summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
AgeCommit message (Collapse)AuthorFilesLines
2024-03-27drm/amdkfd: Reset GPU on queue preemption failureHarish Kasiviswanathan1-0/+1
Currently, with F32 HWS GPU reset is only when unmap queue fails. However, if compute queue doesn't repond to preemption request in time unmap will return without any error. In this case, only preemption error is logged and Reset is not triggered. Call GPU reset in this case also. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-03-20drm/amdkfd: Check preemption status on all XCDsMukul Joshi1-2/+1
This patch adds the following functionality: - Check the queue preemption status on all XCDs in a partition for GFX 9.4.3. - Update the queue preemption debug message to print the queue doorbell id for which preemption failed. - Change the signature of check preemption failed function to return a bool instead of uint32_t and pass the MQD manager as an argument. Suggested-by: Jay Cornwall <jay.cornwall@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>
2024-03-20drm/amdkfd: Rename read_doorbell_id in MQD functionsMukul Joshi1-1/+1
Rename read_doorbell_id function to a more meaningful name, implying what it is used for. No functional change. Suggested-by: Jay Cornwall <jay.cornwall@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>
2024-02-26drm/amdkfd: Skip packet submission on fatal errorLijo Lazar1-0/+4
If fatal error is detected, packet submission won't go through. Return error in such cases. Also, avoid waiting for fence when fatal error is detected. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Asad Kamal <asad.kamal@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-10-10drm/amdkfd: get doorbell's absolute offset based on the db_sizeArvind Yadav1-1/+2
Here, Adding db_size in byte to find the doorbell's absolute offset for both 32-bit and 64-bit doorbell sizes. So that doorbell offset will be aligned based on the doorbell size. v2: - Addressed the review comment from Felix. v3: - Adding doorbell_size as parameter to get db absolute offset. v4: Squash the two patches into one. Cc: Christian Koenig <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-09-20drm/amdkfd: Use gpu_offset for user queue's wptrYuBiao Wang1-1/+1
Directly use tbo's start address will miss the domain start offset. Need to use gpu_offset instead. Signed-off-by: YuBiao Wang <YuBiao.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-09-20drm/amdkfd: fix add queue process context clear without runtime enableJonathan Kim1-2/+4
There are cases where HSA runtime is not enabled through the AMDKFD_IOC_RUNTIME_ENABLE call when adding queues and the MES ADD_QUEUE API should clear the MES process context instead of SET_SHADER_DEBUGGER. Such examples are legacy HSA runtime builds that do not support the current exception handling and running KFD tests. The only time ADD_QUEUE.skip_process_ctx_clear is required is for debugger use cases where a debugged process is always runtime enabled when adding a queue. Tested-by: Shikai Guo <shikai.guo@amd.com> Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Acked-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Eric Huang <jinhuieric.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-09-12drm/amdgpu: Rename KGD_MAX_QUEUES to AMDGPU_MAX_QUEUESMukul Joshi1-2/+2
Rename KGD_MAX_QUEUES to AMDGPU_MAX_QUEUES to conform with the naming convention followed in amdgpu_gfx.h. No functional change. 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>
2023-09-12drm/amdkfd: Fix reg offset for setting CWSR grace periodMukul Joshi1-2/+1
This patch fixes the case where the code currently passes absolute register address and not the reg offset, which HWS expects, when sending the PM4 packet to set/update CWSR grace period. Additionally, cleanup the signature of build_grace_period_packet_info function as it no longer needs the inst parameter. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-30drm/amdkfd: Replace pr_err with dev_errAsad Kamal1-46/+70
Replace pr_err with dev_err to show the bus-id of failing device with kfd queue errors Signed-off-by: Asad Kamal <asad.kamal@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-16drm/amdkfd: fix double assign skip process context clearJonathan Kim1-1/+0
Remove redundant assignment when skipping process ctx clear. 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>
2023-08-16drm/amdkfd: Use memdup_user() rather than duplicating its implementationAtul Raut1-9/+1
To prevent its redundant implementation and streamline code, use memdup_user. This fixes warnings reported by Coccinelle: ./drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c:2811:13-20: WARNING opportunity for memdup_user Signed-off-by: Atul Raut <rauji.raut@gmail.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>
2023-08-11drm/amdkfd: rename device_queue_manager_init_v10_navi10()Alex Deucher1-1/+1
Drop the navi10 in the name for consistency with other families. All gfx10 parts use the same implementation. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Tested-by: Mike Lothian <mike@fireburn.co.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-11drm/amdkfd: drop IOMMUv2 supportAlex Deucher1-2/+2
Now that we use the dGPU path for all APUs, drop the IOMMUv2 support. v2: drop the now unused queue manager functions for gfx7/8 APUs Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Tested-by: Mike Lothian <mike@fireburn.co.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-11drm/amdkfd: disable IOMMUv2 support for KV/CZAlex Deucher1-7/+1
Use the dGPU path instead. There were a lot of platform issues with IOMMU in general on these chips due to windows not enabling IOMMU at the time. The dGPU path has been used for a long time with newer APUs and works fine. This also paves the way to simplify the driver significantly. v2: use the dGPU queue manager functions Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Tested-by: Mike Lothian <mike@fireburn.co.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-08drm/amdgpu: use doorbell mgr for kfd process doorbellsShashank Sharma1-4/+4
This patch: - adds a doorbell object in kfd pdd structure. - allocates doorbells for a process while creating its queue. - frees the doorbells with pdd destroy. - moves doorbell bitmap init function to kfd_doorbell.c PS: This patch ensures that we don't break the existing KFD functionality, but now KFD userspace library should also create doorbell pages as AMDGPU GEM objects using libdrm functions in userspace. The reference code for the same is available with AMDGPU Usermode queue libdrm MR. Once this is done, we will not need to create process doorbells in kernel. V2: - Do not use doorbell wrapper API, use amdgpu_bo_create_kernel instead (Alex). - Do not use custom doorbell structure, instead use separate variables for bo and doorbell_bitmap (Alex) V3: - Do not allocate doorbell page with PDD, delay doorbell process page allocation until really needed (Felix) Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felilx.Kuehling@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-07-27drm/amdkfd: fix and enable ttmp setup for gfx11Jonathan Kim1-0/+2
The MES cached process context must be cleared on adding any queue for the first time. For proper debug support, the MES will clear it's cached process context on the first call to SET_SHADER_DEBUGGER. This allows TTMPs to be pesistently enabled in a safe manner. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Eric Huang <jinhuieric@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-07-25drm/amdkfd: enable cooperative groups for gfx11Jonathan Kim1-5/+2
MES can concurrently schedule queues on the device that require exclusive device access if marked exclusively_scheduled without the requirement of GWS. Similar to the F32 HWS, MES will manage quality of service for these queues. Use this for cooperative groups since cooperative groups are device occupancy limited. Since some GFX11 devices can only be debugged with partial CUs, do not allow the debugging of cooperative groups on these devices as the CU occupancy limit will change on attach. In addition, zero initialize the MES add queue submission vector for MES initialization tests as we do not want these to be cooperative dispatches. 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>
2023-07-21drm/amdkfd: fix trap handling work around for debuggingJonathan Kim1-4/+2
Update the list of devices that require the cwsr trap handling workaround for debugging use cases. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Acked-by: Ruili Ji <ruili.ji@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-07-12drm/amdkfd: Update CWSR grace period for GFX9.4.3Mukul Joshi1-1/+21
For GFX9.4.3, setup a reduced default CWSR grace period equal to 1000 cycles instead of 64000 cycles. 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>
2023-07-12drm/amdkfd: add kfd2kgd debugger callbacks for GC v9.4.3Eric Huang1-1/+2
Implement the similarities as GC v9.4.2, and the difference for GC v9.4.3 HW spec, i.e. xcc instance. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-15drm/amdkfd: decrement queue count on mes queue destroyJonathan Kim1-1/+1
Queue count should decrement on queue destruction regardless of HWS support type. 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>
2023-06-15drm/amdkfd: To enable traps for GC_11_0_4 and upRuili Ji1-2/+2
Flag trap_en should be enabled for trap handler. Signed-off-by: Ruili Ji <ruiliji2@amd.com> Signed-off-by: Aaron Liu <aaron.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: fix and enable debugging for gfx11Jonathan Kim1-2/+1
There are a couple of fixes required to enable gfx11 debugging. First, ADD_QUEUE.trap_en is an inappropriate place to toggle a per-process register so move it to SET_SHADER_DEBUGGER.trap_en. When ADD_QUEUE.skip_process_ctx_clear is set, MES will prioritize the SET_SHADER_DEBUGGER.trap_en setting. Second, to preserve correct save/restore priviledged wave states in coordination with the trap enablement setting, resume suspended waves early in the disable call. 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>
2023-06-09drm/amdkfd: Fix reserved SDMA queues handlingMukul Joshi1-5/+5
This patch fixes a regression caused by a bad merge where the handling of reserved SDMA queues was accidentally removed. With the fix, the reserved SDMA queues are again correctly marked as unavailable for allocation. Fixes: a805889a1531 ("drm/amdkfd: Update SDMA queue management for GFX9.4.3") 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>
2023-06-09drm/amdkfd: add debug queue snapshot operationJonathan Kim1-0/+36
Allow the debugger to get a snapshot of a specified number of queues containing various queue property information that is copied to the debugger. Since the debugger doesn't know how many queues exist at any given time, allow the debugger to pass the requested number of snapshots as 0 to get the actual number of potential snapshots to use for a subsequent snapshot request for actual information. To prevent future ABI breakage, pass in the requested entry_size. The KFD will return it's own entry_size in case the debugger still wants log the information in a core dump on sizing failure. Also allow the debugger to clear exceptions when doing a snapshot. 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>
2023-06-09drm/amdkfd: add debug suspend and resume process queues operationJonathan Kim1-4/+443
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>
2023-06-09drm/amdkfd: apply trap workaround for gfx11Jonathan Kim1-0/+7
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>
2023-06-09drm/amdgpu: prepare map process for multi-process debug devicesJonathan Kim1-0/+51
Unlike single process debug devices, multi-process debug devices allow debug mode setting per-VMID (non-device-global). Because the HWS manages PASID-VMID mapping, the new MAP_PROCESS API allows the KFD to forward the required SPI debug register write requests. To request a new debug mode setting change, the KFD must be able to preempt all queues then remap all queues with these new setting requests for MAP_PROCESS to take effect. Note that by default, trap enablement in non-debug mode must be disabled for performance reasons for multi-process debug devices due to setup overhead in FW. 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>
2023-06-09drm/amdkfd: prepare map process for single process debug devicesJonathan Kim1-0/+93
Older HW only supports debugging on a single process because the SPI debug mode setting registers are device global. The HWS has supplied a single pinned VMID (0xf) for MAP_PROCESS for debug purposes. To pin the VMID, the KFD will remove the VMID from the HWS dynamic VMID allocation via SET_RESOUCES so that a debugged process will never migrate away from its pinned VMID. The KFD is responsible for reserving and releasing this pinned VMID accordingly whenever the debugger attaches and detaches respectively. 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>
2023-06-09drm/amdgpu: add configurable grace period for unmap queuesJonathan Kim1-18/+45
The HWS schedule allows a grace period for wave completion prior to preemption for better performance by avoiding CWSR on waves that can potentially complete quickly. The debugger, on the other hand, will want to inspect wave status immediately after it actively triggers preemption (a suspend function to be provided). To minimize latency between preemption and debugger wave inspection, allow immediate preemption by setting the grace period to 0. Note that setting the preepmtion grace period to 0 will result in an infinite grace period being set due to a CP FW bug so set it to 1 for now. 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>
2023-06-09drm/amdkfd: prepare per-process debug enable and disableJonathan Kim1-6/+20
The ROCm debugger will attach to a process to debug by PTRACE and will expect the KFD to prepare a process for the target PID, whether the target PID has opened the KFD device or not. This patch is to explicity handle this requirement. Further HW mode setting and runtime coordination requirements will be handled in following patches. In the case where the target process has not opened the KFD device, a new KFD process must be created for the target PID. The debugger as well as the target process for this case will have not acquired any VMs so handle process restoration to correctly account for this. To coordinate with HSA runtime, the debugger must be aware of the target process' runtime enablement status and will copy the runtime status information into the debugged KFD process for later query. On enablement, the debugger will subscribe to a set of exceptions where each exception events will notify the debugger through a pollable FIFO file descriptor that the debugger provides to the KFD to manage. Finally on process termination of either the debugger or the target, debugging must be disabled if it has not been done so. 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>
2023-06-09drm/amdkfd: Fix MEC pipe interrupt enablementLijo Lazar1-3/+4
for_each_inst modifies xcc_mask and therefore the loop doesn't initialize properly interrupts on all pipes. Keep looping through xcc as the outer loop to fix this issue. Fixes: c4050ff1a43e ("drm/amdkfd: Use xcc mask for identifying xcc") Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Use xcc mask for identifying xccLijo Lazar1-42/+44
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>
2023-06-09drm/amdkfd: Fix SDMA in CPX modeMukul Joshi1-4/+15
When creating a user-mode SDMA queue, CP FW expects driver to use/set virtual SDMA engine id in MAP_QUEUES packet instead of using the physical SDMA engine id. Each partition node's virtual SDMA number should start from 0. However, when allocating doorbell for the queue, KFD needs to allocate the doorbell from doorbell space corresponding to the physical SDMA engine id, otherwise the hwardware will not see the doorbell press. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Update SDMA queue management for GFX9.4.3Mukul Joshi1-32/+27
This patch updates SDMA queue management for multi XCC in GFX9.4.3. - Allocate/deallocate SDMA queues from the correct SDMA engines based on the partition mode. - Updates the kgd2kfd interface to fetch the correct SDMA register addresses. - It also fixes dumping correct SDMA queue info in debugfs. v2: squash in fix "drm/amdkfd: Fix XGMI SDMA user-mode queue allocation" 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>
2023-06-09drm/amdkfd: Call DQM stop during DQM uninitializeMukul Joshi1-0/+8
During DQM tear down, call DQM stop to unitialize HIQ and associated memory allocated during packet manager init. 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>
2023-06-09drm/amdkfd: Update context save handling for multi XCC setup (v2)Mukul Joshi1-2/+2
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>
2023-06-09drm/amdkfd: Add XCC instance to kgd2kfd interface (v3)Mukul Joshi1-36/+67
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>
2023-06-09drm/amdkfd: Update MQD management on multi XCC setupMukul Joshi1-1/+2
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>
2023-06-09drm/amdkfd: Add spatial partitioning support in KFDMukul Joshi1-1/+1
This patch introduces multi-partition support in KFD. This patch includes: - Support for maximum 8 spatial partitions in KFD. - Initialize one HIQ per partition. - Management of VMID range depending on partition mode. - Management of doorbell aperture space between all partitions. - Each partition does its own queue management, interrupt handling, SMI event reporting. - IOMMU, if enabled with multiple partitions, will only work on first partition. - SPM is only supported on the first partition. - Currently, there is no support for resetting individual partitions. All partitions will reset together. 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>
2023-06-09drm/amdkfd: Introduce kfd_node struct (v5)Mukul Joshi1-50/+50
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>
2023-02-24drm/amdkfd: To fix sdma page fault issue for GC 11Ruili Ji1-2/+3
For the MQD memory, KMD would always allocate 4K memory, and mes scheduler would write to the end of MQD for unmap flag. Signed-off-by: Ruili Ji <ruiliji2@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-01-11drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on mGPUEric Huang1-1/+1
The point bo->kfd_bo is NULL for queue's write pointer BO when creating queue on mGPU. To avoid using the pointer fixes the error. Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-09-30drm/amdkfd: Fix UBSAN shift-out-of-bounds warningFelix Kuehling1-24/+21
This was fixed in initialize_cpsch before, but not in initialize_nocpsch. Factor sdma bitmap initialization into a helper function to apply the correct implementation in both cases without duplicating it. v2: Added a range check Reported-by: Ellis Michael <ellis@ellismichael.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Graham Sider <Graham.Sider@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-09-29drm/amdgpu: pass queue size and is_aql_queue to MESGraham Sider1-0/+2
Update mes_v11_api_def.h add_queue API with is_aql_queue parameter. Also re-use gds_size for the queue size (unused for KFD). MES requires the queue size in order to compute the actual wptr offset within the queue RB since it increases monotonically for AQL queues. v2: Make is_aql_queue assign clearer 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>
2022-07-07drm/amdgpu: Fix one list corruption when create queue failsxinhui pan1-6/+5
Queue would be freed when create_queue_cpsch fails So lets do queue cleanup otherwise various list and memory issues happen. Signed-off-by: xinhui pan <xinhui.pan@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-06-28Revert "drm/amdkfd: Free queue after unmap queue success"Philip Yang1-17/+11
This reverts commit ab8529b0cdb271d9b222cbbddb2641f3fca5df8f. This causes KFDTest KFDMemoryTest.MemoryRegister test failed on gfx9. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-06-28drm/amdgpu: add mc wptr addr support for mesJack Xiao1-3/+3
MES requires mc wptr address for usermode queues. Export bo gart address for mc wptr address. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-06-24drm/amdgpu: Update mes_v11_api_def.hGraham Sider1-0/+2
Update MES API to support oversubscription without aggregated doorbell for usermode queues. v2: Change oversubscription_no_aggregated_en to is_kfd_process (align with MES) Signed-off-by: Graham Sider <Graham.Sider@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-28 08:12:20 +0300