blob: bcc7b6b650099bba27fbdc9d7e3b5ca07750712e (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0-only
#
# Copyright 2015, Daniel Axtens, IBM Corporation
#
# do we have ./getscom, ./putscom?
if [ -x ./getscom ] && [ -x ./putscom ]; then
GETSCOM=./getscom
PUTSCOM=./putscom
elif which getscom > /dev/null; then
GETSCOM=$(which getscom)
PUTSCOM=$(which putscom)
else
cat <<EOF
Can't find getscom/putscom in . or \$PATH.
See https://github.com/open-power/skiboot.
The tool is in external/xscom-utils
EOF
exit 1
fi
# We will get 8 HMI events per injection
# todo: deal with things being offline
expected_hmis=8
COUNT_HMIS() {
dmesg | grep -c 'Harmless Hypervisor Maintenance interrupt'
}
# massively expand snooze delay, allowing injection on all cores
ppc64_cpu --smt-snooze-delay=1000000000
# when we exit, restore it
trap "ppc64_cpu --smt-snooze-delay=100" 0 1
# for each chip+core combination
# todo - less fragile parsing
grep -E -o 'OCC: Chip [0-9a-f]+ Core [0-9a-f]' < /sys/firmware/opal/msglog |
while read chipcore; do
chip=$(echo "$chipcore"|awk '{print $3}')
core=$(echo "$chipcore"|awk '{print $5}')
fir="0x1${core}013100"
# verify that Core FIR is zero as expected
if [ "$($GETSCOM -c 0x${chip} $fir)" != 0 ]; then
echo "FIR was not zero before injection for chip $chip, core $core. Aborting!"
echo "Result of $GETSCOM -c 0x${chip} $fir:"
$GETSCOM -c 0x${chip} $fir
echo "If you get a -5 error, the core may be in idle state. Try stress-ng."
echo "Otherwise, try $PUTSCOM -c 0x${chip} $fir 0"
exit 1
fi
# keep track of the number of HMIs handled
old_hmis=$(COUNT_HMIS)
# do injection, adding a marker to dmesg for clarity
echo "Injecting HMI on core $core, chip $chip" | tee /dev/kmsg
# inject a RegFile recoverable error
if ! $PUTSCOM -c 0x${chip} $fir 2000000000000000 > /dev/null; then
echo "Error injecting. Aborting!"
exit 1
fi
# now we want to wait for all the HMIs to be processed
# we expect one per thread on the core
i=0;
new_hmis=$(COUNT_HMIS)
while [ $new_hmis -lt $((old_hmis + expected_hmis)) ] && [ $i -lt 12 ]; do
echo "Seen $((new_hmis - old_hmis)) HMI(s) out of $expected_hmis expected, sleeping"
sleep 5;
i=$((i + 1))
new_hmis=$(COUNT_HMIS)
done
if [ $i = 12 ]; then
echo "Haven't seen expected $expected_hmis recoveries after 1 min. Aborting."
exit 1
fi
echo "Processed $expected_hmis events; presumed success. Check dmesg."
echo ""
done
|
