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: NXiaojie Yuan <xiaojie.yuan@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

flush/cancel delayed works before doing finalization
to avoid concurrently requests.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

sysfs interface to read pcie speed&width info on navi1x.

v2: fix warning (trivial)
Signed-off-by: NKenneth Feng <kenneth.feng@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[Why]
On Navi10, and presumably arcterus, updating pp_table via sysfs would
not re-scale the maximum possible power limit one can set. On navi10,
the SMU code ignored the power percentage overdrive setting entirely,
and would not allow you to exceed the default power limit at all.

[How]
Adding a function to the SMU interface to get the pptable version of the
default power limit allows ASIC-specific code to provide the correct
maximum-settable power limit for the current pptable.

v3: fix spelling (Alex)
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NMatt Coffin <mcoffin13@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[Why]
Before this patch, navi10 overdrive settings could not be printed via
pp_od_clk_voltage

[How]
Implement printing for the overdrive settings for the following clocks
in navi10's ppt print_clk_levels implementation:

* SMU_OD_SCLK
* SMU_OD_MCLK
* SMU_OD_VDDC_CURVE
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NMatt Coffin <mcoffin13@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[Why]
Before this patch, there was no way to set the gfxclk voltage curve in
the overdrive settings for navi10 through pp_od_clk_voltage

[How]
Add the required implementation to navi10's ppt dpm table editing
implementation, similar to the vega20 implementation and interface.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NMatt Coffin <mcoffin13@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[Why]
Before this patch, there was no way to use pp_od_clk_voltage on navi

[How]
Similar to the vega20 implementation, but using the common smc_v11_0
headers, implemented the pp_od_clk_voltage API for navi10's pptable
implementation
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NMatt Coffin <mcoffin13@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

flush/cancel delayed works before doing finalization
to avoid concurrently requests.
Signed-off-by: NJesse Zhang <zhexi.zhang@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When a custom powerplay table is provided, we need to update
the OD VDDC flag to avoid AVFS being enabled when it shouldn't be.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=205393Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

xgmi, ras, hdcp and dtm ta are actually separated ucode and
need to handled case by case to upload to psp.

We support the case that ta binary have one or multiple of
them built-in. As a result, the driver should check each ta
binariy's availablity before decide to upload them to psp.

In the terminate (unload) case, the driver will check the
context readiness before perform unload activity. It's fine
to keep it as is.
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NLe Ma <Le.Ma@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When a custom powerplay table is provided, we need to update
the OD VDDC flag to avoid AVFS being enabled when it shouldn't be.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=205393Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This is to improve the performance in the compute mode
for vega10. For example, the original performance for a rocm
bandwidth test: 2G internal GPU copy, is about 99GB/s.
With the idle power features disabled dynamically, the porformance
is promoted to about 215GB/s.
Signed-off-by: NKenneth Feng <kenneth.feng@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

OD is not supported on Arcturus. Thus the
pp_od_clk_voltage sysfs interface is also not supported.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NKenneth Feng <kenneth.feng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It will cause modprobe atombios stuck problem in raven2 if it doesn't
allow direct upload save restore list from gfx driver.
So it needs to allow direct upload save restore list for raven2
temporarily.
Signed-off-by: Nchangzhu <Changfeng.Zhu@amd.com>
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Problem:
During GPU reset we call the GPU scheduler to suspend it's
thread, those two functions in amdgpu also suspend and resume
the sceduler for their needs but this can collide with GPU
reset in progress and accidently restart a suspended thread
before time.

Fix:
Serialize with GPU reset.
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>

This reverts commit 89b3d864.

We will do a proper fix in next patch.
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>

vega20 only requires all devices be set to same pstate level for low
pstate and not high.
Signed-off-by: NJonathan Kim <Jonathan.Kim@amd.com>
Reviewed-by: NEvan Quan <Evan.Quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

the asic callback function of get_pcie_replay_count is not implement on navi asic,
it will cause null pinter error when read this interface.
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NKent Russell <kent.russell@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For driver reload test, it will report "can't enable
MSI (MSI-X already enabled)".
Signed-off-by: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Explain fields like aper_base, agp_start etc. The definition
of those fields are confusing as they are from different view
(CPU or GPU). Add comments for easier understand.
Signed-off-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NAlex Deucher <Alex.Deucher@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To properly handle the option parsing ordering.
Reviewed-by: NYong Zhao <yong.zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It needs to add warning to update firmware in gfx9
in case that firmware is too old to have function to
realize dummy read in cp firmware.
Signed-off-by: Nchangzhu <Changfeng.Zhu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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: Nchangzhu <Changfeng.Zhu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Otherwise, the feature enablement will be skipped due to wrong count.

Fixes: beff74bc ("drm/amdgpu: fix a race in GPU reset with IB test (v2)")
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

fix workload bit (WORKLOAD_PPLIB_COMPUTE_BIT) map error
on vega20 and navi asic.

fix commit:
drm/amd/powerplay: add function get_workload_type_map for swsmu
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NKenneth Feng <kenneth.feng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Clarify some areas, clean up formatting, add section for
unrecoverable error handling.

v2: fix grammatical errors
Reviewed-by: NYong Zhao <yong.zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To properly handle the option parsing ordering.
Reviewed-by: NYong Zhao <yong.zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The reference to object fence is dropped at the end of the loop.
However, it is dropped again outside the loop. The reference can be
dropped immediately after calling dma_fence_wait() in the loop and
thus the dropping operation outside the loop can be removed.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NPan Bian <bianpan2016@163.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/powerplay/renoir_ppt.c:186:2: error: missing braces
around initializer [-Werror=missing-braces]
  SmuMetrics_t metrics = {0};
    ^

Fixes: 8b803170 ("drm/amd/powerplay: implement sysfs for getting dpm clock")
Signed-off-by: NRaul E Rangel <rrangel@chromium.org>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The object fence is not set to NULL after its reference is dropped. As a
result, its reference may be dropped again if error occurs after that,
which may lead to a use after free bug. To avoid the issue, fence is
explicitly set to NULL after dropping its reference.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NPan Bian <bianpan2016@163.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Using unified VBIOS has performance drop in sriov environment.
The fix is switching to another register instead.
Signed-off-by: NEric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It needs to add warning to update firmware in gfx9
in case that firmware is too old to have function to
realize dummy read in cp firmware.
Signed-off-by: Nchangzhu <Changfeng.Zhu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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: Nchangzhu <Changfeng.Zhu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

smu_enable_umd_pstate() will try to get the smu->mutex which was already
hold by its parent API smu_force_performance_level() on the call path.
Thus deadlock happens.
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>

P-state switch should be performed after all devices from the hive
get initialized.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Reviewed-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Added lock protection so that the p-state switch will
be guarded to be sequential. Also update the hive
pstate only all device from the hive are in the same
state.
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>

Otherwise, the feature enablement will be skipped due to wrong count.

Fixes: beff74bc ("drm/amdgpu: fix a race in GPU reset with IB test (v2)")
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

fix workload bit (WORKLOAD_PPLIB_COMPUTE_BIT) map error
on vega20 and navi asic.

fix commit:
drm/amd/powerplay: add function get_workload_type_map for swsmu
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NKenneth Feng <kenneth.feng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To fit the latest SMU firmware.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NLe Ma <Le.Ma@amd.com>
Reviewed-by: NKenneth Feng <kenneth.feng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Direct uploading save/restore list via mmio register writes breaks the security
policy. Instead, the driver should pass s&r list to psp.

For all the ASICs that use rlc v2_1 headers, the driver actually upload s&r list
twice, in non-psp ucode front door loading phase and gfx pg initialization phase.
The latter is not allowed.

VG12 is the only exception where the driver still keeps legacy approach for S&R
list uploading. In theory, this can be elimnated if we have valid srcntl ucode
for VG12.
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NCandice Li <Candice.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>