drm/amdkfd: Add module parameter of send_sigterm

This patch adds a new kernel module parameter to amdkfd,
called send_sigterm.

This parameter specifies whether amdkfd should send the
SIGTERM signal to an HSA process, when the following conditions
occur:

1. The GPU triggers an exception regarding a kernel that was
   issued by this process.

2. The HSA process isn't waiting on an event that handles
   this exception.

The default behavior is not to send a SIGTERM and suffice
with a dmesg error print.

Reviewed-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

1 files changed, 9 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 5c3a81e667a8..3cb37d220f60 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -872,10 +872,16 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 
 	/* Send SIGTERM no event of type "type" has been found*/
 	if (send_signal) {
-		dev_warn(kfd_device,
-			"Sending SIGTERM to HSA Process with PID %d ",
+		if (send_sigterm) {
+			dev_warn(kfd_device,
+				"Sending SIGTERM to HSA Process with PID %d ",
+					p->lead_thread->pid);
+			send_sig(SIGTERM, p->lead_thread, 0);
+		} else {
+			dev_err(kfd_device,
+				"HSA Process (PID %d) got unhandled exception",
 				p->lead_thread->pid);
-		send_sig(SIGTERM, p->lead_thread, 0);
+		}
 	}
 }