aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
AgeCommit message (Collapse)AuthorFilesLines
2019-04-19drm/amdgpu: get_fw_version isn't ASIC specificAmber Lin1-0/+14
Method of getting firmware version is the same across ASICs, so remove them from ASIC-specific files and create one in amdgpu_amdkfd.c. This new created get_fw_version simply reads fw_version from adev->gfx than parsing the ucode header. Signed-off-by: Amber Lin <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-28Revert "drm/amdgpu: replace get_user_pages with HMM mirror helpers"Alex Deucher1-0/+1
This reverts commit 915d3eecfa23693bac9e54cdacf84fb4efdcc5c4. This depends on an HMM fix which is not upstream yet. Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdkfd: add RAS ECC event support (v3)Eric Huang1-0/+1
RAS ECC event will combine with GPU reset event, due to ECC interrupts are caused by uncorrectable error that triggers GPU reset. v2: Fix misleading-indentation warning v3: fix build with CONFIG_HSA_AMD disabled Signed-off-by: Eric Huang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: replace get_user_pages with HMM mirror helpersPhilip Yang1-1/+0
Use HMM helper function hmm_vma_fault() to get physical pages backing userptr and start CPU page table update track of those pages. Then use hmm_vma_range_done() to check if those pages are updated before amdgpu_cs_submit for gfx or before user queues are resumed for kfd. If userptr pages are updated, for gfx, amdgpu_cs_ioctl will restart from scratch, for kfd, restore worker is rescheduled to retry. HMM simplify the CPU page table concurrent update check, so remove guptasklock, mmu_invalidations, last_set_pages fields from amdgpu_ttm_tt struct. HMM does not pin the page (increase page ref count), so remove related operations like release_pages(), put_page(), mark_page_dirty(). Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-01-14drm/amdgpu: Remove kgd2kfd function pointersAmber Lin1-2/+1
kgd2kfd function pointers and global kgd2kfd pointer are no longer in use. Signed-off-by: Amber Lin <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-01-14drm/amdgpu: Relocate kgd2kfd function declarationAmber Lin1-1/+19
Since amdkfd is merged into amdgpu module and amdgpu can access amdkfd directly, move declaration of kgd2kfd functions from kfd_priv.h to amdgpu_amdkfd.h Signed-off-by: Amber Lin <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-12-07drm/amdkfd: Add DMABuf import functionalityFelix Kuehling1-0/+11
This is used for interoperability between ROCm compute and graphics APIs. It allows importing graphics driver BOs into the ROCm SVM address space for zero-copy GPU access. The API is split into two steps (query and import) to allow user mode to manage the virtual address space allocation for the imported buffer. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-12-07drm/amdgpu: Add KFD VRAM limit checkingFelix Kuehling1-1/+7
We don't want KFD processes evicting each other over VRAM usage. Therefore prevent overcommitting VRAM among KFD applications with a per-GPU limit. Also leave enough room for page tables on top of the application memory usage. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Eric Huang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-12-07drm/amdgpu: Workaround build failure due to trace conflictKuehling, Felix1-1/+0
Avoid including mmu_context.h in amdgpu_amdkfd.h since that may be included in other header files that define traces. This leads to conflicts due to traces defined in other headers included via mmu_context.h. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-11-05drm/amdkfd: Add proper prefix to functionsAmber Lin1-10/+10
Add amdgpu_amdkfd_ prefix to amdgpu functions served for amdkfd usage. v2: fix indentation Signed-off-by: Amber Lin <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-09-26drm/amd: Interface change to support 64 bit page_table_baseShaoyun Liu1-1/+1
amdgpu_gpuvm_get_process_page_dir should return the page table address in the format expected by the pm4_map_process packet for all ASIC generations. Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Alex Deucher <[email protected]>
2018-09-27BackMerge v4.19-rc5 into drm-nextDave Airlie1-1/+1
Sean Paul requested an -rc5 backmerge from some sun4i fixes. Signed-off-by: Dave Airlie <[email protected]>
2018-09-20drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9Yong Zhao1-1/+1
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 <[email protected]> Signed-off-by: Yong Zhao <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-09-10drm/amdgpu: get_hive_id from amdgpu side (v2)Shaoyun Liu1-0/+1
Retrieve hive_id from amdgpu device v2: compile fix Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-29drm/amdkfd: Release an acquired process vmOak Zeng1-0/+1
For compute vm acquired from amdgpu, vm.pasid is managed by kfd. Decouple pasid from such vm on process destroy to avoid duplicate pasid release. Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-29drm/amdgpu: Set pasid for compute vm (v2)Oak Zeng1-3/+3
To make a amdgpu vm to a compute vm, the old pasid will be freed and replaced with a pasid managed by kfd. Kfd can't reuse original pasid allocated by amdgpu because kfd uses different pasid policy with amdgpu. For example, all graphic devices share one same pasid in a process. v2: rebase (Alex) Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-16drm/amdgpu: Add kfd2kgd.set_compute_idle interfaceFelix Kuehling1-0/+1
This allows automatic switching to the compute power profile depending on compute activity. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Eric Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-07-11drm/amdgpu: Enable the gpu reset from KFDShaoyun Liu1-0/+2
Hook up the gpu_recover callback from KFD to amdgpu to enable handling of GPU hangs detected by KFD. Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-07-11drm/amdgpu: Call KFD reset handlers during GPU resetShaoyun Liu1-0/+4
Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-07-11drm/amdgpu: save vm fault information for amdkfdshaoyunl1-0/+3
amdgpu save the vm fault related information for KFD usage and keep the copy until KFD read it. Signed-off-by: shaoyun liu <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-05-18drm/amdgpu: conditionally compile amdgpu's amdkfd filesOded Gabbay1-6/+6
In case CONFIG_HSA_AMD is not chosen, there is no need to compile amdkfd files that reside inside amdgpu dirver. In addition, because amdkfd depends on x86_64 architecture and amdgpu is not, compiling amdkfd files under i386 architecture can cause compiler errors and warnings. This patch modifies amdgpu's makefile to build amdkfd files only if CONFIG_HSA_AMD is chosen. The only file to be compiled unconditionally is amdgpu_amdkfd.c There are stub functions that are compiled only if amdkfd is not compiled. In that case, calls from amdgpu driver proper will go to those functions instead of the real functions. v2: instead of using function pointers, use stub functions v3: initialize kgd2kfd to NULL in case amdkfd is not compiled Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-04-10drm/amdgpu: Add GFXv9 kfd2kgd interface functionsFelix Kuehling1-0/+1
Signed-off-by: John Bridgman <[email protected]> Signed-off-by: Shaoyun Liu <[email protected]> Signed-off-by: Jay Cornwall <[email protected]> Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-03-23drm/amdgpu: Add userptr support for KFDFelix Kuehling1-0/+11
This adds support for allocating, mapping, unmapping and freeing userptr BOs, and for handling MMU notifiers. v2: updated a comment Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-03-23drm/amdgpu: Add MMU notifier type for KFD userptrFelix Kuehling1-0/+1
This commit adds the notion of MMU notifier types GFX and HSA. GFX continues to work like MMU notifiers did before. HSA adds support for KFD userptr BOs. The implementation of KFD userptr eviction is a stub for now. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-03-15drm/amdgpu: Add kfd2kgd interface to acquire an existing VMFelix Kuehling1-0/+6
This allows acquiring an existing VM from a render node FD to use it for a compute process. Such VMs get destroyed when the original file descriptor is released. Added a callback from amdgpu_vm_fini to handle KFD VM destruction correctly in this case. v2: * Removed vm->vm_context check in amdgpu_amdkfd_gpuvm_destroy_cb, check vm->process_info earlier instead Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-03-15drm/amdgpu: Move KFD-specific fields into struct amdgpu_vmFelix Kuehling1-21/+0
Remove struct amdkfd_vm and move the fields into struct amdgpu_vm. This will allow turning a VM created by a DRM render node into a KFD VM. v2: Removed vm_context field Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-03-15drm/amdkfd: add missing include of mm.hOded Gabbay1-0/+1
This patch fixes kernel build in ARCH=frv Signed-off-by: Oded Gabbay <[email protected]>
2018-02-06drm/amdgpu: Add submit IB function for KFDFelix Kuehling1-0/+4
This can be used for flushing caches when not using the HWS. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-02-06drm/amdgpu: Add GPUVM memory management functions for KFDFelix Kuehling1-2/+89
v2: * Removed unused flags from struct kgd_mem * Updated some comments * Added a check to unmap_memory_from_gpu whether BO was mapped v3: add mutex_destroy in relevant places Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-02-06drm/amdgpu: Update kgd2kfd_shared_resources for dGPU supportFelix Kuehling1-0/+2
Add GPUVM size and DRM render node. Also add function to query the VMID mask to avoid hard-coding it in multiple places later. v2: cut off GPUVM size at the VA hole Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-02-06drm/amdgpu: Add KFD eviction fenceFelix Kuehling1-0/+15
This fence is used by KFD to keep memory resident while user mode queues are enabled. Trying to evict memory will trigger the enable_signaling callback, which starts a KFD eviction, which involves preempting user mode queues before signaling the fence. There is one such fence per process. v2: * Grab a reference to mm_struct * Dereference fence after NULL check * Simplify fence release, no need to signal without anyone waiting * Added signed-off-by Harish, who is the original author of this code v3: * update MAINTAINERS file * change amd_kfd_ prefix to amdkfd_ * remove useless initialization of variable to NULL v4: * set amdkfd_fence_ops to be static * Suggested by: Fengguang Wu <[email protected]> Signed-off-by: Harish Kasiviswanathan <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-12-08drm/amdgpu: Add support for reporting VRAM usageKent Russell1-0/+1
Add functions to report the vram_usage from the amdgpu_device Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-12-08drm/amdkfd: Remove deprecated get_vmem_sizeHarish Kasiviswanathan1-1/+0
Signed-off-by: Harish Kasiviswanathan <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-12-08drm/amdgpu: Implement get_local_mem_infoHarish Kasiviswanathan1-0/+2
Implement new kgd-kfd interface function get_local_mem_info. Signed-off-by: Harish Kasiviswanathan <[email protected]> Signed-off-by: Ben Goz <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-12-08drm/amdgpu: add amdgpu interface to query cu infoFlora Cui1-0/+1
Signed-off-by: Flora Cui <[email protected]> Signed-off-by: Harish Kasiviswanathan <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amd: Update MEC HQD loading code for KFDFelix Kuehling1-0/+16
Various bug fixes and improvements that accumulated over the last two years. Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu: Fix KFD initialization for multi-GPU systemsFelix Kuehling1-2/+0
kfd2kgd is device-specific, so it should not be a global variable. Merge amdgpu_amdkfd_load_interface and amdgpu_amdkfd_device_probe so that it's only needed as a local variable in one function. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-05-31drm/amdgpu: rename rdev to adevAndres Rodriguez1-7/+7
Rename straggler instances of r(adeon)dev to a(mdgpu)dev Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-27drm/amdgpu: Return -EPROBE_DEFER when amdkfd not loadedOded Gabbay1-1/+1
amdgpu must load only after amdkfd's loading has been completed. If that is not enforced, then amdgpu's call into amdkfd's functions will cause a kernel BUG. When amdgpu and amdkfd are built as kernel modules, that rule is enforced by the kernel's modules loading mechanism. When amdgpu and amdkfd are built inside the kernel image, that rule is enforced by ordering in the drm Makefile (amdkfd before amdgpu). Instead of using drm Makefile ordering, we can now use deferred loading as amdkfd now returns -EPROBE_DEFER in kgd2kfd_init() when it is not yet loaded. This patch defers amdgpu loading by propagating -EPROBE_DEFER to the kernel's drivers loading infrastructure. That will put amdgpu into the pending drivers list (see description in dd.c). Once amdkfd is loaded, a call to kgd2kfd_init() will return successfully and amdgpu will be able to load. Signed-off-by: Oded Gabbay <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-07-20drm/amdgpu: Add amdgpu <--> amdkfd gfx8 interfaceBen Goz1-0/+1
This patch adds the gfx8 interface file between amdgpu and amdkfd. This interface file is currently in use when running on a Carrizo-based system. The interface itself is represented by a pointer to struct kfd_dev. The pointer is located inside amdgpu_device structure. All the register accesses that amdkfd need are done using this interface. This allows us to avoid direct register accesses in amdkfd proper, while also allows us to avoid locking between amdkfd and amdgpu. The single exception is the doorbells that are used in both of the drivers. However, because they are located in separate pci bar pages, the danger of sharing registers between the drivers is minimal. Having said that, we are planning to move the doorbells as well to amdgpu. Signed-off-by: Ben Goz <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2015-07-20drm/amdgpu: Add H/W agnostic amdgpu <--> amdkfd interfaceOded Gabbay1-0/+64
This patch adds an interface file between amdgpu and amdkfd. This interface file is H/W agnostic, thus containing functions that operate the same for any AMD APU/GPU H/W generation. The functions in this interface mirror (some) of the functions in radeon_kfd.c (the radeon<-->amdkfd interface file). The main functions are: - amdgpu_amdkfd_init - initialize the amdkfd module - amdgpu_amdkfd_load_interface - load the H/W interface according to the currently probed device - amdgpu_amdkfd_device_probe - probe the device in amdkfd - amdgpu_amdkfd_device_init - initialize the device in amdkfd - amdgpu_amdkfd_interrupt - call the ISR of amdkfd - amdgpu_amdkfd_suspend - suspend callback from amdgpu - amdgpu_amdkfd_resume - resume callback from amdgpu This patch also modifies the relevant amdgpu files, to use this new interface. Signed-off-by: Oded Gabbay <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.