diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_events.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_events.c | 39 |
1 files changed, 38 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 739721254a5d..d075f24e5f9f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -31,6 +31,7 @@ #include <linux/memory.h> #include "kfd_priv.h" #include "kfd_events.h" +#include "kfd_device_queue_manager.h" #include <linux/device.h> /* @@ -747,6 +748,16 @@ void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, uint64_t *slots = page_slots(p->signal_page); uint32_t id; + /* + * If id is valid but slot is not signaled, GPU may signal the same event twice + * before driver have chance to process the first interrupt, then signal slot is + * auto-reset after set_event wakeup the user space, just drop the second event as + * the application only need wakeup once. + */ + if ((valid_id_bits > 31 || (1U << valid_id_bits) >= KFD_SIGNAL_EVENT_LIMIT) && + partial_id < KFD_SIGNAL_EVENT_LIMIT && slots[partial_id] == UNSIGNALED_EVENT_SLOT) + goto out_unlock; + if (valid_id_bits) pr_debug_ratelimited("Partial ID invalid: %u (%u valid bits)\n", partial_id, valid_id_bits); @@ -775,6 +786,7 @@ void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, } } +out_unlock: rcu_read_unlock(); kfd_unref_process(p); } @@ -1244,12 +1256,33 @@ void kfd_signal_reset_event(struct kfd_node *dev) idx = srcu_read_lock(&kfd_processes_srcu); hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) { int user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id); + struct kfd_process_device *pdd = kfd_get_process_device_data(dev, p); if (unlikely(user_gpu_id == -EINVAL)) { WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id); continue; } + if (unlikely(!pdd)) { + WARN_ONCE(1, "Could not get device data from pasid:0x%x\n", p->pasid); + continue; + } + + if (dev->dqm->detect_hang_count && !pdd->has_reset_queue) + continue; + + if (dev->dqm->detect_hang_count) { + struct amdgpu_task_info *ti; + + ti = amdgpu_vm_get_task_info_pasid(dev->adev, p->pasid); + if (ti) { + dev_err(dev->adev->dev, + "Queues reset on process %s tid %d thread %s pid %d\n", + ti->process_name, ti->tgid, ti->task_name, ti->pid); + amdgpu_vm_put_task_info(ti); + } + } + rcu_read_lock(); id = KFD_FIRST_NONSIGNAL_EVENT_ID; @@ -1285,8 +1318,10 @@ void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid) uint32_t id = KFD_FIRST_NONSIGNAL_EVENT_ID; int user_gpu_id; - if (!p) + if (!p) { + dev_warn(dev->adev->dev, "Not find process with pasid:%d\n", pasid); return; /* Presumably process exited. */ + } user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id); if (unlikely(user_gpu_id == -EINVAL)) { @@ -1322,6 +1357,8 @@ void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid) } } + dev_warn(dev->adev->dev, "Send SIGBUS to process %s(pasid:%d)\n", + p->lead_thread->comm, pasid); rcu_read_unlock(); /* user application will handle SIGBUS signal */ |