When destroying an inactive queue, we don't need to call
execute_queues_cpsch.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Oak Zeng <oak.zeng@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This commit adds several debugfs entries for kfd:
kfd/hqds: dumps all HQDs on all GPUs for KFD-controlled compute and
SDMA RLC queues
kfd/mqds: dumps all MQDs of all KFD processes on all GPUs
kfd/rls: dumps HWS runlists on all GPUs
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
A second-level user mode trap handler can be installed. The CWSR trap
handler jumps to the secondary trap handler conditionally for any
conditions not handled by it. This can be used e.g. for debugging or
catching math exceptions.
When CWSR is disabled, the user mode trap handler is installed as
first level trap handler.
Signed-off-by: Shaoyun.liu <shaoyun.liu@amd.com>
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This hardware feature allows the GPU to preempt shader execution in
the middle of a compute wave, save the state and restore it later
to resume execution.
Memory for saving the state is allocated per queue in user mode and
the address and size passed to the create_queue ioctl. The size
depends on the number of waves that can be in flight simultaneously
on a given ASIC.
Signed-off-by: Shaoyun.liu <shaoyun.liu@amd.com>
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
map_queues_cpsch uses the queue_count to decide whether to upload
a new runlist. So update the counter before calling it.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
HWS does not support over-subscription and the scheduler can not internally
modify the engine. Driver needs to program the correct engine ID.
Fix the queue and engine selection to create queues on alternating SDMA
engines. This allows concurrent bi-directional DMA transfers in a process
that creates two SDMA queues.
Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Removed unused num_concurrent_processes.
Implemented counting of queues in QPD. This makes counting the queue
list repeatedly in several places unnecessary.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Separate device queue termination from process queue manager
termination. Unmap all queues at once instead of one at a time.
Unmap device queues before the PASID is unbound, in the
kfd_process_iommu_unbind_callback.
When resetting wavefronts in non-HWS mode, do it before the VMID is
released.
Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
v2:
Make queue mapping interfaces more consistent by passing unmap filter
parameters directly to execute_queues_cpsch, same as unmap_queues_cpsch.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When a queue is mapped, the MQD is owned by the FW. The FW overwrites
the MQD on the next unmap operation. Therefore the queue must be
unmapped before updating the MQD.
For the non-HWS case, also fix disabling of queues and creation of
queues in disabled state.
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When unmapping the queues from HW scheduler, there are two actions:
reset and preempt. So naming the variables with only preempt is
inapproriate.
For functions such as destroy_queues_cpsch, what they do actually is to
unmap the queues on HW scheduler rather than to destroy them. Change the
name to reflect that fact. On the other hand, there is already a function
called destroy_queue_cpsch() which exactly destroys a queue, and the name
is very close to destroy_queues_cpsch(), resulting in confusion.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Several functions in DQM are shared between cpsch and nocpsch code.
Remove the misleading _nocpsch suffix from their names.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
There are already CHIP_* definitions under amd_shared.h file on amdgpu
side, so KFD should reuse them rather than defining new ones.
Using enum for asic type requires default cases on switch statements
to prevent compiler warnings. WARN on unsupported ASICs. It should never
get there because KFD should not be initialized on unsupported devices.
v2: Replace BUG() with WARN and error return
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The hard-coded values related to VMID were removed in KFD, as those
values can be calculated in the KFD initialization function.
v2: remove unnecessary local variable
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Adjust latencies and timeouts for dequeueing with HWS and consolidate
them in one place. Make them longer to allow long running waves to
complete without causing a timeout. The timeout is twice as long as the
latency plus some buffer to make sure we don't detect a timeout
prematurely.
Change timeouts for dequeueing HQDs without HWS. KFD_UNMAP_LATENCY is
more consistent with what the HWS does for user queues.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The timeout in milliseconds should not be regarded as jiffies. This
commit fixed that.
v2:
- use msecs_to_jiffies
- change timeout_ms parameter to unsigned int to match msecs_to_jiffies
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When we do suspend/resume through "sudo pm-suspend" while there is
HSA activity running, upon resume we will encounter HWS hanging, which
is caused by memory read/write failures. The root cause is that when
suspend, we neglected to unbind pasid from kfd device.
Another major change is that the bind/unbinding is changed to be
performed on a per process basis, instead of whether there are queues
in dqm.
v2:
- free IOMMU device if kfd_bind_processes_to_device fails in kfd_resume
- add comments to kfd_bind/unbind_processes_to/from_device
- minor cleanups
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
v2:
* Renamed ALLOC_MEMORY_OF_SCRATCH to SET_SCRATCH_BACKING_VA
* Removed size parameter from the ioctl, it was unused
* Removed hole in ioctl number space
* No more call to write_config_static_mem
* Return correct error code from ioctl
Signed-off-by: Moses Reuben <moses.reuben@amd.com>
Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Various bug fixes and improvements that accumulated over the last two
years.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
In most cases, BUG_ONs can be replaced with WARN_ON with an error
return. In some void functions just turn them into a WARN_ON and
possibly an early exit.
v2:
* Cleaned up error handling in pm_send_unmap_queue
* Removed redundant WARN_ON in kfd_process_destroy_delayed
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Remove BUG_ONs that check for NULL pointer arguments that are
dereferenced in the same function. Dereferencing the NULL pointer
will generate a BUG anyway, so the explicit check is redundant and
unnecessary overhead.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
See https://kernel.org/doc/html/latest/process/coding-style.html
under "14) Allocating Memory" for rationale behind removing the
x=alloc(sizeof(struct) style and using x=alloc(sizeof(*x) instead
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Remove gotos that do not feature any common cleanup, and use gotos
instead of repeating cleanup commands.
According to kernel.org: "The goto statement comes in handy when a
function exits from multiple locations and some common work such as
cleanup has to be done. If there is no cleanup needed then just return
directly."
v2: Applied review suggestions in create_queue_nocpsch
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Upstream prefers the !x notation to x==NULL or x==false. Along those lines
change the ==true or !=NULL references as well. Also make the references
to !x the same, excluding () for readability.
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Consolidate log commands so that dev_info(NULL, "Error...") uses the more
accurate pr_err, remove the module name from the log (can be seen via
dynamic debugging with +m), and the function name (can be seen via
dynamic debugging with +f). We also don't need debug messages saying
what function we're in. Those can be added by devs when needed
Don't print vendor and device ID in error messages. They are typically
the same for all GPUs in a multi-GPU system. So this doesn't add any
value to the message.
Lastly, remove parentheses around %d, %i and 0x%llX.
According to kernel.org:
"Printing numbers in parentheses (%d) adds no value and should be
avoided."
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Using checkpatch.pl -f <file> showed a number of style issues. This
patch addresses as many of them as possible. Some long lines have been
left for readability, but attempts to minimize them have been made.
v2: Broke long lines in gfx_v7 get_fw_version
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Use shared_resources.queue_bitmap to determine the queues available
for KFD in each pipe.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
- Stop reprogramming the MC, the vbios already does this in asic_init
- Reduce internal gart to 256M (this does not affect the ttm GTT pool size)
- Initial support for huge pages
- Rework bo migration logic
- Lots of improvements for vega10
- Powerplay fixes
- Additional Raven enablement
- SR-IOV improvements
- Bug fixes
- Code cleanup
* 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux: (138 commits)
drm/amdgpu: fix header on gfx9 clear state
drm/amdgpu: reduce the time of reading VBIOS
drm/amdgpu/virtual_dce: Remove the rmmod error message
drm/amdgpu/gmc9: disable legacy vga features in gmc init
drm/amdgpu/gmc8: disable legacy vga features in gmc init
drm/amdgpu/gmc7: disable legacy vga features in gmc init
drm/amdgpu/gmc6: disable legacy vga features in gmc init (v2)
drm/radeon: Set depth on low mem to 16 bpp instead of 8 bpp
drm/amdgpu: fix the incorrect scratch reg number on gfx v6
drm/amdgpu: fix the incorrect scratch reg number on gfx v7
drm/amdgpu: fix the incorrect scratch reg number on gfx v8
drm/amdgpu: fix the incorrect scratch reg number on gfx v9
drm/amd/powerplay: add support for 3DP 4K@120Hz on vega10.
drm/amdgpu: enable huge page handling in the VM v5
drm/amdgpu: increase fragmentation size for Vega10 v2
drm/amdgpu: ttm_bind only when user needs gpu_addr in bo pin
drm/amdgpu: correct clock info for SRIOV
drm/amdgpu/gmc8: SRIOV need to program fb location
drm/amdgpu: disable firmware loading for psp v10
drm/amdgpu:fix gfx fence allocate size
...
This is just future proofing code, not something that can be triggered
in real life. We're testing to make sure we don't shift wrap when we
do "1ull << i" so "i" has to be in the 0-63 range. If it's 64 then we
have gone too far.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update the KGD to KFD interface to allow sharing pipes with queue
granularity instead of pipe granularity.
This allows for more interesting pipe/queue splits.
v2: fix overflow check for res.queue_mask
v3: fix shift overflow when setting res.queue_mask
v4: fix comment in is_pipeline_enabled()
v5: clamp res.queue_mask to the first MEC only
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andres Rodriguez <andresx7@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Make amdgpu the owner of all per-pipe state of the HQDs.
This change will allow us to split the queues between kfd and amdgpu
with a queue granularity instead of pipe granularity.
This patch fixes kfd allocating an HDP_EOP region for its 3 pipes which
goes unused.
v2: support for gfx9
v3: fix gfx7 HPD intitialization
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andres Rodriguez <andresx7@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit moves the reset wavefront flag to per process per device
data structure, so we can support multiple devices.
Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This commit makes sure that on process termination, after
we're destroying all the active queues, we're killing all the
existing wave front of the current process.
By doing this we're making sure that if any of the CUs were blocked
by infinite loop we're enforcing it to end the shader explicitly.
Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The wave control operation supports several command types executed upon
existing wave fronts that belong to the currently debugged process.
The available commands are:
HALT - Freeze wave front(s) execution
RESUME - Resume freezed wave front(s) execution
KILL - Kill existing wave front(s)
Signed-off-by: Yair Shachar <yair.shachar@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch adds support for static user-mode queues in QCM.
Queues which are designated as static can NOT be preempted by
the CP microcode when it is executing its scheduling algorithm.
This is needed for supporting the debugger feature, because we
can't allow the CP to preempt queues which are currently being debugged.
The number of queues that can be designated as static is limited by the
number of HQDs (Hardware Queue Descriptors).
Signed-off-by: Yair Shachar <yair.shachar@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJVWh3TAAoJEHm+PkMAQRiG/kwH/2c9irodp2+M9OUnX2bfsBb6
LnChiDpvkF5BB8jhP6d/XmvPp4NJzAbTxByhjdfb2E2HkorCUHCOIn2tI1TE2pUs
2qjkOVH+XCzoV0goGtQjzK1ht8f2IrtlDiEjyRekK5cJHzhggb22QPtWL4npyd0O
reDmG2jsRaF9POr9uLSFEv4CEnkksmRLUU0vuQX0TZeCJ41O7TXrkN/wKrLZ5mj4
IWpqXQaSlrffq/T5HnVbXBxk3/T8QmhrIoppiMpV1mUVj0uTqlFRNi5qwT2Nit1h
FVljWI4+WgOk3bf7fUlp+ahopjkTgu+GuXkiRP/pdgWNQO0cxCWSAzSndAlIIAE=
=uOoJ
-----END PGP SIGNATURE-----
Backmerge v4.1-rc4 into into drm-next
We picked up a silent conflict in amdkfd with drm-fixes and drm-next,
backmerge v4.1-rc5 and fix the conflicts
Signed-off-by: Dave Airlie <airlied@redhat.com>
Conflicts:
drivers/gpu/drm/drm_irq.c
This patch adds the interrupt handling module, kfd_interrupt.c, and its
related members in different data structures to the amdkfd driver.
The amdkfd interrupt module maintains an internal interrupt ring
per amdkfd device. The internal interrupt ring contains interrupts
that needs further handling. The extra handling is deferred to
a later time through a workqueue.
There's no acknowledgment for the interrupts we use. The hardware
simply queues a new interrupt each time without waiting.
The fixed-size internal queue means that it's possible for us to lose
interrupts because we have no back-pressure to the hardware.
However, only interrupts that are "wanted" by amdkfd, are copied into
the amdkfd s/w interrupt ring, in order to minimize the chances
for overflow of the ring.
Signed-off-by: Andrew Lewycky <Andrew.Lewycky@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch fixes a bug where sdma vm wasn't initialized when
an sdma queue was created in HWS mode.
This caused GPUVM faults to appear on dmesg and it is one of the
causes that SDMA queues are not working.
Signed-off-by: Xihan Zhang <xihan.zhang@amd.com>
Reviewed-by: Ben Goz <ben.goz@amd.comt>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Sometimes we might unregister process that have queues, because we couldn't
preempt the queues. Until now we blocked it with BUG_ON but instead just
print it as debug.
Reviewed-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
This backmerges 4.0-rc6 due to the recent fixes in rc5/6
- DP link rate refactoring from Ville
- byt/bsw rps tuning from Chris
- kerneldoc for the shrinker code
- more dynamic ppgtt pte work (Michel, Ben, ...)
- vlv dpll code refactoring to prep fro bxt (Imre)
- refactoring the sprite colorkey code (Ville)
- rotated ggtt view support from Tvrtko
- roll out struct drm_atomic_state to prep for atomic update (Ander)
* tag 'drm-intel-next-2015-03-27-merge' of git://anongit.freedesktop.org/drm-intel: (473 commits)
Linux 4.0-rc6
arm64: juno: Fix misleading name of UART reference clock
drm/i915: Update DRIVER_DATE to 20150327
drm/i915: Skip allocating shadow batch for 0-length batches
drm/i915: Handle error to get connector state when staging config
drm/i915: Compare GGTT view structs instead of types
drm/i915: fix simple_return.cocci warnings
drm/i915: Add module param to test the load detect code
drm/i915: Remove usage of encoder->new_crtc from clock computations
drm/i915: Don't look at staged config crtc when changing DRRS state
drm/i915: Convert intel_pipe_will_have_type() to using atomic state
drm/i915: Pass an atomic state to modeset_global_resources() functions
drm/i915: Add dynamic page trace events
drm/i915: Finish gen6/7 dynamic page table allocation
drm/i915: Remove unnecessary gen6_ppgtt_unmap_pages
drm/i915: Fix i915_dma_map_single positive error code
drm/i915: Prevent out of range pt in gen6_for_each_pde
drm/i915: fix definition of the DRM_IOCTL_I915_GET_SPRITE_COLORKEY ioctl
drm/i915: Rip out GET_SPRITE_COLORKEY ioctl
watchdog: imgpdc: Fix default heartbeat
...
The current code can only support one kgd instance. We have to
support multiple kgd instances in one system. i.e two amdgpu or two
radeon or one amdgpu + one radeon or more than two kgd instances.
Signed-off-by: Xihan Zhang <xihan.zhang@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
