summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
AgeCommit message (Collapse)AuthorFilesLines
2020-08-10drm/amdgpu: update gc golden register for arcturusshiwu.zhang1-0/+1
Update golden setting to improve performance on HPC and ML apps Signed-off-by: shiwu.zhang <shiwu.zhang@amd.com> Tested-by: gang.long <gang.long@amd.com> Reviewed-by: guchun.chen <guchun.chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-02drm/amdgpu: Clean up KFD VMID assignmentFelix Kuehling1-4/+2
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 Das1-1/+1
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>
2020-07-01drm/amdgpu/gfx9: Fix incorrect firmware size calculationLei Guo1-1/+1
[WHY] The memcpy() function copies n bytes from memory area src to memory area dest. So specify the firmware size in bytes. [How] Correct the calculation. Acked-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Lei Guo <raykwok1150@163.com> Reviewed-by: Junwei Zhang <zjunweihit@163.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-01drm/amdgpu: fix the nullptr issue as for PWR IP not existing in discovery tablePrike.Liang1-2/+2
Fixes: c1cf79ca5ced46 ("drm/amdgpu: use IP discovery table for renoir") This nullptr issue should be specific on the Renoir series during try access the PWR_MISC_CNTL_STATUS when PWR IP not been detected by discovery table. Moreover the PWR IP not existing in Renoir series is expected therefore just avoid access PWR register in Renoir series. Signed-off-by: Prike.Liang <Prike.Liang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-28drm/amdgpu: simplify raven and renoir checksAlex Deucher1-2/+2
Just check for APU. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-22drm/amdgpu: add apu flags (v2)Alex Deucher1-8/+8
Add some APU flags to simplify handling of different APU variants. It's easier to understand the special cases if we use names flags rather than checking device ids and silicon revisions. v2: rebase on latest code Acked-by: Evan Quan <evan.quan@amd.com> Acked-by: Christian König <christian.koenig@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 Olšák1-1/+3
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 Grodzovsky1-1/+22
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>
2020-05-11drm/amd/amdgpu: add raven1 part to the gfxoff quirk listTom St Denis1-0/+2
On my raven1 system (rev c6) with VBIOS 113-RAVEN-114 GFXOFF is not stable (resulting in large block tiling noise in some applications). Disabling GFXOFF via the quirk list fixes the problems for me. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-06drm/amdgpu: drop unnecessary cancel_delayed_work_sync on PG ungateEvan Quan1-9/+3
As this is already properly handled in amdgpu_gfx_off_ctrl(). In fact, this unnecessary cancel_delayed_work_sync may leave a small time window for race condition and is dangerous. Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-05-01drm/amdgpu: Changed CU reservation golden settingsOak Zeng1-2/+2
With previous golden settings, compute task can't use reserved LDS (32K) on CU0 and CU1. On 64K LDS system, if compute work group allocate more than 32K LDS, then it can't be dispatched to CU0 and CU1 because of the reservation. This enables compute task to use reserved LDS on CU0 and CU1. Signed-off-by: Oak Zeng <Oak.Zeng@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> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
2020-04-28drm/amdgpu: Fix per-IB secure flag GFX hangHuang Rui1-6/+7
Since commit "Move to a per-IB secure flag (TMZ)", we've been seeing hangs in GFX. We need to send FRAME CONTROL stop/start back-to-back, every time we flip the TMZ flag. That is, when we transition from TMZ to non-TMZ we have to send a stop with TMZ followed by a start with non-TMZ, and similarly for transitioning from non-TMZ into TMZ. This patch implements this, thus fixing the GFX hang. v1 -> v2: As suggested by Luben, and accept part of implemetation from this patch: - Put "secure" closed to the loop and use optimization - Change "secure" to bool again, and move "secure == -1" out of loop. v3: Small fixes/optimizations. Reported-and-Tested-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: Move to a per-IB secure flag (TMZ)Luben Tuikov1-14/+6
Move from a per-CS secure flag (TMZ) to a per-IB secure flag. Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: implement TMZ accessor (v3)Luben Tuikov1-1/+1
Implement an accessor of adev->tmz.enabled. Let not code around access it as "if (adev->tmz.enabled)" as the organization may change. Instead... Recruit "bool amdgpu_is_tmz(adev)" to return exactly this Boolean value. That is, this function is now an accessor of an already initialized and set adev and adev->tmz. Add "void amdgpu_gmc_tmz_set(adev)" to check and set adev->gmc.tmz_enabled at initialization time. After which one uses "bool amdgpu_is_tmz(adev)" to query whether adev supports TMZ. Also, remove circular header file include. v2: Remove amdgpu_tmz.[ch] as requested. v3: Move TMZ into GMC. Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: expand the context control interface with trust flagHuang Rui1-2/+3
This patch expands the context control function to support trusted flag while we want to set command buffer in trusted mode. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-28drm/amdgpu: expand the emit tmz interface with trusted flagHuang Rui1-3/+10
This patch expands the emit_tmz function to support trusted flag while we want to set command buffer in trusted mode. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-27drm/amdgpu: Remove unneeded semicolonZheng Bin1-1/+1
Fixes coccicheck warning: drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:2534:2-3: Unneeded semicolon Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: Zheng Bin <zhengbin13@huawei.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
2020-04-24drm/amdgpu: protect ring overrunYintian Tao1-3/+11
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 <yttao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-23drm/amdgpu: request reg_val_offs each kiq read regYintian Tao1-9/+18
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 König1-3/+10
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>
2020-04-22drm/amdgpu/gfx9: add gfxoff quirkAlex Deucher1-0/+2
Fix screen corruption with firefox. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=207171 Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-13drm/amdgpu: replace DRM prefix with PCI device info for GFX RASGuchun Chen1-20/+27
Prefix RAS message printing in GFX IP with PCI device info, which assists the debug in multiple GPU case. Signed-off-by: Guchun Chen <guchun.chen@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-09drm/amdgpu: unify fw_write_wait for new gfx9 asicsAaron Liu1-0/+2
Make the fw_write_wait default case true since presumably all new gfx9 asics will have updated firmware. That is using unique WAIT_REG_MEM packet with opration=1. Signed-off-by: Aaron Liu <aaron.liu@amd.com> Tested-by: Aaron Liu <aaron.liu@amd.com> Tested-by: Yuxian Dai <Yuxian.Dai@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-09drm/amdgpu: rework sched_list generationNirmoy Das1-6/+7
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 König1-9/+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/amd/amdgpu: Include headers for PWR and SMUIO registersTom St Denis1-7/+3
Clean up the smu10, smu12, and gfx9 drivers to use headers for registers instead of hardcoding in the C source files. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-01drm/amdgpu: implement more ib pools (v2)xinhui pan1-2/+4
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>
2020-03-31drm/amdgpu: fix hpd bo size calculation errorKevin Wang1-1/+1
the HPD bo size calculation error. the "mem.size" can't present actual BO size all time. Signed-off-by: Kevin Wang <kevin1.wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <Christian.Koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-25drm/amdgpu: fix the coverage issue to clear ArcVPGRsDennis Li1-1/+1
Set ComputePGMRSRC1.VGPRS as 0x3f to clear all ArcVGPRs. Signed-off-by: Dennis Li <Dennis.Li@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-19drm: amd: fix spelling mistake "shoudn't" -> "shouldn't"Colin Ian King1-1/+1
There are spelling mistakes in pr_err messages and a comment. Fix these. Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-19drm/amdgpu: Remove unnecessary variable shadow in gfx_v9_0_rlcg_wregNathan Chancellor1-5/+1
clang warns: drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:754:6: warning: variable 'shadow' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] if (offset == grbm_cntl || offset == grbm_idx) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:757:6: note: uninitialized use occurs here if (shadow) { ^~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:754:2: note: remove the 'if' if its condition is always true if (offset == grbm_cntl || offset == grbm_idx) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:738:13: note: initialize the variable 'shadow' to silence this warning bool shadow; ^ = 0 1 warning generated. shadow is only assigned in one condition and used as the condition for another if statement; combine the two if statements and remove shadow to make the code cleaner and resolve this warning. Fixes: 2e0cc4d48b91 ("drm/amdgpu: revise RLCG access path") Link: https://github.com/ClangBuiltLinux/linux/issues/936 Suggested-by: Joe Perches <joe@perches.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-16drm/amdgpu: revise RLCG access pathMonk Liu1-3/+96
what changed: 1)provide new implementation interface for the rlcg access path 2)put SQ_CMD/SQ_IND_INDEX to GFX9 RLCG path to let debugfs's reg_op function can access reg that need RLCG path help now even debugfs's reg_op can used to dump wave. tested-by: Monk Liu <monk.liu@amd.com> tested-by: Zhou pengju <pengju.zhou@amd.com> Signed-off-by: Zhou pengju <pengju.zhou@amd.com> Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Emily Deng <Emily.Deng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-13drm/amdgpu: add codes to clear AccVGPR for arcturusDennis Li1-7/+132
AccVGPRs are newly added in arcturus. Before reading these registers, they should be initialized. Otherwise edc error happens, when RAS is enabled. v2: reuse the existing logical to calculate register size Signed-off-by: Dennis Li <Dennis.Li@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-13drm/amdgpu: check GFX RAS capability before reset countersHawking Zhang1-0/+3
disallow the logical to be enabled on platforms that don't support gfx ras at this stage, like sriov skus, dgpu with legacy ras.etc Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-09drm/amdgpu: remove unused functionsNirmoy Das1-100/+0
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 Das1-0/+20
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: add reset_ras_error_count function for HDPHawking Zhang1-1/+0
HDP ras error counters are dirty ones after cold reboot Read operation is needed to reset them to 0 Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Guchun Chen <guchun.chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-05drm/amdgpu: add reset_ras_error_count function for GFXHawking Zhang1-16/+10
GFX ras error counters are dirty ones after cold reboot Read operation is needed to reset them to 0 Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Guchun Chen <guchun.chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-03-05drm/amdgpu: fix IB test MCBP bugMonk Liu1-1/+1
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>
2020-03-05drm/amdgpu: clean wptr on wb when gpu recoveryYintian Tao1-0/+1
The TDR will be randomly failed due to compute ring test failure. If the compute ring wptr & 0x7ff(ring_buf_mask) is 0x100 then after map mqd the compute ring rptr will be synced with 0x100. And the ring test packet size is also 0x100. Then after invocation of amdgpu_ring_commit, the cp will not really handle the packet on the ring buffer because rptr is equal to wptr. Signed-off-by: Yintian Tao <yttao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-28drm/amdgpu: Initialize SPM_VMID with 0xf (v2)Jacob He1-1/+18
SPM_VMID is a global resource, SPM access the video memory according to SPM_VMID. The initial valude of SPM_VMID is 0 which is used by kernel. That means UMD can overwrite the memory of VMID0 by enabling SPM, that is really dangerous. Initialize SPM_VMID with 0xf, it messes up other user mode process at most. v2: squash in indentation fix Signed-off-by: Jacob He <jacob.he@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-28drm/amdgpu/sriov: Use kiq to copy the gpu clockEmily Deng1-10/+58
For vega10 sriov, the register is blocked, use copy data command to fix the issue. v2: Rename amdgpu_kiq_read_clock to gfx_v9_0_kiq_read_clock. Signed-off-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-19drm/amdgpu: drop the non-sense firmware version check on arcturusEvan Quan1-2/+3
As the firmware versions of arcturus are different from other gfx9 ASICs. And the warning("CP firmware version too old, please update!") caused by this check can be eliminated. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-19drm/amdgpu: add is_raven_kicker judgement for raven1changzhu1-2/+9
The rlc version of raven_kicer_rlc is different from the legacy rlc version of raven_rlc. So it needs to add a judgement function for raven_kicer_rlc and avoid disable GFXOFF when loading raven_kicer_rlc. Signed-off-by: changzhu <Changfeng.Zhu@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-12drm/amdgpu/gfx9: disable gfxoff when reading rlc clockAlex Deucher1-0/+2
Otherwise we readback all ones. Fixes rlc counter readback while gfxoff is active. Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-11drm/amdgpu: correct comment to clear up the confusionGuchun Chen1-1/+6
Former comment looks to be one intended behavior in code, actually it's not. So correct it. Suggested-by: Christian König <christian.koenig@amd.com> Signed-off-by: Guchun Chen <guchun.chen@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-02-11drm/amdgpu: limit GDS clearing workaround in cold boot sequenceGuchun Chen1-3/+6
GDS clear workaround will cause gfx failure in suspend/resume case. [ 98.679559] [drm:amdgpu_device_ip_late_init [amdgpu]] *ERROR* late_init of IP block <gfx_v9_0> failed -110 [ 98.679561] PM: dpm_run_callback(): pci_pm_resume+0x0/0xa0 returns -110 [ 98.679562] PM: Device 0000:03:00.0 failed to resume async: error -110 As this workaround is specific to the HW bug of GDS's ECC error existing in cold boot up, so bypass this workaround in suspend/ resume case after booting up. Signed-off-by: Guchun Chen <guchun.chen@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-01-30drm/amdgpu: Enable DISABLE_BARRIER_WAITCNT for ArcturusJoseph Greathouse1-0/+17
In previous gfx9 parts, S_BARRIER shader instructions are implicitly S_WAITCNT 0 instructions as well. This setting turns off that mechanism in Arcturus and beyond. With this, shaders must follow the ISA guide insofar as putting in explicit S_WAITCNT operations even after an S_BARRIER. v2: Fix patch title to list component Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-01-27drm/amdgpu: attempt to enable gfxoff on more raven1 boards (v2)Alex Deucher1-4/+40
Switch to a blacklist so we can disable specific boards that are problematic. v2: make the blacklist non-raven specific. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-28 17:58:58 +0000