linux-stable.git/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c, branch linux-5.5.y Linux kernel stable tree drm/amdkfd: Fix a bug in SDMA RLC queue counting under HWS mode 2020-02-24T07:38:10+00:00 Yong Zhao Yong.Zhao@amd.com 2020-01-30T00:55:47+00:00 4daa2141cf5514f7ee6d8cad41465a76e5ae42c0 [ Upstream commit 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> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
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>
drm/amdkfd: Record vmid pasid mapping in the driver for non HWS mode 2019-10-03T14:11:03+00:00 Yong Zhao Yong.Zhao@amd.com 2019-09-26T03:49:46+00:00 d9d4623c87e9318549e0c85133c38909d9e8c47a This makes possible the vmid pasid mapping query through software. 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> 
This makes possible the vmid pasid mapping query through software.

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 hex print format for pasid 2019-10-03T14:11:03+00:00 Yong Zhao Yong.Zhao@amd.com 2019-09-25T21:00:59+00:00 6027b1bf6071fc61a5aa11b9922a2e0e91bff1ea Since KFD pasid starts from 0x8000 (32768 in decimal), it is better perceived as a hex number. Meanwhile, change the pasid type from unsigned int to uint16_t to be consistent throughout the code. 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> 
Since KFD pasid starts from 0x8000 (32768 in decimal), it is better
perceived as a hex number. Meanwhile, change the pasid type from
unsigned int to uint16_t to be consistent throughout the code.

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 navi12 specific family id for navi12 code path 2019-10-03T14:11:03+00:00 shaoyunl shaoyun.liu@amd.com 2019-09-25T21:07:38+00:00 0e94b5640bb764cf223f9dec18bed139e8e17f4c Keep the same use of CHIP_IDs for navi12 in kfd Signed-off-by: shaoyunl <shaoyun.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Keep the same use of CHIP_IDs for navi12 in kfd

Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix NULL pointer dereference for set_scratch_backing_va() 2019-10-03T14:11:01+00:00 Yong Zhao Yong.Zhao@amd.com 2019-09-18T22:17:57+00:00 c637b36aeac11685a8258f9bcd667dcc06f6951a Currently this function pointer is missing for GFX10. Considering it is a void function since GFX9, fix it by checking the function pointer before dereferencing it. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Currently this function pointer is missing for GFX10. Considering it is
a void function since GFX9, fix it by checking the function pointer
before dereferencing it.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Remove unnecessary pm_init() for non HWS mode 2019-10-03T14:11:01+00:00 Yong Zhao Yong.Zhao@amd.com 2019-01-23T01:09:17+00:00 424b5442a2a67ba369839455c3b1fb1b00c6d861 The packet manager is not needed for non HWS mode except Hawaii, so only initialize it for Hawaii under non HWS mode. This will simplify debugging under non HWS mode for all new asics, because it eliminates one variable out of the equation in non HWS mode Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The packet manager is not needed for non HWS mode except Hawaii, so only
initialize it for Hawaii under non HWS mode. This will simplify debugging
under non HWS mode for all new asics, because it eliminates one variable
out of the equation in non HWS mode

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: enable kfd device queue manager v9 for renoir 2019-09-16T14:55:02+00:00 Huang Rui ray.huang@amd.com 2019-09-02T15:10:52+00:00 5a959a8988d83f24ed1b854154f2a5c0bf189560 Renoir is GFX9, so enable v9 devcie queue manager. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Renoir is GFX9, so enable v9 devcie queue manager.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>