| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Here, Adding db_size in byte to find the doorbell's
absolute offset for both 32-bit and 64-bit doorbell sizes.
So that doorbell offset will be aligned based on the doorbell
size.
v2:
- Addressed the review comment from Felix.
v3:
- Adding doorbell_size as parameter to get db absolute offset.
v4:
Squash the two patches into one.
Cc: Christian Koenig <[email protected]>
Cc: Alex Deucher <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Arvind Yadav <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
| |
Add doorbell index for Video Processing Engine.
Signed-off-by: Lang Yu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
For sriov, doorbell index for vcn0 for AID needs to be on
32 byte boundary so we need to move the vcn end doorbell
Signed-off-by: Samir Dhume <[email protected]>
Acked-by: Leo Liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch adds a helper function which converts a doorbell's
relative index in a BO to an absolute doorbell offset in the
doorbell BAR.
V2: No space between the variable name doc (Luben)
Cc: Alex Deucher <[email protected]>
Cc: Christian Koenig <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch:
- creates a doorbell page for graphics driver usages.
- adds a few new varlables in adev->doorbell structure to
keep track of kernel's doorbell-bo.
- removes the adev->doorbell.ptr variable, replaces it with
kernel-doorbell-bo's cpu address.
V2: - Create doorbell BO directly, no wrappe functions (Alex)
- no additional doorbell structure (Alex, Christian)
- Use doorbell_cpu_ptr, remove ioremap (Christian, Alex)
- Allocate one extra page of doorbells for MES (Alex)
V4: Move MES doorbell base init into MES related patch (Christian)
Cc: Alex Deucher <[email protected]>
Cc: Christian Koenig <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Fixes the following:
WARNING: do not add new typedefs
Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Guchun Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch:
- creates a new file for doorbell management.
- moves doorbell code from amdgpu_device.c to this file.
V2:
- remove doc from function declaration (Christian)
- remove 'device' from function names to make it consistent (Alex)
- add SPDX license identifier (Luben)
V3:
- change license to MIT license(Christian)
Cc: Alex Deucher <[email protected]>
Cc: Christian Koenig <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Program different ranges in each XCC with MEC_DOORBELL_RANGE_LOWER/HIGHER.
Keeping the same range causes CPF in other XCCs also to be busy when an IB
packet is submitted to KCQ. Only the XCC which processes the packet
comes back to idle afterwards and this causes other CPs not be idle.
This in turn affects clockgating behavior as RLC doesn't get idle
interrupt.
LOWER/HIGHER covers only KIQ/KCQs which are per XCC queues. Assigning
different ranges doesn't seem to have any side effect as user queue ranges
are outside of this range. User queue tests - PM4 through KFD and AQL
through rocr - have the same results after this change.
Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
vcn_v4_0_3 increased jpeg instances,
need increasing MAX resources setting accordlingly.
Signed-off-by: James Zhu <[email protected]>
Acked-by Leo Liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Four basic reasons as below to do the change:
1. number of ring expand a lot on GC 9.4.3, and adjustment on old
assignment cannot make each ring in a continuous doorbell space.
2. the SDMA doorbell index should not exceed 0x1FF on SDMA 4.2.2 due to
regDOORBELLx_CTRL_ENTRY.BIF_DOORBELLx_RANGE_OFFSET_ENTRY field width.
3. re-design the doorbell assignment and unify the calculation as
"start + ring/inst id" will make the code much concise.
4. only defining the START/END makes the table look simple
v2: (Lijo)
1. replace name
2. use num_inst_per_aid/sdma_doorbell_range instead of hardcoding
Signed-off-by: Le Ma <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Allocate new sdma doorbell index for the instances only on AID1 for now.
Todo: there's limitation that SDMA doorbell index on SDMA 4.4.2 needs to be
less than 0x1FF, so the tail part in _AMDGPU_VEGA20_DOORBELL_ASSIGNMENT is not
enough to store sdma doorbell range on maximum 4 AIDs if doorbell_range is 20.
So it looks better to create a new doorbell index assignment table for 4.4.2.
v2: change "(x << 1) + 2" to "(x + 1) << 1" for readability.
Signed-off-by: Le Ma <[email protected]>
Acked-by: Felix Kuehling <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Allocate different doorbell index for kiq/kcq rings
on each die
Signed-off-by: Le Ma <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
This patch adds double include protection for doorbell.h
Cc: Christian Koenig <[email protected]>
Cc: Alex Deucher <[email protected]>
Reviewed-by: Christian Koenig <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
Rename doorbell.num_doorbells to doorbell.num_kernel_doorbells to
make it more readable.
Cc: Alex Deucher <[email protected]>
Cc: Christian Koenig <[email protected]>
Acked-by: Christian Koenig <[email protected]>
Signed-off-by: Shashank Sharma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
1. move MES doorbell inside the mec doorbell range,
for mes belongs to mec block
2. setting the correct gfx/mec doorbell range, so that
fw can correctly detect gfx/compute work load to enter/exit
power saving state.
Signed-off-by: Jack Xiao <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Tested-and-acked-by: Evan Quan <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
| |
Allocate a doorbell index for mes kiq queue.
Signed-off-by: Jack Xiao <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
MES ring will use the assigned doorbell index for
command submission.
Signed-off-by: Jack Xiao <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Sienna_Cichlid have 2 VCN instances, using different register for range
Signed-off-by: Leo Liu <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: James Zhu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Sienna_Cichlid have 4 sdma controllers.
v2: add missing license to sdma_common.h (Alex)
v3: rebase (Alex)
v4: squash in policy fix (Alex)
v4: squash in fw_name fix
Signed-off-by: Likun Gao <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
| |
add doorbell assignment for 2nd vcn instance
Signed-off-by: James Zhu <[email protected]>
Reviewed-by: Leo Liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Update mappings for Navi10.
Signed-off-by: Hawking Zhang <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Jack Xiao <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
This reverts commit 9006c6bd9059cb9807fa863bafc1d776222cb61b.
Signed-off-by: Yong Zhao <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
| |
They will be used to inform KFD the doorbell range not usable for CP.
Signed-off-by: Yong Zhao <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
| |
They are no longer used, so delete them to avoid confusion.
Signed-off-by: Yong Zhao <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
Different ASIC has different sdma doorbell range. Add
a per device sdma_doorbell_range field and initialize
it.
Signed-off-by: Oak Zeng <[email protected]>
Reviewed-by: Philip Yang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Use sdma_engine[8] array instead of sdma_engine0~7 so it is easier
to program.
Signed-off-by: Oak Zeng <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
|
Move doorbell structures, enum definitions and helper functions
from amdgpu.h to amdgpu_doorbell.h. No functional change
Signed-off-by: Oak Zeng <[email protected]>
Proposed-by: Alex Deucher <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|