summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
AgeCommit message (Collapse)AuthorFilesLines
2020-07-14drm/amdgpu/sdma5: fix wptr overwritten in ->get_wptr()Xiaojie Yuan1-18/+8
"u64 *wptr" points to the the wptr value in write back buffer and "*wptr = (*wptr) >> 2;" results in the value being overwritten each time when ->get_wptr() is called. umr uses /sys/kernel/debug/dri/0/amdgpu_ring_sdma0 to get rptr/wptr and decode ring content and it is affected by this issue. fix and simplify the logic similar as sdma_v4_0_ring_get_wptr(). v2: fix for sdma5.2 as well v3: drop sdma 5.2 changes for 5.8 and stable Suggested-by: Le Ma <le.ma@amd.com> Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2020-06-24drm/amdgpu: add fw release for sdma v5_0Wenhui Sheng1-1/+5
sdma fw isn't released when module exit Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Wenhui Sheng <Wenhui.Sheng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2020-04-28drm/amdgpu: enable TMZ bit in sdma copy pkt for sdma v5Aaron Liu1-1/+2
Enable sdma TMZ mode via setting TMZ bit in sdma copy pkt for sdma v5. Signed-off-by: Aaron Liu <aaron.liu@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: expand sdma copy_buffer interface with tmz parameterAaron Liu1-1/+2
This patch expands sdma copy_buffer interface with tmz parameter. Signed-off-by: Aaron Liu <aaron.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: invalidate L2 before SDMA IBs (v2)Marek Olšák1-1/+13
This fixes GPU hangs due to cache coherency issues. v2: Split the version bump to a separate patch Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Tested-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-22drm/amdgpu: Adjust the SDMA doorbell info printingYong Zhao1-1/+1
Turn off the printing by default because it is not very useful, while adding more details. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-09drm/amdgpu: rework sched_list generationNirmoy Das1-1/+2
Generate HW IP's sched_list in amdgpu_ring_init() instead of amdgpu_ctx.c. This makes amdgpu_ctx_init_compute_sched(), ring.has_high_prio and amdgpu_ctx_init_sched() unnecessary. This patch also stores sched_list for all HW IPs in one big array in struct amdgpu_device which makes amdgpu_ctx_init_entity() much more leaner. v2: fix a coding style issue do not use drm hw_ip const to populate amdgpu_ring_type enum v3: remove ctx reference and move sched array and num_sched to a struct use num_scheds to detect uninitialized scheduler list v4: use array_index_nospec for user space controlled variables fix possible checkpatch.pl warnings Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-01drm/amdgpu: skip access sdma_v5_0 registers under SRIOV (v2)Yintian Tao1-36/+76
Due to the new L1.0b0c011b policy, many SDMA registers are blocked which raise the violation warning. There are total 6 pair register needed to be skipped when driver init and de-init. mmSDMA0/1_CNTL mmSDMA0/1_F32_CNTL mmSDMA0/1_UTCL1_PAGE mmSDMA0/1_UTCL1_CNTL mmSDMA0/1_CHICKEN_BITS, mmSDMA0/1_SEM_WAIT_FAIL_TIMER_CNTL v2: squash in warning fix Signed-off-by: Yintian Tao <yttao@amd.com> Reviewed-by: Emily Deng <Emily.Deng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-01drm/amdgpu: stop disable the scheduler during HW finiChristian König1-3/+0
When we stop the HW for example for GPU reset we should not stop the front-end scheduler. Otherwise we run into intermediate failures during command submission. The scheduler should only be stopped in very few cases: 1. We can't get the hardware working in ring or IB test after a GPU reset. 2. The KIQ scheduler is not used in the front-end and should be disabled during GPU reset. 3. In amdgpu_ring_fini() when the driver unloads. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Test-by: Dennis Li <dennis.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-01drm/amdgpu: implement more ib pools (v2)xinhui pan1-1/+2
We have three ib pools, they are normal, VM, direct pools. Any jobs which schedule IBs without dependence on gpu scheduler should use DIRECT pool. Any jobs schedule direct VM update IBs should use VM pool. Any other jobs use NORMAL pool. v2: squash in coding style fix Signed-off-by: xinhui pan <xinhui.pan@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-26drm/amdgpu: use amdgpu_ring_test_helper when possibleNirmoy Das1-4/+2
amdgpu_ring_test_helper already handles ring->sched.ready correctly Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-01-22drm/amdgpu: remove unnecessary conversion to boolNirmoy Das1-2/+2
Better clean that up before some automation starts to complain about it Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-12-23drm/amdgpu: simplify padding calculations (v2)Luben Tuikov1-5/+12
Simplify padding calculations. v2: Comment update and spacing. Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-12-18drm/amdgpu: replace vm_pte's run-queue list with drm gpu scheds listNirmoy Das1-5/+3
drm_sched_entity_init() takes drm gpu scheduler list instead of drm_sched_rq list. This makes conversion of drm_sched_rq list to drm gpu scheduler list unnecessary Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-12-18drm/amdgpu/sdma5: make ring tests less chattyAlex Deucher1-15/+5
We already did this for older generations. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-11-14Merge v5.4-rc7 into drm-nextDave Airlie1-1/+12
We have the i915 security fixes to backmerge, but first let's clear the decks for other drivers to avoid a bigger mess. Signed-off-by: Dave Airlie <airlied@redhat.com>
2019-11-06drm/amdgpu: add dummy read by engines for some GCVM status registers in gfx10changzhu1-1/+12
The GRBM register interface is now capable of bursting 1 cycle per register wr->wr, wr->rd much faster than previous muticycle per transaction done interface. This has caused a problem where status registers requiring HW to update have a 1 cycle delay, due to the register update having to go through GRBM. For cp ucode, it has realized dummy read in cp firmware.It covers the use of WAIT_REG_MEM operation 1 case only.So it needs to call gfx_v10_0_wait_reg_mem in gfx10. Besides it also needs to add warning to update firmware in case firmware is too old to have function to realize dummy read in cp firmware. For sdma ucode, it hasn't realized dummy read in sdma firmware. sdma is moved to gfxhub in gfx10. So it needs to add dummy read in driver between amdgpu_ring_emit_wreg and amdgpu_ring_emit_reg_wait for sdma_v5_0. Signed-off-by: changzhu <Changfeng.Zhu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-10-26Merge tag 'drm-next-5.5-2019-10-09' of ↵Dave Airlie1-4/+4
git://people.freedesktop.org/~agd5f/linux into drm-next drm-next-5.5-2019-10-09: amdgpu: - Additional RAS enablement for vega20 - RAS page retirement and bad page storage in EEPROM - No GPU reset with unrecoverable RAS errors - Reserve vram for page tables rather than trying to evict - Fix issues with GPU reset and xgmi hives - DC i2c over aux fixes - Direct submission for clears, PTE/PDE updates - Improvements to help support recoverable GPU page faults - Silence harmless SAD block messages - Clean up code for creating a bo at a fixed location - Initial DC HDCP support - Lots of documentation fixes - GPU reset for renoir - Add IH clockgating support for soc15 asics - Powerplay improvements - DC MST cleanups - Add support for MSI-X - Misc cleanups and bug fixes amdkfd: - Query KFD device info by asic type rather than pci ids - Add navi14 support - Add renoir support - Add navi12 support - gfx10 trap handler improvements - pasid cleanups - Check against device cgroup ttm: - Return -EBUSY with pipelining with no_gpu_wait radeon: - Silence harmless SAD block messages device_cgroup: - Export devcgroup_check_permission Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexdeucher@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191010041713.3412-1-alexander.deucher@amd.com
2019-10-11drm/amdgpu/sdma5: fix mask value of POLL_REGMEM packet for pipe syncXiaojie Yuan1-1/+1
sdma will hang once sequence number to be polled reaches 0x1000_0000 Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2019-09-13drm/amdgpu: switch to new amdgpu_nbio structureHawking Zhang1-4/+4
no functional change, just switch to new structures Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-08-22drm/amdgpu/sdma5: fix number of sdma5 trap irq types for navi1xXiaojie Yuan1-1/+2
v2: set num_types based on num_instances navi1x has 2 sdma engines but commit "e7b58d03b678 drm/amdgpu: reorganize sdma v4 code to support more instances" changes the max number of sdma irq types (AMDGPU_SDMA_IRQ_LAST) from 2 to 8 which causes amdgpu_irq_gpu_reset_resume_helper() to recover irq of sdma engines with following logic: (enable irq for sdma0) * 1 time (enable irq for sdma1) * 1 time (disable irq for sdma1) * 6 times as a result, after gpu reset, interrupt for sdma1 is lost. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-08-12drm/amdgpu/sdma5: set sdma clock gating for navi12Xiaojie Yuan1-0/+1
add navi12 define Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-08-02drm/amdgpu/sdma5: add golden settings for navi12 (v2)Xiaojie Yuan1-0/+2
common golden settings are put in golden_settings_sdma_5 array v2: update settings (Alex) Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-08-02drm/amdgpu/sdma5: add placeholder for navi12 golden settingsXiaojie Yuan1-0/+11
None yet. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-08-02drm/amdgpu/sdma5: declare sdma firmwares for navi12Xiaojie Yuan1-0/+6
Declare the firmwares and load the proper ones for navi12. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31drm/amdgpu: drop drmP.h from sdma_v5_0.cAlex Deucher1-3/+6
And fix the fallout. Acked-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu: rename AMDGPU_GFXHUB/MMHUB macro with hub numberLe Ma1-1/+1
The number of GFXHUB/MMHUB may be expanded in later ASICs. Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu/sdma5: set clock gating for navi14Xiaojie Yuan1-0/+1
same as navi10. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu/sdma5: update sdma5 golden settings for navi14tiancyin1-0/+2
add new registers: mmSDMA0_RLC3_RB_WPTR_POLL_CNTL, mmSDMA1_RLC3_RB_WPTR_POLL_CNTL Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: tiancyin <tianci.yin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu/sdma5: add sdma5_0 golden settings for navi14Xiaojie Yuan1-2/+4
Add settings for navi14. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Snow Zhang <Snow.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu/sdma5: add placeholder for navi14 golden settingsXiaojie Yuan1-0/+11
To be filled in once they are available. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18drm/amdgpu/sdma5: add support for navi14 firmwareXiaojie Yuan1-0/+6
Add support for navi14 sdma firmware files. Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-21drm/amdgpu/sdma5: incorrect variable type for gpu addressJack Xiao1-1/+2
Incorrect programming with 64bit gpu address assignment for 32bit variable. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-21drm/amdgpu/sdma5: fix a sdma potential hang in VK_Examples testtiancyin1-1/+2
[why] When page fault happens, it could lead to sdma hang is RESP_MODE = 0 for non-PRT case. [how] Setting SDMAx_UTCL1_CNTL.RESP_MODE to 0b011 to avoid SDMA halt. Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: tiancyin <tianci.yin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-21drm/amdgpu: add initial support for sdma v5.0 (v6)Hawking Zhang1-0/+1685
SDMA (System DMA) is a general purpose DMA engine usable by UMDs for transfers or the kernel for paging or GPUVM updates. v1: support basic funcitonalites includes rb, ib, vm, copy buffer and trap irq v2: convert to use new get_vm_pde in emit_vm_flush v3: retire amdgpu_ttm_set_active_vram_size from sdma v5 v4: retire the redundant hdp_invalidate implementation v5: squash in updates v6: some golden regs moved to vbios Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-04 23:49:26 +0000