summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdkfd
Commit message (Collapse)AuthorAgeFilesLines
...
| * | | drm/amdkfd: Fix gfx10 wave64 VGPR context restoreJay Cornwall2019-07-302-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Copy/paste error, first 4 VGPRs are separated by 64 dwords (256 bytes). Cc: Shaoyun Liu <shaoyun.liu@amd.com> Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: shaoyunl <shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Remove dead code from gfx8/gfx9 trap handlersJay Cornwall2019-07-302-765/+5
| | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Replace gfx10 trap handler with correct branchJay Cornwall2019-07-302-1311/+1220
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously submitted code was taken from an incorrect branch and was non-functional. Cc: Oak Zeng <oak.zeng@amd.com> Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-By: Oak Zeng <oak.zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Fix lost single step exceptions in gfx9 trap handlerJay Cornwall2019-07-302-705/+733
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the trap is entered due to MODE.DEBUG_EN=1 and SAVECTX is raised concurrently the handler cannot identify the source of the exception. This causes the debugger to lose single step exception notification when a context save request arrives at the same time. When MODE.DEBUG_EN=1 and STATUS.HALT=0 (exception not already handled) jump to the second-level trap handler upon entering the trap. The second-level trap will set STATUS.HALT=1 and return to the shader. If SAVECTX was raised then control flow will return to the trap, which will then handle the context save request. Cc: Tony Tye <tony.tye@amd.com> Cc: Laurent Morichetti <laurent.morichetti@amd.com> Cc: Qingchuan Shi <qingchuan.shi@amd.com> Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Reviewed-by: Laurent Morichetti <laurent.morichetti@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Use SQC when TCP would fail in gfx9 context save.Jay Cornwall2019-07-302-126/+320
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When a wavefront raises TRAPSTS.XNACK_ERROR with STATUS.ALLOW_REPLAY=0 subsequent memory instructions have undefined behavior. In practice SQC stores continue to work but TCP stores do not. Context save is permitted to fail after XNACK error because the wavefront will be halted and subsequently terminated. However the debugger has an interest in retrieving the wavefront VGPR/LDS state. Detect the out-of-spec case and use SQC stores during context save in place of TCP stores. Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Increase vcrat size for GPUOak Zeng2019-07-181-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | GPU cache info (part of virtual CRAT) size depends on CU number. For arcturus, CU number has been increased. So the required memory for vcrat also increases. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Merge gfx9/arcturus trap handlers, add ACC VGPR saveJay Cornwall2019-07-183-918/+538
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ACC VGPRs are a secondary VGPR set of same size as the primary VGPRs. Save them as a block immediately following VGPRs. Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Add device id for real asicsOak Zeng2019-07-181-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add pci device ids. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Add arcturus CWSR trap handlerOak Zeng2019-07-183-0/+948
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | CWSR (compute wave save/restore) is used for preempting compute queues. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Set number of xgmi optimized SDMA engines for arcturusOak Zeng2019-07-181-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | some sdma engines are optimized for xgmi on arcturus. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Support MMHUB1 in kfd interrupt pathYong Zhao2019-07-181-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Handle interrupts for second mmhub. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Fix sdma_bitmap overflow issueOak Zeng2019-07-181-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In the original formula, when sdma queue number is 64, the left shift overflows. Use an equivalence that won't overflow. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Change arcturus sdma engines numberOak Zeng2019-07-181-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Arcturus has 8 sdma engines Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Yong Zhao <yong.zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | amd/amdkfd: Add ASIC ARCTURUS to kfdYong Zhao2019-07-187-0/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add initial support for ARCTURUS to kfd. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Support bigger gds sizeOak Zeng2019-07-182-7/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Extend map_process and set_resources pm4 packet to support bigger gds size for arcturus. v2: Only make the change for v9 Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | | drm/amdkfd: Extend PM4 packets to support 8 SDMAOak Zeng2019-07-182-6/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Extend map_queue and unmap_queue PM4 packets to support 8 SDMA engines. The new format is backward compatible. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | | | Revert "drm/amdkfd: New IOCTL to allocate queue GWS"Alex Deucher2019-08-071-28/+0
| |/ / |/| | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 1a058c3376765ee31d65e28cbbb9d4ff15120056. This interface is still in too much flux. Revert until it's sorted out. Acked-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | | drm/amdkfd/kfd_mqd_manager_v10: Avoid fall-through warningGustavo A. R. Silva2019-07-251-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In preparation to enabling -Wimplicit-fallthrough, this patch silences the following warning: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c: In function ‘mqd_manager_init_v10’: ./include/linux/dynamic_debug.h:122:52: warning: this statement may fall through [-Wimplicit-fallthrough=] #define __dynamic_func_call(id, fmt, func, ...) do { \ ^ ./include/linux/dynamic_debug.h:143:2: note: in expansion of macro ‘__dynamic_func_call’ __dynamic_func_call(__UNIQUE_ID(ddebug), fmt, func, ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~ ./include/linux/dynamic_debug.h:153:2: note: in expansion of macro ‘_dynamic_func_call’ _dynamic_func_call(fmt, __dynamic_pr_debug, \ ^~~~~~~~~~~~~~~~~~ ./include/linux/printk.h:336:2: note: in expansion of macro ‘dynamic_pr_debug’ dynamic_pr_debug(fmt, ##__VA_ARGS__) ^~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:432:3: note: in expansion of macro ‘pr_debug’ pr_debug("%s@%i\n", __func__, __LINE__); ^~~~~~~~ drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:433:2: note: here case KFD_MQD_TYPE_COMPUTE: ^~~~ by removing the call to pr_debug() in KFD_MQD_TYPE_CP: "The mqd init for CP and COMPUTE will have the same routine." [1] This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. [1] https://lore.kernel.org/lkml/c735a1cc-a545-50fb-44e7-c0ad93ee8ee7@amd.com/ Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
* | | drm/amdkfd: Fix missing break in switch statementGustavo A. R. Silva2019-07-251-0/+1
| |/ |/| | | | | | | | | | | | | | | | | | | | | | | Add missing break statement in order to prevent the code from falling through to case CHIP_NAVI10. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: 14328aa58ce5 ("drm/amdkfd: Add navi10 support to amdkfd. (v3)") Cc: stable@vger.kernel.org Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
* | Merge tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drmLinus Torvalds2019-07-194-9/+14
|\| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull drm fixes from Daniel Vetter: "Dave is back in shape, but now family got it so I'm doing the pull. Two things worthy of note: - nouveau feature pull was way too late, Dave&me decided to not take that, so Ben spun up a pull with just the fixes. - after some chatting with the arm display maintainers we decided to change a bit how that's maintained, for more oversight/review and cross vendor collab. More details below: nouveau: - bugfixes - TU116 enabling (minor iteration) :w amdgpu: - large pile of fixes for new hw support this release (navi, vega20) - audio hotplug fix - bunch of corner cases and small fixes all over for amdgpu/kfd komeda: - back out some new properties (from this merge window) that needs more pondering. bochs: - fb pitch setup core: - a new panel quirk - misc fixes" * tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drm: (73 commits) drm/nouveau/secboot/gp102-: remove WAR for SEC2 RTOS start bug drm/nouveau/flcn/gp102-: improve implementation of bind_context() on SEC2/GSP drm/nouveau: fix memory leak in nouveau_conn_reset() drm/nouveau/dmem: missing mutex_lock in error path drm/nouveau/hwmon: return EINVAL if the GPU is powered down for sensors reads drm/nouveau: fix bogus GPL-2 license header drm/nouveau: fix bogus GPL-2 license header drm/nouveau/i2c: Enable i2c pads & busses during preinit drm/nouveau/disp/tu102-: wire up scdc parameter setter drm/nouveau/core: recognise TU116 chipset drm/nouveau/kms: disallow dual-link harder if hdmi connection detected drm/nouveau/disp/nv50-: fix center/aspect-corrected scaling drm/nouveau/disp/nv50-: force scaler for any non-default LVDS/eDP modes drm/nouveau/mcp89/mmu: Use mcp77_mmu_new instead of g84_mmu_new on MCP89. drm/amd/display: init res_pool dccg_ref, dchub_ref with xtalin_freq drm/amdgpu/pm: remove check for pp funcs in freq sysfs handlers drm/amd/display: Force uclk to max for every state drm/amdkfd: Remove GWS from process during uninit drm/amd/amdgpu: Fix offset for vmid selection in debugfs interface drm/amd/powerplay: update vega20 driver if to fit latest SMU firmware ...
| * drm/amdkfd: Remove GWS from process during uninitJoseph Greathouse2019-07-171-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | If we shut down a process without having destroyed its GWS-using queues, it is possible that GWS BO will still be in the process BO list during the gpuvm destruction. This list should be empty at that time, so we should remove the GWS allocation at the process uninit point if it is still around. Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Consistently apply noretry settingFelix Kuehling2019-07-162-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Apply the same setting to SH_MEM_CONFIG and VM_CONTEXT1_CNTL. This makes the noretry param no longer KFD-specific. On GFX10 I'm not changing SH_MEM_CONFIG in this commit because GFX10 has different retry behaviour in the SQ and I don't have a way to test it at the moment. Suggested-by: Christian König <Christian.Koenig@amd.com> CC: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by : Shaoyun.liu < Shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: fix cp hang in evictionEric Huang2019-07-111-7/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | The cp hang occurs in OCL conformance test only on supermicro platform which has 40 cores and the test generates 40 threads. The root cause is race condition in non-protected flags. The fix is to add flags of is_evicted and is_active(init_mqd()) into protected area. Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drmLinus Torvalds2019-07-1539-966/+3800
|\| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull drm updates from Dave Airlie: "The biggest thing in this is the AMD Navi GPU support, this again contains a bunch of header files that are large. These are the new AMD RX5700 GPUs that just recently became available. New drivers: - ST-Ericsson MCDE driver - Ingenic JZ47xx SoC UAPI change: - HDR source metadata property Core: - HDR inforframes and EDID parsing - drm hdmi infoframe unpacking - remove prime sg_table caching into dma-buf - New gem vram helpers to reduce driver code - Lots of drmP.h removal - reservation fencing fix - documentation updates - drm_fb_helper_connector removed - mode name command handler rewrite fbcon: - Remove the fbcon notifiers ttm: - forward progress fixes dma-buf: - make mmap call optional - debugfs refcount fixes - dma-fence free with pending signals fix - each dma-buf gets an inode Panels: - Lots of additional panel bindings amdgpu: - initial navi10 support - avoid hw reset - HDR metadata support - new thermal sensors for vega asics - RAS fixes - use HMM rather than MMU notifier - xgmi topology via kfd - SR-IOV fixes - driver reload fixes - DC use a core bpc attribute - Aux fixes for DC - Bandwidth calc updates for DC - Clock handling refactor - kfd VEGAM support vmwgfx: - Coherent memory support changes i915: - HDR Support - HDMI i2c link - Icelake multi-segmented gamma support - GuC firmware update - Mule Creek Canyon PCH support for EHL - EHL platform updtes - move i915.alpha_support to i915.force_probe - runtime PM refactoring - VBT parsing refactoring - DSI fixes - struct mutex dependency reduction - GEM code reorg mali-dp: - Komeda driver features msm: - dsi vs EPROBE_DEFER fixes - msm8998 snapdragon 835 support - a540 gpu support - mdp5 and dpu interconnect support exynos: - drmP.h removal tegra: - misc fixes tda998x: - audio support improvements - pixel repeated mode support - quantisation range handling corrections - HDMI vendor info fix armada: - interlace support fix - overlay/video plane register handling refactor - add gamma support rockchip: - RX3328 support panfrost: - expose perf counters via hidden ioctls vkms: - enumerate CRC sources list ast: - rework BO handling mgag200: - rework BO handling dw-hdmi: - suspend/resume support rcar-du: - R8A774A1 Soc Support - LVDS dual-link mode support - Additional formats - Misc fixes omapdrm: - DSI command mode display support stm - fb modifier support - runtime PM support sun4i: - use vmap ops vc4: - binner bo binding rework v3d: - compute shader support - resync/sync fixes - job management refactoring lima: - NULL pointer in irq handler fix - scheduler default timeout virtio: - fence seqno support - trace events bochs: - misc fixes tc458767: - IRQ/HDP handling sii902x: - HDMI audio support atmel-hlcdc: - misc fixes meson: - zpos support" * tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits) Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next" Revert "mm: adjust apply_to_pfn_range interface for dropped token." mm: adjust apply_to_pfn_range interface for dropped token. drm/amdgpu/navi10: add uclk activity sensor drm/amdgpu: properly guard the generic discovery code drm/amdgpu: add missing documentation on new module parameters drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback drm/amd/display: avoid 64-bit division drm/amdgpu/psp11: simplify the ucode register logic drm/amdgpu: properly guard DC support in navi code drm/amd/powerplay: vega20: fix uninitialized variable use drm/amd/display: dcn20: include linux/delay.h amdgpu: make pmu support optional drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq drm/amd/powerplay: Use memset to initialize metrics structs drm/amdgpu/mes10.1: Fix header guard drm/amd/powerplay: add temperature sensor support for navi10 drm/amdgpu: fix scheduler timeout calc drm/amdgpu: Prepare for hmm_range_register API change (v2) ...
| * drm/amdkfd: Disable idle optimization for chained runlistFelix Kuehling2019-07-031-0/+1
| | | | | | | | | | | | | | | | | | This works around difficult-to-reproduce soft hangs on oversubscribed runlists. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Add chained_runlist_idle_disable flag to pm4_mes_runlistFelix Kuehling2019-07-031-1/+1
| | | | | | | | | | | | | | | | | | | | | | New flag to disable an idle runlist optimization that is causing soft hangs with some diffult-to-reproduce customer workloads. This will serve as a workaround until the problem can be reproduced and the root-cause determined. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Print a warning when the runlist becomes oversubscribedFelix Kuehling2019-07-032-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | Oversubscription of queues or processes results in poor performance mostly because HWS blinbly schedules busy and idle queues, resulting in poor occupancy if many queues are idle. Let users know with a warning message when transitioning from a non-oversubscribed to an oversubscribed runlist. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: remove an unused variableJack Xiao2019-07-021-1/+0
| | | | | | | | | | | | | | | | | | Just for cleanup. Reviewed-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: remove duplicated PCIE atomics requestJack Xiao2019-07-011-6/+4
| | | | | | | | | | | | | | | | | | | | | | Since amdgpu has always requested PCIE atomics, kfd don't need duplicated PCIE atomics enablement. Referring to amdgpu request result is enough. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: remove unnecessary warning message on gpu resetshaoyunl2019-06-271-1/+0
| | | | | | | | | | | | | | | | | | In XGMI configuration, more than one asic can be reset at same time, kfd is able to handle this and no need to trigger the warning Signed-off-by: shaoyunl <shaoyun.liu@amd.com> Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Set gws_mask to 64 bit 1sOak Zeng2019-06-221-2/+2
| | | | | | | | | | | | | | | | | | | | Previous kfd doesn't use gws so this mask was set to 0. Set it to 64 bit 1s because now kfd can use all 64 gws resources. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Add navi10 support to amdkfd. (v3)Philip Cox2019-06-2117-12/+2434
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | KFD (kernel fusion driver) is the kernel driver for the compute backend for usermode compute stack. v2: squash in updates (Alex) v3: squash in rebase fixes (Alex) Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Philip Cox <Philip.Cox@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Add procfs-style information for KFD processesKent Russell2019-06-203-2/+113
| | | | | | | | | | | | | | | | | | | | | | Add a folder structure to /sys/class/kfd/kfd/ called proc which contains subfolders, each representing an active KFD process' PID, containing 1 file: pasid. Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Fix sdma queue allocate race conditionOak Zeng2019-06-171-1/+6
| | | | | | | | | | | | | | | | | | SDMA queue allocation requires the dqm lock as it modify the global dqm members. Enclose it in the dqm_lock. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Fix a circular lock dependencyOak Zeng2019-06-171-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The idea to break the circular lock dependency is to temporarily drop dqm lock before calling allocate_mqd. See callstack #1 below. [ 59.510149] [drm] Initialized amdgpu 3.30.0 20150101 for 0000:04:00.0 on minor 0 [ 513.604034] ====================================================== [ 513.604205] WARNING: possible circular locking dependency detected [ 513.604375] 4.18.0-kfd-root #2 Tainted: G W [ 513.604530] ------------------------------------------------------ [ 513.604699] kswapd0/611 is trying to acquire lock: [ 513.604840] 00000000d254022e (&dqm->lock_hidden){+.+.}, at: evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.605150] but task is already holding lock: [ 513.605307] 00000000961547fc (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe4/0x250 [ 513.605540] which lock already depends on the new lock. [ 513.605747] the existing dependency chain (in reverse order) is: [ 513.605944] -> #4 (&anon_vma->rwsem){++++}: [ 513.606106] __vma_adjust+0x147/0x7f0 [ 513.606231] __split_vma+0x179/0x190 [ 513.606353] mprotect_fixup+0x217/0x260 [ 513.606553] do_mprotect_pkey+0x211/0x380 [ 513.606752] __x64_sys_mprotect+0x1b/0x20 [ 513.606954] do_syscall_64+0x50/0x1a0 [ 513.607149] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.607380] -> #3 (&mapping->i_mmap_rwsem){++++}: [ 513.607678] rmap_walk_file+0x1f0/0x280 [ 513.607887] page_referenced+0xdd/0x180 [ 513.608081] shrink_page_list+0x853/0xcb0 [ 513.608279] shrink_inactive_list+0x33b/0x700 [ 513.608483] shrink_node_memcg+0x37a/0x7f0 [ 513.608682] shrink_node+0xd8/0x490 [ 513.608869] balance_pgdat+0x18b/0x3b0 [ 513.609062] kswapd+0x203/0x5c0 [ 513.609241] kthread+0x100/0x140 [ 513.609420] ret_from_fork+0x24/0x30 [ 513.609607] -> #2 (fs_reclaim){+.+.}: [ 513.609883] kmem_cache_alloc_trace+0x34/0x2e0 [ 513.610093] reservation_object_reserve_shared+0x139/0x300 [ 513.610326] ttm_bo_init_reserved+0x291/0x480 [ttm] [ 513.610567] amdgpu_bo_do_create+0x1d2/0x650 [amdgpu] [ 513.610811] amdgpu_bo_create+0x40/0x1f0 [amdgpu] [ 513.611041] amdgpu_bo_create_reserved+0x249/0x2d0 [amdgpu] [ 513.611290] amdgpu_bo_create_kernel+0x12/0x70 [amdgpu] [ 513.611584] amdgpu_ttm_init+0x2cb/0x560 [amdgpu] [ 513.611823] gmc_v9_0_sw_init+0x400/0x750 [amdgpu] [ 513.612491] amdgpu_device_init+0x14eb/0x1990 [amdgpu] [ 513.612730] amdgpu_driver_load_kms+0x78/0x290 [amdgpu] [ 513.612958] drm_dev_register+0x111/0x1a0 [ 513.613171] amdgpu_pci_probe+0x11c/0x1e0 [amdgpu] [ 513.613389] local_pci_probe+0x3f/0x90 [ 513.613581] pci_device_probe+0x102/0x1c0 [ 513.613779] driver_probe_device+0x2a7/0x480 [ 513.613984] __driver_attach+0x10a/0x110 [ 513.614179] bus_for_each_dev+0x67/0xc0 [ 513.614372] bus_add_driver+0x1eb/0x260 [ 513.614565] driver_register+0x5b/0xe0 [ 513.614756] do_one_initcall+0xac/0x357 [ 513.614952] do_init_module+0x5b/0x213 [ 513.615145] load_module+0x2542/0x2d30 [ 513.615337] __do_sys_finit_module+0xd2/0x100 [ 513.615541] do_syscall_64+0x50/0x1a0 [ 513.615731] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.615963] -> #1 (reservation_ww_class_mutex){+.+.}: [ 513.616293] amdgpu_amdkfd_alloc_gtt_mem+0xcf/0x2c0 [amdgpu] [ 513.616554] init_mqd+0x223/0x260 [amdgpu] [ 513.616779] create_queue_nocpsch+0x4d9/0x600 [amdgpu] [ 513.617031] pqm_create_queue+0x37c/0x520 [amdgpu] [ 513.617270] kfd_ioctl_create_queue+0x2f9/0x650 [amdgpu] [ 513.617522] kfd_ioctl+0x202/0x350 [amdgpu] [ 513.617724] do_vfs_ioctl+0x9f/0x6c0 [ 513.617914] ksys_ioctl+0x66/0x70 [ 513.618095] __x64_sys_ioctl+0x16/0x20 [ 513.618286] do_syscall_64+0x50/0x1a0 [ 513.618476] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.618695] -> #0 (&dqm->lock_hidden){+.+.}: [ 513.618984] __mutex_lock+0x98/0x970 [ 513.619197] evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.619459] kfd_process_evict_queues+0x3b/0xb0 [amdgpu] [ 513.619710] kgd2kfd_quiesce_mm+0x1c/0x40 [amdgpu] [ 513.620103] amdgpu_amdkfd_evict_userptr+0x38/0x70 [amdgpu] [ 513.620363] amdgpu_mn_invalidate_range_start_hsa+0xa6/0xc0 [amdgpu] [ 513.620614] __mmu_notifier_invalidate_range_start+0x70/0xb0 [ 513.620851] try_to_unmap_one+0x7fc/0x8f0 [ 513.621049] rmap_walk_anon+0x121/0x290 [ 513.621242] try_to_unmap+0x93/0xf0 [ 513.621428] shrink_page_list+0x606/0xcb0 [ 513.621625] shrink_inactive_list+0x33b/0x700 [ 513.621835] shrink_node_memcg+0x37a/0x7f0 [ 513.622034] shrink_node+0xd8/0x490 [ 513.622219] balance_pgdat+0x18b/0x3b0 [ 513.622410] kswapd+0x203/0x5c0 [ 513.622589] kthread+0x100/0x140 [ 513.622769] ret_from_fork+0x24/0x30 [ 513.622957] other info that might help us debug this: [ 513.623354] Chain exists of: &dqm->lock_hidden --> &mapping->i_mmap_rwsem --> &anon_vma->rwsem [ 513.623900] Possible unsafe locking scenario: [ 513.624189] CPU0 CPU1 [ 513.624397] ---- ---- [ 513.624594] lock(&anon_vma->rwsem); [ 513.624771] lock(&mapping->i_mmap_rwsem); [ 513.625020] lock(&anon_vma->rwsem); [ 513.625253] lock(&dqm->lock_hidden); [ 513.625433] *** DEADLOCK *** [ 513.625783] 3 locks held by kswapd0/611: [ 513.625967] #0: 00000000f14edf84 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x5/0x30 [ 513.626309] #1: 00000000961547fc (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe4/0x250 [ 513.626671] #2: 0000000067b5cd12 (srcu){....}, at: __mmu_notifier_invalidate_range_start+0x5/0xb0 [ 513.627037] stack backtrace: [ 513.627292] CPU: 0 PID: 611 Comm: kswapd0 Tainted: G W 4.18.0-kfd-root #2 [ 513.627632] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 513.627990] Call Trace: [ 513.628143] dump_stack+0x7c/0xbb [ 513.628315] print_circular_bug.isra.37+0x21b/0x228 [ 513.628581] __lock_acquire+0xf7d/0x1470 [ 513.628782] ? unwind_next_frame+0x6c/0x4f0 [ 513.628974] ? lock_acquire+0xec/0x1e0 [ 513.629154] lock_acquire+0xec/0x1e0 [ 513.629357] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.629587] __mutex_lock+0x98/0x970 [ 513.629790] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630047] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630309] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630562] evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630816] kfd_process_evict_queues+0x3b/0xb0 [amdgpu] [ 513.631057] kgd2kfd_quiesce_mm+0x1c/0x40 [amdgpu] [ 513.631288] amdgpu_amdkfd_evict_userptr+0x38/0x70 [amdgpu] [ 513.631536] amdgpu_mn_invalidate_range_start_hsa+0xa6/0xc0 [amdgpu] [ 513.632076] __mmu_notifier_invalidate_range_start+0x70/0xb0 [ 513.632299] try_to_unmap_one+0x7fc/0x8f0 [ 513.632487] ? page_lock_anon_vma_read+0x68/0x250 [ 513.632690] rmap_walk_anon+0x121/0x290 [ 513.632875] try_to_unmap+0x93/0xf0 [ 513.633050] ? page_remove_rmap+0x330/0x330 [ 513.633239] ? rcu_read_unlock+0x60/0x60 [ 513.633422] ? page_get_anon_vma+0x160/0x160 [ 513.633613] shrink_page_list+0x606/0xcb0 [ 513.633800] shrink_inactive_list+0x33b/0x700 [ 513.633997] shrink_node_memcg+0x37a/0x7f0 [ 513.634186] ? shrink_node+0xd8/0x490 [ 513.634363] shrink_node+0xd8/0x490 [ 513.634537] balance_pgdat+0x18b/0x3b0 [ 513.634718] kswapd+0x203/0x5c0 [ 513.634887] ? wait_woken+0xb0/0xb0 [ 513.635062] kthread+0x100/0x140 [ 513.635231] ? balance_pgdat+0x3b0/0x3b0 [ 513.635414] ? kthread_delayed_work_timer_fn+0x80/0x80 [ 513.635626] ret_from_fork+0x24/0x30 [ 513.636042] Evicting PASID 32768 queues [ 513.936236] Restoring PASID 32768 queues [ 524.708912] Evicting PASID 32768 queues [ 524.999875] Restoring PASID 32768 queues Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * Revert "drm/amdkfd: Fix a circular lock dependency"Oak Zeng2019-06-171-10/+11
| | | | | | | | | | | | | | | | | | | | | | This reverts commit 06b89b38f3cc518a761164f9f958a9607bbb3587. This fix is not proper. allocate_mqd can't be moved before allocate_sdma_queue as it depends on q->properties->sdma_id set in later. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * Revert "drm/amdkfd: Fix sdma queue allocate race condition"Oak Zeng2019-06-171-12/+14
| | | | | | | | | | | | | | | | | | | | | | This reverts commit f77dac6cd62e5d4bcadd740620af1218bfb54cc6. This fix is not proper. allocate_mqd can't be moved before allocate_sdma_queue as it depends on q->properties->sdma_id set in later. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * amdkfd: no need to check return value of debugfs_create functionsGreg Kroah-Hartman2019-06-131-28/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Cc: Oded Gabbay <oded.gabbay@gmail.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Add device to topology after it is completely initedOak Zeng2019-06-111-7/+6
| | | | | | | | | | | | | | | | | | | | | | We can't have devices that are not completely initialized in kfd topology. Otherwise it is a race condition when user access not completely initialized device. This also addresses a kfd_topology_add_device accessing NULL dqm pointer issue. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Initialize HSA_CAP_ATS_PRESENT capability in topology codesOak Zeng2019-06-112-11/+10
| | | | | | | | | | | | | | | | | | | | | | Move HSA_CAP_ATS_PRESENT initialization logic from kfd iommu codes to kfd topology codes. This removes kfd_iommu_device_init's dependency on kfd_topology_add_device. Also remove duplicate code setting the same. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Fix sdma queue allocate race conditionOak Zeng2019-06-111-14/+12
| | | | | | | | | | | | | | | | | | | | | | | | SDMA queue allocation requires the dqm lock at it modify the global dqm members. Move up the dqm_lock so sdma queue allocation is enclosed in the critical section. Move mqd allocation out of critical section to avoid circular lock dependency. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Fix a circular lock dependencyOak Zeng2019-06-111-11/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The idea to break the circular lock dependency is to move allocate_mqd out of dqm lock protection. See callstack #1 below. [ 59.510149] [drm] Initialized amdgpu 3.30.0 20150101 for 0000:04:00.0 on minor 0 [ 513.604034] ====================================================== [ 513.604205] WARNING: possible circular locking dependency detected [ 513.604375] 4.18.0-kfd-root #2 Tainted: G W [ 513.604530] ------------------------------------------------------ [ 513.604699] kswapd0/611 is trying to acquire lock: [ 513.604840] 00000000d254022e (&dqm->lock_hidden){+.+.}, at: evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.605150] but task is already holding lock: [ 513.605307] 00000000961547fc (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe4/0x250 [ 513.605540] which lock already depends on the new lock. [ 513.605747] the existing dependency chain (in reverse order) is: [ 513.605944] -> #4 (&anon_vma->rwsem){++++}: [ 513.606106] __vma_adjust+0x147/0x7f0 [ 513.606231] __split_vma+0x179/0x190 [ 513.606353] mprotect_fixup+0x217/0x260 [ 513.606553] do_mprotect_pkey+0x211/0x380 [ 513.606752] __x64_sys_mprotect+0x1b/0x20 [ 513.606954] do_syscall_64+0x50/0x1a0 [ 513.607149] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.607380] -> #3 (&mapping->i_mmap_rwsem){++++}: [ 513.607678] rmap_walk_file+0x1f0/0x280 [ 513.607887] page_referenced+0xdd/0x180 [ 513.608081] shrink_page_list+0x853/0xcb0 [ 513.608279] shrink_inactive_list+0x33b/0x700 [ 513.608483] shrink_node_memcg+0x37a/0x7f0 [ 513.608682] shrink_node+0xd8/0x490 [ 513.608869] balance_pgdat+0x18b/0x3b0 [ 513.609062] kswapd+0x203/0x5c0 [ 513.609241] kthread+0x100/0x140 [ 513.609420] ret_from_fork+0x24/0x30 [ 513.609607] -> #2 (fs_reclaim){+.+.}: [ 513.609883] kmem_cache_alloc_trace+0x34/0x2e0 [ 513.610093] reservation_object_reserve_shared+0x139/0x300 [ 513.610326] ttm_bo_init_reserved+0x291/0x480 [ttm] [ 513.610567] amdgpu_bo_do_create+0x1d2/0x650 [amdgpu] [ 513.610811] amdgpu_bo_create+0x40/0x1f0 [amdgpu] [ 513.611041] amdgpu_bo_create_reserved+0x249/0x2d0 [amdgpu] [ 513.611290] amdgpu_bo_create_kernel+0x12/0x70 [amdgpu] [ 513.611584] amdgpu_ttm_init+0x2cb/0x560 [amdgpu] [ 513.611823] gmc_v9_0_sw_init+0x400/0x750 [amdgpu] [ 513.612491] amdgpu_device_init+0x14eb/0x1990 [amdgpu] [ 513.612730] amdgpu_driver_load_kms+0x78/0x290 [amdgpu] [ 513.612958] drm_dev_register+0x111/0x1a0 [ 513.613171] amdgpu_pci_probe+0x11c/0x1e0 [amdgpu] [ 513.613389] local_pci_probe+0x3f/0x90 [ 513.613581] pci_device_probe+0x102/0x1c0 [ 513.613779] driver_probe_device+0x2a7/0x480 [ 513.613984] __driver_attach+0x10a/0x110 [ 513.614179] bus_for_each_dev+0x67/0xc0 [ 513.614372] bus_add_driver+0x1eb/0x260 [ 513.614565] driver_register+0x5b/0xe0 [ 513.614756] do_one_initcall+0xac/0x357 [ 513.614952] do_init_module+0x5b/0x213 [ 513.615145] load_module+0x2542/0x2d30 [ 513.615337] __do_sys_finit_module+0xd2/0x100 [ 513.615541] do_syscall_64+0x50/0x1a0 [ 513.615731] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.615963] -> #1 (reservation_ww_class_mutex){+.+.}: [ 513.616293] amdgpu_amdkfd_alloc_gtt_mem+0xcf/0x2c0 [amdgpu] [ 513.616554] init_mqd+0x223/0x260 [amdgpu] [ 513.616779] create_queue_nocpsch+0x4d9/0x600 [amdgpu] [ 513.617031] pqm_create_queue+0x37c/0x520 [amdgpu] [ 513.617270] kfd_ioctl_create_queue+0x2f9/0x650 [amdgpu] [ 513.617522] kfd_ioctl+0x202/0x350 [amdgpu] [ 513.617724] do_vfs_ioctl+0x9f/0x6c0 [ 513.617914] ksys_ioctl+0x66/0x70 [ 513.618095] __x64_sys_ioctl+0x16/0x20 [ 513.618286] do_syscall_64+0x50/0x1a0 [ 513.618476] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 513.618695] -> #0 (&dqm->lock_hidden){+.+.}: [ 513.618984] __mutex_lock+0x98/0x970 [ 513.619197] evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.619459] kfd_process_evict_queues+0x3b/0xb0 [amdgpu] [ 513.619710] kgd2kfd_quiesce_mm+0x1c/0x40 [amdgpu] [ 513.620103] amdgpu_amdkfd_evict_userptr+0x38/0x70 [amdgpu] [ 513.620363] amdgpu_mn_invalidate_range_start_hsa+0xa6/0xc0 [amdgpu] [ 513.620614] __mmu_notifier_invalidate_range_start+0x70/0xb0 [ 513.620851] try_to_unmap_one+0x7fc/0x8f0 [ 513.621049] rmap_walk_anon+0x121/0x290 [ 513.621242] try_to_unmap+0x93/0xf0 [ 513.621428] shrink_page_list+0x606/0xcb0 [ 513.621625] shrink_inactive_list+0x33b/0x700 [ 513.621835] shrink_node_memcg+0x37a/0x7f0 [ 513.622034] shrink_node+0xd8/0x490 [ 513.622219] balance_pgdat+0x18b/0x3b0 [ 513.622410] kswapd+0x203/0x5c0 [ 513.622589] kthread+0x100/0x140 [ 513.622769] ret_from_fork+0x24/0x30 [ 513.622957] other info that might help us debug this: [ 513.623354] Chain exists of: &dqm->lock_hidden --> &mapping->i_mmap_rwsem --> &anon_vma->rwsem [ 513.623900] Possible unsafe locking scenario: [ 513.624189] CPU0 CPU1 [ 513.624397] ---- ---- [ 513.624594] lock(&anon_vma->rwsem); [ 513.624771] lock(&mapping->i_mmap_rwsem); [ 513.625020] lock(&anon_vma->rwsem); [ 513.625253] lock(&dqm->lock_hidden); [ 513.625433] *** DEADLOCK *** [ 513.625783] 3 locks held by kswapd0/611: [ 513.625967] #0: 00000000f14edf84 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x5/0x30 [ 513.626309] #1: 00000000961547fc (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe4/0x250 [ 513.626671] #2: 0000000067b5cd12 (srcu){....}, at: __mmu_notifier_invalidate_range_start+0x5/0xb0 [ 513.627037] stack backtrace: [ 513.627292] CPU: 0 PID: 611 Comm: kswapd0 Tainted: G W 4.18.0-kfd-root #2 [ 513.627632] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 513.627990] Call Trace: [ 513.628143] dump_stack+0x7c/0xbb [ 513.628315] print_circular_bug.isra.37+0x21b/0x228 [ 513.628581] __lock_acquire+0xf7d/0x1470 [ 513.628782] ? unwind_next_frame+0x6c/0x4f0 [ 513.628974] ? lock_acquire+0xec/0x1e0 [ 513.629154] lock_acquire+0xec/0x1e0 [ 513.629357] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.629587] __mutex_lock+0x98/0x970 [ 513.629790] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630047] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630309] ? evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630562] evict_process_queues_nocpsch+0x26/0x140 [amdgpu] [ 513.630816] kfd_process_evict_queues+0x3b/0xb0 [amdgpu] [ 513.631057] kgd2kfd_quiesce_mm+0x1c/0x40 [amdgpu] [ 513.631288] amdgpu_amdkfd_evict_userptr+0x38/0x70 [amdgpu] [ 513.631536] amdgpu_mn_invalidate_range_start_hsa+0xa6/0xc0 [amdgpu] [ 513.632076] __mmu_notifier_invalidate_range_start+0x70/0xb0 [ 513.632299] try_to_unmap_one+0x7fc/0x8f0 [ 513.632487] ? page_lock_anon_vma_read+0x68/0x250 [ 513.632690] rmap_walk_anon+0x121/0x290 [ 513.632875] try_to_unmap+0x93/0xf0 [ 513.633050] ? page_remove_rmap+0x330/0x330 [ 513.633239] ? rcu_read_unlock+0x60/0x60 [ 513.633422] ? page_get_anon_vma+0x160/0x160 [ 513.633613] shrink_page_list+0x606/0xcb0 [ 513.633800] shrink_inactive_list+0x33b/0x700 [ 513.633997] shrink_node_memcg+0x37a/0x7f0 [ 513.634186] ? shrink_node+0xd8/0x490 [ 513.634363] shrink_node+0xd8/0x490 [ 513.634537] balance_pgdat+0x18b/0x3b0 [ 513.634718] kswapd+0x203/0x5c0 [ 513.634887] ? wait_woken+0xb0/0xb0 [ 513.635062] kthread+0x100/0x140 [ 513.635231] ? balance_pgdat+0x3b0/0x3b0 [ 513.635414] ? kthread_delayed_work_timer_fn+0x80/0x80 [ 513.635626] ret_from_fork+0x24/0x30 [ 513.636042] Evicting PASID 32768 queues [ 513.936236] Restoring PASID 32768 queues [ 524.708912] Evicting PASID 32768 queues [ 524.999875] Restoring PASID 32768 queues Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Separate mqd allocation and initializationOak Zeng2019-06-117-193/+129
| | | | | | | | | | | | | | | | | | | | | | Introduce a new mqd allocation interface and split the original init_mqd function into two functions: allocate_mqd and init_mqd. Also renamed uninit_mqd to free_mqd. This is preparation work to fix a circular lock dependency. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Refactor create_queue_nocpschOak Zeng2019-06-111-114/+57
| | | | | | | | | | | | | | | | | | This is prepare work to fix a circular lock dependency. No logic change Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Only load sdma mqd when queue is activeOak Zeng2019-06-111-1/+4
| | | | | | | | | | | | | | | | | | Also calls load_mqd with current->mm struct. The mm struct is used to read back user wptr of the queue. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Only initialize sdma vm for sdma queuesOak Zeng2019-06-111-2/+3
| | | | | | | | | | | | | | | | Don't do the same for compute queues Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Implement queue priority controls for gfx9Jay Cornwall2019-06-111-3/+7
| | | | | | | | | | | | | | | | | | | | Ported from gfx8, no changes in register setup. Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: CP queue priority controlsOak Zeng2019-06-115-7/+50
| | | | | | | | | | | | | | | | | | | | | | Translate queue priority into pipe priority and write to MQDs. The priority values are used to perform queue and pipe arbitration. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Simplify eviction state logicFelix Kuehling2019-06-115-68/+56
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Always mark evicted queues with q->properties.is_evicted = true, even queues that are inactive for other reason. This simplifies maintaining the eviction state as it doesn't require updating is_evicted when other queue activation conditions change. On the other hand, we now need to check those other queue activation conditions whenever an evicted queues is restored. To minimize code duplication, move the queue activation check into a macro so it can be maintained in one central place. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Philip Cox <Philip.Cox@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: Return proper error code for gws alloc APIOak Zeng2019-05-312-4/+4
| | | | | | | | | | | | Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
OpenPOWER on IntegriCloud