UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: change reset lock from mutex to rw_semaphore 

clients don't need reset-lock for synchronization when no
GPU recovery.

v2:
change to return the return value of down_read_killable.

v3:
if GPU recovery begin, VF ignore FLR notification.

Reviewed-by: Monk Liu <monk.liu@amd.com>
Acked-by: Christian König <christian.koenig@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 2020-08-20 10:06:32 +08:00 committed by Alex Deucher
parent 66b8a9c0a7
commit 6049db43d6
5 changed files with 32 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/gpu/drm/amd/amdgpu/amdgpu.h
View File

@ -951,7 +951,7 @@ struct amdgpu_device {
atomic_t in_gpu_reset;
enum pp_mp1_state mp1_state;
struct mutex lock_reset;
struct rw_semaphore reset_sem;
struct amdgpu_doorbell_index doorbell_index;
struct mutex notifier_lock;

23
drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
View File

@ -101,14 +101,18 @@ static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
file->private_data = adev;
mutex_lock(&adev->lock_reset);
ret = down_read_killable(&adev->reset_sem);
if (ret)
return ret;
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;
}
@ -1242,7 +1246,9 @@ 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);
r = down_read_killable(&adev->reset_sem);
if (r)
return r;
/* hold on the scheduler */
for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
@ -1269,7 +1275,7 @@ 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);
@ -1459,7 +1465,9 @@ 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);
r = down_read_killable(&adev->reset_sem);
if (r)
goto pro_end;
/* stop the scheduler */
kthread_park(ring->sched.thread);
@ -1500,13 +1508,14 @@ 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);
pro_end:
kfree(fences);
return 0;
return r;
}
static int amdgpu_debugfs_sclk_set(void *data, u64 val)

6
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@ -3054,7 +3054,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
mutex_init(&adev->virt.vf_errors.lock);
hash_init(adev->mn_hash);
atomic_set(&adev->in_gpu_reset, 0);
mutex_init(&adev->lock_reset);
init_rwsem(&adev->reset_sem);
mutex_init(&adev->psp.mutex);
mutex_init(&adev->notifier_lock);
@ -4206,7 +4206,7 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev)
if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
return false;
mutex_lock(&adev->lock_reset);
down_write(&adev->reset_sem);
atomic_inc(&adev->gpu_reset_counter);
switch (amdgpu_asic_reset_method(adev)) {
@ -4229,7 +4229,7 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
amdgpu_vf_error_trans_all(adev);
adev->mp1_state = PP_MP1_STATE_NONE;
atomic_set(&adev->in_gpu_reset, 0);
mutex_unlock(&adev->lock_reset);
up_write(&adev->reset_sem);
}
static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev)

18
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
View File

@ -238,19 +238,15 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work);
struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
int timeout = AI_MAILBOX_POLL_FLR_TIMEDOUT;
int locked;
/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*
* we can unlock the lock_reset to allow "amdgpu_job_timedout"
* to run gpu_recover() after FLR_NOTIFICATION_CMPL received
* which means host side had finished this VF's FLR.
*/
locked = mutex_trylock(&adev->lock_reset);
if (locked)
atomic_set(&adev->in_gpu_reset, 1);
if (!down_read_trylock(&adev->reset_sem))
return;
atomic_set(&adev->in_gpu_reset, 1);
do {
if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@ -261,10 +257,8 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
} while (timeout > 1);
flr_done:
if (locked) {
atomic_set(&adev->in_gpu_reset, 0);
mutex_unlock(&adev->lock_reset);
}
atomic_set(&adev->in_gpu_reset, 0);
up_read(&adev->reset_sem);
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)

18
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
View File

@ -259,19 +259,15 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work);
struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
int timeout = NV_MAILBOX_POLL_FLR_TIMEDOUT;
int locked;
/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*
* we can unlock the lock_reset to allow "amdgpu_job_timedout"
* to run gpu_recover() after FLR_NOTIFICATION_CMPL received
* which means host side had finished this VF's FLR.
*/
locked = mutex_trylock(&adev->lock_reset);
if (locked)
atomic_set(&adev->in_gpu_reset, 1);
if (!down_read_trylock(&adev->reset_sem))
return;
atomic_set(&adev->in_gpu_reset, 1);
do {
if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@ -282,10 +278,8 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
} while (timeout > 1);
flr_done:
if (locked) {
atomic_set(&adev->in_gpu_reset, 0);
mutex_unlock(&adev->lock_reset);
}
atomic_set(&adev->in_gpu_reset, 0);
up_read(&adev->reset_sem);
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)