aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
AgeCommit message (Collapse)AuthorFilesLines
2020-05-01drm/amdgpu: Rename amdgpu_gfx_kcq_queue_mask_transform()Yong Zhao1-8/+8
Rename it to amdgpu_queue_mask_bit_to_set_resource_bit() to be more specific about its functionality. KFD will use it later. Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-05-01drm/amdgpu: update the method to set kcq queue maskLikun Gao1-1/+14
Use a common method to set queue mask before set kiq resource. The value of queue mask must suitablt for the designated form. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-24drm/amdgpu: protect ring overrunYintian Tao1-4/+18
Wait for the oldest sequence on the ring to be signaled in order to make sure there will be no command overrun. v2: fix coding stype and remove abs operation v3: remove the initialization of variable r Signed-off-by: Yintian Tao <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-23drm/amdgpu: request reg_val_offs each kiq read regYintian Tao1-8/+11
According to the current kiq read register method, there will be race condition when using KIQ to read register if multiple clients want to read at same time just like the expample below: 1. client-A start to read REG-0 throguh KIQ 2. client-A poll the seqno-0 3. client-B start to read REG-1 through KIQ 4. client-B poll the seqno-1 5. the kiq complete these two read operation 6. client-A to read the register at the wb buffer and get REG-1 value Therefore, use amdgpu_device_wb_get() to request reg_val_offs for each kiq read register. v2: fix the error remove v3: fix the print typo v4: remove unused variables Signed-off-by: Yintian Tao <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-13drm/amdgpu/kiq: add no_scheduler flag to KIQAlex Deucher1-0/+1
We don't want a GPU scheduler for this ring. Reviewed-by: Christian König <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
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 <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-03-10drm/amdgpu: call ras_debugfs_create_all in debugfs_initTao Zhou1-1/+0
and remove each ras IP's own debugfs creation this is required to fix ras when the driver does not use the drm load and unload callbacks due to ordering issues with the drm device node. Signed-off-by: Tao Zhou <[email protected]> Signed-off-by: Stanley.Yang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-03-09drm/amdgpu: set compute queue priority at mqd_initNirmoy Das1-0/+8
We were changing compute ring priority while rings were being used before every job submission which is not recommended. This patch sets compute queue priority at mqd initialization for gfx8, gfx9 and gfx10. Policy: make queue 0 of each pipe as high priority compute queue High/normal priority compute sched lists are generated from set of high/normal priority compute queues. At context creation, entity of compute queue get a sched list from high or normal priority depending on ctx->priority Signed-off-by: Nirmoy Das <[email protected]> Acked-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-02-26drm/amdgpu: use amdgpu_ring_test_helper when possibleNirmoy Das1-1/+1
amdgpu_ring_test_helper already handles ring->sched.ready correctly Signed-off-by: Nirmoy Das <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-01-22drm/amdgpu: provide a generic function interface for reading/writing ↵chen gong1-2/+94
register by KIQ Move amdgpu_virt_kiq_rreg/amdgpu_virt_kiq_wreg function to amdgpu_gfx.c, and rename them to amdgpu_kiq_rreg/amdgpu_kiq_wreg.Make it generic and flexible. Signed-off-by: chen gong <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-01-14drm/amd/powerplay: cover the powerplay implementation details V3Evan Quan1-6/+0
This can save users much troubles. As they do not actually need to care whether swSMU or traditional powerplay routine should be used. V2: apply the fixes to vi.c and cik.c also V3: squash in oops fix Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-12-18drm/amdgpu: drop useless BACO arg in amdgpu_ras_reset_gpuGuchun Chen1-1/+1
BACO reset mode strategy is determined by latter func when calling amdgpu_ras_reset_gpu. So not to confuse audience, drop it. Signed-off-by: Guchun Chen <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-11-22drm/amdgpu/gfx10: fix out-of-bound mqd_backup array accessXiaojie Yuan1-2/+0
Fixes: 0900a9efdb7909 ("drm/amdgpu/gfx10: fix mqd backup/restore for gfx rings (v2)") Signed-off-by: Xiaojie Yuan <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-11-22drm/amdgpu/gfx10: fix mqd backup/restore for gfx rings (v2)Xiaojie Yuan1-1/+1
1. no need to allocate an extra member for 'mqd_backup' array 2. backup/restore mqd to/from the correct 'mqd_backup' array slot v2: warning fix (Alex) Signed-off-by: Xiaojie Yuan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-25drm/amdgpu: remove unused parameter in amdgpu_gfx_kiq_free_ringNirmoy Das1-2/+1
Signed-off-by: Nirmoy Das <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-03drm/amdgpu: remove set but not used variable 'pipe'yu kuai1-3/+1
Fixes gcc '-Wunused-but-set-variable' warning: rivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c: In function ‘amdgpu_gfx_graphics_queue_acquire’: drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c:234:16: warning: variable ‘pipe’ set but not used [-Wunused-but-set-variable] It is never used, so can be removed. Reported-by: Hulk Robot <[email protected]> Signed-off-by: yu kuai <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-03drm/amdgpu: add comments in ras interrupt callbackTao Zhou1-1/+6
add comments to clarify why checking GFX IP BLOCK for each ras interrupt callback Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-03drm/amdgpu: remove ih_info parameter of gfx_ras_late_initTao Zhou1-9/+7
gfx_ras_late_init can get the info by itself Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-03drm/amdgpu: add common gfx_ras_fini functionTao Zhou1-0/+15
gfx_ras_fini can be shared among all generations of gfx Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-10-03drm/amdgpu: move gfx ecc functions to generic gfx fileTao Zhou1-0/+33
gfx ras ecc common functions could be reused among all gfx generations Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-09-13drm/amdgpu/gfx: switch to amdgpu_gfx_ras_late_init helper functionHawking Zhang1-0/+49
amdgpu_gfx_ras_late_init is used to init gfx specfic ras debugfs/sysfs node and gfx specific interrupt handler. It can be shared among gfx generations Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-07-18drm/amdgpu: enable async gfx ring for navi14Xiaojie Yuan1-3/+3
Same as navi10. Signed-off-by: Xiaojie Yuan <[email protected]> Reviewed-by: Jack Xiao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-25Merge branch 'drm-next' into drm-next-5.3Alex Deucher1-1/+1
Backmerge drm-next and fix up conflicts due to drmP.h removal. Signed-off-by: Alex Deucher <[email protected]>
2019-06-21drm/amd: add gfxoff support on navi10Kenneth Feng1-1/+3
add the gfxoff interface to navi10,it's disabled by default. Signed-off-by: Kenneth Feng <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: create mqd for gfx queues on navi10Hawking Zhang1-1/+34
mqd is the memory queue descriptor for gfx and compute. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Jack Xiao <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu/gfx10: add special unmap_queues packet for preemptionJack Xiao1-1/+2
CP introduced a special unmap_queues packet for gfx preemtion. Acked-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Jack Xiao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: Move common code to amdgpu_gfx.cHawking Zhang1-0/+47
move common code to amdgpu_gfx_enable_kcq,so this function can be shared with gfx8 and gfx9 Signed-off-by: Hawking Zhang <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: Add common gfx func Disable kcq via kiqRex Zhu1-0/+19
so can be shared with gfx8 and gfx9 Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: rename amdgpu_gfx_compute_mqd_sw_initHawking Zhang1-4/+4
The function now will create mqd bos for both gfx queue and compute queue Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Jack Xiao <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: add helper function for gfx queue/bitmap transitionHawking Zhang1-6/+36
Similar to what we do for compute already. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Jack Xiao <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-20drm/amdgpu: acquire available gfx queuesHawking Zhang1-0/+24
currently, amdgpu will owns the first gfx queue of each pipe they are: me:0 pipe:0 queue:0 me:0 pipe:1 queue:0 Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Jack Xiao <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-10drm/amd: drop use of drmP.h in amdgpu/amdgpu*Sam Ravnborg1-1/+1
Drop use of drmP.h in all files named amdgpu* in drm/amd/amdgpu/ Fix fallout. Signed-off-by: Sam Ravnborg <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Cc: "David (ChunMing) Zhou" <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-03-19drm/amd/powerplay: add limit of pp_feature for smu (v3)Likun Gao1-1/+1
Move pp_feature from the struct of amd_powerplay to amdgpu_device. Add pp_feature limit for overdrive interface. v2: put pp_feature into struct amdgpu_pm. v3: merge feature_mask with pp_feature. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Suggested-by: Alex Deucher <[email protected]> Suggested-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-11-28drm/amdgpu: Use asic specific doorbell index instead of macro definitionOak Zeng1-1/+1
ASIC specific doorbell layout is used instead of enum definition Signed-off-by: Oak Zeng <[email protected]> Suggested-by: Felix Kuehling <[email protected]> Suggested-by: Alex Deucher <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-11-09drm/amdgpu: separate amdgpu_rlc into a single fileLikun Gao1-0/+1
Separate the function and struct of RLC from the file of GFX. Abstract the function of amdgpu_gfx_rlc_fini. Signed-off-by: Likun Gao <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-10-24drm/amdgpu: Fix null point errorRex Zhu1-1/+1
need to check adev->powerplay.pp_funcs first, becasue from AI, the smu ip can be disabled by user, and the pp_handle is null in this case. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-27drm/amdgpu: Delay 100ms to enable gfx off featureRex Zhu1-2/+2
Original 500ms delay seems a bit large. Change to 100 ms suggested by Christian. Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-27drm/amdgpu: move gfx definitions into amdgpu_gfx headerHuang Rui1-1/+33
Demangle amdgpu.h Signed-off-by: Huang Rui <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-27drm/amdgpu: Put enable gfx off feature to a delay threadRex Zhu1-2/+6
delay to enable gfx off feature to avoid gfx on/off frequently suggested by Alex and Evan. Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-27drm/amdgpu: Add amdgpu_gfx_off_ctrl functionRex Zhu1-0/+36
v2: 1. drop the special handling for the hw IP suggested by hawking and Christian. 2. refine the variable name suggested by Flora. This funciton as the entry of gfx off feature. we arbitrat gfx off feature enable/disable in this function. Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-29drm/amdgpu: use queue 0 for kiq ringHuang Rui1-2/+6
It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN only can be issued on queue 0. Signed-off-by: Huang Rui <[email protected]> Acked-by: Hawking Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-12-18drm/amdgpu: rename amdgpu_wb_* functionsAlex Deucher1-2/+2
add device for consistency. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-10-19drm/amdgpu: busywait KIQ register accessing (v4)pding1-1/+1
Register accessing is performed when IRQ is disabled. Never sleep in this function. Known issue: dead sleep in many use cases of index/data registers. v2: - wrap polling fence functions. - don't trigger IRQ for polling in case of wrongly fence signal. v3: - handle wrap round gracefully. - add comments for polling function v4: - don't return negative timeout confused with error code Signed-off-by: pding <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: add option for force enable multipipe policy for computeAndres Rodriguez1-0/+6
Useful for testing the effects of multipipe compute without recompiling. Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: use multipipe compute policy on non PL11 asicsAndres Rodriguez1-2/+12
A performance regression for OpenCL tests on Polaris11 had this feature disabled for all asics. Instead, disable it selectively on the affected asics. Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amdgpu/sriov:alloc KIQ MQD in VRAM(v2)Monk Liu1-1/+6
this way after KIQ MQD released in drv unloading, CPC can still let KIQ access this MQD thus RLCV SAVE_VF will not fail v2: always use VRAM domain for KIQ MQD no matter BM or SRIOV Signed-off-by: Monk Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-07-14drm/amdgpu/gfx: keep all compute queues on the same pipeAlex Deucher1-1/+2
Spreading them causes performance regressions using compute queues on Polaris 11. Cc: Jim Qu <[email protected]> Acked-by: Jim Qu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-06-15drm/amd/amdgpu: Rename KIQ ring to avoid spacesTom St Denis1-1/+1
Swap space for underscore in ring name. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-06-07drm/amdgpu/gfx: consolidate mqd buffer setup codeAlex Deucher1-0/+66
It was duplicated across multiple generations. Reviewed-by: Alex Xie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-06-07drm/amdgpu/gfx: move more common KIQ code to amdgpu_gfx.cAlex Deucher1-0/+103
Lots more common stuff. Reviewed-by: Alex Xie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.