As it will destroy clear_state_obj, and also will unpin it in the
gfx_v9_0_sw_fini, so don't need to
call amdgpu_bo_free_kernel in gfx_v9_0_sw_fini, or it will have unpin warning.
Signed-off-by: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

As far as we know this was never used by userspace and so should be removed.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NMarek Olšák <marek.olsak@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

During S3/S4 bootloader will re-init ras state behind us.
Resume might fail or raise a gpu reset.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NJames Zhu <James.Zhu@amd.com>
Tested-by: NJames Zhu <James.Zhu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

During S3 test, when system wake up and resume, ras interface
is already allocated. Move workaround before ras jumps to resume
step in gfx_v9_0_ecc_late_init, and make sure workaround applied
during resume. Also remove unused mmGB_EDC_MODE clearing.
Signed-off-by: NJames Zhu <James.Zhu@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Under Vega10 SR-IOV, with new RLC's new feature, VF should call RLC
to program some registers if supported
Signed-off-by: NTrigger Huang <Trigger.Huang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For Vega10 SR-IOV VF, skip setting some regs due to:
1, host will program them
2, avoid VF register programming violations
Signed-off-by: NTrigger Huang <Trigger.Huang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

request a gpu reset if ras return EAGAIN.
we will run late init again so it is ok to do nothing this time.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When RAS is enabled, initializes the VGPRs/LDS/SGPRs and
resets EDC error counts. This is done in late_init, before
RAS TA GFX enable.
Signed-off-by: NJames Zhu <James.Zhu@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

IP initialize ras in late_init, because of the BUGs of PSP or any
other components, driver receives unexpected irqs. It is ok to add such
check anyway.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

handle ras enable on boot.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The rlc reset function is not necessary during gfx9 initialization/resume phase.
And this function would even cause rlc fw loading failed on some gfx9 ASIC.
Remove this function safely with verification well on Vega/Raven platform.
Signed-off-by: NLe Ma <le.ma@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

RLC #53815 ucode has the noise issue on 4k playback while gfxoff enabled.
Signed-off-by: NHuang Rui <ray.huang@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Tested-by: NTom St Denis <tom.stdenis@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This patch enables gfxoff and stutter mode again, since we take more testing on
raven series. For raven2 and picasso, we can enable it directly. And for raven,
we need check the RLC/SMC ucode version cannot be less than #531/0x1e45.

v2: add smc version checking for raven.
Signed-off-by: NHuang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1)
Tested-by: Likun Gao <Likun.Gao@amd.com> (v2)
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Suspend will put irq, so resume need get irq back.
And in the same time, skip other ras initialization.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

RAS ECC event will combine with GPU reset event, due to
ECC interrupts are caused by uncorrectable error that triggers
GPU reset.

v2: Fix misleading-indentation warning
v3: fix build with CONFIG_HSA_AMD disabled
Signed-off-by: NEric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Register ecc interrupts and ecc interrupt handler on gfx9.
Add ras support on gfx9

v2: squash in warning fix
Signed-off-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

GC owner suggested the setting should be applied which is missed by HW default
Signed-off-by: Nshaoyunl <shaoyun.liu@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The original change caused a regression, so revert it until the new fix
is ready.

BUG: https://bugs.freedesktop.org/show_bug.cgi?id=109650

This reverts commit 764c85fef41722db0f21558c6c2fb38bee172d19.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

CP_RB_DOORBELL_RANGE_LOWER/UPPER and CP_MEC_DOORBELL_RANGE_LOWER/UPPER
are used for waking up an idle scheduler and for power gating support.
Usually the first few doorbells in pci doorbell bar are used for RB
and all leftover for MEC. This patch fixes the incorrect settings.

Theoretically, gfx ring doorbells should come before all MEC doorbells
to be consistent with the design. However, since the doorbell
allocations are agreed by all and we are not free to change them, also
considering the kernel MEC ring doorbells which are before gfx ring
doorbells are not used often, we compromise by leaving the doorbell
allocations unchanged.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

I'm not increasing the DRM version because GDS isn't totally without bugs yet.

v2: update emit_ib_size
Signed-off-by: NMarek Olšák <marek.olsak@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Replace the last bool type parameter with a general flags parameter,
to make the last parameter be able to contain more information.

v2: drop setting need_ctx_switch = false
Reviewed-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NJack Xiao <Jack.Xiao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fix CPDMA hang in PRT mode for both VEGA10 and VEGA20
Signed-off-by: NTao Zhou <tao.zhou1@amd.com>
Tested-by: NYukun.Li <yukun1.li@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

MGCG should RLC enter into safe mode first.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fix CPDMA hang in PRT mode for both VEGA10 and VEGA20
Signed-off-by: NTao Zhou <tao.zhou1@amd.com>
Tested-by: NYukun.Li <yukun1.li@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

MGCG should RLC enter into safe mode first.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For Picasso && AM4 SOCKET board, we use picasso_rlc_am4.bin
For Picasso && FP5 SOCKET board, we use picasso_rlc.bin

Judgment method:
PCO AM4: revision >= 0xC8 && revision <= 0xCF
         or revision >= 0xD8 && revision <= 0xDF
otherwise is PCO FP5
Signed-off-by: NAaron Liu <aaron.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
Reviewed-by: Huang Rui <ray.huang at amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

ASIC specific doorbell layout is used instead of enum definition
Signed-off-by: NOak Zeng <ozeng@amd.com>
Suggested-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Suggested-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Driver shouldn't try to access any GFX registers until RLC is idle.
During the test, it took 12 seconds for RLC to clear the BUSY bit
in RLC_GPM_STAT register which is un-acceptable for driver.
As per RLC engineer, it would take RLC Ucode less than 10,000 GFXCLK
cycles to finish its critical section. In a lowest 300M enginer clock
setting(default from vbios), 50 us delay is enough.

This commit fix the hang when RLC introduce the work around for XGMI
which requires more cycles to setup more registers than normal
Signed-off-by: Nshaoyunl <shaoyun.liu@amd.com>
Acked-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Looks like a copy paste typo.
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To avoid changing the global lbpw module parameter directly.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Abstract the function of amdgpu_gfx_rlc_enter/exit_safe_mode and some part of
rlc_init to improve the reusability of RLC.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Separate the function and struct of RLC from the file of GFX.
Abstract the function of amdgpu_gfx_rlc_fini.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Put function rlc_init,rlc_fini,rlc_resume,rlc_stop,rlc_start into structure
amdgpu_rlc_funcs and change the method to call rlc function for each verssion of
GFX.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For Vega20, LBPW feature is disabled at default.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

use the point of struct amdgpu_job as the function
argument instand of vmid, so the other members of
struct amdgpu_job can be visit in emit_ib function.

v2: add a wrapper for getting the VMID
    add the job before the ib on the parameter list.
v3: refine the wrapper name
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NRex Zhu <Rex.Zhu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Consistently use the ring name instead.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We already print an error message that an IB test failed in the common
code.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Instead of hard coding the ring type in the function just never provide
a test_ib callback.

Additional to that remove the emit_ib callback to make sure the nobody
ever tries to execute an IB on the KIQ.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Move all error messages from IP specific code into the common helper.
This way we now uses the ring name in the messages instead of the index
and note which device is affected as well.

Also cleanup error handling in the IP specific code and consequently use
ETIMEDOUT when the ring test timed out.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Start using drm_gpu_scheduler.ready isntead.

v3:
Add helper function to run ring test and set
sched.ready flag status accordingly, clean explicit
sched.ready sets from the IP specific files.

v4: Add kerneldoc and rebase.
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>