCE_SIMD_DIST=1 to mitigate soft hang scenarions. Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Suggested-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e3de58f8 |
|
31-Jan-2024 |
Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> |
drm/amdkfd: update SIMD distribution algo for GFXIP 9.4.2 onwards In certain cooperative group dispatch scenarios the default SPI resource allocation may cause reduced per-CU workgroup occupancy. Set COMPUTE_RESOURCE_LIMITS.FORCE_SIMD_DIST=1 to mitigate soft hang scenarions. Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Suggested-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f4fa8fcd |
|
22-Aug-2023 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Update CU masking for GFX 9.4.3 The CU mask passed from user-space will change based on different spatial partitioning mode. As a result, update CU masking code for GFX9.4.3 to work for all partitioning modes. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fc6efed2 |
|
22-Aug-2023 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Update CU masking for GFX 9.4.3 The CU mask passed from user-space will change based on different spatial partitioning mode. As a result, update CU masking code for GFX9.4.3 to work for all partitioning modes. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9041b53a |
|
28-Jun-2023 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Use KIQ to unmap HIQ Currently, we unmap HIQ by directly writing to HQD registers. This doesn't work for GFX9.4.3. Instead, use KIQ to unmap HIQ, similar to how we use KIQ to map HIQ. Using KIQ to unmap HIQ works for all GFX series post GFXv9. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a70a93fa |
|
05-May-2022 |
Jonathan Kim <jonathan.kim@amd.com> |
drm/amdkfd: add debug suspend and resume process queues operation In order to inspect waves from the saved context at any point during a debug session, the debugger must be able to preempt queues to trigger context save by suspending them. On queue suspend, the KFD will copy the context save header information so that the debugger can correctly crawl the appropriate size of the saved context. The debugger must then also be allowed to resume suspended queues. A queue that is newly created cannot be suspended because queue ids are recycled after destruction so the debugger needs to know that this has occurred. Query functions will be later added that will clear a given queue of its new queue status. A queue cannot be destroyed while it is suspended to preserve its saved context during debugger inspection. Have queue destruction block while a queue is suspended and unblocked when it is resumed. Likewise, if a queue is about to be destroyed, it cannot be suspended. Return the number of queues successfully suspended or resumed along with a per queue status array where the upper bits per queue status show that the request was invalid (new/destroyed queue suspend request, missing queue) or an error occurred (HWS in a fatal state so it can't suspend or resume queues). Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
69a8c3ae |
|
01-Sep-2022 |
Jonathan Kim <jonathan.kim@amd.com> |
drm/amdkfd: apply trap workaround for gfx11 Due to a HW bug, waves in only half the shader arrays can enter trap. When starting a debug session, relocate all waves to the first shader array of each shader engine and mask off the 2nd shader array as unavailable. When ending a debug session, re-enable the 2nd shader array per shader engine. User CU masking per queue cannot be guaranteed to remain functional if requested during debugging (e.g. user cu mask requests only 2nd shader array as an available resource leading to zero HW resources available) nor can runtime be alerted of any of these changes during execution. Make user CU masking and debugging mutual exclusive with respect to availability. If the debugger tries to attach to a process with a user cu masked queue, return the runtime status as enabled but busy. If the debugger tries to attach and fails to reallocate queue waves to the first shader array of each shader engine, return the runtime status as enabled but with an error. In addition, like any other mutli-process debug supported devices, disable trap temporary setup per-process to avoid performance impact from setup overhead. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4504f143 |
|
30-Mar-2022 |
Jonathan Kim <jonathan.kim@amd.com> |
drm/amdgpu: setup hw debug registers on driver initialization Add missing debug trap registers references and initialize all debug registers on boot by clearing the hardware exception overrides and the wave allocation ID index. The debugger requires that TTMPs 6 & 7 save the dispatch ID to map waves onto dispatch during compute context inspection. In order to correctly set this up, set the special reserved CP bit by default whenever the MQD is initailized. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4050ff1 |
|
09-Feb-2023 |
Lijo Lazar <lijo.lazar@amd.com> |
drm/amdkfd: Use xcc mask for identifying xcc Instead of start xcc id and number of xcc per node, use the xcc mask which is the mask of logical ids of xccs belonging to a parition. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Le Ma <le.ma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c2d43918 |
|
09-Dec-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Setup current_logical_xcc_id in MQD Setup rolling current_logical_xcc_id in MQD for GFX9.4.3 to ensure each queue starts at a different place and prevent hotspotting issues. Also, remove updating current_logical_xcc_id during queue update. Suggested-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1526ec9a |
|
15-Feb-2022 |
David Belanger <david.belanger@amd.com> |
drm/amdkfd: EOP Removal - Handle size 0 correctly On GC 9.4.3, we are removing the EOP buffer. If we specify 0 for the size, CP_HQD_EOP_CONTROL ends up with incorrect value as order_size_2 calculations does not handle 0. Fix it by using zero for the MQD entry for EOP size 0. v2: Reworked code with a conditional assignment and fixed style issues. Signed-off-by: David Belanger <david.belanger@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7fe51e6f |
|
09-May-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Update context save handling for multi XCC setup (v2) Context save handling needs to be updated for a multi XCC setup: - On a multi XCC setup, KFD needs to report context save base address and size for each XCC in MQD. - Thunk will allocate a large context save area covering all XCCs which will be equal to: num_of_xccs in a partition * size of context save area for 1 XCC. However, it will report only the size of context save area for 1 XCC only in the ioctl call. - Driver then setups the MQD correctly using the size passed from Thunk and information about number of XCCs in a partition. - Update get_wave_state function to return context save area for all XCCs in the partition. v2: update the get_wave_state function for mqd manager v11 (Morris) Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e2069a7b |
|
09-May-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Add XCC instance to kgd2kfd interface (v3) Gfx 9 starts to have multiple XCC instances in one device. Add instance parameter to kgd2kfd functions where XCC instance was hard coded as 0. Also, update code to pass the correct instance number when running on a multi-XCC setup. v2: introduce the XCC instance to gfx v11 (Morris) v3: rebase (Alex) Signed-off-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3c8bdb51 |
|
09-May-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Add PM4 target XCC In a device that supports multiple XCCs, unlike AQL queues, the PM4 queue will be only processed in one XCC in the partitioning. This patch re-purposes the queue percentage variable in create queue and update queue ioctl for the user space to specify the target XCC. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2f77b9a2 |
|
09-May-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Update MQD management on multi XCC setup Update MQD management for both HIQ and user-mode compute queues on a multi XCC setup. MQDs needs to be allocated, initialized, loaded and destroyed for each XCC in the KFD node. v2: squash in fix "drm/amdkfd: Fix SDMA+HIQ HQD allocation on GFX9.4.3" Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Amber Lin <Amber.Lin@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8dc1db31 |
|
14-Sep-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Introduce kfd_node struct (v5) Introduce a new structure, kfd_node, which will now represent a compute node. kfd_node is carved out of kfd_dev structure. kfd_dev struct now will become the parent of kfd_node, and will store common resources such as doorbells, GTT sub-alloctor etc. kfd_node struct will store all resources specific to a compute node, such as device queue manager, interrupt handling etc. This is the first step in adding compute partition support in KFD. v2: introduce kfd_node struct to gc v11 (Hawking) v3: make reference to kfd_dev struct through kfd_node (Morris) v4: use kfd_node instead for kfd isr/mqd functions (Morris) v5: rebase (Alex) Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
cabbdea1 |
|
11-May-2023 |
Daniil Dulov <d.dulov@aladdin.ru> |
drm/amdkfd: Fix potential deallocation of previously deallocated memory. Pointer mqd_mem_obj can be deallocated in kfd_gtt_sa_allocate(). The function then returns non-zero value, which causes the second deallocation. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: d1f8f0d17d40 ("drm/amdkfd: Move non-sdma mqd allocation out of init_mqd") Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
83688771 |
|
23-Sep-2021 |
Amber Lin <Amber.Lin@amd.com> |
drm/amdkfd: Enable HW_UPDATE_RPTR on GC 9.4.3 GC 9.4.3 uses the hardware to update AQL queues read pointer, so remove CP_HQD_PQ_CONTROL__NO_UPDATE_RPTR_MASK flag from MQD if it's GC 9.4.3, and keep it for other existing gfx9 ASICs. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e5a6702e |
|
06-Dec-2021 |
Amber Lin <Amber.Lin@amd.com> |
drm/amdkfd: Set TG_CHUNK_SIZE for GC 9.4.3 On GC 9.4.3, DW 41 in MQD is repurposed as compute_tg_chunk_size for cooperative dispatch. When it's a AQL queue, set compute_tg_chunk_size as 1 to spread work groups evenly among XCCs. If it's PM4 queue, unset compute_tg_chunk_size to disable cooperative mode. v3: set compute_tg_chunk_size as 1 instead of #CUs per XCC v2: set compute_tg_chunk_size as #CUs per XCC instead of total wave slots per XCC Signed-off-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Sean Keely <Sean.Keely@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d87f36a0 |
|
10-Feb-2022 |
Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> |
drm/amdkfd: update SPDX license header Update the SPDX License header for all the KFD files. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a439b890 |
|
03-Feb-2022 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdkfd: Consolidate MQD manager functions A few MQD manager functions are duplicated for all versions of MQD manager. Remove this duplication by moving the common functions into kfd_mqd_manager.c file. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3a9822d7 |
|
25-Jan-2021 |
David Yat Sin <david.yatsin@amd.com> |
drm/amdkfd: CRIU checkpoint and restore queue control stack Checkpoint contents of queue control stacks on CRIU dump and restore them during CRIU restore. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: David Yat Sin <david.yatsin@amd.com> Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
42c6c482 |
|
24-Jan-2021 |
David Yat Sin <david.yatsin@amd.com> |
drm/amdkfd: CRIU checkpoint and restore queue mqds Checkpoint contents of queue MQD's on CRIU dump and restore them during CRIU restore. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: David Yat Sin <david.yatsin@amd.com> Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6bfc7c7e |
|
19-Oct-2021 |
Graham Sider <Graham.Sider@amd.com> |
drm/amdkfd: replace kgd_dev in various amgpu_amdkfd funcs Modified definitions: - amdgpu_amdkfd_submit_ib - amdgpu_amdkfd_set_compute_idle - amdgpu_amdkfd_have_atomics_support - amdgpu_amdkfd_flush_gpu_tlb_pasid - amdgpu_amdkfd_flush_gpu_tlb_pasid - amdgpu_amdkfd_gpu_reset - amdgpu_amdkfd_alloc_gtt_mem - amdgpu_amdkfd_free_gtt_mem - amdgpu_amdkfd_alloc_gws - amdgpu_amdkfd_free_gws - amdgpu_amdkfd_ras_poison_consumption_handler Signed-off-by: Graham Sider <Graham.Sider@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
420185fd |
|
15-Oct-2021 |
Graham Sider <Graham.Sider@amd.com> |
drm/amdkfd: replace kgd_dev in hqd/mqd kfd2kgd funcs Modified definitions: - hqd_load - hiq_mqd_load - hqd_sdma_load - hqd_dump - hqd_sdma_dump - hqd_is_occupied - hqd_destroy - hqd_sdma_is_occupied - hqd_sdma_destroy Signed-off-by: Graham Sider <Graham.Sider@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7c695a2c |
|
08-Oct-2021 |
Lang Yu <lang.yu@amd.com> |
drm/amdkfd: Remove cu mask from struct queue_properties(v2) Actually, cu_mask has been copied to mqd memory and does't have to persist in queue_properties. Remove it from queue_properties. And use struct mqd_update_info to store such properties, then pass it to update queue operation. v2: * Rename pqm_update_queue to pqm_update_queue_properties. * Rename struct queue_update_info to struct mqd_update_info. * Rename pqm_set_cu_mask to pqm_update_mqd. Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Lang Yu <lang.yu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c6e559eb |
|
07-Oct-2021 |
Lang Yu <lang.yu@amd.com> |
drm/amdkfd: Add an optional argument into update queue operation(v2) Currently, queue is updated with data in queue_properties. And all allocated resource in queue_properties will not be freed until the queue is destroyed. But some properties(e.g., cu mask) bring some memory management headaches(e.g., memory leak) and make code complex. Actually they have been copied to mqd and don't have to persist in queue_properties. Add an argument into update queue to pass such properties, then we can remove them from queue_properties. v2: Don't use void *. Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Lang Yu <lang.yu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
51a0f459 |
|
07-Jul-2020 |
Oak Zeng <Oak.Zeng@amd.com> |
drm/amdkfd: Check HIQ's MQD for queue preemption status MEC firmware can silently fail the queue preemption request without time out. In this case, HIQ's MQD's queue_doorbell_id will be set. Check this field to see whether last queue preemption was successful or not. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Suggested-by: Jay Cornwall <Jay.Cornwall@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5d7c6f18 |
|
29-Jun-2020 |
Joseph Greathouse <Joseph.Greathouse@amd.com> |
drm/amdkfd: Update hardware scheduling time quanta Update PROCESS_QUANTUM, the time the hardware scheduler allows processes to run before switching to other processes when it becomes over-subscribed. Increase this to 10ms, to allow processes to better amortize their task switch times. Update HQD Quantum, the amount of time that an active queue stays attached to the CP before we forcibly switch it for another active queue for fairness. Setting these so that HQD < PROCESS makes it easier to ensure that we get fairness when we have multiple active queues on the device. Otherwise we may start process-swapping before we get to all the queues in a CP. Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2f6ae2de |
|
04-Mar-2020 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: Add more comments on GFX9 user CP queue MQD workaround Because too many things are involved in this workaround, we need more comments to avoid pitfalls. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
35cd89d5 |
|
25-Dec-2019 |
Aaron Liu <aaron.liu@amd.com> |
drm/amdkfd: use kiq to load the mqd of hiq queue for gfx v9 (v6) There is an issue that CP will check the HIQ queue to be configured and mapped with KIQ ring, otherwise, it will be unable to read back the secure buffer while the gfxoff is enabled even with trusted IP blocks. v1 -> v2: - Fix to remove surplus set_resources packets. - Fill the whole configuration in MQD. - Change the author as Aaron because he addressed the key point of this issue. - Add kiq ring lock. v2 -> v3: - Free the lock while in error return case. - Remove the programming only needed by the queue is unmapped. v3 -> v4: - Remove doorbell programming because it's used for restarting queue. - Remove CP scheduler programming because map_queue packet will handle this. v4 -> v5: - Remove cp_hqd_active because mec ucode will enable it while use map_queues. - Revise goto out_unlock. - Correct the right doorbell offset for HIQ that kfd driver assigned in the packet. v5 -> v6: - Merge Arcturus fix into this patch because it will get oops in Arcturus platform. Reported-by: Lisa Saturday <Lisa.Saturday@amd.com> Signed-off-by: Aaron Liu <aaron.liu@amd.com> Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-and-Tested-by: Aaron Liu <aaron.liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c8c50a7e |
|
08-Nov-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: Remove duplicate functions update_mqd_hiq() The functions are the same as update_mqd(). Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Zhan Liu <zhan.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7633c5e0 |
|
08-Nov-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: DIQ should not use HIQ way to allocate memory In the mqd_diq_sdma buffer, there should be only one HIQ mqd. All DIQs should be allocated somewhere else using the regular way. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d7c0b047 |
|
08-Nov-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: Delete KFD_MQD_TYPE_COMPUTE It is the same as KFD_MQD_TYPE_CP, so delete it. As a result, we will have one less mqd mananger per device. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8c27a0c4 |
|
08-Nov-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: Stop using GFP_NOIO explicitly for two places Adapt the change from: 1cd106ecfc1f04 ("drm/amdkfd: Stop using GFP_NOIO explicitly") Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bc05b0ec |
|
08-Nov-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdkfd: Fix a bug when calculating save_area_used_size workgroup context data writes from m->cp_hqd_cntl_stack_size, so we should deduct it when calculating the used size. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5145d57e |
|
18-Jul-2019 |
Jay Cornwall <Jay.Cornwall@amd.com> |
drm/amdkfd: Extend CU mask to 8 SEs (v3) Following bitmap layout logic introduced by: "drm/amdgpu: support get_cu_info for Arcturus". v2: squash in fixup for gfx_v9_0.c (Alex) v3: squash in debug print output fix Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8636e53c |
|
03-Jun-2019 |
Oak Zeng <Oak.Zeng@amd.com> |
drm/amdkfd: Separate mqd allocation and initialization Introduce a new mqd allocation interface and split the original init_mqd function into two functions: allocate_mqd and init_mqd. Also renamed uninit_mqd to free_mqd. This is preparation work to fix a circular lock dependency. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
77866d54 |
|
19-Jun-2018 |
Jay Cornwall <Jay.Cornwall@amd.com> |
drm/amdkfd: Implement queue priority controls for gfx9 Ported from gfx8, no changes in register setup. Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bb2d2128 |
|
01-May-2019 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdkfd: Simplify eviction state logic Always mark evicted queues with q->properties.is_evicted = true, even queues that are inactive for other reason. This simplifies maintaining the eviction state as it doesn't require updating is_evicted when other queue activation conditions change. On the other hand, we now need to check those other queue activation conditions whenever an evicted queues is restored. To minimize code duplication, move the queue activation check into a macro so it can be maintained in one central place. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Philip Cox <Philip.Cox@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0803e7a9 |
|
27-Nov-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdkfd: Allocate hiq and sdma mqd from mqd trunk Instead of allocat hiq and sdma mqd from sub-allocator, allocate them from a mqd trunk pool. This is done for all asics Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d1f8f0d1 |
|
27-Nov-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdkfd: Move non-sdma mqd allocation out of init_mqd This is preparation work to introduce more mqd allocation scheme Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e73390d1 |
|
27-Nov-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdkfd: Fix a potential memory leak Free mqd_mem_obj it GTT buffer allocation for MQD+control stack fails. Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6c6cde55 |
|
05-Dec-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdkfd: Add mqd size in mqd manager struct Also initialize mqd size on mqd manager initialization Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
59f650a0 |
|
03-Dec-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdkfd: Introduce DIQ type mqd manager With introduction of new mqd allocation scheme for HIQ, DIQ and HIQ use different mqd allocation scheme, DIQ can't reuse HIQ mqd manager Signed-off-by: Oak Zeng <ozeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7cd52c91 |
|
18-Oct-2018 |
Amber Lin <Amber.Lin@amd.com> |
drm/amdkfd: Add proper prefix to functions Add amdgpu_amdkfd_ prefix to amdgpu functions served for amdkfd usage. v2: fix indentation Signed-off-by: Amber Lin <Amber.Lin@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5b87245f |
|
16-Oct-2018 |
Amber Lin <Amber.Lin@amd.com> |
drm/amdkfd: Simplify kfd2kgd interface After amdkfd module is merged into amdgpu, KFD can call amdgpu directly and no longer needs to use the function pointer. Replace those function pointers with functions if they are not ASIC dependent. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5df099e8 |
|
02-May-2017 |
Jay Cornwall <Jay.Cornwall@amd.com> |
drm/amdkfd: Add wavefront context save state retrieval ioctl Wavefront context save data is of interest to userspace clients for debugging static wavefront state. The MQD contains two parameters required to parse the control stack and the control stack itself is kept in the MQD from gfx9 onwards. Add an ioctl to fetch the context save area and control stack offsets and to copy the control stack to a userspace address if it is kept in the MQD. Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
15426dbb |
|
12-Sep-2018 |
Yong Zhao <yong.zhao@amd.com> |
drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9 CWSR fails on Raven if the control stack is MTYPE_UC, which is used for regular GART mappings. As a workaround we map it using MTYPE_NC. The MEC firmware expects the control stack at one page offset from the start of the MQD so it is part of the MQD allocation on GFXv9. AMDGPU added a memory allocation flag just for this purpose. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Yong Zhao <yong.zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
39e7f331 |
|
14-Jul-2018 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdkfd: Add CU-masking ioctl to KFD CU-masking allows a KFD client to control the set of CUs used by a user mode queue for executing compute dispatches. This can be used for optimizing the partitioning of the GPU and minimize conflicts between concurrent tasks. Signed-off-by: Flora Cui <flora.cui@amd.com> Signed-off-by: Kent Russell <kent.russell@amd.com> Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
|
#
1cd106ec |
|
11-Jul-2018 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdkfd: Stop using GFP_NOIO explicitly This is no longer needed with the memalloc_nofs_save/restore in dqm_lock/unlock. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
|
#
b91d43dd |
|
10-Apr-2018 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdkfd: Add GFXv9 MQD manager Signed-off-by: John Bridgman <john.bridgman@amd.com> Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
|