Update the ptr handle to amdgpu_ip_block ptr in all
the functions affected.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update the ptr handle to amdgpu_ip_block ptr in all
the functions.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Need to make sure it's halted as we don't know what state
the GPU may have been left in previously.
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Need to set the pipe reset and cache invalidation bits
on halt otherwise we can get stale state if the CP firmware
changes (e.g., on module unload and reload).
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Enabling gfxoff quirk results in perfectly usable
graphical user interface on HP 705G4 DM with R5 2400G.
Without the quirk, X server is completely unusable as
every few seconds there is gpu reset due to ring gfx timeout.
Signed-off-by: Peng Liu <liupeng01@kylinos.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix screen corruption with openkylin.
Link: https://bbs.openkylin.top/t/topic/171497
Signed-off-by: Peng Liu <liupeng01@kylinos.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit applies isolation enforcement to the GFX and Compute rings
in the gfx_v9_0 module.
The commit sets `amdgpu_gfx_enforce_isolation_ring_begin_use` and
`amdgpu_gfx_enforce_isolation_ring_end_use` as the functions to be
called when a ring begins and ends its use, respectively.
`amdgpu_gfx_enforce_isolation_ring_begin_use` is called when a ring
begins its use. This function cancels any scheduled
`enforce_isolation_work` and, if necessary, signals the Kernel Fusion
Driver (KFD) to stop the runqueue.
`amdgpu_gfx_enforce_isolation_ring_end_use` is called when a ring ends
its use. This function schedules `enforce_isolation_work` to be run
after a delay.
These functions are part of the Enforce Isolation Handler, which
enforces shader isolation on AMD GPUs to prevent data leakage between
different processes.
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
The patch modifies the gfx_v9_0_kiq_set_resources function to write
the cleaner shader's memory controller address to the ring buffer. It
also adds a new function, gfx_v9_0_ring_emit_cleaner_shader, which
emits the PACKET3_RUN_CLEANER_SHADER packet to the ring buffer.
This patch adds support for the PACKET3_RUN_CLEANER_SHADER packet in the
gfx_v9_0 module. This packet is used to emit the cleaner shader, which
is used to clear GPU memory before it's reused, helping to prevent data
leakage between different processes.
Finally, the patch updates the ring function structures to include the
new gfx_v9_0_ring_emit_cleaner_shader function. This allows the
cleaner shader to be emitted as part of the ring's operations.
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rather than open coding it for the queue reset.
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's not supported under SR-IOV at the moment.
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Using mmio to do queue reset. Enter safe mode
when writing registers.
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
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>
There is a racing condition that cp firmware modifies
MQD in reset sequence after driver updates it for
remapping. We have to wait till CP_HQD_ACTIVE becoming
false then remap the queue.
v2: fix KIQ locking (Alex)
v3: fix KIQ locking harder
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
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>
Kiq command unmap_queues only does the dequeueing action.
We have to map the queue back with clean mqd.
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
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>
Change if (ptr == NULL) to if (!ptr) for a better
format and fix the warning.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Adding NOP packets one by one in the ring
does not use the CP efficiently.
Solution:
Use CP optimization while adding NOP packet's so PFP
can discard NOP packets based on information of count
from the Header instead of fetching all NOP packets
one by one.
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Cc: Tvrtko Ursulin <tursulin@igalia.com>
Cc: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For the bad opcode case, it will cause CP/ME hang.
The firmware will prevent the ME side from hanging by raising a bad opcode interrupt.
And the driver needs to perform a vmid reset when receiving the interrupt.
Acked-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Need to handle the interrupt enables for all pipes.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It should work the same for compute as well as gfx.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
refine gfx9 firmware loading
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix comments and error messages to rightly represent
the information.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rename the variable ip_dump_cp_queues to ip_dump_compute_queue
as it represent compute queues.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add gfx9 support of CP queue registers for all queues
to be used by devcoredump.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support of gfx9 ipdump print so devcoredump
could trigger it to dump the captured registers
in devcoredump.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add general registers of gfx9 in ipdump for
devcoredump support.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add the protoype for print ip state to be used
to print the registers in devcoredump during
a gpu reset.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add the prototype to dump ip registers
for all ips of different asics and set
them to NULL for now. Based on the
requirement add a function pointer for
each of them.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Here are the corrections needed for the queue ring buffer size
calculation for the following cases:
- Remove the KIQ VM flush ring usage.
- Add the invalidate TLBs packet for gfx10 and gfx11 queue.
- There's no VM flush and PFP sync, so remove the gfx9 real
ring and compute ring buffer usage.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The size of fw_name is increased to ensure that it can accommodate
the maximum possible size of the string being written into it.
Fixes the below with gcc W=1:
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c: In function ‘gfx_v9_0_early_init’:
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1255:52: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1255 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
| ^~
......
1393 | r = gfx_v9_0_init_cp_gfx_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1255:9: note: ‘snprintf’ output between 16 and 45 bytes into a destination of size 30
1255 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1261:52: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1261 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
| ^~
......
1393 | r = gfx_v9_0_init_cp_gfx_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1261:9: note: ‘snprintf’ output between 15 and 44 bytes into a destination of size 30
1261 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1267:52: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1267 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
| ^~
......
1393 | r = gfx_v9_0_init_cp_gfx_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1267:9: note: ‘snprintf’ output between 15 and 44 bytes into a destination of size 30
1267 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1303:60: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1303 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc_am4.bin", chip_name);
| ^~
......
1398 | r = gfx_v9_0_init_rlc_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1303:17: note: ‘snprintf’ output between 20 and 49 bytes into a destination of size 30
1303 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc_am4.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1309:60: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1309 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_kicker_rlc.bin", chip_name);
| ^~
......
1398 | r = gfx_v9_0_init_rlc_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1309:17: note: ‘snprintf’ output between 23 and 52 bytes into a destination of size 30
1309 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_kicker_rlc.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1311:60: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1311 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
| ^~
......
1398 | r = gfx_v9_0_init_rlc_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1311:17: note: ‘snprintf’ output between 16 and 45 bytes into a destination of size 30
1311 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1344:60: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1344 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sjt_mec.bin", chip_name);
| ^~
......
1402 | r = gfx_v9_0_init_cp_compute_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1344:17: note: ‘snprintf’ output between 20 and 49 bytes into a destination of size 30
1344 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sjt_mec.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1346:60: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1346 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
| ^~
......
1402 | r = gfx_v9_0_init_cp_compute_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1346:17: note: ‘snprintf’ output between 16 and 45 bytes into a destination of size 30
1346 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1356:68: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1356 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sjt_mec2.bin", chip_name);
| ^~
......
1402 | r = gfx_v9_0_init_cp_compute_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1356:25: note: ‘snprintf’ output between 21 and 50 bytes into a destination of size 30
1356 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sjt_mec2.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1358:68: warning: ‘%s’ directive output may be truncated writing up to 29 bytes into a region of size 23 [-Wformat-truncation=]
1358 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
| ^~
......
1402 | r = gfx_v9_0_init_cp_compute_microcode(adev, ucode_prefix);
| ~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1358:25: note: ‘snprintf’ output between 17 and 46 bytes into a destination of size 30
1358 | snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@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>
Using the ring_muxer without preemption adds overhead for no
reason since mcbp cannot be triggered.
Moving back to a single queue in this case also helps when
high priority app are used: in this case the gpu_scheduler
priority handling will work as expected - much better than
ring_muxer with its 2 independant schedulers competing for
the same hardware queue.
This change requires moving amdgpu_device_set_mcbp above
amdgpu_device_ip_early_init because we use adev->gfx.mcbp.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
First of all calculating the number of dw to patch into a
conditional execution is not something HW generation specific.
This is just standard ring buffer calculations. While at it also
reduce the BUG_ON() into WARN_ON().
Then instead of a random bit pattern use 0 as default value for
the number of dw skipped, this way it's not mandatory any more
to patch the conditional execution.
And last make the address to check a parameter of the
conditional execution instead of getting this from the ring.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Drop redundant parameters in function amdgpu_gfx_kiq_init_ring
to simplify the code
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In the suspend abort cases, the gfx power rail doesn't turn off so
some GFXDEC registers/CSB can't reset to default value and at this
moment reinitialize GFXDEC/CSB will result in an unexpected error.
So let skip those program sequence for the suspend abort case.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Submit command of wreg in GFX and COMPUTE ring to update
RLC_SPM_MC_CNT in guest machine during runtime.
Signed-off-by: YuanShang <YuanShang.Mao@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix a memory overflow issue in the gfx IB test
for some ASICs. At least 20 bytes are needed for
the IB test packet.
v2: correct code indentation errors. (Christian)
Signed-off-by: Tim Huang <Tim.Huang@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use an inline function for version check. Gives more flexibility to
handle any format changes.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently, we store CU info only for a single XCC assuming
that it is the same for all XCCs. However, that may not be
true. As a result, store CU info for all XCCs. This info is
later used for CU masking.
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>
This warning is for the declaration of a static array, and it is
recommended to declare it as type "static const char * const" instead of
"static const char *".
an array pointer declared as type "static const char *" can point to a
different character constant because the pointer is mutable. However, if
it is declared as type "static const char * const", the pointer will
point to an immutable character constant, preventing it from being
modified which can better ensure the safety and stability of the
program.
Fixes the below:
WARNING: static const char * array should probably be static const char * const
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Pan, Xinhui" <Xinhui.Pan@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The driver's CSA buffer is shared by all the ibs. When the high priority ib
is submitted after the preempted ib, CP overrides the ib_completion_status
as completed in the csa buffer. After that the preempted ib is resubmitted,
CP would clear some locals stored for ib resume when reading the completed
status, which causes gpu hang in some cases.
Always set status as preempted for those resubmitted ib instead of reading
everything from the CSA buffer.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2535
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2717
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>
Add RLCG interface support for gfx v9.4.3 and multiple XCCs.
Do not enable it yet.
v2: Fix amdgpu_rlcg_reg_access_ctrl init, add support for multiple XCCs
in amdgpu_mm_wreg_mmio_rlc
v3: Use GET_INST() when indexing amdgpu_rlcg_reg_access_ctrl
Signed-off-by: Victor Lu <victorchengchi.lu@amd.com>
Reviewed-by: Zhigang Luo <zhigang.luo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
rlc_init() is part of sw_init() so it should not touch hardware.
Additionally, calling the rlc update_spm_vmid() callback
directly invokes a gfx on/off cycle which could result in
powergating being enabled before hw init is complete. Split
update_spm_vmid() into an internal implementation for local
use without gfxoff interaction and then the rlc callback
which includes gfxoff handling. lbpw_init also touches
hardware so mvoe that to rlc_resume as well.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
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>
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>
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>
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>
Sunil Khatri
Alex Deucher
Peng Liu
Srinivasan Shanmugam
Jiadong Zhu
Yang Wang
Prike Liang
Pierre-Eric Pelloux-Prayer
Christian König
Ma Jun
YuanShang
Tim Huang
Lijo Lazar
Mukul Joshi
Victor Lu
Jonathan Kim