drm/amdgpu: Add option to refresh NPS data

In certain use cases, NPS data needs to be refreshed again from
discovery table. Add API parameter to refresh NPS data from discovery
table.

Signed-off-by

drm/amdgpu: Add option to refresh NPS data

In certain use cases, NPS data needs to be refreshed again from
discovery table. Add API parameter to refresh NPS data from discovery
table.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Rajneesh Bhardwaj <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Use NPS ranges from discovery table

Add GMC API to fetch NPS range information from discovery table. Use NPS
range information in GMC 9.4.3 SOCs when available, otherwise fallback
to sof

drm/amdgpu: Use NPS ranges from discovery table

Add GMC API to fetch NPS range information from discovery table. Use NPS
range information in GMC 9.4.3 SOCs when available, otherwise fallback
to software method.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Le Ma <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Increase IP discovery region size

IP discovery region has increased to > 8K on some SOCs.Maximum reserve
size is upto 12K, but not used. For now increase to 10K.

Signed-off-by: Lijo Laz

drm/amdgpu: Increase IP discovery region size

IP discovery region has increased to > 8K on some SOCs.Maximum reserve
size is upto 12K, but not used. For now increase to 10K.

Signed-off-by: Lijo Lazar <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: increase DISCOVERY_TMR_SIZE

New ip_discovery binary size is increased.

Signed-off-by: Le Ma <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <ale

drm/amdgpu: increase DISCOVERY_TMR_SIZE

New ip_discovery binary size is increased.

Signed-off-by: Le Ma <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: drop unused function

amdgpu_discovery_get_ip_version() has not been used since
commit c40bdfb2ffa4 ("drm/amdgpu: fix incorrect VCN revision in SRIOV")
so drop it.

Reviewed-by: Luben Tui

drm/amdgpu: drop unused function

amdgpu_discovery_get_ip_version() has not been used since
commit c40bdfb2ffa4 ("drm/amdgpu: fix incorrect VCN revision in SRIOV")
so drop it.

Reviewed-by: Luben Tuikov <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/discovery: move all table parsing into amdgpu_discovery.c

This data has no dependencies, so encapsulate it all within
amdgpu_discovery.c.

Acked-by: Christian König <christian.koenig@amd.

drm/amdgpu/discovery: move all table parsing into amdgpu_discovery.c

This data has no dependencies, so encapsulate it all within
amdgpu_discovery.c.

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/discovery: add a function to parse the vcn info table

To get the codec disable fuse mask.

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <alexander.deuc

drm/amdgpu/discovery: add a function to parse the vcn info table

To get the codec disable fuse mask.

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/discovery: add a function to get the mall_size

Add a function to fetch the mall size from the IP discovery
table. Properly handle harvest configurations where more
or less cache may be av

drm/amdgpu/discovery: add a function to get the mall_size

Add a function to fetch the mall size from the IP discovery
table. Properly handle harvest configurations where more
or less cache may be available.

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: fix incorrect VCN revision in SRIOV

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 fa

drm/amdgpu: fix incorrect VCN revision in SRIOV

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: baf3f8f3740625 ("drm/amdgpu: handle SRIOV VCN revision parsing")
Signed-off-by: Leslie Shi <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Reviewed-by: Guchun Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: add initial IP enumeration via IP discovery table

Add initial support for all navi based parts.

v2: rebase

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deuc

drm/amdgpu: add initial IP enumeration via IP discovery table

Add initial support for all navi based parts.

v2: rebase

Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/amdgpu: Use IP discovery data to determine VCN enablement instead of MMSCH

In the past, we use MMSCH to determine whether a VCN is enabled or not.
This is not reliable since after a FLR, MMS

drm/amd/amdgpu: Use IP discovery data to determine VCN enablement instead of MMSCH

In the past, we use MMSCH to determine whether a VCN is enabled or not.
This is not reliable since after a FLR, MMSCH may report junk data.

It is better to use IP discovery data.

Signed-off-by: Bokun Zhang <[email protected]>
Signed-off-by: Peng Ju Zhou <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/amdgpu: add instance_number check in amdgpu_discovery_get_ip_version

The original code returns IP version of instantce_0 for every IP. This implementation may be correct for most of IPs.

Ho

drm/amd/amdgpu: add instance_number check in amdgpu_discovery_get_ip_version

The original code returns IP version of instantce_0 for every IP. This implementation may be correct for most of IPs.

However, for certain IP block (VCN for example), it may have 2 instances and
both of them have the same hw_id, BUT they have different revision number (0 and 1).

In this case, the original amdgpu_discovery_get_ip_version cannot correct reflects
the result and returns false information

Signed-off-by: Bokun Zhang <[email protected]>
Signed-off-by: Peng Ju Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: add judgement when add ip blocks (v2)

Judgement whether to add an sw ip according to the harvest info.

v2: fix indentation (Alex)

Signed-off-by: Likun Gao <[email protected]>
Reviewed-

drm/amdgpu: add judgement when add ip blocks (v2)

Judgement whether to add an sw ip according to the harvest info.

v2: fix indentation (Alex)

Signed-off-by: Likun Gao <[email protected]>
Reviewed-by: Guchun Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: add judgement when add ip blocks (v2)

Judgement whether to add an sw ip according to the harvest info.

v2: fix indentation (Alex)

Signed-off-by: Likun Gao <[email protected]>
Reviewed-

drm/amdgpu: add judgement when add ip blocks (v2)

Judgement whether to add an sw ip according to the harvest info.

v2: fix indentation (Alex)

Signed-off-by: Likun Gao <[email protected]>
Reviewed-by: Guchun Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: reduce ip discovery data reading size

Only read first 4K data instead of whole TMR block,
so we can reduce the time in full access mode.

Signed-off-by: Wenhui Sheng <[email protected]

drm/amdgpu: reduce ip discovery data reading size

Only read first 4K data instead of whole TMR block,
so we can reduce the time in full access mode.

Signed-off-by: Wenhui Sheng <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: adjust sequence of ip_discovery init and timeout_setting

what:
1)move timtout setting before ip_early_init to reduce exclusive mode
cost for SRIOV

2)move ip_discovery_init() to inside o

drm/amdgpu: adjust sequence of ip_discovery init and timeout_setting

what:
1)move timtout setting before ip_early_init to reduce exclusive mode
cost for SRIOV

2)move ip_discovery_init() to inside of amdgpu_discovery_reg_base_init()
it is a prepare for the later upcoming patches.

why:
in later upcoming patches we would use a new mailbox event --
"req_gpu_init_data", which is a callback hooked in adev->virt.ops and
this callback send a new event "REQ_GPU_INIT_DAT" to host to notify
host to do some preparation like "IP discovery/vbios on the VF FB"
and this callback must be:

A) invoked after set_ip_block() because virt.ops is configured during
set_ip_block()

B) invoked before ip_discovery_init() becausen ip_discovery_init()
need host side prepares everything in VF FB first.

current place of ip_discovery_init() is before we can invoke callback
of adev->virt.ops, thus we must move ip_discovery_init() to a place
after the adev->virt.ops all settle done, and the perfect place is in
amdgpu_discovery_reg_base_init()

Signed-off-by: Monk Liu <[email protected]>
Reviewed-by: Emily Deng <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: update amdgpu_discovery to handle revision

update amdgpu_discovery to get IP revision.

Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.

drm/amdgpu: update amdgpu_discovery to handle revision

update amdgpu_discovery to get IP revision.

Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Luben Tuikov <[email protected]>
Signed-off-by: Tianci.Yin <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/discovery: reserve discovery data at the top of VRAM

IP Discovery data is TMR fenced by the latest PSP BL,
so we need to reserve this region.

Tested on navi10/12/14 with VBIOS integrated

drm/amdgpu/discovery: reserve discovery data at the top of VRAM

IP Discovery data is TMR fenced by the latest PSP BL,
so we need to reserve this region.

Tested on navi10/12/14 with VBIOS integrated with latest PSP BL.

v2: use DISCOVERY_TMR_SIZE macro as bo size
use amdgpu_bo_create_kernel_at() to allocate bo

Signed-off-by: Xiaojie Yuan <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/discovery: add ip discovery initial support

The IP discovery table lists is populated by the psp at power on
and includes all of the hw details on the board:
- List of IPs and MMIO offset

drm/amdgpu/discovery: add ip discovery initial support

The IP discovery table lists is populated by the psp at power on
and includes all of the hw details on the board:
- List of IPs and MMIO offsets
- IP harvest details
- IP configuration details

v2: prefix struct and function names with 'amdgpu'
v3: read table binary from vram using mmMM_INDEX and mmMM_DATA
update TABLE_BINARY_MAX_SIZE to 64kb (1 TMR)
add 'instance_number' field per ip info
consider endianness and replace uint8/16/32_t with u8/16/32
initialize register base addresses
initialize adev->gfx.config and adev->gfx.cu_info to replace gpu info fw
get major and minor version using a single api
don't expose internal data structures in amdgpu_discovery.h
v4: RCC_CONFIG_MEMSIZE is in MB units
hold mmio_idx_lock while reading ip discovery binary
v5: pick out discovery.h as a cross-OS header
do structure pointer cast directly
consider endianness while using the member of structure
convert base addresses to dword

at boot up, PSP BL copies ip discovery binary from VBIOS(SPIROM) image to the
top of the frame buffer (just below the reserved regions for PSP & SMU).

ip discovery data table includes the collection of each ip's identification
number, base addresses, version number, and harvest setting placeholder.

gc data table includes gfx info structure.

Signed-off-by: Xiaojie Yuan <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...