summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
AgeCommit message (Collapse)Author
2023-06-09drm/amdgpu/gfx8: always restore kcq MQDsAlex Deucher
Always restore the MQD not just when we do a reset. This allows us to move the MQD to VRAM if we want. v2: always reset ring pointer as well (Christian) Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm:amd:amdgpu: Fix missing bo unlock in failure pathSukrut Bellary
smatch warning - inconsistent handling of buffer object reserve and unreserve. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Sukrut Bellary <sukrut.bellary@linux.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-04-18drm/amdgpu: add xcc index argument to rlc safe_mode func (v4)Le Ma
v1: To support multple XCD case (Le) v2: unify naming style (Le) v3: apply the changes to gc v11_0 (Hawking) v4: apply the changes to gc SOC21 (Morris) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-04-18drm/amdgpu: add xcc index argument to select_sh_se function v2Le Ma
v1: To support multiple XCD case (Le) v2: introduce xcc index to gfx_v11_0_select_sh_se (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-04-18drm/amdgpu: add multi-xcc support to amdgpu_gfx interfaces (v4)Le Ma
v1: Modify kiq_init/fini, mqd_sw_init/fini and enable/disable_kcq to adapt to multi-die case. Pass 0 as default to all asics with single xcc (Le) v2: squash commits to avoid breaking the build (Le) v3: unify naming style (Le) v4: apply the changes to gc v11_0 (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-04-18drm/amdgpu: move queue_bitmap to an independent structure (v3)Le Ma
To allocate independent queue_bitmap for each XCD, then the old bitmap policy can be continued to use with a clear logic. Use mec_bitmap[0] as default for all non-GC 9.4.3 IPs. v2: squash commits to avoid breaking the build v3: unify naming style Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-04-18drm/amdgpu: convert gfx.kiq to array type (v3)Le Ma
v1: more kiq instances are a available in SOC (Le) v2: squash commits to avoid breaking the build (Le) v3: make the conversion for gfx/mec v11_0 (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-01-17drm/amdgpu: Add a missing tabDan Carpenter
This tab was deleted accidentally and triggers a Smatch warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:1006 gfx_v8_0_init_microcode() warn: inconsistent indenting Add it back. Fixes: 0aaafb7359d2 ("drm/amd: Use `amdgpu_ucode_*` helpers for GFX8") Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-01-10drm/amd: Use `amdgpu_ucode_*` helpers for GFX8Mario Limonciello
The `amdgpu_ucode_request` helper will ensure that the return code for missing firmware is -ENODEV so that early_init can fail. The `amdgpu_ucode_release` helper is for symmetry on unloading. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-01-03drm/amdgpu: use VRAM|GTT for a bunch of kernel allocationsChristian König
Technically all of those can use GTT as well, no need to force things into VRAM. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-11-04drm/amdgpu: fix for suspend/resume sequence under sriovVictor Zhao
- clear kiq ring after suspend/resume under sriov to aviod kiq ring test failure - update irq after resume to fix kiq interrput loss Signed-off-by: Victor Zhao <Victor.Zhao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-05-26drm/amdgpu/gfx: fix typos in commentsJulia Lawall
Spelling mistakes (triple letters) in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-05-26drm/amdgpu: Set CP_HQD_PQ_CONTROL.RPTR_BLOCK_SIZE correctlyHaohui Mai
Remove the accidental shifts on the values of RPTR_BLOCK_SIZE in gfx_v8-v11. The bug essentially always programs the corresponding fields to zero instead of the correct value. The hardware clamps the min value to 5 so this resulted in a value of 5 being programmed. Signed-off-by: Haohui Mai <ricetons@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-05-06drm/amdgpu: nuke dynamic gfx scratch reg allocationChristian König
It's over a decade ago that this was actually used for more than ring and IB tests. Just use the static register directly where needed and nuke the now useless infrastructure. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Lang Yu <Lang.Yu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-05-04drm/amdgpu: use ring structure to access rptr/wptr v2Jack Xiao
Use ring structure to access the cpu/gpu address of rptr/wptr. v2: merge gfx10/sdma5/sdma5.2 patches Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-04-11drm/amdgpu: Fix incorrect enum typeGrigory Vasilyev
Instead of the 'amdgpu_ring_priority_level' type, the 'amdgpu_gfx_pipe_priority' type was used, which is an error when setting ring priority. This is a minor error, but may cause problems in the future. Instead of AMDGPU_RING_PRIO_2 = 2, we can use AMDGPU_RING_PRIO_MAX = 3, but AMDGPU_RING_PRIO_2 = 2 is used for compatibility with AMDGPU_GFX_PIPE_PRIO_HIGH = 2, and not change the behavior of the code. Signed-off-by: Grigory Vasilyev <h0tc0d3@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-04-08drm/amdgpu: expand cg_flags from u32 to u64Evan Quan
With this, we can support more CG flags. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-11-05drm/amdgpu: correctly toggle gfx on/off around RLC_SPM_* register accessEvan Quan
As part of the ib padding process, accessing the RLC_SPM_* register may trigger gfx hang. Since gfxoff may be already kicked during the whole period. To address that, we manually toggle gfx on/off around the RLC_SPM_* register access. This can resolve the gfx hang issue observed on running Talos with RDP launched in parallel. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Guchun Chen <guchun.chen@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-08-05drm/amdgpu: Put MODE register in wave debug infoJoseph Greathouse
Add the MODE register into the per-wave debug information. This register holds state such as FP rounding and denorm modes, which exceptions are enabled, and active clamping modes. Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-04-09drm/amdgpu: add the sched_score to amdgpu_ring_initChristian König
Allow separate ring to share the same scheduler score. No functional change. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-and-Tested-by: Leo Liu <leo.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-03-23drm/amdgpu: Replace in_task() in gfx_v8_0_parse_sq_irq()Sebastian Andrzej Siewior
gfx_v8_0_parse_sq_irq() is using in_task() to distinguish if it is invoked from a workqueue worker or directly from the interrupt handler. The usage of in_interrupt() in drivers is phased out and Linus clearly requested that code which changes behaviour depending on context should either be separated or the context be conveyed in an argument passed by the caller, which usually knows the context. gfx_v8_0_parse_sq_irq() is invoked directly either from a worker or from the interrupt service routine. The worker is only bypassed if the worker is already busy. Add an argument `from_wq' to gfx_v8_0_parse_sq_irq() which is true if invoked from the worker. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-02-09drm/amdgpu: enable wave limit on non high prio cs pipesNirmoy Das
To achieve the best QoS for high priority compute jobs it is required to limit waves on other compute pipes as well. This patch will set min value in non high priority mmSPI_WCL_PIPE_PERCENT_CS[0-3] registers to minimize the impact of normal/low priority compute jobs over high priority compute jobs. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-02-09drm/amdgpu: add wave limit functionality for gfx8,9Nirmoy Das
Wave limiting can be use to load balance high priority compute jobs along with gfx jobs. When enabled, this will reserve ~75% of waves for compute jobs. We do not need this from gfx10 onwards because >=gfx10 has asynchronous compute tunneling to replace wave limit requirement. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-02-09drm/amdgpu: enable only one high prio compute queueNirmoy Das
For high priority compute to work properly we need to enable wave limiting on gfx pipe. Wave limiting is done through writing into mmSPI_WCL_PIPE_PERCENT_GFX register. Enable only one high priority compute queue to avoid race condition between multiple high priority compute queues writing that register simultaneously. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-12-08drm/amdgpu: use AMDGPU_NUM_VMID when possibleNirmoy Das
Replace hardcoded vmid number with AMDGPU_NUM_VMID macro. 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>
2020-12-01drm/amd/amdgpu/gfx_v8_0: Functions must follow directly after their headersLee Jones
Fixes the following W=1 kernel build warning(s): drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3698: warning: Excess function parameter 'adev' description in 'DEFAULT_SH_MEM_BASES' Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Sumit Semwal <sumit.semwal@linaro.org> Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Lee Jones <lee.jones@linaro.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-11-13drm/amdgpu: fix compute queue priority if num_kcq is less than 4Nirmoy Das
Compute queues are configurable with module param, num_kcq. amdgpu_gfx_is_high_priority_compute_queue was setting 1st 4 queues to high priority queue leaving a null drm scheduler in adev->gpu_sched[hw_ip]["normal_prio"].sched if num_kcq < 5. This patch tries to fix it by alternating compute queue priority between normal and high priority. Fixes: 33abcb1f5a1719b1c (drm/amdgpu: set compute queue priority at mqd_init) Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-11-02drm/amdgpu/gfx: improve code indentation and alignmentDeepak R Varma
General code indentation and alignment changes such as replace spaces by tabs or align function arguments as per the coding style guidelines. Issue reported by checkpatch script. Signed-off-by: Deepak R Varma <mh12gx2825@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-10-27drm/amdgpu: correct CG_ACLK_CNTL settingEvan Quan
Correct polaris CG_ACLK_CNTL setting. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-10-16drm/amdgpu: move amdgpu_num_kcq handling to a helperAlex Deucher
Add a helper so we can set per asic default values. Also, the module parameter is currently clamped to 8, but clamp it per asic just in case some asics have different limits in the future. Enable the option on gfx6,7 as well for consistency. Acked-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-09-08Merge tag 'amd-drm-next-5.10-2020-09-03' of ↵Dave Airlie
git://people.freedesktop.org/~agd5f/linux into drm-next amd-drm-next-5.10-2020-09-03: amdgpu: - RAS fixes - Sienna Cichlid updates - Navy Flounder updates - DCE6 (SI) support in DC - Enable plane rotation - Rework pre-OS vram reservation handling during driver init - Add standard interface to dump GPU metrics table from SMU - Rework tiling and tmz state handling in atomic commits - Pstate fixes - Add voltage and power hwmon interfaces for renoir - SW CTF fixes - S/G display fix for Raven - Print client strings for vmfaults for vega and newer - Manual fan control fixes - Display updates - Reorg power management directory structure - Misc bug fixes - Misc code cleanups amdkfd: - Topology fixes - Add SMI events for thermal throttling and GPU resets radeon: - switch from pci_* to dma_* for dma allocations - PLL fix Scheduler: - Clean up priority levels UAPI: - amdgpu INFO IOCTL query update for TMZ state https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6049 - amdkfd SMI event interface updates https://github.com/RadeonOpenCompute/rocm_smi_lib/tree/therm_thrott From: Alex Deucher <alexdeucher@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200903222921.4152-1-alexander.deucher@amd.com
2020-08-24drm/amdgpu: refine codes to avoid reentering GPU recoveryDennis Li
if other threads have holden the reset lock, recovery will fail to try_lock. Therefore we introduce atomic hive->in_reset and adev->in_gpu_reset, to avoid reentering GPU recovery. v2: drop "? true : false" in the definition of amdgpu_in_reset Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Dennis Li <Dennis.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-08-23treewide: Use fallthrough pseudo-keywordGustavo A. R. Silva
Replace the existing /* fall through */ comments and its variants with the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary fall-through markings when it is the case. [1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
2020-08-14drm/amd/powerplay: drop unnecessary pp_funcs checkerEvan Quan
It's redundant. Also, the callers should not care about the implementation details. Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-08-14drm/amd/powerplay: optimize amdgpu_dpm_set_clockgating_by_smu() implementationEvan Quan
Cover the implementation details from outside(of power part). Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-08-14drm/amdgpu: revert "fix system hang issue during GPU reset"Christian König
The whole approach wasn't thought through till the end. We already had a reset lock like this in the past and it caused the same problems like this one. Completely revert the patch for now and add individual trylock protection to the hardware access functions as necessary. This reverts commit df9c8d1aa278c435c30a69b8f2418b4a52fcb929. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-08-04drm/amdgpu: introduce a new parameter to configure how many KCQ we want(v5)Monk Liu
what: the MQD's save and restore of KCQ (kernel compute queue) cost lots of clocks during world switch which impacts a lot to multi-VF performance how: introduce a paramter to control the number of KCQ to avoid performance drop if there is no kernel compute queue needed notes: this paramter only affects gfx 8/9/10 v2: refine namings v3: choose queues for each ring to that try best to cross pipes evenly. v4: fix indentation some cleanupsin the gfx_compute_queue_acquire() v5: further fix on indentations more cleanupsin gfx_compute_queue_acquire() TODO: in the future we will let hypervisor driver to set this paramter automatically thus no need for user to configure it through modprobe in virtual machine Signed-off-by: Monk Liu <Monk.Liu@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>
2020-07-27drm/amdgpu: fix system hang issue during GPU resetDennis Li
when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover, the atomic adev->in_gpu_reset and hive->in_reset are used to avoid re-entering GPU recovery. During GPU reset and resume, it is unsafe that other threads access GPU, which maybe cause GPU reset failed. Therefore the new rw_semaphore adev->reset_sem is introduced, which protect GPU from being accessed by external threads during recovery. v2: 1. add rwlock for some ioctls, debugfs and file-close function. 2. change to use dqm->is_resetting and dqm_lock for protection in kfd driver. 3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid re-enter GPU recovery for the same GPU hang. v3: 1. change back to use adev->reset_sem to protect kfd callback functions, because dqm_lock couldn't protect all codes, for example: free_mqd must be called outside of dqm_lock; [ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019 [ 1230.177221] Call Trace: [ 1230.178249] dump_stack+0x98/0xd5 [ 1230.179443] amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu] [ 1230.180673] gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu] [ 1230.181882] amdgpu_gart_unbind+0xa9/0xe0 [amdgpu] [ 1230.183098] amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu] [ 1230.184239] ? ttm_bo_put+0x171/0x5f0 [ttm] [ 1230.185394] ttm_tt_unbind+0x21/0x40 [ttm] [ 1230.186558] ttm_tt_destroy.part.12+0x12/0x60 [ttm] [ 1230.187707] ttm_tt_destroy+0x13/0x20 [ttm] [ 1230.188832] ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm] [ 1230.189979] ttm_bo_put+0x1be/0x5f0 [ttm] [ 1230.191230] amdgpu_bo_unref+0x1e/0x30 [amdgpu] [ 1230.192522] amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu] [ 1230.193833] free_mqd+0x25/0x40 [amdgpu] [ 1230.195143] destroy_queue_cpsch+0x1a7/0x270 [amdgpu] [ 1230.196475] pqm_destroy_queue+0x105/0x260 [amdgpu] [ 1230.197819] kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu] [ 1230.199154] kfd_ioctl+0x277/0x500 [amdgpu] [ 1230.200458] ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu] [ 1230.201656] ? tomoyo_file_ioctl+0x19/0x20 [ 1230.202831] ksys_ioctl+0x98/0xb0 [ 1230.204004] __x64_sys_ioctl+0x1a/0x20 [ 1230.205174] do_syscall_64+0x5f/0x250 [ 1230.206339] entry_SYSCALL_64_after_hwframe+0x49/0xbe 2. remove try_lock and introduce atomic hive->in_reset, to avoid re-enter GPU recovery. v4: 1. remove an unnecessary whitespace change in kfd_chardev.c 2. remove comment codes in amdgpu_device.c 3. add more detailed comment in commit message 4. define a wrap function amdgpu_in_reset v5: 1. Fix some style issues. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Suggested-by: Christian König <christian.koenig@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com> Suggested-by: Luben Tukov <luben.tuikov@amd.com> Signed-off-by: Dennis Li <Dennis.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-02drm/amdgpu: Clean up KFD VMID assignmentFelix Kuehling
The KFD VMID assignment was hard-coded in a few places. Consolidate that in a single variable adev->vm_manager.first_kfd_vmid. The value is still assigned in gmc-ip-version-specific code. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-01drm/amdgpu: label internally used symbols as staticNirmoy Das
Used sparse(make C=1) to find these loose ends. v2: removed unwanted extra line Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-18drm/amdgpu: apply AMDGPU_IB_FLAG_EMIT_MEM_SYNC to compute IBs too (v3)Marek Olšák
Compute IBs need this too. v2: split out version bump v3: squash in emit frame count fixes Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-18drm/amdgpu: Add mem_sync implementation for all the ASICs.Andrey Grodzovsky
Implement the .mem_sync hook defined earlier. v2: Rename functions Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Luben Tuikov <luben.tuikov@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-23drm/amdgpu: request reg_val_offs each kiq read regYintian Tao
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 <yttao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-22drm/amdgpu: change how we update mmRLC_SPM_MC_CNTLChristian König
In pp_one_vf mode avoid the extra overhead and read/write the registers without the KIQ. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Acked-by: Yintian Tao <yintian.tao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-09drm/amdgpu: rework sched_list generationNirmoy Das
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: stop disable the scheduler during HW finiChristian König
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 pan
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>
2020-03-09drm/amdgpu: remove unused functionsNirmoy Das
AMDGPU statically sets priority for compute queues at initialization so remove all the functions responsible for changing compute queue priority dynamically. 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>
2020-03-09drm/amdgpu: set compute queue priority at mqd_initNirmoy Das
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 <nirmoy.das@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-05drm/amdgpu: fix IB test MCBP bugMonk Liu
1)for gfx IB test we shouldn't insert DE meta data 2)we should make sure IB test finished before we send event 3 to hypervisor otherwise the IDLE from event 3 will preempt IB test, which is not designed as a compatible structure for MCBP Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-04-02 09:28:44 +0000