drm/amdkfd: update process interrupt handling for debug events

The debugger must be notified by any debugger subscribed exception
that comes from hardware interrupts.

If a debugger session exits, any exceptions it subscribed to may still
have interrupts in the interrupt ring buffer or KGD/KFD pipeline.
To prevent a new session from inheriting stale interrupts, when a new
queue is created, open an interrupt drain and allow the IH ring to drain
from a timestamped checkpoint.  Then inject a custom IV so that once
the custom IV is picked up by the KFD, it's safe to close the drain
and proceed with queue creation.

The drain must also be on debug disable as SW interrupts may still
be processed.  Drain at this time and clear all the exception status.

The debugger may also not be attached nor subscibed to certain
exceptions so forward them directly to the runtime.

GFX10 also requires its own IV processing, hence the creation of
kfd_int_process_v10.c.  This is because the IV from SQ interrupts are
packed into a new continguous format unlike GFX9. To make this clear,
a separate interrupting handling code file was created.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 47 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 3b7f219c9d06..3d3611705d41 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -862,6 +862,8 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 		kfd_procfs_add_sysfs_stats(process);
 		kfd_procfs_add_sysfs_files(process);
 		kfd_procfs_add_sysfs_counters(process);
+
+		init_waitqueue_head(&process->wait_irq_drain);
 	}
 out:
 	if (!IS_ERR(process))
@@ -2136,6 +2138,51 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type)
 	}
 }
 
+/* assumes caller holds process lock. */
+int kfd_process_drain_interrupts(struct kfd_process_device *pdd)
+{
+	uint32_t irq_drain_fence[8];
+	int r = 0;
+
+	if (!KFD_IS_SOC15(pdd->dev))
+		return 0;
+
+	pdd->process->irq_drain_is_open = true;
+
+	memset(irq_drain_fence, 0, sizeof(irq_drain_fence));
+	irq_drain_fence[0] = (KFD_IRQ_FENCE_SOURCEID << 8) |
+							KFD_IRQ_FENCE_CLIENTID;
+	irq_drain_fence[3] = pdd->process->pasid;
+
+	/* ensure stale irqs scheduled KFD interrupts and send drain fence. */
+	if (amdgpu_amdkfd_send_close_event_drain_irq(pdd->dev->adev,
+						     irq_drain_fence)) {
+		pdd->process->irq_drain_is_open = false;
+		return 0;
+	}
+
+	r = wait_event_interruptible(pdd->process->wait_irq_drain,
+				     !READ_ONCE(pdd->process->irq_drain_is_open));
+	if (r)
+		pdd->process->irq_drain_is_open = false;
+
+	return r;
+}
+
+void kfd_process_close_interrupt_drain(unsigned int pasid)
+{
+	struct kfd_process *p;
+
+	p = kfd_lookup_process_by_pasid(pasid);
+
+	if (!p)
+		return;
+
+	WRITE_ONCE(p->irq_drain_is_open, false);
+	wake_up_all(&p->wait_irq_drain);
+	kfd_unref_process(p);
+}
+
 struct send_exception_work_handler_workarea {
 	struct work_struct work;
 	struct kfd_process *p;