summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/powerpc/eeh
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/powerpc/eeh')
-rw-r--r--tools/testing/selftests/powerpc/eeh/Makefile9
-rwxr-xr-xtools/testing/selftests/powerpc/eeh/eeh-basic.sh90
-rwxr-xr-xtools/testing/selftests/powerpc/eeh/eeh-functions.sh85
3 files changed, 184 insertions, 0 deletions
diff --git a/tools/testing/selftests/powerpc/eeh/Makefile b/tools/testing/selftests/powerpc/eeh/Makefile
new file mode 100644
index 000000000..b397babd5
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+ $(MAKE) -C ../
+
+TEST_PROGS := eeh-basic.sh
+TEST_FILES := eeh-functions.sh
+
+top_srcdir = ../../../../..
+include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
new file mode 100755
index 000000000..64779f073
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
@@ -0,0 +1,90 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+KSELFTESTS_SKIP=4
+
+. ./eeh-functions.sh
+
+if ! eeh_supported ; then
+ echo "EEH not supported on this system, skipping"
+ exit $KSELFTESTS_SKIP;
+fi
+
+if [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_check" ] && \
+ [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_break" ] ; then
+ echo "debugfs EEH testing files are missing. Is debugfs mounted?"
+ exit $KSELFTESTS_SKIP;
+fi
+
+pre_lspci=`mktemp`
+lspci > $pre_lspci
+
+# Bump the max freeze count to something absurd so we don't
+# trip over it while breaking things.
+echo 5000 > /sys/kernel/debug/powerpc/eeh_max_freezes
+
+# record the devices that we break in here. Assuming everything
+# goes to plan we should get them back once the recover process
+# is finished.
+devices=""
+
+# Build up a list of candidate devices.
+for dev in `ls -1 /sys/bus/pci/devices/ | grep '\.0$'` ; do
+ # skip bridges since we can't recover them (yet...)
+ if [ -e "/sys/bus/pci/devices/$dev/pci_bus" ] ; then
+ echo "$dev, Skipped: bridge"
+ continue;
+ fi
+
+ # Skip VFs for now since we don't have a reliable way
+ # to break them.
+ if [ -e "/sys/bus/pci/devices/$dev/physfn" ] ; then
+ echo "$dev, Skipped: virtfn"
+ continue;
+ fi
+
+ if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then
+ echo "$dev, Skipped: ahci doesn't support recovery"
+ continue
+ fi
+
+ # Don't inject errosr into an already-frozen PE. This happens with
+ # PEs that contain multiple PCI devices (e.g. multi-function cards)
+ # and injecting new errors during the recovery process will probably
+ # result in the recovery failing and the device being marked as
+ # failed.
+ if ! pe_ok $dev ; then
+ echo "$dev, Skipped: Bad initial PE state"
+ continue;
+ fi
+
+ echo "$dev, Added"
+
+ # Add to this list of device to check
+ devices="$devices $dev"
+done
+
+dev_count="$(echo $devices | wc -w)"
+echo "Found ${dev_count} breakable devices..."
+
+failed=0
+for dev in $devices ; do
+ echo "Breaking $dev..."
+
+ if ! pe_ok $dev ; then
+ echo "Skipping $dev, Initial PE state is not ok"
+ failed="$((failed + 1))"
+ continue;
+ fi
+
+ if ! eeh_one_dev $dev ; then
+ failed="$((failed + 1))"
+ fi
+done
+
+echo "$failed devices failed to recover ($dev_count tested)"
+lspci | diff -u $pre_lspci -
+rm -f $pre_lspci
+
+test "$failed" -eq 0
+exit $?
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
new file mode 100755
index 000000000..00dc32c0e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
@@ -0,0 +1,85 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+pe_ok() {
+ local dev="$1"
+ local path="/sys/bus/pci/devices/$dev/eeh_pe_state"
+
+ # if a driver doesn't support the error handling callbacks then the
+ # device is recovered by removing and re-probing it. This causes the
+ # sysfs directory to disappear so read the PE state once and squash
+ # any potential error messages
+ local eeh_state="$(cat $path 2>/dev/null)"
+ if [ -z "$eeh_state" ]; then
+ return 1;
+ fi
+
+ local fw_state="$(echo $eeh_state | cut -d' ' -f1)"
+ local sw_state="$(echo $eeh_state | cut -d' ' -f2)"
+
+ # If EEH_PE_ISOLATED or EEH_PE_RECOVERING are set then the PE is in an
+ # error state or being recovered. Either way, not ok.
+ if [ "$((sw_state & 0x3))" -ne 0 ] ; then
+ return 1
+ fi
+
+ # A functioning PE should have the EEH_STATE_MMIO_ACTIVE and
+ # EEH_STATE_DMA_ACTIVE flags set. For some goddamn stupid reason
+ # the platform backends set these when the PE is in reset. The
+ # RECOVERING check above should stop any false positives though.
+ if [ "$((fw_state & 0x18))" -ne "$((0x18))" ] ; then
+ return 1
+ fi
+
+ return 0;
+}
+
+eeh_supported() {
+ test -e /proc/powerpc/eeh && \
+ grep -q 'EEH Subsystem is enabled' /proc/powerpc/eeh
+}
+
+eeh_one_dev() {
+ local dev="$1"
+
+ # Using this function from the command line is sometimes useful for
+ # testing so check that the argument is a well-formed sysfs device
+ # name.
+ if ! test -e /sys/bus/pci/devices/$dev/ ; then
+ echo "Error: '$dev' must be a sysfs device name (DDDD:BB:DD.F)"
+ return 1;
+ fi
+
+ # Break it
+ echo $dev >/sys/kernel/debug/powerpc/eeh_dev_break
+
+ # Force an EEH device check. If the kernel has already
+ # noticed the EEH (due to a driver poll or whatever), this
+ # is a no-op.
+ echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check
+
+ # Default to a 60s timeout when waiting for a device to recover. This
+ # is an arbitrary default which can be overridden by setting the
+ # EEH_MAX_WAIT environmental variable when required.
+
+ # The current record holder for longest recovery time is:
+ # "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds
+ max_wait=${EEH_MAX_WAIT:=60}
+
+ for i in `seq 0 ${max_wait}` ; do
+ if pe_ok $dev ; then
+ break;
+ fi
+ echo "$dev, waited $i/${max_wait}"
+ sleep 1
+ done
+
+ if ! pe_ok $dev ; then
+ echo "$dev, Failed to recover!"
+ return 1;
+ fi
+
+ echo "$dev, Recovered after $i seconds"
+ return 0;
+}
+