summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorDaniel Vetter <daniel.vetter@ffwll.ch>2017-11-21 11:33:10 +0100
committerDaniel Vetter <daniel.vetter@ffwll.ch>2017-11-21 14:17:56 +0100
commit70c5f93669249886b151812076509f30569aff80 (patch)
tree05dce785f3a70e022b91016c87e4092f143a2fef /drivers
parentc83ecfa5851f4d35be88f32dabb3a53f51cf5c32 (diff)
parentf150891fd9878ef0d9197c4e8451ce67c3bdd014 (diff)
Merge airlied/drm-next into drm-misc-next
Bake in the conflict between the drm_print.h extraction and the addition of DRM_DEBUG_LEASES since we lost it a few too many times. Also fix a new use of drm_plane_helper_check_state in msm to follow Ville's conversion in commit a01cb8ba3f6282934cff65e89ab36b18b14cbe27 Author: Ville Syrjälä <ville.syrjala@linux.intel.com> Date: Wed Nov 1 22:16:19 2017 +0200 drm: Move drm_plane_helper_check_state() into drm_atomic_helper.c Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/acpi/arm64/iort.c35
-rw-r--r--drivers/acpi/property.c29
-rw-r--r--drivers/android/binder.c112
-rw-r--r--drivers/android/binder_alloc.c42
-rw-r--r--drivers/android/binder_alloc.h1
-rw-r--r--drivers/ata/ahci.c5
-rw-r--r--drivers/ata/ata_piix.c1
-rw-r--r--drivers/ata/libata-core.c20
-rw-r--r--drivers/auxdisplay/charlcd.c11
-rw-r--r--drivers/auxdisplay/panel.c11
-rw-r--r--drivers/base/arch_topology.c12
-rw-r--r--drivers/base/cpu.c3
-rw-r--r--drivers/base/node.c12
-rw-r--r--drivers/base/platform.c3
-rw-r--r--drivers/base/power/domain_governor.c53
-rw-r--r--drivers/base/power/qos.c2
-rw-r--r--drivers/base/power/runtime.c2
-rw-r--r--drivers/base/power/sysfs.c25
-rw-r--r--drivers/base/property.c19
-rw-r--r--drivers/block/Kconfig2
-rw-r--r--drivers/block/nbd.c21
-rw-r--r--drivers/block/skd_main.c2
-rw-r--r--drivers/block/zram/zram_drv.c36
-rw-r--r--drivers/bus/mvebu-mbus.c2
-rw-r--r--drivers/clk/clk-bulk.c1
-rw-r--r--drivers/clk/rockchip/clk-rk3128.c12
-rw-r--r--drivers/clk/samsung/clk-exynos4.c15
-rw-r--r--drivers/clocksource/cs5535-clockevt.c3
-rw-r--r--drivers/cpuidle/governors/menu.c4
-rw-r--r--drivers/crypto/axis/artpec6_crypto.c4
-rw-r--r--drivers/crypto/stm32/stm32-hash.c15
-rw-r--r--drivers/dma-buf/sync_file.c17
-rw-r--r--drivers/dma/altera-msgdma.c41
-rw-r--r--drivers/dma/edma.c19
-rw-r--r--drivers/dma/ti-dma-crossbar.c3
-rw-r--r--drivers/firmware/efi/libstub/arm-stub.c3
-rw-r--r--drivers/firmware/efi/test/efi_test.c3
-rw-r--r--drivers/fpga/altera-cvp.c6
-rw-r--r--drivers/gpio/Kconfig3
-rw-r--r--drivers/gpio/gpio-omap.c24
-rw-r--r--drivers/gpio/gpiolib-acpi.c2
-rw-r--r--drivers/gpu/drm/Makefile2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/Makefile2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h41
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c161
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c56
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c22
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c23
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c16
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c225
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c106
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c178
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c63
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c13
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c22
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_job.c18
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c16
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.c14
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.h13
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c83
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c59
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c104
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h24
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c109
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h (renamed from drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.h)24
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c227
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h12
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.c61
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.h5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c109
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h191
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c94
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h17
-rw-r--r--drivers/gpu/drm/amd/amdgpu/ci_dpm.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cik_ih.c19
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cz_ih.c19
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_virtual.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c195
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c15
-rw-r--r--drivers/gpu/drm/amd/amdgpu/iceland_ih.c19
-rw-r--r--drivers/gpu/drm/amd/amdgpu/kv_dpm.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c44
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c44
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v10_0.c14
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v3_1.c14
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c20
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c21
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/si_dpm.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c24
-rw-r--r--drivers/gpu/drm/amd/amdgpu/tonga_ih.c19
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c515
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c16
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vega10_ih.c11
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vi.c22
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vid.h10
-rw-r--r--drivers/gpu/drm/amd/amdkfd/Kconfig2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c8
-rw-r--r--drivers/gpu/drm/amd/amdkfd/cik_int.h3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_chardev.c12
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c14
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device.c108
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c459
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h24
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c20
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c20
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_events.c615
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_events.h18
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c83
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c20
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c34
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c7
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c29
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_priv.h118
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process.c169
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c73
-rw-r--r--drivers/gpu/drm/amd/include/amd_shared.h109
-rw-r--r--drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h15
-rw-r--r--drivers/gpu/drm/amd/include/atombios.h1
-rw-r--r--drivers/gpu/drm/amd/include/cgs_common.h8
-rw-r--r--drivers/gpu/drm/amd/lib/Kconfig3
-rw-r--r--drivers/gpu/drm/amd/lib/chash.c4
-rw-r--r--drivers/gpu/drm/amd/powerplay/amd_powerplay.c283
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c103
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c1
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.c2489
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.h4
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c6
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c138
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.h2
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c55
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c60
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h1
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c8
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c35
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c4
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.h3
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h9
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/fiji_pwrvirus.h10299
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/hwmgr.h6
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/polaris10_pwrvirus.h11792
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/pp_instance.h3
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h7
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/smumgr.h5
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h5
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/Makefile6
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/ci_smc.c2753
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c2736
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/fiji_smc.c2486
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/fiji_smc.h53
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c2415
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.h9
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c2568
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c2491
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c2344
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c2262
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c48
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h4
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/tonga_smc.c3261
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/tonga_smc.h62
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c3117
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.h20
-rw-r--r--drivers/gpu/drm/amd/scheduler/gpu_scheduler.c47
-rw-r--r--drivers/gpu/drm/amd/scheduler/gpu_scheduler.h19
-rw-r--r--drivers/gpu/drm/ast/ast_mode.c2
-rw-r--r--drivers/gpu/drm/bochs/bochs_kms.c2
-rw-r--r--drivers/gpu/drm/cirrus/cirrus_mode.c2
-rw-r--r--drivers/gpu/drm/drm_atomic.c15
-rw-r--r--drivers/gpu/drm/drm_atomic_helper.c2
-rw-r--r--drivers/gpu/drm/drm_auth.c32
-rw-r--r--drivers/gpu/drm/drm_color_mgmt.c4
-rw-r--r--drivers/gpu/drm/drm_connector.c2
-rw-r--r--drivers/gpu/drm/drm_crtc.c8
-rw-r--r--drivers/gpu/drm/drm_crtc_internal.h1
-rw-r--r--drivers/gpu/drm/drm_dp_dual_mode_helper.c16
-rw-r--r--drivers/gpu/drm/drm_drv.c3
-rw-r--r--drivers/gpu/drm/drm_encoder.c7
-rw-r--r--drivers/gpu/drm/drm_framebuffer.c10
-rw-r--r--drivers/gpu/drm/drm_internal.h7
-rw-r--r--drivers/gpu/drm/drm_ioctl.c8
-rw-r--r--drivers/gpu/drm/drm_lease.c767
-rw-r--r--drivers/gpu/drm/drm_mode_config.c23
-rw-r--r--drivers/gpu/drm/drm_mode_object.c32
-rw-r--r--drivers/gpu/drm/drm_modeset_lock.c2
-rw-r--r--drivers/gpu/drm/drm_plane.c68
-rw-r--r--drivers/gpu/drm/drm_probe_helper.c2
-rw-r--r--drivers/gpu/drm/drm_property.c6
-rw-r--r--drivers/gpu/drm/drm_syncobj.c82
-rw-r--r--drivers/gpu/drm/drm_vblank.c457
-rw-r--r--drivers/gpu/drm/etnaviv/Kconfig2
-rw-r--r--drivers/gpu/drm/etnaviv/Makefile3
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_buffer.c36
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c15
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h6
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_drv.c43
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_drv.h6
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_gem.c19
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c69
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_gpu.c217
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_gpu.h13
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_iommu.c197
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_iommu.h7
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c120
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_mmu.c106
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_mmu.h36
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_perfmon.c495
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_perfmon.h49
-rw-r--r--drivers/gpu/drm/exynos/Kconfig1
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_crtc.c15
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_drv.c8
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_drv.h3
-rw-r--r--drivers/gpu/drm/exynos/exynos_hdmi.c310
-rw-r--r--drivers/gpu/drm/exynos/exynos_mixer.c460
-rw-r--r--drivers/gpu/drm/exynos/regs-hdmi.h8
-rw-r--r--drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c2
-rw-r--r--drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c3
-rw-r--r--drivers/gpu/drm/i915/Kconfig1
-rw-r--r--drivers/gpu/drm/i915/Makefile8
-rw-r--r--drivers/gpu/drm/i915/gvt/cfg_space.c30
-rw-r--r--drivers/gpu/drm/i915/gvt/cmd_parser.c40
-rw-r--r--drivers/gpu/drm/i915/gvt/execlist.c130
-rw-r--r--drivers/gpu/drm/i915/gvt/gtt.c5
-rw-r--r--drivers/gpu/drm/i915/gvt/gvt.c2
-rw-r--r--drivers/gpu/drm/i915/gvt/gvt.h14
-rw-r--r--drivers/gpu/drm/i915/gvt/handlers.c70
-rw-r--r--drivers/gpu/drm/i915/gvt/kvmgt.c44
-rw-r--r--drivers/gpu/drm/i915/gvt/mmio.c47
-rw-r--r--drivers/gpu/drm/i915/gvt/reg.h3
-rw-r--r--drivers/gpu/drm/i915/gvt/render.c2
-rw-r--r--drivers/gpu/drm/i915/gvt/sched_policy.c22
-rw-r--r--drivers/gpu/drm/i915/gvt/scheduler.c115
-rw-r--r--drivers/gpu/drm/i915/gvt/scheduler.h2
-rw-r--r--drivers/gpu/drm/i915/i915_debugfs.c638
-rw-r--r--drivers/gpu/drm/i915/i915_drv.c90
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h314
-rw-r--r--drivers/gpu/drm/i915/i915_gem.c583
-rw-r--r--drivers/gpu/drm/i915/i915_gem_clflush.c1
-rw-r--r--drivers/gpu/drm/i915/i915_gem_context.c123
-rw-r--r--drivers/gpu/drm/i915/i915_gem_dmabuf.c18
-rw-r--r--drivers/gpu/drm/i915/i915_gem_evict.c77
-rw-r--r--drivers/gpu/drm/i915/i915_gem_execbuffer.c29
-rw-r--r--drivers/gpu/drm/i915/i915_gem_fence_reg.c40
-rw-r--r--drivers/gpu/drm/i915/i915_gem_gtt.c614
-rw-r--r--drivers/gpu/drm/i915/i915_gem_gtt.h66
-rw-r--r--drivers/gpu/drm/i915/i915_gem_internal.c18
-rw-r--r--drivers/gpu/drm/i915/i915_gem_object.h42
-rw-r--r--drivers/gpu/drm/i915/i915_gem_render_state.c2
-rw-r--r--drivers/gpu/drm/i915/i915_gem_request.c52
-rw-r--r--drivers/gpu/drm/i915/i915_gem_request.h48
-rw-r--r--drivers/gpu/drm/i915/i915_gem_shrinker.c131
-rw-r--r--drivers/gpu/drm/i915/i915_gem_stolen.c21
-rw-r--r--drivers/gpu/drm/i915/i915_gem_tiling.c2
-rw-r--r--drivers/gpu/drm/i915/i915_gem_userptr.c144
-rw-r--r--drivers/gpu/drm/i915/i915_gemfs.c74
-rw-r--r--drivers/gpu/drm/i915/i915_gemfs.h34
-rw-r--r--drivers/gpu/drm/i915/i915_gpu_error.c43
-rw-r--r--drivers/gpu/drm/i915/i915_guc_submission.c476
-rw-r--r--drivers/gpu/drm/i915/i915_guc_submission.h80
-rw-r--r--drivers/gpu/drm/i915/i915_irq.c1093
-rw-r--r--drivers/gpu/drm/i915/i915_oa_cflgt2.c109
-rw-r--r--drivers/gpu/drm/i915/i915_oa_cflgt2.h34
-rw-r--r--drivers/gpu/drm/i915/i915_params.c207
-rw-r--r--drivers/gpu/drm/i915/i915_params.h85
-rw-r--r--drivers/gpu/drm/i915/i915_pci.c94
-rw-r--r--drivers/gpu/drm/i915/i915_perf.c18
-rw-r--r--drivers/gpu/drm/i915/i915_pvinfo.h1
-rw-r--r--drivers/gpu/drm/i915/i915_reg.h70
-rw-r--r--drivers/gpu/drm/i915/i915_suspend.c2
-rw-r--r--drivers/gpu/drm/i915/i915_sw_fence.c45
-rw-r--r--drivers/gpu/drm/i915/i915_sysfs.c76
-rw-r--r--drivers/gpu/drm/i915/i915_trace.h116
-rw-r--r--drivers/gpu/drm/i915/i915_utils.h18
-rw-r--r--drivers/gpu/drm/i915/i915_vgpu.h6
-rw-r--r--drivers/gpu/drm/i915/i915_vma.c144
-rw-r--r--drivers/gpu/drm/i915/i915_vma.h49
-rw-r--r--drivers/gpu/drm/i915/intel_audio.c7
-rw-r--r--drivers/gpu/drm/i915/intel_bios.c233
-rw-r--r--drivers/gpu/drm/i915/intel_breadcrumbs.c20
-rw-r--r--drivers/gpu/drm/i915/intel_cdclk.c46
-rw-r--r--drivers/gpu/drm/i915/intel_color.c16
-rw-r--r--drivers/gpu/drm/i915/intel_crt.c114
-rw-r--r--drivers/gpu/drm/i915/intel_csr.c41
-rw-r--r--drivers/gpu/drm/i915/intel_ddi.c906
-rw-r--r--drivers/gpu/drm/i915/intel_device_info.c41
-rw-r--r--drivers/gpu/drm/i915/intel_display.c459
-rw-r--r--drivers/gpu/drm/i915/intel_dp.c137
-rw-r--r--drivers/gpu/drm/i915/intel_dp_aux_backlight.c2
-rw-r--r--drivers/gpu/drm/i915/intel_dp_mst.c60
-rw-r--r--drivers/gpu/drm/i915/intel_dpio_phy.c20
-rw-r--r--drivers/gpu/drm/i915/intel_dpll_mgr.c2
-rw-r--r--drivers/gpu/drm/i915/intel_drv.h48
-rw-r--r--drivers/gpu/drm/i915/intel_dsi.c54
-rw-r--r--drivers/gpu/drm/i915/intel_dvo.c33
-rw-r--r--drivers/gpu/drm/i915/intel_engine_cs.c493
-rw-r--r--drivers/gpu/drm/i915/intel_fbc.c24
-rw-r--r--drivers/gpu/drm/i915/intel_fbdev.c4
-rw-r--r--drivers/gpu/drm/i915/intel_fifo_underrun.c14
-rw-r--r--drivers/gpu/drm/i915/intel_guc.c369
-rw-r--r--drivers/gpu/drm/i915/intel_guc.h120
-rw-r--r--drivers/gpu/drm/i915/intel_guc_fw.c (renamed from drivers/gpu/drm/i915/intel_guc_loader.c)252
-rw-r--r--drivers/gpu/drm/i915/intel_guc_fw.h33
-rw-r--r--drivers/gpu/drm/i915/intel_guc_fwif.h62
-rw-r--r--drivers/gpu/drm/i915/intel_guc_log.c32
-rw-r--r--drivers/gpu/drm/i915/intel_guc_log.h59
-rw-r--r--drivers/gpu/drm/i915/intel_gvt.c12
-rw-r--r--drivers/gpu/drm/i915/intel_hangcheck.c2
-rw-r--r--drivers/gpu/drm/i915/intel_hdmi.c26
-rw-r--r--drivers/gpu/drm/i915/intel_huc.c172
-rw-r--r--drivers/gpu/drm/i915/intel_huc.h41
-rw-r--r--drivers/gpu/drm/i915/intel_lrc.c705
-rw-r--r--drivers/gpu/drm/i915/intel_lrc.h37
-rw-r--r--drivers/gpu/drm/i915/intel_lspcon.c22
-rw-r--r--drivers/gpu/drm/i915/intel_lvds.c27
-rw-r--r--drivers/gpu/drm/i915/intel_modes.c17
-rw-r--r--drivers/gpu/drm/i915/intel_opregion.c2
-rw-r--r--drivers/gpu/drm/i915/intel_overlay.c2
-rw-r--r--drivers/gpu/drm/i915/intel_panel.c8
-rw-r--r--drivers/gpu/drm/i915/intel_pipe_crc.c15
-rw-r--r--drivers/gpu/drm/i915/intel_pm.c1078
-rw-r--r--drivers/gpu/drm/i915/intel_psr.c399
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.c194
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.h174
-rw-r--r--drivers/gpu/drm/i915/intel_runtime_pm.c48
-rw-r--r--drivers/gpu/drm/i915/intel_sideband.c6
-rw-r--r--drivers/gpu/drm/i915/intel_sprite.c12
-rw-r--r--drivers/gpu/drm/i915/intel_tv.c2
-rw-r--r--drivers/gpu/drm/i915/intel_uc.c363
-rw-r--r--drivers/gpu/drm/i915/intel_uc.h247
-rw-r--r--drivers/gpu/drm/i915/intel_uc_fw.c318
-rw-r--r--drivers/gpu/drm/i915/intel_uc_fw.h121
-rw-r--r--drivers/gpu/drm/i915/intel_uncore.c268
-rw-r--r--drivers/gpu/drm/i915/intel_uncore.h18
-rw-r--r--drivers/gpu/drm/i915/intel_vbt_defs.h8
-rw-r--r--drivers/gpu/drm/i915/selftests/huge_gem_object.c14
-rw-r--r--drivers/gpu/drm/i915/selftests/huge_pages.c1734
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_context.c2
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_evict.c162
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_gtt.c15
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_object.c8
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_request.c12
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_timeline.c2
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_live_selftests.h2
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_mock_selftests.h1
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_random.c5
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_random.h5
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_sw_fence.c42
-rw-r--r--drivers/gpu/drm/i915/selftests/intel_hangcheck.c50
-rw-r--r--drivers/gpu/drm/i915/selftests/lib_sw_fence.c78
-rw-r--r--drivers/gpu/drm/i915/selftests/lib_sw_fence.h42
-rw-r--r--drivers/gpu/drm/i915/selftests/mock_context.c6
-rw-r--r--drivers/gpu/drm/i915/selftests/mock_engine.c8
-rw-r--r--drivers/gpu/drm/i915/selftests/mock_gem_device.c20
-rw-r--r--drivers/gpu/drm/i915/selftests/mock_gtt.c11
-rw-r--r--drivers/gpu/drm/i915/selftests/scatterlist.c15
-rw-r--r--drivers/gpu/drm/mgag200/mgag200_mode.c2
-rw-r--r--drivers/gpu/drm/msm/Makefile4
-rw-r--r--drivers/gpu/drm/msm/adreno/a3xx_gpu.c10
-rw-r--r--drivers/gpu/drm/msm/adreno/a4xx_gpu.c10
-rw-r--r--drivers/gpu/drm/msm/adreno/a5xx_gpu.c261
-rw-r--r--drivers/gpu/drm/msm/adreno/a5xx_gpu.h109
-rw-r--r--drivers/gpu/drm/msm/adreno/a5xx_power.c9
-rw-r--r--drivers/gpu/drm/msm/adreno/a5xx_preempt.c305
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_device.c78
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.c297
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.h66
-rw-r--r--drivers/gpu/drm/msm/dsi/dsi_cfg.c8
-rw-r--r--drivers/gpu/drm/msm/dsi/dsi_host.c32
-rw-r--r--drivers/gpu/drm/msm/dsi/phy/dsi_phy.c2
-rw-r--r--drivers/gpu/drm/msm/edp/edp_ctrl.c22
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi.c10
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi_phy.c2
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi_phy_8960.c2
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c4
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi_phy_8x74.c3
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c7
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c2
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c2
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c162
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c2
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c10
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c8
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.c71
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h7
-rw-r--r--drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c233
-rw-r--r--drivers/gpu/drm/msm/msm_atomic.c41
-rw-r--r--drivers/gpu/drm/msm/msm_drv.c83
-rw-r--r--drivers/gpu/drm/msm/msm_drv.h37
-rw-r--r--drivers/gpu/drm/msm/msm_fence.c2
-rw-r--r--drivers/gpu/drm/msm/msm_fence.h2
-rw-r--r--drivers/gpu/drm/msm/msm_gem.c37
-rw-r--r--drivers/gpu/drm/msm/msm_gem.h5
-rw-r--r--drivers/gpu/drm/msm/msm_gem_submit.c61
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.c238
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.h51
-rw-r--r--drivers/gpu/drm/msm/msm_rd.c154
-rw-r--r--drivers/gpu/drm/msm/msm_ringbuffer.c36
-rw-r--r--drivers/gpu/drm/msm/msm_ringbuffer.h33
-rw-r--r--drivers/gpu/drm/msm/msm_submitqueue.c152
-rw-r--r--drivers/gpu/drm/nouveau/Kbuild2
-rw-r--r--drivers/gpu/drm/nouveau/Kconfig7
-rw-r--r--drivers/gpu/drm/nouveau/dispnv04/disp.c2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl506e.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl506f.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl826e.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl826f.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl906f.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cla06f.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/class.h17
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/device.h5
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if0008.h42
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if000a.h22
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if000b.h11
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if000c.h64
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if000d.h12
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if500b.h25
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if500d.h21
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if900b.h23
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/if900d.h21
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/ifb00d.h27
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/ifc00d.h21
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/ioctl.h10
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/mem.h18
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/mmu.h56
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/object.h7
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/os.h14
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/vmm.h42
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/client.h3
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/device.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/engine.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/gpuobj.h14
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/memory.h64
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/mm.h32
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/object.h41
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/oclass.h31
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/os.h19
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/ramht.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/engine/dma.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h5
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h3
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/bar.h9
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h36
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h7
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h140
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h1
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_abi16.c42
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_abi16.h2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_bios.c10
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_bo.c391
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_bo.h17
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_chan.c51
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_chan.h3
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_connector.c4
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_display.h5
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_dma.c15
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_dma.h2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_drm.c161
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_drv.h33
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_fbcon.c14
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_fence.c58
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_fence.h7
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_gem.c123
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_gem.h3
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_mem.c198
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_mem.h30
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_sgdma.c54
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_ttm.c280
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_vmm.c135
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_vmm.h31
-rw-r--r--drivers/gpu/drm/nouveau/nv50_display.c17
-rw-r--r--drivers/gpu/drm/nouveau/nv50_fbcon.c9
-rw-r--r--drivers/gpu/drm/nouveau/nv84_fence.c43
-rw-r--r--drivers/gpu/drm/nouveau/nvc0_fbcon.c9
-rw-r--r--drivers/gpu/drm/nouveau/nvif/Kbuild3
-rw-r--r--drivers/gpu/drm/nouveau/nvif/mem.c88
-rw-r--r--drivers/gpu/drm/nouveau/nvif/mmu.c117
-rw-r--r--drivers/gpu/drm/nouveau/nvif/object.c87
-rw-r--r--drivers/gpu/drm/nouveau/nvif/vmm.c167
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/client.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/engine.c10
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/gpuobj.c47
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/ioctl.c15
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/memory.c100
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/mm.c5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/object.c14
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/oproxy.c13
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/ramht.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/base.c98
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c24
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/user.c9
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/dma/usernv04.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/falcon.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c8
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/chan.c43
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/chang84.c13
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/changf100.h5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/channv50.c14
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/channv50.h5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmag84.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv50.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gf100.c18
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gf100.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c19
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifog84.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogf100.c45
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c51
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifonv50.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv50.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c123
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf108.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c9
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp102.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c83
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h9
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c13
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/nv50.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv50.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/pm/priv.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/sw/chan.h4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/sw/nvsw.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/xtensa.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/falcon/base.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/falcon/v1.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/Kbuild2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c60
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/g84.c10
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c151
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.h16
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/gk20a.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/gm107.c65
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/gm20b.c42
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/nv50.c174
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/nv50.h16
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/priv.h20
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/iccsense.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c7
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/timing.c5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv04.c12
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c35
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/g84.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c24
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk20a.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c18
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm20b.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp10b.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gt215.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv04.c9
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv10.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv1a.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv20.c13
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv25.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv30.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv35.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv36.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv40.c4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv41.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv44.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv46.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv47.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv49.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv4e.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c30
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h13
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.c144
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h11
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c94
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf108.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgk104.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm107.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm200.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgt215.c20
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/rammcp77.c7
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv04.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv10.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv1a.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv20.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.c7
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv41.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv44.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv49.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv4e.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c98
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c266
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c61
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c70
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.c71
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c329
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/priv.h14
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c25
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gf100.c20
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild29
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c694
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/g84.c41
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gf100.c228
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gk104.c41
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gk20a.c41
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm200.c97
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm20b.c (renamed from drivers/gpu/drm/amd/powerplay/smumgr/ci_smc.h)57
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp100.c (renamed from drivers/gpu/drm/radeon/radeon_kfd.h)44
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.0
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.c45
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/mem.c242
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/mem.h23
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/memgf100.c94
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/memnv04.c69
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/memnv50.c88
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv04.c122
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv04.h18
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv41.c104
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv44.c190
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv50.c231
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h70
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/umem.c192
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/umem.h26
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.c178
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.h14
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c352
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.h14
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c1513
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h310
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c403
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgk104.c102
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgk20a.c71
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgm200.c185
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgm20b.c70
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c347
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c49
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv04.c140
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv41.c113
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv44.c230
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c385
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c43
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.h5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/therm/gp100.c (renamed from drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.h)48
-rw-r--r--drivers/gpu/drm/omapdrm/displays/connector-hdmi.c8
-rw-r--r--drivers/gpu/drm/omapdrm/displays/encoder-tpd12s015.c18
-rw-r--r--drivers/gpu/drm/omapdrm/dss/Kconfig8
-rw-r--r--drivers/gpu/drm/omapdrm/dss/Makefile1
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi.h7
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4.c62
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c381
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4_cec.h55
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4_core.c7
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4_core.h4
-rw-r--r--drivers/gpu/drm/omapdrm/dss/omapdss.h1
-rw-r--r--drivers/gpu/drm/qxl/qxl_cmd.c22
-rw-r--r--drivers/gpu/drm/qxl/qxl_display.c49
-rw-r--r--drivers/gpu/drm/qxl/qxl_drv.h28
-rw-r--r--drivers/gpu/drm/qxl/qxl_dumb.c1
-rw-r--r--drivers/gpu/drm/qxl/qxl_fb.c13
-rw-r--r--drivers/gpu/drm/qxl/qxl_release.c5
-rw-r--r--drivers/gpu/drm/qxl/qxl_ttm.c4
-rw-r--r--drivers/gpu/drm/radeon/Makefile3
-rw-r--r--drivers/gpu/drm/radeon/atombios_dp.c46
-rw-r--r--drivers/gpu/drm/radeon/ci_dpm.c22
-rw-r--r--drivers/gpu/drm/radeon/ci_dpm.h1
-rw-r--r--drivers/gpu/drm/radeon/ci_smc.c21
-rw-r--r--drivers/gpu/drm/radeon/cik.c14
-rw-r--r--drivers/gpu/drm/radeon/cikd.h2
-rw-r--r--drivers/gpu/drm/radeon/r100.c2
-rw-r--r--drivers/gpu/drm/radeon/r600_cs.c2
-rw-r--r--drivers/gpu/drm/radeon/radeon.h3
-rw-r--r--drivers/gpu/drm/radeon/radeon_connectors.c16
-rw-r--r--drivers/gpu/drm/radeon/radeon_drv.c10
-rw-r--r--drivers/gpu/drm/radeon/radeon_kfd.c901
-rw-r--r--drivers/gpu/drm/radeon/radeon_kms.c7
-rw-r--r--drivers/gpu/drm/radeon/radeon_mode.h4
-rw-r--r--drivers/gpu/drm/rockchip/Kconfig2
-rw-r--r--drivers/gpu/drm/rockchip/analogix_dp-rockchip.c14
-rw-r--r--drivers/gpu/drm/tegra/Kconfig1
-rw-r--r--drivers/gpu/drm/tegra/dc.c84
-rw-r--r--drivers/gpu/drm/tegra/dc.h120
-rw-r--r--drivers/gpu/drm/tegra/drm.c30
-rw-r--r--drivers/gpu/drm/tegra/drm.h106
-rw-r--r--drivers/gpu/drm/tegra/gr2d.c2
-rw-r--r--drivers/gpu/drm/tegra/gr3d.c2
-rw-r--r--drivers/gpu/drm/tegra/hdmi.c17
-rw-r--r--drivers/gpu/drm/tegra/output.c6
-rw-r--r--drivers/gpu/drm/tegra/sor.c5
-rw-r--r--drivers/gpu/drm/tegra/vic.c22
-rw-r--r--drivers/gpu/drm/tilcdc/tilcdc_crtc.c51
-rw-r--r--drivers/gpu/drm/tilcdc/tilcdc_panel.c2
-rw-r--r--drivers/gpu/drm/tilcdc/tilcdc_slave_compat.c1
-rw-r--r--drivers/gpu/drm/tilcdc/tilcdc_tfp410.c4
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo.c13
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_util.c1
-rw-r--r--drivers/gpu/drm/ttm/ttm_memory.c12
-rw-r--r--drivers/gpu/drm/ttm/ttm_page_alloc.c380
-rw-r--r--drivers/gpu/drm/ttm/ttm_page_alloc_dma.c236
-rw-r--r--drivers/gpu/drm/udl/udl_connector.c2
-rw-r--r--drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c4
-rw-r--r--drivers/gpu/drm/vmwgfx/vmwgfx_kms.c2
-rw-r--r--drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c4
-rw-r--r--drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c4
-rw-r--r--drivers/gpu/host1x/Makefile3
-rw-r--r--drivers/gpu/host1x/bus.c3
-rw-r--r--drivers/gpu/host1x/channel.c3
-rw-r--r--drivers/gpu/host1x/debug.c14
-rw-r--r--drivers/gpu/host1x/debug.h14
-rw-r--r--drivers/gpu/host1x/dev.c69
-rw-r--r--drivers/gpu/host1x/dev.h19
-rw-r--r--drivers/gpu/host1x/hw/cdma_hw.c49
-rw-r--r--drivers/gpu/host1x/hw/channel_hw.c24
-rw-r--r--drivers/gpu/host1x/hw/debug_hw.c240
-rw-r--r--drivers/gpu/host1x/hw/debug_hw_1x01.c154
-rw-r--r--drivers/gpu/host1x/hw/debug_hw_1x06.c135
-rw-r--r--drivers/gpu/host1x/hw/host1x01.c2
-rw-r--r--drivers/gpu/host1x/hw/host1x02.c2
-rw-r--r--drivers/gpu/host1x/hw/host1x04.c2
-rw-r--r--drivers/gpu/host1x/hw/host1x05.c2
-rw-r--r--drivers/gpu/host1x/hw/host1x06.c44
-rw-r--r--drivers/gpu/host1x/hw/host1x06.h26
-rw-r--r--drivers/gpu/host1x/hw/host1x06_hardware.h142
-rw-r--r--drivers/gpu/host1x/hw/hw_host1x04_channel.h12
-rw-r--r--drivers/gpu/host1x/hw/hw_host1x05_channel.h12
-rw-r--r--drivers/gpu/host1x/hw/hw_host1x06_hypervisor.h32
-rw-r--r--drivers/gpu/host1x/hw/hw_host1x06_uclass.h181
-rw-r--r--drivers/gpu/host1x/hw/hw_host1x06_vm.h47
-rw-r--r--drivers/gpu/host1x/hw/intr_hw.c29
-rw-r--r--drivers/gpu/host1x/hw/syncpt_hw.c46
-rw-r--r--drivers/gpu/host1x/syncpt.c24
-rw-r--r--drivers/gpu/host1x/syncpt.h2
-rw-r--r--drivers/gpu/ipu-v3/ipu-common.c8
-rw-r--r--drivers/gpu/ipu-v3/ipu-pre.c29
-rw-r--r--drivers/gpu/ipu-v3/ipu-prg.c7
-rw-r--r--drivers/hid/Kconfig1
-rw-r--r--drivers/hid/hid-core.c2
-rw-r--r--drivers/hid/hid-elecom.c13
-rw-r--r--drivers/hid/hid-ids.h4
-rw-r--r--drivers/hid/hid-multitouch.c7
-rw-r--r--drivers/hid/hid-rmi.c13
-rw-r--r--drivers/hid/hidraw.c2
-rw-r--r--drivers/hid/i2c-hid/i2c-hid.c3
-rw-r--r--drivers/hid/usbhid/hid-core.c12
-rw-r--r--drivers/hid/usbhid/hid-quirks.c1
-rw-r--r--drivers/hid/wacom_sys.c7
-rw-r--r--drivers/hid/wacom_wac.c110
-rw-r--r--drivers/hv/channel.c6
-rw-r--r--drivers/hv/channel_mgmt.c46
-rw-r--r--drivers/hv/hv_fcopy.c4
-rw-r--r--drivers/hv/vmbus_drv.c3
-rw-r--r--drivers/hwmon/da9052-hwmon.c5
-rw-r--r--drivers/hwmon/tmp102.c13
-rw-r--r--drivers/hwmon/xgene-hwmon.c19
-rw-r--r--drivers/hwtracing/intel_th/pci.c10
-rw-r--r--drivers/hwtracing/stm/core.c2
-rw-r--r--drivers/i2c/busses/Kconfig1
-rw-r--r--drivers/i2c/busses/i2c-i801.c4
-rw-r--r--drivers/i2c/busses/i2c-img-scb.c2
-rw-r--r--drivers/i2c/busses/i2c-imx.c4
-rw-r--r--drivers/i2c/busses/i2c-ismt.c5
-rw-r--r--drivers/i2c/busses/i2c-omap.c14
-rw-r--r--drivers/i2c/busses/i2c-piix4.c162
-rw-r--r--drivers/i2c/busses/i2c-sprd.c1
-rw-r--r--drivers/i2c/busses/i2c-stm32f7.c17
-rw-r--r--drivers/ide/ide-probe.c1
-rw-r--r--drivers/ide/ide-scan-pci.c13
-rw-r--r--drivers/ide/setup-pci.c63
-rw-r--r--drivers/iio/adc/Kconfig2
-rw-r--r--drivers/iio/adc/ad7793.c4
-rw-r--r--drivers/iio/adc/ad_sigma_delta.c28
-rw-r--r--drivers/iio/adc/at91-sama5d2_adc.c45
-rw-r--r--drivers/iio/adc/mcp320x.c25
-rw-r--r--drivers/iio/adc/stm32-adc.c2
-rw-r--r--drivers/iio/adc/ti-ads1015.c8
-rw-r--r--drivers/iio/adc/twl4030-madc.c14
-rw-r--r--drivers/iio/common/st_sensors/st_sensors_core.c11
-rw-r--r--drivers/iio/dummy/iio_simple_dummy_events.c1
-rw-r--r--drivers/iio/industrialio-core.c4
-rw-r--r--drivers/iio/magnetometer/st_magn_core.c4
-rw-r--r--drivers/iio/pressure/bmp280-core.c2
-rw-r--r--drivers/iio/pressure/zpa2326.c10
-rw-r--r--drivers/iio/proximity/as3935.c43
-rw-r--r--drivers/iio/trigger/stm32-timer-trigger.c4
-rw-r--r--drivers/infiniband/core/iwpm_msg.c8
-rw-r--r--drivers/infiniband/core/iwpm_util.c5
-rw-r--r--drivers/infiniband/core/netlink.c13
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw_ctrl.c2
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw_p.h2
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw_puda.c11
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw_verbs.c2
-rw-r--r--drivers/infiniband/hw/mlx5/main.c4
-rw-r--r--drivers/infiniband/hw/qedr/qedr.h2
-rw-r--r--drivers/infiniband/hw/qedr/qedr_cm.c12
-rw-r--r--drivers/input/input.c84
-rw-r--r--drivers/input/joydev.c70
-rw-r--r--drivers/input/keyboard/tca8418_keypad.c29
-rw-r--r--drivers/input/misc/axp20x-pek.c2
-rw-r--r--drivers/input/misc/ims-pcu.c16
-rw-r--r--drivers/input/mouse/elan_i2c_core.c1
-rw-r--r--drivers/input/mouse/synaptics.c3
-rw-r--r--drivers/input/rmi4/rmi_f30.c5
-rw-r--r--drivers/input/tablet/gtco.c17
-rw-r--r--drivers/input/touchscreen/goodix.c67
-rw-r--r--drivers/input/touchscreen/stmfts.c6
-rw-r--r--drivers/input/touchscreen/ti_am335x_tsc.c2
-rw-r--r--drivers/iommu/amd_iommu.c11
-rw-r--r--drivers/iommu/exynos-iommu.c2
-rw-r--r--drivers/irqchip/irq-gic-v3-its.c43
-rw-r--r--drivers/irqchip/irq-tango.c2
-rw-r--r--drivers/md/bcache/closure.c4
-rw-r--r--drivers/md/dm-core.h1
-rw-r--r--drivers/md/dm-crypt.c5
-rw-r--r--drivers/md/dm-ioctl.c37
-rw-r--r--drivers/md/dm-raid.c11
-rw-r--r--drivers/md/dm.c10
-rw-r--r--drivers/media/cec/cec-adap.c13
-rw-r--r--drivers/media/dvb-core/dvb_frontend.c25
-rw-r--r--drivers/media/dvb-frontends/dib3000mc.c50
-rw-r--r--drivers/media/dvb-frontends/dvb-pll.c22
-rw-r--r--drivers/media/platform/Kconfig2
-rw-r--r--drivers/media/platform/qcom/camss-8x16/camss-vfe.c2
-rw-r--r--drivers/media/platform/qcom/venus/helpers.c1
-rw-r--r--drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c3
-rw-r--r--drivers/media/platform/s5p-cec/s5p_cec.c11
-rw-r--r--drivers/media/platform/s5p-cec/s5p_cec.h2
-rw-r--r--drivers/media/rc/ir-sharp-decoder.c2
-rw-r--r--drivers/media/tuners/mt2060.c59
-rw-r--r--drivers/media/v4l2-core/videobuf2-dma-contig.c4
-rw-r--r--drivers/misc/cxl/cxllib.c13
-rw-r--r--drivers/misc/mei/hw-me-regs.h2
-rw-r--r--drivers/misc/mei/pci-me.c23
-rw-r--r--drivers/misc/mei/pci-txe.c30
-rw-r--r--drivers/mmc/core/block.c3
-rw-r--r--drivers/mmc/core/mmc.c36
-rw-r--r--drivers/mmc/core/queue.c125
-rw-r--r--drivers/mmc/core/queue.h6
-rw-r--r--drivers/mmc/host/cavium.c2
-rw-r--r--drivers/mmc/host/meson-gx-mmc.c26
-rw-r--r--drivers/mmc/host/pxamci.c6
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c2
-rw-r--r--drivers/mmc/host/sdhci-xenon.c24
-rw-r--r--drivers/mmc/host/sdhci-xenon.h1
-rw-r--r--drivers/net/can/flexcan.c91
-rw-r--r--drivers/net/can/sun4i_can.c3
-rw-r--r--drivers/net/can/usb/esd_usb2.c2
-rw-r--r--drivers/net/can/usb/gs_usb.c10
-rw-r--r--drivers/net/can/usb/kvaser_usb.c9
-rw-r--r--drivers/net/dsa/mv88e6060.c10
-rw-r--r--drivers/net/dsa/mv88e6xxx/chip.c6
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_ethtool.c4
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_netdev.c7
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_cfg.h12
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c157
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_hw.h5
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_nic.c182
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_nic.h6
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c14
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_ring.c53
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_ring.h10
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_vec.c11
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c21
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c89
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h5
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c72
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h18
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c99
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.h5
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c23
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c8
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c11
-rw-r--r--drivers/net/ethernet/broadcom/cnic.c2
-rw-r--r--drivers/net/ethernet/cavium/liquidio/lio_main.c2
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_main.c2
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c3
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c16
-rw-r--r--drivers/net/ethernet/intel/e1000/e1000_ethtool.c9
-rw-r--r--drivers/net/ethernet/intel/e1000/e1000_main.c11
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_nvm.c2
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.c66
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c2
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c22
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_common.c19
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c16
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c24
-rw-r--r--drivers/net/ethernet/marvell/mvpp2.c81
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/dev.c70
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c113
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_fs.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rx.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_stats.h6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c180
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c8
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_core.h11
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/health.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/port.c21
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sriov.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/core.c11
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/reg.h31
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c43
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/action.c2
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_net_common.c20
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c8
-rw-r--r--drivers/net/ethernet/qualcomm/emac/emac-mac.c3
-rw-r--r--drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c5
-rw-r--r--drivers/net/ethernet/realtek/r8169.c2
-rw-r--r--drivers/net/ethernet/rocker/rocker_tlv.h48
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c3
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c112
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c7
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c17
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c7
-rw-r--r--drivers/net/geneve.c6
-rw-r--r--drivers/net/ipvlan/ipvtap.c4
-rw-r--r--drivers/net/macsec.c2
-rw-r--r--drivers/net/macvtap.c4
-rw-r--r--drivers/net/ppp/ppp_generic.c22
-rw-r--r--drivers/net/tap.c23
-rw-r--r--drivers/net/tun.c12
-rw-r--r--drivers/net/usb/cdc_ether.c48
-rw-r--r--drivers/net/usb/r8152.c4
-rw-r--r--drivers/net/usb/rndis_host.c4
-rw-r--r--drivers/net/wimax/i2400m/fw.c2
-rw-r--r--drivers/net/wireless/ath/ath10k/pci.c7
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c37
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c3
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h5
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c197
-rw-r--r--drivers/net/wireless/intel/iwlwifi/cfg/7000.c1
-rw-r--r--drivers/net/wireless/intel/iwlwifi/cfg/8000.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/cfg/9000.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/cfg/a000.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/fw/dbg.c7
-rw-r--r--drivers/net/wireless/intel/iwlwifi/fw/dbg.h15
-rw-r--r--drivers/net/wireless/intel/iwlwifi/iwl-config.h16
-rw-r--r--drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c137
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/d3.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c69
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/mvm.h5
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/nvm.c21
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rs.c3
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rx.c4
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c11
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/scan.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/sta.c8
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/sta.h2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/tt.c3
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/tx.c10
-rw-r--r--drivers/net/wireless/quantenna/qtnfmac/cfg80211.c9
-rw-r--r--drivers/net/wireless/quantenna/qtnfmac/cfg80211.h3
-rw-r--r--drivers/net/wireless/quantenna/qtnfmac/event.c2
-rw-r--r--drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c9
-rw-r--r--drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h2
-rw-r--r--drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c2
-rw-r--r--drivers/net/xen-netback/interface.c2
-rw-r--r--drivers/net/xen-netfront.c2
-rw-r--r--drivers/nvme/host/core.c2
-rw-r--r--drivers/nvme/host/fc.c37
-rw-r--r--drivers/nvme/host/pci.c14
-rw-r--r--drivers/nvme/host/rdma.c16
-rw-r--r--drivers/nvme/target/core.c15
-rw-r--r--drivers/nvme/target/nvmet.h2
-rw-r--r--drivers/nvmem/core.c3
-rw-r--r--drivers/of/base.c8
-rw-r--r--drivers/of/of_mdio.c39
-rw-r--r--drivers/of/of_reserved_mem.c2
-rw-r--r--drivers/of/property.c2
-rw-r--r--drivers/pci/host/pci-aardvark.c2
-rw-r--r--drivers/pci/host/pci-tegra.c22
-rw-r--r--drivers/phy/marvell/phy-mvebu-cp110-comphy.c18
-rw-r--r--drivers/phy/mediatek/phy-mtk-tphy.c3
-rw-r--r--drivers/phy/rockchip/phy-rockchip-typec.c82
-rw-r--r--drivers/phy/tegra/xusb.c2
-rw-r--r--drivers/pinctrl/Kconfig1
-rw-r--r--drivers/pinctrl/bcm/pinctrl-bcm2835.c4
-rw-r--r--drivers/pinctrl/intel/pinctrl-cherryview.c14
-rw-r--r--drivers/pinctrl/pinctrl-amd.c10
-rw-r--r--drivers/pinctrl/pinctrl-mcp23s08.c6
-rw-r--r--drivers/platform/x86/intel_pmc_ipc.c115
-rw-r--r--drivers/rapidio/devices/rio_mport_cdev.c4
-rw-r--r--drivers/rapidio/devices/tsi721.c7
-rw-r--r--drivers/rapidio/rio-access.c40
-rw-r--r--drivers/ras/cec.c2
-rw-r--r--drivers/regulator/axp20x-regulator.c2
-rw-r--r--drivers/regulator/rn5t618-regulator.c2
-rw-r--r--drivers/remoteproc/Kconfig2
-rw-r--r--drivers/remoteproc/imx_rproc.c9
-rw-r--r--drivers/reset/Kconfig9
-rw-r--r--drivers/reset/Makefile2
-rw-r--r--drivers/reset/reset-hsdk.c (renamed from drivers/reset/reset-hsdk-v1.c)44
-rw-r--r--drivers/reset/reset-socfpga.c17
-rw-r--r--drivers/rpmsg/qcom_glink_native.c14
-rw-r--r--drivers/s390/scsi/zfcp_aux.c5
-rw-r--r--drivers/s390/scsi/zfcp_erp.c18
-rw-r--r--drivers/s390/scsi/zfcp_scsi.c5
-rw-r--r--drivers/scsi/aacraid/comminit.c8
-rw-r--r--drivers/scsi/aacraid/linit.c7
-rw-r--r--drivers/scsi/hpsa.c2
-rw-r--r--drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c2
-rw-r--r--drivers/scsi/libfc/fc_rport.c2
-rw-r--r--drivers/scsi/libiscsi.c10
-rw-r--r--drivers/scsi/qla2xxx/qla_os.c3
-rw-r--r--drivers/scsi/scsi_lib.c8
-rw-r--r--drivers/scsi/scsi_scan.c3
-rw-r--r--drivers/scsi/scsi_sysfs.c10
-rw-r--r--drivers/scsi/scsi_transport_fc.c3
-rw-r--r--drivers/scsi/scsi_transport_iscsi.c16
-rw-r--r--drivers/scsi/sd.c35
-rw-r--r--drivers/scsi/sg.c2
-rw-r--r--drivers/spi/spi-armada-3700.c145
-rw-r--r--drivers/spi/spi-bcm-qspi.c9
-rw-r--r--drivers/spi/spi-stm32.c4
-rw-r--r--drivers/spi/spi.c13
-rw-r--r--drivers/staging/iio/adc/ad7192.c4
-rw-r--r--drivers/staging/iio/meter/ade7759.c2
-rw-r--r--drivers/staging/media/imx/imx-media-dev.c4
-rw-r--r--drivers/staging/mt29f_spinand/mt29f_spinand.c8
-rw-r--r--drivers/staging/pi433/rf69.c9
-rw-r--r--drivers/staging/rtl8723bs/core/rtw_mlme.c3
-rw-r--r--drivers/staging/rtl8723bs/os_dep/rtw_proc.c2
-rw-r--r--drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c4
-rw-r--r--drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c13
-rw-r--r--drivers/staging/speakup/main.c15
-rw-r--r--drivers/staging/unisys/visorbus/visorchipset.c4
-rw-r--r--drivers/staging/vboxvideo/vbox_mode.c2
-rw-r--r--drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c19
-rw-r--r--drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c6
-rw-r--r--drivers/tty/mxser.c16
-rw-r--r--drivers/tty/serial/bcm63xx_uart.c5
-rw-r--r--drivers/tty/serial/fsl_lpuart.c40
-rw-r--r--drivers/tty/serial/sccnxp.c13
-rw-r--r--drivers/tty/tty_ldisc.c11
-rw-r--r--drivers/usb/class/cdc-acm.c3
-rw-r--r--drivers/usb/class/cdc-wdm.c4
-rw-r--r--drivers/usb/core/config.c22
-rw-r--r--drivers/usb/core/devio.c5
-rw-r--r--drivers/usb/core/hub.c13
-rw-r--r--drivers/usb/core/message.c4
-rw-r--r--drivers/usb/core/quirks.c4
-rw-r--r--drivers/usb/dwc3/dwc3-of-simple.c1
-rw-r--r--drivers/usb/dwc3/ep0.c7
-rw-r--r--drivers/usb/gadget/composite.c5
-rw-r--r--drivers/usb/gadget/configfs.c15
-rw-r--r--drivers/usb/gadget/configfs.h11
-rw-r--r--drivers/usb/gadget/function/f_fs.c17
-rw-r--r--drivers/usb/gadget/function/f_mass_storage.c27
-rw-r--r--drivers/usb/gadget/function/f_mass_storage.h14
-rw-r--r--drivers/usb/gadget/function/f_printer.c7
-rw-r--r--drivers/usb/gadget/function/f_rndis.c12
-rw-r--r--drivers/usb/gadget/function/u_fs.h1
-rw-r--r--drivers/usb/gadget/function/u_rndis.h1
-rw-r--r--drivers/usb/gadget/legacy/inode.c46
-rw-r--r--drivers/usb/gadget/legacy/mass_storage.c26
-rw-r--r--drivers/usb/gadget/udc/Kconfig1
-rw-r--r--drivers/usb/gadget/udc/atmel_usba_udc.c4
-rw-r--r--drivers/usb/gadget/udc/core.c3
-rw-r--r--drivers/usb/gadget/udc/dummy_hcd.c74
-rw-r--r--drivers/usb/gadget/udc/renesas_usb3.c19
-rw-r--r--drivers/usb/host/pci-quirks.c10
-rw-r--r--drivers/usb/host/xhci-hub.c37
-rw-r--r--drivers/usb/host/xhci-pci.c12
-rw-r--r--drivers/usb/host/xhci-plat.c16
-rw-r--r--drivers/usb/host/xhci-ring.c21
-rw-r--r--drivers/usb/host/xhci.c6
-rw-r--r--drivers/usb/host/xhci.h10
-rw-r--r--drivers/usb/misc/usbtest.c10
-rw-r--r--drivers/usb/musb/musb_core.c21
-rw-r--r--drivers/usb/musb/musb_core.h2
-rw-r--r--drivers/usb/musb/musb_cppi41.c94
-rw-r--r--drivers/usb/musb/sunxi.c2
-rw-r--r--drivers/usb/phy/phy-tegra-usb.c17
-rw-r--r--drivers/usb/renesas_usbhs/fifo.c23
-rw-r--r--drivers/usb/serial/console.c3
-rw-r--r--drivers/usb/serial/cp210x.c13
-rw-r--r--drivers/usb/serial/ftdi_sio.c2
-rw-r--r--drivers/usb/serial/ftdi_sio_ids.h7
-rw-r--r--drivers/usb/serial/metro-usb.c1
-rw-r--r--drivers/usb/serial/option.c2
-rw-r--r--drivers/usb/serial/qcserial.c4
-rw-r--r--drivers/usb/storage/transport.c14
-rw-r--r--drivers/usb/storage/uas-detect.h15
-rw-r--r--drivers/usb/storage/uas.c10
-rw-r--r--drivers/usb/storage/unusual_devs.h7
-rw-r--r--drivers/uwb/hwa-rc.c2
-rw-r--r--drivers/uwb/uwbd.c12
-rw-r--r--drivers/xen/gntdev.c2
-rw-r--r--drivers/xen/xen-balloon.c19
1143 files changed, 52796 insertions, 52282 deletions
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 9565d572f8dd..de56394dd161 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1178,12 +1178,44 @@ dev_put:
return ret;
}
+static bool __init iort_enable_acs(struct acpi_iort_node *iort_node)
+{
+ if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+ struct acpi_iort_node *parent;
+ struct acpi_iort_id_mapping *map;
+ int i;
+
+ map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node,
+ iort_node->mapping_offset);
+
+ for (i = 0; i < iort_node->mapping_count; i++, map++) {
+ if (!map->output_reference)
+ continue;
+
+ parent = ACPI_ADD_PTR(struct acpi_iort_node,
+ iort_table, map->output_reference);
+ /*
+ * If we detect a RC->SMMU mapping, make sure
+ * we enable ACS on the system.
+ */
+ if ((parent->type == ACPI_IORT_NODE_SMMU) ||
+ (parent->type == ACPI_IORT_NODE_SMMU_V3)) {
+ pci_request_acs();
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+
static void __init iort_init_platform_devices(void)
{
struct acpi_iort_node *iort_node, *iort_end;
struct acpi_table_iort *iort;
struct fwnode_handle *fwnode;
int i, ret;
+ bool acs_enabled = false;
/*
* iort_table and iort both point to the start of IORT table, but
@@ -1203,6 +1235,9 @@ static void __init iort_init_platform_devices(void)
return;
}
+ if (!acs_enabled)
+ acs_enabled = iort_enable_acs(iort_node);
+
if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 3fb8ff513461..e26ea209b63e 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -571,10 +571,9 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
* }
* }
*
- * Calling this function with index %2 return %-ENOENT and with index %3
- * returns the last entry. If the property does not contain any more values
- * %-ENODATA is returned. The NULL entry must be single integer and
- * preferably contain value %0.
+ * Calling this function with index %2 or index %3 return %-ENOENT. If the
+ * property does not contain any more values %-ENOENT is returned. The NULL
+ * entry must be single integer and preferably contain value %0.
*
* Return: %0 on success, negative error code on failure.
*/
@@ -590,11 +589,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
data = acpi_device_data_of_node(fwnode);
if (!data)
- return -EINVAL;
+ return -ENOENT;
ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj);
if (ret)
- return ret;
+ return ret == -EINVAL ? -ENOENT : -EINVAL;
/*
* The simplest case is when the value is a single reference. Just
@@ -606,7 +605,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
ret = acpi_bus_get_device(obj->reference.handle, &device);
if (ret)
- return ret;
+ return ret == -ENODEV ? -EINVAL : ret;
args->adev = device;
args->nargs = 0;
@@ -622,8 +621,10 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
* The index argument is then used to determine which reference
* the caller wants (along with the arguments).
*/
- if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count)
- return -EPROTO;
+ if (obj->type != ACPI_TYPE_PACKAGE)
+ return -EINVAL;
+ if (index >= obj->package.count)
+ return -ENOENT;
element = obj->package.elements;
end = element + obj->package.count;
@@ -635,7 +636,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
ret = acpi_bus_get_device(element->reference.handle,
&device);
if (ret)
- return -ENODEV;
+ return -EINVAL;
nargs = 0;
element++;
@@ -649,11 +650,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
else if (type == ACPI_TYPE_LOCAL_REFERENCE)
break;
else
- return -EPROTO;
+ return -EINVAL;
}
if (nargs > MAX_ACPI_REFERENCE_ARGS)
- return -EPROTO;
+ return -EINVAL;
if (idx == index) {
args->adev = device;
@@ -670,13 +671,13 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
return -ENOENT;
element++;
} else {
- return -EPROTO;
+ return -EINVAL;
}
idx++;
}
- return -ENODATA;
+ return -ENOENT;
}
EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference);
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index d055b3f2a207..fddf76ef5bd6 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2217,7 +2217,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
debug_id, (u64)fda->num_fds);
continue;
}
- fd_array = (u32 *)(parent_buffer + fda->parent_offset);
+ fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
for (fd_index = 0; fd_index < fda->num_fds; fd_index++)
task_close_fd(proc, fd_array[fd_index]);
} break;
@@ -2326,7 +2326,6 @@ static int binder_translate_handle(struct flat_binder_object *fp,
(u64)node->ptr);
binder_node_unlock(node);
} else {
- int ret;
struct binder_ref_data dest_rdata;
binder_node_unlock(node);
@@ -2442,7 +2441,7 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda,
*/
parent_buffer = parent->buffer -
binder_alloc_get_user_buffer_offset(&target_proc->alloc);
- fd_array = (u32 *)(parent_buffer + fda->parent_offset);
+ fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) {
binder_user_error("%d:%d parent offset not aligned correctly.\n",
proc->pid, thread->pid);
@@ -2508,7 +2507,7 @@ static int binder_fixup_parent(struct binder_transaction *t,
proc->pid, thread->pid);
return -EINVAL;
}
- parent_buffer = (u8 *)(parent->buffer -
+ parent_buffer = (u8 *)((uintptr_t)parent->buffer -
binder_alloc_get_user_buffer_offset(
&target_proc->alloc));
*(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer;
@@ -2583,6 +2582,48 @@ static bool binder_proc_transaction(struct binder_transaction *t,
return true;
}
+/**
+ * binder_get_node_refs_for_txn() - Get required refs on node for txn
+ * @node: struct binder_node for which to get refs
+ * @proc: returns @node->proc if valid
+ * @error: if no @proc then returns BR_DEAD_REPLY
+ *
+ * User-space normally keeps the node alive when creating a transaction
+ * since it has a reference to the target. The local strong ref keeps it
+ * alive if the sending process dies before the target process processes
+ * the transaction. If the source process is malicious or has a reference
+ * counting bug, relying on the local strong ref can fail.
+ *
+ * Since user-space can cause the local strong ref to go away, we also take
+ * a tmpref on the node to ensure it survives while we are constructing
+ * the transaction. We also need a tmpref on the proc while we are
+ * constructing the transaction, so we take that here as well.
+ *
+ * Return: The target_node with refs taken or NULL if no @node->proc is NULL.
+ * Also sets @proc if valid. If the @node->proc is NULL indicating that the
+ * target proc has died, @error is set to BR_DEAD_REPLY
+ */
+static struct binder_node *binder_get_node_refs_for_txn(
+ struct binder_node *node,
+ struct binder_proc **procp,
+ uint32_t *error)
+{
+ struct binder_node *target_node = NULL;
+
+ binder_node_inner_lock(node);
+ if (node->proc) {
+ target_node = node;
+ binder_inc_node_nilocked(node, 1, 0, NULL);
+ binder_inc_node_tmpref_ilocked(node);
+ node->proc->tmp_ref++;
+ *procp = node->proc;
+ } else
+ *error = BR_DEAD_REPLY;
+ binder_node_inner_unlock(node);
+
+ return target_node;
+}
+
static void binder_transaction(struct binder_proc *proc,
struct binder_thread *thread,
struct binder_transaction_data *tr, int reply,
@@ -2686,43 +2727,35 @@ static void binder_transaction(struct binder_proc *proc,
ref = binder_get_ref_olocked(proc, tr->target.handle,
true);
if (ref) {
- binder_inc_node(ref->node, 1, 0, NULL);
- target_node = ref->node;
- }
- binder_proc_unlock(proc);
- if (target_node == NULL) {
+ target_node = binder_get_node_refs_for_txn(
+ ref->node, &target_proc,
+ &return_error);
+ } else {
binder_user_error("%d:%d got transaction to invalid handle\n",
- proc->pid, thread->pid);
+ proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
- return_error_param = -EINVAL;
- return_error_line = __LINE__;
- goto err_invalid_target_handle;
}
+ binder_proc_unlock(proc);
} else {
mutex_lock(&context->context_mgr_node_lock);
target_node = context->binder_context_mgr_node;
- if (target_node == NULL) {
+ if (target_node)
+ target_node = binder_get_node_refs_for_txn(
+ target_node, &target_proc,
+ &return_error);
+ else
return_error = BR_DEAD_REPLY;
- mutex_unlock(&context->context_mgr_node_lock);
- return_error_line = __LINE__;
- goto err_no_context_mgr_node;
- }
- binder_inc_node(target_node, 1, 0, NULL);
mutex_unlock(&context->context_mgr_node_lock);
}
- e->to_node = target_node->debug_id;
- binder_node_lock(target_node);
- target_proc = target_node->proc;
- if (target_proc == NULL) {
- binder_node_unlock(target_node);
- return_error = BR_DEAD_REPLY;
+ if (!target_node) {
+ /*
+ * return_error is set above
+ */
+ return_error_param = -EINVAL;
return_error_line = __LINE__;
goto err_dead_binder;
}
- binder_inner_proc_lock(target_proc);
- target_proc->tmp_ref++;
- binder_inner_proc_unlock(target_proc);
- binder_node_unlock(target_node);
+ e->to_node = target_node->debug_id;
if (security_binder_transaction(proc->tsk,
target_proc->tsk) < 0) {
return_error = BR_FAILED_REPLY;
@@ -3072,6 +3105,8 @@ static void binder_transaction(struct binder_proc *proc,
if (target_thread)
binder_thread_dec_tmpref(target_thread);
binder_proc_dec_tmpref(target_proc);
+ if (target_node)
+ binder_dec_node_tmpref(target_node);
/*
* write barrier to synchronize with initialization
* of log entry
@@ -3083,6 +3118,7 @@ static void binder_transaction(struct binder_proc *proc,
err_dead_proc_or_thread:
return_error = BR_DEAD_REPLY;
return_error_line = __LINE__;
+ binder_dequeue_work(proc, tcomplete);
err_translate_failed:
err_bad_object_type:
err_bad_offset:
@@ -3090,6 +3126,8 @@ err_bad_parent:
err_copy_data_failed:
trace_binder_transaction_failed_buffer_release(t->buffer);
binder_transaction_buffer_release(target_proc, t->buffer, offp);
+ if (target_node)
+ binder_dec_node_tmpref(target_node);
target_node = NULL;
t->buffer->transaction = NULL;
binder_alloc_free_buf(&target_proc->alloc, t->buffer);
@@ -3104,13 +3142,14 @@ err_bad_call_stack:
err_empty_call_stack:
err_dead_binder:
err_invalid_target_handle:
-err_no_context_mgr_node:
if (target_thread)
binder_thread_dec_tmpref(target_thread);
if (target_proc)
binder_proc_dec_tmpref(target_proc);
- if (target_node)
+ if (target_node) {
binder_dec_node(target_node, 1, 0);
+ binder_dec_node_tmpref(target_node);
+ }
binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
"%d:%d transaction failed %d/%d, size %lld-%lld line %d\n",
@@ -3623,12 +3662,6 @@ static void binder_stat_br(struct binder_proc *proc,
}
}
-static int binder_has_thread_work(struct binder_thread *thread)
-{
- return !binder_worklist_empty(thread->proc, &thread->todo) ||
- thread->looper_need_return;
-}
-
static int binder_put_node_cmd(struct binder_proc *proc,
struct binder_thread *thread,
void __user **ptrp,
@@ -4258,12 +4291,9 @@ static unsigned int binder_poll(struct file *filp,
binder_inner_proc_unlock(thread->proc);
- if (binder_has_work(thread, wait_for_proc_work))
- return POLLIN;
-
poll_wait(filp, &thread->wait, wait);
- if (binder_has_thread_work(thread))
+ if (binder_has_work(thread, wait_for_proc_work))
return POLLIN;
return 0;
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 8fe165844e47..c2819a3d58a6 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -215,17 +215,12 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
}
}
- if (!vma && need_mm)
- mm = get_task_mm(alloc->tsk);
+ if (!vma && need_mm && mmget_not_zero(alloc->vma_vm_mm))
+ mm = alloc->vma_vm_mm;
if (mm) {
down_write(&mm->mmap_sem);
vma = alloc->vma;
- if (vma && mm != alloc->vma_vm_mm) {
- pr_err("%d: vma mm and task mm mismatch\n",
- alloc->pid);
- vma = NULL;
- }
}
if (!vma && need_mm) {
@@ -565,7 +560,7 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
"%d: merge free, buffer %pK do not share page with %pK or %pK\n",
alloc->pid, buffer->data,
- prev->data, next->data);
+ prev->data, next ? next->data : NULL);
binder_update_page_range(alloc, 0, buffer_start_page(buffer),
buffer_start_page(buffer) + PAGE_SIZE,
NULL);
@@ -720,6 +715,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
barrier();
alloc->vma = vma;
alloc->vma_vm_mm = vma->vm_mm;
+ mmgrab(alloc->vma_vm_mm);
return 0;
@@ -795,6 +791,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
vfree(alloc->buffer);
}
mutex_unlock(&alloc->mutex);
+ if (alloc->vma_vm_mm)
+ mmdrop(alloc->vma_vm_mm);
binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
"%s: %d buffers %d, pages %d\n",
@@ -889,7 +887,6 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
void binder_alloc_vma_close(struct binder_alloc *alloc)
{
WRITE_ONCE(alloc->vma, NULL);
- WRITE_ONCE(alloc->vma_vm_mm, NULL);
}
/**
@@ -913,6 +910,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
struct binder_alloc *alloc;
uintptr_t page_addr;
size_t index;
+ struct vm_area_struct *vma;
alloc = page->alloc;
if (!mutex_trylock(&alloc->mutex))
@@ -923,16 +921,22 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
index = page - alloc->pages;
page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
- if (alloc->vma) {
- mm = get_task_mm(alloc->tsk);
- if (!mm)
- goto err_get_task_mm_failed;
+ vma = alloc->vma;
+ if (vma) {
+ if (!mmget_not_zero(alloc->vma_vm_mm))
+ goto err_mmget;
+ mm = alloc->vma_vm_mm;
if (!down_write_trylock(&mm->mmap_sem))
goto err_down_write_mmap_sem_failed;
+ }
+
+ list_lru_isolate(lru, item);
+ spin_unlock(lock);
+ if (vma) {
trace_binder_unmap_user_start(alloc, index);
- zap_page_range(alloc->vma,
+ zap_page_range(vma,
page_addr + alloc->user_buffer_offset,
PAGE_SIZE);
@@ -950,14 +954,13 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
trace_binder_unmap_kernel_end(alloc, index);
- list_lru_isolate(lru, item);
-
+ spin_lock(lock);
mutex_unlock(&alloc->mutex);
- return LRU_REMOVED;
+ return LRU_REMOVED_RETRY;
err_down_write_mmap_sem_failed:
- mmput(mm);
-err_get_task_mm_failed:
+ mmput_async(mm);
+err_mmget:
err_page_already_freed:
mutex_unlock(&alloc->mutex);
err_get_alloc_mutex_failed:
@@ -996,7 +999,6 @@ struct shrinker binder_shrinker = {
*/
void binder_alloc_init(struct binder_alloc *alloc)
{
- alloc->tsk = current->group_leader;
alloc->pid = current->group_leader->pid;
mutex_init(&alloc->mutex);
INIT_LIST_HEAD(&alloc->buffers);
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index a3a3602c689c..2dd33b6df104 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -100,7 +100,6 @@ struct binder_lru_page {
*/
struct binder_alloc {
struct mutex mutex;
- struct task_struct *tsk;
struct vm_area_struct *vma;
struct mm_struct *vma_vm_mm;
void *buffer;
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index cb9b0e9090e3..9f78bb03bb76 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -621,8 +621,11 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev,
static int ahci_pci_reset_controller(struct ata_host *host)
{
struct pci_dev *pdev = to_pci_dev(host->dev);
+ int rc;
- ahci_reset_controller(host);
+ rc = ahci_reset_controller(host);
+ if (rc)
+ return rc;
if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
struct ahci_host_priv *hpriv = host->private_data;
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 8401c3b5be92..b702c20fbc2b 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -492,6 +492,7 @@ static const struct ich_laptop ich_laptop[] = {
{ 0x27DF, 0x152D, 0x0778 }, /* ICH7 on unknown Intel */
{ 0x24CA, 0x1025, 0x0061 }, /* ICH4 on ACER Aspire 2023WLMi */
{ 0x24CA, 0x1025, 0x003d }, /* ICH4 on ACER TM290 */
+ { 0x24CA, 0x10CF, 0x11AB }, /* ICH4M on Fujitsu-Siemens Lifebook S6120 */
{ 0x266F, 0x1025, 0x0066 }, /* ICH6 on ACER Aspire 1694WLMi */
{ 0x2653, 0x1043, 0x82D8 }, /* ICH6M on Asus Eee 701 */
{ 0x27df, 0x104d, 0x900e }, /* ICH7 on Sony TZ-90 */
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 1945a8ea2099..ee4c1ec9dca0 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3234,19 +3234,19 @@ static const struct ata_timing ata_timing[] = {
};
#define ENOUGH(v, unit) (((v)-1)/(unit)+1)
-#define EZ(v, unit) ((v)?ENOUGH(v, unit):0)
+#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0)
static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT)
{
- q->setup = EZ(t->setup * 1000, T);
- q->act8b = EZ(t->act8b * 1000, T);
- q->rec8b = EZ(t->rec8b * 1000, T);
- q->cyc8b = EZ(t->cyc8b * 1000, T);
- q->active = EZ(t->active * 1000, T);
- q->recover = EZ(t->recover * 1000, T);
- q->dmack_hold = EZ(t->dmack_hold * 1000, T);
- q->cycle = EZ(t->cycle * 1000, T);
- q->udma = EZ(t->udma * 1000, UT);
+ q->setup = EZ(t->setup, T);
+ q->act8b = EZ(t->act8b, T);
+ q->rec8b = EZ(t->rec8b, T);
+ q->cyc8b = EZ(t->cyc8b, T);
+ q->active = EZ(t->active, T);
+ q->recover = EZ(t->recover, T);
+ q->dmack_hold = EZ(t->dmack_hold, T);
+ q->cycle = EZ(t->cycle, T);
+ q->udma = EZ(t->udma, UT);
}
void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b,
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index cfeb049a01ef..642afd88870b 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -647,18 +647,25 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf,
static int charlcd_open(struct inode *inode, struct file *file)
{
struct charlcd_priv *priv = to_priv(the_charlcd);
+ int ret;
+ ret = -EBUSY;
if (!atomic_dec_and_test(&charlcd_available))
- return -EBUSY; /* open only once at a time */
+ goto fail; /* open only once at a time */
+ ret = -EPERM;
if (file->f_mode & FMODE_READ) /* device is write-only */
- return -EPERM;
+ goto fail;
if (priv->must_clear) {
charlcd_clear_display(&priv->lcd);
priv->must_clear = false;
}
return nonseekable_open(inode, file);
+
+ fail:
+ atomic_inc(&charlcd_available);
+ return ret;
}
static int charlcd_release(struct inode *inode, struct file *file)
diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c
index df126dcdaf18..6911acd896d9 100644
--- a/drivers/auxdisplay/panel.c
+++ b/drivers/auxdisplay/panel.c
@@ -1105,14 +1105,21 @@ static ssize_t keypad_read(struct file *file,
static int keypad_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = -EBUSY;
if (!atomic_dec_and_test(&keypad_available))
- return -EBUSY; /* open only once at a time */
+ goto fail; /* open only once at a time */
+ ret = -EPERM;
if (file->f_mode & FMODE_WRITE) /* device is read-only */
- return -EPERM;
+ goto fail;
keypad_buflen = 0; /* flush the buffer on opening */
return 0;
+ fail:
+ atomic_inc(&keypad_available);
+ return ret;
}
static int keypad_release(struct inode *inode, struct file *file)
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 41be9ff7d70a..6df7d6676a48 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -166,11 +166,11 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
}
#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+static cpumask_var_t cpus_to_visit __initdata;
+static void __init parsing_done_workfn(struct work_struct *work);
+static __initdata DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-static int
+static int __init
init_cpu_capacity_callback(struct notifier_block *nb,
unsigned long val,
void *data)
@@ -206,7 +206,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
return 0;
}
-static struct notifier_block init_cpu_capacity_notifier = {
+static struct notifier_block init_cpu_capacity_notifier __initdata = {
.notifier_call = init_cpu_capacity_callback,
};
@@ -232,7 +232,7 @@ static int __init register_cpufreq_notifier(void)
}
core_initcall(register_cpufreq_notifier);
-static void parsing_done_workfn(struct work_struct *work)
+static void __init parsing_done_workfn(struct work_struct *work)
{
cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
CPUFREQ_POLICY_NOTIFIER);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 321cd7b4d817..227bac5f1191 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -377,7 +377,8 @@ int register_cpu(struct cpu *cpu, int num)
per_cpu(cpu_sys_devices, num) = &cpu->dev;
register_cpu_under_node(num, cpu_to_node(num));
- dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
+ dev_pm_qos_expose_latency_limit(&cpu->dev,
+ PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
return 0;
}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 3855902f2c5b..aae2402f3791 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -27,13 +27,21 @@ static struct bus_type node_subsys = {
static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf)
{
+ ssize_t n;
+ cpumask_var_t mask;
struct node *node_dev = to_node(dev);
- const struct cpumask *mask = cpumask_of_node(node_dev->dev.id);
/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
- return cpumap_print_to_pagebuf(list, buf, mask);
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return 0;
+
+ cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask);
+ n = cpumap_print_to_pagebuf(list, buf, mask);
+ free_cpumask_var(mask);
+
+ return n;
}
static inline ssize_t node_read_cpumask(struct device *dev,
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index d1bd99271066..9045c5f3734e 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -868,7 +868,8 @@ static ssize_t driver_override_store(struct device *dev,
struct platform_device *pdev = to_platform_device(dev);
char *driver_override, *old, *cp;
- if (count > PATH_MAX)
+ /* We need to keep extra room for a newline */
+ if (count >= (PAGE_SIZE - 1))
return -EINVAL;
driver_override = kstrndup(buf, count, GFP_KERNEL);
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 281f949c5ffe..51751cc8c9e6 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -14,23 +14,20 @@
static int dev_update_qos_constraint(struct device *dev, void *data)
{
s64 *constraint_ns_p = data;
- s32 constraint_ns = -1;
+ s64 constraint_ns = -1;
if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
- if (constraint_ns < 0) {
+ if (constraint_ns < 0)
constraint_ns = dev_pm_qos_read_value(dev);
- constraint_ns *= NSEC_PER_USEC;
- }
- if (constraint_ns == 0)
+
+ if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
return 0;
- /*
- * constraint_ns cannot be negative here, because the device has been
- * suspended.
- */
- if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+ constraint_ns *= NSEC_PER_USEC;
+
+ if (constraint_ns < *constraint_ns_p || *constraint_ns_p < 0)
*constraint_ns_p = constraint_ns;
return 0;
@@ -63,10 +60,14 @@ static bool default_suspend_ok(struct device *dev)
spin_unlock_irqrestore(&dev->power.lock, flags);
- if (constraint_ns < 0)
+ if (constraint_ns == 0)
return false;
- constraint_ns *= NSEC_PER_USEC;
+ if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+ constraint_ns = -1;
+ else
+ constraint_ns *= NSEC_PER_USEC;
+
/*
* We can walk the children without any additional locking, because
* they all have been suspended at this point and their
@@ -76,14 +77,19 @@ static bool default_suspend_ok(struct device *dev)
device_for_each_child(dev, &constraint_ns,
dev_update_qos_constraint);
- if (constraint_ns > 0) {
- constraint_ns -= td->suspend_latency_ns +
- td->resume_latency_ns;
- if (constraint_ns == 0)
- return false;
+ if (constraint_ns < 0) {
+ /* The children have no constraints. */
+ td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+ td->cached_suspend_ok = true;
+ } else {
+ constraint_ns -= td->suspend_latency_ns + td->resume_latency_ns;
+ if (constraint_ns > 0) {
+ td->effective_constraint_ns = constraint_ns;
+ td->cached_suspend_ok = true;
+ } else {
+ td->effective_constraint_ns = 0;
+ }
}
- td->effective_constraint_ns = constraint_ns;
- td->cached_suspend_ok = constraint_ns >= 0;
/*
* The children have been suspended already, so we don't need to take
@@ -145,13 +151,14 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
td = &to_gpd_data(pdd)->td;
constraint_ns = td->effective_constraint_ns;
/* default_suspend_ok() need not be called before us. */
- if (constraint_ns < 0) {
+ if (constraint_ns < 0)
constraint_ns = dev_pm_qos_read_value(pdd->dev);
- constraint_ns *= NSEC_PER_USEC;
- }
- if (constraint_ns == 0)
+
+ if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
continue;
+ constraint_ns *= NSEC_PER_USEC;
+
/*
* constraint_ns cannot be negative here, because the device has
* been suspended.
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 277d43a83f53..7d29286d9313 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -189,7 +189,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
plist_head_init(&c->list);
c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
- c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+ c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
c->type = PM_QOS_MIN;
c->notifiers = n;
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 7bcf80fa9ada..13e015905543 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -253,7 +253,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
|| (dev->power.request_pending
&& dev->power.request == RPM_REQ_RESUME))
retval = -EAGAIN;
- else if (__dev_pm_qos_read_value(dev) < 0)
+ else if (__dev_pm_qos_read_value(dev) == 0)
retval = -EPERM;
else if (dev->power.runtime_status == RPM_SUSPENDED)
retval = 1;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 156ab57bca77..632077f05c57 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -218,7 +218,14 @@ static ssize_t pm_qos_resume_latency_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
+ s32 value = dev_pm_qos_requested_resume_latency(dev);
+
+ if (value == 0)
+ return sprintf(buf, "n/a\n");
+ else if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+ value = 0;
+
+ return sprintf(buf, "%d\n", value);
}
static ssize_t pm_qos_resume_latency_store(struct device *dev,
@@ -228,11 +235,21 @@ static ssize_t pm_qos_resume_latency_store(struct device *dev,
s32 value;
int ret;
- if (kstrtos32(buf, 0, &value))
- return -EINVAL;
+ if (!kstrtos32(buf, 0, &value)) {
+ /*
+ * Prevent users from writing negative or "no constraint" values
+ * directly.
+ */
+ if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+ return -EINVAL;
- if (value < 0)
+ if (value == 0)
+ value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+ } else if (!strcmp(buf, "n/a") || !strcmp(buf, "n/a\n")) {
+ value = 0;
+ } else {
return -EINVAL;
+ }
ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
value);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index d0b65bbe7e15..7ed99c1b2a8b 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -21,6 +21,7 @@
#include <linux/phy.h>
struct property_set {
+ struct device *dev;
struct fwnode_handle fwnode;
const struct property_entry *properties;
};
@@ -682,6 +683,10 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string);
* Caller is responsible to call fwnode_handle_put() on the returned
* args->fwnode pointer.
*
+ * Returns: %0 on success
+ * %-ENOENT when the index is out of bounds, the index has an empty
+ * reference or the property was not found
+ * %-EINVAL on parse error
*/
int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
const char *prop, const char *nargs_prop,
@@ -891,6 +896,7 @@ static struct property_set *pset_copy_set(const struct property_set *pset)
void device_remove_properties(struct device *dev)
{
struct fwnode_handle *fwnode;
+ struct property_set *pset;
fwnode = dev_fwnode(dev);
if (!fwnode)
@@ -900,16 +906,16 @@ void device_remove_properties(struct device *dev)
* the pset. If there is no real firmware node (ACPI/DT) primary
* will hold the pset.
*/
- if (is_pset_node(fwnode)) {
+ pset = to_pset_node(fwnode);
+ if (pset) {
set_primary_fwnode(dev, NULL);
- pset_free_set(to_pset_node(fwnode));
} else {
- fwnode = fwnode->secondary;
- if (!IS_ERR(fwnode) && is_pset_node(fwnode)) {
+ pset = to_pset_node(fwnode->secondary);
+ if (pset && dev == pset->dev)
set_secondary_fwnode(dev, NULL);
- pset_free_set(to_pset_node(fwnode));
- }
}
+ if (pset && dev == pset->dev)
+ pset_free_set(pset);
}
EXPORT_SYMBOL_GPL(device_remove_properties);
@@ -938,6 +944,7 @@ int device_add_properties(struct device *dev,
p->fwnode.ops = &pset_fwnode_ops;
set_secondary_fwnode(dev, &p->fwnode);
+ p->dev = dev;
return 0;
}
EXPORT_SYMBOL_GPL(device_add_properties);
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 4a438b8abe27..2dfe99b328f8 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -17,7 +17,7 @@ if BLK_DEV
config BLK_DEV_NULL_BLK
tristate "Null test block driver"
- depends on CONFIGFS_FS
+ select CONFIGFS_FS
config BLK_DEV_FD
tristate "Normal floppy disk support"
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3684e21d543f..9adfb5445f8d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -243,7 +243,6 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
struct nbd_config *config = nbd->config;
config->blksize = blocksize;
config->bytesize = blocksize * nr_blocks;
- nbd_size_update(nbd);
}
static void nbd_complete_rq(struct request *req)
@@ -387,6 +386,15 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
return result;
}
+/*
+ * Different settings for sk->sk_sndtimeo can result in different return values
+ * if there is a signal pending when we enter sendmsg, because reasons?
+ */
+static inline int was_interrupted(int result)
+{
+ return result == -ERESTARTSYS || result == -EINTR;
+}
+
/* always call with the tx_lock held */
static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
{
@@ -459,7 +467,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
result = sock_xmit(nbd, index, 1, &from,
(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
if (result <= 0) {
- if (result == -ERESTARTSYS) {
+ if (was_interrupted(result)) {
/* If we havne't sent anything we can just return BUSY,
* however if we have sent something we need to make
* sure we only allow this req to be sent until we are
@@ -503,7 +511,7 @@ send_pages:
}
result = sock_xmit(nbd, index, 1, &from, flags, &sent);
if (result <= 0) {
- if (result == -ERESTARTSYS) {
+ if (was_interrupted(result)) {
/* We've already sent the header, we
* have no choice but to set pending and
* return BUSY.
@@ -820,9 +828,13 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
* appropriate.
*/
ret = nbd_handle_cmd(cmd, hctx->queue_num);
+ if (ret < 0)
+ ret = BLK_STS_IOERR;
+ else if (!ret)
+ ret = BLK_STS_OK;
complete(&cmd->send_complete);
- return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK;
+ return ret;
}
static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
@@ -1090,6 +1102,7 @@ static int nbd_start_device(struct nbd_device *nbd)
args->index = i;
queue_work(recv_workqueue, &args->work);
}
+ nbd_size_update(nbd);
return error;
}
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 7cedb4295e9d..64d0fc17c174 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -2604,7 +2604,7 @@ static void *skd_alloc_dma(struct skd_device *skdev, struct kmem_cache *s,
return NULL;
*dma_handle = dma_map_single(dev, buf, s->size, dir);
if (dma_mapping_error(dev, *dma_handle)) {
- kfree(buf);
+ kmem_cache_free(s, buf);
buf = NULL;
}
return buf;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 2981c27d3aae..f149d3e61234 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -766,27 +766,6 @@ static void zram_slot_unlock(struct zram *zram, u32 index)
bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
}
-static bool zram_same_page_read(struct zram *zram, u32 index,
- struct page *page,
- unsigned int offset, unsigned int len)
-{
- zram_slot_lock(zram, index);
- if (unlikely(!zram_get_handle(zram, index) ||
- zram_test_flag(zram, index, ZRAM_SAME))) {
- void *mem;
-
- zram_slot_unlock(zram, index);
- mem = kmap_atomic(page);
- zram_fill_page(mem + offset, len,
- zram_get_element(zram, index));
- kunmap_atomic(mem);
- return true;
- }
- zram_slot_unlock(zram, index);
-
- return false;
-}
-
static void zram_meta_free(struct zram *zram, u64 disksize)
{
size_t num_pages = disksize >> PAGE_SHIFT;
@@ -884,11 +863,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
zram_slot_unlock(zram, index);
}
- if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE))
- return 0;
-
zram_slot_lock(zram, index);
handle = zram_get_handle(zram, index);
+ if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
+ unsigned long value;
+ void *mem;
+
+ value = handle ? zram_get_element(zram, index) : 0;
+ mem = kmap_atomic(page);
+ zram_fill_page(mem, PAGE_SIZE, value);
+ kunmap_atomic(mem);
+ zram_slot_unlock(zram, index);
+ return 0;
+ }
+
size = zram_get_obj_size(zram, index);
src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index c7f396903184..70db4d5638a6 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -720,7 +720,7 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
if (mbus->hw_io_coherency)
w->mbus_attr |= ATTR_HW_COHERENCY;
w->base = base & DDR_BASE_CS_LOW_MASK;
- w->size = (size | ~DDR_SIZE_MASK) + 1;
+ w->size = (u64)(size | ~DDR_SIZE_MASK) + 1;
}
}
mvebu_mbus_dram_info.num_cs = cs;
diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c
index c834f5abfc49..4c10456f8a32 100644
--- a/drivers/clk/clk-bulk.c
+++ b/drivers/clk/clk-bulk.c
@@ -105,6 +105,7 @@ err:
return ret;
}
+EXPORT_SYMBOL_GPL(clk_bulk_prepare);
#endif /* CONFIG_HAVE_CLK_PREPARE */
diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c
index 62d7854e4b87..5970a50671b9 100644
--- a/drivers/clk/rockchip/clk-rk3128.c
+++ b/drivers/clk/rockchip/clk-rk3128.c
@@ -315,13 +315,13 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
RK2928_CLKGATE_CON(10), 8, GFLAGS),
GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0,
- RK2928_CLKGATE_CON(10), 8, GFLAGS),
+ RK2928_CLKGATE_CON(10), 0, GFLAGS),
GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0,
- RK2928_CLKGATE_CON(10), 8, GFLAGS),
+ RK2928_CLKGATE_CON(10), 1, GFLAGS),
GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0,
- RK2928_CLKGATE_CON(10), 8, GFLAGS),
+ RK2928_CLKGATE_CON(10), 2, GFLAGS),
GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
- RK2928_CLKGATE_CON(10), 8, GFLAGS),
+ RK2928_CLKGATE_CON(2), 15, GFLAGS),
COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
@@ -541,7 +541,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS),
GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS),
- GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS),
+ GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS),
GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS),
/* PD_MMC */
@@ -577,6 +577,8 @@ static const char *const rk3128_critical_clocks[] __initconst = {
"aclk_peri",
"hclk_peri",
"pclk_peri",
+ "pclk_pmu",
+ "sclk_timer5",
};
static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index e40b77583c47..d8d3cb67b402 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -294,6 +294,18 @@ static const struct samsung_clk_reg_dump src_mask_suspend_e4210[] = {
#define PLL_ENABLED (1 << 31)
#define PLL_LOCKED (1 << 29)
+static void exynos4_clk_enable_pll(u32 reg)
+{
+ u32 pll_con = readl(reg_base + reg);
+ pll_con |= PLL_ENABLED;
+ writel(pll_con, reg_base + reg);
+
+ while (!(pll_con & PLL_LOCKED)) {
+ cpu_relax();
+ pll_con = readl(reg_base + reg);
+ }
+}
+
static void exynos4_clk_wait_for_pll(u32 reg)
{
u32 pll_con;
@@ -315,6 +327,9 @@ static int exynos4_clk_suspend(void)
samsung_clk_save(reg_base, exynos4_save_pll,
ARRAY_SIZE(exynos4_clk_pll_regs));
+ exynos4_clk_enable_pll(EPLL_CON0);
+ exynos4_clk_enable_pll(VPLL_CON0);
+
if (exynos4_soc == EXYNOS4210) {
samsung_clk_save(reg_base, exynos4_save_soc,
ARRAY_SIZE(exynos4210_clk_save));
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index a1df588343f2..1de8cac99a0e 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -117,7 +117,8 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id)
/* Turn off the clock (and clear the event) */
disable_timer(cs5535_event_clock);
- if (clockevent_state_shutdown(&cs5535_clockevent))
+ if (clockevent_state_detached(&cs5535_clockevent) ||
+ clockevent_state_shutdown(&cs5535_clockevent))
return IRQ_HANDLED;
/* Clear the counter */
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 48eaf2879228..aa390404e85f 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -298,8 +298,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
data->needs_update = 0;
}
- /* resume_latency is 0 means no restriction */
- if (resume_latency && resume_latency < latency_req)
+ if (resume_latency < latency_req &&
+ resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
latency_req = resume_latency;
/* Special case when user has set very strict latency requirement */
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index d9fbbf01062b..0f9754e07719 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -349,8 +349,6 @@ struct artpec6_crypto_aead_req_ctx {
/* The crypto framework makes it hard to avoid this global. */
static struct device *artpec6_crypto_dev;
-static struct dentry *dbgfs_root;
-
#ifdef CONFIG_FAULT_INJECTION
static DECLARE_FAULT_ATTR(artpec6_crypto_fail_status_read);
static DECLARE_FAULT_ATTR(artpec6_crypto_fail_dma_array_full);
@@ -2984,6 +2982,8 @@ struct dbgfs_u32 {
char *desc;
};
+static struct dentry *dbgfs_root;
+
static void artpec6_crypto_init_debugfs(void)
{
dbgfs_root = debugfs_create_dir("artpec6_crypto", NULL);
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index b585ce54a802..4835dd4a9e50 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -553,9 +553,9 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev)
{
struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req);
struct scatterlist sg[1], *tsg;
- int err = 0, len = 0, reg, ncp;
+ int err = 0, len = 0, reg, ncp = 0;
unsigned int i;
- const u32 *buffer = (const u32 *)rctx->buffer;
+ u32 *buffer = (void *)rctx->buffer;
rctx->sg = hdev->req->src;
rctx->total = hdev->req->nbytes;
@@ -620,10 +620,13 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev)
reg |= HASH_CR_DMAA;
stm32_hash_write(hdev, HASH_CR, reg);
- for (i = 0; i < DIV_ROUND_UP(ncp, sizeof(u32)); i++)
- stm32_hash_write(hdev, HASH_DIN, buffer[i]);
-
- stm32_hash_set_nblw(hdev, ncp);
+ if (ncp) {
+ memset(buffer + ncp, 0,
+ DIV_ROUND_UP(ncp, sizeof(u32)) - ncp);
+ writesl(hdev->io_base + HASH_DIN, buffer,
+ DIV_ROUND_UP(ncp, sizeof(u32)));
+ }
+ stm32_hash_set_nblw(hdev, DIV_ROUND_UP(ncp, sizeof(u32)));
reg = stm32_hash_read(hdev, HASH_STR);
reg |= HASH_STR_DCAL;
stm32_hash_write(hdev, HASH_STR, reg);
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 66fb40d0ebdb..03830634e141 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -383,7 +383,7 @@ err_put_fd:
return err;
}
-static void sync_fill_fence_info(struct dma_fence *fence,
+static int sync_fill_fence_info(struct dma_fence *fence,
struct sync_fence_info *info)
{
strlcpy(info->obj_name, fence->ops->get_timeline_name(fence),
@@ -399,6 +399,8 @@ static void sync_fill_fence_info(struct dma_fence *fence,
test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ?
ktime_to_ns(fence->timestamp) :
ktime_set(0, 0);
+
+ return info->status;
}
static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
@@ -424,8 +426,12 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
* sync_fence_info and return the actual number of fences on
* info->num_fences.
*/
- if (!info.num_fences)
+ if (!info.num_fences) {
+ info.status = dma_fence_is_signaled(sync_file->fence);
goto no_fences;
+ } else {
+ info.status = 1;
+ }
if (info.num_fences < num_fences)
return -EINVAL;
@@ -435,8 +441,10 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
if (!fence_info)
return -ENOMEM;
- for (i = 0; i < num_fences; i++)
- sync_fill_fence_info(fences[i], &fence_info[i]);
+ for (i = 0; i < num_fences; i++) {
+ int status = sync_fill_fence_info(fences[i], &fence_info[i]);
+ info.status = info.status <= 0 ? info.status : status;
+ }
if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info,
size)) {
@@ -446,7 +454,6 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
no_fences:
sync_file_get_name(sync_file, info.name, sizeof(info.name));
- info.status = dma_fence_is_signaled(sync_file->fence);
info.num_fences = num_fences;
if (copy_to_user((void __user *)arg, &info, sizeof(info)))
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index 32905d5606ac..55f9c62ee54b 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -212,11 +212,12 @@ struct msgdma_device {
static struct msgdma_sw_desc *msgdma_get_descriptor(struct msgdma_device *mdev)
{
struct msgdma_sw_desc *desc;
+ unsigned long flags;
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, flags);
desc = list_first_entry(&mdev->free_list, struct msgdma_sw_desc, node);
list_del(&desc->node);
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, flags);
INIT_LIST_HEAD(&desc->tx_list);
@@ -306,13 +307,14 @@ static dma_cookie_t msgdma_tx_submit(struct dma_async_tx_descriptor *tx)
struct msgdma_device *mdev = to_mdev(tx->chan);
struct msgdma_sw_desc *new;
dma_cookie_t cookie;
+ unsigned long flags;
new = tx_to_desc(tx);
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, flags);
cookie = dma_cookie_assign(tx);
list_add_tail(&new->node, &mdev->pending_list);
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, flags);
return cookie;
}
@@ -336,17 +338,18 @@ msgdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst,
struct msgdma_extended_desc *desc;
size_t copy;
u32 desc_cnt;
+ unsigned long irqflags;
desc_cnt = DIV_ROUND_UP(len, MSGDMA_MAX_TRANS_LEN);
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, irqflags);
if (desc_cnt > mdev->desc_free_cnt) {
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, irqflags);
dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev);
return NULL;
}
mdev->desc_free_cnt -= desc_cnt;
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, irqflags);
do {
/* Allocate and populate the descriptor */
@@ -397,18 +400,19 @@ msgdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
u32 desc_cnt = 0, i;
struct scatterlist *sg;
u32 stride;
+ unsigned long irqflags;
for_each_sg(sgl, sg, sg_len, i)
desc_cnt += DIV_ROUND_UP(sg_dma_len(sg), MSGDMA_MAX_TRANS_LEN);
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, irqflags);
if (desc_cnt > mdev->desc_free_cnt) {
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, irqflags);
dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev);
return NULL;
}
mdev->desc_free_cnt -= desc_cnt;
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, irqflags);
avail = sg_dma_len(sgl);
@@ -566,10 +570,11 @@ static void msgdma_start_transfer(struct msgdma_device *mdev)
static void msgdma_issue_pending(struct dma_chan *chan)
{
struct msgdma_device *mdev = to_mdev(chan);
+ unsigned long flags;
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, flags);
msgdma_start_transfer(mdev);
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, flags);
}
/**
@@ -634,10 +639,11 @@ static void msgdma_free_descriptors(struct msgdma_device *mdev)
static void msgdma_free_chan_resources(struct dma_chan *dchan)
{
struct msgdma_device *mdev = to_mdev(dchan);
+ unsigned long flags;
- spin_lock_bh(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, flags);
msgdma_free_descriptors(mdev);
- spin_unlock_bh(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, flags);
kfree(mdev->sw_desq);
}
@@ -682,8 +688,9 @@ static void msgdma_tasklet(unsigned long data)
u32 count;
u32 __maybe_unused size;
u32 __maybe_unused status;
+ unsigned long flags;
- spin_lock(&mdev->lock);
+ spin_lock_irqsave(&mdev->lock, flags);
/* Read number of responses that are available */
count = ioread32(mdev->csr + MSGDMA_CSR_RESP_FILL_LEVEL);
@@ -698,13 +705,13 @@ static void msgdma_tasklet(unsigned long data)
* bits. So we need to just drop these values.
*/
size = ioread32(mdev->resp + MSGDMA_RESP_BYTES_TRANSFERRED);
- status = ioread32(mdev->resp - MSGDMA_RESP_STATUS);
+ status = ioread32(mdev->resp + MSGDMA_RESP_STATUS);
msgdma_complete_descriptor(mdev);
msgdma_chan_desc_cleanup(mdev);
}
- spin_unlock(&mdev->lock);
+ spin_unlock_irqrestore(&mdev->lock, flags);
}
/**
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 3879f80a4815..a7ea20e7b8e9 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1143,11 +1143,24 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
struct edma_desc *edesc;
struct device *dev = chan->device->dev;
struct edma_chan *echan = to_edma_chan(chan);
- unsigned int width, pset_len;
+ unsigned int width, pset_len, array_size;
if (unlikely(!echan || !len))
return NULL;
+ /* Align the array size (acnt block) with the transfer properties */
+ switch (__ffs((src | dest | len))) {
+ case 0:
+ array_size = SZ_32K - 1;
+ break;
+ case 1:
+ array_size = SZ_32K - 2;
+ break;
+ default:
+ array_size = SZ_32K - 4;
+ break;
+ }
+
if (len < SZ_64K) {
/*
* Transfer size less than 64K can be handled with one paRAM
@@ -1169,7 +1182,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
* When the full_length is multibple of 32767 one slot can be
* used to complete the transfer.
*/
- width = SZ_32K - 1;
+ width = array_size;
pset_len = rounddown(len, width);
/* One slot is enough for lengths multiple of (SZ_32K -1) */
if (unlikely(pset_len == len))
@@ -1217,7 +1230,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
}
dest += pset_len;
src += pset_len;
- pset_len = width = len % (SZ_32K - 1);
+ pset_len = width = len % array_size;
ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1,
width, pset_len, DMA_MEM_TO_MEM);
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 2f65a8fde21d..f1d04b70ee67 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -262,13 +262,14 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
mutex_lock(&xbar->mutex);
map->xbar_out = find_first_zero_bit(xbar->dma_inuse,
xbar->dma_requests);
- mutex_unlock(&xbar->mutex);
if (map->xbar_out == xbar->dma_requests) {
+ mutex_unlock(&xbar->mutex);
dev_err(&pdev->dev, "Run out of free DMA requests\n");
kfree(map);
return ERR_PTR(-ENOMEM);
}
set_bit(map->xbar_out, xbar->dma_inuse);
+ mutex_unlock(&xbar->mutex);
map->xbar_in = (u16)dma_spec->args[0];
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 1cb2d1c070c3..a94601d5939e 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -238,7 +238,8 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
efi_random_get_seed(sys_table);
- if (!nokaslr()) {
+ /* hibernation expects the runtime regions to stay in the same place */
+ if (!IS_ENABLED(CONFIG_HIBERNATION) && !nokaslr()) {
/*
* Randomize the base of the UEFI runtime services region.
* Preserve the 2 MB alignment of the region by taking a
diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c
index 08129b7b80ab..41c48a1e8baa 100644
--- a/drivers/firmware/efi/test/efi_test.c
+++ b/drivers/firmware/efi/test/efi_test.c
@@ -593,6 +593,9 @@ static long efi_runtime_query_capsulecaps(unsigned long arg)
if (copy_from_user(&qcaps, qcaps_user, sizeof(qcaps)))
return -EFAULT;
+ if (qcaps.capsule_count == ULONG_MAX)
+ return -EINVAL;
+
capsules = kcalloc(qcaps.capsule_count + 1,
sizeof(efi_capsule_header_t), GFP_KERNEL);
if (!capsules)
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index 08629ee69d11..00e73d28077c 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -361,12 +361,12 @@ static const struct fpga_manager_ops altera_cvp_ops = {
.write_complete = altera_cvp_write_complete,
};
-static ssize_t show_chkcfg(struct device_driver *dev, char *buf)
+static ssize_t chkcfg_show(struct device_driver *dev, char *buf)
{
return snprintf(buf, 3, "%d\n", altera_cvp_chkcfg);
}
-static ssize_t store_chkcfg(struct device_driver *drv, const char *buf,
+static ssize_t chkcfg_store(struct device_driver *drv, const char *buf,
size_t count)
{
int ret;
@@ -378,7 +378,7 @@ static ssize_t store_chkcfg(struct device_driver *drv, const char *buf,
return count;
}
-static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg);
+static DRIVER_ATTR_RW(chkcfg);
static int altera_cvp_probe(struct pci_dev *pdev,
const struct pci_device_id *dev_id);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 3388d54ba114..3f80f167ed56 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -453,7 +453,8 @@ config GPIO_TS4800
config GPIO_THUNDERX
tristate "Cavium ThunderX/OCTEON-TX GPIO"
depends on ARCH_THUNDER || (64BIT && COMPILE_TEST)
- depends on PCI_MSI && IRQ_DOMAIN_HIERARCHY
+ depends on PCI_MSI
+ select IRQ_DOMAIN_HIERARCHY
select IRQ_FASTEOI_HIERARCHY_HANDLERS
help
Say yes here to support the on-chip GPIO lines on the ThunderX
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index dbf869fb63ce..3233b72b6828 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -518,7 +518,13 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
irq_set_handler_locked(d, handle_level_irq);
else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
- irq_set_handler_locked(d, handle_edge_irq);
+ /*
+ * Edge IRQs are already cleared/acked in irq_handler and
+ * not need to be masked, as result handle_edge_irq()
+ * logic is excessed here and may cause lose of interrupts.
+ * So just use handle_simple_irq.
+ */
+ irq_set_handler_locked(d, handle_simple_irq);
return 0;
@@ -678,7 +684,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank)
{
void __iomem *isr_reg = NULL;
- u32 isr;
+ u32 enabled, isr, level_mask;
unsigned int bit;
struct gpio_bank *bank = gpiobank;
unsigned long wa_lock_flags;
@@ -691,23 +697,21 @@ static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank)
pm_runtime_get_sync(bank->chip.parent);
while (1) {
- u32 isr_saved, level_mask = 0;
- u32 enabled;
-
raw_spin_lock_irqsave(&bank->lock, lock_flags);
enabled = omap_get_gpio_irqbank_mask(bank);
- isr_saved = isr = readl_relaxed(isr_reg) & enabled;
+ isr = readl_relaxed(isr_reg) & enabled;
if (bank->level_mask)
level_mask = bank->level_mask & enabled;
+ else
+ level_mask = 0;
/* clear edge sensitive interrupts before handler(s) are
called so that we don't miss any interrupt occurred while
executing them */
- omap_disable_gpio_irqbank(bank, isr_saved & ~level_mask);
- omap_clear_gpio_irqbank(bank, isr_saved & ~level_mask);
- omap_enable_gpio_irqbank(bank, isr_saved & ~level_mask);
+ if (isr & ~level_mask)
+ omap_clear_gpio_irqbank(bank, isr & ~level_mask);
raw_spin_unlock_irqrestore(&bank->lock, lock_flags);
@@ -1010,7 +1014,7 @@ static void omap_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
/*---------------------------------------------------------------------*/
-static void __init omap_gpio_show_rev(struct gpio_bank *bank)
+static void omap_gpio_show_rev(struct gpio_bank *bank)
{
static bool called;
u32 rev;
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 4d2113530735..eb4528c87c0b 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -203,7 +203,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
if (pin <= 255) {
char ev_name[5];
- sprintf(ev_name, "_%c%02X",
+ sprintf(ev_name, "_%c%02hhX",
agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L',
pin);
if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index a3fdc5a68dff..81ff79336623 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -17,7 +17,7 @@ drm-y := drm_auth.o drm_bufs.o drm_cache.o \
drm_encoder.o drm_mode_object.o drm_property.o \
drm_plane.o drm_color_mgmt.o drm_print.o \
drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
- drm_syncobj.o
+ drm_syncobj.o drm_lease.o
drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
drm-$(CONFIG_DRM_VM) += drm_vm.o
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 25a95c95df14..ef9a3b6d7b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -25,7 +25,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
amdgpu_prime.o amdgpu_vm.o amdgpu_ib.o amdgpu_pll.o \
amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
- amdgpu_queue_mgr.o amdgpu_vf_error.o
+ amdgpu_queue_mgr.o amdgpu_vf_error.o amdgpu_sched.o
# add asic specific block
amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index ebfc267467ee..cbcb6a153aba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -121,6 +121,7 @@ extern int amdgpu_cntl_sb_buf_per_se;
extern int amdgpu_param_buf_per_se;
extern int amdgpu_job_hang_limit;
extern int amdgpu_lbpw;
+extern int amdgpu_compute_multipipe;
#ifdef CONFIG_DRM_AMDGPU_SI
extern int amdgpu_si_support;
@@ -731,10 +732,14 @@ struct amdgpu_ctx {
struct amdgpu_device *adev;
struct amdgpu_queue_mgr queue_mgr;
unsigned reset_counter;
+ uint32_t vram_lost_counter;
spinlock_t ring_lock;
struct dma_fence **fences;
struct amdgpu_ctx_ring rings[AMDGPU_MAX_RINGS];
- bool preamble_presented;
+ bool preamble_presented;
+ enum amd_sched_priority init_priority;
+ enum amd_sched_priority override_priority;
+ struct mutex lock;
};
struct amdgpu_ctx_mgr {
@@ -751,13 +756,18 @@ int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
struct dma_fence *fence, uint64_t *seq);
struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
struct amdgpu_ring *ring, uint64_t seq);
+void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
+ enum amd_sched_priority priority);
int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
+int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
+
void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
+
/*
* file private structure
*/
@@ -769,7 +779,6 @@ struct amdgpu_fpriv {
struct mutex bo_list_lock;
struct idr bo_list_handles;
struct amdgpu_ctx_mgr ctx_mgr;
- u32 vram_lost_counter;
};
/*
@@ -870,7 +879,7 @@ struct amdgpu_mec {
struct amdgpu_kiq {
u64 eop_gpu_addr;
struct amdgpu_bo *eop_obj;
- struct mutex ring_mutex;
+ spinlock_t ring_lock;
struct amdgpu_ring ring;
struct amdgpu_irq_src irq;
};
@@ -1034,6 +1043,10 @@ struct amdgpu_gfx {
bool in_suspend;
/* NGG */
struct amdgpu_ngg ngg;
+
+ /* pipe reservation */
+ struct mutex pipe_reserve_mutex;
+ DECLARE_BITMAP (pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
};
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -1112,6 +1125,7 @@ struct amdgpu_job {
uint32_t gds_base, gds_size;
uint32_t gws_base, gws_size;
uint32_t oa_base, oa_size;
+ uint32_t vram_lost_counter;
/* user fence handling */
uint64_t uf_addr;
@@ -1137,7 +1151,7 @@ static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p,
/*
* Writeback
*/
-#define AMDGPU_MAX_WB 1024 /* Reserve at most 1024 WB slots for amdgpu-owned rings. */
+#define AMDGPU_MAX_WB 512 /* Reserve at most 512 WB slots for amdgpu-owned rings. */
struct amdgpu_wb {
struct amdgpu_bo *wb_obj;
@@ -1310,6 +1324,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *filp);
int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
@@ -1376,6 +1392,18 @@ struct amdgpu_atcs {
};
/*
+ * Firmware VRAM reservation
+ */
+struct amdgpu_fw_vram_usage {
+ u64 start_offset;
+ u64 size;
+ struct amdgpu_bo *reserved_bo;
+ void *va;
+};
+
+int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev);
+
+/*
* CGS
*/
struct cgs_device *amdgpu_cgs_create_device(struct amdgpu_device *adev);
@@ -1524,7 +1552,6 @@ struct amdgpu_device {
/* powerplay */
struct amd_powerplay powerplay;
- bool pp_enabled;
bool pp_force_state_enabled;
/* dpm */
@@ -1580,6 +1607,8 @@ struct amdgpu_device {
struct delayed_work late_init_work;
struct amdgpu_virt virt;
+ /* firmware VRAM reservation */
+ struct amdgpu_fw_vram_usage fw_vram_usage;
/* link all shadow bo */
struct list_head shadow_list;
@@ -1831,8 +1860,6 @@ static inline bool amdgpu_has_atpx(void) { return false; }
extern const struct drm_ioctl_desc amdgpu_ioctls_kms[];
extern const int amdgpu_max_kms_ioctl;
-bool amdgpu_kms_vram_lost(struct amdgpu_device *adev,
- struct amdgpu_fpriv *fpriv);
int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags);
void amdgpu_driver_unload_kms(struct drm_device *dev);
void amdgpu_driver_lastclose_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index a52795d9b458..c04f44a90392 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -35,41 +35,50 @@
#include "acp_gfx_if.h"
-#define ACP_TILE_ON_MASK 0x03
-#define ACP_TILE_OFF_MASK 0x02
-#define ACP_TILE_ON_RETAIN_REG_MASK 0x1f
-#define ACP_TILE_OFF_RETAIN_REG_MASK 0x20
-
-#define ACP_TILE_P1_MASK 0x3e
-#define ACP_TILE_P2_MASK 0x3d
-#define ACP_TILE_DSP0_MASK 0x3b
-#define ACP_TILE_DSP1_MASK 0x37
-
-#define ACP_TILE_DSP2_MASK 0x2f
-
-#define ACP_DMA_REGS_END 0x146c0
-#define ACP_I2S_PLAY_REGS_START 0x14840
-#define ACP_I2S_PLAY_REGS_END 0x148b4
-#define ACP_I2S_CAP_REGS_START 0x148b8
-#define ACP_I2S_CAP_REGS_END 0x1496c
-
-#define ACP_I2S_COMP1_CAP_REG_OFFSET 0xac
-#define ACP_I2S_COMP2_CAP_REG_OFFSET 0xa8
-#define ACP_I2S_COMP1_PLAY_REG_OFFSET 0x6c
-#define ACP_I2S_COMP2_PLAY_REG_OFFSET 0x68
-
-#define mmACP_PGFSM_RETAIN_REG 0x51c9
-#define mmACP_PGFSM_CONFIG_REG 0x51ca
-#define mmACP_PGFSM_READ_REG_0 0x51cc
-
-#define mmACP_MEM_SHUT_DOWN_REQ_LO 0x51f8
-#define mmACP_MEM_SHUT_DOWN_REQ_HI 0x51f9
-#define mmACP_MEM_SHUT_DOWN_STS_LO 0x51fa
-#define mmACP_MEM_SHUT_DOWN_STS_HI 0x51fb
-
-#define ACP_TIMEOUT_LOOP 0x000000FF
-#define ACP_DEVS 3
-#define ACP_SRC_ID 162
+#define ACP_TILE_ON_MASK 0x03
+#define ACP_TILE_OFF_MASK 0x02
+#define ACP_TILE_ON_RETAIN_REG_MASK 0x1f
+#define ACP_TILE_OFF_RETAIN_REG_MASK 0x20
+
+#define ACP_TILE_P1_MASK 0x3e
+#define ACP_TILE_P2_MASK 0x3d
+#define ACP_TILE_DSP0_MASK 0x3b
+#define ACP_TILE_DSP1_MASK 0x37
+
+#define ACP_TILE_DSP2_MASK 0x2f
+
+#define ACP_DMA_REGS_END 0x146c0
+#define ACP_I2S_PLAY_REGS_START 0x14840
+#define ACP_I2S_PLAY_REGS_END 0x148b4
+#define ACP_I2S_CAP_REGS_START 0x148b8
+#define ACP_I2S_CAP_REGS_END 0x1496c
+
+#define ACP_I2S_COMP1_CAP_REG_OFFSET 0xac
+#define ACP_I2S_COMP2_CAP_REG_OFFSET 0xa8
+#define ACP_I2S_COMP1_PLAY_REG_OFFSET 0x6c
+#define ACP_I2S_COMP2_PLAY_REG_OFFSET 0x68
+
+#define mmACP_PGFSM_RETAIN_REG 0x51c9
+#define mmACP_PGFSM_CONFIG_REG 0x51ca
+#define mmACP_PGFSM_READ_REG_0 0x51cc
+
+#define mmACP_MEM_SHUT_DOWN_REQ_LO 0x51f8
+#define mmACP_MEM_SHUT_DOWN_REQ_HI 0x51f9
+#define mmACP_MEM_SHUT_DOWN_STS_LO 0x51fa
+#define mmACP_MEM_SHUT_DOWN_STS_HI 0x51fb
+
+#define mmACP_CONTROL 0x5131
+#define mmACP_STATUS 0x5133
+#define mmACP_SOFT_RESET 0x5134
+#define ACP_CONTROL__ClkEn_MASK 0x1
+#define ACP_SOFT_RESET__SoftResetAud_MASK 0x100
+#define ACP_SOFT_RESET__SoftResetAudDone_MASK 0x1000000
+#define ACP_CLOCK_EN_TIME_OUT_VALUE 0x000000FF
+#define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE 0x000000FF
+
+#define ACP_TIMEOUT_LOOP 0x000000FF
+#define ACP_DEVS 3
+#define ACP_SRC_ID 162
enum {
ACP_TILE_P1 = 0,
@@ -260,6 +269,8 @@ static int acp_hw_init(void *handle)
{
int r, i;
uint64_t acp_base;
+ u32 val = 0;
+ u32 count = 0;
struct device *dev;
struct i2s_platform_data *i2s_pdata;
@@ -371,6 +382,8 @@ static int acp_hw_init(void *handle)
adev->acp.acp_cell[0].name = "acp_audio_dma";
adev->acp.acp_cell[0].num_resources = 4;
adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0];
+ adev->acp.acp_cell[0].platform_data = &adev->asic_type;
+ adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type);
adev->acp.acp_cell[1].name = "designware-i2s";
adev->acp.acp_cell[1].num_resources = 1;
@@ -400,6 +413,46 @@ static int acp_hw_init(void *handle)
}
}
+ /* Assert Soft reset of ACP */
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
+
+ val |= ACP_SOFT_RESET__SoftResetAud_MASK;
+ cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
+
+ count = ACP_SOFT_RESET_DONE_TIME_OUT_VALUE;
+ while (true) {
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
+ if (ACP_SOFT_RESET__SoftResetAudDone_MASK ==
+ (val & ACP_SOFT_RESET__SoftResetAudDone_MASK))
+ break;
+ if (--count == 0) {
+ dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
+ return -ETIMEDOUT;
+ }
+ udelay(100);
+ }
+ /* Enable clock to ACP and wait until the clock is enabled */
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_CONTROL);
+ val = val | ACP_CONTROL__ClkEn_MASK;
+ cgs_write_register(adev->acp.cgs_device, mmACP_CONTROL, val);
+
+ count = ACP_CLOCK_EN_TIME_OUT_VALUE;
+
+ while (true) {
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_STATUS);
+ if (val & (u32) 0x1)
+ break;
+ if (--count == 0) {
+ dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
+ return -ETIMEDOUT;
+ }
+ udelay(100);
+ }
+ /* Deassert the SOFT RESET flags */
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
+ val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
+ cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
+
return 0;
}
@@ -412,6 +465,8 @@ static int acp_hw_init(void *handle)
static int acp_hw_fini(void *handle)
{
int i, ret;
+ u32 val = 0;
+ u32 count = 0;
struct device *dev;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -419,6 +474,42 @@ static int acp_hw_fini(void *handle)
if (!adev->acp.acp_cell)
return 0;
+ /* Assert Soft reset of ACP */
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
+
+ val |= ACP_SOFT_RESET__SoftResetAud_MASK;
+ cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
+
+ count = ACP_SOFT_RESET_DONE_TIME_OUT_VALUE;
+ while (true) {
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
+ if (ACP_SOFT_RESET__SoftResetAudDone_MASK ==
+ (val & ACP_SOFT_RESET__SoftResetAudDone_MASK))
+ break;
+ if (--count == 0) {
+ dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
+ return -ETIMEDOUT;
+ }
+ udelay(100);
+ }
+ /* Disable ACP clock */
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_CONTROL);
+ val &= ~ACP_CONTROL__ClkEn_MASK;
+ cgs_write_register(adev->acp.cgs_device, mmACP_CONTROL, val);
+
+ count = ACP_CLOCK_EN_TIME_OUT_VALUE;
+
+ while (true) {
+ val = cgs_read_register(adev->acp.cgs_device, mmACP_STATUS);
+ if (val & (u32) 0x1)
+ break;
+ if (--count == 0) {
+ dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
+ return -ETIMEDOUT;
+ }
+ udelay(100);
+ }
+
if (adev->acp.acp_genpd) {
for (i = 0; i < ACP_DEVS ; i++) {
dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index dc7e25cce741..47d1c132ac40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -338,6 +338,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
struct cik_mqd *m;
uint32_t *mqd_hqd;
uint32_t reg, wptr_val, data;
+ bool valid_wptr = false;
m = get_mqd(mqd);
@@ -356,7 +357,14 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, data);
- if (read_user_wptr(mm, wptr, wptr_val))
+ /* read_user_ptr may take the mm->mmap_sem.
+ * release srbm_mutex to avoid circular dependency between
+ * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
+ */
+ release_queue(kgd);
+ valid_wptr = read_user_wptr(mm, wptr, wptr_val);
+ acquire_queue(kgd, pipe_id, queue_id);
+ if (valid_wptr)
WREG32(mmCP_HQD_PQ_WPTR, (wptr_val << wptr_shift) & wptr_mask);
data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index c678c69936a0..056929b8ccd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -292,6 +292,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
struct vi_mqd *m;
uint32_t *mqd_hqd;
uint32_t reg, wptr_val, data;
+ bool valid_wptr = false;
m = get_mqd(mqd);
@@ -339,7 +340,14 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, data);
- if (read_user_wptr(mm, wptr, wptr_val))
+ /* read_user_ptr may take the mm->mmap_sem.
+ * release srbm_mutex to avoid circular dependency between
+ * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
+ */
+ release_queue(kgd);
+ valid_wptr = read_user_wptr(mm, wptr, wptr_val);
+ acquire_queue(kgd, pipe_id, queue_id);
+ if (valid_wptr)
WREG32(mmCP_HQD_PQ_WPTR, (wptr_val << wptr_shift) & wptr_mask);
data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index ce443586a0c7..f450b69323fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1766,34 +1766,32 @@ bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev)
return true;
}
-/* Atom needs data in little endian format
- * so swap as appropriate when copying data to
- * or from atom. Note that atom operates on
- * dw units.
+/* Atom needs data in little endian format so swap as appropriate when copying
+ * data to or from atom. Note that atom operates on dw units.
+ *
+ * Use to_le=true when sending data to atom and provide at least
+ * ALIGN(num_bytes,4) bytes in the dst buffer.
+ *
+ * Use to_le=false when receiving data from atom and provide ALIGN(num_bytes,4)
+ * byes in the src buffer.
*/
void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
{
#ifdef __BIG_ENDIAN
- u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
- u32 *dst32, *src32;
+ u32 src_tmp[5], dst_tmp[5];
int i;
+ u8 align_num_bytes = ALIGN(num_bytes, 4);
- memcpy(src_tmp, src, num_bytes);
- src32 = (u32 *)src_tmp;
- dst32 = (u32 *)dst_tmp;
if (to_le) {
- for (i = 0; i < ((num_bytes + 3) / 4); i++)
- dst32[i] = cpu_to_le32(src32[i]);
- memcpy(dst, dst_tmp, num_bytes);
+ memcpy(src_tmp, src, num_bytes);
+ for (i = 0; i < align_num_bytes / 4; i++)
+ dst_tmp[i] = cpu_to_le32(src_tmp[i]);
+ memcpy(dst, dst_tmp, align_num_bytes);
} else {
- u8 dws = num_bytes & ~3;
- for (i = 0; i < ((num_bytes + 3) / 4); i++)
- dst32[i] = le32_to_cpu(src32[i]);
- memcpy(dst, dst_tmp, dws);
- if (num_bytes % 4) {
- for (i = 0; i < (num_bytes % 4); i++)
- dst[dws+i] = dst_tmp[dws+i];
- }
+ memcpy(src_tmp, src, align_num_bytes);
+ for (i = 0; i < align_num_bytes / 4; i++)
+ dst_tmp[i] = le32_to_cpu(src_tmp[i]);
+ memcpy(dst, dst_tmp, num_bytes);
}
#else
memcpy(dst, src, num_bytes);
@@ -1807,6 +1805,8 @@ int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
uint16_t data_offset;
int usage_bytes = 0;
struct _ATOM_VRAM_USAGE_BY_FIRMWARE *firmware_usage;
+ u64 start_addr;
+ u64 size;
if (amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) {
firmware_usage = (struct _ATOM_VRAM_USAGE_BY_FIRMWARE *)(ctx->bios + data_offset);
@@ -1815,7 +1815,21 @@ int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
le32_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].ulStartAddrUsedByFirmware),
le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb));
- usage_bytes = le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb) * 1024;
+ start_addr = firmware_usage->asFirmwareVramReserveInfo[0].ulStartAddrUsedByFirmware;
+ size = firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb;
+
+ if ((uint32_t)(start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) ==
+ (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION <<
+ ATOM_VRAM_OPERATION_FLAGS_SHIFT)) {
+ /* Firmware request VRAM reservation for SR-IOV */
+ adev->fw_vram_usage.start_offset = (start_addr &
+ (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10;
+ adev->fw_vram_usage.size = size << 10;
+ /* Use the default scratch size */
+ usage_bytes = 0;
+ } else {
+ usage_bytes = le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb) * 1024;
+ }
}
ctx->scratch_size_bytes = 0;
if (usage_bytes == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index f9ffe8ef0cd6..ff8efd0f8fd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -71,19 +71,33 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
struct atom_context *ctx = adev->mode_info.atom_context;
int index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
vram_usagebyfirmware);
+ struct vram_usagebyfirmware_v2_1 * firmware_usage;
+ uint32_t start_addr, size;
uint16_t data_offset;
int usage_bytes = 0;
if (amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) {
- struct vram_usagebyfirmware_v2_1 *firmware_usage =
- (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset);
-
+ firmware_usage = (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset);
DRM_DEBUG("atom firmware requested %08x %dkb fw %dkb drv\n",
le32_to_cpu(firmware_usage->start_address_in_kb),
le16_to_cpu(firmware_usage->used_by_firmware_in_kb),
le16_to_cpu(firmware_usage->used_by_driver_in_kb));
- usage_bytes = le16_to_cpu(firmware_usage->used_by_driver_in_kb) * 1024;
+ start_addr = le32_to_cpu(firmware_usage->start_address_in_kb);
+ size = le16_to_cpu(firmware_usage->used_by_firmware_in_kb);
+
+ if ((uint32_t)(start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) ==
+ (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION <<
+ ATOM_VRAM_OPERATION_FLAGS_SHIFT)) {
+ /* Firmware request VRAM reservation for SR-IOV */
+ adev->fw_vram_usage.start_offset = (start_addr &
+ (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10;
+ adev->fw_vram_usage.size = size << 10;
+ /* Use the default scratch size */
+ usage_bytes = 0;
+ } else {
+ usage_bytes = le16_to_cpu(firmware_usage->used_by_driver_in_kb) << 10;
+ }
}
ctx->scratch_size_bytes = 0;
if (usage_bytes == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 383204e911a4..a7afe553e0a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -42,6 +42,28 @@ struct amdgpu_cgs_device {
struct amdgpu_device *adev = \
((struct amdgpu_cgs_device *)cgs_device)->adev
+static void *amdgpu_cgs_register_pp_handle(struct cgs_device *cgs_device,
+ int (*call_back_func)(struct amd_pp_init *, void **))
+{
+ CGS_FUNC_ADEV;
+ struct amd_pp_init pp_init;
+ struct amd_powerplay *amd_pp;
+
+ if (call_back_func == NULL)
+ return NULL;
+
+ amd_pp = &(adev->powerplay);
+ pp_init.chip_family = adev->family;
+ pp_init.chip_id = adev->asic_type;
+ pp_init.pm_en = (amdgpu_dpm != 0 && !amdgpu_sriov_vf(adev)) ? true : false;
+ pp_init.feature_mask = amdgpu_pp_feature_mask;
+ pp_init.device = cgs_device;
+ if (call_back_func(&pp_init, &(amd_pp->pp_handle)))
+ return NULL;
+
+ return adev->powerplay.pp_handle;
+}
+
static int amdgpu_cgs_alloc_gpu_mem(struct cgs_device *cgs_device,
enum cgs_gpu_mem_type type,
uint64_t size, uint64_t align,
@@ -1179,6 +1201,7 @@ static const struct cgs_ops amdgpu_cgs_ops = {
.is_virtualization_enabled = amdgpu_cgs_is_virtualization_enabled,
.enter_safe_mode = amdgpu_cgs_enter_safe_mode,
.lock_grbm_idx = amdgpu_cgs_lock_grbm_idx,
+ .register_pp_handle = amdgpu_cgs_register_pp_handle,
};
static const struct cgs_os_ops amdgpu_cgs_os_ops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 126be9e0f05f..8ca3783f2deb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -231,7 +231,7 @@ amdgpu_connector_update_scratch_regs(struct drm_connector *connector,
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev,
+ encoder = drm_encoder_find(connector->dev, NULL,
connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -256,7 +256,7 @@ amdgpu_connector_find_encoder(struct drm_connector *connector,
for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev,
+ encoder = drm_encoder_find(connector->dev, NULL,
connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -371,7 +371,7 @@ amdgpu_connector_best_single_encoder(struct drm_connector *connector)
/* pick the encoder ids */
if (enc_id)
- return drm_encoder_find(connector->dev, enc_id);
+ return drm_encoder_find(connector->dev, NULL, enc_id);
return NULL;
}
@@ -1076,7 +1076,7 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev, connector->encoder_ids[i]);
+ encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -1133,7 +1133,7 @@ amdgpu_connector_dvi_encoder(struct drm_connector *connector)
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev, connector->encoder_ids[i]);
+ encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -1152,7 +1152,7 @@ amdgpu_connector_dvi_encoder(struct drm_connector *connector)
/* then check use digitial */
/* pick the first one */
if (enc_id)
- return drm_encoder_find(connector->dev, enc_id);
+ return drm_encoder_find(connector->dev, NULL, enc_id);
return NULL;
}
@@ -1293,7 +1293,7 @@ u16 amdgpu_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev,
+ encoder = drm_encoder_find(connector->dev, NULL,
connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -1322,7 +1322,7 @@ static bool amdgpu_connector_encoder_is_hbr2(struct drm_connector *connector)
for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev,
+ encoder = drm_encoder_find(connector->dev, NULL,
connector->encoder_ids[i]);
if (!encoder)
continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index c6a214f1e991..f7fceb63413c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -25,6 +25,7 @@
* Jerome Glisse <glisse@freedesktop.org>
*/
#include <linux/pagemap.h>
+#include <linux/sync_file.h>
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_syncobj.h>
@@ -89,12 +90,14 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
goto free_chunk;
}
+ mutex_lock(&p->ctx->lock);
+
/* get chunks */
chunk_array_user = u64_to_user_ptr(cs->in.chunks);
if (copy_from_user(chunk_array, chunk_array_user,
sizeof(uint64_t)*cs->in.num_chunks)) {
ret = -EFAULT;
- goto put_ctx;
+ goto free_chunk;
}
p->nchunks = cs->in.num_chunks;
@@ -102,7 +105,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
GFP_KERNEL);
if (!p->chunks) {
ret = -ENOMEM;
- goto put_ctx;
+ goto free_chunk;
}
for (i = 0; i < p->nchunks; i++) {
@@ -169,6 +172,11 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
if (ret)
goto free_all_kdata;
+ if (p->ctx->vram_lost_counter != p->job->vram_lost_counter) {
+ ret = -ECANCELED;
+ goto free_all_kdata;
+ }
+
if (p->uf_entry.robj)
p->job->uf_addr = uf_offset;
kfree(chunk_array);
@@ -182,8 +190,6 @@ free_partial_kdata:
kfree(p->chunks);
p->chunks = NULL;
p->nchunks = 0;
-put_ctx:
- amdgpu_ctx_put(p->ctx);
free_chunk:
kfree(chunk_array);
@@ -704,7 +710,8 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
list_for_each_entry(e, &p->validated, tv.head) {
struct reservation_object *resv = e->robj->tbo.resv;
- r = amdgpu_sync_resv(p->adev, &p->job->sync, resv, p->filp);
+ r = amdgpu_sync_resv(p->adev, &p->job->sync, resv, p->filp,
+ amdgpu_bo_explicit_sync(e->robj));
if (r)
return r;
@@ -735,8 +742,10 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
dma_fence_put(parser->fence);
- if (parser->ctx)
+ if (parser->ctx) {
+ mutex_unlock(&parser->ctx->lock);
amdgpu_ctx_put(parser->ctx);
+ }
if (parser->bo_list)
amdgpu_bo_list_put(parser->bo_list);
@@ -843,14 +852,58 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
struct amdgpu_vm *vm = &fpriv->vm;
struct amdgpu_ring *ring = p->job->ring;
- int i, r;
+ int r;
/* Only for UVD/VCE VM emulation */
- if (ring->funcs->parse_cs) {
- for (i = 0; i < p->job->num_ibs; i++) {
- r = amdgpu_ring_parse_cs(ring, p, i);
+ if (p->job->ring->funcs->parse_cs) {
+ unsigned i, j;
+
+ for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
+ struct drm_amdgpu_cs_chunk_ib *chunk_ib;
+ struct amdgpu_bo_va_mapping *m;
+ struct amdgpu_bo *aobj = NULL;
+ struct amdgpu_cs_chunk *chunk;
+ struct amdgpu_ib *ib;
+ uint64_t offset;
+ uint8_t *kptr;
+
+ chunk = &p->chunks[i];
+ ib = &p->job->ibs[j];
+ chunk_ib = chunk->kdata;
+
+ if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB)
+ continue;
+
+ r = amdgpu_cs_find_mapping(p, chunk_ib->va_start,
+ &aobj, &m);
+ if (r) {
+ DRM_ERROR("IB va_start is invalid\n");
+ return r;
+ }
+
+ if ((chunk_ib->va_start + chunk_ib->ib_bytes) >
+ (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
+ DRM_ERROR("IB va_start+ib_bytes is invalid\n");
+ return -EINVAL;
+ }
+
+ /* the IB should be reserved at this point */
+ r = amdgpu_bo_kmap(aobj, (void **)&kptr);
+ if (r) {
+ return r;
+ }
+
+ offset = m->start * AMDGPU_GPU_PAGE_SIZE;
+ kptr += chunk_ib->va_start - offset;
+
+ memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
+ amdgpu_bo_kunmap(aobj);
+
+ r = amdgpu_ring_parse_cs(ring, p, j);
if (r)
return r;
+
+ j++;
}
}
@@ -917,54 +970,18 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
parser->job->ring = ring;
- if (ring->funcs->parse_cs) {
- struct amdgpu_bo_va_mapping *m;
- struct amdgpu_bo *aobj = NULL;
- uint64_t offset;
- uint8_t *kptr;
-
- r = amdgpu_cs_find_mapping(parser, chunk_ib->va_start,
- &aobj, &m);
- if (r) {
- DRM_ERROR("IB va_start is invalid\n");
- return r;
- }
-
- if ((chunk_ib->va_start + chunk_ib->ib_bytes) >
- (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
- DRM_ERROR("IB va_start+ib_bytes is invalid\n");
- return -EINVAL;
- }
-
- /* the IB should be reserved at this point */
- r = amdgpu_bo_kmap(aobj, (void **)&kptr);
- if (r) {
- return r;
- }
-
- offset = m->start * AMDGPU_GPU_PAGE_SIZE;
- kptr += chunk_ib->va_start - offset;
-
- r = amdgpu_ib_get(adev, vm, chunk_ib->ib_bytes, ib);
- if (r) {
- DRM_ERROR("Failed to get ib !\n");
- return r;
- }
-
- memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
- amdgpu_bo_kunmap(aobj);
- } else {
- r = amdgpu_ib_get(adev, vm, 0, ib);
- if (r) {
- DRM_ERROR("Failed to get ib !\n");
- return r;
- }
-
+ r = amdgpu_ib_get(adev, vm,
+ ring->funcs->parse_cs ? chunk_ib->ib_bytes : 0,
+ ib);
+ if (r) {
+ DRM_ERROR("Failed to get ib !\n");
+ return r;
}
ib->gpu_addr = chunk_ib->va_start;
ib->length_dw = chunk_ib->ib_bytes / 4;
ib->flags = chunk_ib->flags;
+
j++;
}
@@ -974,7 +991,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
parser->job->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
return -EINVAL;
- return 0;
+ return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->job->ring->idx);
}
static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
@@ -1175,6 +1192,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
job->uf_sequence = seq;
amdgpu_job_free_resources(job);
+ amdgpu_ring_priority_get(job->ring,
+ amd_sched_get_job_priority(&job->base));
trace_amdgpu_cs_ioctl(job);
amd_sched_entity_push_job(&job->base);
@@ -1188,7 +1207,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
{
struct amdgpu_device *adev = dev->dev_private;
- struct amdgpu_fpriv *fpriv = filp->driver_priv;
union drm_amdgpu_cs *cs = data;
struct amdgpu_cs_parser parser = {};
bool reserved_buffers = false;
@@ -1196,8 +1214,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
if (!adev->accel_working)
return -EBUSY;
- if (amdgpu_kms_vram_lost(adev, fpriv))
- return -ENODEV;
parser.adev = adev;
parser.filp = filp;
@@ -1208,6 +1224,10 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
goto out;
}
+ r = amdgpu_cs_ib_fill(adev, &parser);
+ if (r)
+ goto out;
+
r = amdgpu_cs_parser_bos(&parser, data);
if (r) {
if (r == -ENOMEM)
@@ -1218,9 +1238,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
}
reserved_buffers = true;
- r = amdgpu_cs_ib_fill(adev, &parser);
- if (r)
- goto out;
r = amdgpu_cs_dependencies(adev, &parser);
if (r) {
@@ -1256,16 +1273,12 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
{
union drm_amdgpu_wait_cs *wait = data;
struct amdgpu_device *adev = dev->dev_private;
- struct amdgpu_fpriv *fpriv = filp->driver_priv;
unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout);
struct amdgpu_ring *ring = NULL;
struct amdgpu_ctx *ctx;
struct dma_fence *fence;
long r;
- if (amdgpu_kms_vram_lost(adev, fpriv))
- return -ENODEV;
-
ctx = amdgpu_ctx_get(filp->driver_priv, wait->in.ctx_id);
if (ctx == NULL)
return -EINVAL;
@@ -1283,6 +1296,8 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
r = PTR_ERR(fence);
else if (fence) {
r = dma_fence_wait_timeout(fence, true, timeout);
+ if (r > 0 && fence->error)
+ r = fence->error;
dma_fence_put(fence);
} else
r = 1;
@@ -1330,6 +1345,62 @@ static struct dma_fence *amdgpu_cs_get_fence(struct amdgpu_device *adev,
return fence;
}
+int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *filp)
+{
+ struct amdgpu_device *adev = dev->dev_private;
+ union drm_amdgpu_fence_to_handle *info = data;
+ struct dma_fence *fence;
+ struct drm_syncobj *syncobj;
+ struct sync_file *sync_file;
+ int fd, r;
+
+ fence = amdgpu_cs_get_fence(adev, filp, &info->in.fence);
+ if (IS_ERR(fence))
+ return PTR_ERR(fence);
+
+ switch (info->in.what) {
+ case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ:
+ r = drm_syncobj_create(&syncobj, 0, fence);
+ dma_fence_put(fence);
+ if (r)
+ return r;
+ r = drm_syncobj_get_handle(filp, syncobj, &info->out.handle);
+ drm_syncobj_put(syncobj);
+ return r;
+
+ case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD:
+ r = drm_syncobj_create(&syncobj, 0, fence);
+ dma_fence_put(fence);
+ if (r)
+ return r;
+ r = drm_syncobj_get_fd(syncobj, (int*)&info->out.handle);
+ drm_syncobj_put(syncobj);
+ return r;
+
+ case AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD:
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0) {
+ dma_fence_put(fence);
+ return fd;
+ }
+
+ sync_file = sync_file_create(fence);
+ dma_fence_put(fence);
+ if (!sync_file) {
+ put_unused_fd(fd);
+ return -ENOMEM;
+ }
+
+ fd_install(fd, sync_file->file);
+ info->out.handle = fd;
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
/**
* amdgpu_cs_wait_all_fence - wait on all fences to signal
*
@@ -1364,6 +1435,9 @@ static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
if (r == 0)
break;
+
+ if (fence->error)
+ return fence->error;
}
memset(wait, 0, sizeof(*wait));
@@ -1424,7 +1498,7 @@ out:
wait->out.status = (r > 0);
wait->out.first_signaled = first;
/* set return value 0 to indicate success */
- r = 0;
+ r = array[first]->error;
err_free_fence_array:
for (i = 0; i < fence_count; i++)
@@ -1445,15 +1519,12 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp)
{
struct amdgpu_device *adev = dev->dev_private;
- struct amdgpu_fpriv *fpriv = filp->driver_priv;
union drm_amdgpu_wait_fences *wait = data;
uint32_t fence_count = wait->in.fence_count;
struct drm_amdgpu_fence *fences_user;
struct drm_amdgpu_fence *fences;
int r;
- if (amdgpu_kms_vram_lost(adev, fpriv))
- return -ENODEV;
/* Get the fences from userspace */
fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
GFP_KERNEL);
@@ -1511,14 +1582,14 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
if (READ_ONCE((*bo)->tbo.resv->lock.ctx) != &parser->ticket)
return -EINVAL;
- r = amdgpu_ttm_bind(&(*bo)->tbo, &(*bo)->tbo.mem);
- if (unlikely(r))
- return r;
-
- if ((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
- return 0;
+ if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
+ (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+ amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
+ r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, false,
+ false);
+ if (r)
+ return r;
+ }
- (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
- amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
- return ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, false, false);
+ return amdgpu_ttm_bind(&(*bo)->tbo, &(*bo)->tbo.mem);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 75c933b1a432..c184468e2b2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -23,13 +23,41 @@
*/
#include <drm/drmP.h>
+#include <drm/drm_auth.h>
#include "amdgpu.h"
+#include "amdgpu_sched.h"
-static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
+static int amdgpu_ctx_priority_permit(struct drm_file *filp,
+ enum amd_sched_priority priority)
+{
+ /* NORMAL and below are accessible by everyone */
+ if (priority <= AMD_SCHED_PRIORITY_NORMAL)
+ return 0;
+
+ if (capable(CAP_SYS_NICE))
+ return 0;
+
+ if (drm_is_current_master(filp))
+ return 0;
+
+ return -EACCES;
+}
+
+static int amdgpu_ctx_init(struct amdgpu_device *adev,
+ enum amd_sched_priority priority,
+ struct drm_file *filp,
+ struct amdgpu_ctx *ctx)
{
unsigned i, j;
int r;
+ if (priority < 0 || priority >= AMD_SCHED_PRIORITY_MAX)
+ return -EINVAL;
+
+ r = amdgpu_ctx_priority_permit(filp, priority);
+ if (r)
+ return r;
+
memset(ctx, 0, sizeof(*ctx));
ctx->adev = adev;
kref_init(&ctx->refcount);
@@ -39,19 +67,24 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
if (!ctx->fences)
return -ENOMEM;
+ mutex_init(&ctx->lock);
+
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
ctx->rings[i].sequence = 1;
ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
}
ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+ ctx->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
+ ctx->init_priority = priority;
+ ctx->override_priority = AMD_SCHED_PRIORITY_UNSET;
/* create context entity for each ring */
for (i = 0; i < adev->num_rings; i++) {
struct amdgpu_ring *ring = adev->rings[i];
struct amd_sched_rq *rq;
- rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
+ rq = &ring->sched.sched_rq[priority];
if (ring == &adev->gfx.kiq.ring)
continue;
@@ -96,10 +129,14 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
&ctx->rings[i].entity);
amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
+
+ mutex_destroy(&ctx->lock);
}
static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
struct amdgpu_fpriv *fpriv,
+ struct drm_file *filp,
+ enum amd_sched_priority priority,
uint32_t *id)
{
struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
@@ -117,8 +154,9 @@ static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
kfree(ctx);
return r;
}
+
*id = (uint32_t)r;
- r = amdgpu_ctx_init(adev, ctx);
+ r = amdgpu_ctx_init(adev, priority, filp, ctx);
if (r) {
idr_remove(&mgr->ctx_handles, *id);
*id = 0;
@@ -193,6 +231,7 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
{
int r;
uint32_t id;
+ enum amd_sched_priority priority;
union drm_amdgpu_ctx *args = data;
struct amdgpu_device *adev = dev->dev_private;
@@ -200,10 +239,16 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
r = 0;
id = args->in.ctx_id;
+ priority = amdgpu_to_sched_priority(args->in.priority);
+
+ /* For backwards compatibility reasons, we need to accept
+ * ioctls with garbage in the priority field */
+ if (priority == AMD_SCHED_PRIORITY_INVALID)
+ priority = AMD_SCHED_PRIORITY_NORMAL;
switch (args->in.op) {
case AMDGPU_CTX_OP_ALLOC_CTX:
- r = amdgpu_ctx_alloc(adev, fpriv, &id);
+ r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id);
args->out.alloc.ctx_id = id;
break;
case AMDGPU_CTX_OP_FREE_CTX:
@@ -256,12 +301,8 @@ int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
idx = seq & (amdgpu_sched_jobs - 1);
other = cring->fences[idx];
- if (other) {
- signed long r;
- r = dma_fence_wait_timeout(other, true, MAX_SCHEDULE_TIMEOUT);
- if (r < 0)
- return r;
- }
+ if (other)
+ BUG_ON(!dma_fence_is_signaled(other));
dma_fence_get(fence);
@@ -305,6 +346,51 @@ struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
return fence;
}
+void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
+ enum amd_sched_priority priority)
+{
+ int i;
+ struct amdgpu_device *adev = ctx->adev;
+ struct amd_sched_rq *rq;
+ struct amd_sched_entity *entity;
+ struct amdgpu_ring *ring;
+ enum amd_sched_priority ctx_prio;
+
+ ctx->override_priority = priority;
+
+ ctx_prio = (ctx->override_priority == AMD_SCHED_PRIORITY_UNSET) ?
+ ctx->init_priority : ctx->override_priority;
+
+ for (i = 0; i < adev->num_rings; i++) {
+ ring = adev->rings[i];
+ entity = &ctx->rings[i].entity;
+ rq = &ring->sched.sched_rq[ctx_prio];
+
+ if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+ continue;
+
+ amd_sched_entity_set_rq(entity, rq);
+ }
+}
+
+int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id)
+{
+ struct amdgpu_ctx_ring *cring = &ctx->rings[ring_id];
+ unsigned idx = cring->sequence & (amdgpu_sched_jobs - 1);
+ struct dma_fence *other = cring->fences[idx];
+
+ if (other) {
+ signed long r;
+ r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+ if (r < 0) {
+ DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+ return r;
+ }
+ }
+
+ return 0;
+}
+
void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
{
mutex_init(&mgr->lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3e84ddf9e3b5..efcacb827de7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -56,6 +56,7 @@
#include "amdgpu_vf_error.h"
#include "amdgpu_amdkfd.h"
+#include "amdgpu_pm.h"
MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -108,10 +109,8 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
{
uint32_t ret;
- if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev)) {
- BUG_ON(in_interrupt());
+ if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
return amdgpu_virt_kiq_rreg(adev, reg);
- }
if ((reg * 4) < adev->rmmio_size && !(acc_flags & AMDGPU_REGS_IDX))
ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
@@ -136,10 +135,8 @@ void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
adev->last_mm_index = v;
}
- if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev)) {
- BUG_ON(in_interrupt());
+ if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
return amdgpu_virt_kiq_wreg(adev, reg, v);
- }
if ((reg * 4) < adev->rmmio_size && !(acc_flags & AMDGPU_REGS_IDX))
writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
@@ -549,7 +546,7 @@ int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb)
if (offset < adev->wb.num_wb) {
__set_bit(offset, adev->wb.used);
- *wb = offset * 8; /* convert to dw offset */
+ *wb = offset << 3; /* convert to dw offset */
return 0;
} else {
return -EINVAL;
@@ -567,7 +564,7 @@ int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb)
void amdgpu_wb_free(struct amdgpu_device *adev, u32 wb)
{
if (wb < adev->wb.num_wb)
- __clear_bit(wb, adev->wb.used);
+ __clear_bit(wb >> 3, adev->wb.used);
}
/**
@@ -657,42 +654,96 @@ void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc)
}
/*
- * GPU helpers function.
+ * Firmware Reservation functions
*/
/**
- * amdgpu_need_post - check if the hw need post or not
+ * amdgpu_fw_reserve_vram_fini - free fw reserved vram
*
* @adev: amdgpu_device pointer
*
- * Check if the asic has been initialized (all asics) at driver startup
- * or post is needed if hw reset is performed.
- * Returns true if need or false if not.
+ * free fw reserved vram if it has been reserved.
*/
-bool amdgpu_need_post(struct amdgpu_device *adev)
+void amdgpu_fw_reserve_vram_fini(struct amdgpu_device *adev)
{
- uint32_t reg;
+ amdgpu_bo_free_kernel(&adev->fw_vram_usage.reserved_bo,
+ NULL, &adev->fw_vram_usage.va);
+}
- if (adev->has_hw_reset) {
- adev->has_hw_reset = false;
- return true;
- }
+/**
+ * amdgpu_fw_reserve_vram_init - create bo vram reservation from fw
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * create bo vram reservation from fw.
+ */
+int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev)
+{
+ int r = 0;
+ u64 gpu_addr;
+ u64 vram_size = adev->mc.visible_vram_size;
- /* bios scratch used on CIK+ */
- if (adev->asic_type >= CHIP_BONAIRE)
- return amdgpu_atombios_scratch_need_asic_init(adev);
+ adev->fw_vram_usage.va = NULL;
+ adev->fw_vram_usage.reserved_bo = NULL;
- /* check MEM_SIZE for older asics */
- reg = amdgpu_asic_get_config_memsize(adev);
+ if (adev->fw_vram_usage.size > 0 &&
+ adev->fw_vram_usage.size <= vram_size) {
- if ((reg != 0) && (reg != 0xffffffff))
- return false;
+ r = amdgpu_bo_create(adev, adev->fw_vram_usage.size,
+ PAGE_SIZE, true, 0,
+ AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+ AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS, NULL, NULL, 0,
+ &adev->fw_vram_usage.reserved_bo);
+ if (r)
+ goto error_create;
- return true;
+ r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false);
+ if (r)
+ goto error_reserve;
+ r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ adev->fw_vram_usage.start_offset,
+ (adev->fw_vram_usage.start_offset +
+ adev->fw_vram_usage.size), &gpu_addr);
+ if (r)
+ goto error_pin;
+ r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
+ &adev->fw_vram_usage.va);
+ if (r)
+ goto error_kmap;
+ amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
+ }
+ return r;
+
+error_kmap:
+ amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo);
+error_pin:
+ amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
+error_reserve:
+ amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo);
+error_create:
+ adev->fw_vram_usage.va = NULL;
+ adev->fw_vram_usage.reserved_bo = NULL;
+ return r;
}
-static bool amdgpu_vpost_needed(struct amdgpu_device *adev)
+
+/*
+ * GPU helpers function.
+ */
+/**
+ * amdgpu_need_post - check if the hw need post or not
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Check if the asic has been initialized (all asics) at driver startup
+ * or post is needed if hw reset is performed.
+ * Returns true if need or false if not.
+ */
+bool amdgpu_need_post(struct amdgpu_device *adev)
{
+ uint32_t reg;
+
if (amdgpu_sriov_vf(adev))
return false;
@@ -715,7 +766,23 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev)
return true;
}
}
- return amdgpu_need_post(adev);
+
+ if (adev->has_hw_reset) {
+ adev->has_hw_reset = false;
+ return true;
+ }
+
+ /* bios scratch used on CIK+ */
+ if (adev->asic_type >= CHIP_BONAIRE)
+ return amdgpu_atombios_scratch_need_asic_init(adev);
+
+ /* check MEM_SIZE for older asics */
+ reg = amdgpu_asic_get_config_memsize(adev);
+
+ if ((reg != 0) && (reg != 0xffffffff))
+ return false;
+
+ return true;
}
/**
@@ -1879,6 +1946,7 @@ static int amdgpu_sriov_reinit_late(struct amdgpu_device *adev)
static enum amd_ip_block_type ip_order[] = {
AMD_IP_BLOCK_TYPE_SMC,
+ AMD_IP_BLOCK_TYPE_PSP,
AMD_IP_BLOCK_TYPE_DCE,
AMD_IP_BLOCK_TYPE_GFX,
AMD_IP_BLOCK_TYPE_SDMA,
@@ -1964,12 +2032,17 @@ static int amdgpu_resume(struct amdgpu_device *adev)
static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev)
{
- if (adev->is_atom_fw) {
- if (amdgpu_atomfirmware_gpu_supports_virtualization(adev))
- adev->virt.caps |= AMDGPU_SRIOV_CAPS_SRIOV_VBIOS;
- } else {
- if (amdgpu_atombios_has_gpu_virtualization_table(adev))
- adev->virt.caps |= AMDGPU_SRIOV_CAPS_SRIOV_VBIOS;
+ if (amdgpu_sriov_vf(adev)) {
+ if (adev->is_atom_fw) {
+ if (amdgpu_atomfirmware_gpu_supports_virtualization(adev))
+ adev->virt.caps |= AMDGPU_SRIOV_CAPS_SRIOV_VBIOS;
+ } else {
+ if (amdgpu_atombios_has_gpu_virtualization_table(adev))
+ adev->virt.caps |= AMDGPU_SRIOV_CAPS_SRIOV_VBIOS;
+ }
+
+ if (!(adev->virt.caps & AMDGPU_SRIOV_CAPS_SRIOV_VBIOS))
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_NO_VBIOS, 0, 0);
}
}
@@ -2010,6 +2083,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
adev->vm_manager.vm_pte_num_rings = 0;
adev->gart.gart_funcs = NULL;
adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS);
+ bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
adev->smc_rreg = &amdgpu_invalid_rreg;
adev->smc_wreg = &amdgpu_invalid_wreg;
@@ -2038,8 +2112,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
mutex_init(&adev->pm.mutex);
mutex_init(&adev->gfx.gpu_clock_mutex);
mutex_init(&adev->srbm_mutex);
+ mutex_init(&adev->gfx.pipe_reserve_mutex);
mutex_init(&adev->grbm_idx_mutex);
mutex_init(&adev->mn_lock);
+ mutex_init(&adev->virt.vf_errors.lock);
hash_init(adev->mn_hash);
amdgpu_check_arguments(adev);
@@ -2125,7 +2201,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_atombios_init(adev);
if (r) {
dev_err(adev->dev, "amdgpu_atombios_init failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0);
goto failed;
}
@@ -2133,10 +2209,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
amdgpu_device_detect_sriov_bios(adev);
/* Post card if necessary */
- if (amdgpu_vpost_needed(adev)) {
+ if (amdgpu_need_post(adev)) {
if (!adev->bios) {
dev_err(adev->dev, "no vBIOS found\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_NO_VBIOS, 0, 0);
r = -EINVAL;
goto failed;
}
@@ -2144,7 +2219,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
if (r) {
dev_err(adev->dev, "gpu post error!\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_GPU_POST_ERROR, 0, 0);
goto failed;
}
} else {
@@ -2156,7 +2230,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_atomfirmware_get_clock_info(adev);
if (r) {
dev_err(adev->dev, "amdgpu_atomfirmware_get_clock_info failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_ATOMBIOS_GET_CLOCK_FAIL, 0, 0);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_GET_CLOCK_FAIL, 0, 0);
goto failed;
}
} else {
@@ -2164,7 +2238,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_atombios_get_clock_info(adev);
if (r) {
dev_err(adev->dev, "amdgpu_atombios_get_clock_info failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_ATOMBIOS_GET_CLOCK_FAIL, 0, 0);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_GET_CLOCK_FAIL, 0, 0);
goto failed;
}
/* init i2c buses */
@@ -2175,7 +2249,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_fence_driver_init(adev);
if (r) {
dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
goto failed;
}
@@ -2185,7 +2259,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_init(adev);
if (r) {
dev_err(adev->dev, "amdgpu_init failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
amdgpu_fini(adev);
goto failed;
}
@@ -2205,7 +2279,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_ib_pool_init(adev);
if (r) {
dev_err(adev->dev, "IB initialization failed (%d).\n", r);
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_IB_INIT_FAIL, 0, r);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_IB_INIT_FAIL, 0, r);
goto failed;
}
@@ -2213,8 +2287,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
if (r)
DRM_ERROR("ib ring test failed (%d).\n", r);
+ if (amdgpu_sriov_vf(adev))
+ amdgpu_virt_init_data_exchange(adev);
+
amdgpu_fbdev_init(adev);
+ r = amdgpu_pm_sysfs_init(adev);
+ if (r)
+ DRM_ERROR("registering pm debugfs failed (%d).\n", r);
+
r = amdgpu_gem_debugfs_init(adev);
if (r)
DRM_ERROR("registering gem debugfs failed (%d).\n", r);
@@ -2254,7 +2335,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_late_init(adev);
if (r) {
dev_err(adev->dev, "amdgpu_late_init failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
+ amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
goto failed;
}
@@ -2286,6 +2367,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
/* evict vram memory */
amdgpu_bo_evict_vram(adev);
amdgpu_ib_pool_fini(adev);
+ amdgpu_fw_reserve_vram_fini(adev);
amdgpu_fence_driver_fini(adev);
amdgpu_fbdev_fini(adev);
r = amdgpu_fini(adev);
@@ -2311,6 +2393,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
iounmap(adev->rmmio);
adev->rmmio = NULL;
amdgpu_doorbell_fini(adev);
+ amdgpu_pm_sysfs_fini(adev);
amdgpu_debugfs_regs_cleanup(adev);
}
@@ -2537,6 +2620,9 @@ static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
int i;
bool asic_hang = false;
+ if (amdgpu_sriov_vf(adev))
+ return true;
+
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.valid)
continue;
@@ -2936,7 +3022,6 @@ out:
}
} else {
dev_err(adev->dev, "asic resume failed (%d).\n", r);
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_ASIC_RESUME_FAIL, 0, r);
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
if (adev->rings[i] && adev->rings[i]->sched.thread) {
kthread_unpark(adev->rings[i]->sched.thread);
@@ -2950,7 +3035,6 @@ out:
if (r) {
/* bad news, how to tell it to userspace ? */
dev_info(adev->dev, "GPU reset failed\n");
- amdgpu_vf_error_put(AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
}
else {
dev_info(adev->dev, "GPU reset successed!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index f79f9ea58b17..7279fb5c3abc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -356,6 +356,10 @@ enum amdgpu_pcie_gen {
((adev)->powerplay.pp_funcs->switch_power_profile(\
(adev)->powerplay.pp_handle, type))
+#define amdgpu_dpm_set_clockgating_by_smu(adev, msg_id) \
+ ((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
+ (adev)->powerplay.pp_handle, msg_id))
+
struct amdgpu_dpm {
struct amdgpu_ps *ps;
/* number of valid power states */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 4f98960e47f9..dd2f060d62a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -70,9 +70,12 @@
* - 3.18.0 - Export gpu always on cu bitmap
* - 3.19.0 - Add support for UVD MJPEG decode
* - 3.20.0 - Add support for local BOs
+ * - 3.21.0 - Add DRM_AMDGPU_FENCE_TO_HANDLE ioctl
+ * - 3.22.0 - Add DRM_AMDGPU_SCHED ioctl
+ * - 3.23.0 - Add query for VRAM lost counter
*/
#define KMS_DRIVER_MAJOR 3
-#define KMS_DRIVER_MINOR 20
+#define KMS_DRIVER_MINOR 23
#define KMS_DRIVER_PATCHLEVEL 0
int amdgpu_vram_limit = 0;
@@ -122,6 +125,7 @@ int amdgpu_cntl_sb_buf_per_se = 0;
int amdgpu_param_buf_per_se = 0;
int amdgpu_job_hang_limit = 0;
int amdgpu_lbpw = -1;
+int amdgpu_compute_multipipe = -1;
MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -265,6 +269,9 @@ module_param_named(job_hang_limit, amdgpu_job_hang_limit, int ,0444);
MODULE_PARM_DESC(lbpw, "Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable, -1 = auto)");
module_param_named(lbpw, amdgpu_lbpw, int, 0444);
+MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
+module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
+
#ifdef CONFIG_DRM_AMDGPU_SI
#if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 333bad749067..fb9f88ef6059 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -169,6 +169,32 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f)
}
/**
+ * amdgpu_fence_emit_polling - emit a fence on the requeste ring
+ *
+ * @ring: ring the fence is associated with
+ * @s: resulting sequence number
+ *
+ * Emits a fence command on the requested ring (all asics).
+ * Used For polling fence.
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s)
+{
+ uint32_t seq;
+
+ if (!s)
+ return -EINVAL;
+
+ seq = ++ring->fence_drv.sync_seq;
+ amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
+ seq, AMDGPU_FENCE_FLAG_INT);
+
+ *s = seq;
+
+ return 0;
+}
+
+/**
* amdgpu_fence_schedule_fallback - schedule fallback check
*
* @ring: pointer to struct amdgpu_ring
@@ -282,6 +308,30 @@ int amdgpu_fence_wait_empty(struct amdgpu_ring *ring)
}
/**
+ * amdgpu_fence_wait_polling - busy wait for givn sequence number
+ *
+ * @ring: ring index the fence is associated with
+ * @wait_seq: sequence number to wait
+ * @timeout: the timeout for waiting in usecs
+ *
+ * Wait for all fences on the requested ring to signal (all asics).
+ * Returns left time if no timeout, 0 or minus if timeout.
+ */
+signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
+ uint32_t wait_seq,
+ signed long timeout)
+{
+ uint32_t seq;
+
+ do {
+ seq = amdgpu_fence_read(ring);
+ udelay(5);
+ timeout -= 5;
+ } while ((int32_t)(wait_seq - seq) > 0 && timeout > 0);
+
+ return timeout > 0 ? timeout : 0;
+}
+/**
* amdgpu_fence_count_emitted - get the count of emitted fences
*
* @ring: ring the fence is associated with
@@ -641,6 +691,19 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data)
atomic_read(&ring->fence_drv.last_seq));
seq_printf(m, "Last emitted 0x%08x\n",
ring->fence_drv.sync_seq);
+
+ if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
+ continue;
+
+ /* set in CP_VMID_PREEMPT and preemption occurred */
+ seq_printf(m, "Last preempted 0x%08x\n",
+ le32_to_cpu(*(ring->fence_drv.cpu_addr + 2)));
+ /* set in CP_VMID_RESET and reset occurred */
+ seq_printf(m, "Last reset 0x%08x\n",
+ le32_to_cpu(*(ring->fence_drv.cpu_addr + 4)));
+ /* Both preemption and reset occurred */
+ seq_printf(m, "Last both 0x%08x\n",
+ le32_to_cpu(*(ring->fence_drv.cpu_addr + 6)));
}
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index f4370081f6e6..fe818501c520 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -332,12 +332,13 @@ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
adev->gart.pages[p] = pagelist[i];
#endif
- if (adev->gart.ptr) {
- r = amdgpu_gart_map(adev, offset, pages, dma_addr, flags,
- adev->gart.ptr);
- if (r)
- return r;
- }
+ if (!adev->gart.ptr)
+ return 0;
+
+ r = amdgpu_gart_map(adev, offset, pages, dma_addr, flags,
+ adev->gart.ptr);
+ if (r)
+ return r;
mb();
amdgpu_gart_flush_gpu_tlb(adev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index b0d45c8e6bb3..fb72edc4c026 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -212,7 +212,9 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
AMDGPU_GEM_CREATE_CPU_GTT_USWC |
AMDGPU_GEM_CREATE_VRAM_CLEARED |
- AMDGPU_GEM_CREATE_VM_ALWAYS_VALID))
+ AMDGPU_GEM_CREATE_VM_ALWAYS_VALID |
+ AMDGPU_GEM_CREATE_EXPLICIT_SYNC))
+
return -EINVAL;
/* reject invalid gem domains */
@@ -577,11 +579,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
args->operation);
return -EINVAL;
}
- if ((args->operation == AMDGPU_VA_OP_MAP) ||
- (args->operation == AMDGPU_VA_OP_REPLACE)) {
- if (amdgpu_kms_vram_lost(adev, fpriv))
- return -ENODEV;
- }
INIT_LIST_HEAD(&list);
INIT_LIST_HEAD(&duplicates);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 4fcd98e65998..ef043361009f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -109,9 +109,26 @@ void amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_s
}
}
+static bool amdgpu_gfx_is_multipipe_capable(struct amdgpu_device *adev)
+{
+ if (amdgpu_compute_multipipe != -1) {
+ DRM_INFO("amdgpu: forcing compute pipe policy %d\n",
+ amdgpu_compute_multipipe);
+ return amdgpu_compute_multipipe == 1;
+ }
+
+ /* FIXME: spreading the queues across pipes causes perf regressions
+ * on POLARIS11 compute workloads */
+ if (adev->asic_type == CHIP_POLARIS11)
+ return false;
+
+ return adev->gfx.mec.num_mec > 1;
+}
+
void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
{
int i, queue, pipe, mec;
+ bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
/* policy for amdgpu compute queue ownership */
for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
@@ -125,8 +142,7 @@ void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
if (mec >= adev->gfx.mec.num_mec)
break;
- /* FIXME: spreading the queues across pipes causes perf regressions */
- if (0) {
+ if (multipipe_policy) {
/* policy: amdgpu owns the first two queues of the first MEC */
if (mec == 0 && queue < 2)
set_bit(i, adev->gfx.mec.queue_bitmap);
@@ -185,7 +201,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
int r = 0;
- mutex_init(&kiq->ring_mutex);
+ spin_lock_init(&kiq->ring_lock);
r = amdgpu_wb_get(adev, &adev->virt.reg_val_offs);
if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 0d15eb7d31d7..33535d347734 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -169,7 +169,8 @@ static int amdgpu_gtt_mgr_new(struct ttm_mem_type_manager *man,
int r;
spin_lock(&mgr->lock);
- if (atomic64_read(&mgr->available) < mem->num_pages) {
+ if ((&tbo->mem == mem || tbo->mem.mem_type != TTM_PL_TT) &&
+ atomic64_read(&mgr->available) < mem->num_pages) {
spin_unlock(&mgr->lock);
return 0;
}
@@ -244,8 +245,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_mem_type_manager *man,
uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man)
{
struct amdgpu_gtt_mgr *mgr = man->priv;
+ s64 result = man->size - atomic64_read(&mgr->available);
- return (u64)(man->size - atomic64_read(&mgr->available)) * PAGE_SIZE;
+ return (result > 0 ? result : 0) * PAGE_SIZE;
}
/**
@@ -265,7 +267,7 @@ static void amdgpu_gtt_mgr_debug(struct ttm_mem_type_manager *man,
drm_mm_print(&mgr->mm, printer);
spin_unlock(&mgr->lock);
- drm_printf(printer, "man size:%llu pages, gtt available:%llu pages, usage:%lluMB\n",
+ drm_printf(printer, "man size:%llu pages, gtt available:%lld pages, usage:%lluMB\n",
man->size, (u64)atomic64_read(&mgr->available),
amdgpu_gtt_mgr_usage(man) >> 20);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4510627ae83e..0cfc68db575b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -65,6 +65,7 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
amdgpu_sync_create(&(*job)->sync);
amdgpu_sync_create(&(*job)->dep_sync);
amdgpu_sync_create(&(*job)->sched_sync);
+ (*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
return 0;
}
@@ -103,6 +104,7 @@ static void amdgpu_job_free_cb(struct amd_sched_job *s_job)
{
struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+ amdgpu_ring_priority_put(job->ring, amd_sched_get_job_priority(s_job));
dma_fence_put(job->fence);
amdgpu_sync_free(&job->sync);
amdgpu_sync_free(&job->dep_sync);
@@ -139,6 +141,8 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
job->fence_ctx = entity->fence_context;
*f = dma_fence_get(&job->base.s_fence->finished);
amdgpu_job_free_resources(job);
+ amdgpu_ring_priority_get(job->ring,
+ amd_sched_get_job_priority(&job->base));
amd_sched_entity_push_job(&job->base);
return 0;
@@ -177,8 +181,8 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_device *adev;
struct amdgpu_job *job;
- struct amdgpu_fpriv *fpriv = NULL;
int r;
if (!sched_job) {
@@ -186,23 +190,25 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
return NULL;
}
job = to_amdgpu_job(sched_job);
+ adev = job->adev;
BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
trace_amdgpu_sched_run_job(job);
- if (job->vm)
- fpriv = container_of(job->vm, struct amdgpu_fpriv, vm);
/* skip ib schedule when vram is lost */
- if (fpriv && amdgpu_kms_vram_lost(job->adev, fpriv))
+ if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter)) {
+ dma_fence_set_error(&job->base.s_fence->finished, -ECANCELED);
DRM_ERROR("Skip scheduling IBs!\n");
- else {
- r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job, &fence);
+ } else {
+ r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
+ &fence);
if (r)
DRM_ERROR("Error scheduling IBs (%d)\n", r);
}
/* if gpu reset, hw fence will be replaced here */
dma_fence_put(job->fence);
job->fence = dma_fence_get(fence);
+
amdgpu_job_free_resources(job);
return fence;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 4fd06f8d9768..6f0b26dae3b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -28,6 +28,7 @@
#include <drm/drmP.h>
#include "amdgpu.h"
#include <drm/amdgpu_drm.h>
+#include "amdgpu_sched.h"
#include "amdgpu_uvd.h"
#include "amdgpu_vce.h"
@@ -269,7 +270,6 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
{
struct amdgpu_device *adev = dev->dev_private;
- struct amdgpu_fpriv *fpriv = filp->driver_priv;
struct drm_amdgpu_info *info = data;
struct amdgpu_mode_info *minfo = &adev->mode_info;
void __user *out = (void __user *)(uintptr_t)info->return_pointer;
@@ -282,8 +282,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
if (!info->return_size || !info->return_pointer)
return -EINVAL;
- if (amdgpu_kms_vram_lost(adev, fpriv))
- return -ENODEV;
switch (info->query) {
case AMDGPU_INFO_ACCEL_WORKING:
@@ -765,6 +763,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
}
return copy_to_user(out, &ui32, min(size, 4u)) ? -EFAULT : 0;
}
+ case AMDGPU_INFO_VRAM_LOST_COUNTER:
+ ui32 = atomic_read(&adev->vram_lost_counter);
+ return copy_to_user(out, &ui32, min(size, 4u)) ? -EFAULT : 0;
default:
DRM_DEBUG_KMS("Invalid request %d\n", info->query);
return -EINVAL;
@@ -791,12 +792,6 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev)
vga_switcheroo_process_delayed_switch();
}
-bool amdgpu_kms_vram_lost(struct amdgpu_device *adev,
- struct amdgpu_fpriv *fpriv)
-{
- return fpriv->vram_lost_counter != atomic_read(&adev->vram_lost_counter);
-}
-
/**
* amdgpu_driver_open_kms - drm callback for open
*
@@ -853,7 +848,6 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
amdgpu_ctx_mgr_init(&fpriv->ctx_mgr);
- fpriv->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
file_priv->driver_priv = fpriv;
out_suspend:
@@ -1023,7 +1017,9 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = {
DRM_IOCTL_DEF_DRV(AMDGPU_GEM_CREATE, amdgpu_gem_create_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(AMDGPU_CTX, amdgpu_ctx_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(AMDGPU_VM, amdgpu_vm_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(AMDGPU_SCHED, amdgpu_sched_ioctl, DRM_MASTER),
DRM_IOCTL_DEF_DRV(AMDGPU_BO_LIST, amdgpu_bo_list_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(AMDGPU_FENCE_TO_HANDLE, amdgpu_cs_fence_to_handle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
/* KMS */
DRM_IOCTL_DEF_DRV(AMDGPU_GEM_MMAP, amdgpu_gem_mmap_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(AMDGPU_GEM_WAIT_IDLE, amdgpu_gem_wait_idle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6982baeccd14..ea25164e7f4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -40,9 +40,7 @@
static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
- struct amdgpu_bo *bo;
-
- bo = container_of(tbo, struct amdgpu_bo, tbo);
+ struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
amdgpu_bo_kunmap(bo);
@@ -371,6 +369,9 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
&bo->placement, page_align, !kernel, NULL,
acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
+ if (unlikely(r != 0))
+ return r;
+
bytes_moved = atomic64_read(&adev->num_bytes_moved) -
initial_bytes_moved;
if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
@@ -380,9 +381,6 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
else
amdgpu_cs_report_moved_bytes(adev, bytes_moved, 0);
- if (unlikely(r != 0))
- return r;
-
if (kernel)
bo->tbo.priority = 1;
@@ -884,7 +882,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
return;
- abo = container_of(bo, struct amdgpu_bo, tbo);
+ abo = ttm_to_amdgpu_bo(bo);
amdgpu_vm_bo_invalidate(adev, abo, evict);
amdgpu_bo_kunmap(abo);
@@ -911,7 +909,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
return 0;
- abo = container_of(bo, struct amdgpu_bo, tbo);
+ abo = ttm_to_amdgpu_bo(bo);
/* Remember that this BO was accessed by the CPU */
abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 39b6bf6fb051..428aae048f4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -94,6 +94,11 @@ struct amdgpu_bo {
};
};
+static inline struct amdgpu_bo *ttm_to_amdgpu_bo(struct ttm_buffer_object *tbo)
+{
+ return container_of(tbo, struct amdgpu_bo, tbo);
+}
+
/**
* amdgpu_mem_type_to_domain - return domain corresponding to mem_type
* @mem_type: ttm memory type
@@ -188,6 +193,14 @@ static inline bool amdgpu_bo_gpu_accessible(struct amdgpu_bo *bo)
}
}
+/**
+ * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced
+ */
+static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
+{
+ return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
+}
+
int amdgpu_bo_create(struct amdgpu_device *adev,
unsigned long size, int byte_align,
bool kernel, u32 domain, u64 flags,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f6ce52956e6d..a59e04f3eeba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -64,10 +64,6 @@ static const struct cg_flag_name clocks[] = {
void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
{
- if (adev->pp_enabled)
- /* TODO */
- return;
-
if (adev->pm.dpm_enabled) {
mutex_lock(&adev->pm.mutex);
if (power_supply_is_system_supplied() > 0)
@@ -118,7 +114,7 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
goto fail;
}
- if (adev->pp_enabled) {
+ if (adev->powerplay.pp_funcs->dispatch_tasks) {
amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_ENABLE_USER_STATE, &state, NULL);
} else {
mutex_lock(&adev->pm.mutex);
@@ -303,7 +299,8 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
if (strlen(buf) == 1)
adev->pp_force_state_enabled = false;
- else if (adev->pp_enabled) {
+ else if (adev->powerplay.pp_funcs->dispatch_tasks &&
+ adev->powerplay.pp_funcs->get_pp_num_states) {
struct pp_states_info data;
ret = kstrtoul(buf, 0, &idx);
@@ -531,7 +528,7 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
if (adev->powerplay.pp_funcs->set_sclk_od)
amdgpu_dpm_set_sclk_od(adev, (uint32_t)value);
- if (adev->pp_enabled) {
+ if (adev->powerplay.pp_funcs->dispatch_tasks) {
amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_READJUST_POWER_STATE, NULL, NULL);
} else {
adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps;
@@ -575,7 +572,7 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
if (adev->powerplay.pp_funcs->set_mclk_od)
amdgpu_dpm_set_mclk_od(adev, (uint32_t)value);
- if (adev->pp_enabled) {
+ if (adev->powerplay.pp_funcs->dispatch_tasks) {
amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_READJUST_POWER_STATE, NULL, NULL);
} else {
adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps;
@@ -959,9 +956,6 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
attr == &sensor_dev_attr_pwm1_min.dev_attr.attr))
return 0;
- if (adev->pp_enabled)
- return effective_mode;
-
/* Skip fan attributes if fan is not present */
if (adev->pm.no_fan &&
(attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
@@ -1317,6 +1311,9 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
if (adev->pm.sysfs_initialized)
return 0;
+ if (adev->pm.dpm_enabled == 0)
+ return 0;
+
if (adev->powerplay.pp_funcs->get_temperature == NULL)
return 0;
@@ -1341,27 +1338,26 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
return ret;
}
- if (adev->pp_enabled) {
- ret = device_create_file(adev->dev, &dev_attr_pp_num_states);
- if (ret) {
- DRM_ERROR("failed to create device file pp_num_states\n");
- return ret;
- }
- ret = device_create_file(adev->dev, &dev_attr_pp_cur_state);
- if (ret) {
- DRM_ERROR("failed to create device file pp_cur_state\n");
- return ret;
- }
- ret = device_create_file(adev->dev, &dev_attr_pp_force_state);
- if (ret) {
- DRM_ERROR("failed to create device file pp_force_state\n");
- return ret;
- }
- ret = device_create_file(adev->dev, &dev_attr_pp_table);
- if (ret) {
- DRM_ERROR("failed to create device file pp_table\n");
- return ret;
- }
+
+ ret = device_create_file(adev->dev, &dev_attr_pp_num_states);
+ if (ret) {
+ DRM_ERROR("failed to create device file pp_num_states\n");
+ return ret;
+ }
+ ret = device_create_file(adev->dev, &dev_attr_pp_cur_state);
+ if (ret) {
+ DRM_ERROR("failed to create device file pp_cur_state\n");
+ return ret;
+ }
+ ret = device_create_file(adev->dev, &dev_attr_pp_force_state);
+ if (ret) {
+ DRM_ERROR("failed to create device file pp_force_state\n");
+ return ret;
+ }
+ ret = device_create_file(adev->dev, &dev_attr_pp_table);
+ if (ret) {
+ DRM_ERROR("failed to create device file pp_table\n");
+ return ret;
}
ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk);
@@ -1417,16 +1413,19 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
{
+ if (adev->pm.dpm_enabled == 0)
+ return;
+
if (adev->pm.int_hwmon_dev)
hwmon_device_unregister(adev->pm.int_hwmon_dev);
device_remove_file(adev->dev, &dev_attr_power_dpm_state);
device_remove_file(adev->dev, &dev_attr_power_dpm_force_performance_level);
- if (adev->pp_enabled) {
- device_remove_file(adev->dev, &dev_attr_pp_num_states);
- device_remove_file(adev->dev, &dev_attr_pp_cur_state);
- device_remove_file(adev->dev, &dev_attr_pp_force_state);
- device_remove_file(adev->dev, &dev_attr_pp_table);
- }
+
+ device_remove_file(adev->dev, &dev_attr_pp_num_states);
+ device_remove_file(adev->dev, &dev_attr_pp_cur_state);
+ device_remove_file(adev->dev, &dev_attr_pp_force_state);
+ device_remove_file(adev->dev, &dev_attr_pp_table);
+
device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk);
device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk);
device_remove_file(adev->dev, &dev_attr_pp_dpm_pcie);
@@ -1457,7 +1456,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
amdgpu_fence_wait_empty(ring);
}
- if (adev->pp_enabled) {
+ if (adev->powerplay.pp_funcs->dispatch_tasks) {
amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_DISPLAY_CONFIG_CHANGE, NULL, NULL);
} else {
mutex_lock(&adev->pm.mutex);
@@ -1592,15 +1591,15 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
if ((adev->flags & AMD_IS_PX) &&
(ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
seq_printf(m, "PX asic powered off\n");
- } else if (adev->pp_enabled) {
- return amdgpu_debugfs_pm_info_pp(m, adev);
- } else {
+ } else if (adev->powerplay.pp_funcs->debugfs_print_current_performance_level) {
mutex_lock(&adev->pm.mutex);
if (adev->powerplay.pp_funcs->debugfs_print_current_performance_level)
adev->powerplay.pp_funcs->debugfs_print_current_performance_level(adev, m);
else
seq_printf(m, "Debugfs support not implemented for this asic\n");
mutex_unlock(&adev->pm.mutex);
+ } else {
+ return amdgpu_debugfs_pm_info_pp(m, adev);
}
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 2d2f0960b025..5f5aa5fddc16 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -34,24 +34,6 @@
#include "cik_dpm.h"
#include "vi_dpm.h"
-static int amdgpu_create_pp_handle(struct amdgpu_device *adev)
-{
- struct amd_pp_init pp_init;
- struct amd_powerplay *amd_pp;
- int ret;
-
- amd_pp = &(adev->powerplay);
- pp_init.chip_family = adev->family;
- pp_init.chip_id = adev->asic_type;
- pp_init.pm_en = (amdgpu_dpm != 0 && !amdgpu_sriov_vf(adev)) ? true : false;
- pp_init.feature_mask = amdgpu_pp_feature_mask;
- pp_init.device = amdgpu_cgs_create_device(adev);
- ret = amd_powerplay_create(&pp_init, &(amd_pp->pp_handle));
- if (ret)
- return -EINVAL;
- return 0;
-}
-
static int amdgpu_pp_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -59,7 +41,6 @@ static int amdgpu_pp_early_init(void *handle)
int ret = 0;
amd_pp = &(adev->powerplay);
- adev->pp_enabled = false;
amd_pp->pp_handle = (void *)adev;
switch (adev->asic_type) {
@@ -73,9 +54,7 @@ static int amdgpu_pp_early_init(void *handle)
case CHIP_STONEY:
case CHIP_VEGA10:
case CHIP_RAVEN:
- adev->pp_enabled = true;
- if (amdgpu_create_pp_handle(adev))
- return -EINVAL;
+ amd_pp->cgs_device = amdgpu_cgs_create_device(adev);
amd_pp->ip_funcs = &pp_ip_funcs;
amd_pp->pp_funcs = &pp_dpm_funcs;
break;
@@ -97,9 +76,7 @@ static int amdgpu_pp_early_init(void *handle)
amd_pp->ip_funcs = &ci_dpm_ip_funcs;
amd_pp->pp_funcs = &ci_dpm_funcs;
} else {
- adev->pp_enabled = true;
- if (amdgpu_create_pp_handle(adev))
- return -EINVAL;
+ amd_pp->cgs_device = amdgpu_cgs_create_device(adev);
amd_pp->ip_funcs = &pp_ip_funcs;
amd_pp->pp_funcs = &pp_dpm_funcs;
}
@@ -118,12 +95,9 @@ static int amdgpu_pp_early_init(void *handle)
if (adev->powerplay.ip_funcs->early_init)
ret = adev->powerplay.ip_funcs->early_init(
- adev->powerplay.pp_handle);
+ amd_pp->cgs_device ? amd_pp->cgs_device :
+ amd_pp->pp_handle);
- if (ret == PP_DPM_DISABLED) {
- adev->pm.dpm_enabled = false;
- return 0;
- }
return ret;
}
@@ -137,11 +111,6 @@ static int amdgpu_pp_late_init(void *handle)
ret = adev->powerplay.ip_funcs->late_init(
adev->powerplay.pp_handle);
- if (adev->pp_enabled && adev->pm.dpm_enabled) {
- amdgpu_pm_sysfs_init(adev);
- amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_COMPLETE_INIT, NULL, NULL);
- }
-
return ret;
}
@@ -176,21 +145,13 @@ static int amdgpu_pp_hw_init(void *handle)
int ret = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->pp_enabled && adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
amdgpu_ucode_init_bo(adev);
if (adev->powerplay.ip_funcs->hw_init)
ret = adev->powerplay.ip_funcs->hw_init(
adev->powerplay.pp_handle);
- if (ret == PP_DPM_DISABLED) {
- adev->pm.dpm_enabled = false;
- return 0;
- }
-
- if ((amdgpu_dpm != 0) && !amdgpu_sriov_vf(adev))
- adev->pm.dpm_enabled = true;
-
return ret;
}
@@ -199,14 +160,11 @@ static int amdgpu_pp_hw_fini(void *handle)
int ret = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->pp_enabled && adev->pm.dpm_enabled)
- amdgpu_pm_sysfs_fini(adev);
-
if (adev->powerplay.ip_funcs->hw_fini)
ret = adev->powerplay.ip_funcs->hw_fini(
adev->powerplay.pp_handle);
- if (adev->pp_enabled && adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
amdgpu_ucode_fini_bo(adev);
return ret;
@@ -220,9 +178,8 @@ static void amdgpu_pp_late_fini(void *handle)
adev->powerplay.ip_funcs->late_fini(
adev->powerplay.pp_handle);
-
- if (adev->pp_enabled)
- amd_powerplay_destroy(adev->powerplay.pp_handle);
+ if (adev->powerplay.cgs_device)
+ amdgpu_cgs_destroy_device(adev->powerplay.cgs_device);
}
static int amdgpu_pp_suspend(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index befc09b68543..190e28cb827e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -121,7 +121,7 @@ static enum amdgpu_ring_type amdgpu_hw_ip_to_ring_type(int hw_ip)
static int amdgpu_lru_map(struct amdgpu_device *adev,
struct amdgpu_queue_mapper *mapper,
- int user_ring,
+ int user_ring, bool lru_pipe_order,
struct amdgpu_ring **out_ring)
{
int r, i, j;
@@ -139,7 +139,7 @@ static int amdgpu_lru_map(struct amdgpu_device *adev,
}
r = amdgpu_ring_lru_get(adev, ring_type, ring_blacklist,
- j, out_ring);
+ j, lru_pipe_order, out_ring);
if (r)
return r;
@@ -284,8 +284,10 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
r = amdgpu_identity_map(adev, mapper, ring, out_ring);
break;
case AMDGPU_HW_IP_DMA:
+ r = amdgpu_lru_map(adev, mapper, ring, false, out_ring);
+ break;
case AMDGPU_HW_IP_COMPUTE:
- r = amdgpu_lru_map(adev, mapper, ring, out_ring);
+ r = amdgpu_lru_map(adev, mapper, ring, true, out_ring);
break;
default:
*out_ring = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 5ce65280b396..a98fbbb4739f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -136,7 +136,8 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring)
if (ring->funcs->end_use)
ring->funcs->end_use(ring);
- amdgpu_ring_lru_touch(ring->adev, ring);
+ if (ring->funcs->type != AMDGPU_RING_TYPE_KIQ)
+ amdgpu_ring_lru_touch(ring->adev, ring);
}
/**
@@ -155,6 +156,75 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
}
/**
+ * amdgpu_ring_priority_put - restore a ring's priority
+ *
+ * @ring: amdgpu_ring structure holding the information
+ * @priority: target priority
+ *
+ * Release a request for executing at @priority
+ */
+void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
+ enum amd_sched_priority priority)
+{
+ int i;
+
+ if (!ring->funcs->set_priority)
+ return;
+
+ if (atomic_dec_return(&ring->num_jobs[priority]) > 0)
+ return;
+
+ /* no need to restore if the job is already at the lowest priority */
+ if (priority == AMD_SCHED_PRIORITY_NORMAL)
+ return;
+
+ mutex_lock(&ring->priority_mutex);
+ /* something higher prio is executing, no need to decay */
+ if (ring->priority > priority)
+ goto out_unlock;
+
+ /* decay priority to the next level with a job available */
+ for (i = priority; i >= AMD_SCHED_PRIORITY_MIN; i--) {
+ if (i == AMD_SCHED_PRIORITY_NORMAL
+ || atomic_read(&ring->num_jobs[i])) {
+ ring->priority = i;
+ ring->funcs->set_priority(ring, i);
+ break;
+ }
+ }
+
+out_unlock:
+ mutex_unlock(&ring->priority_mutex);
+}
+
+/**
+ * amdgpu_ring_priority_get - change the ring's priority
+ *
+ * @ring: amdgpu_ring structure holding the information
+ * @priority: target priority
+ *
+ * Request a ring's priority to be raised to @priority (refcounted).
+ */
+void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
+ enum amd_sched_priority priority)
+{
+ if (!ring->funcs->set_priority)
+ return;
+
+ atomic_inc(&ring->num_jobs[priority]);
+
+ mutex_lock(&ring->priority_mutex);
+ if (priority <= ring->priority)
+ goto out_unlock;
+
+ ring->priority = priority;
+ ring->funcs->set_priority(ring, priority);
+
+out_unlock:
+ mutex_unlock(&ring->priority_mutex);
+}
+
+/**
* amdgpu_ring_init - init driver ring struct.
*
* @adev: amdgpu_device pointer
@@ -169,7 +239,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
unsigned max_dw, struct amdgpu_irq_src *irq_src,
unsigned irq_type)
{
- int r;
+ int r, i;
int sched_hw_submission = amdgpu_sched_hw_submission;
/* Set the hw submission limit higher for KIQ because
@@ -247,9 +317,14 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
}
ring->max_dw = max_dw;
+ ring->priority = AMD_SCHED_PRIORITY_NORMAL;
+ mutex_init(&ring->priority_mutex);
INIT_LIST_HEAD(&ring->lru_list);
amdgpu_ring_lru_touch(adev, ring);
+ for (i = 0; i < AMD_SCHED_PRIORITY_MAX; ++i)
+ atomic_set(&ring->num_jobs[i], 0);
+
if (amdgpu_debugfs_ring_init(adev, ring)) {
DRM_ERROR("Failed to register debugfs file for rings !\n");
}
@@ -315,14 +390,16 @@ static bool amdgpu_ring_is_blacklisted(struct amdgpu_ring *ring,
* @type: amdgpu_ring_type enum
* @blacklist: blacklisted ring ids array
* @num_blacklist: number of entries in @blacklist
+ * @lru_pipe_order: find a ring from the least recently used pipe
* @ring: output ring
*
* Retrieve the amdgpu_ring structure for the least recently used ring of
* a specific IP block (all asics).
* Returns 0 on success, error on failure.
*/
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
- int num_blacklist, struct amdgpu_ring **ring)
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
+ int *blacklist, int num_blacklist,
+ bool lru_pipe_order, struct amdgpu_ring **ring)
{
struct amdgpu_ring *entry;
@@ -337,10 +414,23 @@ int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
if (amdgpu_ring_is_blacklisted(entry, blacklist, num_blacklist))
continue;
- *ring = entry;
- amdgpu_ring_lru_touch_locked(adev, *ring);
- break;
+ if (!*ring) {
+ *ring = entry;
+
+ /* We are done for ring LRU */
+ if (!lru_pipe_order)
+ break;
+ }
+
+ /* Move all rings on the same pipe to the end of the list */
+ if (entry->pipe == (*ring)->pipe)
+ amdgpu_ring_lru_touch_locked(adev, entry);
}
+
+ /* Move the ring we found to the end of the list */
+ if (*ring)
+ amdgpu_ring_lru_touch_locked(adev, *ring);
+
spin_unlock(&adev->ring_lru_list_lock);
if (!*ring) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 322d25299a00..b18c2b96691f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -24,6 +24,7 @@
#ifndef __AMDGPU_RING_H__
#define __AMDGPU_RING_H__
+#include <drm/amdgpu_drm.h>
#include "gpu_scheduler.h"
/* max number of rings */
@@ -56,6 +57,7 @@ struct amdgpu_device;
struct amdgpu_ring;
struct amdgpu_ib;
struct amdgpu_cs_parser;
+struct amdgpu_job;
/*
* Fences.
@@ -88,8 +90,12 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
void amdgpu_fence_driver_suspend(struct amdgpu_device *adev);
void amdgpu_fence_driver_resume(struct amdgpu_device *adev);
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence);
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s);
void amdgpu_fence_process(struct amdgpu_ring *ring);
int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
+signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
+ uint32_t wait_seq,
+ signed long timeout);
unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring);
/*
@@ -147,6 +153,9 @@ struct amdgpu_ring_funcs {
void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg);
void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
void (*emit_tmz)(struct amdgpu_ring *ring, bool start);
+ /* priority functions */
+ void (*set_priority) (struct amdgpu_ring *ring,
+ enum amd_sched_priority priority);
};
struct amdgpu_ring {
@@ -187,6 +196,12 @@ struct amdgpu_ring {
volatile u32 *cond_exe_cpu_addr;
unsigned vm_inv_eng;
bool has_compute_vm_bug;
+
+ atomic_t num_jobs[AMD_SCHED_PRIORITY_MAX];
+ struct mutex priority_mutex;
+ /* protected by priority_mutex */
+ int priority;
+
#if defined(CONFIG_DEBUG_FS)
struct dentry *ent;
#endif
@@ -197,12 +212,17 @@ void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
void amdgpu_ring_commit(struct amdgpu_ring *ring);
void amdgpu_ring_undo(struct amdgpu_ring *ring);
+void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
+ enum amd_sched_priority priority);
+void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
+ enum amd_sched_priority priority);
int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
unsigned ring_size, struct amdgpu_irq_src *irq_src,
unsigned irq_type);
void amdgpu_ring_fini(struct amdgpu_ring *ring);
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
- int num_blacklist, struct amdgpu_ring **ring);
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
+ int *blacklist, int num_blacklist,
+ bool lru_pipe_order, struct amdgpu_ring **ring);
void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
{
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
new file mode 100644
index 000000000000..290cc3f9c433
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2017 Valve Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Andres Rodriguez <andresx7@gmail.com>
+ */
+
+#include <linux/fdtable.h>
+#include <linux/pid.h>
+#include <drm/amdgpu_drm.h>
+#include "amdgpu.h"
+
+#include "amdgpu_vm.h"
+
+enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+{
+ switch (amdgpu_priority) {
+ case AMDGPU_CTX_PRIORITY_VERY_HIGH:
+ return AMD_SCHED_PRIORITY_HIGH_HW;
+ case AMDGPU_CTX_PRIORITY_HIGH:
+ return AMD_SCHED_PRIORITY_HIGH_SW;
+ case AMDGPU_CTX_PRIORITY_NORMAL:
+ return AMD_SCHED_PRIORITY_NORMAL;
+ case AMDGPU_CTX_PRIORITY_LOW:
+ case AMDGPU_CTX_PRIORITY_VERY_LOW:
+ return AMD_SCHED_PRIORITY_LOW;
+ case AMDGPU_CTX_PRIORITY_UNSET:
+ return AMD_SCHED_PRIORITY_UNSET;
+ default:
+ WARN(1, "Invalid context priority %d\n", amdgpu_priority);
+ return AMD_SCHED_PRIORITY_INVALID;
+ }
+}
+
+static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
+ int fd,
+ enum amd_sched_priority priority)
+{
+ struct file *filp = fcheck(fd);
+ struct drm_file *file;
+ struct pid *pid;
+ struct amdgpu_fpriv *fpriv;
+ struct amdgpu_ctx *ctx;
+ uint32_t id;
+
+ if (!filp)
+ return -EINVAL;
+
+ pid = get_pid(((struct drm_file *)filp->private_data)->pid);
+
+ mutex_lock(&adev->ddev->filelist_mutex);
+ list_for_each_entry(file, &adev->ddev->filelist, lhead) {
+ if (file->pid != pid)
+ continue;
+
+ fpriv = file->driver_priv;
+ idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id)
+ amdgpu_ctx_priority_override(ctx, priority);
+ }
+ mutex_unlock(&adev->ddev->filelist_mutex);
+
+ put_pid(pid);
+
+ return 0;
+}
+
+int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *filp)
+{
+ union drm_amdgpu_sched *args = data;
+ struct amdgpu_device *adev = dev->dev_private;
+ enum amd_sched_priority priority;
+ int r;
+
+ priority = amdgpu_to_sched_priority(args->in.priority);
+ if (args->in.flags || priority == AMD_SCHED_PRIORITY_INVALID)
+ return -EINVAL;
+
+ switch (args->in.op) {
+ case AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE:
+ r = amdgpu_sched_process_priority_override(adev,
+ args->in.fd,
+ priority);
+ break;
+ default:
+ DRM_ERROR("Invalid sched op specified: %d\n", args->in.op);
+ r = -EINVAL;
+ break;
+ }
+
+ return r;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
index 13c8dbbccaf2..b28c067d3822 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
@@ -1,5 +1,5 @@
/*
- * Copyright 2015 Advanced Micro Devices, Inc.
+ * Copyright 2017 Valve Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
@@ -19,22 +19,16 @@
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*
+ * Authors: Andres Rodriguez <andresx7@gmail.com>
*/
-#ifndef _ICELAND_SMC_H
-#define _ICELAND_SMC_H
-#include "smumgr.h"
+#ifndef __AMDGPU_SCHED_H__
+#define __AMDGPU_SCHED_H__
+#include <drm/drmP.h>
-int iceland_populate_all_graphic_levels(struct pp_hwmgr *hwmgr);
-int iceland_populate_all_memory_levels(struct pp_hwmgr *hwmgr);
-int iceland_init_smc_table(struct pp_hwmgr *hwmgr);
-int iceland_thermal_setup_fan_table(struct pp_hwmgr *hwmgr);
-int iceland_update_sclk_threshold(struct pp_hwmgr *hwmgr);
-uint32_t iceland_get_offsetof(uint32_t type, uint32_t member);
-uint32_t iceland_get_mac_definition(uint32_t value);
-int iceland_process_firmware_header(struct pp_hwmgr *hwmgr);
-int iceland_initialize_mc_reg_table(struct pp_hwmgr *hwmgr);
-bool iceland_is_dpm_running(struct pp_hwmgr *hwmgr);
-#endif
+enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority);
+int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *filp);
+#endif // __AMDGPU_SCHED_H__
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index c586f44312f9..a4bf21f8f1c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -169,14 +169,14 @@ int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
*
* @sync: sync object to add fences from reservation object to
* @resv: reservation object with embedded fence
- * @shared: true if we should only sync to the exclusive fence
+ * @explicit_sync: true if we should only sync to the exclusive fence
*
* Sync to the fence
*/
int amdgpu_sync_resv(struct amdgpu_device *adev,
struct amdgpu_sync *sync,
struct reservation_object *resv,
- void *owner)
+ void *owner, bool explicit_sync)
{
struct reservation_object_list *flist;
struct dma_fence *f;
@@ -191,6 +191,9 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
f = reservation_object_get_excl(resv);
r = amdgpu_sync_fence(adev, sync, f);
+ if (explicit_sync)
+ return r;
+
flist = reservation_object_get_list(resv);
if (!flist || r)
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index dc7687993317..70d7e3a279a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -45,7 +45,8 @@ int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
int amdgpu_sync_resv(struct amdgpu_device *adev,
struct amdgpu_sync *sync,
struct reservation_object *resv,
- void *owner);
+ void *owner,
+ bool explicit_sync);
struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
struct amdgpu_ring *ring);
struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 15a28578d458..1f036af85ba6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -44,6 +44,7 @@
#include <linux/debugfs.h>
#include <linux/iommu.h>
#include "amdgpu.h"
+#include "amdgpu_object.h"
#include "amdgpu_trace.h"
#include "bif/bif_4_1_d.h"
@@ -209,7 +210,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
placement->num_busy_placement = 1;
return;
}
- abo = container_of(bo, struct amdgpu_bo, tbo);
+ abo = ttm_to_amdgpu_bo(bo);
switch (bo->mem.mem_type) {
case TTM_PL_VRAM:
if (adev->mman.buffer_funcs &&
@@ -257,7 +258,7 @@ gtt:
static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
{
- struct amdgpu_bo *abo = container_of(bo, struct amdgpu_bo, tbo);
+ struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
if (amdgpu_ttm_tt_get_usermm(bo->ttm))
return -EPERM;
@@ -289,97 +290,177 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
return addr;
}
-static int amdgpu_move_blit(struct ttm_buffer_object *bo,
- bool evict, bool no_wait_gpu,
- struct ttm_mem_reg *new_mem,
- struct ttm_mem_reg *old_mem)
+/**
+ * amdgpu_find_mm_node - Helper function finds the drm_mm_node
+ * corresponding to @offset. It also modifies the offset to be
+ * within the drm_mm_node returned
+ */
+static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
+ unsigned long *offset)
{
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
- struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+ struct drm_mm_node *mm_node = mem->mm_node;
- struct drm_mm_node *old_mm, *new_mm;
- uint64_t old_start, old_size, new_start, new_size;
- unsigned long num_pages;
- struct dma_fence *fence = NULL;
- int r;
+ while (*offset >= (mm_node->size << PAGE_SHIFT)) {
+ *offset -= (mm_node->size << PAGE_SHIFT);
+ ++mm_node;
+ }
+ return mm_node;
+}
- BUILD_BUG_ON((PAGE_SIZE % AMDGPU_GPU_PAGE_SIZE) != 0);
+/**
+ * amdgpu_copy_ttm_mem_to_mem - Helper function for copy
+ *
+ * The function copies @size bytes from {src->mem + src->offset} to
+ * {dst->mem + dst->offset}. src->bo and dst->bo could be same BO for a
+ * move and different for a BO to BO copy.
+ *
+ * @f: Returns the last fence if multiple jobs are submitted.
+ */
+int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
+ struct amdgpu_copy_mem *src,
+ struct amdgpu_copy_mem *dst,
+ uint64_t size,
+ struct reservation_object *resv,
+ struct dma_fence **f)
+{
+ struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+ struct drm_mm_node *src_mm, *dst_mm;
+ uint64_t src_node_start, dst_node_start, src_node_size,
+ dst_node_size, src_page_offset, dst_page_offset;
+ struct dma_fence *fence = NULL;
+ int r = 0;
+ const uint64_t GTT_MAX_BYTES = (AMDGPU_GTT_MAX_TRANSFER_SIZE *
+ AMDGPU_GPU_PAGE_SIZE);
if (!ring->ready) {
DRM_ERROR("Trying to move memory with ring turned off.\n");
return -EINVAL;
}
- old_mm = old_mem->mm_node;
- old_size = old_mm->size;
- old_start = amdgpu_mm_node_addr(bo, old_mm, old_mem);
+ src_mm = amdgpu_find_mm_node(src->mem, &src->offset);
+ src_node_start = amdgpu_mm_node_addr(src->bo, src_mm, src->mem) +
+ src->offset;
+ src_node_size = (src_mm->size << PAGE_SHIFT) - src->offset;
+ src_page_offset = src_node_start & (PAGE_SIZE - 1);
- new_mm = new_mem->mm_node;
- new_size = new_mm->size;
- new_start = amdgpu_mm_node_addr(bo, new_mm, new_mem);
+ dst_mm = amdgpu_find_mm_node(dst->mem, &dst->offset);
+ dst_node_start = amdgpu_mm_node_addr(dst->bo, dst_mm, dst->mem) +
+ dst->offset;
+ dst_node_size = (dst_mm->size << PAGE_SHIFT) - dst->offset;
+ dst_page_offset = dst_node_start & (PAGE_SIZE - 1);
- num_pages = new_mem->num_pages;
mutex_lock(&adev->mman.gtt_window_lock);
- while (num_pages) {
- unsigned long cur_pages = min(min(old_size, new_size),
- (u64)AMDGPU_GTT_MAX_TRANSFER_SIZE);
- uint64_t from = old_start, to = new_start;
+
+ while (size) {
+ unsigned long cur_size;
+ uint64_t from = src_node_start, to = dst_node_start;
struct dma_fence *next;
- if (old_mem->mem_type == TTM_PL_TT &&
- !amdgpu_gtt_mgr_is_allocated(old_mem)) {
- r = amdgpu_map_buffer(bo, old_mem, cur_pages,
- old_start, 0, ring, &from);
+ /* Copy size cannot exceed GTT_MAX_BYTES. So if src or dst
+ * begins at an offset, then adjust the size accordingly
+ */
+ cur_size = min3(min(src_node_size, dst_node_size), size,
+ GTT_MAX_BYTES);
+ if (cur_size + src_page_offset > GTT_MAX_BYTES ||
+ cur_size + dst_page_offset > GTT_MAX_BYTES)
+ cur_size -= max(src_page_offset, dst_page_offset);
+
+ /* Map only what needs to be accessed. Map src to window 0 and
+ * dst to window 1
+ */
+ if (src->mem->mem_type == TTM_PL_TT &&
+ !amdgpu_gtt_mgr_is_allocated(src->mem)) {
+ r = amdgpu_map_buffer(src->bo, src->mem,
+ PFN_UP(cur_size + src_page_offset),
+ src_node_start, 0, ring,
+ &from);
if (r)
goto error;
+ /* Adjust the offset because amdgpu_map_buffer returns
+ * start of mapped page
+ */
+ from += src_page_offset;
}
- if (new_mem->mem_type == TTM_PL_TT &&
- !amdgpu_gtt_mgr_is_allocated(new_mem)) {
- r = amdgpu_map_buffer(bo, new_mem, cur_pages,
- new_start, 1, ring, &to);
+ if (dst->mem->mem_type == TTM_PL_TT &&
+ !amdgpu_gtt_mgr_is_allocated(dst->mem)) {
+ r = amdgpu_map_buffer(dst->bo, dst->mem,
+ PFN_UP(cur_size + dst_page_offset),
+ dst_node_start, 1, ring,
+ &to);
if (r)
goto error;
+ to += dst_page_offset;
}
- r = amdgpu_copy_buffer(ring, from, to,
- cur_pages * PAGE_SIZE,
- bo->resv, &next, false, true);
+ r = amdgpu_copy_buffer(ring, from, to, cur_size,
+ resv, &next, false, true);
if (r)
goto error;
dma_fence_put(fence);
fence = next;
- num_pages -= cur_pages;
- if (!num_pages)
+ size -= cur_size;
+ if (!size)
break;
- old_size -= cur_pages;
- if (!old_size) {
- old_start = amdgpu_mm_node_addr(bo, ++old_mm, old_mem);
- old_size = old_mm->size;
+ src_node_size -= cur_size;
+ if (!src_node_size) {
+ src_node_start = amdgpu_mm_node_addr(src->bo, ++src_mm,
+ src->mem);
+ src_node_size = (src_mm->size << PAGE_SHIFT);
} else {
- old_start += cur_pages * PAGE_SIZE;
+ src_node_start += cur_size;
+ src_page_offset = src_node_start & (PAGE_SIZE - 1);
}
-
- new_size -= cur_pages;
- if (!new_size) {
- new_start = amdgpu_mm_node_addr(bo, ++new_mm, new_mem);
- new_size = new_mm->size;
+ dst_node_size -= cur_size;
+ if (!dst_node_size) {
+ dst_node_start = amdgpu_mm_node_addr(dst->bo, ++dst_mm,
+ dst->mem);
+ dst_node_size = (dst_mm->size << PAGE_SHIFT);
} else {
- new_start += cur_pages * PAGE_SIZE;
+ dst_node_start += cur_size;
+ dst_page_offset = dst_node_start & (PAGE_SIZE - 1);
}
}
+error:
mutex_unlock(&adev->mman.gtt_window_lock);
+ if (f)
+ *f = dma_fence_get(fence);
+ dma_fence_put(fence);
+ return r;
+}
+
+
+static int amdgpu_move_blit(struct ttm_buffer_object *bo,
+ bool evict, bool no_wait_gpu,
+ struct ttm_mem_reg *new_mem,
+ struct ttm_mem_reg *old_mem)
+{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+ struct amdgpu_copy_mem src, dst;
+ struct dma_fence *fence = NULL;
+ int r;
+
+ src.bo = bo;
+ dst.bo = bo;
+ src.mem = old_mem;
+ dst.mem = new_mem;
+ src.offset = 0;
+ dst.offset = 0;
+
+ r = amdgpu_ttm_copy_mem_to_mem(adev, &src, &dst,
+ new_mem->num_pages << PAGE_SHIFT,
+ bo->resv, &fence);
+ if (r)
+ goto error;
r = ttm_bo_pipeline_move(bo, fence, evict, new_mem);
dma_fence_put(fence);
return r;
error:
- mutex_unlock(&adev->mman.gtt_window_lock);
-
if (fence)
dma_fence_wait(fence, false);
dma_fence_put(fence);
@@ -484,7 +565,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo,
int r;
/* Can't move a pinned BO */
- abo = container_of(bo, struct amdgpu_bo, tbo);
+ abo = ttm_to_amdgpu_bo(bo);
if (WARN_ON_ONCE(abo->pin_count > 0))
return -EINVAL;
@@ -582,13 +663,12 @@ static void amdgpu_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
unsigned long page_offset)
{
- struct drm_mm_node *mm = bo->mem.mm_node;
- uint64_t size = mm->size;
- uint64_t offset = page_offset;
+ struct drm_mm_node *mm;
+ unsigned long offset = (page_offset << PAGE_SHIFT);
- page_offset = do_div(offset, size);
- mm += offset;
- return (bo->mem.bus.base >> PAGE_SHIFT) + mm->start + page_offset;
+ mm = amdgpu_find_mm_node(&bo->mem, &offset);
+ return (bo->mem.bus.base >> PAGE_SHIFT) + mm->start +
+ (offset >> PAGE_SHIFT);
}
/*
@@ -829,7 +909,8 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem)
placement.busy_placement = &placements;
placements.fpfn = 0;
placements.lpfn = adev->mc.gart_size >> PAGE_SHIFT;
- placements.flags = bo->mem.placement | TTM_PL_FLAG_TT;
+ placements.flags = (bo->mem.placement & ~TTM_PL_MASK_MEM) |
+ TTM_PL_FLAG_TT;
r = ttm_bo_mem_space(bo, &placement, &tmp, true, false);
if (unlikely(r))
@@ -1112,9 +1193,6 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
unsigned long num_pages = bo->mem.num_pages;
struct drm_mm_node *node = bo->mem.mm_node;
- if (bo->mem.start != AMDGPU_BO_INVALID_OFFSET)
- return ttm_bo_eviction_valuable(bo, place);
-
switch (bo->mem.mem_type) {
case TTM_PL_TT:
return true;
@@ -1129,7 +1207,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
num_pages -= node->size;
++node;
}
- break;
+ return false;
default:
break;
@@ -1142,9 +1220,9 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
unsigned long offset,
void *buf, int len, int write)
{
- struct amdgpu_bo *abo = container_of(bo, struct amdgpu_bo, tbo);
+ struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
- struct drm_mm_node *nodes = abo->tbo.mem.mm_node;
+ struct drm_mm_node *nodes;
uint32_t value = 0;
int ret = 0;
uint64_t pos;
@@ -1153,10 +1231,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
if (bo->mem.mem_type != TTM_PL_VRAM)
return -EIO;
- while (offset >= (nodes->size << PAGE_SHIFT)) {
- offset -= nodes->size << PAGE_SHIFT;
- ++nodes;
- }
+ nodes = amdgpu_find_mm_node(&abo->tbo.mem, &offset);
pos = (nodes->start << PAGE_SHIFT) + offset;
while (len && pos < adev->mc.mc_vram_size) {
@@ -1255,6 +1330,15 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
/* Change the size here instead of the init above so only lpfn is affected */
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
+ /*
+ *The reserved vram for firmware must be pinned to the specified
+ *place on the VRAM, so reserve it early.
+ */
+ r = amdgpu_fw_reserve_vram_init(adev);
+ if (r) {
+ return r;
+ }
+
r = amdgpu_bo_create_kernel(adev, adev->mc.stolen_size, PAGE_SIZE,
AMDGPU_GEM_DOMAIN_VRAM,
&adev->stolen_vga_memory,
@@ -1479,7 +1563,8 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
job->vm_needs_flush = vm_needs_flush;
if (resv) {
r = amdgpu_sync_resv(adev, &job->sync, resv,
- AMDGPU_FENCE_OWNER_UNDEFINED);
+ AMDGPU_FENCE_OWNER_UNDEFINED,
+ false);
if (r) {
DRM_ERROR("sync failed (%d).\n", r);
goto error_free;
@@ -1571,7 +1656,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
if (resv) {
r = amdgpu_sync_resv(adev, &job->sync, resv,
- AMDGPU_FENCE_OWNER_UNDEFINED);
+ AMDGPU_FENCE_OWNER_UNDEFINED, false);
if (r) {
DRM_ERROR("sync failed (%d).\n", r);
goto error_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 7abae6867339..abd4084982a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -58,6 +58,12 @@ struct amdgpu_mman {
struct amd_sched_entity entity;
};
+struct amdgpu_copy_mem {
+ struct ttm_buffer_object *bo;
+ struct ttm_mem_reg *mem;
+ unsigned long offset;
+};
+
extern const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func;
extern const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func;
@@ -72,6 +78,12 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
struct reservation_object *resv,
struct dma_fence **fence, bool direct_submit,
bool vm_needs_flush);
+int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
+ struct amdgpu_copy_mem *src,
+ struct amdgpu_copy_mem *dst,
+ uint64_t size,
+ struct reservation_object *resv,
+ struct dma_fence **f);
int amdgpu_fill_buffer(struct amdgpu_bo *bo,
uint64_t src_data,
struct reservation_object *resv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b46280c1279f..2918de2f39ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -648,7 +648,7 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
uint32_t allocated = 0;
uint32_t tmp, handle = 0;
uint32_t *size = &tmp;
- int i, r, idx = 0;
+ int i, r = 0, idx = 0;
p->job->vm = NULL;
ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.c
index 45ac91861965..7f7097931c6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.c
@@ -25,30 +25,26 @@
#include "amdgpu_vf_error.h"
#include "mxgpu_ai.h"
-#define AMDGPU_VF_ERROR_ENTRY_SIZE 16
-
-/* struct error_entry - amdgpu VF error information. */
-struct amdgpu_vf_error_buffer {
- int read_count;
- int write_count;
- uint16_t code[AMDGPU_VF_ERROR_ENTRY_SIZE];
- uint16_t flags[AMDGPU_VF_ERROR_ENTRY_SIZE];
- uint64_t data[AMDGPU_VF_ERROR_ENTRY_SIZE];
-};
-
-struct amdgpu_vf_error_buffer admgpu_vf_errors;
-
-
-void amdgpu_vf_error_put(uint16_t sub_error_code, uint16_t error_flags, uint64_t error_data)
+void amdgpu_vf_error_put(struct amdgpu_device *adev,
+ uint16_t sub_error_code,
+ uint16_t error_flags,
+ uint64_t error_data)
{
int index;
- uint16_t error_code = AMDGIM_ERROR_CODE(AMDGIM_ERROR_CATEGORY_VF, sub_error_code);
+ uint16_t error_code;
- index = admgpu_vf_errors.write_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
- admgpu_vf_errors.code [index] = error_code;
- admgpu_vf_errors.flags [index] = error_flags;
- admgpu_vf_errors.data [index] = error_data;
- admgpu_vf_errors.write_count ++;
+ if (!amdgpu_sriov_vf(adev))
+ return;
+
+ error_code = AMDGIM_ERROR_CODE(AMDGIM_ERROR_CATEGORY_VF, sub_error_code);
+
+ mutex_lock(&adev->virt.vf_errors.lock);
+ index = adev->virt.vf_errors.write_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
+ adev->virt.vf_errors.code [index] = error_code;
+ adev->virt.vf_errors.flags [index] = error_flags;
+ adev->virt.vf_errors.data [index] = error_data;
+ adev->virt.vf_errors.write_count ++;
+ mutex_unlock(&adev->virt.vf_errors.lock);
}
@@ -58,7 +54,8 @@ void amdgpu_vf_error_trans_all(struct amdgpu_device *adev)
u32 data1, data2, data3;
int index;
- if ((NULL == adev) || (!amdgpu_sriov_vf(adev)) || (!adev->virt.ops) || (!adev->virt.ops->trans_msg)) {
+ if ((NULL == adev) || (!amdgpu_sriov_vf(adev)) ||
+ (!adev->virt.ops) || (!adev->virt.ops->trans_msg)) {
return;
}
/*
@@ -68,18 +65,22 @@ void amdgpu_vf_error_trans_all(struct amdgpu_device *adev)
return;
}
*/
+
+ mutex_lock(&adev->virt.vf_errors.lock);
/* The errors are overlay of array, correct read_count as full. */
- if (admgpu_vf_errors.write_count - admgpu_vf_errors.read_count > AMDGPU_VF_ERROR_ENTRY_SIZE) {
- admgpu_vf_errors.read_count = admgpu_vf_errors.write_count - AMDGPU_VF_ERROR_ENTRY_SIZE;
+ if (adev->virt.vf_errors.write_count - adev->virt.vf_errors.read_count > AMDGPU_VF_ERROR_ENTRY_SIZE) {
+ adev->virt.vf_errors.read_count = adev->virt.vf_errors.write_count - AMDGPU_VF_ERROR_ENTRY_SIZE;
}
- while (admgpu_vf_errors.read_count < admgpu_vf_errors.write_count) {
- index =admgpu_vf_errors.read_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
- data1 = AMDGIM_ERROR_CODE_FLAGS_TO_MAILBOX (admgpu_vf_errors.code[index], admgpu_vf_errors.flags[index]);
- data2 = admgpu_vf_errors.data[index] & 0xFFFFFFFF;
- data3 = (admgpu_vf_errors.data[index] >> 32) & 0xFFFFFFFF;
+ while (adev->virt.vf_errors.read_count < adev->virt.vf_errors.write_count) {
+ index =adev->virt.vf_errors.read_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
+ data1 = AMDGIM_ERROR_CODE_FLAGS_TO_MAILBOX(adev->virt.vf_errors.code[index],
+ adev->virt.vf_errors.flags[index]);
+ data2 = adev->virt.vf_errors.data[index] & 0xFFFFFFFF;
+ data3 = (adev->virt.vf_errors.data[index] >> 32) & 0xFFFFFFFF;
adev->virt.ops->trans_msg(adev, IDH_LOG_VF_ERROR, data1, data2, data3);
- admgpu_vf_errors.read_count ++;
+ adev->virt.vf_errors.read_count ++;
}
+ mutex_unlock(&adev->virt.vf_errors.lock);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.h
index 2a3278ec76ba..6436bd053325 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vf_error.h
@@ -56,7 +56,10 @@ enum AMDGIM_ERROR_CATEGORY {
AMDGIM_ERROR_CATEGORY_MAX
};
-void amdgpu_vf_error_put(uint16_t sub_error_code, uint16_t error_flags, uint64_t error_data);
+void amdgpu_vf_error_put(struct amdgpu_device *adev,
+ uint16_t sub_error_code,
+ uint16_t error_flags,
+ uint64_t error_data);
void amdgpu_vf_error_trans_all (struct amdgpu_device *adev);
#endif /* __VF_ERROR_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index ab05121b9272..6738df836a70 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -22,7 +22,7 @@
*/
#include "amdgpu.h"
-#define MAX_KIQ_REG_WAIT 100000
+#define MAX_KIQ_REG_WAIT 100000000 /* in usecs */
int amdgpu_allocate_static_csa(struct amdgpu_device *adev)
{
@@ -114,27 +114,25 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
{
signed long r;
- uint32_t val;
- struct dma_fence *f;
+ unsigned long flags;
+ uint32_t val, seq;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
struct amdgpu_ring *ring = &kiq->ring;
BUG_ON(!ring->funcs->emit_rreg);
- mutex_lock(&kiq->ring_mutex);
+ spin_lock_irqsave(&kiq->ring_lock, flags);
amdgpu_ring_alloc(ring, 32);
amdgpu_ring_emit_rreg(ring, reg);
- amdgpu_fence_emit(ring, &f);
+ amdgpu_fence_emit_polling(ring, &seq);
amdgpu_ring_commit(ring);
- mutex_unlock(&kiq->ring_mutex);
+ spin_unlock_irqrestore(&kiq->ring_lock, flags);
- r = dma_fence_wait_timeout(f, false, msecs_to_jiffies(MAX_KIQ_REG_WAIT));
- dma_fence_put(f);
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
if (r < 1) {
- DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+ DRM_ERROR("wait for kiq fence error: %ld\n", r);
return ~0;
}
-
val = adev->wb.wb[adev->virt.reg_val_offs];
return val;
@@ -143,23 +141,23 @@ uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
{
signed long r;
- struct dma_fence *f;
+ unsigned long flags;
+ uint32_t seq;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
struct amdgpu_ring *ring = &kiq->ring;
BUG_ON(!ring->funcs->emit_wreg);
- mutex_lock(&kiq->ring_mutex);
+ spin_lock_irqsave(&kiq->ring_lock, flags);
amdgpu_ring_alloc(ring, 32);
amdgpu_ring_emit_wreg(ring, reg, v);
- amdgpu_fence_emit(ring, &f);
+ amdgpu_fence_emit_polling(ring, &seq);
amdgpu_ring_commit(ring);
- mutex_unlock(&kiq->ring_mutex);
+ spin_unlock_irqrestore(&kiq->ring_lock, flags);
- r = dma_fence_wait_timeout(f, false, msecs_to_jiffies(MAX_KIQ_REG_WAIT));
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
if (r < 1)
- DRM_ERROR("wait for kiq fence error: %ld.\n", r);
- dma_fence_put(f);
+ DRM_ERROR("wait for kiq fence error: %ld\n", r);
}
/**
@@ -274,3 +272,80 @@ void amdgpu_virt_free_mm_table(struct amdgpu_device *adev)
(void *)&adev->virt.mm_table.cpu_addr);
adev->virt.mm_table.gpu_addr = 0;
}
+
+
+int amdgpu_virt_fw_reserve_get_checksum(void *obj,
+ unsigned long obj_size,
+ unsigned int key,
+ unsigned int chksum)
+{
+ unsigned int ret = key;
+ unsigned long i = 0;
+ unsigned char *pos;
+
+ pos = (char *)obj;
+ /* calculate checksum */
+ for (i = 0; i < obj_size; ++i)
+ ret += *(pos + i);
+ /* minus the chksum itself */
+ pos = (char *)&chksum;
+ for (i = 0; i < sizeof(chksum); ++i)
+ ret -= *(pos + i);
+ return ret;
+}
+
+void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
+{
+ uint32_t pf2vf_ver = 0;
+ uint32_t pf2vf_size = 0;
+ uint32_t checksum = 0;
+ uint32_t checkval;
+ char *str;
+
+ adev->virt.fw_reserve.p_pf2vf = NULL;
+ adev->virt.fw_reserve.p_vf2pf = NULL;
+
+ if (adev->fw_vram_usage.va != NULL) {
+ adev->virt.fw_reserve.p_pf2vf =
+ (struct amdgim_pf2vf_info_header *)(
+ adev->fw_vram_usage.va + AMDGIM_DATAEXCHANGE_OFFSET);
+ pf2vf_ver = adev->virt.fw_reserve.p_pf2vf->version;
+ AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size);
+ AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum);
+
+ /* pf2vf message must be in 4K */
+ if (pf2vf_size > 0 && pf2vf_size < 4096) {
+ checkval = amdgpu_virt_fw_reserve_get_checksum(
+ adev->virt.fw_reserve.p_pf2vf, pf2vf_size,
+ adev->virt.fw_reserve.checksum_key, checksum);
+ if (checkval == checksum) {
+ adev->virt.fw_reserve.p_vf2pf =
+ ((void *)adev->virt.fw_reserve.p_pf2vf +
+ pf2vf_size);
+ memset((void *)adev->virt.fw_reserve.p_vf2pf, 0,
+ sizeof(amdgim_vf2pf_info));
+ AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.version,
+ AMDGPU_FW_VRAM_VF2PF_VER);
+ AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.size,
+ sizeof(amdgim_vf2pf_info));
+ AMDGPU_FW_VRAM_VF2PF_READ(adev, driver_version,
+ &str);
+#ifdef MODULE
+ if (THIS_MODULE->version != NULL)
+ strcpy(str, THIS_MODULE->version);
+ else
+#endif
+ strcpy(str, "N/A");
+ AMDGPU_FW_VRAM_VF2PF_WRITE(adev, driver_cert,
+ 0);
+ AMDGPU_FW_VRAM_VF2PF_WRITE(adev, checksum,
+ amdgpu_virt_fw_reserve_get_checksum(
+ adev->virt.fw_reserve.p_vf2pf,
+ pf2vf_size,
+ adev->virt.fw_reserve.checksum_key, 0));
+ }
+ }
+ }
+}
+
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index afcfb8bcfb65..b89d37fc406f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -36,6 +36,18 @@ struct amdgpu_mm_table {
uint64_t gpu_addr;
};
+#define AMDGPU_VF_ERROR_ENTRY_SIZE 16
+
+/* struct error_entry - amdgpu VF error information. */
+struct amdgpu_vf_error_buffer {
+ struct mutex lock;
+ int read_count;
+ int write_count;
+ uint16_t code[AMDGPU_VF_ERROR_ENTRY_SIZE];
+ uint16_t flags[AMDGPU_VF_ERROR_ENTRY_SIZE];
+ uint64_t data[AMDGPU_VF_ERROR_ENTRY_SIZE];
+};
+
/**
* struct amdgpu_virt_ops - amdgpu device virt operations
*/
@@ -46,6 +58,179 @@ struct amdgpu_virt_ops {
void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3);
};
+/*
+ * Firmware Reserve Frame buffer
+ */
+struct amdgpu_virt_fw_reserve {
+ struct amdgim_pf2vf_info_header *p_pf2vf;
+ struct amdgim_vf2pf_info_header *p_vf2pf;
+ unsigned int checksum_key;
+};
+/*
+ * Defination between PF and VF
+ * Structures forcibly aligned to 4 to keep the same style as PF.
+ */
+#define AMDGIM_DATAEXCHANGE_OFFSET (64 * 1024)
+
+#define AMDGIM_GET_STRUCTURE_RESERVED_SIZE(total, u8, u16, u32, u64) \
+ (total - (((u8)+3) / 4 + ((u16)+1) / 2 + (u32) + (u64)*2))
+
+enum AMDGIM_FEATURE_FLAG {
+ /* GIM supports feature of Error log collecting */
+ AMDGIM_FEATURE_ERROR_LOG_COLLECT = 0x1,
+ /* GIM supports feature of loading uCodes */
+ AMDGIM_FEATURE_GIM_LOAD_UCODES = 0x2,
+};
+
+struct amdgim_pf2vf_info_header {
+ /* the total structure size in byte. */
+ uint32_t size;
+ /* version of this structure, written by the GIM */
+ uint32_t version;
+} __aligned(4);
+struct amdgim_pf2vf_info_v1 {
+ /* header contains size and version */
+ struct amdgim_pf2vf_info_header header;
+ /* max_width * max_height */
+ unsigned int uvd_enc_max_pixels_count;
+ /* 16x16 pixels/sec, codec independent */
+ unsigned int uvd_enc_max_bandwidth;
+ /* max_width * max_height */
+ unsigned int vce_enc_max_pixels_count;
+ /* 16x16 pixels/sec, codec independent */
+ unsigned int vce_enc_max_bandwidth;
+ /* MEC FW position in kb from the start of visible frame buffer */
+ unsigned int mecfw_kboffset;
+ /* The features flags of the GIM driver supports. */
+ unsigned int feature_flags;
+ /* use private key from mailbox 2 to create chueksum */
+ unsigned int checksum;
+} __aligned(4);
+
+struct amdgim_pf2vf_info_v2 {
+ /* header contains size and version */
+ struct amdgim_pf2vf_info_header header;
+ /* use private key from mailbox 2 to create chueksum */
+ uint32_t checksum;
+ /* The features flags of the GIM driver supports. */
+ uint32_t feature_flags;
+ /* max_width * max_height */
+ uint32_t uvd_enc_max_pixels_count;
+ /* 16x16 pixels/sec, codec independent */
+ uint32_t uvd_enc_max_bandwidth;
+ /* max_width * max_height */
+ uint32_t vce_enc_max_pixels_count;
+ /* 16x16 pixels/sec, codec independent */
+ uint32_t vce_enc_max_bandwidth;
+ /* MEC FW position in kb from the start of VF visible frame buffer */
+ uint64_t mecfw_kboffset;
+ /* MEC FW size in KB */
+ uint32_t mecfw_ksize;
+ /* UVD FW position in kb from the start of VF visible frame buffer */
+ uint64_t uvdfw_kboffset;
+ /* UVD FW size in KB */
+ uint32_t uvdfw_ksize;
+ /* VCE FW position in kb from the start of VF visible frame buffer */
+ uint64_t vcefw_kboffset;
+ /* VCE FW size in KB */
+ uint32_t vcefw_ksize;
+ uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 0, 0, (9 + sizeof(struct amdgim_pf2vf_info_header)/sizeof(uint32_t)), 3)];
+} __aligned(4);
+
+
+struct amdgim_vf2pf_info_header {
+ /* the total structure size in byte. */
+ uint32_t size;
+ /*version of this structure, written by the guest */
+ uint32_t version;
+} __aligned(4);
+
+struct amdgim_vf2pf_info_v1 {
+ /* header contains size and version */
+ struct amdgim_vf2pf_info_header header;
+ /* driver version */
+ char driver_version[64];
+ /* driver certification, 1=WHQL, 0=None */
+ unsigned int driver_cert;
+ /* guest OS type and version: need a define */
+ unsigned int os_info;
+ /* in the unit of 1M */
+ unsigned int fb_usage;
+ /* guest gfx engine usage percentage */
+ unsigned int gfx_usage;
+ /* guest gfx engine health percentage */
+ unsigned int gfx_health;
+ /* guest compute engine usage percentage */
+ unsigned int compute_usage;
+ /* guest compute engine health percentage */
+ unsigned int compute_health;
+ /* guest vce engine usage percentage. 0xffff means N/A. */
+ unsigned int vce_enc_usage;
+ /* guest vce engine health percentage. 0xffff means N/A. */
+ unsigned int vce_enc_health;
+ /* guest uvd engine usage percentage. 0xffff means N/A. */
+ unsigned int uvd_enc_usage;
+ /* guest uvd engine usage percentage. 0xffff means N/A. */
+ unsigned int uvd_enc_health;
+ unsigned int checksum;
+} __aligned(4);
+
+struct amdgim_vf2pf_info_v2 {
+ /* header contains size and version */
+ struct amdgim_vf2pf_info_header header;
+ uint32_t checksum;
+ /* driver version */
+ uint8_t driver_version[64];
+ /* driver certification, 1=WHQL, 0=None */
+ uint32_t driver_cert;
+ /* guest OS type and version: need a define */
+ uint32_t os_info;
+ /* in the unit of 1M */
+ uint32_t fb_usage;
+ /* guest gfx engine usage percentage */
+ uint32_t gfx_usage;
+ /* guest gfx engine health percentage */
+ uint32_t gfx_health;
+ /* guest compute engine usage percentage */
+ uint32_t compute_usage;
+ /* guest compute engine health percentage */
+ uint32_t compute_health;
+ /* guest vce engine usage percentage. 0xffff means N/A. */
+ uint32_t vce_enc_usage;
+ /* guest vce engine health percentage. 0xffff means N/A. */
+ uint32_t vce_enc_health;
+ /* guest uvd engine usage percentage. 0xffff means N/A. */
+ uint32_t uvd_enc_usage;
+ /* guest uvd engine usage percentage. 0xffff means N/A. */
+ uint32_t uvd_enc_health;
+ uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 64, 0, (12 + sizeof(struct amdgim_vf2pf_info_header)/sizeof(uint32_t)), 0)];
+} __aligned(4);
+
+#define AMDGPU_FW_VRAM_VF2PF_VER 2
+typedef struct amdgim_vf2pf_info_v2 amdgim_vf2pf_info ;
+
+#define AMDGPU_FW_VRAM_VF2PF_WRITE(adev, field, val) \
+ do { \
+ ((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field = (val); \
+ } while (0)
+
+#define AMDGPU_FW_VRAM_VF2PF_READ(adev, field, val) \
+ do { \
+ (*val) = ((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field; \
+ } while (0)
+
+#define AMDGPU_FW_VRAM_PF2VF_READ(adev, field, val) \
+ do { \
+ if (!adev->virt.fw_reserve.p_pf2vf) \
+ *(val) = 0; \
+ else { \
+ if (adev->virt.fw_reserve.p_pf2vf->version == 1) \
+ *(val) = ((struct amdgim_pf2vf_info_v1 *)adev->virt.fw_reserve.p_pf2vf)->field; \
+ if (adev->virt.fw_reserve.p_pf2vf->version == 2) \
+ *(val) = ((struct amdgim_pf2vf_info_v2 *)adev->virt.fw_reserve.p_pf2vf)->field; \
+ } \
+ } while (0)
+
/* GPU virtualization */
struct amdgpu_virt {
uint32_t caps;
@@ -59,6 +244,8 @@ struct amdgpu_virt {
struct work_struct flr_work;
struct amdgpu_mm_table mm_table;
const struct amdgpu_virt_ops *ops;
+ struct amdgpu_vf_error_buffer vf_errors;
+ struct amdgpu_virt_fw_reserve fw_reserve;
};
#define AMDGPU_CSA_SIZE (8 * 1024)
@@ -101,5 +288,9 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job);
int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
+int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
+ unsigned int key,
+ unsigned int chksum);
+void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index bbcc67038203..c8c26f21993c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -328,9 +328,10 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
AMDGPU_GEM_CREATE_SHADOW);
if (vm->pte_support_ats) {
- init_value = AMDGPU_PTE_SYSTEM;
+ init_value = AMDGPU_PTE_DEFAULT_ATC;
if (level != adev->vm_manager.num_level - 1)
init_value |= AMDGPU_PDE_PTE;
+
}
/* walk over the address space and allocate the page tables */
@@ -1034,7 +1035,7 @@ static int amdgpu_vm_wait_pd(struct amdgpu_device *adev, struct amdgpu_vm *vm,
int r;
amdgpu_sync_create(&sync);
- amdgpu_sync_resv(adev, &sync, vm->root.base.bo->tbo.resv, owner);
+ amdgpu_sync_resv(adev, &sync, vm->root.base.bo->tbo.resv, owner, false);
r = amdgpu_sync_wait(&sync, true);
amdgpu_sync_free(&sync);
@@ -1175,11 +1176,11 @@ static int amdgpu_vm_update_level(struct amdgpu_device *adev,
amdgpu_ring_pad_ib(ring, params.ib);
amdgpu_sync_resv(adev, &job->sync,
parent->base.bo->tbo.resv,
- AMDGPU_FENCE_OWNER_VM);
+ AMDGPU_FENCE_OWNER_VM, false);
if (shadow)
amdgpu_sync_resv(adev, &job->sync,
shadow->tbo.resv,
- AMDGPU_FENCE_OWNER_VM);
+ AMDGPU_FENCE_OWNER_VM, false);
WARN_ON(params.ib->length_dw > ndw);
r = amdgpu_job_submit(job, ring, &vm->entity,
@@ -1243,7 +1244,7 @@ static void amdgpu_vm_invalidate_level(struct amdgpu_vm *vm,
int amdgpu_vm_update_directories(struct amdgpu_device *adev,
struct amdgpu_vm *vm)
{
- int r;
+ int r = 0;
spin_lock(&vm->status_lock);
while (!list_empty(&vm->relocated)) {
@@ -1643,7 +1644,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
goto error_free;
r = amdgpu_sync_resv(adev, &job->sync, vm->root.base.bo->tbo.resv,
- owner);
+ owner, false);
if (r)
goto error_free;
@@ -1698,6 +1699,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
struct drm_mm_node *nodes,
struct dma_fence **fence)
{
+ unsigned min_linear_pages = 1 << adev->vm_manager.fragment_size;
uint64_t pfn, start = mapping->start;
int r;
@@ -1732,6 +1734,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
}
do {
+ dma_addr_t *dma_addr = NULL;
uint64_t max_entries;
uint64_t addr, last;
@@ -1745,15 +1748,32 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
}
if (pages_addr) {
+ uint64_t count;
+
max_entries = min(max_entries, 16ull * 1024ull);
- addr = 0;
+ for (count = 1; count < max_entries; ++count) {
+ uint64_t idx = pfn + count;
+
+ if (pages_addr[idx] !=
+ (pages_addr[idx - 1] + PAGE_SIZE))
+ break;
+ }
+
+ if (count < min_linear_pages) {
+ addr = pfn << PAGE_SHIFT;
+ dma_addr = pages_addr;
+ } else {
+ addr = pages_addr[pfn];
+ max_entries = count;
+ }
+
} else if (flags & AMDGPU_PTE_VALID) {
addr += adev->vm_manager.vram_base_offset;
+ addr += pfn << PAGE_SHIFT;
}
- addr += pfn << PAGE_SHIFT;
last = min((uint64_t)mapping->last, start + max_entries - 1);
- r = amdgpu_vm_bo_update_mapping(adev, exclusive, pages_addr, vm,
+ r = amdgpu_vm_bo_update_mapping(adev, exclusive, dma_addr, vm,
start, last, flags, addr,
fence);
if (r)
@@ -2017,7 +2037,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
list_del(&mapping->list);
if (vm->pte_support_ats)
- init_pte_value = AMDGPU_PTE_SYSTEM;
+ init_pte_value = AMDGPU_PTE_DEFAULT_ATC;
r = amdgpu_vm_bo_update_mapping(adev, NULL, NULL, vm,
mapping->start, mapping->last,
@@ -2541,7 +2561,8 @@ static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
* @adev: amdgpu_device pointer
* @fragment_size_default: the default fragment size if it's set auto
*/
-void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev, uint32_t fragment_size_default)
+void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev,
+ uint32_t fragment_size_default)
{
if (amdgpu_vm_fragment_size == -1)
adev->vm_manager.fragment_size = fragment_size_default;
@@ -2555,7 +2576,8 @@ void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev, uint32_t fragment_s
* @adev: amdgpu_device pointer
* @vm_size: the default vm size if it's set auto
*/
-void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size, uint32_t fragment_size_default)
+void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,
+ uint32_t fragment_size_default)
{
/* adjust vm size firstly */
if (amdgpu_vm_size == -1)
@@ -2627,7 +2649,9 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
if (adev->asic_type == CHIP_RAVEN) {
vm->pte_support_ats = true;
- init_pde_value = AMDGPU_PTE_SYSTEM | AMDGPU_PDE_PTE;
+ init_pde_value = AMDGPU_PTE_DEFAULT_ATC
+ | AMDGPU_PDE_PTE;
+
}
} else
vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
@@ -2682,6 +2706,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
}
INIT_KFIFO(vm->faults);
+ vm->fault_credit = 16;
return 0;
@@ -2734,8 +2759,9 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
struct amdgpu_bo_va_mapping *mapping, *tmp;
bool prt_fini_needed = !!adev->gart.gart_funcs->set_prt;
+ struct amdgpu_bo *root;
u64 fault;
- int i;
+ int i, r;
/* Clear pending page faults from IH when the VM is destroyed */
while (kfifo_get(&vm->faults, &fault))
@@ -2770,13 +2796,51 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
}
- amdgpu_vm_free_levels(&vm->root);
+ root = amdgpu_bo_ref(vm->root.base.bo);
+ r = amdgpu_bo_reserve(root, true);
+ if (r) {
+ dev_err(adev->dev, "Leaking page tables because BO reservation failed\n");
+ } else {
+ amdgpu_vm_free_levels(&vm->root);
+ amdgpu_bo_unreserve(root);
+ }
+ amdgpu_bo_unref(&root);
dma_fence_put(vm->last_update);
for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
amdgpu_vm_free_reserved_vmid(adev, vm, i);
}
/**
+ * amdgpu_vm_pasid_fault_credit - Check fault credit for given PASID
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: PASID do identify the VM
+ *
+ * This function is expected to be called in interrupt context. Returns
+ * true if there was fault credit, false otherwise
+ */
+bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
+ unsigned int pasid)
+{
+ struct amdgpu_vm *vm;
+
+ spin_lock(&adev->vm_manager.pasid_lock);
+ vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+ spin_unlock(&adev->vm_manager.pasid_lock);
+ if (!vm)
+ /* VM not found, can't track fault credit */
+ return true;
+
+ /* No lock needed. only accessed by IRQ handler */
+ if (!vm->fault_credit)
+ /* Too many faults in this VM */
+ return false;
+
+ vm->fault_credit--;
+ return true;
+}
+
+/**
* amdgpu_vm_manager_init - init the VM manager
*
* @adev: amdgpu_device pointer
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 0af090667dfc..aa914256b4bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -73,6 +73,16 @@ struct amdgpu_bo_list_entry;
#define AMDGPU_PTE_MTYPE(a) ((uint64_t)a << 57)
#define AMDGPU_PTE_MTYPE_MASK AMDGPU_PTE_MTYPE(3ULL)
+/* For Raven */
+#define AMDGPU_MTYPE_CC 2
+
+#define AMDGPU_PTE_DEFAULT_ATC (AMDGPU_PTE_SYSTEM \
+ | AMDGPU_PTE_SNOOPED \
+ | AMDGPU_PTE_EXECUTABLE \
+ | AMDGPU_PTE_READABLE \
+ | AMDGPU_PTE_WRITEABLE \
+ | AMDGPU_PTE_MTYPE(AMDGPU_MTYPE_CC))
+
/* How to programm VM fault handling */
#define AMDGPU_VM_FAULT_STOP_NEVER 0
#define AMDGPU_VM_FAULT_STOP_FIRST 1
@@ -165,8 +175,11 @@ struct amdgpu_vm {
/* Flag to indicate ATS support from PTE for GFX9 */
bool pte_support_ats;
- /* Up to 128 pending page faults */
+ /* Up to 128 pending retry page faults */
DECLARE_KFIFO(faults, u64, 128);
+
+ /* Limit non-retry fault storms */
+ unsigned int fault_credit;
};
struct amdgpu_vm_id {
@@ -244,6 +257,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
int vm_context, unsigned int pasid);
void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
+ unsigned int pasid);
void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
struct list_head *validated,
struct amdgpu_bo_list_entry *entry);
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 68ce1bdaf2fc..68b505c768ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6365,7 +6365,6 @@ static int ci_dpm_sw_fini(void *handle)
flush_work(&adev->pm.dpm.thermal.work);
mutex_lock(&adev->pm.mutex);
- amdgpu_pm_sysfs_fini(adev);
ci_dpm_fini(adev);
mutex_unlock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 07d3d895da10..a870b354e3f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -237,8 +237,23 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev)
*/
static bool cik_ih_prescreen_iv(struct amdgpu_device *adev)
{
- /* Process all interrupts */
- return true;
+ u32 ring_index = adev->irq.ih.rptr >> 2;
+ u16 pasid;
+
+ switch (le32_to_cpu(adev->irq.ih.ring[ring_index]) & 0xff) {
+ case 146:
+ case 147:
+ pasid = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]) >> 16;
+ if (!pasid || amdgpu_vm_pasid_fault_credit(adev, pasid))
+ return true;
+ break;
+ default:
+ /* Not a VM fault */
+ return true;
+ }
+
+ adev->irq.ih.rptr += 16;
+ return false;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index b6cdf4afaf46..fa61d649bb44 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,8 +216,23 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev)
*/
static bool cz_ih_prescreen_iv(struct amdgpu_device *adev)
{
- /* Process all interrupts */
- return true;
+ u32 ring_index = adev->irq.ih.rptr >> 2;
+ u16 pasid;
+
+ switch (le32_to_cpu(adev->irq.ih.ring[ring_index]) & 0xff) {
+ case 146:
+ case 147:
+ pasid = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]) >> 16;
+ if (!pasid || amdgpu_vm_pasid_fault_credit(adev, pasid))
+ return true;
+ break;
+ default:
+ /* Not a VM fault */
+ return true;
+ }
+
+ adev->irq.ih.rptr += 16;
+ return false;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index b9ee9073cb0d..a8829af120c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -288,7 +288,7 @@ dce_virtual_encoder(struct drm_connector *connector)
if (connector->encoder_ids[i] == 0)
break;
- encoder = drm_encoder_find(connector->dev, connector->encoder_ids[i]);
+ encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
if (!encoder)
continue;
@@ -298,7 +298,7 @@ dce_virtual_encoder(struct drm_connector *connector)
/* pick the first one */
if (enc_id)
- return drm_encoder_find(connector->dev, enc_id);
+ return drm_encoder_find(connector->dev, NULL, enc_id);
return NULL;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index dfc10b1baea0..b8002ac3e536 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -20,6 +20,7 @@
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
+#include <linux/kernel.h>
#include <linux/firmware.h>
#include <drm/drmP.h>
#include "amdgpu.h"
@@ -3952,10 +3953,10 @@ static int gfx_v8_0_init_save_restore_list(struct amdgpu_device *adev)
adev->gfx.rlc.reg_list_format_size_bytes >> 2,
unique_indices,
&indices_count,
- sizeof(unique_indices) / sizeof(int),
+ ARRAY_SIZE(unique_indices),
indirect_start_offsets,
&offset_count,
- sizeof(indirect_start_offsets)/sizeof(int));
+ ARRAY_SIZE(indirect_start_offsets));
/* save and restore list */
WREG32_FIELD(RLC_SRM_CNTL, AUTO_INCR_ADDR, 1);
@@ -3977,14 +3978,14 @@ static int gfx_v8_0_init_save_restore_list(struct amdgpu_device *adev)
/* starting offsets starts */
WREG32(mmRLC_GPM_SCRATCH_ADDR,
adev->gfx.rlc.starting_offsets_start);
- for (i = 0; i < sizeof(indirect_start_offsets)/sizeof(int); i++)
+ for (i = 0; i < ARRAY_SIZE(indirect_start_offsets); i++)
WREG32(mmRLC_GPM_SCRATCH_DATA,
indirect_start_offsets[i]);
/* unique indices */
temp = mmRLC_SRM_INDEX_CNTL_ADDR_0;
data = mmRLC_SRM_INDEX_CNTL_DATA_0;
- for (i = 0; i < sizeof(unique_indices) / sizeof(int); i++) {
+ for (i = 0; i < ARRAY_SIZE(unique_indices); i++) {
if (unique_indices[i] != 0) {
WREG32(temp + i, unique_indices[i] & 0x3FFFF);
WREG32(data + i, unique_indices[i] >> 20);
@@ -4132,18 +4133,12 @@ static int gfx_v8_0_rlc_resume(struct amdgpu_device *adev)
gfx_v8_0_rlc_reset(adev);
gfx_v8_0_init_pg(adev);
- if (!adev->pp_enabled) {
- if (adev->firmware.load_type != AMDGPU_FW_LOAD_SMU) {
- /* legacy rlc firmware loading */
- r = gfx_v8_0_rlc_load_microcode(adev);
- if (r)
- return r;
- } else {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_RLC_G);
- if (r)
- return -EINVAL;
- }
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
+ /* legacy rlc firmware loading */
+ r = gfx_v8_0_rlc_load_microcode(adev);
+ if (r)
+ return r;
}
gfx_v8_0_rlc_start(adev);
@@ -4959,43 +4954,15 @@ static int gfx_v8_0_cp_resume(struct amdgpu_device *adev)
if (!(adev->flags & AMD_IS_APU))
gfx_v8_0_enable_gui_idle_interrupt(adev, false);
- if (!adev->pp_enabled) {
- if (adev->firmware.load_type != AMDGPU_FW_LOAD_SMU) {
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
/* legacy firmware loading */
- r = gfx_v8_0_cp_gfx_load_microcode(adev);
- if (r)
- return r;
+ r = gfx_v8_0_cp_gfx_load_microcode(adev);
+ if (r)
+ return r;
- r = gfx_v8_0_cp_compute_load_microcode(adev);
- if (r)
- return r;
- } else {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_CP_CE);
- if (r)
- return -EINVAL;
-
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_CP_PFP);
- if (r)
- return -EINVAL;
-
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_CP_ME);
- if (r)
- return -EINVAL;
-
- if (adev->asic_type == CHIP_TOPAZ) {
- r = gfx_v8_0_cp_compute_load_microcode(adev);
- if (r)
- return r;
- } else {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_CP_MEC1);
- if (r)
- return -EINVAL;
- }
- }
+ r = gfx_v8_0_cp_compute_load_microcode(adev);
+ if (r)
+ return r;
}
r = gfx_v8_0_cp_gfx_resume(adev);
@@ -6018,7 +5985,6 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
{
uint32_t msg_id, pp_state = 0;
uint32_t pp_support_state = 0;
- void *pp_handle = adev->powerplay.pp_handle;
if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)) {
if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) {
@@ -6036,7 +6002,8 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_CG,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
@@ -6057,7 +6024,8 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_MG,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
return 0;
@@ -6069,7 +6037,6 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
uint32_t msg_id, pp_state = 0;
uint32_t pp_support_state = 0;
- void *pp_handle = adev->powerplay.pp_handle;
if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)) {
if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) {
@@ -6087,7 +6054,8 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_CG,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS)) {
@@ -6106,7 +6074,8 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_3D,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
@@ -6127,7 +6096,8 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_MG,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & AMD_CG_SUPPORT_GFX_RLC_LS) {
@@ -6142,7 +6112,8 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_RLC,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
@@ -6156,7 +6127,8 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
PP_BLOCK_GFX_CP,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
return 0;
@@ -6423,6 +6395,104 @@ static void gfx_v8_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
}
+static void gfx_v8_0_ring_set_pipe_percent(struct amdgpu_ring *ring,
+ bool acquire)
+{
+ struct amdgpu_device *adev = ring->adev;
+ int pipe_num, tmp, reg;
+ int pipe_percent = acquire ? SPI_WCL_PIPE_PERCENT_GFX__VALUE_MASK : 0x1;
+
+ pipe_num = ring->me * adev->gfx.mec.num_pipe_per_mec + ring->pipe;
+
+ /* first me only has 2 entries, GFX and HP3D */
+ if (ring->me > 0)
+ pipe_num -= 2;
+
+ reg = mmSPI_WCL_PIPE_PERCENT_GFX + pipe_num;
+ tmp = RREG32(reg);
+ tmp = REG_SET_FIELD(tmp, SPI_WCL_PIPE_PERCENT_GFX, VALUE, pipe_percent);
+ WREG32(reg, tmp);
+}
+
+static void gfx_v8_0_pipe_reserve_resources(struct amdgpu_device *adev,
+ struct amdgpu_ring *ring,
+ bool acquire)
+{
+ int i, pipe;
+ bool reserve;
+ struct amdgpu_ring *iring;
+
+ mutex_lock(&adev->gfx.pipe_reserve_mutex);
+ pipe = amdgpu_gfx_queue_to_bit(adev, ring->me, ring->pipe, 0);
+ if (acquire)
+ set_bit(pipe, adev->gfx.pipe_reserve_bitmap);
+ else
+ clear_bit(pipe, adev->gfx.pipe_reserve_bitmap);
+
+ if (!bitmap_weight(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES)) {
+ /* Clear all reservations - everyone reacquires all resources */
+ for (i = 0; i < adev->gfx.num_gfx_rings; ++i)
+ gfx_v8_0_ring_set_pipe_percent(&adev->gfx.gfx_ring[i],
+ true);
+
+ for (i = 0; i < adev->gfx.num_compute_rings; ++i)
+ gfx_v8_0_ring_set_pipe_percent(&adev->gfx.compute_ring[i],
+ true);
+ } else {
+ /* Lower all pipes without a current reservation */
+ for (i = 0; i < adev->gfx.num_gfx_rings; ++i) {
+ iring = &adev->gfx.gfx_ring[i];
+ pipe = amdgpu_gfx_queue_to_bit(adev,
+ iring->me,
+ iring->pipe,
+ 0);
+ reserve = test_bit(pipe, adev->gfx.pipe_reserve_bitmap);
+ gfx_v8_0_ring_set_pipe_percent(iring, reserve);
+ }
+
+ for (i = 0; i < adev->gfx.num_compute_rings; ++i) {
+ iring = &adev->gfx.compute_ring[i];
+ pipe = amdgpu_gfx_queue_to_bit(adev,
+ iring->me,
+ iring->pipe,
+ 0);
+ reserve = test_bit(pipe, adev->gfx.pipe_reserve_bitmap);
+ gfx_v8_0_ring_set_pipe_percent(iring, reserve);
+ }
+ }
+
+ mutex_unlock(&adev->gfx.pipe_reserve_mutex);
+}
+
+static void gfx_v8_0_hqd_set_priority(struct amdgpu_device *adev,
+ struct amdgpu_ring *ring,
+ bool acquire)
+{
+ uint32_t pipe_priority = acquire ? 0x2 : 0x0;
+ uint32_t queue_priority = acquire ? 0xf : 0x0;
+
+ mutex_lock(&adev->srbm_mutex);
+ vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
+
+ WREG32(mmCP_HQD_PIPE_PRIORITY, pipe_priority);
+ WREG32(mmCP_HQD_QUEUE_PRIORITY, queue_priority);
+
+ vi_srbm_select(adev, 0, 0, 0, 0);
+ mutex_unlock(&adev->srbm_mutex);
+}
+static void gfx_v8_0_ring_set_priority_compute(struct amdgpu_ring *ring,
+ enum amd_sched_priority priority)
+{
+ struct amdgpu_device *adev = ring->adev;
+ bool acquire = priority == AMD_SCHED_PRIORITY_HIGH_HW;
+
+ if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
+ return;
+
+ gfx_v8_0_hqd_set_priority(adev, ring, acquire);
+ gfx_v8_0_pipe_reserve_resources(adev, ring, acquire);
+}
+
static void gfx_v8_0_ring_emit_fence_compute(struct amdgpu_ring *ring,
u64 addr, u64 seq,
unsigned flags)
@@ -6868,6 +6938,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
.test_ib = gfx_v8_0_ring_test_ib,
.insert_nop = amdgpu_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
+ .set_priority = gfx_v8_0_ring_set_priority_compute,
};
static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_kiq = {
@@ -7076,7 +7147,7 @@ static void gfx_v8_0_ring_emit_ce_meta(struct amdgpu_ring *ring)
{
uint64_t ce_payload_addr;
int cnt_ce;
- static union {
+ union {
struct vi_ce_ib_state regular;
struct vi_ce_ib_state_chained_ib chained;
} ce_payload = {};
@@ -7105,7 +7176,7 @@ static void gfx_v8_0_ring_emit_de_meta(struct amdgpu_ring *ring)
{
uint64_t de_payload_addr, gds_addr, csa_addr;
int cnt_de;
- static union {
+ union {
struct vi_de_ib_state regular;
struct vi_de_ib_state_chained_ib chained;
} de_payload = {};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index deeaee1457ef..7f15bb2c5233 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -20,6 +20,7 @@
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
+#include <linux/kernel.h>
#include <linux/firmware.h>
#include <drm/drmP.h>
#include "amdgpu.h"
@@ -1730,10 +1731,10 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
adev->gfx.rlc.reg_list_format_size_bytes >> 2,
unique_indirect_regs,
&unique_indirect_reg_count,
- sizeof(unique_indirect_regs)/sizeof(int),
+ ARRAY_SIZE(unique_indirect_regs),
indirect_start_offsets,
&indirect_start_offsets_count,
- sizeof(indirect_start_offsets)/sizeof(int));
+ ARRAY_SIZE(indirect_start_offsets));
/* enable auto inc in case it is disabled */
tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL));
@@ -1770,12 +1771,12 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
/* write the starting offsets to RLC scratch ram */
WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_SCRATCH_ADDR),
adev->gfx.rlc.starting_offsets_start);
- for (i = 0; i < sizeof(indirect_start_offsets)/sizeof(int); i++)
+ for (i = 0; i < ARRAY_SIZE(indirect_start_offsets); i++)
WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_SCRATCH_DATA),
indirect_start_offsets[i]);
/* load unique indirect regs*/
- for (i = 0; i < sizeof(unique_indirect_regs)/sizeof(int); i++) {
+ for (i = 0; i < ARRAY_SIZE(unique_indirect_regs); i++) {
WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_ADDR_0) + i,
unique_indirect_regs[i] & 0x3FFFF);
WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_DATA_0) + i,
@@ -3583,7 +3584,7 @@ static void gfx_v9_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
static void gfx_v9_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
{
u32 ref_and_mask, reg_mem_engine;
- struct nbio_hdp_flush_reg *nbio_hf_reg;
+ const struct nbio_hdp_flush_reg *nbio_hf_reg;
if (ring->adev->flags & AMD_IS_APU)
nbio_hf_reg = &nbio_v7_0_hdp_flush_reg;
@@ -3806,7 +3807,7 @@ static void gfx_v9_ring_emit_sb(struct amdgpu_ring *ring)
static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring)
{
- static struct v9_ce_ib_state ce_payload = {0};
+ struct v9_ce_ib_state ce_payload = {0};
uint64_t csa_addr;
int cnt;
@@ -3825,7 +3826,7 @@ static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring)
static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring)
{
- static struct v9_de_ib_state de_payload = {0};
+ struct v9_de_ib_state de_payload = {0};
uint64_t csa_addr, gds_addr;
int cnt;
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index 65ed6d3a8f05..bd592cb39f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -216,8 +216,23 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev)
*/
static bool iceland_ih_prescreen_iv(struct amdgpu_device *adev)
{
- /* Process all interrupts */
- return true;
+ u32 ring_index = adev->irq.ih.rptr >> 2;
+ u16 pasid;
+
+ switch (le32_to_cpu(adev->irq.ih.ring[ring_index]) & 0xff) {
+ case 146:
+ case 147:
+ pasid = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]) >> 16;
+ if (!pasid || amdgpu_vm_pasid_fault_credit(adev, pasid))
+ return true;
+ break;
+ default:
+ /* Not a VM fault */
+ return true;
+ }
+
+ adev->irq.ih.rptr += 16;
+ return false;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index b57399a462c2..f33d1ffdb20b 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2969,16 +2969,10 @@ static int kv_dpm_late_init(void *handle)
{
/* powerdown unused blocks for now */
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int ret;
if (!amdgpu_dpm)
return 0;
- /* init the sysfs and debugfs files late */
- ret = amdgpu_pm_sysfs_init(adev);
- if (ret)
- return ret;
-
kv_dpm_powergate_acp(adev, true);
kv_dpm_powergate_samu(adev, true);
@@ -3040,7 +3034,6 @@ static int kv_dpm_sw_fini(void *handle)
flush_work(&adev->pm.dpm.thermal.work);
mutex_lock(&adev->pm.mutex);
- amdgpu_pm_sysfs_fini(adev);
kv_dpm_fini(adev);
mutex_unlock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 2812d88a8bdd..b4906d2f30d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -183,6 +183,12 @@ static int xgpu_ai_send_access_requests(struct amdgpu_device *adev,
pr_err("Doesn't get READY_TO_ACCESS_GPU from pf, give up\n");
return r;
}
+ /* Retrieve checksum from mailbox2 */
+ if (req == IDH_REQ_GPU_INIT_ACCESS) {
+ adev->virt.fw_reserve.checksum_key =
+ RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0,
+ mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW2));
+ }
}
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 045988b18bc3..904a1bab9b9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -215,31 +215,27 @@ void nbio_v6_1_get_clockgating_state(struct amdgpu_device *adev, u32 *flags)
*flags |= AMD_CG_SUPPORT_BIF_LS;
}
-struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg;
-struct nbio_pcie_index_data nbio_v6_1_pcie_index_data;
+const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
+ .hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_REQ),
+ .hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_DONE),
+ .ref_and_mask_cp0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP0_MASK,
+ .ref_and_mask_cp1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP1_MASK,
+ .ref_and_mask_cp2 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP2_MASK,
+ .ref_and_mask_cp3 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP3_MASK,
+ .ref_and_mask_cp4 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP4_MASK,
+ .ref_and_mask_cp5 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP5_MASK,
+ .ref_and_mask_cp6 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP6_MASK,
+ .ref_and_mask_cp7 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP7_MASK,
+ .ref_and_mask_cp8 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP8_MASK,
+ .ref_and_mask_cp9 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP9_MASK,
+ .ref_and_mask_sdma0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__SDMA0_MASK,
+ .ref_and_mask_sdma1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__SDMA1_MASK
+};
-int nbio_v6_1_init(struct amdgpu_device *adev)
-{
- nbio_v6_1_hdp_flush_reg.hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_REQ);
- nbio_v6_1_hdp_flush_reg.hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_DONE);
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP0_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP1_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp2 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP2_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp3 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP3_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp4 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP4_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp5 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP5_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp6 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP6_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp7 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP7_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp8 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP8_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_cp9 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP9_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_sdma0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__SDMA0_MASK;
- nbio_v6_1_hdp_flush_reg.ref_and_mask_sdma1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__SDMA1_MASK;
-
- nbio_v6_1_pcie_index_data.index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX);
- nbio_v6_1_pcie_index_data.data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA);
-
- return 0;
-}
+const struct nbio_pcie_index_data nbio_v6_1_pcie_index_data = {
+ .index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX),
+ .data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA),
+};
void nbio_v6_1_detect_hw_virt(struct amdgpu_device *adev)
{
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
index 686e4b4d296a..14ca8d45a46c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
@@ -26,8 +26,8 @@
#include "soc15_common.h"
-extern struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg;
-extern struct nbio_pcie_index_data nbio_v6_1_pcie_index_data;
+extern const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg;
+extern const struct nbio_pcie_index_data nbio_v6_1_pcie_index_data;
int nbio_v6_1_init(struct amdgpu_device *adev);
u32 nbio_v6_1_get_atombios_scratch_regs(struct amdgpu_device *adev,
uint32_t idx);
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index 11b70d601922..f802b973410a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -185,28 +185,24 @@ void nbio_v7_0_ih_control(struct amdgpu_device *adev)
WREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL, interrupt_cntl);
}
-struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg;
-struct nbio_pcie_index_data nbio_v7_0_pcie_index_data;
+const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
+ .hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_REQ),
+ .hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_DONE),
+ .ref_and_mask_cp0 = GPU_HDP_FLUSH_DONE__CP0_MASK,
+ .ref_and_mask_cp1 = GPU_HDP_FLUSH_DONE__CP1_MASK,
+ .ref_and_mask_cp2 = GPU_HDP_FLUSH_DONE__CP2_MASK,
+ .ref_and_mask_cp3 = GPU_HDP_FLUSH_DONE__CP3_MASK,
+ .ref_and_mask_cp4 = GPU_HDP_FLUSH_DONE__CP4_MASK,
+ .ref_and_mask_cp5 = GPU_HDP_FLUSH_DONE__CP5_MASK,
+ .ref_and_mask_cp6 = GPU_HDP_FLUSH_DONE__CP6_MASK,
+ .ref_and_mask_cp7 = GPU_HDP_FLUSH_DONE__CP7_MASK,
+ .ref_and_mask_cp8 = GPU_HDP_FLUSH_DONE__CP8_MASK,
+ .ref_and_mask_cp9 = GPU_HDP_FLUSH_DONE__CP9_MASK,
+ .ref_and_mask_sdma0 = GPU_HDP_FLUSH_DONE__SDMA0_MASK,
+ .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK,
+};
-int nbio_v7_0_init(struct amdgpu_device *adev)
-{
- nbio_v7_0_hdp_flush_reg.hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_REQ);
- nbio_v7_0_hdp_flush_reg.hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_DONE);
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp0 = GPU_HDP_FLUSH_DONE__CP0_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp1 = GPU_HDP_FLUSH_DONE__CP1_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp2 = GPU_HDP_FLUSH_DONE__CP2_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp3 = GPU_HDP_FLUSH_DONE__CP3_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp4 = GPU_HDP_FLUSH_DONE__CP4_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp5 = GPU_HDP_FLUSH_DONE__CP5_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp6 = GPU_HDP_FLUSH_DONE__CP6_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp7 = GPU_HDP_FLUSH_DONE__CP7_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp8 = GPU_HDP_FLUSH_DONE__CP8_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_cp9 = GPU_HDP_FLUSH_DONE__CP9_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_sdma0 = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
- nbio_v7_0_hdp_flush_reg.ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
-
- nbio_v7_0_pcie_index_data.index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX2);
- nbio_v7_0_pcie_index_data.data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2);
-
- return 0;
-}
+const struct nbio_pcie_index_data nbio_v7_0_pcie_index_data = {
+ .index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX2),
+ .data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2)
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
index 054ff49427e6..df8fa90f40d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
@@ -26,8 +26,8 @@
#include "soc15_common.h"
-extern struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg;
-extern struct nbio_pcie_index_data nbio_v7_0_pcie_index_data;
+extern const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg;
+extern const struct nbio_pcie_index_data nbio_v7_0_pcie_index_data;
int nbio_v7_0_init(struct amdgpu_device *adev);
u32 nbio_v7_0_get_atombios_scratch_regs(struct amdgpu_device *adev,
uint32_t idx);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index dea7c909ca5f..4e20d91d5d50 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -257,6 +257,9 @@ int psp_v10_0_cmd_submit(struct psp_context *psp,
unsigned int psp_write_ptr_reg = 0;
struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
struct psp_ring *ring = &psp->km_ring;
+ struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
+ struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
+ ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
struct amdgpu_device *adev = psp->adev;
uint32_t ring_size_dw = ring->ring_size / 4;
uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
@@ -266,9 +269,16 @@ int psp_v10_0_cmd_submit(struct psp_context *psp,
/* Update KM RB frame pointer to new frame */
if ((psp_write_ptr_reg % ring_size_dw) == 0)
- write_frame = ring->ring_mem;
+ write_frame = ring_buffer_start;
else
- write_frame = ring->ring_mem + (psp_write_ptr_reg / rb_frame_size_dw);
+ write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
+ /* Check invalid write_frame ptr address */
+ if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
+ DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
+ ring_buffer_start, ring_buffer_end, write_frame);
+ DRM_ERROR("write_frame is pointing to address out of bounds\n");
+ return -EINVAL;
+ }
/* Initialize KM RB frame */
memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index cee5c396b277..c7bcfe8e286c 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -367,6 +367,9 @@ int psp_v3_1_cmd_submit(struct psp_context *psp,
unsigned int psp_write_ptr_reg = 0;
struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
struct psp_ring *ring = &psp->km_ring;
+ struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
+ struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
+ ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
struct amdgpu_device *adev = psp->adev;
uint32_t ring_size_dw = ring->ring_size / 4;
uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
@@ -378,9 +381,16 @@ int psp_v3_1_cmd_submit(struct psp_context *psp,
/* write_frame ptr increments by size of rb_frame in bytes */
/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
if ((psp_write_ptr_reg % ring_size_dw) == 0)
- write_frame = ring->ring_mem;
+ write_frame = ring_buffer_start;
else
- write_frame = ring->ring_mem + (psp_write_ptr_reg / rb_frame_size_dw);
+ write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
+ /* Check invalid write_frame ptr address */
+ if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
+ DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
+ ring_buffer_start, ring_buffer_end, write_frame);
+ DRM_ERROR("write_frame is pointing to address out of bounds\n");
+ return -EINVAL;
+ }
/* Initialize KM RB frame */
memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index acdee3a4602c..67f375bfe452 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -561,21 +561,11 @@ static int sdma_v2_4_start(struct amdgpu_device *adev)
{
int r;
- if (!adev->pp_enabled) {
- if (adev->firmware.load_type != AMDGPU_FW_LOAD_SMU) {
- r = sdma_v2_4_load_microcode(adev);
- if (r)
- return r;
- } else {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_SDMA0);
- if (r)
- return -EINVAL;
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_SDMA1);
- if (r)
- return -EINVAL;
- }
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
+ r = sdma_v2_4_load_microcode(adev);
+ if (r)
+ return r;
}
/* halt the engine before programing */
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 72f31cc7df00..6d06f8eb659f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -819,23 +819,12 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev)
*/
static int sdma_v3_0_start(struct amdgpu_device *adev)
{
- int r, i;
+ int r;
- if (!adev->pp_enabled) {
- if (adev->firmware.load_type != AMDGPU_FW_LOAD_SMU) {
- r = sdma_v3_0_load_microcode(adev);
- if (r)
- return r;
- } else {
- for (i = 0; i < adev->sdma.num_instances; i++) {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- (i == 0) ?
- AMDGPU_UCODE_ID_SDMA0 :
- AMDGPU_UCODE_ID_SDMA1);
- if (r)
- return -EINVAL;
- }
- }
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
+ r = sdma_v3_0_load_microcode(adev);
+ if (r)
+ return r;
}
/* disable sdma engine before programing it */
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index c26d205ff3bf..46009db3d195 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -371,7 +371,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
{
u32 ref_and_mask = 0;
- struct nbio_hdp_flush_reg *nbio_hf_reg;
+ const struct nbio_hdp_flush_reg *nbio_hf_reg;
if (ring->adev->flags & AMD_IS_APU)
nbio_hf_reg = &nbio_v7_0_hdp_flush_reg;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 9b8db6046271..51fd0c9a20a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -7604,11 +7604,6 @@ static int si_dpm_late_init(void *handle)
if (!amdgpu_dpm)
return 0;
- /* init the sysfs and debugfs files late */
- ret = amdgpu_pm_sysfs_init(adev);
- if (ret)
- return ret;
-
ret = si_set_temperature_range(adev);
if (ret)
return ret;
@@ -7764,7 +7759,6 @@ static int si_dpm_sw_fini(void *handle)
flush_work(&adev->pm.dpm.thermal.work);
mutex_lock(&adev->pm.mutex);
- amdgpu_pm_sysfs_fini(adev);
si_dpm_fini(adev);
mutex_unlock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 245a18aeb389..3ca9d114f630 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -101,7 +101,7 @@ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
{
unsigned long flags, address, data;
u32 r;
- struct nbio_pcie_index_data *nbio_pcie_id;
+ const struct nbio_pcie_index_data *nbio_pcie_id;
if (adev->flags & AMD_IS_APU)
nbio_pcie_id = &nbio_v7_0_pcie_index_data;
@@ -122,7 +122,7 @@ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
static void soc15_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
{
unsigned long flags, address, data;
- struct nbio_pcie_index_data *nbio_pcie_id;
+ const struct nbio_pcie_index_data *nbio_pcie_id;
if (adev->flags & AMD_IS_APU)
nbio_pcie_id = &nbio_v7_0_pcie_index_data;
@@ -279,10 +279,7 @@ static void soc15_init_golden_registers(struct amdgpu_device *adev)
}
static u32 soc15_get_xclk(struct amdgpu_device *adev)
{
- if (adev->asic_type == CHIP_VEGA10)
- return adev->clock.spll.reference_freq/4;
- else
- return adev->clock.spll.reference_freq;
+ return adev->clock.spll.reference_freq;
}
@@ -604,21 +601,6 @@ static int soc15_common_early_init(void *handle)
(amdgpu_ip_block_mask & (1 << AMD_IP_BLOCK_TYPE_PSP)))
psp_enabled = true;
- /*
- * nbio need be used for both sdma and gfx9, but only
- * initializes once
- */
- switch(adev->asic_type) {
- case CHIP_VEGA10:
- nbio_v6_1_init(adev);
- break;
- case CHIP_RAVEN:
- nbio_v7_0_init(adev);
- break;
- default:
- return -EINVAL;
- }
-
adev->rev_id = soc15_get_rev_id(adev);
adev->external_rev_id = 0xFF;
switch (adev->asic_type) {
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 5ed00692618e..aa4e320e31f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -227,8 +227,23 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev)
*/
static bool tonga_ih_prescreen_iv(struct amdgpu_device *adev)
{
- /* Process all interrupts */
- return true;
+ u32 ring_index = adev->irq.ih.rptr >> 2;
+ u16 pasid;
+
+ switch (le32_to_cpu(adev->irq.ih.ring[ring_index]) & 0xff) {
+ case 146:
+ case 147:
+ pasid = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]) >> 16;
+ if (!pasid || amdgpu_vm_pasid_fault_credit(adev, pasid))
+ return true;
+ break;
+ default:
+ /* Not a VM fault */
+ return true;
+ }
+
+ adev->irq.ih.rptr += 16;
+ return false;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 31db356476f8..2581543b35a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -38,6 +38,8 @@
#include "vi.h"
static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev);
+static void uvd_v6_0_set_enc_ring_funcs(struct amdgpu_device *adev);
+
static void uvd_v6_0_set_irq_funcs(struct amdgpu_device *adev);
static int uvd_v6_0_start(struct amdgpu_device *adev);
static void uvd_v6_0_stop(struct amdgpu_device *adev);
@@ -48,6 +50,18 @@ static void uvd_v6_0_enable_mgcg(struct amdgpu_device *adev,
bool enable);
/**
+* uvd_v6_0_enc_support - get encode support status
+*
+* @adev: amdgpu_device pointer
+*
+* Returns the current hardware encode support status
+*/
+static inline bool uvd_v6_0_enc_support(struct amdgpu_device *adev)
+{
+ return ((adev->asic_type >= CHIP_POLARIS10) && (adev->asic_type <= CHIP_POLARIS12));
+}
+
+/**
* uvd_v6_0_ring_get_rptr - get read pointer
*
* @ring: amdgpu_ring pointer
@@ -62,6 +76,22 @@ static uint64_t uvd_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
}
/**
+ * uvd_v6_0_enc_ring_get_rptr - get enc read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware enc read pointer
+ */
+static uint64_t uvd_v6_0_enc_ring_get_rptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (ring == &adev->uvd.ring_enc[0])
+ return RREG32(mmUVD_RB_RPTR);
+ else
+ return RREG32(mmUVD_RB_RPTR2);
+}
+/**
* uvd_v6_0_ring_get_wptr - get write pointer
*
* @ring: amdgpu_ring pointer
@@ -76,6 +106,23 @@ static uint64_t uvd_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
}
/**
+ * uvd_v6_0_enc_ring_get_wptr - get enc write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware enc write pointer
+ */
+static uint64_t uvd_v6_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (ring == &adev->uvd.ring_enc[0])
+ return RREG32(mmUVD_RB_WPTR);
+ else
+ return RREG32(mmUVD_RB_WPTR2);
+}
+
+/**
* uvd_v6_0_ring_set_wptr - set write pointer
*
* @ring: amdgpu_ring pointer
@@ -89,11 +136,248 @@ static void uvd_v6_0_ring_set_wptr(struct amdgpu_ring *ring)
WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
}
+/**
+ * uvd_v6_0_enc_ring_set_wptr - set enc write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the enc write pointer to the hardware
+ */
+static void uvd_v6_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (ring == &adev->uvd.ring_enc[0])
+ WREG32(mmUVD_RB_WPTR,
+ lower_32_bits(ring->wptr));
+ else
+ WREG32(mmUVD_RB_WPTR2,
+ lower_32_bits(ring->wptr));
+}
+
+/**
+ * uvd_v6_0_enc_ring_test_ring - test if UVD ENC ring is working
+ *
+ * @ring: the engine to test on
+ *
+ */
+static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+ uint32_t rptr = amdgpu_ring_get_rptr(ring);
+ unsigned i;
+ int r;
+
+ r = amdgpu_ring_alloc(ring, 16);
+ if (r) {
+ DRM_ERROR("amdgpu: uvd enc failed to lock ring %d (%d).\n",
+ ring->idx, r);
+ return r;
+ }
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_END);
+ amdgpu_ring_commit(ring);
+
+ for (i = 0; i < adev->usec_timeout; i++) {
+ if (amdgpu_ring_get_rptr(ring) != rptr)
+ break;
+ DRM_UDELAY(1);
+ }
+
+ if (i < adev->usec_timeout) {
+ DRM_INFO("ring test on %d succeeded in %d usecs\n",
+ ring->idx, i);
+ } else {
+ DRM_ERROR("amdgpu: ring %d test failed\n",
+ ring->idx);
+ r = -ETIMEDOUT;
+ }
+
+ return r;
+}
+
+/**
+ * uvd_v6_0_enc_get_create_msg - generate a UVD ENC create msg
+ *
+ * @adev: amdgpu_device pointer
+ * @ring: ring we should submit the msg to
+ * @handle: session handle to use
+ * @fence: optional fence to return
+ *
+ * Open up a stream for HW test
+ */
+static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct dma_fence **fence)
+{
+ const unsigned ib_size_dw = 16;
+ struct amdgpu_job *job;
+ struct amdgpu_ib *ib;
+ struct dma_fence *f = NULL;
+ uint64_t dummy;
+ int i, r;
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+ if (r)
+ return r;
+
+ ib = &job->ibs[0];
+ dummy = ib->gpu_addr + 1024;
+
+ ib->length_dw = 0;
+ ib->ptr[ib->length_dw++] = 0x00000018;
+ ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
+ ib->ptr[ib->length_dw++] = handle;
+ ib->ptr[ib->length_dw++] = 0x00010000;
+ ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
+ ib->ptr[ib->length_dw++] = dummy;
+
+ ib->ptr[ib->length_dw++] = 0x00000014;
+ ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
+ ib->ptr[ib->length_dw++] = 0x0000001c;
+ ib->ptr[ib->length_dw++] = 0x00000001;
+ ib->ptr[ib->length_dw++] = 0x00000000;
+
+ ib->ptr[ib->length_dw++] = 0x00000008;
+ ib->ptr[ib->length_dw++] = 0x08000001; /* op initialize */
+
+ for (i = ib->length_dw; i < ib_size_dw; ++i)
+ ib->ptr[i] = 0x0;
+
+ r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+ job->fence = dma_fence_get(f);
+ if (r)
+ goto err;
+
+ amdgpu_job_free(job);
+ if (fence)
+ *fence = dma_fence_get(f);
+ dma_fence_put(f);
+ return 0;
+
+err:
+ amdgpu_job_free(job);
+ return r;
+}
+
+/**
+ * uvd_v6_0_enc_get_destroy_msg - generate a UVD ENC destroy msg
+ *
+ * @adev: amdgpu_device pointer
+ * @ring: ring we should submit the msg to
+ * @handle: session handle to use
+ * @fence: optional fence to return
+ *
+ * Close up a stream for HW test or if userspace failed to do so
+ */
+static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
+ uint32_t handle,
+ bool direct, struct dma_fence **fence)
+{
+ const unsigned ib_size_dw = 16;
+ struct amdgpu_job *job;
+ struct amdgpu_ib *ib;
+ struct dma_fence *f = NULL;
+ uint64_t dummy;
+ int i, r;
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+ if (r)
+ return r;
+
+ ib = &job->ibs[0];
+ dummy = ib->gpu_addr + 1024;
+
+ ib->length_dw = 0;
+ ib->ptr[ib->length_dw++] = 0x00000018;
+ ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
+ ib->ptr[ib->length_dw++] = handle;
+ ib->ptr[ib->length_dw++] = 0x00010000;
+ ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
+ ib->ptr[ib->length_dw++] = dummy;
+
+ ib->ptr[ib->length_dw++] = 0x00000014;
+ ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
+ ib->ptr[ib->length_dw++] = 0x0000001c;
+ ib->ptr[ib->length_dw++] = 0x00000001;
+ ib->ptr[ib->length_dw++] = 0x00000000;
+
+ ib->ptr[ib->length_dw++] = 0x00000008;
+ ib->ptr[ib->length_dw++] = 0x08000002; /* op close session */
+
+ for (i = ib->length_dw; i < ib_size_dw; ++i)
+ ib->ptr[i] = 0x0;
+
+ if (direct) {
+ r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+ job->fence = dma_fence_get(f);
+ if (r)
+ goto err;
+
+ amdgpu_job_free(job);
+ } else {
+ r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+ AMDGPU_FENCE_OWNER_UNDEFINED, &f);
+ if (r)
+ goto err;
+ }
+
+ if (fence)
+ *fence = dma_fence_get(f);
+ dma_fence_put(f);
+ return 0;
+
+err:
+ amdgpu_job_free(job);
+ return r;
+}
+
+/**
+ * uvd_v6_0_enc_ring_test_ib - test if UVD ENC IBs are working
+ *
+ * @ring: the engine to test on
+ *
+ */
+static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+ struct dma_fence *fence = NULL;
+ long r;
+
+ r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL);
+ if (r) {
+ DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r);
+ goto error;
+ }
+
+ r = uvd_v6_0_enc_get_destroy_msg(ring, 1, true, &fence);
+ if (r) {
+ DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
+ goto error;
+ }
+
+ r = dma_fence_wait_timeout(fence, false, timeout);
+ if (r == 0) {
+ DRM_ERROR("amdgpu: IB test timed out.\n");
+ r = -ETIMEDOUT;
+ } else if (r < 0) {
+ DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+ } else {
+ DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+ r = 0;
+ }
+error:
+ dma_fence_put(fence);
+ return r;
+}
static int uvd_v6_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
uvd_v6_0_set_ring_funcs(adev);
+
+ if (uvd_v6_0_enc_support(adev)) {
+ adev->uvd.num_enc_rings = 2;
+ uvd_v6_0_set_enc_ring_funcs(adev);
+ }
+
uvd_v6_0_set_irq_funcs(adev);
return 0;
@@ -102,7 +386,7 @@ static int uvd_v6_0_early_init(void *handle)
static int uvd_v6_0_sw_init(void *handle)
{
struct amdgpu_ring *ring;
- int r;
+ int i, r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* UVD TRAP */
@@ -110,10 +394,31 @@ static int uvd_v6_0_sw_init(void *handle)
if (r)
return r;
+ /* UVD ENC TRAP */
+ if (uvd_v6_0_enc_support(adev)) {
+ for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+ r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.irq);
+ if (r)
+ return r;
+ }
+ }
+
r = amdgpu_uvd_sw_init(adev);
if (r)
return r;
+ if (uvd_v6_0_enc_support(adev)) {
+ struct amd_sched_rq *rq;
+ ring = &adev->uvd.ring_enc[0];
+ rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
+ r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
+ rq, amdgpu_sched_jobs);
+ if (r) {
+ DRM_ERROR("Failed setting up UVD ENC run queue.\n");
+ return r;
+ }
+ }
+
r = amdgpu_uvd_resume(adev);
if (r)
return r;
@@ -121,19 +426,38 @@ static int uvd_v6_0_sw_init(void *handle)
ring = &adev->uvd.ring;
sprintf(ring->name, "uvd");
r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+ if (r)
+ return r;
+
+ if (uvd_v6_0_enc_support(adev)) {
+ for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+ ring = &adev->uvd.ring_enc[i];
+ sprintf(ring->name, "uvd_enc%d", i);
+ r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+ if (r)
+ return r;
+ }
+ }
return r;
}
static int uvd_v6_0_sw_fini(void *handle)
{
- int r;
+ int i, r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
r = amdgpu_uvd_suspend(adev);
if (r)
return r;
+ if (uvd_v6_0_enc_support(adev)) {
+ amd_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
+
+ for (i = 0; i < adev->uvd.num_enc_rings; ++i)
+ amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
+ }
+
return amdgpu_uvd_sw_fini(adev);
}
@@ -149,7 +473,7 @@ static int uvd_v6_0_hw_init(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
struct amdgpu_ring *ring = &adev->uvd.ring;
uint32_t tmp;
- int r;
+ int i, r;
amdgpu_asic_set_uvd_clocks(adev, 10000, 10000);
uvd_v6_0_set_clockgating_state(adev, AMD_CG_STATE_UNGATE);
@@ -189,9 +513,25 @@ static int uvd_v6_0_hw_init(void *handle)
amdgpu_ring_commit(ring);
+ if (uvd_v6_0_enc_support(adev)) {
+ for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+ ring = &adev->uvd.ring_enc[i];
+ ring->ready = true;
+ r = amdgpu_ring_test_ring(ring);
+ if (r) {
+ ring->ready = false;
+ goto done;
+ }
+ }
+ }
+
done:
- if (!r)
- DRM_INFO("UVD initialized successfully.\n");
+ if (!r) {
+ if (uvd_v6_0_enc_support(adev))
+ DRM_INFO("UVD and UVD ENC initialized successfully.\n");
+ else
+ DRM_INFO("UVD initialized successfully.\n");
+ }
return r;
}
@@ -225,11 +565,7 @@ static int uvd_v6_0_suspend(void *handle)
if (r)
return r;
- /* Skip this for APU for now */
- if (!(adev->flags & AMD_IS_APU))
- r = amdgpu_uvd_suspend(adev);
-
- return r;
+ return amdgpu_uvd_suspend(adev);
}
static int uvd_v6_0_resume(void *handle)
@@ -237,12 +573,10 @@ static int uvd_v6_0_resume(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- /* Skip this for APU for now */
- if (!(adev->flags & AMD_IS_APU)) {
- r = amdgpu_uvd_resume(adev);
- if (r)
- return r;
- }
+ r = amdgpu_uvd_resume(adev);
+ if (r)
+ return r;
+
return uvd_v6_0_hw_init(adev);
}
@@ -514,6 +848,22 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
WREG32_FIELD(UVD_RBC_RB_CNTL, RB_NO_FETCH, 0);
+ if (uvd_v6_0_enc_support(adev)) {
+ ring = &adev->uvd.ring_enc[0];
+ WREG32(mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32(mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+ WREG32(mmUVD_RB_BASE_LO, ring->gpu_addr);
+ WREG32(mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+ WREG32(mmUVD_RB_SIZE, ring->ring_size / 4);
+
+ ring = &adev->uvd.ring_enc[1];
+ WREG32(mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmUVD_RB_BASE_LO2, ring->gpu_addr);
+ WREG32(mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+ WREG32(mmUVD_RB_SIZE2, ring->ring_size / 4);
+ }
+
return 0;
}
@@ -577,6 +927,26 @@ static void uvd_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
}
/**
+ * uvd_v6_0_enc_ring_emit_fence - emit an enc fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write enc a fence and a trap command to the ring.
+ */
+static void uvd_v6_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
+ u64 seq, unsigned flags)
+{
+ WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_FENCE);
+ amdgpu_ring_write(ring, addr);
+ amdgpu_ring_write(ring, upper_32_bits(addr));
+ amdgpu_ring_write(ring, seq);
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_TRAP);
+}
+
+/**
* uvd_v6_0_ring_emit_hdp_flush - emit an hdp flush
*
* @ring: amdgpu_ring pointer
@@ -667,6 +1037,24 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
amdgpu_ring_write(ring, ib->length_dw);
}
+/**
+ * uvd_v6_0_enc_ring_emit_ib - enc execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write enc ring commands to execute the indirect buffer
+ */
+static void uvd_v6_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
+ struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+{
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_IB_VM);
+ amdgpu_ring_write(ring, vm_id);
+ amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+ amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+ amdgpu_ring_write(ring, ib->length_dw);
+}
+
static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
unsigned vm_id, uint64_t pd_addr)
{
@@ -718,6 +1106,33 @@ static void uvd_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, 0xE);
}
+static void uvd_v6_0_enc_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
+{
+ uint32_t seq = ring->fence_drv.sync_seq;
+ uint64_t addr = ring->fence_drv.gpu_addr;
+
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_WAIT_GE);
+ amdgpu_ring_write(ring, lower_32_bits(addr));
+ amdgpu_ring_write(ring, upper_32_bits(addr));
+ amdgpu_ring_write(ring, seq);
+}
+
+static void uvd_v6_0_enc_ring_insert_end(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_END);
+}
+
+static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+ unsigned int vm_id, uint64_t pd_addr)
+{
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_UPDATE_PTB);
+ amdgpu_ring_write(ring, vm_id);
+ amdgpu_ring_write(ring, pd_addr >> 12);
+
+ amdgpu_ring_write(ring, HEVC_ENC_CMD_FLUSH_TLB);
+ amdgpu_ring_write(ring, vm_id);
+}
+
static bool uvd_v6_0_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -825,8 +1240,31 @@ static int uvd_v6_0_process_interrupt(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
+ bool int_handled = true;
DRM_DEBUG("IH: UVD TRAP\n");
- amdgpu_fence_process(&adev->uvd.ring);
+
+ switch (entry->src_id) {
+ case 124:
+ amdgpu_fence_process(&adev->uvd.ring);
+ break;
+ case 119:
+ if (likely(uvd_v6_0_enc_support(adev)))
+ amdgpu_fence_process(&adev->uvd.ring_enc[0]);
+ else
+ int_handled = false;
+ break;
+ case 120:
+ if (likely(uvd_v6_0_enc_support(adev)))
+ amdgpu_fence_process(&adev->uvd.ring_enc[1]);
+ else
+ int_handled = false;
+ break;
+ }
+
+ if (false == int_handled)
+ DRM_ERROR("Unhandled interrupt: %d %d\n",
+ entry->src_id, entry->src_data[0]);
+
return 0;
}
@@ -1153,6 +1591,33 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
.end_use = amdgpu_uvd_ring_end_use,
};
+static const struct amdgpu_ring_funcs uvd_v6_0_enc_ring_vm_funcs = {
+ .type = AMDGPU_RING_TYPE_UVD_ENC,
+ .align_mask = 0x3f,
+ .nop = HEVC_ENC_CMD_NO_OP,
+ .support_64bit_ptrs = false,
+ .get_rptr = uvd_v6_0_enc_ring_get_rptr,
+ .get_wptr = uvd_v6_0_enc_ring_get_wptr,
+ .set_wptr = uvd_v6_0_enc_ring_set_wptr,
+ .emit_frame_size =
+ 4 + /* uvd_v6_0_enc_ring_emit_pipeline_sync */
+ 6 + /* uvd_v6_0_enc_ring_emit_vm_flush */
+ 5 + 5 + /* uvd_v6_0_enc_ring_emit_fence x2 vm fence */
+ 1, /* uvd_v6_0_enc_ring_insert_end */
+ .emit_ib_size = 5, /* uvd_v6_0_enc_ring_emit_ib */
+ .emit_ib = uvd_v6_0_enc_ring_emit_ib,
+ .emit_fence = uvd_v6_0_enc_ring_emit_fence,
+ .emit_vm_flush = uvd_v6_0_enc_ring_emit_vm_flush,
+ .emit_pipeline_sync = uvd_v6_0_enc_ring_emit_pipeline_sync,
+ .test_ring = uvd_v6_0_enc_ring_test_ring,
+ .test_ib = uvd_v6_0_enc_ring_test_ib,
+ .insert_nop = amdgpu_ring_insert_nop,
+ .insert_end = uvd_v6_0_enc_ring_insert_end,
+ .pad_ib = amdgpu_ring_generic_pad_ib,
+ .begin_use = amdgpu_uvd_ring_begin_use,
+ .end_use = amdgpu_uvd_ring_end_use,
+};
+
static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev)
{
if (adev->asic_type >= CHIP_POLARIS10) {
@@ -1164,6 +1629,16 @@ static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev)
}
}
+static void uvd_v6_0_set_enc_ring_funcs(struct amdgpu_device *adev)
+{
+ int i;
+
+ for (i = 0; i < adev->uvd.num_enc_rings; ++i)
+ adev->uvd.ring_enc[i].funcs = &uvd_v6_0_enc_ring_vm_funcs;
+
+ DRM_INFO("UVD ENC is enabled in VM mode\n");
+}
+
static const struct amdgpu_irq_src_funcs uvd_v6_0_irq_funcs = {
.set = uvd_v6_0_set_interrupt_state,
.process = uvd_v6_0_process_interrupt,
@@ -1171,7 +1646,11 @@ static const struct amdgpu_irq_src_funcs uvd_v6_0_irq_funcs = {
static void uvd_v6_0_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->uvd.irq.num_types = 1;
+ if (uvd_v6_0_enc_support(adev))
+ adev->uvd.irq.num_types = adev->uvd.num_enc_rings + 1;
+ else
+ adev->uvd.irq.num_types = 1;
+
adev->uvd.irq.funcs = &uvd_v6_0_irq_funcs;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index b8ed8faf2003..6634545060fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -592,11 +592,7 @@ static int uvd_v7_0_suspend(void *handle)
if (r)
return r;
- /* Skip this for APU for now */
- if (!(adev->flags & AMD_IS_APU))
- r = amdgpu_uvd_suspend(adev);
-
- return r;
+ return amdgpu_uvd_suspend(adev);
}
static int uvd_v7_0_resume(void *handle)
@@ -604,12 +600,10 @@ static int uvd_v7_0_resume(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- /* Skip this for APU for now */
- if (!(adev->flags & AMD_IS_APU)) {
- r = amdgpu_uvd_resume(adev);
- if (r)
- return r;
- }
+ r = amdgpu_uvd_resume(adev);
+ if (r)
+ return r;
+
return uvd_v7_0_hw_init(adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index a3b30d84dbb3..697325737ba8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -260,15 +260,18 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev)
return true;
}
- /* Not a retry fault */
- if (!(dw5 & 0x80))
- return true;
-
pasid = dw3 & 0xffff;
/* No PASID, can't identify faulting process */
if (!pasid)
return true;
+ /* Not a retry fault, check fault credit */
+ if (!(dw5 & 0x80)) {
+ if (!amdgpu_vm_pasid_fault_credit(adev, pasid))
+ goto ignore_iv;
+ return true;
+ }
+
addr = ((u64)(dw5 & 0xf) << 44) | ((u64)dw4 << 12);
key = AMDGPU_VM_FAULT(pasid, addr);
r = amdgpu_ih_add_fault(adev, key);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 9ff69b90df36..f3cfef48aa99 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1254,7 +1254,6 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
uint32_t msg_id, pp_state = 0;
uint32_t pp_support_state = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- void *pp_handle = adev->powerplay.pp_handle;
if (adev->cg_flags & (AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_MC_MGCG)) {
if (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) {
@@ -1271,7 +1270,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_MC,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
@@ -1289,7 +1289,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_SDMA,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
@@ -1307,7 +1308,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_HDP,
pp_support_state,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
@@ -1321,7 +1323,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_BIF,
PP_STATE_SUPPORT_LS,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG) {
if (state == AMD_CG_STATE_UNGATE)
@@ -1333,7 +1336,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_BIF,
PP_STATE_SUPPORT_CG,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & AMD_CG_SUPPORT_DRM_LS) {
@@ -1347,7 +1351,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_DRM,
PP_STATE_SUPPORT_LS,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
if (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG) {
@@ -1361,7 +1366,8 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
PP_BLOCK_SYS_ROM,
PP_STATE_SUPPORT_CG,
pp_state);
- amd_set_clockgating_by_smu(pp_handle, msg_id);
+ if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
+ amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
}
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vid.h b/drivers/gpu/drm/amd/amdgpu/vid.h
index a6485254a169..dbf3703cbd1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vid.h
+++ b/drivers/gpu/drm/amd/amdgpu/vid.h
@@ -465,6 +465,16 @@
#define VCE_CMD_UPDATE_PTB 0x00000107
#define VCE_CMD_FLUSH_TLB 0x00000108
+/* HEVC ENC */
+#define HEVC_ENC_CMD_NO_OP 0x00000000
+#define HEVC_ENC_CMD_END 0x00000001
+#define HEVC_ENC_CMD_FENCE 0x00000003
+#define HEVC_ENC_CMD_TRAP 0x00000004
+#define HEVC_ENC_CMD_IB_VM 0x00000102
+#define HEVC_ENC_CMD_WAIT_GE 0x00000106
+#define HEVC_ENC_CMD_UPDATE_PTB 0x00000107
+#define HEVC_ENC_CMD_FLUSH_TLB 0x00000108
+
/* mmPA_SC_RASTER_CONFIG mask */
#define RB_MAP_PKR0(x) ((x) << 0)
#define RB_MAP_PKR0_MASK (0x3 << 0)
diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index e13c67c8d2c0..bc5a2945bd2b 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -4,6 +4,6 @@
config HSA_AMD
tristate "HSA kernel driver for AMD GPU devices"
- depends on (DRM_RADEON || DRM_AMDGPU) && AMD_IOMMU_V2 && X86_64
+ depends on DRM_AMDGPU && AMD_IOMMU_V2 && X86_64
help
Enable this if you want to use HSA features on AMD GPU devices.
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 211fc48697fa..3d5ccb3755d4 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -36,6 +36,7 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
/* Do not process in ISR, just request it to be forwarded to WQ. */
return (pasid != 0) &&
(ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
+ ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE);
}
@@ -46,6 +47,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
unsigned int pasid;
const struct cik_ih_ring_entry *ihre =
(const struct cik_ih_ring_entry *)ih_ring_entry;
+ uint32_t context_id = ihre->data & 0xfffffff;
pasid = (ihre->ring_id & 0xffff0000) >> 16;
@@ -53,9 +55,11 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
return;
if (ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE)
- kfd_signal_event_interrupt(pasid, 0, 0);
+ kfd_signal_event_interrupt(pasid, context_id, 28);
+ else if (ihre->source_id == CIK_INTSRC_SDMA_TRAP)
+ kfd_signal_event_interrupt(pasid, context_id, 28);
else if (ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG)
- kfd_signal_event_interrupt(pasid, ihre->data & 0xFF, 8);
+ kfd_signal_event_interrupt(pasid, context_id & 0xff, 8);
else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE)
kfd_signal_hw_exception_event(pasid);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h
index 79a16d24c1b8..109298b9d507 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h
@@ -32,9 +32,10 @@ struct cik_ih_ring_entry {
uint32_t reserved;
};
-#define CIK_INTSRC_DEQUEUE_COMPLETE 0xC6
#define CIK_INTSRC_CP_END_OF_PIPE 0xB5
#define CIK_INTSRC_CP_BAD_OPCODE 0xB7
+#define CIK_INTSRC_DEQUEUE_COMPLETE 0xC6
+#define CIK_INTSRC_SDMA_TRAP 0xE0
#define CIK_INTSRC_SQ_INTERRUPT_MSG 0xEF
#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 660b3fbade41..505d39156acd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -282,8 +282,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
p->pasid,
dev->id);
- err = pqm_create_queue(&p->pqm, dev, filep, &q_properties,
- 0, q_properties.type, &queue_id);
+ err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id);
if (err != 0)
goto err_create_queue;
@@ -451,8 +450,8 @@ static int kfd_ioctl_dbg_register(struct file *filep,
return -EINVAL;
}
- mutex_lock(kfd_get_dbgmgr_mutex());
mutex_lock(&p->mutex);
+ mutex_lock(kfd_get_dbgmgr_mutex());
/*
* make sure that we have pdd, if this the first queue created for
@@ -480,8 +479,8 @@ static int kfd_ioctl_dbg_register(struct file *filep,
}
out:
- mutex_unlock(&p->mutex);
mutex_unlock(kfd_get_dbgmgr_mutex());
+ mutex_unlock(&p->mutex);
return status;
}
@@ -836,15 +835,12 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
void *data)
{
struct kfd_ioctl_wait_events_args *args = data;
- enum kfd_event_wait_result wait_result;
int err;
err = kfd_wait_on_events(p, args->num_events,
(void __user *)args->events_ptr,
(args->wait_for_all != 0),
- args->timeout, &wait_result);
-
- args->wait_result = wait_result;
+ args->timeout, &args->wait_result);
return err;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 0aa021aa0aa1..c407f6bd9956 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -184,9 +184,10 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
struct kernel_queue *kq = NULL;
int status;
+ properties.type = KFD_QUEUE_TYPE_DIQ;
+
status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
- &properties, 0, KFD_QUEUE_TYPE_DIQ,
- &qid);
+ &properties, &qid);
if (status) {
pr_err("Failed to create DIQ\n");
@@ -769,13 +770,8 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
union GRBM_GFX_INDEX_BITS reg_gfx_index;
struct kfd_process_device *pdd;
struct dbg_wave_control_info wac_info;
- int temp;
- int first_vmid_to_scan = 8;
- int last_vmid_to_scan = 15;
-
- first_vmid_to_scan = ffs(dev->shared_resources.compute_vmid_bitmap) - 1;
- temp = dev->shared_resources.compute_vmid_bitmap >> first_vmid_to_scan;
- last_vmid_to_scan = first_vmid_to_scan + ffz(temp);
+ int first_vmid_to_scan = dev->vm_info.first_vmid_kfd;
+ int last_vmid_to_scan = dev->vm_info.last_vmid_kfd;
reg_sq_cmd.u32All = 0;
status = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 5df12b287201..621a3b53a038 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -92,6 +92,8 @@ static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
unsigned int chunk_size);
static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
+static int kfd_resume(struct kfd_dev *kfd);
+
static const struct kfd_device_info *lookup_device_info(unsigned short did)
{
size_t i;
@@ -169,15 +171,8 @@ static bool device_iommu_pasid_init(struct kfd_dev *kfd)
(unsigned int)(1 << kfd->device_info->max_pasid_bits),
iommu_info.max_pasids);
- err = amd_iommu_init_device(kfd->pdev, pasid_limit);
- if (err < 0) {
- dev_err(kfd_device, "error initializing iommu device\n");
- return false;
- }
-
if (!kfd_set_pasid_limit(pasid_limit)) {
dev_err(kfd_device, "error setting pasid limit\n");
- amd_iommu_free_device(kfd->pdev);
return false;
}
@@ -189,7 +184,7 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
if (dev)
- kfd_unbind_process_from_device(dev, pasid);
+ kfd_process_iommu_unbind_callback(dev, pasid);
}
/*
@@ -224,6 +219,11 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
kfd->shared_resources = *gpu_resources;
+ kfd->vm_info.first_vmid_kfd = ffs(gpu_resources->compute_vmid_bitmap)-1;
+ kfd->vm_info.last_vmid_kfd = fls(gpu_resources->compute_vmid_bitmap)-1;
+ kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
+ - kfd->vm_info.first_vmid_kfd + 1;
+
/* calculate max size of mqds needed for queues */
size = max_num_of_queues_per_device *
kfd->device_info->mqd_size_aligned;
@@ -273,29 +273,22 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
goto kfd_interrupt_error;
}
- if (!device_iommu_pasid_init(kfd)) {
- dev_err(kfd_device,
- "Error initializing iommuv2 for device %x:%x\n",
- kfd->pdev->vendor, kfd->pdev->device);
- goto device_iommu_pasid_error;
- }
- amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
- iommu_pasid_shutdown_callback);
- amd_iommu_set_invalid_ppr_cb(kfd->pdev, iommu_invalid_ppr_cb);
-
kfd->dqm = device_queue_manager_init(kfd);
if (!kfd->dqm) {
dev_err(kfd_device, "Error initializing queue manager\n");
goto device_queue_manager_error;
}
- if (kfd->dqm->ops.start(kfd->dqm)) {
+ if (!device_iommu_pasid_init(kfd)) {
dev_err(kfd_device,
- "Error starting queue manager for device %x:%x\n",
+ "Error initializing iommuv2 for device %x:%x\n",
kfd->pdev->vendor, kfd->pdev->device);
- goto dqm_start_error;
+ goto device_iommu_pasid_error;
}
+ if (kfd_resume(kfd))
+ goto kfd_resume_error;
+
kfd->dbgmgr = NULL;
kfd->init_complete = true;
@@ -307,11 +300,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
goto out;
-dqm_start_error:
+kfd_resume_error:
+device_iommu_pasid_error:
device_queue_manager_uninit(kfd->dqm);
device_queue_manager_error:
- amd_iommu_free_device(kfd->pdev);
-device_iommu_pasid_error:
kfd_interrupt_exit(kfd);
kfd_interrupt_error:
kfd_topology_remove_device(kfd);
@@ -331,8 +323,8 @@ out:
void kgd2kfd_device_exit(struct kfd_dev *kfd)
{
if (kfd->init_complete) {
+ kgd2kfd_suspend(kfd);
device_queue_manager_uninit(kfd->dqm);
- amd_iommu_free_device(kfd->pdev);
kfd_interrupt_exit(kfd);
kfd_topology_remove_device(kfd);
kfd_doorbell_fini(kfd);
@@ -345,35 +337,59 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
void kgd2kfd_suspend(struct kfd_dev *kfd)
{
- if (kfd->init_complete) {
- kfd->dqm->ops.stop(kfd->dqm);
- amd_iommu_set_invalidate_ctx_cb(kfd->pdev, NULL);
- amd_iommu_set_invalid_ppr_cb(kfd->pdev, NULL);
- amd_iommu_free_device(kfd->pdev);
- }
+ if (!kfd->init_complete)
+ return;
+
+ kfd->dqm->ops.stop(kfd->dqm);
+
+ kfd_unbind_processes_from_device(kfd);
+
+ amd_iommu_set_invalidate_ctx_cb(kfd->pdev, NULL);
+ amd_iommu_set_invalid_ppr_cb(kfd->pdev, NULL);
+ amd_iommu_free_device(kfd->pdev);
}
int kgd2kfd_resume(struct kfd_dev *kfd)
{
- unsigned int pasid_limit;
- int err;
+ if (!kfd->init_complete)
+ return 0;
- pasid_limit = kfd_get_pasid_limit();
+ return kfd_resume(kfd);
- if (kfd->init_complete) {
- err = amd_iommu_init_device(kfd->pdev, pasid_limit);
- if (err < 0) {
- dev_err(kfd_device, "failed to initialize iommu\n");
- return -ENXIO;
- }
+}
+
+static int kfd_resume(struct kfd_dev *kfd)
+{
+ int err = 0;
+ unsigned int pasid_limit = kfd_get_pasid_limit();
- amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
- iommu_pasid_shutdown_callback);
- amd_iommu_set_invalid_ppr_cb(kfd->pdev, iommu_invalid_ppr_cb);
- kfd->dqm->ops.start(kfd->dqm);
+ err = amd_iommu_init_device(kfd->pdev, pasid_limit);
+ if (err)
+ return -ENXIO;
+ amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
+ iommu_pasid_shutdown_callback);
+ amd_iommu_set_invalid_ppr_cb(kfd->pdev,
+ iommu_invalid_ppr_cb);
+
+ err = kfd_bind_processes_to_device(kfd);
+ if (err)
+ goto processes_bind_error;
+
+ err = kfd->dqm->ops.start(kfd->dqm);
+ if (err) {
+ dev_err(kfd_device,
+ "Error starting queue manager for device %x:%x\n",
+ kfd->pdev->vendor, kfd->pdev->device);
+ goto dqm_start_error;
}
- return 0;
+ return err;
+
+dqm_start_error:
+processes_bind_error:
+ amd_iommu_free_device(kfd->pdev);
+
+ return err;
}
/* This is called directly from KGD at ISR. */
@@ -387,7 +403,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
if (kfd->interrupts_active
&& interrupt_is_wanted(kfd, ih_ring_entry)
&& enqueue_ih_ring_entry(kfd, ih_ring_entry))
- schedule_work(&kfd->interrupt_work);
+ queue_work(kfd->ih_wq, &kfd->interrupt_work);
spin_unlock(&kfd->interrupt_lock);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 53a66e821624..e202921c150e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -44,9 +44,14 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
struct queue *q,
struct qcm_process_device *qpd);
-static int execute_queues_cpsch(struct device_queue_manager *dqm, bool lock);
-static int destroy_queues_cpsch(struct device_queue_manager *dqm,
- bool preempt_static_queues, bool lock);
+static int execute_queues_cpsch(struct device_queue_manager *dqm,
+ enum kfd_unmap_queues_filter filter,
+ uint32_t filter_param);
+static int unmap_queues_cpsch(struct device_queue_manager *dqm,
+ enum kfd_unmap_queues_filter filter,
+ uint32_t filter_param);
+
+static int map_queues_cpsch(struct device_queue_manager *dqm);
static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
struct queue *q,
@@ -113,11 +118,11 @@ static int allocate_vmid(struct device_queue_manager *dqm,
if (dqm->vmid_bitmap == 0)
return -ENOMEM;
- bit = find_first_bit((unsigned long *)&dqm->vmid_bitmap, CIK_VMID_NUM);
+ bit = find_first_bit((unsigned long *)&dqm->vmid_bitmap,
+ dqm->dev->vm_info.vmid_num_kfd);
clear_bit(bit, (unsigned long *)&dqm->vmid_bitmap);
- /* Kaveri kfd vmid's starts from vmid 8 */
- allocated_vmid = bit + KFD_VMID_START_OFFSET;
+ allocated_vmid = bit + dqm->dev->vm_info.first_vmid_kfd;
pr_debug("vmid allocation %d\n", allocated_vmid);
qpd->vmid = allocated_vmid;
q->properties.vmid = allocated_vmid;
@@ -132,7 +137,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
struct qcm_process_device *qpd,
struct queue *q)
{
- int bit = qpd->vmid - KFD_VMID_START_OFFSET;
+ int bit = qpd->vmid - dqm->dev->vm_info.first_vmid_kfd;
/* Release the vmid mapping */
set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
@@ -184,6 +189,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
}
list_add(&q->list, &qpd->queues_list);
+ qpd->queue_count++;
if (q->properties.is_active)
dqm->queue_count++;
@@ -273,6 +279,9 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
dqm->dev->kfd2kgd->set_scratch_backing_va(
dqm->dev->kgd, qpd->sh_hidden_private_base, qpd->vmid);
+ if (!q->properties.is_active)
+ return 0;
+
retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
q->process->mm);
if (retval)
@@ -288,65 +297,74 @@ out_deallocate_hqd:
return retval;
}
-static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
+/* Access to DQM has to be locked before calling destroy_queue_nocpsch_locked
+ * to avoid asynchronized access
+ */
+static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
struct qcm_process_device *qpd,
struct queue *q)
{
int retval;
struct mqd_manager *mqd;
- retval = 0;
-
- mutex_lock(&dqm->lock);
+ mqd = dqm->ops.get_mqd_manager(dqm,
+ get_mqd_type_from_queue_type(q->properties.type));
+ if (!mqd)
+ return -ENOMEM;
if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) {
- mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
- if (mqd == NULL) {
- retval = -ENOMEM;
- goto out;
- }
deallocate_hqd(dqm, q);
} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
- mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
- if (mqd == NULL) {
- retval = -ENOMEM;
- goto out;
- }
dqm->sdma_queue_count--;
deallocate_sdma_queue(dqm, q->sdma_id);
} else {
pr_debug("q->properties.type %d is invalid\n",
q->properties.type);
- retval = -EINVAL;
- goto out;
+ return -EINVAL;
}
+ dqm->total_queue_count--;
retval = mqd->destroy_mqd(mqd, q->mqd,
KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
- QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
+ KFD_UNMAP_LATENCY_MS,
q->pipe, q->queue);
-
- if (retval)
- goto out;
+ if (retval == -ETIME)
+ qpd->reset_wavefronts = true;
mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
list_del(&q->list);
- if (list_empty(&qpd->queues_list))
+ if (list_empty(&qpd->queues_list)) {
+ if (qpd->reset_wavefronts) {
+ pr_warn("Resetting wave fronts (nocpsch) on dev %p\n",
+ dqm->dev);
+ /* dbgdev_wave_reset_wavefronts has to be called before
+ * deallocate_vmid(), i.e. when vmid is still in use.
+ */
+ dbgdev_wave_reset_wavefronts(dqm->dev,
+ qpd->pqm->process);
+ qpd->reset_wavefronts = false;
+ }
+
deallocate_vmid(dqm, qpd, q);
+ }
+ qpd->queue_count--;
if (q->properties.is_active)
dqm->queue_count--;
- /*
- * Unconditionally decrement this counter, regardless of the queue's
- * type
- */
- dqm->total_queue_count--;
- pr_debug("Total of %d queues are accountable so far\n",
- dqm->total_queue_count);
+ return retval;
+}
-out:
+static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
+ struct qcm_process_device *qpd,
+ struct queue *q)
+{
+ int retval;
+
+ mutex_lock(&dqm->lock);
+ retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
mutex_unlock(&dqm->lock);
+
return retval;
}
@@ -364,29 +382,56 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
goto out_unlock;
}
- if (q->properties.is_active)
- prev_active = true;
+ /* Save previous activity state for counters */
+ prev_active = q->properties.is_active;
+
+ /* Make sure the queue is unmapped before updating the MQD */
+ if (sched_policy != KFD_SCHED_POLICY_NO_HWS) {
+ retval = unmap_queues_cpsch(dqm,
+ KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+ if (retval) {
+ pr_err("unmap queue failed\n");
+ goto out_unlock;
+ }
+ } else if (prev_active &&
+ (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+ q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+ retval = mqd->destroy_mqd(mqd, q->mqd,
+ KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
+ KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
+ if (retval) {
+ pr_err("destroy mqd failed\n");
+ goto out_unlock;
+ }
+ }
+
+ retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
/*
- *
- * check active state vs. the previous state
- * and modify counter accordingly
+ * check active state vs. the previous state and modify
+ * counter accordingly. map_queues_cpsch uses the
+ * dqm->queue_count to determine whether a new runlist must be
+ * uploaded.
*/
- retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
- if ((q->properties.is_active) && (!prev_active))
+ if (q->properties.is_active && !prev_active)
dqm->queue_count++;
else if (!q->properties.is_active && prev_active)
dqm->queue_count--;
if (sched_policy != KFD_SCHED_POLICY_NO_HWS)
- retval = execute_queues_cpsch(dqm, false);
+ retval = map_queues_cpsch(dqm);
+ else if (q->properties.is_active &&
+ (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+ q->properties.type == KFD_QUEUE_TYPE_SDMA))
+ retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue,
+ &q->properties, q->process->mm);
out_unlock:
mutex_unlock(&dqm->lock);
return retval;
}
-static struct mqd_manager *get_mqd_manager_nocpsch(
+static struct mqd_manager *get_mqd_manager(
struct device_queue_manager *dqm, enum KFD_MQD_TYPE type)
{
struct mqd_manager *mqd;
@@ -407,7 +452,7 @@ static struct mqd_manager *get_mqd_manager_nocpsch(
return mqd;
}
-static int register_process_nocpsch(struct device_queue_manager *dqm,
+static int register_process(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
struct device_process_node *n;
@@ -422,7 +467,7 @@ static int register_process_nocpsch(struct device_queue_manager *dqm,
mutex_lock(&dqm->lock);
list_add(&n->list, &dqm->queues);
- retval = dqm->ops_asic_specific.register_process(dqm, qpd);
+ retval = dqm->asic_ops.update_qpd(dqm, qpd);
dqm->processes_count++;
@@ -431,7 +476,7 @@ static int register_process_nocpsch(struct device_queue_manager *dqm,
return retval;
}
-static int unregister_process_nocpsch(struct device_queue_manager *dqm,
+static int unregister_process(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
int retval;
@@ -507,13 +552,13 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
dqm->allocated_queues[pipe] |= 1 << queue;
}
- dqm->vmid_bitmap = (1 << VMID_PER_DEVICE) - 1;
+ dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
return 0;
}
-static void uninitialize_nocpsch(struct device_queue_manager *dqm)
+static void uninitialize(struct device_queue_manager *dqm)
{
int i;
@@ -577,14 +622,14 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
if (retval)
return retval;
- q->properties.sdma_queue_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
- q->properties.sdma_engine_id = q->sdma_id / CIK_SDMA_ENGINE_NUM;
+ q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+ q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
pr_debug("SDMA id is: %d\n", q->sdma_id);
pr_debug("SDMA queue id: %d\n", q->properties.sdma_queue_id);
pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
- dqm->ops_asic_specific.init_sdma_vm(dqm, q, qpd);
+ dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
&q->gart_mqd_addr, &q->properties);
if (retval)
@@ -613,8 +658,7 @@ static int set_sched_resources(struct device_queue_manager *dqm)
int i, mec;
struct scheduling_resources res;
- res.vmid_mask = (1 << VMID_PER_DEVICE) - 1;
- res.vmid_mask <<= KFD_VMID_START_OFFSET;
+ res.vmid_mask = dqm->dev->shared_resources.compute_vmid_bitmap;
res.queue_mask = 0;
for (i = 0; i < KGD_MAX_QUEUES; ++i) {
@@ -652,8 +696,6 @@ static int set_sched_resources(struct device_queue_manager *dqm)
static int initialize_cpsch(struct device_queue_manager *dqm)
{
- int retval;
-
pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
mutex_init(&dqm->lock);
@@ -661,16 +703,13 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
dqm->queue_count = dqm->processes_count = 0;
dqm->sdma_queue_count = 0;
dqm->active_runlist = false;
- retval = dqm->ops_asic_specific.initialize(dqm);
- if (retval)
- mutex_destroy(&dqm->lock);
+ dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
- return retval;
+ return 0;
}
static int start_cpsch(struct device_queue_manager *dqm)
{
- struct device_process_node *node;
int retval;
retval = 0;
@@ -697,12 +736,9 @@ static int start_cpsch(struct device_queue_manager *dqm)
init_interrupts(dqm);
- list_for_each_entry(node, &dqm->queues, list)
- if (node->qpd->pqm->process && dqm->dev)
- kfd_bind_process_to_device(dqm->dev,
- node->qpd->pqm->process);
-
- execute_queues_cpsch(dqm, true);
+ mutex_lock(&dqm->lock);
+ execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+ mutex_unlock(&dqm->lock);
return 0;
fail_allocate_vidmem:
@@ -714,15 +750,10 @@ fail_packet_manager_init:
static int stop_cpsch(struct device_queue_manager *dqm)
{
- struct device_process_node *node;
- struct kfd_process_device *pdd;
-
- destroy_queues_cpsch(dqm, true, true);
+ mutex_lock(&dqm->lock);
+ unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+ mutex_unlock(&dqm->lock);
- list_for_each_entry(node, &dqm->queues, list) {
- pdd = qpd_to_pdd(node->qpd);
- pdd->bound = false;
- }
kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
pm_uninit(&dqm->packets);
@@ -752,7 +783,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
list_add(&kq->list, &qpd->priv_queue_list);
dqm->queue_count++;
qpd->is_debug = true;
- execute_queues_cpsch(dqm, false);
+ execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
mutex_unlock(&dqm->lock);
return 0;
@@ -763,12 +794,10 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
mutex_lock(&dqm->lock);
- /* here we actually preempt the DIQ */
- destroy_queues_cpsch(dqm, true, false);
list_del(&kq->list);
dqm->queue_count--;
qpd->is_debug = false;
- execute_queues_cpsch(dqm, false);
+ execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
/*
* Unconditionally decrement this counter, regardless of the queue's
* type.
@@ -779,14 +808,6 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
mutex_unlock(&dqm->lock);
}
-static void select_sdma_engine_id(struct queue *q)
-{
- static int sdma_id;
-
- q->sdma_id = sdma_id;
- sdma_id = (sdma_id + 1) % 2;
-}
-
static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
struct qcm_process_device *qpd, int *allocate_vmid)
{
@@ -807,9 +828,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
goto out;
}
- if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
- select_sdma_engine_id(q);
-
+ if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+ retval = allocate_sdma_queue(dqm, &q->sdma_id);
+ if (retval)
+ goto out;
+ q->properties.sdma_queue_id =
+ q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+ q->properties.sdma_engine_id =
+ q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+ }
mqd = dqm->ops.get_mqd_manager(dqm,
get_mqd_type_from_queue_type(q->properties.type));
@@ -818,16 +845,18 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
goto out;
}
- dqm->ops_asic_specific.init_sdma_vm(dqm, q, qpd);
+ dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
&q->gart_mqd_addr, &q->properties);
if (retval)
goto out;
list_add(&q->list, &qpd->queues_list);
+ qpd->queue_count++;
if (q->properties.is_active) {
dqm->queue_count++;
- retval = execute_queues_cpsch(dqm, false);
+ retval = execute_queues_cpsch(dqm,
+ KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
}
if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
@@ -848,12 +877,12 @@ out:
int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
unsigned int fence_value,
- unsigned long timeout)
+ unsigned int timeout_ms)
{
- timeout += jiffies;
+ unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;
while (*fence_addr != fence_value) {
- if (time_after(jiffies, timeout)) {
+ if (time_after(jiffies, end_jiffies)) {
pr_err("qcm fence wait loop timeout expired\n");
return -ETIME;
}
@@ -863,44 +892,57 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
return 0;
}
-static int destroy_sdma_queues(struct device_queue_manager *dqm,
+static int unmap_sdma_queues(struct device_queue_manager *dqm,
unsigned int sdma_engine)
{
return pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_SDMA,
- KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES, 0, false,
+ KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, false,
sdma_engine);
}
-static int destroy_queues_cpsch(struct device_queue_manager *dqm,
- bool preempt_static_queues, bool lock)
+/* dqm->lock mutex has to be locked before calling this function */
+static int map_queues_cpsch(struct device_queue_manager *dqm)
{
int retval;
- enum kfd_preempt_type_filter preempt_type;
- struct kfd_process_device *pdd;
- retval = 0;
+ if (dqm->queue_count <= 0 || dqm->processes_count <= 0)
+ return 0;
+
+ if (dqm->active_runlist)
+ return 0;
+
+ retval = pm_send_runlist(&dqm->packets, &dqm->queues);
+ if (retval) {
+ pr_err("failed to execute runlist\n");
+ return retval;
+ }
+ dqm->active_runlist = true;
+
+ return retval;
+}
+
+/* dqm->lock mutex has to be locked before calling this function */
+static int unmap_queues_cpsch(struct device_queue_manager *dqm,
+ enum kfd_unmap_queues_filter filter,
+ uint32_t filter_param)
+{
+ int retval = 0;
- if (lock)
- mutex_lock(&dqm->lock);
if (!dqm->active_runlist)
- goto out;
+ return retval;
pr_debug("Before destroying queues, sdma queue count is : %u\n",
dqm->sdma_queue_count);
if (dqm->sdma_queue_count > 0) {
- destroy_sdma_queues(dqm, 0);
- destroy_sdma_queues(dqm, 1);
+ unmap_sdma_queues(dqm, 0);
+ unmap_sdma_queues(dqm, 1);
}
- preempt_type = preempt_static_queues ?
- KFD_PREEMPT_TYPE_FILTER_ALL_QUEUES :
- KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES;
-
retval = pm_send_unmap_queue(&dqm->pac