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: Isabella Basso <isabbasso@riseup.net>
Signed-off-by: Alex 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: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex 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: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex 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: Lang Yu <lang.yu@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex 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: Christian Koenig <christian.koenig@amd.com>
Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Lang Yu <lang.yu@amd.com>
Reviewed-by: Christian Koenig <christian.koenig@amd.co>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
in case they are not avaiable in early phase
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Leave this bit as hardware default setting
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
should count on GC IP base address
Signed-off-by: Le Ma <le.ma@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex 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: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To be used to check ip discovery binary signature
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
add _from_vram in the funciton name to diffrentiate
the one used to read from file
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To be used when ip_discovery binary is not carried by vbios
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex 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: baf3f8f374 ("drm/amdgpu: handle SRIOV VCN revision parsing")
Signed-off-by: Leslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex 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: Leslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We found some headaches on ASICs don't need that,
so remove that for them.
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Lang Yu <lang.yu@amd.com>
Reviewed-by: Kevin Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex 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/1818
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex 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: Isabella Basso <isabbasso@riseup.net>
Signed-off-by: Alex 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: Isabella Basso <isabbasso@riseup.net>
Signed-off-by: Alex 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: Isabella Basso <isabbasso@riseup.net>
Signed-off-by: Alex 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: Zhigang Luo <zhigang.luo@amd.com>
Acked-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex 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: Zhigang Luo <zhigang.luo@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex 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: Zhigang Luo <zhigang.luo@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex 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: Zhigang Luo <zhigang.luo@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The RAS poison mode is enabled by default on the platform.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amd-drm-next-5.17-2021-12-02:
amdgpu:
- Use generic drm fb helpers
- PSR fixes
- Rework DCN3.1 clkmgr
- DPCD 1.3 fixes
- Misc display fixes can cleanups
- Clock query fixes for APUs
- LTTPR fixes
- DSC fixes
- Misc PM fixes
- RAS fixes
- OLED backlight fix
- SRIOV fixes
- Add STB (Smart Trace Buffer) for supported dGPUs
- IH rework
- Enable seamless boot for DCN3.01
amdkfd:
- Rework more stuff around IP discovery enumeration
- Further clean up of interfaces with amdgpu
- SVM fixes
radeon:
- Indentation fixes
UAPI:
- Add a new KFD header that defines some of the sysfs bitfields and enums that userspace has been using for a while
The corresponding bit-fields and enums in user mode are defined in
https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/blob/master/include/hsakmttypes.h
Signed-off-by: Dave Airlie <airlied@redhat.com>
# Conflicts:
# drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211202191643.5970-1-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: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Claudio Suarez <cssk@net-c.es>
Signed-off-by: Alex 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: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Claudio Suarez <cssk@net-c.es>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Leslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Leslie Shi <Yuliang.Shi@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
skip get ecc info for aldebarn through check ip version
do not affect other asic type
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex 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: d38ceaf99e ("drm/amdgpu: add core driver (v4)")
Signed-off-by: Zhou Qingyang <zhou1615@umn.edu>
Signed-off-by: Alex 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: Guchun Chen <guchun.chen@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex 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: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This change revert previous commits:
9f4f2c1a35 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
271fd38ce5 ("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: 9f4f2c1a35 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
Fixes: 271fd38ce5 ("drm/amdgpu: move kfd post_reset out of reset_sriov function")
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm_gem_object_put calls release_notify callback to free the mem
structure and unreserve_mem_limit, move it down after the last access
of mem and make it conditional call.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is no base reg offset or ip_version set for SDMA2
and SDMA3 on SIENNA_CICHLID, so add them.
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Kevin Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
since vkms support atomic KMS interface
Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Acked-by: Alex Deucher <aleander.deucher@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHY]
for sriov odd# vf will modify vcn0 engine ip revision(due to multimedia bandwidth feature),
which will be mismatched with original vcn0 revision
[HOW]
add new version check for vcn0 disabled revision(3, 0, 192), typically modified under
sriov mode
Signed-off-by: Jane Jian <Jane.Jian@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex 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: Yann Dirson <ydirson@free.fr>
Signed-off-by: Alex 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: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This change revert previous commits:
9f4f2c1a35 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
271fd38ce5 ("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: 9f4f2c1a35 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
Fixes: 271fd38ce5 ("drm/amdgpu: move kfd post_reset out of reset_sriov function")
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm_gem_object_put calls release_notify callback to free the mem
structure and unreserve_mem_limit, move it down after the last access
of mem and make it conditional call.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
HW_ID_MAX considers HWID of all IPs, far more than what amdgpu uses.
amdgpu tracks only the IPs defined by amd_hw_ip_block_type whose max
is MAX_HWIP.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
