Host initiated VF FLR may fail if someone else is
already holding a read_lock. Change from down_write_trylock
to down_write to guarantee the reset goes through.
Signed-off-by: NVictor Skvortsov <victor.skvortsov@amd.com>
Reviewed by: Shaoyun.liu <Shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

return value form directly instead of
taking this in another redundant variable.
Reported-by: NZeal Robot <zealci@zte.com.cm>
Signed-off-by: Nchiminghao <chi.minghao@zte.com.cn>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fix the warning below:

 warning: Cannot understand  * \file amdgpu_ioc32.c
 on line 2 - I thought it was a doc line

Changes since v1:
- As suggested by Alexander Deucher:
  1. Reduce diff to minimum as this DOC section doesn't provide much
     value.
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This commit fixes the compile-time warning below:

 warning: no previous prototype for ‘amdgpu_ras_mca_query_error_status’
 [-Wmissing-prototypes]

Changes since v1:
- As suggested by Alexander Deucher:
  1. Make function static instead of adding prototype.
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For userptr bo, if adev is not in IOMMU isolation mode, RAM direct map
to GPU, multiple GPUs use same system memory dma mapping address, they
can share the original mem->bo in attachment to reduce dma address array
memory usage.
Signed-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

If host and amdgpu IOMMU is not enabled or IOMMU is pass through mode,
set adev->ram_is_direct_mapped flag which will be used to optimize
memory usage for multi GPU mappings.
Signed-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

SMU firmware expects the driver maintains error context
and doesn't interact with SMU any more when SMU errors
occurred. That will aid in debugging SMU firmware issues.

Add SMU debug option support for this request, it can be
enabled or disabled via amdgpu_smu_debug debugfs file.
Use a 32-bit mask to indicate corresponding debug modes.
Currently, only one mode(HALT_ON_ERROR) is supported.
When enabled, it brings hardware to a kind of halt state
so that no one can touch it any more in the envent of SMU
errors.

The dirver interacts with SMU via sending messages. And
threre are three ways to sending messages to SMU in current
implementation. Handle them respectively as following:

1, smu_cmn_send_smc_msg_with_param() for normal timeout cases

  Halt on any error.

2, smu_cmn_send_msg_without_waiting()/smu_cmn_wait_for_response()
for longer timeout cases

  Halt on errors apart from ETIME. Otherwise this way won't work.
  Let the user handle ETIME error in such a case.

3, smu_cmn_send_msg_without_waiting() for no waiting cases

  Halt on errors apart from ETIME. Otherwise second way won't work.

== Command Guide ==

1, enable HALT_ON_ERROR mode

 # echo 0x1 > /sys/kernel/debug/dri/0/amdgpu_smu_debug

2, disable HALT_ON_ERROR mode

 # echo 0x0 > /sys/kernel/debug/dri/0/amdgpu_smu_debug

v5:
 - Use bit mask to allow more debug features.(Evan)
 - Use WRAN() instead of BUG().(Evan)

v4:
 - Set to halt state instead of a simple hang.(Christian)

v3:
 - Use debugfs_create_bool().(Christian)
 - Put variable into smu_context struct.
 - Don't resend command when timeout.

v2:
 - Resend command when timeout.(Lijo)
 - Use debugfs file instead of module parameter.
Signed-off-by: NLang Yu <lang.yu@amd.com>
Reviewed-by: NLijo Lazar <lijo.lazar@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It is useful to maintain error context when debugging
SW/FW issues. Introduce amdgpu_device_halt() for this
purpose. It will bring hardware to a kind of halt state,
so that no one can touch it any more.

Compare to a simple hang, the system will keep stable
at least for SSH access. Then it should be trivial to
inspect the hardware state and see what's going on.

v2:
 - Set adev->no_hw_access earlier to avoid potential crashes.(Christian)
Suggested-by: NChristian Koenig <christian.koenig@amd.com>
Suggested-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: NLang Yu <lang.yu@amd.com>
Reviewed-by: NChristian Koenig <christian.koenig@amd.co>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

in case they are not avaiable in early phase
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>

Leave this bit as hardware default setting
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

should count on GC IP base address
Signed-off-by: NLe Ma <le.ma@amd.com>
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

read and authenticate ip discovery binary getting from
vram first, if it is not valid, read and authenticate
the one getting from file
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To be used to check ip discovery binary signature
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

add _from_vram in the funciton name to diffrentiate
the one used to read from file
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

To be used when ip_discovery binary is not carried by vbios
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Guest OS will setup VCN instance 1 which is disabled as an enabled instance and
execute initialization work on it, but this causes VCN ib ring test failure
on the disabled VCN instance during modprobe:

amdgpu 0000:00:08.0: amdgpu: ring vcn_enc_1.0 uses VM inv eng 5 on hub 1
amdgpu 0000:00:08.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on vcn_dec_0 (-110).
amdgpu 0000:00:08.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on vcn_enc_0.0 (-110).
[drm:amdgpu_device_delayed_init_work_handler [amdgpu]] *ERROR* ib ring test failed (-110).

v2: drop amdgpu_discovery_get_vcn_version and rename sriov_config to
vcn_config
v3: modify VCN's revision in SR-IOV and bare-metal

Fixes: baf3f8f3 ("drm/amdgpu: handle SRIOV VCN revision parsing")
Signed-off-by: NLeslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: NLijo Lazar <lijo.lazar@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fix following warning in SRIOV during modprobe:

amdgpu 0000:00:08.0: GFX9+ requires FB check based on format modifier
WARNING: CPU: 0 PID: 1023 at drivers/gpu/drm/amd/amdgpu/amdgpu_display.c:1150 amdgpu_display_framebuffer_init+0x8e7/0xb40 [amdgpu]
Signed-off-by: NLeslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We found some headaches on ASICs don't need that,
so remove that for them.
Suggested-by: NLijo Lazar <lijo.lazar@amd.com>
Signed-off-by: NLang Yu <lang.yu@amd.com>
Reviewed-by: NKevin Wang <kevinyang.wang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Remove not unique timestamp WARNING as same timestamp interrupt happens
on some chips,

Drain fault need to wait for the processed_timestamp to be truly greater
than the checkpoint or the ring to be empty to be sure no stale faults
are handled.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1818Signed-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This fixes the warning below by changing the prototype to a location
that's actually included by the .c files that call
amdgpu_kms_compat_ioctl:

 warning: no previous prototype for ‘amdgpu_kms_compat_ioctl’
 [-Wmissing-prototypes]
 37 | long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
    |      ^~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This fixes warnings caused by global functions lacking prototypes:, such as:

 warning: no previous prototype for 'dcn303_hw_sequencer_construct'
 [-Wmissing-prototypes]
 12 | void dcn303_hw_sequencer_construct(struct dc *dc)
    |      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 ...
 warning: no previous prototype for ‘amdgpu_has_atpx’
 [-Wmissing-prototypes]
 76 | bool amdgpu_has_atpx(void) {
    |      ^~~~~~~~~~~~~~~
Reviewed-by: NRodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This turns previously global functions into static, thus removing
compile-time warnings such as:

 warning: no previous prototype for 'amdgpu_vkms_output_init' [-Wmissing-prototypes]
 399 | int amdgpu_vkms_output_init(struct drm_device *dev,
     |     ^~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This fixes various warnings relating to erroneous docstring syntax, of
which some are listed below:

 warning: Function parameter or member 'adev' not described in
 'amdgpu_atomfirmware_ras_rom_addr'
 ...
 warning: expecting prototype for amdgpu_atpx_validate_functions().
 Prototype was for amdgpu_atpx_validate() instead
 ...
 warning: Excess function parameter 'mem' description in 'amdgpu_preempt_mgr_new'
 ...
 warning: Cannot understand  * @kfd_get_cu_occupancy - Collect number of
 waves in-flight on this device
 ...
 warning: This comment starts with '/**', but isn't a kernel-doc
 comment. Refer Documentation/doc-guide/kernel-doc.rst
Signed-off-by: NIsabella Basso <isabbasso@riseup.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For the ASIC has big FB, it need more time to clear FB during reset.
This change extended SRIOV VF waiting reset completion timeout from 5s
to 10s.
Signed-off-by: NZhigang Luo <zhigang.luo@amd.com>
Acked-by: NShaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For SRIOV VF, the XGMI topology was not recovered after reset. This
change added code to SRIOV VF reset function to update XGMI topology
for SRIOV VF after reset.
Signed-off-by: NZhigang Luo <zhigang.luo@amd.com>
Reviewed-by: NShaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For SRIOV VF, XGMI was not initialized in PSP during recover. This change
added PSP XGMI initialization for SRIOV VF during recover.
Signed-off-by: NZhigang Luo <zhigang.luo@amd.com>
Reviewed-by: NShaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

On SRIOV, host driver can support FLR(function level reset) on individual VF
within the hive which might bring the individual device back to normal without
the necessary to execute the hive reset. If the FLR failed , host driver will
trigger the hive reset, each guest VF will get reset notification before the
real hive reset been executed. The VF device can handle the reset request
individually in it's reset work handler.

This change updated gpu recover sequence to skip reset other device in
the same hive for SRIOV VF.
Signed-off-by: NZhigang Luo <zhigang.luo@amd.com>
Reviewed-by: NShaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The RAS poison mode is enabled by default on the platform.
Signed-off-by: NTao Zhou <tao.zhou1@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Once EDID is parsed, the monitor HDMI support information is available
through drm_display_info.is_hdmi. The amdgpu driver still calls
drm_detect_hdmi_monitor() to retrieve the same information, which
is less efficient. Change to drm_display_info.is_hdmi

This is a TODO task in Documentation/gpu/todo.rst
Reviewed-by: NHarry Wentland <harry.wentland@amd.com>
Signed-off-by: NClaudio Suarez <cssk@net-c.es>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drm_display_info is updated by drm_get_edid() or
drm_connector_update_edid_property(). In the amdgpu driver it is almost
always updated when the edid is read in amdgpu_connector_get_edid(),
but not always.  Change amdgpu_connector_get_edid() and
amdgpu_connector_free_edid() to keep drm_display_info updated.
Reviewed-by: NHarry Wentland <harry.wentland@amd.com>
Signed-off-by: NClaudio Suarez <cssk@net-c.es>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

remove in recovery stat check, skip umc ras err cnt
harvest in amdgpu_ras_log_on_err_counter
Signed-off-by: NStanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: NFlora Cui <flora.cui@amd.com>
Reviewed-by: NLeslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: NFlora Cui <flora.cui@amd.com>
Reviewed-by: NLeslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

skip get ecc info for aldebarn through check ip version
do not affect other asic type
Signed-off-by: NStanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

In amdgpu_connector_lcd_native_mode(), the return value of
drm_mode_duplicate() is assigned to mode, and there is a dereference
of it in amdgpu_connector_lcd_native_mode(), which will lead to a NULL
pointer dereference on failure of drm_mode_duplicate().

Fix this bug add a check of mode.

This bug was found by a static analyzer. The analysis employs
differential checking to identify inconsistent security operations
(e.g., checks or kfrees) between two code paths and confirms that the
inconsistent operations are not recovered in the current function or
the callers, so they constitute bugs.

Note that, as a bug found by static analysis, it can be a false
positive or hard to trigger. Multiple researchers have cross-reviewed
the bug.

Builds with CONFIG_DRM_AMDGPU=m show no new warnings, and
our static analyzer no longer warns about this code.

Fixes: d38ceaf9 ("drm/amdgpu: add core driver (v4)")
Signed-off-by: NZhou Qingyang <zhou1615@umn.edu>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For SR-IOV, the IP discovery revision number encodes
additional information.  Handle that case here.

v2: drop additional IP versions
Reviewed-by: NGuchun Chen <guchun.chen@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

this is a workaround due to get ecc info failed during gpu recovery

[  700.236122] amdgpu 0000:09:00.0: amdgpu: Failed to export SMU ecc table!
[  700.236128] amdgpu 0000:09:00.0: amdgpu: GPU reset begin!
[  704.331171] amdgpu: qcm fence wait loop timeout expired
[  704.331194] amdgpu: The cp might be in an unrecoverable state due to an unsuccessful queues preemption
[  704.332445] amdgpu 0000:09:00.0: amdgpu: GPU reset begin!
[  704.332448] amdgpu 0000:09:00.0: amdgpu: Bailing on TDR for s_job:ffffffffffffffff, as another already in progress
[  704.332456] amdgpu: Pasid 0x8000 destroy queue 0 failed, ret -62
[  710.360924] amdgpu 0000:09:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x00000013 SMN_C2PMSG_82:0x00000007
[  710.360964] amdgpu 0000:09:00.0: amdgpu: Failed to disable smu features.
[  710.361002] amdgpu 0000:09:00.0: amdgpu: Fail to disable dpm features!
[  710.361014] [drm:amdgpu_device_ip_suspend_phase2 [amdgpu]] *ERROR* suspend of IP block <smu> failed -62
Signed-off-by: NStanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

amdgpu_ucode_get_load_type() does not interpret this parameter as
documented.  It is ignored for many ASIC types (which presumably
only support one load_type), and when not ignored it is only used
to force direct loading instead of PSP loading.  SMU loading is
only available for ASICs for which the parameter is ignored.
Signed-off-by: NYann Dirson <ydirson@free.fr>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Refactor userptr and pin_bo path to make it less confusing, move
err_pin_bo label up to remove mem from process_info kfd_bo_list.
Signed-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This change revert previous commits:
9f4f2c1a ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
271fd38c ("drm/amdgpu: move kfd post_reset out of reset_sriov function")

This change moves the amdgpu_amdkfd_pre_reset to an earlier place
in amdgpu_device_reset_sriov, presumably to address the sequence issue
that the first patch was originally meant to fix.

Some register access(GRBM_GFX_CNTL) only be allowed on full access
mode. Move kfd_pre_reset and  kfd_post_reset back inside reset_sriov
function.

Fixes: 9f4f2c1a ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
Fixes: 271fd38c ("drm/amdgpu: move kfd post_reset out of reset_sriov function")
Signed-off-by: Nshaoyunl <shaoyun.liu@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>