kernel/linux.git/drivers/gpu/drm/amd/amdkfd, branch v4.19.77

drm/amdkfd: Add missing Polaris10 ID

2019-09-16T06:22:14+00:00

[ Upstream commit 0a5a9c276c335870a1cecc4f02b76d6d6f663c8b ] This was added to amdgpu but was missed in amdkfd Signed-off-by: Kent Russell Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.rg Signed-off-by: Sasha Levin

drm/amdkfd: Fix sdma queue map issue

2019-07-31T05:26:58+00:00

[ Upstream commit 065e4bdfa1f3ab2884c110394d8b7e7ebe3b988c ] Previous codes assumes there are two sdma engines. This is not true e.g., Raven only has 1 SDMA engine. Fix the issue by using sdma engine number info in device_info. Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Fix a potential memory leak

2019-07-31T05:26:58+00:00

[ Upstream commit e73390d181103a19e1111ec2f25559a0570e9fe0 ] Free mqd_mem_obj it GTT buffer allocation for MQD+control stack fails. Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: use init_mqd function to allocate object for hid_mqd (CI)

2019-04-20T07:16:04+00:00

[ Upstream commit cac734c2dbd2514f14c8c6a17caba1990d83bf1d ] if use the legacy method to allocate object, when mqd_hiq need to run uninit code, it will be cause WARNING call trace. eg: (s3 suspend test) [ 34.918944] Call Trace: [ 34.918948] [] dump_stack+0x19/0x1b [ 34.918950] [] __warn+0xd8/0x100 [ 34.918951] [] warn_slowpath_null+0x1d/0x20 [ 34.918991] [] uninit_mqd_hiq_sdma+0x4e/0x50 [amdgpu] [ 34.919028] [] uninitialize+0x37/0xe0 [amdgpu] [ 34.919064] [] kernel_queue_uninit+0x16/0x30 [amdgpu] [ 34.919086] [] pm_uninit+0x12/0x20 [amdgpu] [ 34.919107] [] stop_nocpsch+0x15/0x20 [amdgpu] [ 34.919129] [] kgd2kfd_suspend.part.4+0x2e/0x50 [amdgpu] [ 34.919150] [] kgd2kfd_suspend+0x17/0x20 [amdgpu] [ 34.919171] [] amdgpu_amdkfd_suspend+0x1a/0x20 [amdgpu] [ 34.919187] [] amdgpu_device_suspend+0x88/0x3a0 [amdgpu] [ 34.919189] [] ? enqueue_entity+0x2ef/0xbe0 [ 34.919205] [] amdgpu_pmops_suspend+0x20/0x30 [amdgpu] [ 34.919207] [] pci_pm_suspend+0x6f/0x150 [ 34.919208] [] ? pci_pm_freeze+0xf0/0xf0 [ 34.919210] [] dpm_run_callback+0x46/0x90 [ 34.919212] [] __device_suspend+0xfb/0x2a0 [ 34.919213] [] async_suspend+0x1f/0xa0 [ 34.919214] [] async_run_entry_fn+0x3f/0x130 [ 34.919216] [] process_one_work+0x17f/0x440 [ 34.919217] [] worker_thread+0x126/0x3c0 [ 34.919218] [] ? manage_workers.isra.25+0x2a0/0x2a0 [ 34.919220] [] kthread+0xd1/0xe0 [ 34.919221] [] ? insert_kthread_work+0x40/0x40 [ 34.919222] [] ret_from_fork_nospec_begin+0x7/0x21 [ 34.919224] [] ? insert_kthread_work+0x40/0x40 [ 34.919224] ---[ end trace 38cd9f65c963adad ]--- Signed-off-by: Kevin Wang Reviewed-by: Oak Zeng Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Don't assign dGPUs to APU topology devices

2019-02-27T09:08:55+00:00

[ Upstream commit bbdf514fe5648566b0754476cbcb92ac3422dde2 ] dGPUs need their own topology devices. Don't assign them to APU topology devices with CPU cores. Bug: https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/issues/66 Signed-off-by: Felix Kuehling Tested-by: Elias Konstantinidis Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix interrupt spin lock

2019-01-26T08:32:33+00:00

[ Upstream commit 2383a767c0ca06f96534456d8313909017c6c8d0 ] Vega10 has multiple interrupt rings, so this can be called from multiple calles at the same time resulting in: [ 71.779334] ================================ [ 71.779406] WARNING: inconsistent lock state [ 71.779478] 4.19.0-rc1+ #44 Tainted: G W [ 71.779565] -------------------------------- [ 71.779637] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. [ 71.779740] kworker/6:1/120 [HC0[0]:SC0[0]:HE1:SE1] takes: [ 71.779832] 00000000ad761971 (&(&kfd->interrupt_lock)->rlock){?...}, at: kgd2kfd_interrupt+0x75/0x100 [amdgpu] [ 71.780058] {IN-HARDIRQ-W} state was registered at: [ 71.780115] _raw_spin_lock+0x2c/0x40 [ 71.780180] kgd2kfd_interrupt+0x75/0x100 [amdgpu] [ 71.780248] amdgpu_irq_callback+0x6c/0x150 [amdgpu] [ 71.780315] amdgpu_ih_process+0x88/0x100 [amdgpu] [ 71.780380] amdgpu_irq_handler+0x20/0x40 [amdgpu] [ 71.780409] __handle_irq_event_percpu+0x49/0x2a0 [ 71.780436] handle_irq_event_percpu+0x30/0x70 [ 71.780461] handle_irq_event+0x37/0x60 [ 71.780484] handle_edge_irq+0x83/0x1b0 [ 71.780506] handle_irq+0x1f/0x30 [ 71.780526] do_IRQ+0x53/0x110 [ 71.780544] ret_from_intr+0x0/0x22 [ 71.780566] cpuidle_enter_state+0xaa/0x330 [ 71.780591] do_idle+0x203/0x280 [ 71.780610] cpu_startup_entry+0x6f/0x80 [ 71.780634] start_secondary+0x1b0/0x200 [ 71.780657] secondary_startup_64+0xa4/0xb0 Fix this by always using irq save spin locks. Signed-off-by: Christian König Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: add new vega10 pci ids

2018-12-19T18:19:53+00:00

commit 756e16bf79f2815e7c83a04881b5545b55a99fd3 upstream. New vega10 ids. Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: Fix incorrect use of process->mm

2018-10-04T15:37:25+00:00

This mm_struct pointer should never be dereferenced. If running in a user thread, just use current->mm. If running in a kernel worker use get_task_mm to get a safe reference to the mm_struct. Reviewed-by: Oded Gabbay Acked-by: Christian König Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Fix ATS capablity was not reported correctly on some APUs

2018-09-20T15:25:23+00:00

Because CRAT_CU_FLAGS_IOMMU_PRESENT was not set in some BIOS crat, we need to workaround this. For future compatibility, we also overwrite the bit in capability according to the value of needs_iommu_device. Acked-by: Alex Deucher Signed-off-by: Yong Zhao Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9

2018-09-20T15:25:17+00:00

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 Signed-off-by: Yong Zhao Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher