This is a note to let you know that I've just added the patch titled
drm/amdkfd: Handle restart of kfd_ioctl_wait_events
to the 5.19-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdkfd-handle-restart-of-kfd_ioctl_wait_events.patch
and it can be found in the queue-5.19 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 57944749731472eb98c7feffc6c251ecc23b02cc
Author: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Date: Thu Aug 4 18:19:38 2022 -0400
drm/amdkfd: Handle restart of kfd_ioctl_wait_events
[ Upstream commit bea9a56afbc4b5a41ea579b8b0dc5e189b439504 ]
When kfd_ioctl_wait_events needs to restart due to a signal, we need to
update the timeout to account for the time already elapsed. We also need
to undo auto_reset of events that have signaled already, so that the
restarted ioctl will be able to count those signals again.
This fixes infinite hangs when kfd_ioctl_wait_events is interrupted by a
signal.
Signed-off-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Reviewed-and-tested-by: Xiaogang Chen <Xiaogang.Chen@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 1c7016958d6d9..bfca17ca399c6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -814,7 +814,7 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
err = kfd_wait_on_events(p, args->num_events,
(void __user *)args->events_ptr,
(args->wait_for_all != 0),
- args->timeout, &args->wait_result);
+ &args->timeout, &args->wait_result);
return err;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 4df9c36146ba9..cbc20d779e5aa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -895,7 +895,8 @@ static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
return msecs_to_jiffies(user_timeout_ms) + 1;
}
-static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
+static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters,
+ bool undo_auto_reset)
{
uint32_t i;
@@ -904,6 +905,9 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
spin_lock(&waiters[i].event->lock);
remove_wait_queue(&waiters[i].event->wq,
&waiters[i].wait);
+ if (undo_auto_reset && waiters[i].activated &&
+ waiters[i].event && waiters[i].event->auto_reset)
+ set_event(waiters[i].event);
spin_unlock(&waiters[i].event->lock);
}
@@ -912,7 +916,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
- bool all, uint32_t user_timeout_ms,
+ bool all, uint32_t *user_timeout_ms,
uint32_t *wait_result)
{
struct kfd_event_data __user *events =
@@ -921,7 +925,7 @@ int kfd_wait_on_events(struct kfd_process *p,
int ret = 0;
struct kfd_event_waiter *event_waiters = NULL;
- long timeout = user_timeout_to_jiffies(user_timeout_ms);
+ long timeout = user_timeout_to_jiffies(*user_timeout_ms);
event_waiters = alloc_event_waiters(num_events);
if (!event_waiters) {
@@ -971,15 +975,11 @@ int kfd_wait_on_events(struct kfd_process *p,
}
if (signal_pending(current)) {
- /*
- * This is wrong when a nonzero, non-infinite timeout
- * is specified. We need to use
- * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
- * contains a union with data for each user and it's
- * in generic kernel code that I don't want to
- * touch yet.
- */
ret = -ERESTARTSYS;
+ if (*user_timeout_ms != KFD_EVENT_TIMEOUT_IMMEDIATE &&
+ *user_timeout_ms != KFD_EVENT_TIMEOUT_INFINITE)
+ *user_timeout_ms = jiffies_to_msecs(
+ max(0l, timeout-1));
break;
}
@@ -1020,7 +1020,7 @@ int kfd_wait_on_events(struct kfd_process *p,
event_waiters, events);
out_unlock:
- free_waiters(num_events, event_waiters);
+ free_waiters(num_events, event_waiters, ret == -ERESTARTSYS);
mutex_unlock(&p->event_mutex);
out:
if (ret)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 2585d6e61d422..c6eec54b8102f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1314,7 +1314,7 @@ void kfd_event_free_process(struct kfd_process *p);
int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
- bool all, uint32_t user_timeout_ms,
+ bool all, uint32_t *user_timeout_ms,
uint32_t *wait_result);
void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
uint32_t valid_id_bits);
