diff options
Diffstat (limited to 'tools/guest-diag/guest_kprobes.sh')
| -rw-r--r-- | tools/guest-diag/guest_kprobes.sh | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/tools/guest-diag/guest_kprobes.sh b/tools/guest-diag/guest_kprobes.sh index 75b2ba3..cf34833 100644 --- a/tools/guest-diag/guest_kprobes.sh +++ b/tools/guest-diag/guest_kprobes.sh @@ -22,6 +22,19 @@ if [ ! -d "$TR/events" ]; then mount -t debugfs debugfs "$TR" 2>/dev/null || true fi +# The UVM symbols only exist after nvidia_uvm is loaded. It loads lazily with +# the first CUDA client, but the probes must be armed BEFORE that client's +# first CE push - otherwise no #sem reaches the host, the push page never +# translates and the client stalls in cudaMalloc forever. modprobe it and +# wait (bounded) for the tracking-symbol to appear. +modprobe nvidia_uvm 2>/dev/null || true +i=0 +while [ $i -lt 30 ]; do + grep -qw uvm_gpu_tracking_semaphore_update_completed_value /proc/kallsyms 2>/dev/null && break + i=$((i+1)) + sleep 1 +done + # An enabled kprobe event cannot be deleted (EBUSY); disable the group first. echo 0 > "$TR/events/kprobes/enable" 2>/dev/null || true @@ -81,3 +94,11 @@ echo 65536 > "$TR/buffer_size_kb" 2>/dev/null || true echo > "$TR/trace" 2>/dev/null || true echo "--- installed probes ---" grep -E 'uvmt|uvch|uvbp|uvpbf|uvtw|uvsv' "$TR/kprobe_events" 2>/dev/null || echo "(none)" + +# Arming check: the host recovery pipeline (#sem -> pushbuffer pin) depends on +# these probes; make success/failure explicit for the bring-up scripts. +if grep -q "uvmt" "$TR/kprobe_events" 2>/dev/null; then + echo "KP_ARMED" +else + echo "KP_FAIL uvmt missing" +fi |