Under xgmi setup,some sysfs fail to create for the second time of kmd
driver loading. It's due to sysfs nodes are not removed appropriately
in the last unlod time.

Changes of this patch:
1. remove sysfs for dev_attr_xgmi_error
2. remove sysfs_link adev->dev->kobj with target name.
   And it only needs to be removed once for a xgmi setup
3. remove sysfs_link hive->kobj with target name

In amdgpu_xgmi_remove_device:
1. amdgpu_xgmi_sysfs_rem_dev_info needs to be run per device
2. amdgpu_xgmi_sysfs_destroy needs to be run on the last node of
device.

v2: initialize array with memset
Signed-off-by: NJack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

SCRATCH2 is used to keep decode wptr as a workaround
which fix a hardware DPG decode wptr update bug for
vcn2.5 beforehand.
Signed-off-by: NJames Zhu <James.Zhu@amd.com>
Reviewed-by: NLeo Liu <leo.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Remove JPEG_ENC_MASK from clock ungating since MJPEG encoder
hasn't been support yet.
Signed-off-by: NJames Zhu <James.Zhu@amd.com>
Reviewed-by: NLeo Liu <leo.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[Why]
At bringup we want to be able to disable various power features.

[How]
These features are already exposed as dc_debug_options and exercised
on other OSes. Create a new dc_debug_mask module parameter and expose
relevant bits, in particular
 * DC_DISABLE_PIPE_SPLIT
 * DC_DISABLE_STUTTER
 * DC_DISABLE_DSC
 * DC_DISABLE_CLOCK_GATING
Signed-off-by: NHarry Wentland <harry.wentland@amd.com>
Reviewed-by: NNicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

the amdgpu device attribute node will be created accordding to sriov vf
mode at runtime.
cleanup unnecessary sriov check in attribute operation function.
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When this flag is set in the CS IB flags, it causes
a memory cache flush of the GFX.

v2:
Move new flag to drm_amdgpu_cs_chunk_ib.flags
Bump up UAPI version
Remove condition on job != null to emit mem_sync
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NLuben Tuikov <luben.tuikov@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Compute IBs need this too.

v2: split out version bump
v3: squash in emit frame count fixes
Signed-off-by: NMarek Olšák <marek.olsak@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Implement the .mem_sync hook defined earlier.

v2: Rename functions
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NLuben Tuikov <luben.tuikov@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Used to flush and invalidate various caches.

v2: Rename function hook
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NLuben Tuikov <luben.tuikov@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

unified amdgpu device attribute node functions:
1. add some helper functions to create amdgpu device attribute node.
2. create device node according to device attr flags on different VF mode.
3. rename some functions name to adapt a new interface.

v2:
1. remove ATTR_STATE_DEAD, ATTR_STATE_ALIVE enum.
2. rename callback function perform to attr_update.
3. modify some variable names
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

the swsmu or powerplay(hwmgr) need to handle task according to different VF mode,
this function to help query vf mode.

vf mode:
1. SRIOV_VF_MODE_BARE_METAL: the driver work on host  OS (PF)
2. SRIOV_VF_MODE_ONE_VF    : the driver work on guest OS with one VF
3. SRIOV_VF_MODE_MULTI_VF  : the driver work on guest OS with multi VF
Signed-off-by: NKevin Wang <kevin1.wang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When GPU got timeout, it would notify an interested part
of an opportunity to dump info before actual GPU reset.

A usermode app would open 'autodump' node under debugfs system
and poll() for readable/writable. When a GPU reset is due,
amdgpu would notify usermode app through wait_queue_head and give
it 10 minutes to dump info.

After usermode app has done its work, this 'autodump' node is closed.
On node closure, amdgpu gets to know the dump is done through
the completion that is triggered in release().

There is no write or read callback because necessary info can be
obtained through dmesg and umr. Messages back and forth between
usermode app and amdgpu are unnecessary.

v2: (1) changed 'registered' to 'app_listening'
    (2) add a mutex in open() to prevent race condition

v3 (chk): grab the reset lock to avoid race in autodump_open,
          rename debugfs file to amdgpu_autodump,
          provide autodump_read as well,
          style and code cleanups

v4: add 'bool app_listening' to differentiate situations, so that
    the node can be reopened; also, there is no need to wait for
    completion when no app is waiting for a dump.

v5: change 'bool app_listening' to 'enum amdgpu_autodump_state'
    add 'app_state_mutex' for race conditions:
	(1)Only 1 user can open this file node
	(2)wait_dump() can only take effect after poll() executed.
	(3)eliminated the race condition between release() and
	   wait_dump()

v6: removed 'enum amdgpu_autodump_state' and 'app_state_mutex'
    removed state checking in amdgpu_debugfs_wait_dump
    Improve on top of version 3 so that the node can be reopened.

v7: move reinit_completion into open() so that only one user
    can open it.

v8: remove complete_all() from amdgpu_debugfs_wait_dump().
Signed-off-by: NJiange Zhao <Jiange.Zhao@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Disable XGMI link power down prior to issuing a XGMI RAS error
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NJohn Clements <john.clements@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NJohn Clements <john.clements@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The variable ret is being initializeed with a value that is never read
and it is being updated later with a new value. The initialization
is redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

There is no need to use amdgpu_mm_wreg_mmio_rlc()
during initialization time because this interface
is only designed for debugfs case to access the
registers which are only permitted by RLCG during
run-time. Therefore, turn back rlcg write for gfx_v10.
If we not turn back it, it will raise amdgpu load failure.
[   54.904333] amdgpu: SMU driver if version not matched
[   54.904393] amdgpu: SMU is initialized successfully!
[   54.905971] [drm] kiq ring mec 2 pipe 1 q 0
[   55.115416] amdgpu 0000:00:06.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring gfx_0.0.0 test failed (-110)
[   55.118877] [drm:amdgpu_device_init [amdgpu]] *ERROR* hw_init of IP block <gfx_v10_0> failed -110
[   55.126587] amdgpu 0000:00:06.0: amdgpu_device_ip_init failed
[   55.133466] amdgpu 0000:00:06.0: Fatal error during GPU init
Signed-off-by: NYintian Tao <yttao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add this for gfx10 and gfx9.

v2: Fix identation
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NLuben Tuikov <luben.tuikov@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fix the following gcc warning:

drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c:65:18: warning: ‘crtc_offsets’
defined but not used [-Wunused-const-variable=]
 static const u32 crtc_offsets[6] =
                  ^~~~~~~~~~~~
Reported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NJason Yan <yanaijie@huawei.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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: NTom St Denis <tom.stdenis@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We only need to set DPM_FLAG_NEVER_SKIP for the legacy ATPX
BOCO case.  D3cold and BACO work as expected.
Acked-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The core handles this for us.
Acked-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We should be checking whether the driver enabled runtime pm
rather than whether the asic supports BOCO or BACO.  That said
in general they are equivalent unless the user has disabled
runpm or it has been disabled for a specific asic.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The pci core handles this for us in pci_pm_init.
Acked-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Same as gfx9.  This allows us to kill the waves for hung
shaders.
Acked-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Create sysfs file using attributes.
Signed-off-by: NNirmoy Das <nirmoy.das@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

BACO is needed to support hibernate on Navi1X.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

physical_node_id * node_segment_size should be the
dram_base_address for current gpu node in xgmi config
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drop IP specific psp function for rlc autoload since
the autoload_supported was introduced to mark ASICs
that support rlc_autoload
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

cure posion command was replaced by ras recovery
solution and was not a formal command supported
by ras ta anymore
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

TRIGGER_ERROR is common ras ta command for all the
ASICs that support RAS feature. switch to common helper
to avoid duplicate implementation per IP generation
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

get_hive_id/get_node_id/get_topology_info/set_topology_info
are common xgmi command supported by TA for all the ASICs
that support xgmi link. They should be implemented as common
helper functions to avoid duplicated code per IP generation
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

There is DEVICE_ATTR mechanism in separate attribute define.
So this change is to use attr array, also use
sysfs_create_files in init function & sysfs_remove_files in
fini function.
This maybe make the code a bit readable.
Signed-off-by: NBernard Zhao <bernard@vivo.com>

Changes since V1:
*Use DEVICE_ATTR mechanism

Link for V1:
*https://lore.kernel.org/patchwork/patch/1228076/

V2: make array const to fix build errors
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Invoke sequence should abort when ras interrupt is detected before reading TA host shared memory
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NJohn Clements <john.clements@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Releasing the AMDGPU BO ref directly leads to problems when BOs were
exported as DMA bufs. Releasing the GEM reference makes sure that the
AMDGPU/TTM BO is not freed too early.

Also take a GEM reference when importing BOs from DMABufs to keep
references to imported BOs balances properly.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Tested-by: NAlex Sierra <alex.sierra@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Sierra <alex.sierra@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We set the fb smem pointer to the offset into the BAR, so keep
the fbdev bo in vram.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=207581
Fixes: 6c8d74ca ("drm/amdgpu: Enable scatter gather display support")
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Otherwise, MGCG/MGLS will be left enabled.
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>

This should speed up debugging VRAM access a lot.

v2: add HDP flush/invalidate

Unrevert: RAS issue at root of the issue has been addressed
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Acked-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NKent Russell <kent.russell@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

After the structure was padded to 1024 bytes, it is no longer
suitable for being a local variable, as the function surpasses
the warning limit for 32-bit architectures:

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:587:5: error: stack frame size of 1072 bytes in function 'amdgpu_ras_feature_enable' [-Werror,-Wframe-larger-than=]
int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
    ^

Use kzalloc() instead to get it from the heap.

Fixes: a0d25482 ("drm/amdgpu: update RAS TA to Host interface")
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This uses backlight_device_set_brightness() to set the brightness
level requested via ATIF.
Signed-off-by: NAndriy Gapon <avg@FreeBSD.org>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>