2
0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
Commit Graph

12981 Commits

Author SHA1 Message Date
Mukul Joshi
41ce6d6d03 drm/amdgpu: Rename DRM schedulers in amdgpu TTM
Rename mman.entity to mman.high_pr to make the distinction
clearer that this is a high priority scheduler. Similarly,
rename the recently added mman.delayed to mman.low_pr to
make it clear it is a low priority scheduler.
No functional change in this patch.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-15 10:42:33 -04:00
Dave Airlie
901bdf5ea1 Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com
2023-06-15 14:11:22 +10:00
Arunpravin Paneer Selvam
34e5a54327 Revert "drm/amdgpu: remove TOPDOWN flags when allocating VRAM in large bar system"
This reverts commit c105518679.

This patch disables the TOPDOWN flag for APU and few dGPU cards
which has the VRAM size equal to the BAR size.

When we enable the TOPDOWN flag, we get the free blocks at
the highest available memory region and we don't split the
lower order blocks. This change is required to keep off
the fragmentation related issues particularly in ASIC
which has VRAM space <= 500MiB

Hence, we are reverting this patch.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2270
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2023-06-13 17:12:41 -04:00
Sonny Jiang
9db5ec1ceb drm/amdgpu: vcn_4_0 set instance 0 init sched score to 1
Only vcn0 can process AV1 codecx. In order to use both vcn0 and
vcn1 in h264/265 transcode to AV1 cases, set vcn0 sched score to 1
at initialization time.

Signed-off-by: Sonny Jiang <sonjiang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
2023-06-13 17:08:42 -04:00
Mario Limonciello
7ab1a4913d drm/amd: Tighten permissions on VBIOS flashing attributes
Non-root users shouldn't be able to try to trigger a VBIOS flash
or query the flashing status.  This should be reserved for users with the
appropriate permissions.

Cc: stable@vger.kernel.org
Fixes: 8424f2ccb3 ("drm/amdgpu/psp: Add vbflash sysfs interface support")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-13 17:04:51 -04:00
Mario Limonciello
3eb1a3a040 drm/amd: Make sure image is written to trigger VBIOS image update flow
The VBIOS image update flow requires userspace to:
1) Write the image to `psp_vbflash`
2) Read `psp_vbflash`
3) Poll `psp_vbflash_status` to check for completion

If userspace reads `psp_vbflash` before writing an image, it's
possible that it causes problems that can put the dGPU into an invalid
state.

Explicitly check that an image has been written before letting a read
succeed.

Cc: stable@vger.kernel.org
Fixes: 8424f2ccb3 ("drm/amdgpu/psp: Add vbflash sysfs interface support")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-13 17:04:45 -04:00
Alex Deucher
e61f67749b drm/amdgpu: add missing radeon secondary PCI ID
0x5b70 is a missing RV370 secondary id.  Add it so
we don't try and probe it with amdgpu.

Cc: michel@daenzer.net
Reviewed-by: Michel Dänzer <mdaenzer@redhat.com>
Tested-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2023-06-13 17:02:51 -04:00
Jiadong Zhu
5b711e7f9c drm/amdgpu: Implement gfx9 patch functions for resubmission
Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9
during the resubmission scenario.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.3.x
2023-06-13 16:58:23 -04:00
Jiadong Zhu
87af86ae89 drm/amdgpu: Modify indirect buffer packages for resubmission
When the preempted IB frame resubmitted to cp, we need to modify the frame
data including:
1. set PRE_RESUME 1 in CONTEXT_CONTROL.
2. use meta data(DE and CE) read from CSA in WRITE_DATA.

Add functions to save the location the first time IBs emitted and callback
to patch the package when resubmission happens.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.3.x
2023-06-13 16:57:44 -04:00
Jiadong Zhu
94034b306d drm/amdgpu: Program gds backup address as zero if no gds allocated
It is firmware requirement to set gds_backup_addrlo and gds_backup_addrhi
of DE meta both zero if no gds partition is allocated for the frame.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.3.x
2023-06-13 16:57:14 -04:00
Jiadong Zhu
1dbcf770cc drm/amdgpu: Reset CP_VMID_PREEMPT after trailing fence signaled
When MEC executes unmap_queue for mid command buffer preemption, it will
kick the write pointer of the gfx ring, set CP_VMID_PREEMPT to trigger the
preemption and wait for CP_VMID_PREEMPT becomes zero after the preemption
done. There is a race condition that PFP may excute the resetting command
before MEC set CP_VMID_PREEMPT. As a result, hang happens as
CP_VMID_PREEMPT is always 0xffff.

To avoid this, we send resetting CP_VMID_PREEMPT command after the trailing
fence is siganled and update gfx write pointer explicitly.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.3.x
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2535
2023-06-13 16:51:05 -04:00
Chong Li
80e709ee6e drm/amdgpu: add option params to enforce process isolation between graphics and compute
enforce process isolation between graphics and compute via using the same reserved vmid.

v2: remove params "struct amdgpu_vm *vm" from
    amdgpu_vmid_alloc_reserved and amdgpu_vmid_free_reserved.

Signed-off-by: Chong Li <chongli2@amd.com>
Reviewed-by: Christian Koenig <Christian.Koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:49:48 -04:00
Nathan Chancellor
4e70da985c drm/amdgpu: Wrap -Wunused-but-set-variable in cc-option
-Wunused-but-set-variable was only supported in clang starting with
13.0.0, so earlier versions will emit a warning, which is turned into a
hard error for the kernel to mirror GCC:

  error: unknown warning option '-Wunused-but-set-variable'; did you mean '-Wunused-const-variable'? [-Werror,-Wunknown-warning-option]

The minimum supported version of clang for building the kernel is
11.0.0, so match the rest of the kernel and wrap
-Wunused-but-set-variable in a cc-option call, so that it is only used
when supported by the compiler.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1869
Fixes: 1b320ad3f5 ("drm/amd/amdgpu: introduce DRM_AMDGPU_WERROR")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:49:06 -04:00
Shiwu Zhang
9d65b1b4bc drm/amdgpu: add the accelerator PCIe class
Add the accelerator PCIe class and match the
class in amdgpu for 0x1002 devices of that class.

From PCI spec:
"PCI Code and ID Assignment, r1.9, sec 1, 1.19"

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>  # pci_ids.h
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:48:57 -04:00
Jonathan Kim
09d49e14ea drm/amdkfd: fix and enable debugging for gfx11
There are a couple of fixes required to enable gfx11 debugging.

First, ADD_QUEUE.trap_en is an inappropriate place to toggle
a per-process register so move it to SET_SHADER_DEBUGGER.trap_en.
When ADD_QUEUE.skip_process_ctx_clear is set, MES will prioritize
the SET_SHADER_DEBUGGER.trap_en setting.

Second, to preserve correct save/restore priviledged wave states
in coordination with the trap enablement setting, resume suspended
waves early in the disable call.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:48:19 -04:00
Mario Limonciello
fe56c6ee04 drm/amd: Tighten permissions on VBIOS flashing attributes
Non-root users shouldn't be able to try to trigger a VBIOS flash
or query the flashing status.  This should be reserved for users with the
appropriate permissions.

Cc: stable@vger.kernel.org
Fixes: 8424f2ccb3 ("drm/amdgpu/psp: Add vbflash sysfs interface support")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:48:10 -04:00
Mario Limonciello
3537d6a48c drm/amd: Make sure image is written to trigger VBIOS image update flow
The VBIOS image update flow requires userspace to:
1) Write the image to `psp_vbflash`
2) Read `psp_vbflash`
3) Poll `psp_vbflash_status` to check for completion

If userspace reads `psp_vbflash` before writing an image, it's
possible that it causes problems that can put the dGPU into an invalid
state.

Explicitly check that an image has been written before letting a read
succeed.

Cc: stable@vger.kernel.org
Fixes: 8424f2ccb3 ("drm/amdgpu/psp: Add vbflash sysfs interface support")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:47:50 -04:00
Yang Wang
cab69d36cc drm/amdgpu: skip to resume rlcg for gc 9.4.3 in vf side
skip to resume rlcg, because rlcg is already enabled in pf side.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:47:35 -04:00
Yang Wang
731b48463b drm/amdgpu: disable virtual display support on APP device
virtual display is not support on APP device.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Gavin Wan <gavin.wan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:47:31 -04:00
Lang Yu
5daff15cd0 drm/amdgpu: unmap and remove csa_va properly
Root PD BO should be reserved before unmap and remove
a bo_va from VM otherwise lockdep will complain.

v2: check fpriv->csa_va is not NULL instead of amdgpu_mcbp (christian)

[14616.936827] WARNING: CPU: 6 PID: 1711 at drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1762 amdgpu_vm_bo_del+0x399/0x3f0 [amdgpu]
[14616.937096] Call Trace:
[14616.937097]  <TASK>
[14616.937102]  amdgpu_driver_postclose_kms+0x249/0x2f0 [amdgpu]
[14616.937187]  drm_file_free+0x1d6/0x300 [drm]
[14616.937207]  drm_close_helper.isra.0+0x62/0x70 [drm]
[14616.937220]  drm_release+0x5e/0x100 [drm]
[14616.937234]  __fput+0x9f/0x280
[14616.937239]  ____fput+0xe/0x20
[14616.937241]  task_work_run+0x61/0x90
[14616.937246]  exit_to_user_mode_prepare+0x215/0x220
[14616.937251]  syscall_exit_to_user_mode+0x2a/0x60
[14616.937254]  do_syscall_64+0x48/0x90
[14616.937257]  entry_SYSCALL_64_after_hwframe+0x63/0xcd

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:47:26 -04:00
Alex Deucher
c1ac2ea802 drm/amdgpu: add missing radeon secondary PCI ID
0x5b70 is a missing RV370 secondary id.  Add it so
we don't try and probe it with amdgpu.

Cc: michel@daenzer.net
Reviewed-by: Michel Dänzer <mdaenzer@redhat.com>
Tested-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:44:49 -04:00
Stanley.Yang
0bc3137b21 drm/amdgpu: Set EEPROM ras info
Set EEPROM ras info: rma status, health percent and bad
page threshold.

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>
2023-06-09 12:44:40 -04:00
Stanley.Yang
7c2551fa1d drm/amdgpu: Calculate EEPROM table ras info bytes sum
It's more reasonable to check EEPROM table ras info bytes.

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>
2023-06-09 12:44:38 -04:00
Stanley.Yang
7f599fed3b drm/amdgpu: Add support EEPROM table v2.1
Add ras info to EEPROM table, app can analyse device ECC
status without GPU driver through EEPROM table ras info.

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>
2023-06-09 12:44:34 -04:00
Stanley.Yang
b573cf88c0 drm/amdgpu: Support setting EEPROM table version
Add setting EEPROM table version interface for umcv8.10,
Add EEPROM table v2.1 to UMC v8.10.

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>
2023-06-09 12:44:31 -04:00
Stanley.Yang
65183faec8 drm/amdgpu: Add RAS table v2.1 macro definition
Add RAS EEPROM table version 2.1 macro definition.

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>
2023-06-09 12:44:28 -04:00
Stanley.Yang
71c79a1960 drm/amdgpu: Rename ras table version
Rename RAS_TABLE_VER to RAS_TABLE_VER_V1,
move RAS_TABLE_VER_V1 from amdgpu_ras_eeprom.c to amdgpu_ras_eeprom.h.

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>
2023-06-09 12:44:24 -04:00
Jiadong Zhu
ea791e704b drm/amdgpu: Implement gfx9 patch functions for resubmission
Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9
during the resubmission scenario.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:44:22 -04:00
Jiadong Zhu
8ff865be93 drm/amdgpu: Modify indirect buffer packages for resubmission
When the preempted IB frame resubmitted to cp, we need to modify the frame
data including:
1. set PRE_RESUME 1 in CONTEXT_CONTROL.
2. use meta data(DE and CE) read from CSA in WRITE_DATA.

Add functions to save the location the first time IBs emitted and callback
to patch the package when resubmission happens.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:44:15 -04:00
Emily Deng
f2bcc0c7db drm/amdgpu/mmsch: Correct the definition for mmsch init header
For the header, it is version related, shouldn't use MAX_VCN_INSTANCES.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:44:12 -04:00
YiPeng Chai
869bcf59fd drm/amdgpu: change reserved vram info print
The link object of mgr->reserved_pages is the blocks
variable in struct amdgpu_vram_reservation, not the
link variable in struct drm_buddy_block.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2023-06-09 12:41:14 -04:00
Chia-I Wu
5a863904ba drm/amdgpu: fix xclk freq on CHIP_STONEY
According to Alex, most APUs from that time seem to have the same issue
(vbios says 48Mhz, actual is 100Mhz).  I only have a CHIP_STONEY so I
limit the fixup to CHIP_STONEY

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:41:11 -04:00
Alex Deucher
5a03159ab7 Revert "drm/amdgpu: switch to golden tsc registers for raven/raven2"
This reverts commit f03eb1d26c.

This results in inconsistent timing reported via asynchronous
GPU queries.

Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html
Cc: Jesse.Zhang@amd.com
Cc: michel@daenzer.net
Reviewed-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:40:56 -04:00
Alex Deucher
f9bfc9fff2 Revert "drm/amdgpu: Differentiate between Raven2 and Raven/Picasso according to revision id"
This reverts commit 9d2d1827af.

This results in inconsistent timing reported via asynchronous
GPU queries.

Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html
Cc: Jesse.Zhang@amd.com
Cc: michel@daenzer.net
Reviewed-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:40:17 -04:00
Alex Deucher
a15a77c8e6 Revert "drm/amdgpu: change the reference clock for raven/raven2"
This reverts commit fbc24293ca.

This results in inconsistent timing reported via asynchronous
GPU queries.

Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html
Cc: Jesse.Zhang@amd.com
Cc: michel@daenzer.net
Reviewed-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:40:01 -04:00
Stanley.Yang
3898c8fc42 drm/amdgpu: convert vcn/jpeg logical mask to physical mask
Changed from V1:
 	Remove amdgpu_ras_logical_mask_to_physical_mask
	due to GET_MASK provides same feature.
	Support convert VCN/JPEG logical mask to physical
	mask.

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:39:58 -04:00
Stanley.Yang
e3959cb547 drm/amdgpu: support check vcn jpeg block mask
Support VCN/JPEG instance mask checking, pass logical
mask directly except GFX/SDMA/VCN/JPEG blocks.

Changed from V1:
	correct a typo

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:39:54 -04:00
Stanley.Yang
61a7c16239 drm/amdgpu: pass xcc mask to ras ta
pass xcc mask to ras ta, ras ta will compare
the mask with the one from chiplet topology.

Changed from V1:
	Remove IP version checking.
	Set ras_cmd->ras_init_message.init_flags.xcc_mask
	directly due to xcc_mask is common structres to
	all the devices.

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:39:51 -04:00
Srinivasan Shanmugam
25c30a12d7 drm/amdgpu: Mark 'kgd_gfx_aldebaran_clear_address_watch' & 'kgd_gfx_v11_clear_address_watch' functions as static
Below two functions cause a warning because they lack a prototype:

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c:164:10: warning: no previous prototype for ‘kgd_gfx_aldebaran_clear_address_watch’ [-Wmissing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c:782:10: warning: no previous prototype for ‘kgd_gfx_v11_clear_address_watch’ [-Wmissing-prototypes]

There are no callers from other files, so just mark them as 'static'.

Also fixes the following checks:

CHECK: Alignment should match open parenthesis +static uint32_t
kgd_gfx_aldebaran_clear_address_watch(struct amdgpu_device *adev,
uint32_t watch_id)

CHECK: Alignment should match open parenthesis +static uint32_t
kgd_gfx_v11_clear_address_watch(struct amdgpu_device *adev, uint32_t
watch_id)

Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:39:36 -04:00
Chia-I Wu
9f0bcf49e9 amdgpu: validate offset_in_bo of drm_amdgpu_gem_va
This is motivated by OOB access in amdgpu_vm_update_range when
offset_in_bo+map_size overflows.

v2: keep the validations in amdgpu_vm_bo_map
v3: add the validations to amdgpu_vm_bo_map/amdgpu_vm_bo_replace_map
    rather than to amdgpu_gem_va_ioctl

Fixes: 9f7eb5367d ("drm/amdgpu: actually use the VM map parameters")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:37:56 -04:00
Jonathan Kim
9bd443cb74 drm/amdgpu: fix debug wait on idle for gfx9.4.1
Wait calls for amd_ip_block_type not amd_hw_ip_block_type.

Reported-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:37:50 -04:00
Jonathan Kim
e0f85f4690 drm/amdkfd: add debug set and clear address watch points operation
Shader read, write and atomic memory operations can be alerted to the
debugger as an address watch exception.

Allow the debugger to pass in a watch point to a particular memory
address per device.

Note that there exists only 4 watch points per devices to date, so have
the KFD keep track of what watch points are allocated or not.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:36:46 -04:00
Jonathan Kim
a70a93fa56 drm/amdkfd: add debug suspend and resume process queues operation
In order to inspect waves from the saved context at any point during a
debug session, the debugger must be able to preempt queues to trigger
context save by suspending them.

On queue suspend, the KFD will copy the context save header information
so that the debugger can correctly crawl the appropriate size of the saved
context. The debugger must then also be allowed to resume suspended queues.

A queue that is newly created cannot be suspended because queue ids are
recycled after destruction so the debugger needs to know that this has
occurred.  Query functions will be later added that will clear a given
queue of its new queue status.

A queue cannot be destroyed while it is suspended to preserve its saved
context during debugger inspection.  Have queue destruction block while
a queue is suspended and unblocked when it is resumed.  Likewise, if a
queue is about to be destroyed, it cannot be suspended.

Return the number of queues successfully suspended or resumed along with
a per queue status array where the upper bits per queue status show that
the request was invalid (new/destroyed queue suspend request, missing
queue) or an error occurred (HWS in a fatal state so it can't suspend or
resume queues).

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:36:43 -04:00
Jonathan Kim
aea1b4738b drm/amdkfd: add debug wave launch mode operation
Allow the debugger to set wave behaviour on to either normally operate,
halt at launch, trap on every instruction, terminate immediately or
stall on allocation.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:36:39 -04:00
Jonathan Kim
101827e130 drm/amdkfd: add debug wave launch override operation
This operation allows the debugger to override the enabled HW
exceptions on the device.

On debug devices that only support the debugging of a single process,
the HW exceptions are global and set through the SPI_GDBG_TRAP_MASK
register.
Because they are global, only address watch exceptions are allowed to
be enabled.  In other words, the debugger must preserve all non-address
watch exception states in normal mode operation by barring a full
replacement override or a non-address watch override request.

For multi-process debugging, all HW exception overrides are per-VMID so
all exceptions can be overridden or fully replaced.

In order for the debugger to know what is permissible, returned the
supported override mask back to the debugger along with the previously
enable overrides.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:36:37 -04:00
Jonathan Kim
12fb1ad70d drm/amdkfd: update process interrupt handling for debug events
The debugger must be notified by any debugger subscribed exception
that comes from hardware interrupts.

If a debugger session exits, any exceptions it subscribed to may still
have interrupts in the interrupt ring buffer or KGD/KFD pipeline.
To prevent a new session from inheriting stale interrupts, when a new
queue is created, open an interrupt drain and allow the IH ring to drain
from a timestamped checkpoint.  Then inject a custom IV so that once
the custom IV is picked up by the KFD, it's safe to close the drain
and proceed with queue creation.

The drain must also be on debug disable as SW interrupts may still
be processed.  Drain at this time and clear all the exception status.

The debugger may also not be attached nor subscibed to certain
exceptions so forward them directly to the runtime.

GFX10 also requires its own IV processing, hence the creation of
kfd_int_process_v10.c.  This is because the IV from SQ interrupts are
packed into a new continguous format unlike GFX9. To make this clear,
a separate interrupting handling code file was created.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:36:17 -04:00
Jonathan Kim
69a8c3ae2d drm/amdkfd: apply trap workaround for gfx11
Due to a HW bug, waves in only half the shader arrays can enter trap.

When starting a debug session, relocate all waves to the first shader
array of each shader engine and mask off the 2nd shader array as
unavailable.

When ending a debug session, re-enable the 2nd shader array per
shader engine.

User CU masking per queue cannot be guaranteed to remain functional
if requested during debugging (e.g. user cu mask requests only 2nd shader
array as an available resource leading to zero HW resources available)
nor can runtime be alerted of any of these changes during execution.

Make user CU masking and debugging mutual exclusive with respect to
availability.

If the debugger tries to attach to a process with a user cu masked
queue, return the runtime status as enabled but busy.

If the debugger tries to attach and fails to reallocate queue waves to
the first shader array of each shader engine, return the runtime status
as enabled but with an error.

In addition, like any other mutli-process debug supported devices,
disable trap temporary setup per-process to avoid performance impact from
setup overhead.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:52 -04:00
Jonathan Kim
a9818854ea drm/amdgpu: expose debug api for mes
Similar to the F32 HWS, the RS64 HWS for GFX11 now supports a multi-process
debug API.

The skip_process_ctx_clear ADD_QUEUE requirement is to prevent the MES
from clearing the process context when the first queue is added to the
scheduler in order to maintain debug mode settings during queue preemption
and restore.  The MES clears the process context in this case due to an
unresolved FW caching bug during normal mode operations.
During debug mode, the KFD will hold a reference to the target process
so the process context should never go stale and MES can afford to skip
this requirement.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:43 -04:00
Jonathan Kim
7cee6a6824 drm/amdgpu: add configurable grace period for unmap queues
The HWS schedule allows a grace period for wave completion prior to
preemption for better performance by avoiding CWSR on waves that can
potentially complete quickly. The debugger, on the other hand, will
want to inspect wave status immediately after it actively triggers
preemption (a suspend function to be provided).

To minimize latency between preemption and debugger wave inspection, allow
immediate preemption by setting the grace period to 0.

Note that setting the preepmtion grace period to 0 will result in an
infinite grace period being set due to a CP FW bug so set it to 1 for now.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:31 -04:00
Jonathan Kim
33f3437ae1 drm/amdgpu: add gfx11 hw debug mode enable and disable calls
Implement the per-device calls to enable or disable HW debug mode
for GFX11.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:28 -04:00
Jonathan Kim
be6f94039e drm/amdgpu: add gfx9.4.2 hw debug mode enable and disable calls
GFX9.4.2 now supports per-VMID debug mode controls registers
(SPI_GDBG_PER_VMID_CNTL).

Because the KFD lets the HWS handle PASID-VMID mapping, the KFD will
forward all debug mode setting register writes to the HWS scheduler
using a new MAP_PROCESS API, so instead of writing to registers, return
the required register values that the HWS needs to write on debug enable
and disable.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:25 -04:00
Jonathan Kim
d13f050fee drm/amdgpu: add gfx10 hw debug mode enable and disable calls
Similar to GFX9 debug devices, set the hardware debug mode by draining
the SPI appropriately prior the mode setting request.

Because GFX10 has waves allocated by the work group boundary and each
SE's SPI instances do not communicate, the SPI drain time is much longer.
This long drain time will be fixed for GFX11 onwards.

Also remove a bunch of deprecated misplaced references for GFX10.3.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:21 -04:00
Jonathan Kim
01f648202c drm/amdgpu: add gfx9.4.1 hw debug mode enable and disable calls
On GFX9.4.1, the implicit wait count instruction on s_barrier is
disabled by default in the driver during normal operation for
performance requirements.

There is a hardware bug in GFX9.4.1 where if the implicit wait count
instruction after an s_barrier instruction is disabled, any wave that
hits an exception may step over the s_barrier when returning from the
trap handler with the barrier logic having no ability to be
aware of this, thereby causing other waves to wait at the barrier
indefinitely resulting in a shader hang.  This bug has been corrected
for GFX9.4.2 and onward.

Since the debugger subscribes to hardware exceptions, in order to avoid
this bug, the debugger must enable implicit wait count on s_barrier
for a debug session and disable it on detach.

In order to change this setting in the in the device global SQ_CONFIG
register, the GFX pipeline must be idle.  GFX9.4.1 as a compute device
will either dispatch work through the compute ring buffers used for
image post processing or through the hardware scheduler by the KFD.

Have the KGD suspend and drain the compute ring buffer, then suspend the
hardware scheduler and block any future KFD process job requests before
changing the implicit wait count setting.  Once set, resume all work.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:15 -04:00
Jonathan Kim
cde2e087a3 drm/amdgpu: add gfx9 hw debug mode enable and disable calls
Implement the per-device calls to enable or disable HW debug mode for
GFX9 prior to GFX9.4.1.

GFX9.4.1 and onward will require their own enable/disable sequence as
follow on patches.

When hardware debug mode setting is requested, waves will inherit
these settings in the Shader Processor Input's (SPI) Sequencer Global
Block (SQG). This means that the KGD must drain all waves from the SPI
into SQG (approximately 96 SPI clock cycles) prior to debug mode setting
to ensure that the order of operations that the debugger expects with
regards to debug mode setting transaction requests and wave inheritence
of that mode is upheld.

Also ensure that exception overrides are reset to their original state
prior to debug enable or disable.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:35:11 -04:00
Mario Limonciello
257d7b7be2 drm/amd: Make lack of ACPI_FADT_LOW_POWER_S0 or CONFIG_AMD_PMC louder during suspend path
Users have reported that s2idle wasn't working on OEM Phoenix systems,
but it was root caused to be because `CONFIG_AMD_PMC` wasn't set in
the distribution kernel config.

To make this more apparent, raise the messaging to err instead of warn.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217497
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:34:59 -04:00
Jonathan Kim
4504f14338 drm/amdgpu: setup hw debug registers on driver initialization
Add missing debug trap registers references and initialize all debug
registers on boot by clearing the hardware exception overrides and the
wave allocation ID index.

The debugger requires that TTMPs 6 & 7 save the dispatch ID to map
waves onto dispatch during compute context inspection.
In order to correctly set this up, set the special reserved CP bit by
default whenever the MQD is initailized.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:34:56 -04:00
Horatio Zhang
cbb63eccc0 drm/amdgpu: fix Null pointer dereference error in amdgpu_device_recover_vram
Use the function of amdgpu_bo_vm_destroy to handle the resource release
of shadow bo. During the amdgpu_mes_self_test, shadow bo released, but
vmbo->shadow_list was not, which caused a null pointer reference error
in amdgpu_device_recover_vram when GPU reset.

Fixes: 6c032c37ac ("drm/amdgpu: Fix vram recover doesn't work after whole GPU reset (v2)")
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Acked-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:34:02 -04:00
Srinivasan Shanmugam
2e9fee9b8e drm/amdgpu: Fix up kdoc in amdgpu_device.c
Fix these warnings by deleting the deviant arguments.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:799: warning: Excess function parameter 'pcie_index' description in 'amdgpu_device_indirect_wreg'
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:799: warning: Excess function parameter 'pcie_data' description in 'amdgpu_device_indirect_wreg'
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:870: warning: Excess function parameter 'pcie_index' description in 'amdgpu_device_indirect_wreg64'
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:870: warning: Excess function parameter 'pcie_data' description in 'amdgpu_device_indirect_wreg64'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:33:55 -04:00
Srinivasan Shanmugam
ebe884e8b9 drm/amdgpu: Fix up kdoc 'ring' parameter in sdma_v6_0_ring_pad_ib
Fix this warning by adding 'ring' arguments to kdoc.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:1128: warning: Function parameter or member 'ring' not described in 'sdma_v6_0_ring_pad_ib'

Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:33:50 -04:00
Hamza Mahfooz
1b320ad3f5 drm/amd/amdgpu: introduce DRM_AMDGPU_WERROR
We want to do -Werror builds on our CI. However, non-amdgpu breakages
have prevented us from doing so thus far. Also, there are a number of
additional checks that we should enable, that the community cares about
and are hidden behind -Wextra. So, define DRM_AMDGPU_WERROR to only
enable -Werror for the amdgpu kernel module and enable -Wextra while
disabling all of the checks that are too noisy.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Kenny Ho <kenny.ho@amd.com>
Suggested-by: Jani Nikula <jani.nikula@linux.intel.com>
Reviewed-by: Kenny Ho <Kenny.Ho@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:33:42 -04:00
Mario Limonciello
09521b5d49 drm/amd: Disallow s0ix without BIOS support again
commit cf488dcd0a ("drm/amd: Allow s0ix without BIOS support") showed
improvements to power consumption over suspend when s0ix wasn't enabled in
BIOS and the system didn't support S3.

This patch however was misguided because the reason the system didn't
support S3 was because SMT was disabled in OEM BIOS setup.
This prevented the BIOS from allowing S3.

Also allowing GPUs to use the s2idle path actually causes problems if
they're invoked on systems that may not support s2idle in the platform
firmware. `systemd` has a tendency to try to use `s2idle` if `deep` fails
for any reason, which could lead to unexpected flows.

The original commit also fixed a problem during resume from suspend to idle
without hardware support, but this is no longer necessary with commit
ca47518663 ("drm/amd: Don't allow s0ix on APUs older than Raven")

Revert commit cf488dcd0a ("drm/amd: Allow s0ix without BIOS support")
to make it match the expected behavior again.

Cc: Rafael Ávila de Espíndola <rafael@espindo.la>
Link: https://github.com/torvalds/linux/blob/v6.1/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c#L1060
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2599
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:33:12 -04:00
ZhenGuo Yin
7a66ad6c08 drm/amdgpu: set finished fence error if job timedout
Set finished fence to ETIME error if job timedout.

Signed-off-by: ZhenGuo Yin <zhenguo.yin@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:43 -04:00
Srinivasan Shanmugam
932fc49479 drm/amdgpu: Fix missing parameter desc for 'xcp_id' in amdgpu_amdkfd_reserve_mem_limit
Fix these warnings by adding 'xcp_id' argument.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c:160: warning: Function parameter or member 'xcp_id' not described in 'amdgpu_amdkfd_reserve_mem_limit'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:40 -04:00
Srinivasan Shanmugam
1bae03aab2 drm/amdgpu: Fix up missing parameter in kdoc for 'inst' in gmc_ v7, v8, v9, v10, v11.c
Fix these warnings by adding 'inst' arguments to kdocs.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c:428: warning: Function parameter or member 'inst' not described in 'gmc_v7_0_flush_gpu_tlb_pasid'
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c:626: warning: Function parameter or member 'inst' not described in 'gmc_v8_0_flush_gpu_tlb_pasid'
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c:423: warning: Function parameter or member 'inst' not described in 'gmc_v10_0_flush_gpu_tlb_pasid'
drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c:328: warning: Function parameter or member 'inst' not described in 'gmc_v11_0_flush_gpu_tlb_pasid'
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c:950: warning: Function parameter or member 'inst' not described in 'gmc_v9_0_flush_gpu_tlb_pasid'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:35 -04:00
Srinivasan Shanmugam
3eeb0d037a drm/amdgpu: Fix up missing kdoc parameter 'inst' in get_wave_count() & kgd_gfx_v9_get_cu_occupancy()
Fix these warnings by adding 'inst' arguments to kdocs.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c:692: warning: Function parameter or member 'inst' not described in 'get_wave_count'
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c:763: warning: Function parameter or member 'inst' not described in 'kgd_gfx_v9_get_cu_occupancy'

Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:32 -04:00
Srinivasan Shanmugam
ca2943fe0a drm/amdgpu: Fix missing parameter desc for 'xcc_id' in gfx_v7_0.c & amdgpu_rlc.c
Fix these warnings by adding 'xcc_id' arguments.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c:1557: warning: Function parameter or member 'xcc_id' not described in 'gfx_v7_0_select_se_sh'
drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c:38: warning: Function parameter or member 'xcc_id' not described in 'amdgpu_gfx_rlc_enter_safe_mode'
drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c:62: warning: Function parameter or member 'xcc_id' not described in 'amdgpu_gfx_rlc_exit_safe_mode'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:30 -04:00
Lijo Lazar
c6a64ad9b7 drm/amdgpu: Initialize xcc mask
For ASICs which are not initialized through discovery, initialize GFX
cluster as 1.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:21 -04:00
Srinivasan Shanmugam
837d4e071d drm/amdgpu: Fix create_dmamap_sg_bo kdoc warnings
Fix the following gcc with W=1:

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c:292: warning: Cannot understand  * @create_dmamap_sg_bo: Creates a amdgpu_bo object to reflect information

Cc: Felix Kuehling <felix.kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:32:12 -04:00
Srinivasan Shanmugam
9eba1b8b70 drm/amdgpu: Fix up missing kdoc in sdma_v6_0.c
Address a bunch of kdoc warnings:

gcc with W=1
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:248: warning: Function parameter or member 'job' not described in 'sdma_v6_0_ring_emit_ib'
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:248: warning: Function parameter or member 'flags' not described in 'sdma_v6_0_ring_emit_ib'
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:946: warning: Function parameter or member 'timeout' not described in 'sdma_v6_0_ring_test_ib'
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:1125: warning: Function parameter or member 'ring' not described in 'sdma_v6_0_ring_pad_ib'
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:1176: warning: Function parameter or member 'vmid' not described in 'sdma_v6_0_ring_emit_vm_flush'
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:1176: warning: Function parameter or member 'pd_addr' not described in 'sdma_v6_0_ring_emit_vm_flush'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:31:29 -04:00
Srinivasan Shanmugam
66dadf1ab1 drm/amdgpu: Fix up kdoc in amdgpu_acpi.c
Fix these warnings by adding & deleting the deviant arguments.

gcc with W=1
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:906: warning: Function parameter or member 'numa_info' not described in 'amdgpu_acpi_get_node_id'
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:906: warning: Excess function parameter 'nid' description in 'amdgpu_acpi_get_node_id'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:31:26 -04:00
Srinivasan Shanmugam
23616d1ff3 drm/amdgpu: Fix up kdoc in sdma_v4_4_2.c
Address a bunch of kdoc warnings:

gcc with W=1
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:426: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_gfx_stop'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:457: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_rlc_stop'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:470: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_page_stop'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:506: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_ctx_switch_enable'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:794: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_rlc_resume'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:810: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_load_microcode'
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:854: warning: Function parameter or member 'inst_mask' not described in 'sdma_v4_4_2_inst_start'

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:31:23 -04:00
Ikshwaku Chauhan
3a25071a97 drm/amdgpu: enable tmz by default for GC 11.0.1
Add IP GC 11.0.1 in the list of target to have
tmz enabled by default.

Signed-off-by: Ikshwaku Chauhan <ikshwaku.chauhan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:31:20 -04:00
Guchun Chen
8ffd6f0442 drm/amdgpu: keep irq count in amdgpu_irq_disable_all
This can clean up all irq warnings because of unbalanced
amdgpu_irq_get/put when unplugging/unbinding device, and leave
irq count decrease in each ip fini function.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 12:31:12 -04:00
Dan Carpenter
9c9d501b28 drm/amd/amdgpu: Fix up locking etc in amdgpu_debugfs_gprwave_ioctl()
There are two bugs here.
1) Drop the lock if copy_from_user() fails.
2) If the copy fails then the correct error code is -EFAULT instead of
   -EINVAL.

I also broke up the long line and changed "sizeof rd->id" to
"sizeof(rd->id)".

Fixes: 553f973a0d ("drm/amd/amdgpu: Update debugfs for XCC support (v3)")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:10:04 -04:00
James Zhu
9938333a46 drm/amdgpu: use amdxcp platform device as spatial partition
Use amdxcp platform device as spatial partition device.

-v2: remove unused variable

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:08:58 -04:00
Srinivasan Shanmugam
3034983db3 drm/amdgpu: Mark mmhub_v1_8_mmea_err_status_reg as __maybe_unused
Silencing the compiler from below compilation error:

drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c:704:23: error: variable 'mmhub_v1_8_mmea_err_status_reg' is not needed and will not be emitted [-Werror,-Wunneeded-internal-declaration]
static const uint32_t mmhub_v1_8_mmea_err_status_reg[] = {
                      ^
1 error generated.

Mark the variable as __maybe_unused to make it clear to clang that this
is expected, so there is no more warning.

Cc: Christian König <christian.koenig@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:08:43 -04:00
Shiwu Zhang
5d6cd20075 drm/amdgpu: add the accelerator pcie class
v2: add the base class id for accelerator (lijo)
v3: add the new pci class in amdgpu tree (hawking)

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:07:16 -04:00
James Zhu
2310554172 drm/amdgpu: save/restore part of xcp drm_device fields
Redirect xcp allocated drm_device::rdev/pdev/driver with
amdgpu pci_device/drm_device setting. They need be saved
before redirect and restored after unregister xcp drm_device.

-v2: fix warning discarded-qualifiers

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:07:12 -04:00
Shiwu Zhang
20997c04b7 drm/amdgpu: set the APU flag based on package type
Since currently APU and dGPU share the same pcie class
while gmc init needs the flag to set up correctly for upcomming
memory allocations

v2: call get_pkg_type in smuio 13_0_3 is enough (hawking)

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:07:04 -04:00
James Zhu
28bb7f13e7 drm/jpeg: add init value for num_jpeg_rings
Need init new num_jpeg_rings to 1 on jpeg.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Richard Liang <rliang1@amd.com>
Tested-by: Ying Li <ying.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:07:00 -04:00
Shiwu Zhang
491ae27829 drm/amdgpu: complement the 4, 6 and 8 XCC cases
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:02:17 -04:00
Shiwu Zhang
89f8576555 drm/amdgpu: golden settings for ASIC rev_id 0
Suggested by FW team that GB_ADDR_CONFIG is handled by golden
settings in driver to get the expected value

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:02:15 -04:00
Shiwu Zhang
9535a86a40 drm/amdgpu: bypass bios dependent operations
Since bios reading does not work currently so just bypass all operations
related to bios

v2: hardcode the vram info for APP_APU case (hawking)
v3: correct the vram_width with channel number * channel size (lijo)

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:02:12 -04:00
Jiadong Zhu
cfdce59417 drm/amdgpu: Program gds backup address as zero if no gds allocated
It is firmware requirement to set gds_backup_addrlo and gds_backup_addrhi
of DE meta both zero if no gds partition is allocated for the frame.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:02:08 -04:00
Jiadong Zhu
b7941e2fef drm/amdgpu: Reset CP_VMID_PREEMPT after trailing fence signaled
When MEC executes unmap_queue for mid command buffer preemption, it will
kick the write pointer of the gfx ring, set CP_VMID_PREEMPT to trigger the
preemption and wait for CP_VMID_PREEMPT becomes zero after the preemption
done. There is a race condition that PFP may excute the resetting command
before MEC set CP_VMID_PREEMPT. As a result, hang happens as
CP_VMID_PREEMPT is always 0xffff.

To avoid this, we send resetting CP_VMID_PREEMPT command after the trailing
fence is siganled and update gfx write pointer explicitly.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:02:05 -04:00
Srinivasan Shanmugam
8cce16826f drm/amdgpu: Fix unused variable in amdgpu_gfx.c
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c: In function ‘amdgpu_gfx_disable_kcq’:
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c:497:6: warning: variable ‘j’ set but not used [-Wunused-but-set-variable]
  497 |  int j;
      |      ^
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c: In function ‘amdgpu_gfx_disable_kgq’:
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c:528:6: warning: variable ‘j’ set but not used [-Wunused-but-set-variable]
  528 |  int j;
      |      ^
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c: In function ‘amdgpu_gfx_enable_kgq’:
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c:630:12: warning: variable ‘j’ set but not used [-Wunused-but-set-variable]
  630 |  int r, i, j;
      |

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:01:10 -04:00
Srinivasan Shanmugam
a09e206510 drm/amdgpu: Fix defined but not used gfx9_cs_data in gfx_v9_4_3.c
gcc with W=1
In file included from drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:33:
drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h:939:36: warning: ‘gfx9_cs_data’ defined but not used [-Wunused-const-variable=]
  939 | static const struct cs_section_def gfx9_cs_data[] = {
      |

gfx9_cs_data is not used in gfx_v9_4_3.c, hence remove its
include in gfx_v9_4_3.c

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 11:00:53 -04:00
Nathan Chancellor
6c882a573b drm/amdgpu: Fix return types of certain NBIOv7.9 callbacks
When building with clang's -Wincompatible-function-pointer-types-strict,
which ensures that function pointer signatures match exactly to avoid
tripping clang's Control Flow Integrity (kCFI) checks at run time and
will eventually be turned on for the kernel, the following instances
appear in the NBIOv7.9 code:

  drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c:465:32: error: incompatible function pointer types initializing 'int (*)(struct amdgpu_device *)' with an expression of type 'enum amdgpu_gfx_partition (struct amdgpu_device *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          .get_compute_partition_mode = nbio_v7_9_get_compute_partition_mode,
                                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c:467:31: error: incompatible function pointer types initializing 'u32 (*)(struct amdgpu_device *, u32 *)' (aka 'unsigned int (*)(struct amdgpu_device *, unsigned int *)') with an expression of type 'enum amdgpu_memory_partition (struct amdgpu_device *, u32 *)' (aka 'enum amdgpu_memory_partition (struct amdgpu_device *, unsigned int *)') [-Werror,-Wincompatible-function-pointer-types-strict]
          .get_memory_partition_mode = nbio_v7_9_get_memory_partition_mode,
                                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  2 errors generated.

Change the return types of these callbacks to match the prototypes to
clear up the warning and avoid tripping kCFI at run time. Both functions
return a value from ffs(), which is an integer that can fit into either
int or unsigned int.

Fixes: 98a54e88e8 ("drm/amdgpu: add sysfs node for compute partition mode")
Fixes: ea2d2f8ece ("drm/amdgpu: detect current GPU memory partition mode")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:59:07 -04:00
Lijo Lazar
3525844d48 drm/amdgpu: Use single copy per SDMA instance type (v2)
v1: Only single copy per instance type is required for PSP. All instance types
use the same firmware copy. (Lijo)

v2: Apply the change into amdgpu_sdma_init_microcode() due to rebase. (Morris)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:57:16 -04:00
Guchun Chen
93ab59ac6d drm/amdgpu: switch to unified amdgpu_ring_test_helper
This will simplify code.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:57:13 -04:00
Guchun Chen
232f243189 drm/amdgpu/gfx: set sched.ready status after ring/IB test in gfx
sched.ready is nothing with ring initialization, it needs to set
to be true after ring/IB test in amdgpu_ring_test_helper to tell
the ring is ready for submission.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:57:11 -04:00
Guchun Chen
61c31b8b6c drm/amdgpu/sdma: set sched.ready status after ring/IB test in sdma
sched.ready is nothing with ring initialization, it needs to set
to be true after ring/IB test in amdgpu_ring_test_helper to tell
the ring is ready for submission.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:57:07 -04:00
Lijo Lazar
194224a54c drm/amdgpu: Fix warnings
Fix warnings reported by kernel test bot/smatch

smatch warnings:
drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c:65 amdgpu_xcp_run_transition()
error: buffer overflow 'xcp_mgr->xcp' 8 <= 8

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Link: https://lore.kernel.org/r/202305231453.I0bXngYn-lkp@intel.com/
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:56:58 -04:00
Srinivasan Shanmugam
413521a4c9 drm/amd/amdgpu: Fix warnings in amdgpu_irq.c
checkpatch reports:

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: braces {} are not necessary for any arm of this statement
+               if (nvec <= 0) {
[...]
+               } else {
[...]
WARNING: Block comments use a trailing */ on a separate line

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:55:38 -04:00
Mukul Joshi
c3aaca43fb drm/amdgpu: Add a low priority scheduler for VRAM clearing
Add a low priority DRM scheduler for VRAM clearing instead of using
the exisiting high priority scheduler. Use the high priority scheduler
for migrations and evictions.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:54:40 -04:00
Jiapeng Chong
1fbc69b8f5 drm/amdgpu/vcn: Modify mismatched function name
No functional modification involved.

drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c:374: warning: expecting prototype for vcn_v4_0_mc_resume_dpg_mode(). Prototype was for vcn_v4_0_3_mc_resume_dpg_mode() instead.
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c:631: warning: expecting prototype for vcn_v4_0_enable_clock_gating(). Prototype was for vcn_v4_0_3_enable_clock_gating() instead.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=5284
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:54:37 -04:00
Jiapeng Chong
aaff9c0899 drm/amdgpu: Modify mismatched function name
No functional modification involved.

drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:426: warning: expecting prototype for sdma_v4_4_2_gfx_stop(). Prototype was for sdma_v4_4_2_inst_gfx_stop() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:457: warning: expecting prototype for sdma_v4_4_2_rlc_stop(). Prototype was for sdma_v4_4_2_inst_rlc_stop() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:470: warning: expecting prototype for sdma_v4_4_2_page_stop(). Prototype was for sdma_v4_4_2_inst_page_stop() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:506: warning: expecting prototype for sdma_v4_4_2_ctx_switch_enable(). Prototype was for sdma_v4_4_2_inst_ctx_switch_enable() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:561: warning: expecting prototype for sdma_v4_4_2_enable(). Prototype was for sdma_v4_4_2_inst_enable() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:798: warning: expecting prototype for sdma_v4_4_2_rlc_resume(). Prototype was for sdma_v4_4_2_inst_rlc_resume() instead.
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c:814: warning: expecting prototype for sdma_v4_4_2_load_microcode(). Prototype was for sdma_v4_4_2_inst_load_microcode() instead.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=5283
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:54:34 -04:00
Jiapeng Chong
e7665d0ca7 drm/amdgpu: Remove duplicate include
./drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c: amdgpu_xcp.h is included more than once.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=5281
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:54:31 -04:00
Philip Yang
acf429dcac drm/amdkfd: Align partition memory size to page size
The compute partition memory size calculated from KFD_XCP_MEMORY_SIZE
may not align to page size if xcp_mgr->num_xcp_per_mem_partition is 6.

Change the KFD_XCP_MEMORY_SIZE macro to return page align size, so KFD
node memory size reported in sysfs is page align size, to avoid
application VRAM allocation failure because application may use the size
directly and Thunk requires the memory allocation size is page size
align.

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>
2023-06-09 10:53:03 -04:00
Tom Rix
803e4c9efc drm/amdgpu: remove unused variable num_xcc
gcc with W=1 reports
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:2138:13: error: variable
  ‘num_xcc’ set but not used [-Werror=unused-but-set-variable]
 2138 |         int num_xcc;
      |             ^~~~~~~

This variable is not used so remove it.

Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:52:45 -04:00
Arnd Bergmann
1501fe94ee drm/amdgpu: fix acpi build warnings
Two newly introduced functions are in the global namespace but have no prototypes
or callers outside of amdgpu_acpi.c, another function is static but only has
a caller inside of an #ifdef:

drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:902:13: error: no previous prototype for 'amdgpu_acpi_get_node_id' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:928:30: error: no previous prototype for 'amdgpu_acpi_get_dev' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:860:33: error: 'amdgpu_acpi_get_numa_info' defined but not used [-Werror=unused-function]

Avoid the warnings by marking all of them static and ensuring that the compiler is
able to see the callsites.

v2: rebase on latest code (Alex)

Fixes: fa0497c34e ("drm/amdgpu: Add API to get numa information of XCC")
Fixes: 1cc823011a ("drm/amdgpu: Store additional numa node information")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:51:35 -04:00
Arnd Bergmann
1f9bb94f12 drm/amdgpu: use %pad format string for dma_addr_t
DMA addresses can be shorter than u64, which results in a broken debug output:

drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c: In function 'amdgpu_gart_table_ram_alloc':
drivers/gpu/drm/amd/amdgpu/amdgpu.h:41:22: error: format '%llx' expects argument of type 'long long unsigned int', but argument 4 has type 'dma_addr_t' {aka 'unsigned int'} [-Werror=format=]
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c:146:9: note: in expansion of macro 'dev_info'
  146 |         dev_info(adev->dev, "%s dma_addr:%llx\n", __func__, dma_addr);

Use the special %pad format string and pass the DMA address by reference.

Fixes: c9a502e981 ("drm/amdgpu: Allocate GART table in RAM for AMD APU")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:50:55 -04:00
Arnd Bergmann
1b177b5c68 drm/amdgpu:mark aqua_vanjaram_reg_init.c function as static
A few newly added global functions have no prototype, which causes warnings:

drivers/gpu/drm/amd/amdgpu/aqua_vanjaram_reg_init.c:169:5: error: no previous prototype for 'aqua_vanjaram_select_scheds' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/aqua_vanjaram_reg_init.c:310:5: error: no previous prototype for '__aqua_vanjaram_get_xcc_per_xcp' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/aqua_vanjaram_reg_init.c:337:5: error: no previous prototype for '__aqua_vanjaram_get_xcp_ip_info' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/aqua_vanjaram_reg_init.c:593:5: error: no previous prototype for 'aqua_vanjaram_get_xcp_ip_details' [-Werror=missing-prototypes]

There are no callers from other files, so just mark them as 'static'.

Fixes: cd7d8400aa ("drm/amdgpu: add partition schedule for GC(9, 4, 3)")
Fixes: 9cb18287d8 ("drm/amdgpu: Add SOC partition funcs for GC v9.4.3")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:48:43 -04:00
Arnd Bergmann
d522458e63 drm/amdkfd: mark local functions as static
The file was newly added and causes some -Wmissing-prototype warnings:

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c:57:5: error: no previous prototype for 'kgd_gfx_v9_4_3_hqd_sdma_load' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c:126:5: error: no previous prototype for 'kgd_gfx_v9_4_3_hqd_sdma_dump' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c:163:6: error: no previous prototype for 'kgd_gfx_v9_4_3_hqd_sdma_is_occupied' [-Werror=missing-prototypes]
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c:181:5: error: no previous prototype for 'kgd_gfx_v9_4_3_hqd_sdma_destroy' [-Werror=missing-prototypes]

Mark these all as 'static' since there are no outside callers.

Fixes: a805889a15 ("drm/amdkfd: Update SDMA queue management for GFX9.4.3")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:47:53 -04:00
Harshit Mogalapalli
6dabce860d drm/amdgpu: Fix unsigned comparison with zero in gmc_v9_0_process_interrupt()
Smatch warns:
	drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c:579:
	unsigned 'xcc_id' is never less than zero.

gfx_v9_4_3_ih_to_xcc_inst() returns negative numbers as well.
Fix this by changing type of xcc_id to int.

Fixes: 98b2e9cad2 ("drm/amdgpu: correct the vmhub index when page fault occurs")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:45:46 -04:00
Colin Ian King
9f77af014c drm/amdgpu: Fix a couple of spelling mistakes in info and debug messages
There are a couple of spelling mistakes, one in a dev_info message
and the other in a dev_debug message. Fix them.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:45:43 -04:00
Lijo Lazar
a3ffabb250 drm/amdgpu: Disable interrupt tracker on NBIOv7.9
Enabling nBIF interrupt history tracker prevents LCLK deep sleep,
hence disable it

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:45:23 -04:00
Shiwu Zhang
89fb3020d6 drm/amdgpu: init the XCC_DOORBELL_FENCE regs
add the the init_registers callback for nbio_v7_9

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:44:37 -04:00
Tao Zhou
332bb09352 drm/amdgpu: remove unused definition
mmhub_v1_8_mmea_cgtt_clk_cntl_reg is defined but not used.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:44:33 -04:00
Srinivasan Shanmugam
1893549af6 drm/amdgpu: Fix uninitialized variable in gfxhub_v1_2_xcp_resume
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c:657:6: error: variable 'ret' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized]
        if (!amdgpu_sriov_vf(adev))
            ^~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c:660:9: note: uninitialized use occurs here
        return ret;
               ^~~
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c:657:2: note: remove the 'if' if its condition is always true
        if (!amdgpu_sriov_vf(adev))
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c:648:9: note: initialize the variable 'ret' to silence this warning
        int ret;
               ^
                = 0
1 error generated.

Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:44:30 -04:00
Srinivasan Shanmugam
40e39d7227 drm/amdgpu: Fix unused amdgpu_acpi_get_numa_info function in amdgpu_acpi_get_node_id()
Fix the below compiler complaining error:

drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:860:33: error: unused function 'amdgpu_acpi_get_numa_info' [-Werror,-Wunused-function]
static struct amdgpu_numa_info *amdgpu_acpi_get_numa_info(uint32_t pxm)
                                ^
1 error generated.

By guarding amdgpu_acpi_get_numa_info & amdgpu_acpi_get_numa_size
function, only when CONFIG_ACPI_NUMA is enabled.

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:44:27 -04:00
Christoph Hellwig
73ade646c5 drm/amdgpu: stop including swiotlb.h
amdgpu does not need swiotlb.h, so stop including it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:42:21 -04:00
Srinivasan Shanmugam
b3b0e016ec drm/amdgpu: Fix uninitalized variable in jpeg_v4_0_3_is_idle & jpeg_v4_0_3_wait_for_idle
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c:752:4: error: variable 'ret' is uninitialized when used here [-Werror,-Wuninitialized]
                        ret &= ((RREG32_SOC15_OFFSET(
                        ^~~
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c:745:10: note: initialize the variable 'ret' to silence this warning
        bool ret;
                ^
                 = 0
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c:774:4: error: variable 'ret' is uninitialized when used here [-Werror,-Wuninitialized]
                        ret &= SOC15_WAIT_ON_RREG_OFFSET(
                        ^~~
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c:767:9: note: initialize the variable 'ret' to silence this warning
        int ret;
               ^
                = 0
2 errors generated.

Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: James Zhu <James.Zhu@amd.com>
Cc: Leo Liu <leo.liu@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:58 -04:00
Srinivasan Shanmugam
ff6b11cc72 drm/amd/amdgpu: Fix errors & warnings in mmhub_v1_8.c
Fix below errors & warnings reported by checkpatch:

ERROR: code indent should use tabs where possible
WARNING: please, no space before tabs
WARNING: please, no spaces at the start of a line
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
ERROR: space prohibited before that '++' (ctx:WxB)
WARNING: Block comments use a trailing */ on a separate line

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:53 -04:00
Likun Gao
20a29ac091 drm/amdgpu: retire set_vga_state for some ASIC
set_vga_state operation only allowed on SI generation
ASIC, retire the realted function on those ASIC which
did not do anything.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:50 -04:00
Likun Gao
b336c681bd drm/amdgpu: fix vga_set_state NULL pointer issue
Fix NULL pointer issue for vga_set_state function
as not all the ASIC need this operation.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:40 -04:00
Srinivasan Shanmugam
d7b8e68dc0 drm/amdgpu: Fix uninitialized variable in gfx_v9_4_3_cp_resume
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:1925:6: error: variable 'r' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized]
        if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:1931:6: note: uninitialized use occurs here
        if (r)
            ^
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:1925:2: note: remove the 'if' if its condition is always true
        if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c:1923:7: note: initialize the variable 'r' to silence this warning
        int r, i, num_xcc;
             ^
              = 0
1 error generated.

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:35 -04:00
Horatio Zhang
a34b09060a drm/amdgpu: add RAS POISON interrupt funcs for jpeg_v4_0
Add ras_poison_irq and functions. And fix the amdgpu_irq_put
call trace in jpeg_v4_0_hw_fini.

[   50.497562] RIP: 0010:amdgpu_irq_put+0xa4/0xc0 [amdgpu]
[   50.497619] RSP: 0018:ffffaa2400fcfcb0 EFLAGS: 00010246
[   50.497620] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
[   50.497621] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[   50.497621] RBP: ffffaa2400fcfcd0 R08: 0000000000000000 R09: 0000000000000000
[   50.497622] R10: 0000000000000000 R11: 0000000000000000 R12: ffff99b2105242d8
[   50.497622] R13: 0000000000000000 R14: ffff99b210500000 R15: ffff99b210500000
[   50.497623] FS:  0000000000000000(0000) GS:ffff99b518480000(0000) knlGS:0000000000000000
[   50.497623] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   50.497624] CR2: 00007f9d32aa91e8 CR3: 00000001ba210000 CR4: 0000000000750ee0
[   50.497624] PKRU: 55555554
[   50.497625] Call Trace:
[   50.497625]  <TASK>
[   50.497627]  jpeg_v4_0_hw_fini+0x43/0xc0 [amdgpu]
[   50.497693]  jpeg_v4_0_suspend+0x13/0x30 [amdgpu]
[   50.497751]  amdgpu_device_ip_suspend_phase2+0x240/0x470 [amdgpu]
[   50.497802]  amdgpu_device_ip_suspend+0x41/0x80 [amdgpu]
[   50.497854]  amdgpu_device_pre_asic_reset+0xd9/0x4a0 [amdgpu]
[   50.497905]  amdgpu_device_gpu_recover.cold+0x548/0xcf1 [amdgpu]
[   50.498005]  amdgpu_debugfs_reset_work+0x4c/0x80 [amdgpu]
[   50.498060]  process_one_work+0x21f/0x400
[   50.498063]  worker_thread+0x200/0x3f0
[   50.498064]  ? process_one_work+0x400/0x400
[   50.498065]  kthread+0xee/0x120
[   50.498067]  ? kthread_complete_and_exit+0x20/0x20
[   50.498068]  ret_from_fork+0x22/0x30

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:29 -04:00
Horatio Zhang
674f90f83b drm/amdgpu: add RAS POISON interrupt funcs for jpeg_v2_6
Add ras_poison_irq and functions.

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:27 -04:00
Horatio Zhang
18dad20c3d drm/amdgpu: separate ras irq from jpeg instance irq for UVD_POISON
Separate jpegbRAS poison consumption handling from the instance irq, and
register dedicated ras_poison_irq src and funcs for UVD_POISON.

v2:
- Separate ras irq from jpeg instance irq
- Improve the subject and code comments

v3:
- Split the patch into three parts
- Improve the code comments

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:23 -04:00
Horatio Zhang
66a11ecbde drm/amdgpu: add RAS POISON interrupt funcs for vcn_v4_0
Add ras_poison_irq and functions. And fix the amdgpu_irq_put
call trace in vcn_v4_0_hw_fini.

[   44.563572] RIP: 0010:amdgpu_irq_put+0xa4/0xc0 [amdgpu]
[   44.563629] RSP: 0018:ffffb36740edfc90 EFLAGS: 00010246
[   44.563630] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
[   44.563630] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[   44.563631] RBP: ffffb36740edfcb0 R08: 0000000000000000 R09: 0000000000000000
[   44.563631] R10: 0000000000000000 R11: 0000000000000000 R12: ffff954c568e2ea8
[   44.563631] R13: 0000000000000000 R14: ffff954c568c0000 R15: ffff954c568e2ea8
[   44.563632] FS:  0000000000000000(0000) GS:ffff954f584c0000(0000) knlGS:0000000000000000
[   44.563632] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   44.563633] CR2: 00007f028741ba70 CR3: 000000026ca10000 CR4: 0000000000750ee0
[   44.563633] PKRU: 55555554
[   44.563633] Call Trace:
[   44.563634]  <TASK>
[   44.563634]  vcn_v4_0_hw_fini+0x62/0x160 [amdgpu]
[   44.563700]  vcn_v4_0_suspend+0x13/0x30 [amdgpu]
[   44.563755]  amdgpu_device_ip_suspend_phase2+0x240/0x470 [amdgpu]
[   44.563806]  amdgpu_device_ip_suspend+0x41/0x80 [amdgpu]
[   44.563858]  amdgpu_device_pre_asic_reset+0xd9/0x4a0 [amdgpu]
[   44.563909]  amdgpu_device_gpu_recover.cold+0x548/0xcf1 [amdgpu]
[   44.564006]  amdgpu_debugfs_reset_work+0x4c/0x80 [amdgpu]
[   44.564061]  process_one_work+0x21f/0x400
[   44.564062]  worker_thread+0x200/0x3f0
[   44.564063]  ? process_one_work+0x400/0x400
[   44.564064]  kthread+0xee/0x120
[   44.564065]  ? kthread_complete_and_exit+0x20/0x20
[   44.564066]  ret_from_fork+0x22/0x30

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:16 -04:00
Horatio Zhang
46d75d2300 drm/amdgpu: add RAS POISON interrupt funcs for vcn_v2_6
Add ras_poison_irq and functions.

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:13 -04:00
Horatio Zhang
2ecf927b17 drm/amdgpu: separate ras irq from vcn instance irq for UVD_POISON
Separate vcn RAS poison consumption handling from the instance irq, and
register dedicated ras_poison_irq src and funcs for UVD_POISON.

v2:
- Separate ras irq from vcn instance irq
- Improve the subject and code comments

v3:
- Split the patch into three parts
- Improve the code comments

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:11 -04:00
YuanShang
c77b3608b8 drm/amdgpu: Remove IMU ucode in vf2pf
The IMU firmware is loaded on the host side, not the guest.
Remove IMU in vf2pf ucode id enum.

Signed-off-by: YuanShang <YuanShang.Mao@amd.com>
Reviewed-By: Horace Chen <horace.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:07 -04:00
Shiwu Zhang
e825fb641b drm/amdgpu: fix the memory override in kiq ring struct
This is introduced by the code merge and will let the
adev->gfx.kiq[0].ring struct being overrided

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:04 -04:00
Shiwu Zhang
c796d7e039 drm/amdgpu: add the smu_v13_0_6 and gfx_v9_4_3 ip block
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:41:02 -04:00
Jesse Zhang
b3122c9269 drm/amdgpu: don't enable secure display on incompatible platforms
[why]
[drm] psp gfx command LOAD_TA(0x1) failed and response status is (0x7)
[drm] psp gfx command INVOKE_CMD(0x3) failed and response status is (0x4)
amdgpu 0000:04:00.0: amdgpu: Secure display: Generic Failure.

[how]
don't enable secure display on incompatible platforms

Suggested-by: Aaron Liu <aaron.liu@amd.com>
Signed-off-by: Jesse zhang <jesse.zhang@amd.com>
Reviewed-by: Aaron Liu <aaron.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:40:57 -04:00
Sukrut Bellary
1385d88c6a drm:amd:amdgpu: Fix missing buffer object unlock in failure path
smatch warning -
1) drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:3615 gfx_v9_0_kiq_resume()
warn: inconsistent returns 'ring->mqd_obj->tbo.base.resv'.

2) drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c:6901 gfx_v10_0_kiq_resume()
warn: inconsistent returns 'ring->mqd_obj->tbo.base.resv'.

Signed-off-by: Sukrut Bellary <sukrut.bellary@linux.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:40:52 -04:00
Bas Nieuwenhuizen
a2b308044d drm/amdgpu: Validate VM ioctl flags.
None have been defined yet, so reject anybody setting any. Mesa sets
it to 0 anyway.

Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2023-06-09 10:40:25 -04:00
Su Hui
109b4d8cfe drm/amdgpu: remove unnecessary (void*) conversions
No need cast (void*) to (struct amdgpu_device *).

Signed-off-by: Su Hui <suhui@nfschina.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:40:12 -04:00
Tong Liu01
04e8595819 drm/amdgpu: fix incorrect pcie_gen_mask in passthrough case
[why]
Passthrough case is treated as root bus and pcie_gen_mask is set as
default value that does not support GEN 3 and GEN 4 for PCIe link
speed. So PCIe link speed will be downgraded at smu hw init in
passthrough condition

[how]
Move get pci info after detect virtualization and check if it is
passthrough case when set pcie_gen_mask

Signed-off-by: Tong Liu01 <Tong.Liu01@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:40:00 -04:00
Jack Xiao
e602157ec0 drm/amdgpu: fix S3 issue if MQD in VRAM
1. Need flush HDP for MQD putting in vram
2. Zero out mes MQD

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:33 -04:00
Srinivasan Shanmugam
e03f04b849 drm/amdgpu: Fix warnings in amdgpu _sdma, _ucode.c
Fix below checkpatch warnings:

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: Comparisons should place the constant on the right side of the test
WARNING: Missing a blank line after declarations

Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:29 -04:00
Srinivasan Shanmugam
f10984a353 drm/amd/amdgpu: Fix errors & warnings in amdgpu _uvd, _vce.c
Fix below checkpatch errors & warnings:

In amdgpu_uvd.c:

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: Prefer 'unsigned int *' to bare use of 'unsigned *'
WARNING: Missing a blank line after declarations
WARNING: %Lx is non-standard C, use %llx
ERROR: space required before the open parenthesis '('
ERROR: space required before the open brace '{'
WARNING: %LX is non-standard C, use %llX
WARNING: Block comments use * on subsequent lines
+/* multiple fence commands without any stream commands in between can
+   crash the vcpu so just try to emmit a dummy create/destroy msg to
WARNING: Block comments use a trailing */ on a separate line
+   avoid this */
WARNING: braces {} are not necessary for single statement blocks
+               for (j = 0; j < adev->uvd.num_enc_rings; ++j) {
+                       fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring_enc[j]);
+               }

In amdgpu_vce.c:

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: Missing a blank line after declarations
WARNING: %Lx is non-standard C, use %llx
WARNING: Possible repeated word: 'we'
ERROR: space required before the open parenthesis '('

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:22 -04:00
YiPeng Chai
6c47a79b3b drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3
perform mode2 reset for sdma fed error on gfx v11_0_3.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:19 -04:00
Srinivasan Shanmugam
5d0622705f drm/amd/amdgpu: Fix errors & warnings in amdgpu_vcn.c
Fix below checkpatch insisted error & warnings:

ERROR: space required before the open brace '{'
WARNING: braces {} are not necessary for any arm of this statement
+       if ((type == VCN_ENCODE_RING) && (vcn_config & VCN_BLOCK_ENCODE_DISABLE_MASK)) {
[...]
+       } else if ((type == VCN_DECODE_RING) && (vcn_config & VCN_BLOCK_DECODE_DISABLE_MASK)) {
[...]
+       } else if ((type == VCN_UNIFIED_RING) && (vcn_config & VCN_BLOCK_QUEUE_DISABLE_MASK)) {
[...]
ERROR: code indent should use tabs where possible
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: braces {} are not necessary for single statement blocks
+               for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+                       fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
+
ERROR: space required before the open parenthesis '('
WARNING: Missing a blank line after declarations
WARNING: please, no spaces at the start of a line
WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal permissions '0444'.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:15 -04:00
Srinivasan Shanmugam
29f187f71e drm/amd/amdgpu: Fix warnings in amdgpu_encoders.c
Fix below checkpatch warnings:

WARNING: Missing a blank line after declarations
+                       struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
+                       amdgpu_encoder->active_device = amdgpu_encoder->devices & amdgpu_connector->devices;

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:09 -04:00
Srinivasan Shanmugam
01c3f46474 drm/amd/amdgpu: Fix errors & warnings in amdgpu_ttm.c
Fix below checkpatch insisted error & warnings:

ERROR: Macros with complex values should be enclosed in parentheses
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: braces {} are not necessary for single statement blocks
WARNING: Block comments use a trailing */ on a separate line
WARNING: Missing a blank line after declarations

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:38:03 -04:00
Alex Deucher
0ce50b2efe drm/amdgpu/vcn4: fix endian conversion
sq.is_enabled is a byte so there is no need to endian swap it.

Acked-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:59 -04:00
Alex Deucher
45b3a914d4 drm/amdgpu/gmc9: fix 64 bit division in partition code
Rework logic or use do_div() to avoid problems on 32 bit.

v2: add a missing case for XCP macro
v3: fix out of bounds array access
v4: fix xcp handling harder

Acked-by: Guchun Chen <guchun.chen@amd.com> (v1)
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> (v3)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:52 -04:00
Tao Zhou
92ecb92ccc drm/amdgpu: initialize RAS for gfx_v9_4_3
Register GFX RAS functions and initialize GFX RAS.

v2: remove xcp operations.
v3: reuse the return value of gfx_ras_sw_init.

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>
2023-06-09 10:37:50 -04:00
Tao Zhou
0386d52d15 drm/amdgpu: add sq timeout status functions for gfx_v9_4_3
Query and reset sq timeout status.

v2: change instance from 0 to xcc_id for register access.

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>
2023-06-09 10:37:47 -04:00
Tao Zhou
30feef0676 drm/amdgpu: add RAS error count reset for gfx_v9_4_3
Add GFX RAS error count reset function.

v2: remove xcp operation.
    only select_se_sh when instance number is more than 1.
v3: add check for se_num before select_se_sh.
    change instance from 0 to xcc_id for register access.

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>
2023-06-09 10:37:44 -04:00
Tao Zhou
bfa84da618 drm/amdgpu: add RAS error count query for gfx_v9_4_3
Query GFX RAS ce/ue count.

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>
2023-06-09 10:37:42 -04:00
Tao Zhou
5c1c09a716 drm/amdgpu: add RAS error count definitions for gfx_v9_4_3
Prepare for the query of GFX RAS ce/ue count.

v2: remove xcp operation.
    only select_se_sh when instance number is more than 1.
v3: add more CE/UE registsers to query list.
    add check for se_num before select_se_sh.
    change instance from 0 to xcc_id for register access.
v4: move gfx memory id definitions to gfx_v9_4_3.
v5: create a dedicated patch for adding error count query function.

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>
2023-06-09 10:37:39 -04:00
Tao Zhou
77462ab8c6 drm/amdgpu: add RAS definitions for GFX
Add common GFX RAS definitions.

v2: remove instance from amdgpu_gfx_ras_reg_entry,
    amdgpu_ras_err_status_reg_entry has already defined it.
v3: remove memory id definitions from amdgpu_gfx.h, they are
    related to IP version.

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>
2023-06-09 10:37:37 -04:00
Tao Zhou
47e7f527c8 drm/amdgpu: add RAS status reset for gfx_v9_4_3
Reset GFX RAS status registers.

v2: fix typo in title.
    remove xcp operation.
v3: change instance from 0 to xcc_id for register access.

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>
2023-06-09 10:37:32 -04:00
Tao Zhou
bf16235b39 drm/amdgpu: add RAS status query for gfx_v9_4_3
Query GFX RAS status.

v2: remove xcp operation.
v3: change instance from 0 to xcc_id for register access.

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>
2023-06-09 10:37:29 -04:00
Tao Zhou
d78c71321e drm/amdgpu: add GFX RAS common function
The common function can help reduce redundant code.

v2: remove xcp operation, only need to do RAS operations for all
instances.
v3: remove check for GFX RAS support, will be checked in higher level.
    add amdgpu prefix for the function name.

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>
2023-06-09 10:37:26 -04:00
Hawking Zhang
9a3ce1a7a9 drm/amdgpu: Do not access members of xcp w/o check (v2)
Not all the asic needs xcp. ensure check xcp availabity
before accessing its member.

v2: add missing change in kfd_topology.c

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>
2023-06-09 10:37:24 -04:00
Tao Zhou
f464c5dd4d drm/amdgpu: add check for RAS instance mask
The mask is only needed to be set when RAS block instance number is
more than 1 and invalid bits should be also masked out.
We only check valid bits for GFX and SDMA block for now, and will
add check for other RAS blocks in the future.

v2: move the check under injection operation since the mask is only
    used by RAS error inject.
v3: add valid bits handling for SDMA.
v4: print message if the mask is adjusted.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:18 -04:00
Tao Zhou
6e3c51a581 drm/amdgpu: remove RAS GFX injection for gfx_v9_4/gfx_v9_4_2
No special requirement in RAS injection for the two versions, switch to
use default injection interface.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:15 -04:00
Tao Zhou
27c5f29526 drm/amdgpu: reorganize RAS injection flow
So GFX RAS injection could use default function if it doesn't define its
own injection interface.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:13 -04:00
Tao Zhou
2c22ed0bdb drm/amdgpu: add instance mask for RAS inject
User can specify injected instances by the mask. For backward
compatibility, the mask value is incorporated into sub block index
without interface change of RAS TA.
User uses logical mask and driver should convert it to physical value
before sending it to RAS TA.

v2: update parameter name.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:10 -04:00
Tao Zhou
af2ba36883 drm/amdgpu: convert logical instance mask to physical one
Convert instance mask for the convenience of RAS TA.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:08 -04:00
Mukul Joshi
40b832aac0 drm/amdgpu: Enable IH CAM on GFX9.4.3
This patch enables IH CAM on GFX9.4.3 ASIC.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:04 -04:00
Philip Yang
3cde91172d drm/amdgpu: Correct get_xcp_mem_id calculation
Current calculation only works for NPS4/QPX mode, correct it for
NPS4/CPX mode.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:37:02 -04:00
Philip Yang
84b4dd3f84 drm/amdkfd: Refactor migrate init to support partition switch
Rename smv_migrate_init to a better name kgd2kfd_init_zone_device
because it setup zone devive pgmap for page migration and keep it in
kfd_migrate.c to access static functions svm_migrate_pgmap_ops. Call it
only once in amdgpu_device_ip_init after adev ip blocks are initialized,
but before amdgpu_amdkfd_device_init initialize kfd nodes which enable
SVM support based on pgmap.

svm_range_set_max_pages is called by kgd2kfd_device_init everytime after
switching compute partition mode.

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>
2023-06-09 10:36:58 -04:00
Shiwu Zhang
44a9766555 drm/amdgpu: route ioctls on primary node of XCPs to primary device
During XCP init, unlike the primary device, there is no amdgpu_device
attached to each XCP's drm_device

In case that user trying to open/close the primary node of XCP drm_device
this rerouting is to solve the NULL pointer issue causing by referring
to any member of the amdgpu_device

 BUG: unable to handle page fault for address: 0000000000020c80
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 Oops: 0002 [#1] PREEMPT SMP NOPTI
 Call Trace:
  <TASK>
  lock_timer_base+0x6b/0x90
  try_to_del_timer_sync+0x2b/0x80
  del_timer_sync+0x29/0x40
  flush_delayed_work+0x1c/0x50
  amdgpu_driver_open_kms+0x2c/0x280 [amdgpu]
  drm_file_alloc+0x1b3/0x260 [drm]
  drm_open+0xaa/0x280 [drm]
  drm_stub_open+0xa2/0x120 [drm]
  chrdev_open+0xa6/0x1c0

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:36:53 -04:00
Mukul Joshi
1c77527a69 drm/amdkfd: Fix memory reporting on GFX 9.4.3
This patch fixes memory reporting on the GFX 9.4.3 APU and dGPU
by reporting available memory on a per partition basis. If its an
APU, available and used memory calculations take into account
system and TTM memory.

v2: squash in fix ("drm/amdkfd: Fix array out of bound warning")
    squash in fix ("drm/amdgpu: Update memory reporting for GFX9.4.3")

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:36:48 -04:00
Mukul Joshi
315e29eca5 drm/amdkfd: Move local_mem_info to kfd_node
We need to track memory usage on a per partition basis. To do
that, store the local memory information in KFD node instead
of kfd device.

v2: squash in fix ("amdkfd: Use mem_id to access mem_partition info")

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:36:45 -04:00
James Zhu
b125b80bd5 drm/amdgpu: use xcp partition ID for amdgpu_gem
Find xcp_id from amdgpu_fpriv, use it for amdgpu_gem_object_create.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 10:36:43 -04:00
Philip Yang
2fa9ff25de drm/amdgpu: KFD graphics interop support compute partition
kfd_ioctl_get_dmabuf use the amdgpu bo xcp_id to get the gpu_id of the
KFD node from the exported dmabuf_adev, and then create kfd bo on the
correct adev and KFD node when importing the amdgpu bo to KFD.

Remove function kfd_device_by_adev, it is not needed as it is the same
result as dmabuf_adev->kfd.dev->nodes[0]->id.

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>
2023-06-09 10:36:41 -04:00
Philip Yang
3ebfd221c1 drm/amdkfd: Store xcp partition id to amdgpu bo
For memory accounting per compute partition and export drm amdgpu bo and
then import to KFD, we need the xcp id to account the memory usage or
find the KFD node of the original amdgpu bo to create the KFD bo on the
correct adev KFD node.

Set xcp_id_plus1 of amdgpu_bo_param to create bo and store xcp_id to
amddgpu bo. Add helper macro to get the mem_id from adev and xcp_id.

v2: squash in fix ("drm/amdgpu: Fix BO creation failure on GFX 9.4.3 dGPU")

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>
2023-06-09 10:36:38 -04:00
Philip Yang
6cfba94a77 drm/amdgpu: dGPU mode set VRAM range lpfn as exclusive
TTM place lpfn is exclusive used as end (start + size) in drm and buddy
allocator, adev->gmc memory partition range lpfn is inclusive (start +
size - 1), should plus 1 to set TTM place lpfn.

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>
2023-06-09 10:36:35 -04:00
Philip Yang
ea7bf2f220 drm/amdgpu: Alloc page table on correct memory partition
Alloc kernel mode page table bo uses the amdgpu_vm->mem_id + 1 as bp
mem_id_plus1 parameter. For APU mode, select the correct TTM pool to
alloc page from the corresponding memory partition, this will be the
closest NUMA node. For dGPU mode, select the correct address range for
vram manager.

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>
2023-06-09 10:36:33 -04:00
Philip Yang
dc12f9edde drm/amdkfd: Update MTYPE for far memory partition
Use MTYPE RW/MTYPE_CC for mapping system memory or VRAM to KFD node
within the same memory partition, use MTYPE_NC for mapping on KFD node
from the far memory partition of the same socket or from another socket
on same XGMI hive.

On NPS4 or 4P system, MTYPE will be overridden per page depending on
the memory NUMA node id and vm->mem_id.

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>
2023-06-09 10:36:30 -04:00
Philip Yang
7f6db89418 drm/amdgpu: dGPU mode placement support memory partition
dGPU mode uses VRAM manager to validate bo, amdgpu bo placement use the
mem_id  to get the allocation range first, last page frame number
from xcp manager, pass to drm buddy allocator as the allowed range.

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>
2023-06-09 10:36:27 -04:00
Philip Yang
53c5692e7a drm/amdkfd: Alloc memory of GPU support memory partition
For dGPU mode VRAM allocation, create amdgpu_bo from amdgpu_vm->mem_id,
to alloc from the correct memory range.

For APU mode VRAM allocation, set alloc domain to GTT, and set
bp->mem_id_plus1 from amdgpu_vm->mem_id + 1 to create amdgpu_bo, to
allocate system memory from correct NUMA node.

For GTT allocation, use mem_id -1 to allocate system memory from any
NUMA nodes.

Remove amdgpu_ttm_tt_set_mem_pool, to avoid the confusion that memory
maybe allocated from different mem_id.

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>
2023-06-09 10:00:03 -04:00
Philip Yang
f24e924b7e drm/amdgpu: Add memory partition mem_id to amdgpu_bo
Add mem_id_plus1 parameter to amdgpu_gem_object_create and pass it to
amdgpu_bo_create. For dGPU mode allocation, mem_id is used by VRAM
manager to get the memory partition fpfn, lpfn from xcp manager. For APU
native mode allocation, mem_id is used to get NUMA node id from xcp
manager, then pass to TTM as numa pool id to alloc memory from the
specific NUMA node. mem_id -1 means for entire VRAM or any NUMA nodes.

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>
2023-06-09 10:00:00 -04:00
Philip Yang
4c6ce75fdd drm/amdkfd: Show KFD node memory partition info
Show KFD node memory partition id and size, add helper function
KFD_XCP_MEMORY_SIZE to get kfd node memory size, will be used
later to support memory accounting per partition.

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>
2023-06-09 09:59:58 -04:00
Philip Yang
934deb64fd drm/amdgpu: Add memory partition id to amdgpu_vm
If xcp_mgr is initialized, add mem_id to amdgpu_vm structure to store
memory partition number when creating amdgpu_vm for the xcp. The xcp
number is decided when opening the render device, for example
/dev/dri/renderD129 is xcp_id 0, /dev/dri/renderD130 is xcp_id 1.

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>
2023-06-09 09:59:56 -04:00
Philip Yang
d26ea1b346 drm/amdgpu: Add xcp manager num_xcp_per_mem_partition
Used by KFD to check memory limit accounting.

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>
2023-06-09 09:59:48 -04:00
James Zhu
3e7c6fe387 drm/amdgpu: update ref_cnt before ctx free
Update ref_cnt before ctx free.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:44 -04:00
James Zhu
9a18292d41 drm/amdgpu: run partition schedule if it is supported
Run partition schedule if it is supported during ctx init entity.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:42 -04:00
James Zhu
cd7d8400aa drm/amdgpu: add partition schedule for GC(9, 4, 3)
Implement partition schedule for GC(9, 4, 3).

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:39 -04:00
James Zhu
c30e326e48 drm/amdgpu: keep amdgpu_ctx_mgr in ctx structure
Keep amdgpu_ctx_mgr in ctx structure to track fpriv.

v2: add missing fpriv declaration lost in rebase

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:37 -04:00
James Zhu
d425c6f48b drm/amdgpu: add partition scheduler list update
Add partition scheduler list update in late init
and xcp partition mode switch.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:35 -04:00
James Zhu
0a9115fd95 drm/amdgpu: update header to support partition scheduling
Update header to support partition scheduling.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:32 -04:00
James Zhu
797a0a142c drm/amdgpu: add partition ID track in ring
Keep track partition ID in ring.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:30 -04:00
James Zhu
be3800f57c drm/amdgpu: find partition ID when open device
Find partition ID when open device from render device minor.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-and-tested-by: Philip Yang<Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:27 -04:00
James Zhu
2c1c7ba457 drm/amdgpu: support partition drm devices
Support partition drm devices on GC_HWIP IP_VERSION(9, 4, 3).

This is a temporary solution and will be superceded.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-and-tested-by: Philip Yang<Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:20 -04:00
Graham Sider
b9cbd51000 drm/amdgpu/bu: update mtype_local parameter settings
Update mtype_local module parameter to use MTYPE_RW by default.

0: MTYPE_RW (default)
1: MTYPE_NC
2: MTYPE_CC

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:15 -04:00
David Francis
76eb9c95a4 drm/amdgpu/bu: add mtype_local as a module parameter
Selects the MTYPE to be used for local memory,
(0 = MTYPE_CC (default), 1 = MTYPE_NC, 2 = MTYPE_RW)

v2: squash in build fix (Alex)

Reviewed-by: Graham Sider <Graham.Sider@amd.com>
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:13 -04:00
Felix Kuehling
352b919c1e drm/amdgpu: Override MTYPE per page on GFXv9.4.3 APUs
On GFXv9.4.3 NUMA APUs, system memory locality must be determined per
page to choose the correct MTYPE. This patch adds a GMC callback that
can provide this per-page override and implements it for native mode.

Carve-out mode is not yet supported and will use the safe default
(remote) MTYPE for system memory.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-and-tested-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:08 -04:00
Felix Kuehling
1e4a00334a drm/amdgpu: Fix per-BO MTYPE selection for GFXv9.4.3
Treat system memory on NUMA systems as remote by default. Overriding with
a more efficient MTYPE per page will be implemented in the next patch.

No need for a special case for APP APUs. System memory is handled the same
for carve-out and native mode. And VRAM doesn't exist in native mode.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-and-tested-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:05 -04:00
Graham Sider
895797d919 drm/amdgpu/bu: Add use_mtype_cc_wa module param
By default, set use_mtype_cc_wa to 1 to set PTE coherence flag MTYPE_CC
instead of MTYPE_RW by default. This is required for the time being to
mitigate a bug causing XCCs to hit stale data due to TCC marking fully
dirty lines as exclusive.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Reviewed-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:59:03 -04:00
Graham Sider
2e8cc5d317 drm/amdgpu: Use legacy TLB flush for gfx943
Invalidate TLBs via a legacy flush request (flush_type=0) prior to the
heavyweight flush requests (flush_type=2) in gmc_v9_0.c. This is
temporarily required to mitigate a bug causing CPC UTCL1 to return stale
translations after invalidation requests in address range mode.

v2: squash in long term fix "drm/amdgpu: disable extra gfx943 legacy flush on rev1+"

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:58 -04:00
Harish Kasiviswanathan
f915f3af99 drm/amdgpu: For GFX 9.4.3 APU fix vram_usage value
For GFX 9.4.3 APP APU VRAM is allocated in GTT domain. While freeing
memory check for GTT domain instead of VRAM if it is APP APU

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:52 -04:00
Philip Yang
fc021438d0 drm/amdgpu: Enable NPS4 CPX mode
CPX compute mode is valid mode for NPS4 memory partition mode.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:48 -04:00
Philip Yang
610dab118f drm/amdkfd: Move pgmap to amdgpu_kfd_dev structure
VRAM pgmap resource is allocated every time when switching compute
partitions because kfd_dev is re-initialized by post_partition_switch,
As a result, it causes memory region resource leaking and system
memory usage accounting unbalanced.

pgmap resource should be allocated and registered only once when loading
driver and freed when unloading driver, move it from kfd_dev to
amdgpu_kfd_dev.

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>
2023-06-09 09:58:45 -04:00
Lijo Lazar
00e1ab02c2 drm/amdgpu: Skip halting RLC on GFX v9.4.3
RLC-PMFW handshake happens periodically when GFXCLK DPM is enabled and
halting RLC may cause unexpected results. Avoid halting RLC from driver
side.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:41 -04:00
Lijo Lazar
1e91a5f791 drm/amdgpu: Fix register accesses in GFX v9.4.3
Access registers with the right xcc id. Also, remove the unused logic as
PG is not used in GFX v9.4.3

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:39 -04:00
Hawking Zhang
9b337b7d62 drm/amdgpu: Adjust the sequence to query ras error info
It turns out STATUS_VALID_FLAG needs to be checked
ahead of any other fields. ADDRESS_VALID_FLAG and
ERR_INFO_VALID_FLAG only manages ADDRESS and ERR_INFO
field respectively. driver should continue poll
ERR CNT field even ERR_INFO_VALD_FLAG is not set.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:32 -04:00
Hawking Zhang
35d54e21e0 drm/amdgpu: Initialize jpeg v4_0_3 ras function
Initialize jpeg v4_0_3 ras function.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:30 -04:00
Hawking Zhang
570df4bca6 drm/amdgpu: Add reset_ras_error_count for jpeg v4_0_3
Add reset_ras_error_count callback for jpeg v4_0_3.
It will be used to reset jpeg ras error count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:28 -04:00
Hawking Zhang
41e491d8b6 drm/amdgpu: Add query_ras_error_count for jpeg v4_0_3
Add query_ras_error_count callback for jpeg v4_0_3.
It will be used to query and log jpeg error count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:25 -04:00
Hawking Zhang
85f23b0a8c drm/amdgpu: Re-enable VCN RAS if DPG is enabled
VCN RAS enablement sequence needs to be added in
DPG HW init sequence.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:22 -04:00
Hawking Zhang
c3f05ab8c4 drm/amdgpu: Initialize vcn v4_0_3 ras function
Initialize vcn v4_0_3 ras function

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:20 -04:00
Hawking Zhang
6d39fa3fc8 drm/amdgpu: Add reset_ras_error_count for vcn v4_0_3
Add reset_ras_error_count callback for vcn v4_0_3.
It will be used to reset vcn ras error count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:17 -04:00
Hawking Zhang
5e1e227fb7 drm/amdgpu: Add query_ras_error_count for vcn v4_0_3
Add query_ras_error_count callback for vcn v4_0_3.
It will be used to query and log vcn error count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:15 -04:00
Gavin Wan
b4520bfd80 drm/amdgpu: Checked if the pointer NULL before use it.
For SRIOV on some parts, the host driver does not post VBIOS. So the guest
cannot get bios information. Therefore, adev->virt.fw_reserve.p_pf2vf
and adev->mode_info.atom_context are NULL.

Signed-off-by: Gavin Wan <Gavin.Wan@amd.com>
Reviewed-by: Zhigang Luo <Zhigang.Luo@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:09 -04:00
Gavin Wan
46f7b4deb3 drm/amdgpu: Set memory partitions to 1 for SRIOV.
For SRIOV, the memory partitions are set on host drover. Each VF only
has one memory partition. We need set the memory partitions to 1 on
guest driver for SRIOV.

V2: sqaush in fix ("drm/amdgpu: Fix memory range info of GC 9.4.3 VFs")

Signed-off-by: Gavin Wan <Gavin.Wan@amd.com>
Acked-by: Zhigang Luo <zhigang.luo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:06 -04:00
Gavin Wan
b0a3bbf947 drm/amdgpu: Skip using MC FB Offset when APU flag is set for SRIOV.
The MC_VM_FB_OFFSET is PF only register. It cannot be read on VF.
So, the driver should not use MC_VM_FB_OFFSET address to set the
address of dev->gmc.aper_base.

Signed-off-by: Gavin Wan <Gavin.Wan@amd.com>
Reviewed-by: Zhigang Luo <zhigang.luo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:58:02 -04:00
Gavin Wan
63630c9e5c drm/amdgpu: Add PSP supporting PSP 13.0.6 SRIOV ucode init.
Add PSP supporting PSP 13.0.6 SRIOV ucode init.

Signed-off-by: Gavin Wan <Gavin.Wan@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:55 -04:00
Lijo Lazar
ba08e9cb6f drm/amdgpu: Add PSP spatial parition interface
Add PSP ring command interface for spatial partitioning.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:53 -04:00
Lijo Lazar
b6b85c8b43 drm/amdgpu: Return error on invalid compute mode
Return error if an invalid compute partition mode is requested.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:50 -04:00
Lijo Lazar
f9632096be drm/amdgpu: Add compute mode descriptor function
Keep a helper function to get description of compute partition mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:48 -04:00
Lijo Lazar
a0ba127960 drm/amdgpu: Fix unmapping of aperture
When aperture size is zero, there is no mapping done.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:46 -04:00
Rajneesh Bhardwaj
e181be58cc drm/amdgpu: Fix xGMI access P2P mapping failure on GFXIP 9.4.3
On GFXIP 9.4.3, we dont need to rely on xGMI hive info to determine P2P
access.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-and-tested-by:  Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:43 -04:00
Rajneesh Bhardwaj
fcfefd85f1 drm/amdkfd: Native mode memory partition support
For native mode, after amdgpu_bo is created on CPU domain, then call
amdgpu_ttm_tt_set_mem_pool to select the TTM pool using bo->mem_id.
ttm_bo_validate will allocate the memory to the correct memory partition
before mapping to GPUs.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-and-tested-by:  Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:37 -04:00
Philip Yang
1e03322cfe drm/amdgpu: Set TTM pools for memory partitions
For native mode only, create TTM pool for each memory partition to store
the NUMA node id, then the TTM pool will be selected using memory
partition id to allocate memory from the correct partition.

Acked-by: Christian König <christian.koenig@amd.com>
(rajneesh: changed need_swiotlb and need_dma32 to false for pool init)
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-and-tested-by:  Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:31 -04:00
Lijo Lazar
570de94b9c drm/amdgpu: Add auto mode for compute partition
When auto mode is specified, driver will choose the right compute
partition mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:27 -04:00
Lijo Lazar
1589c82a10 drm/amdgpu: Check memory ranges for valid xcp mode
Check the memory ranges available to the device also for deciding a
valid partition mode. Only select combinations are valid for a
particular mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:25 -04:00
Lijo Lazar
e47947abb9 drm/amdgpu: Move initialization of xcp before kfd
After partition switch, fill all relevant xcp information before kfd
starts initialization.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:14 -04:00
Lijo Lazar
15e3eee8d3 drm/amdgpu: Fill xcp mem node in aquavanjaram
Implement callbacks to fill memory node information in aquavanjaram.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:11 -04:00
Lijo Lazar
da539b213d drm/amdgpu: Add callback to fill xcp memory id
Add callback in xcp interface to fill xcp memory id information. Memory
id is used to identify the range/partition of an XCP from the available
memory partitions in device. Also, fill the id information.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:08 -04:00
Lijo Lazar
a433f1f594 drm/amdgpu: Initialize memory ranges for GC 9.4.3
GC 9.4.3 ASICS may have memory split into multiple partitions.Initialize
the memory partition information for each range. The information may be
in the form of a numa node id or a range of pages.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:03 -04:00
Lijo Lazar
14493cb99b drm/amdgpu: Add memory partitions to gmc
Some ASICs have the device memory divided into multiple partitions. The
parititions could be denoted by a numa node or by a range of pages.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:57:01 -04:00
Lijo Lazar
fa0497c34e drm/amdgpu: Add API to get numa information of XCC
Add interface to get numa information of ACPI XCC object. The interface
uses logical id to identify an XCC.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:59 -04:00
Lijo Lazar
1cc823011a drm/amdgpu: Store additional numa node information
Use a struct to store additional numa node information including size
and base address. Add numa_info pointer to xcc object to point to the
relevant structure based on its proximity domain.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:57 -04:00
Lijo Lazar
0f2e1d620e drm/amdgpu: Get supported memory partition modes
Expand the interface to get supported memory partition modes also along
with the current memory partition mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:54 -04:00
Lijo Lazar
b6f90baafe drm/amdgpu: Move memory partition query to gmc
GMC block handles memory related information, it makes more sense to
keep memory partition functions in gmc block.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:50 -04:00
Lijo Lazar
4bdca20579 drm/amdgpu: Add utility functions for xcp
Add utility functions to get details of xcp and iterate through
available xcps.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:48 -04:00
Lijo Lazar
db3b5cb64a drm/amdgpu: Use apt name for FW reserved region
Use the generic term fw_reserved_memory for FW reserve region. This
region may also hold discovery TMR in addition to other reserve
regions. This region size could be larger than discovery tmr size, hence
don't change the discovery tmr size based on this.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:42 -04:00
Lijo Lazar
bc71daff4f drm/amdgpu: Use GPU VA space for IH v4.4.2 in APU
For IH ring buffer and read/write pointers, use GPU VA space rather than
Guest PA on APU configs. Access through Guest PA doesn't work when IOMMU
is enabled. It is also beneficial in NUMA configs as it allocates from
the closest numa pool in a numa enabled system.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:39 -04:00
Lijo Lazar
672c883c26 drm/amdgpu: Simplify aquavanjram instance mapping
Simplify so as to use the same sequence to assign logical to physical
ids for all IPs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:35 -04:00
Lijo Lazar
a3edd1ac70 drm/amdgpu/vcn: Use buffer object's deletion logic
VCN DPG buffer object is intialized to NULL. If allotted, buffer object
deletion logic will take care of NULL check and delete accordingly. This
is useful for cases where indirect sram flag could be manipulated later
after buffer allocation.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:32 -04:00
Sonny Jiang
e7947c021a drm/amdgpu: Use a different value than 0xDEADBEEF for jpeg ring test
The 0xDEADBEEF standard anti-hang value. Use it may cause
fake pass.

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:28 -04:00
Sonny Jiang
96e693ad78 drm/amdgpu: Add a read after write DB_CTRL for vcn_v4_0_3
To make sure VCN DB_CTRL is delivered before doorbell write.

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:26 -04:00
Sonny Jiang
55ff23d9eb drm/amdgpu: fixes a JPEG get write/read pointer bug
Need parentheses for the micro parameters.

Signed-off-by: Sonny Jiang <sonjiang@amd.com>
Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:19 -04:00
Sonny Jiang
26dc0448ef drm/amdgpu: A workaround for JPEG_v4_0_3 ring test fail
The jpeg_v4_0_3 jpeg_pitch register uses UVD_JRBC_SCRATCH0. It needs to
move WREG() to after jpeg_start.
Switch to a posted register write when doing the ring test to make sure
the register write lands before we test the result.

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:15 -04:00
James Zhu
358e6c3830 drm/amdgpu: use physical AID index for ring name
Use physical AID index for VCN/JPEG ring name instead of
logical AID index.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Sonny Jiang <sonny.jiang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:13 -04:00
James Zhu
d3e53452b0 drm/amdgpu/vcn: use dummy register selects AID for VCN_RAM ucode
Use dummy register 0xDEADBEEF selects AID for PSP VCN_RAM ucode.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Sonny Jiang <sonny.jiang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:10 -04:00
Lijo Lazar
6a944ccbf5 drm/amdgpu: Fix harvest reporting of VCN
Use VCN instance mask to check if an instance is harvested or not.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:08 -04:00
Lijo Lazar
fd91d38b52 drm/amdgpu: Use logical ids for VCN/JPEG v4.0.3
Address VCN/JPEG instances using logical ids. Whenever register access is
required, get the physical instance using GET_INST.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:06 -04:00
Lijo Lazar
07bc0ac8ff drm/amdgpu: Add VCN logical to physical id mapping
Add mappings for logical to physical id for VCN/JPEG 4.0.3

v2: make local function static (Alex)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:56:03 -04:00
Lijo Lazar
aaf1090a6c drm/amdgpu: Add instance mask for VCN and JPEG
Keep an instance mask formed by physical instance numbers for VCN and JPEG
IPs. Populate the mask from discovery table information.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:59 -04:00
Sonny Jiang
48d19834ea drm/amdgpu: Load vcn_v4_0_3 ucode during early_init
VCN loading ucode is moved to early_init with using 'amdgpu_ucode_*'
helpers.

Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Sonny Jiang <sonjiang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:56 -04:00
Shiwu Zhang
5ae0ec8b80 drm/amdgpu: preserve the num_links in case of reflection
For topology reflection, each socket to every other socket has the
exactly same topology info as the other way around. So it is safe
to keep the reflected num_links value otherwise it will be overriden
by the link info output of GET_PEER_LINKS command.

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:54 -04:00
Lijo Lazar
f2b8447b1f drm/amdgpu: Fix discovery sys node harvest info
Initalize syfs nodes after harvest information is fetched and fetch the
correct harvest info based on each IP instance.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:51 -04:00
Lijo Lazar
ac772a3c07 drm/amdgpu: Add fallback path for discovery info
If SOC doesn't expose dedicated vram, discovery region may be
available through system memory. Rename the existing interface to
generic read_binary_from_mem and add a fallback path to read from system
memory.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:45 -04:00
Lijo Lazar
368bb1bcfb drm/amdgpu: Read discovery info from system memory
On certain ASICs, discovery info is available at reserved region in system
memory. The location is available through ACPI interface. Add API to read
discovery info from there.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:42 -04:00
Lijo Lazar
6e01882267 drm/amdgpu: Add API to get tmr info from acpi
In certain configs, TMR information is available from ACPI. Add API to
fetch the information.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:40 -04:00
Lijo Lazar
4d5275ab0b drm/amdgpu: Add parsing of acpi xcc objects
Add parsing of ACPI xcc objects and fill in relevant info from them by
invoking the DSM methods.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-and-tested-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:38 -04:00
Lijo Lazar
01ef47477d drm/amdgpu: Add FGCG for GFX v9.4.3
It's not fine grain, behaves similar to MGCG.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:33 -04:00
Lijo Lazar
46d79cbf9a drm/amdgpu: Use transient mode during xcp switch
During partition switch, keep the state as transient mode. Fetch the
latest state if switch fails.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:31 -04:00
Lijo Lazar
ded7d99eb5 drm/amdgpu: Add flags for partition mode query
It's not required to take lock on all cases while querying partition
mode. Querying partition mode during KFD init process doesn't need to
take a lock. Init process after a switch will already be happening under
lock. Control the behaviour by adding flags to xcp_query_partition_mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:29 -04:00
Lijo Lazar
8f2ccaaa37 drm/amdgpu: Add mode-2 reset in SMU v13.0.6
Modifications to mode-2 reset flow for SMU v13.0.6 ASICs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:55:12 -04:00
Stanley.Yang
1ad29cb343 drm/amdgpu: fix sdma instance
It should change logical instance to device instance
to query ras info

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:54:15 -04:00
Le Ma
0c451baf3b drm/amdgpu: change the print level to warn for ip block disabled
Avoid to mislead users as it's not a real error.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:54:12 -04:00
Mukul Joshi
9e4216cf2d drm/amdgpu: Increase Max GPU instance to 64
Increase Max GPU instances to 64 to handle multi-socket
system with GFX 9.4.3 asic.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:54:09 -04:00
Le Ma
bb0ed57b44 drm/amdgpu: increase AMDGPU_MAX_RINGS
On newer GPUs, the number of kernel rings are increased.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:54:05 -04:00
Rajneesh Bhardwaj
970c1646b5 drm/amdgpu: Create VRAM BOs on GTT for GFXIP9.4.3
On GFXIP9.4.3 APP APU where there is no dedicated VRAM domain handle
VRAM BO allocation requests on CPU domain and validate them on GTT.

Support for handling multi-socket and multi-numa partitions within a
socket will be added by future patches, this enables 1P NPS1 asic
bringup configuration.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:54:01 -04:00
Rajneesh Bhardwaj
f431393d60 drm/amdgpu: Implement new dummy vram manager
This adds dummy vram manager to support ASICs that do not have a
dedicated or carvedout vram domain.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:57 -04:00
Rajneesh Bhardwaj
228ce17643 drm/amdgpu: Handle VRAM dependencies on GFXIP9.4.3
[For 1P NPS1 mode driver bringup]

Changes required to initialize the amdgpu driver with frontdoor firmware
loading and discovery=2 with the native mode SBIOS that enables CPU GPU
unified interleaved memory.

sudo modprobe amdgpu discovery=2

Once PSP TMR region is reported via the ACPI interface, the dependency
on the ip_discovery.bin will be removed.

Choice of where to allocate driver table is given to each IP version. In
general, both GTT and VRAM domains will be considered. If one of the
tables has a strict restriction for VRAM domain, then only VRAM domain
is considered.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
(lijo: Modified the handling for SMU Tables)
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:52 -04:00
Asad kamal
9faf929fbf drm/amdgpu: Enable CG for IH v4.4.2
Enable clock gating on IH v4.4.2 versions.

Signed-off-by: Asad kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:49 -04:00
Hawking Zhang
8107e4996f drm/amdgpu: Enable persistent edc harvesting in APP APU
Persistent edc harvesting is supported in APP APU

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:45 -04:00
Hawking Zhang
73c2b3fd2c drm/amdgpu: Initialize mmhub v1_8 ras function
Initialize mmhub v1_8 ras function.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:42 -04:00
Hawking Zhang
ccfdbd4bdc drm/amdgpu: Add reset_ras_error_status for mmhub v1_8
Add reset_ras_error_status callback for mmhub
v1_8. It will be used to reset mmhub error status.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:34 -04:00
Hawking Zhang
00c145222b drm/amdgpu: Add query_ras_error_status for mmhub v1_8
Add query_ras_error_status callback for mmhub
v1_8. It will be used to log mmhub error status.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:32 -04:00
Hawking Zhang
a0cdb3d093 drm/amdgpu: Add reset_ras_error_count for mmhub v1_8
Add reset_ras_error_count callback for mmhub
v1_8. It will be used to reset mmhub ras error
count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:15 -04:00
Hawking Zhang
bc069d823b drm/amdgpu: Add query_ras_error_count for mmhub v1_8
Add query_ras_error_count callback for mmhub v1_8.
It will be used to query and log mmhub error count
and memory block.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:13 -04:00
Hawking Zhang
1e69fde700 drm/amdgpu: Initialize sdma v4_4_2 ras function
Initialize sdma v4_4_2 ras function and interrupt
handler.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:06 -04:00
Hawking Zhang
a64b15520c drm/amdgpu: Add reset_ras_error_count for sdma v4_4_2
Add reset_ras_error_count callback for sdma
v4_4_2. It will be used to reset sdma ras error
count.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:03 -04:00
Hawking Zhang
dc37a9194a drm/amdgpu: Add query_ras_error_count for sdma v4_4_2
Add query_ras_error_count callback for sdma
v4_4_2. It will be used to query and log sdma
uncorrectable error count and memory block.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:53:00 -04:00
Hawking Zhang
e53a3250f7 drm/amdgpu: Add common helper to reset ras error
Add common helper to reset ras error status. It
applies to IP blocks that follow the new ras error
logging register design, and need to write 0 to
reset the error status. For IP blocks that don't
support the new design, please still implement ip
specific helper.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:54 -04:00
Hawking Zhang
322a7e005d drm/amdgpu: Add common helper to query ras error (v2)
Add common helper to query ras error status and
log error information, including memory block id
and erorr count. The helpers are applicable to IP
blocks that follow the new ras error logging design.
For IP blocks that don't support the new design,
please still implement ip specific helper to query
ras error.

v2: optimize struct amdgpu_ras_err_status_reg_entry
and the implementaion in helper (Lijo/Tao)

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:50 -04:00
Lijo Lazar
cbf9e46ab0 drm/amdgpu: Enable MGCG on SDMAv4.4.2
Enable clock gating on SDMAv4.4.2 versions. Leave memory light sleep to
default.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:46 -04:00
Le Ma
35ff4301eb drm/amdgpu: enable context empty interrupt on sdma v4.4.2
With SDMA_CTNL.CTXEMPTY_INT_ENABLE set, the F32 clock can be gated when
SDMA finishes all job and goes to idle.

And no specific interrupt handling is required in driver.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:41 -04:00
Sonny Jiang
7b08b2e1ca drm/amdgpu: add vcn_4_0_3 codec query
Add support for vcn_4_0_3 video codec query

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:39 -04:00
Lijo Lazar
c1d3f627ff drm/amdgpu: Fix mqd init on GFX v9.4.3
For MQD init, an XCC's queue is selected with GRBM select. However, for
initialization of MQD, values read from logical XCC0 registers are used.
This results in garbage values being read from XCC0 whose queue is not
selected. Change to read from the right XCC for MQD initialization.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:25 -04:00
Harish Kasiviswanathan
5ca1ceebab drm/amd: fix compiler error to support older compilers
‘for’ loop initial declarations are only allowed in C99 or C11 mode

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:21 -04:00
Lijo Lazar
b7c7011e67 drm/amdgpu: Enable CGCG/LS for GC 9.4.3
Enable coarse grain clockgating/light sleep for GC v9.4.3. Remove
programming that is not meant for GC 9.4.3.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:12 -04:00
Lijo Lazar
233bb3733b drm/amdgpu: Use unique doorbell range per xcc
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 <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:06 -04:00
Lijo Lazar
7389c75114 drm/amdgpu: Keep SDMAv4.4.2 active during reset
During ASIC wide reset, SDMA shouldn't be clockgated and be ready to
accept freeze requests from PMFW. For that, don't stop SDMA engine
during reset and keep the clocks active.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:52:02 -04:00
James Zhu
13a94f3f13 drm/amdgpu: add num_xcps return
Add num_xcps return.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:55 -04:00
James Zhu
1bd99ca269 drm/amdgpu: increase AMDGPU_MAX_HWIP_RINGS
[WA] Increase AMDGPU_MAX_HWIP_RINGS to 64 to support more compute
ring resource. Later need redesign with queue/prirority/scheduler
factors to reduce AMDGPU_MAX_HWIP_RINGS.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:51 -04:00
James Zhu
f471de2586 drm/amdgpu: vcn_v4_0_3 load vcn fw once for all AIDs
Signed-off-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:48 -04:00
Lijo Lazar
52c293ab06 drm/amdgpu: Populate VCN/JPEG harvest information
Certain instances of VCN/JPEG IPs may not be usable. Fetch the information
from harvest table.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:46 -04:00
Graham Sider
d839a158b2 drm/amdgpu: Correct dGPU MTYPE settings for gfx943
Revert temporary dGPU VRAM MTYPE setting and align with expected
coherency protocol.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:40 -04:00
Asad kamal
30b52995c2 drm/amdgpu: Remove SMU powergate message call for SDMA
SDMA v4.4.2 doesn't need explicit power gating control through PMFW

Signed-off-by: Asad kamal <asad.kamal@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:36 -04:00
James Zhu
ed1f42f03c drm/amdgpu: enable vcn/jpeg on vcn_v4_0_3
Enable vcn/jpeg on vcn_v4_0_3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:33 -04:00
James Zhu
e40b4b9a47 drm/amdgpu: enable indirect_sram mode on vcn_v4_0_3
Enable indirect_sram mode on vcn_v4_0_3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:30 -04:00
James Zhu
da044aaeb3 drm/amdgpu: add unified queue support on vcn_v4_0_3
Add unified queue support on vcn_v4_0_3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:27 -04:00
James Zhu
2d7f1d51c1 drm/amdgpu: add fwlog support on vcn_v4_0_3
Add fwlog support on vcn_v4_0_3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:24 -04:00
James Zhu
45ed97ad36 drm/amdgpu: increase MAX setting to hold more jpeg instances
vcn_v4_0_3 increased jpeg instances,
need increasing MAX resources setting accordlingly.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:19 -04:00
Lijo Lazar
73fa255328 drm/amdgpu: Use discovery to get XCC/SDMA mask
Get information about active XCC and SDMAs from discovery table.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:17 -04:00
Lijo Lazar
44cbc4534b drm/amdgpu: Make VRAM discovery read optional
When overridden with module param, directly read discovery info
from discovery binary instead of reading from VRAM.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:13 -04:00
Felix Kuehling
c9a502e981 drm/amdgpu: Allocate GART table in RAM for AMD APU
Some AMD APUs may not have a dedicated VRAM. On such platforms the GART
table should be allocated on the system memory. When real vram size is
zero, place the GART table in system memory and create an SG BO to make
it GPU accessible.

v2: fix includes

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
(rajneesh: removed set_memory_wc workaround)
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:06 -04:00
Lijo Lazar
34fd9d6867 drm/amdgpu: Add FGCG logic for GFX v9.4.3
Add logic for fine grain clock gating logic for GFX v9.4.3. The feature
will be controlled using CG flags. Also, make a change so that RLC safe
mode entry/exit is done only once during CG update sequence.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:51:03 -04:00
Rajneesh Bhardwaj
7a7aaab021 drm/amdgpu: Make UTCL2 snoop CPU caches
On AMD APP APUs, to make UTCL2 snoop CPU caches, its not sufficient to
rely on xgmi connected flag so add the logic to use is_app_apu to
program the PDE_REQUEST_PHYSICAL bit correctly for gfxhub and mmhub
both.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:59 -04:00
Lijo Lazar
d524180b88 drm/amdgpu: Fix GFX v9.4.3 EOP buffer allocation
Each compute cluster gets 8 compute queues in GFX v9.4.3. Fix the EOP
buffer allocation so that compute queue on every XCC gets a unique
address.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Tested-and-Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:52 -04:00
Lijo Lazar
12c4d7edfb drm/amdgpu: Fix GFX 9.4.3 dma address capability
ASICs with GFX 9.4.3 support 48-bit addressing.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:48 -04:00
Lijo Lazar
a0a0c69c05 drm/amdgpu: Fix semaphore release
Use the right register for semaphore release during invalidation.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:46 -04:00
Lijo Lazar
a820d3ca8e drm/amdgpu: Remove unnecessary return value check
There is no need to check return value, as the function internally
used - amdgpu_discovery_read_binary_from_vram() - returns void.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:34 -04:00
Le Ma
98b2e9cad2 drm/amdgpu: correct the vmhub index when page fault occurs
The AMDGPU_GFXHUB was bind to each xcc in the logical order.
Thus convert the node_id to logical xcc_id to index the
correct AMDGPU_GFXHUB. And "node_id / 4" can get the correct
AMDGPU_MMHUB0 index.

Signed-off-by: Le Ma <le.ma@amd.com>
Tested-by: Asad kamal <asad.kamal@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:30 -04:00
Rajneesh Bhardwaj
753b999afe drm/amdgpu: set MTYPE in PTE for GFXIP 9.4.3
Apply the GFXIP 9.4.3 specific snoop and mtype settings for various
scenarios such as APU, APU in Carveout mode and dGPU mode.

Note: This is expected to change due to:
1 - NPS > 1 support in future
2 - Hardware bugs found during initial asic bringup.

Cc: Graham Sider <graham.sider@amd.com>
Cc: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:13 -04:00
Lijo Lazar
7a1efad04c drm/amdgpu: Use mask for active clusters
Use a mask of available active clusters instead of using only the number
of active clusters.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:08 -04:00
Lijo Lazar
bbca579fd2 drm/amdgpu: Derive active clusters from SDMA
SDMA instances per active cluster and SDMA instance mask are used
to find the number of active clusters.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:06 -04:00
Lijo Lazar
dc6df2095d drm/amdgpu: Move generic logic to soc config
Move soc specific configuration details to aqua vanjaram specific file.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:04 -04:00
Shiwu Zhang
fee500fa7c drm/amdgpu: Fix the KCQ hang when binding back
Just like the KIQ, KCQ need to clear the doorbell related regs as well
to avoid hangs when to load driver again after unloading.

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:50:01 -04:00
Lijo Lazar
5b03127d47 drm/amdgpu: Skip TMR allocation if not required
On ASICs with PSPv13.0.6, TMR is reserved at boot time. There is no need
to allocate TMR region by driver. However, it's still required to send
SETUP_TMR command to PSP.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:59 -04:00
Lijo Lazar
845c9b313f drm/amdgpu: Add XCP IP callback funcs for each IP
Initialize with the IP specific functions needed for GFXHUB, GFX and
SDMA.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:56 -04:00
Lijo Lazar
73c84f7c47 drm/amdgpu: Add XCP functions for GFX v9.4.3
Add functions to suspend/resume GFX instances belonging to an XCP.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:53 -04:00
Lijo Lazar
3446cb78f3 drm/amdgpu: Add SDMA v4.4.2 XCP funcs
Add functions required to suspend/resume instances of SDMA which
are part of an XCP.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:48 -04:00
Lijo Lazar
dfdd6f89c4 drm/amdgpu: Add GFXHUB v1.2 XCP funcs
Add functions required for suspend/resume of GFXHUB instances which are
part of an XCP.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:45 -04:00
Lijo Lazar
8e7fd19380 drm/amdgpu: Switch to SOC partition funcs
For GFXv9.4.3, use SOC level partition switch implementation rather than
keeping them at GFX IP level. Change the exisiting implementation in
GFX IP for keeping partition mode and restrict it to only GFX related
switch.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:42 -04:00
Lijo Lazar
e56c9ef6cb drm/amdgpu: Add soc config init for GC9.4.3 ASICs
Add function to initialize soc configuration information for GC 9.4.3
ASICs. Use it to map IPs and other SOC related information once IP
configuration information is available through discovery.

For GC9.4.3 compute partition related callbacks are initialized as part
of configuration init.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:39 -04:00
Lijo Lazar
9cb18287d8 drm/amdgpu: Add SOC partition funcs for GC v9.4.3
Switching the partition mode configuration of ASIC is SOC
level function rather than something at GFX core level. Add
partition mode switch functions as SOC specific callbacks.
Implement the XCP manager callbacks needed for partition
switch for GC 9.4.3 based ASICs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:35 -04:00
Lijo Lazar
75d1692393 drm/amdgpu: Add initial version of XCP routines
Within a device, an accelerator core partition can be constituted with
different IP instances. These partitions are spatial in nature. Number
of partitions which can exist at the same time depends on the 'partition
mode'. Add a manager entity which is responsible for switching between
different partition modes and maintaining partitions. It is also
responsible for suspend/resume of different partitions.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:31 -04:00
Lijo Lazar
527c670e53 drm/amdgpu: Add sdma instance specific functions
SDMA 4.4.2 supports multiple instances. Add functions to support
handling of each SDMA instance separately.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:17 -04:00
Lijo Lazar
dd1a02e280 drm/amdgpu: Add xcc specific functions for gfxhub
GFXHUB 1.2 supports multiple XCC instances. Add XCC specific functions
to handle XCC instances separately.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:14 -04:00
Lijo Lazar
44b5cf2e0f drm/amdgpu: Add xcc specific functions
Add more XCC specific functions and use them from IP block functions.
RLC, CP functions are further split to have xcc specific versions.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:12 -04:00
Lijo Lazar
880f8b3f80 drm/amdgpu: Rename xcc specific functions
Add 'xcc' prefix to xcc specific functions to distinguish from IP block
functions.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:09 -04:00
Rajneesh Bhardwaj
497db7ea33 drm/amdgpu: Check APU supports true APP mode
On GPXIP 9.4.3 APU, in no carveout mode there is no real vram heap and
could be emulated by the driver over the interleaved NUMA system memory
and the APU could also  be in the carveout mode during early development
stage or otherwise for debugging purpose so introduce a new member in
amdgpu_gmc to figure out whether the APU is in the native mode as per
the production configuration. AMD_IS_APU cannot be used for Accelerated
Processing Platform APUs as it might be used in a different context on
previous generations or on small APUs.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Graham Sider <graham.sider@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:49:05 -04:00
Philip Yang
eaae4beee8 drm/amdgpu: more GPU page fault info for GC v9.4.3
Output IH cookie node_id and translate it to the corresponding AID id
and XCC id, to help debug the GPU page fault.

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>
2023-06-09 09:49:02 -04:00
Shiwu Zhang
993d218f82 drm/amdgpu: remove partition attributes sys file for gfx_v9_4_3
For driver de-init like rmmod operations those partition specific
attributes need to be removed accordingly.

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:59 -04:00
Shiwu Zhang
37dd9d58a5 drm/amdgpu: fix kcq mqd_backup buffer double free for multi-XCD
For gfx_v9_4_3 and beyond, struct kiq has its own mqd_backup pointer
rather than using the last pointer from mec struct. Then the kfree
operation on the pointer from the mec struct should be removed otherwise
it will cause double free on the first kcq's mqd_backup buffer on XCD1.

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:52 -04:00
Lijo Lazar
cbd442ce91 drm/amdgpu: Skip runtime db read for PSP 13.0.6
Skip reading runtime db information for PSP 13.0.6.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:50 -04:00
Le Ma
4bc615a523 drm/amdgpu: fix vm context register assignment in mmhub v1.8
Assign the vm context register addr per aid instance.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:48 -04:00
Lijo Lazar
d55391c213 drm/amdgpu: Revert programming of CP_PSP_XCP_CTL
Programming of this register is taken care by PSP. Incorrect programming
causes CP not to detect its XCC.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reported-by: Alexander Turek <Alexander.Turek@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:46 -04:00
Rajneesh Bhardwaj
ea2d2f8ece drm/amdgpu: detect current GPU memory partition mode
- Add helpers to detect the current GPU memory partition.
 - Add current memory partition mode sysfs node.

Tested-by: Ori Messinger <Ori.Messinger@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:42 -04:00
Hawking Zhang
6b7ec18b04 drm/amdgpu: init smuio funcs for smuio v13_0_3
Add callbacks for SMUIO 13.0.3

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>
2023-06-09 09:48:36 -04:00
Rajneesh Bhardwaj
3d2ea552b2 drm/amdgpu: implement smuio v13_0_3 callbacks
Add smuio v13_0_3 callbacks for SMUIO.

Tested-by: Ori Messinger <Ori.Messinger@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:33 -04:00
Hawking Zhang
ebadc1061e drm/amdgpu: retire render backend setup from gfx_v9_4_3
gfx v9_4_3 only support compute. render backend
doesn't need to be involved in any compute shader
execution.

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>
2023-06-09 09:48:28 -04:00
Tom St Denis
553f973a0d drm/amd/amdgpu: Update debugfs for XCC support (v3)
This patch updates the 'regs2' interface for MMIO
registers to add a new IOCTL command for a 'v2' state
data that includes the XCC ID.

This patch then updates amdgpu_gfx_select_se_sh()
and amdgpu_gfx_select_me_pipe_q() (and the implementations
in the gfx drivers) to support an additional parameter.

This patch then creates a new debugfs interface "gprwave"
which is a merge of shader GPR and wave status access.  This
new inteface uses an IOCTL to select banks as well as XCC identity.

(v2) Fix missing xcc_id in wave_ind function

(v3) Fix pm runtime calls and mutex locking

(v4) Fix bad label

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:22 -04:00
Lijo Lazar
5f09237b82 drm/amdgpu: Add SDMA v4.4.2 golden settings
Add programming of SDMA golden settings for v4.4.2

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:20 -04:00
Hawking Zhang
57a83b2daf drm/amdgpu: init gfx_v9_4_3 external_rev_id
it is used for user space driver to identify gfx_v9_4_3 chip

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:17 -04:00
Lijo Lazar
870d1e5afc drm/amdgpu: Fix interrupt handling in GFX v9.4.3
IH follows a different identification scheme for its clients. Get the
right mapping of xcc instance from IH node id.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:12 -04:00
Le Ma
369576c2d5 drm/amdgpu: consolidate the access helpers in nbio v7_9
Use WREG32_SOC15_EXT to write registers with address larger than 32bit.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:09 -04:00
Le Ma
2fa480d36e drm/amdgpu: add helpers to access registers on different AIDs
SMN address which is larger than 32bit has different indications
through bit[34:32] on different AIDs.

v2: put smn addressing of different AIDs into asic specific place
v3: change to ext_id/ext_offset naming

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:48:05 -04:00
Le Ma
7d158f52bf drm/amdgpu: parse base address from new ip discovery with 64bit ip base address
Truncate the 64bit base address from ip discovery and only store lower 32bit
ip base in reg_offset[].

Bits > 32 follows ASIC specific format, thus just discard them and handle it
within specific ASIC.

By this way reg_offset[] and related helpers can stay unchanged.

v2: make comments more generic

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:59 -04:00
Le Ma
aabb478421 drm/amdgpu: upgrade amdgpu_discovery struct ip to ip_v4
version 4 supports 64bit ip base address

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:56 -04:00
Le Ma
3955b14134 drm/amdgpu: do some register access cleanup in nbio v7_9
Use WREG_SOC15x() instead of WREG32(SOC15_REG_OFFSET())

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:50 -04:00
Le Ma
7e0eebdc47 drm/amdgpu: extend max instances
Number of instances is extended.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:46 -04:00
Le Ma
c3729997a2 drm/amdgpu: increase DISCOVERY_TMR_SIZE
New ip_discovery binary size is increased.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:43 -04:00
Le Ma
1dfcdc3027 drm/amdgpu: switch to aqua_vanjaram_doorbell_index_init
New doorbell index assignment is used by aqua_vanjaram.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:35 -04:00
Lijo Lazar
5c606836ef drm/amdgpu: Use SDMA instance table for aqua vanjaram
For aqua vanjaram, add mapping for logical to physical
instances.

v2:
	Register accesses on bare metal should be based on physical
instance. Use GET_INST() to get physical instance.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:32 -04:00
Lijo Lazar
cf24f6a0d7 drm/amdgpu: Add mask for SDMA instances
Add a mask of SDMA instances available for use. On certain ASIC configs,
not all SDMA instances are available for software use.

v2:
	Change sdma mask type to uint32_t (Le)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:29 -04:00
Lijo Lazar
cab7d478da drm/amdgpu: Add IP instance map for aqua vanjaram
Add XCC logical to physical instance map for aqua vanjaram

v2:
	Keep look up table only for required IPs, for others return
default mapping (Felix).

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:23 -04:00
Le Ma
6df442a03d drm/amdgpu: add new doorbell assignment table for aqua_vanjaram
Four basic reasons as below to do the change:
  1. number of ring expand a lot on aqua_vanjaram, and adjustment on old
     assignment cannot make each ring in a continuous doorbell space.
  2. the SDMA doorbell index should not exceed 0x1FF on aqua_vanjaram 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 <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:11 -04:00
Lijo Lazar
5a8b26a886 drm/amdgpu: Fix register access on GC v9.4.3
In GC v9.4.3 there are multiple XCCs. It's required to use
physical instance number to get the right register offset. Use
GET_INST API for that.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:08 -04:00
Lijo Lazar
955220b04d drm/amdgpu: Fix programming of initial XCP mode
On initialization set the partition mode correctly to SPX (default) or
any other user specified partition mode. Use switch_compute_partition
API so that all settings are initialized correctly.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:47:03 -04:00
Mukul Joshi
f5fe7edfd6 drm/amdkfd: Update interrupt handling for GFX9.4.3
Update interrupt handling in CPX mode for GFX9.4.3 by using the
VMID space instead of SDMA client id to determine if an interrupt
should be processed by a KFD node. This is especially needed for
handling retry faults from MMHUB.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:56 -04:00
Mukul Joshi
cb30544e3c drm/amdgpu: Fix failure when switching to DPX mode
Fix the if condition which causes dynamic repartitioning
to fail when trying to switch to DPX mode.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:54 -04:00
Mukul Joshi
02ee3b02d7 drm/amdkfd: Use instance table for GFX 9.4.3
For GFX 9.4.3, use the logical to physical mapping table,
to get the correct XCD instance when accessing registers on
bare metal.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:51 -04:00
Amber Lin
a058799923 drm/amdgpu: Fix SWS on multi-XCD GPU
GFX_9_4_3 supports multi-XCDs and multi-AIDs in one GPU device. SWS needs
to program IH_VMID_x_LUT with specified XCC instance and corresponded
AID instance.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:48 -04:00
Le Ma
9cd51d5369 drm/amdgpu: drop redundant csb init for gfx943
It's not required for compute pipeline and will cause soft lockup on emulation
due to long-time writing.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:42 -04:00
Le Ma
58bd802375 drm/amdgpu: adjust s2a entry register for sdma doorbell trans decoding
Use s2a entry 5/6 registers to decode sdma doorbell trans on different AIDs,
which aligns the entry table in SHUB spec, and leave entry 4 dedicated for VCN
doorbell to avoid conflict.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:34 -04:00
Lijo Lazar
cd321e6fd6 drm/amdgpu: Use status register for partition mode
Program partition status register to reflect the current partition mode.
Partition capability register is for capability and is a one-time setting.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:19 -04:00
Alex Sierra
5fb34bd9cf drm/amdkfd: pass kfd_node ref to svm migration api
This work is required for GC 9.4.3, previous to support memory
partitions per node at SVM. When multiple partition is configured,
every BO should be allocated inside one specific partition which
corresponds to the current amdgpu_device and kfd_node.

v2: squash in compilation fix (Alex)
v3: squash in fix for pre-gfx 9.4.3 (Alex)
v4: squash in best_loc fix (Alex)

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:17 -04:00
Lijo Lazar
0b02364e03 drm/amdgpu: Conform to SET_UCONFIG_REG spec
The packet expects only 16 bits register offset. Hence pass register
offset which is local to each XCC.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:12 -04:00
James Zhu
762702ebd3 drm/amdgpu/vcn: add vcn multiple AIDs support
add vcn multiple AIDs support.

v2: squash in FW setting fix (Alex)

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:07 -04:00
James Zhu
7229bd6fe0 drm/amdgpu/vcn: update clock gate setting for VCN 4.0.3
Update clock gate setting.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:05 -04:00
James Zhu
d4ad24a0b7 drm/amdgpu/jpeg: add JPEG multiple AIDs support
Add JPEG multiple AIDs support.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:46:02 -04:00
James Zhu
2e10ced47f drm/amdgpu/nbio: add vcn doorbell multiple AIDs support
Update vcn doorbell range to support multiple AIDs.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:58 -04:00
Lijo Lazar
7aa8a266aa drm/amdgpu: Fix GRBM programming sequence
It needs to be done only for XCC instances in non-AID0. Use the physical
instance to determine non-AID0 XCC instances.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:54 -04:00
Lijo Lazar
f8b34a0518 drm/amdgpu: Use instance table for sdma 4.4.2
For ASICs with sdma IP v4.4.2, add mapping for logical to physical
instances.

v2:
	Register accesses on bare metal should be based on physical
instance. Use GET_INST() to get physical instance.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:51 -04:00
Lijo Lazar
4db6f200a5 drm/amdgpu: Add mask for SDMA instances
Add a mask of SDMA instances available for use. On certain ASIC configs,
not all SDMA instances are available for software use.

v2:
	Change sdma mask type to uint32_t (Le)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:48 -04:00
Lijo Lazar
659a4ab8e2 drm/amdgpu: Use instance lookup table for GC 9.4.3
Register accesses need to be based on physical instance on bare metal.
Pass the right instance using logical to physical instance lookup
table before accessing registers. Add a macro GET_INST to get the right
physical instance of an IP corresponding to a logical instance.

v2: fix gfx_v9_4_3_check_rlcg_range() (Alex)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:44 -04:00
Lijo Lazar
5d30cbb4db drm/amdgpu: Add map of logical to physical inst
Add a map for logical to physical instances of an IP. For ex: on some device
configurations, the first logical XCC may not be the first physical XCC.
Software may continue to access in logical IP instance order. The map
provides a convenient way to get to the actual physical instance.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:42 -04:00
Mukul Joshi
0c7315e7d5 drm/amdkfd: Add device repartition support
GFX9.4.3 will support dynamic repartitioning of the GPU through sysfs.
Add device repartitioning support in KFD to repartition GPU from one
mode to other.

v2: squash in fix ("drm/amdkfd: Fix warning kgd2kfd_unlock_kfd defined but not used")

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:38 -04:00
Le Ma
6b22ef2574 drm/amdgpu: configure the doorbell settings for sdma on non-AID0
Configure the sdma doorbell settings on NBIF0 and SYSHUB of each AID

v2: fetch aid_id from amdgpu_sdma_instance (Lijo)

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:32 -04:00
Le Ma
0c552ed387 drm/amdgpu: add indirect r/w interface for smn address greater than 32bits
On multiple AIDs platform, bit[34:32] in SMD address is leveraged to access
nonAID0 register smn address and new PCI_INDEX_HI register is introduced
to access the higher bits.

v2: rebase on latest register accessors (Alex)

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:29 -04:00
Jonathan Kim
07bc768afb drm/amdgpu: reflect psp xgmi topology info for gfx9.4.3
Similar to GFX9.4.2 non-A+A devices, GFX9.4.3 psp xgmi topology info is
half duplex and requires the driver to fill in the bidirectional info.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Shiwu Zhang <shiwu.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:07 -04:00
James Zhu
cf1f3737c2 drm/amdgpu/vcn: update amdgpu_fw_shared to amdgpu_vcn4_fw_shared
Use amdgpu_vcn4_fw_shared for vcn 4.0.3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:05 -04:00
James Zhu
7f0af02ab3 drm/amdgpu/vcn: remove unused code
Remove unused code.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:02 -04:00
James Zhu
429a111851 drm/amdgpu/vcn: update ucode setup
Use common amdgpu_vcn_setup_ucode for ucode setup.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:45:00 -04:00
James Zhu
53054e9a77 drm/amdgpu/vcn: update new doorbell map
New doorbell map is used for VCN 4.0.3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:57 -04:00
James Zhu
492c464750 drm/amdgpu/jpeg: update jpeg header to support multiple AIDs
Add aid_id in jpeg header to support multiple AIDs.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:52 -04:00
James Zhu
f9f74df58f drm/amdgpu/vcn: update vcn header to support multiple AIDs
Add aid_id in vcn header to support multiple AIDs

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:48 -04:00
James Zhu
d244a4167a drm/amdgpu/vcn: use vcn4 irqsrc header for VCN 4.0.3
Use vcn4 irqsrc header for VCN 4.0.3.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:45 -04:00
Lijo Lazar
8078f1c610 drm/amdgpu: Change num_xcd to xcc_mask
Instead of number of XCCs, keep a mask of XCCs for the exact XCCs
available on the ASIC. XCC configuration could differ based on
different ASIC configs.

v2:
	Rename num_xcd to num_xcc (Hawking)
	Use smaller xcc_mask size, changed to u16 (Le)

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:38 -04:00
Shiwu Zhang
9eb7681f76 drm/amdgpu: add the support of XGMI link for GC 9.4.3
Add the xgmi LFB_CNTL/LBF_SIZE reg addresses to fetch the xgmi info from.

v2: move get_xgmi_info() to GC_V9_4_3 sepecific source files to utilize
the register definitions specific for GC_V9_4_3
v3: remove the duplicated register definitions
v4: enable xgmi based on asic_type as XGMI_IP ver is not available
yet for IP discovery

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Ack-by: Lijo Lazar <Lijo.Lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:33 -04:00
Hawking Zhang
cd8d77f328 drm/amdgpu: add new vram type for dgpu
hbm3 will be supported in some dgpu program

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:25 -04:00
Le Ma
20bedf1379 drm/amdgpu: introduce new doorbell assignment table for GC 9.4.3
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 <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:44:03 -04:00
Le Ma
36be0181ea drm/amdgpu: program GRBM_MCM_ADDR for non-AID0 GRBM
Otherwise the EOP interrupt on non-AID0 cannot route to IH0.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:59 -04:00
Le Ma
feb36dd014 drm/amdgpu: convert the doorbell_index to 2 dwords offset for kiq
KIQ doorbell_index is non-zero from XCC1, thus need to left-shift it like
other rings.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:56 -04:00
Le Ma
5de6bd6a13 drm/amdgpu: set mmhub bitmask for multiple AIDs
Like GFXHUB, set MMHUB0 bitmask for each AID.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:53 -04:00
Le Ma
0d81101c19 drm/amdgpu: complement the IH node_id table for multiple AIDs
With different node_id, the SDMA interrupt from multiple AIDs can be
distinguished by sw driver.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:50 -04:00
Le Ma
ed42f2cc3b drm/amdgpu: correct the vmhub reference for each XCD in gfxhub init
Correct this though the value is same across different vmhub.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:47 -04:00
Le Ma
3a1083873b drm/amdgpu: do mmhub init for multiple AIDs
Mmhub on each AID needs to be initialized respectively

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:45 -04:00
Le Ma
2a47a2d90e drm/amdgpu: assign the doorbell index for sdma on non-AID0
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 <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:41 -04:00
Le Ma
f786b1d4ec drm/amdgpu: add support for SDMA on multiple AIDs
Initialize SDMA instances on each AID.

v2: revise coding fault in hw_fini

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:39 -04:00
Le Ma
386ea27c3b drm/amdgpu: adjust some basic elements for multiple AID case
add some elements below:
 - num_aid
 - aid_id for each sdma instance
 - num_inst_per_aid for sdma

and extend macro size below:
 - SDMA_MAX_INSTANCES to 16
 - AMDGPU_MAX_RINGS to 96
 - AMDGPU_MAX_HWIP_RINGS to 32

v2: move aid_id from amdgpu_ring to amdgpu_sdma_instance. (Lijo)

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:35 -04:00
Le Ma
0ee20b8696 drm/amdgpu: assign the doorbell index in 1st page to sdma page queue
Previously for vega10, the sdma_doorbell_range is only enough for sdma
gfx queue, thus the index on second doorbell page is allocated for sdma
page queue. From vega20, the sdma_doorbell_range on 1st page is enlarged.
Therefore, just leverage these index instead of allocation on 2nd page.

v2: change "(x << 1) + 2" to "(x + 1) << 1" for readability and add comments.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:29 -04:00
Amber Lin
d255558661 drm/amdgpu: Set XNACK per process on GC 9.4.3
Set RETRY_PERMISSION_OR_INVALID_PAGE_FAULT bit in VM_CONTEXT1_CNTL
as well so XNACK can be enabled in the SQ per process.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:26 -04:00
Lijo Lazar
5db392a045 drm/amdgpu: Use new atomfirmware init for GC 9.4.3
Use the new atomfirmware initialization logic for GC 9.4.3 based ASICs
also. ASIC init logic doesn't consider boot clocks during init.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:22 -04:00
Mukul Joshi
a8027fcd08 drm/amdgpu: Fix CP_HYP_XCP_CTL register programming in CPX mode
Currently, in CPX mode, the CP_HYP_XCP_CTL register is programmed
incorrectly with the number of XCCs in the partition. As a result,
HIQ doesn't work in CPX mode. Fix this by programming the correct
number of XCCs in a partition, which is 1, in CPX mode.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:09 -04:00
Mukul Joshi
a805889a15 drm/amdkfd: Update SDMA queue management for GFX9.4.3
This patch updates SDMA queue management for multi XCC in GFX9.4.3.
- Allocate/deallocate SDMA queues from the correct SDMA engines
  based on the partition mode.
- Updates the kgd2kfd interface to fetch the correct SDMA register
  addresses.
- It also fixes dumping correct SDMA queue info in debugfs.

v2: squash in fix "drm/amdkfd: Fix XGMI SDMA user-mode queue allocation"

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:43:05 -04:00
Mukul Joshi
21e1217b4c drm/amdgpu: Fix VM fault reporting on XCC1
Fix VM fault reporting and clear VM fault register
for XCC1.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:55 -04:00
Mukul Joshi
f87f686482 drm/amdgpu: Add XCC inst to PASID TLB flushing
Add XCC instance to select the correct KIQ ring when
flushing TLBs on a multi-XCC setup.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:46 -04:00
Mukul Joshi
e2069a7b08 drm/amdkfd: Add XCC instance to kgd2kfd interface (v3)
Gfx 9 starts to have multiple XCC instances in one device. Add instance
parameter to kgd2kfd functions where XCC instance was hard coded as 0.
Also, update code to pass the correct instance number when running
on a multi-XCC setup.

v2: introduce the XCC instance to gfx v11 (Morris)
v3: rebase (Alex)

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:43 -04:00
Mukul Joshi
2f77b9a242 drm/amdkfd: Update MQD management on multi XCC setup
Update MQD management for both HIQ and user-mode compute
queues on a multi XCC setup. MQDs needs to be allocated,
initialized, loaded and destroyed for each XCC in the KFD
node.

v2: squash in fix "drm/amdkfd: Fix SDMA+HIQ HQD allocation on GFX9.4.3"

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:36 -04:00
Mukul Joshi
8dc1db3172 drm/amdkfd: Introduce kfd_node struct (v5)
Introduce a new structure, kfd_node, which will now represent
a compute node. kfd_node is carved out of kfd_dev structure.
kfd_dev struct now will become the parent of kfd_node, and will
store common resources such as doorbells, GTT sub-alloctor etc.
kfd_node struct will store all resources specific to a compute
node, such as device queue manager, interrupt handling etc.

This is the first step in adding compute partition support in KFD.

v2: introduce kfd_node struct to gc v11 (Hawking)
v3: make reference to kfd_dev struct through kfd_node (Morris)
v4: use kfd_node instead for kfd isr/mqd functions (Morris)
v5: rebase (Alex)

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:27 -04:00
Lijo Lazar
5cf1675591 drm/amdgpu: Add mode2 reset logic for v13.0.6
Mode2 reset for v13.0.6 has similar workflow as v13.0.2

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:20 -04:00
Lijo Lazar
e6a02e2cc7 drm/amdgpu: Add some XCC programming
Add additional XCC programming sequences.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:17 -04:00
Le Ma
15091a6f43 drm/amdgpu: add node_id to physical id conversion in EOP handler
A new field nodeid in interrupt cookie indicates the node ID.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Shiwu Zhang <shiwu.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:13 -04:00
Shiwu Zhang
147862d00b drm/amdgpu: enable the ring and IB test for slave kcq
With the mec FW update to utilize the mqd base set by
driver for kcq mapping, slave kcq ring test and IB test
can be re-enabled.

Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09 09:42:08 -04:00