git/linux-cryptodev-2.6
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git synced 2026-04-18 19:43:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: fix system hang issue during GPU reset

Browse Source 
when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover,
the atomic adev->in_gpu_reset and hive->in_reset are used to avoid
re-entering GPU recovery.

During GPU reset and resume, it is unsafe that other threads access GPU,
which maybe cause GPU reset failed. Therefore the new rw_semaphore
adev->reset_sem is introduced, which protect GPU from being accessed by
external threads during recovery.

v2:
1. add rwlock for some ioctls, debugfs and file-close function.
2. change to use dqm->is_resetting and dqm_lock for protection in kfd
driver.
3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid
re-enter GPU recovery for the same GPU hang.

v3:
1. change back to use adev->reset_sem to protect kfd callback
functions, because dqm_lock couldn't protect all codes, for example:
free_mqd must be called outside of dqm_lock;

[ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019
[ 1230.177221] Call Trace:
[ 1230.178249]  dump_stack+0x98/0xd5
[ 1230.179443]  amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu]
[ 1230.180673]  gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu]
[ 1230.181882]  amdgpu_gart_unbind+0xa9/0xe0 [amdgpu]
[ 1230.183098]  amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu]
[ 1230.184239]  ? ttm_bo_put+0x171/0x5f0 [ttm]
[ 1230.185394]  ttm_tt_unbind+0x21/0x40 [ttm]
[ 1230.186558]  ttm_tt_destroy.part.12+0x12/0x60 [ttm]
[ 1230.187707]  ttm_tt_destroy+0x13/0x20 [ttm]
[ 1230.188832]  ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm]
[ 1230.189979]  ttm_bo_put+0x1be/0x5f0 [ttm]
[ 1230.191230]  amdgpu_bo_unref+0x1e/0x30 [amdgpu]
[ 1230.192522]  amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu]
[ 1230.193833]  free_mqd+0x25/0x40 [amdgpu]
[ 1230.195143]  destroy_queue_cpsch+0x1a7/0x270 [amdgpu]
[ 1230.196475]  pqm_destroy_queue+0x105/0x260 [amdgpu]
[ 1230.197819]  kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu]
[ 1230.199154]  kfd_ioctl+0x277/0x500 [amdgpu]
[ 1230.200458]  ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu]
[ 1230.201656]  ? tomoyo_file_ioctl+0x19/0x20
[ 1230.202831]  ksys_ioctl+0x98/0xb0
[ 1230.204004]  __x64_sys_ioctl+0x1a/0x20
[ 1230.205174]  do_syscall_64+0x5f/0x250
[ 1230.206339]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

2. remove try_lock and introduce atomic hive->in_reset, to avoid
re-enter GPU recovery.

v4:
1. remove an unnecessary whitespace change in kfd_chardev.c
2. remove comment codes in amdgpu_device.c
3. add more detailed comment in commit message
4. define a wrap function amdgpu_in_reset

v5:
1. Fix some style issues.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com>
Suggested-by: Luben Tukov <luben.tuikov@amd.com>
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Dennis Li
2020-07-08 15:07:13 +08:00
committed by Alex Deucher
parent c5079f35c0
commit df9c8d1aa2
39 changed files with 463 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
View File

@@ -100,14 +100,14 @@ static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
file->private_data = adev;
mutex_lock(&adev->lock_reset);
down_read(&adev->reset_sem);
if (adev->autodump.dumping.done) {
reinit_completion(&adev->autodump.dumping);
ret = 0;
} else {
ret = -EBUSY;
}
mutex_unlock(&adev->lock_reset);
up_read(&adev->reset_sem);
return ret;
}
@@ -126,7 +126,7 @@ static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_
poll_wait(file, &adev->autodump.gpu_hang, poll_table);
if (adev->in_gpu_reset)
if (amdgpu_in_reset(adev))
return POLLIN | POLLRDNORM | POLLWRNORM;
return 0;
@@ -1241,7 +1241,7 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
}
/* Avoid accidently unparking the sched thread during GPU reset */
mutex_lock(&adev->lock_reset);
down_read(&adev->reset_sem);
/* hold on the scheduler */
for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
@@ -1268,7 +1268,7 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
kthread_unpark(ring->sched.thread);
}
mutex_unlock(&adev->lock_reset);
up_read(&adev->reset_sem);
pm_runtime_mark_last_busy(dev->dev);
pm_runtime_put_autosuspend(dev->dev);
@@ -1458,7 +1458,7 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
return -ENOMEM;
/* Avoid accidently unparking the sched thread during GPU reset */
mutex_lock(&adev->lock_reset);
down_read(&adev->reset_sem);
/* stop the scheduler */
kthread_park(ring->sched.thread);
@@ -1499,7 +1499,7 @@ failure:
/* restart the scheduler */
kthread_unpark(ring->sched.thread);
mutex_unlock(&adev->lock_reset);
up_read(&adev->reset_sem);
ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);