linux.git/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c, branch v5.6 Linux kernel source tree drm/amdkfd: Fix a bug in SDMA RLC queue counting under HWS mode 2020-02-04T15:32:41+00:00 Yong Zhao Yong.Zhao@amd.com 2020-01-30T00:55:47+00:00 f38abc15d157b7b31fa7f651dc8bf92858c963f8 The sdma_queue_count increment should be done before execute_queues_cpsch(), which calls pm_calc_rlib_size() where sdma_queue_count is used to calculate whether over_subscription is triggered. With the previous code, when a SDMA queue is created, compute_queue_count in pm_calc_rlib_size() is one more than the actual compute queue number, because the queue_count has been incremented while sdma_queue_count has not. This patch fixes that. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The sdma_queue_count increment should be done before
execute_queues_cpsch(), which calls pm_calc_rlib_size() where
sdma_queue_count is used to calculate whether over_subscription is
triggered.

With the previous code, when a SDMA queue is created,
compute_queue_count in pm_calc_rlib_size() is one more than the
actual compute queue number, because the queue_count has been
incremented while sdma_queue_count has not. This patch fixes that.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Add a message when SW scheduler is used 2020-01-16T18:38:07+00:00 Yong Zhao Yong.Zhao@amd.com 2020-01-10T19:15:52+00:00 52055039297622f164ed2cead43954bb3e29e1b2 SW scheduler is previously called non HW scheduler, or non HWS. This message is useful when triaging issues from dmesg. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Acked-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
SW scheduler is previously called non HW scheduler, or non HWS. This
message is useful when triaging issues from dmesg.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Avoid hanging hardware in stop_cpsch 2020-01-07T16:55:04+00:00 Felix Kuehling Felix.Kuehling@amd.com 2019-12-20T07:46:55+00:00 c2a77fde10ec2cac33a23c8ac53d181bc2fe0cee Don't use the HWS if it's known to be hanging. In a reset also don't try to destroy the HIQ because that may hang on SRIOV if the KIQ is unresponsive. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: shaoyunl <shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Don't use the HWS if it's known to be hanging. In a reset also
don't try to destroy the HIQ because that may hang on SRIOV if the
KIQ is unresponsive.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: shaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Improve HWS hang detection and handling 2020-01-07T16:54:56+00:00 Felix Kuehling Felix.Kuehling@amd.com 2019-12-20T07:07:54+00:00 09c34e8d7a631cf541c82f46ee73433c28b6ce0e Move HWS hang detection into unmap_queues_cpsch to catch hangs in all cases. If this happens during a reset, don't schedule another reset because the reset already in progress is expected to take care of it. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: shaoyunl <shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Move HWS hang detection into unmap_queues_cpsch to catch hangs in all
cases. If this happens during a reset, don't schedule another reset
because the reset already in progress is expected to take care of it.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: shaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Remove unused variable 2020-01-07T16:54:50+00:00 Felix Kuehling Felix.Kuehling@amd.com 2019-12-20T07:01:24+00:00 63e088acfc330c7031c4c07e8503337d1f36639a dqm->pipeline_mem wasn't used anywhere. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: shaoyunl <shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
dqm->pipeline_mem wasn't used anywhere.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: shaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Delete KFD_MQD_TYPE_COMPUTE 2019-11-22T19:27:11+00:00 Yong Zhao Yong.Zhao@amd.com 2019-11-09T04:57:37+00:00 d7c0b0477bf32f85ca43a1a306092deded50a0b7 It is the same as KFD_MQD_TYPE_CP, so delete it. As a result, we will have one less mqd mananger per device. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
It is the same as KFD_MQD_TYPE_CP, so delete it. As a result, we will
have one less mqd mananger per device.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Use better name to indicate the offset is in dwords 2019-11-13T20:29:45+00:00 Yong Zhao Yong.Zhao@amd.com 2019-01-15T18:16:34+00:00 339903fa989b7a0c9fc26e0f35e36df7e110d737 The doorbell offset could mean the byte offset or the dword offset, and the 0 offset place is also different, sometimes the start of PCI doorbell bar or the start of process doorbell pages. Use better name to avoid confusion. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The doorbell offset could mean the byte offset or the dword offset,
and the 0 offset place is also different, sometimes the start of PCI
doorbell bar or the start of process doorbell pages. Use better name
to avoid confusion.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: don't use dqm lock during device reset/suspend/resume 2019-10-25T20:50:10+00:00 Philip Yang Philip.Yang@amd.com 2019-10-18T14:15:21+00:00 2c99a547bcf9bb8532abd2953479949018449f93 If device reset/suspend/resume failed for some reason, dqm lock is hold forever and this causes deadlock. Below is a kernel backtrace when application open kfd after suspend/resume failed. Instead of holding dqm lock in pre_reset and releasing dqm lock in post_reset, add dqm->sched_running flag which is modified in dqm->ops.start and dqm->ops.stop. The flag doesn't need lock protection because write/read are all inside dqm lock. For HWS case, map_queues_cpsch and unmap_queues_cpsch checks sched_running flag before sending the updated runlist. v2: For no-HWS case, when device is stopped, don't call load/destroy_mqd for eviction, restore and create queue, and avoid debugfs dump hdqs. Backtrace of dqm lock deadlock: [Thu Oct 17 16:43:37 2019] INFO: task rocminfo:3024 blocked for more than 120 seconds. [Thu Oct 17 16:43:37 2019] Not tainted 5.0.0-rc1-kfd-compute-rocm-dkms-no-npi-1131 #1 [Thu Oct 17 16:43:37 2019] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [Thu Oct 17 16:43:37 2019] rocminfo D 0 3024 2947 0x80000000 [Thu Oct 17 16:43:37 2019] Call Trace: [Thu Oct 17 16:43:37 2019] ? __schedule+0x3d9/0x8a0 [Thu Oct 17 16:43:37 2019] schedule+0x32/0x70 [Thu Oct 17 16:43:37 2019] schedule_preempt_disabled+0xa/0x10 [Thu Oct 17 16:43:37 2019] __mutex_lock.isra.9+0x1e3/0x4e0 [Thu Oct 17 16:43:37 2019] ? __call_srcu+0x264/0x3b0 [Thu Oct 17 16:43:37 2019] ? process_termination_cpsch+0x24/0x2f0 [amdgpu] [Thu Oct 17 16:43:37 2019] process_termination_cpsch+0x24/0x2f0 [amdgpu] [Thu Oct 17 16:43:37 2019] kfd_process_dequeue_from_all_devices+0x42/0x60 [amdgpu] [Thu Oct 17 16:43:37 2019] kfd_process_notifier_release+0x1be/0x220 [amdgpu] [Thu Oct 17 16:43:37 2019] __mmu_notifier_release+0x3e/0xc0 [Thu Oct 17 16:43:37 2019] exit_mmap+0x160/0x1a0 [Thu Oct 17 16:43:37 2019] ? __handle_mm_fault+0xba3/0x1200 [Thu Oct 17 16:43:37 2019] ? exit_robust_list+0x5a/0x110 [Thu Oct 17 16:43:37 2019] mmput+0x4a/0x120 [Thu Oct 17 16:43:37 2019] do_exit+0x284/0xb20 [Thu Oct 17 16:43:37 2019] ? handle_mm_fault+0xfa/0x200 [Thu Oct 17 16:43:37 2019] do_group_exit+0x3a/0xa0 [Thu Oct 17 16:43:37 2019] __x64_sys_exit_group+0x14/0x20 [Thu Oct 17 16:43:37 2019] do_syscall_64+0x4f/0x100 [Thu Oct 17 16:43:37 2019] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> 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> 
If device reset/suspend/resume failed for some reason, dqm lock is
hold forever and this causes deadlock. Below is a kernel backtrace when
application open kfd after suspend/resume failed.

Instead of holding dqm lock in pre_reset and releasing dqm lock in
post_reset, add dqm->sched_running flag which is modified in
dqm->ops.start and dqm->ops.stop. The flag doesn't need lock protection
because write/read are all inside dqm lock.

For HWS case, map_queues_cpsch and unmap_queues_cpsch checks
sched_running flag before sending the updated runlist.

v2: For no-HWS case, when device is stopped, don't call
load/destroy_mqd for eviction, restore and create queue, and avoid
debugfs dump hdqs.

Backtrace of dqm lock deadlock:

[Thu Oct 17 16:43:37 2019] INFO: task rocminfo:3024 blocked for more
than 120 seconds.
[Thu Oct 17 16:43:37 2019]       Not tainted
5.0.0-rc1-kfd-compute-rocm-dkms-no-npi-1131 #1
[Thu Oct 17 16:43:37 2019] "echo 0 >
/proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Thu Oct 17 16:43:37 2019] rocminfo        D    0  3024   2947
0x80000000
[Thu Oct 17 16:43:37 2019] Call Trace:
[Thu Oct 17 16:43:37 2019]  ? __schedule+0x3d9/0x8a0
[Thu Oct 17 16:43:37 2019]  schedule+0x32/0x70
[Thu Oct 17 16:43:37 2019]  schedule_preempt_disabled+0xa/0x10
[Thu Oct 17 16:43:37 2019]  __mutex_lock.isra.9+0x1e3/0x4e0
[Thu Oct 17 16:43:37 2019]  ? __call_srcu+0x264/0x3b0
[Thu Oct 17 16:43:37 2019]  ? process_termination_cpsch+0x24/0x2f0
[amdgpu]
[Thu Oct 17 16:43:37 2019]  process_termination_cpsch+0x24/0x2f0
[amdgpu]
[Thu Oct 17 16:43:37 2019]
kfd_process_dequeue_from_all_devices+0x42/0x60 [amdgpu]
[Thu Oct 17 16:43:37 2019]  kfd_process_notifier_release+0x1be/0x220
[amdgpu]
[Thu Oct 17 16:43:37 2019]  __mmu_notifier_release+0x3e/0xc0
[Thu Oct 17 16:43:37 2019]  exit_mmap+0x160/0x1a0
[Thu Oct 17 16:43:37 2019]  ? __handle_mm_fault+0xba3/0x1200
[Thu Oct 17 16:43:37 2019]  ? exit_robust_list+0x5a/0x110
[Thu Oct 17 16:43:37 2019]  mmput+0x4a/0x120
[Thu Oct 17 16:43:37 2019]  do_exit+0x284/0xb20
[Thu Oct 17 16:43:37 2019]  ? handle_mm_fault+0xfa/0x200
[Thu Oct 17 16:43:37 2019]  do_group_exit+0x3a/0xa0
[Thu Oct 17 16:43:37 2019]  __x64_sys_exit_group+0x14/0x20
[Thu Oct 17 16:43:37 2019]  do_syscall_64+0x4f/0x100
[Thu Oct 17 16:43:37 2019]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
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>
drm/amdkfd: Print more sdma engine hqds in debug fs 2019-10-07T20:10:01+00:00 Oak Zeng Oak.Zeng@amd.com 2019-10-04T14:34:29+00:00 c4bb16e0f81751b1b2811ebf2136371d8b8307e9 Previously only PCIe-optimized SDMA engine hqds were exposed in debug fs. Print all SDMA engine hqds. Reported-by: Jonathan Kim <Jonathan.Kim@amd.com> Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com> Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Previously only PCIe-optimized SDMA engine hqds were
exposed in debug fs. Print all SDMA engine hqds.

Reported-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix MQD size calculation 2019-10-07T20:09:53+00:00 Oak Zeng Oak.Zeng@amd.com 2019-10-04T14:28:21+00:00 40a9592a26608e16f7545a068ea4165e1869f629 On device initialization, a chunk of GTT memory is pre-allocated for HIQ and all SDMA queues mqd. The size of this allocation was wrong. The correct sdma engine number should be PCIe-optimized SDMA engine number plus xgmi SDMA engine number. Reported-by: Jonathan Kim <Jonathan.Kim@amd.com> Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com> Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
On device initialization, a chunk of GTT memory is pre-allocated for
HIQ and all SDMA queues mqd. The size of this allocation was wrong.
The correct sdma engine number should be PCIe-optimized SDMA engine
number plus xgmi SDMA engine number.

Reported-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>