selftests/powerpc: Add VF recovery tests

The basic EEH test ignores VFs since we the way the eeh_dev_break debugfs
interface works means that if multiple VFs are enabled we may cause errors
on all them them. However, we can work around that by only enabling a
single VF at a time.

This patch adds some infrastructure for finding SR-IOV capable devices and
enabling / disabling VFs so we can exercise the VF specific EEH recovery
paths. Two new tests are added, one for testing EEH aware devices and one
for EEH un-aware VFs.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201103044503.917128-3-oohall@gmail.com

tools/testing/selftests/powerpc/eeh/eeh-functions.sh

@@ -135,3 +135,111 @@ eeh_one_dev() {
 	return 0;
 }
 
+eeh_has_driver() {
+	test -e /sys/bus/pci/devices/$1/driver;
+	return $?
+}
+
+eeh_can_recover() {
+	# we'll get an IO error if the device's current driver doesn't support
+	# error recovery
+	echo $1 > '/sys/kernel/debug/powerpc/eeh_dev_can_recover' 2>/dev/null
+
+	return $?
+}
+
+eeh_find_all_pfs() {
+	devices=""
+
+	# SR-IOV on pseries requires hypervisor support, so check for that
+	is_pseries=""
+	if grep -q pSeries /proc/cpuinfo ; then
+		if [ ! -f /proc/device-tree/rtas/ibm,open-sriov-allow-unfreeze ] ||
+		   [ ! -f /proc/device-tree/rtas/ibm,open-sriov-map-pe-number ] ; then
+			return 1;
+		fi
+
+		is_pseries="true"
+	fi
+
+	for dev in `ls -1 /sys/bus/pci/devices/` ; do
+		sysfs="/sys/bus/pci/devices/$dev"
+		if [ ! -e "$sysfs/sriov_numvfs" ] ; then
+			continue
+		fi
+
+		# skip unsupported PFs on pseries
+		if [ -z "$is_pseries" ] &&
+		   [ ! -f "$sysfs/of_node/ibm,is-open-sriov-pf" ] &&
+		   [ ! -f "$sysfs/of_node/ibm,open-sriov-vf-bar-info" ] ; then
+			continue;
+		fi
+
+		# no driver, no vfs
+		if ! eeh_has_driver $dev ; then
+			continue
+		fi
+
+		devices="$devices $dev"
+	done
+
+	if [ -z "$devices" ] ; then
+		return 1;
+	fi
+
+	echo $devices
+	return 0;
+}
+
+# attempts to enable one VF on each PF so we can do VF specific tests.
+# stdout: list of enabled VFs, one per line
+# return code: 0 if vfs are found, 1 otherwise
+eeh_enable_vfs() {
+	pf_list="$(eeh_find_all_pfs)"
+
+	vfs=0
+	for dev in $pf_list ; do
+		pf_sysfs="/sys/bus/pci/devices/$dev"
+
+		# make sure we have a single VF
+		echo 0 > "$pf_sysfs/sriov_numvfs"
+		echo 1 > "$pf_sysfs/sriov_numvfs"
+		if [ "$?" != 0 ] ; then
+			log "Unable to enable VFs on $pf, skipping"
+			continue;
+		fi
+
+		vf="$(basename $(realpath "$pf_sysfs/virtfn0"))"
+		if [ $? != 0 ] ; then
+			log "unable to find enabled vf on $pf"
+			echo 0 > "$pf_sysfs/sriov_numvfs"
+			continue;
+		fi
+
+		if ! eeh_can_break $vf ; then
+			log "skipping "
+
+			echo 0 > "$pf_sysfs/sriov_numvfs"
+			continue;
+		fi
+
+		vfs="$((vfs + 1))"
+		echo $vf
+	done
+
+	test "$vfs" != 0
+	return $?
+}
+
+eeh_disable_vfs() {
+	pf_list="$(eeh_find_all_pfs)"
+	if [ -z "$pf_list" ] ; then
+		return 1;
+	fi
+
+	for dev in $pf_list ; do
+		echo 0 > "/sys/bus/pci/devices/$dev/sriov_numvfs"
+	done
+
+	return 0;
+}

tools/testing/selftests/powerpc/eeh/eeh-vf-aware.sh

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+. ./eeh-functions.sh
+
+eeh_test_prep # NB: may exit
+
+vf_list="$(eeh_enable_vfs)";
+if $? != 0 ; then
+	log "No usable VFs found. Skipping EEH unaware VF test"
+	exit $KSELFTESTS_SKIP;
+fi
+
+log "Enabled VFs: $vf_list"
+
+tested=0
+passed=0
+for vf in $vf_list ; do
+	log "Testing $vf"
+
+	if ! eeh_can_recover $vf ; then
+		log "Driver for $vf doesn't support error recovery, skipping"
+		continue;
+	fi
+
+	tested="$((tested + 1))"
+
+	log "Breaking $vf..."
+	if ! eeh_one_dev $vf ; then
+		log "$vf failed to recover"
+		continue;
+	fi
+
+	passed="$((passed + 1))"
+done
+
+eeh_disable_vfs
+
+if [ "$tested" == 0 ] ; then
+	echo "No VFs with EEH aware drivers found, skipping"
+	exit $KSELFTESTS_SKIP
+fi
+
+test "$failed" != 0
+exit $?;

tools/testing/selftests/powerpc/eeh/eeh-vf-unaware.sh

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+. ./eeh-functions.sh
+
+eeh_test_prep # NB: may exit
+
+vf_list="$(eeh_enable_vfs)";
+if $? != 0 ; then
+	log "No usable VFs found. Skipping EEH unaware VF test"
+	exit $KSELFTESTS_SKIP;
+fi
+
+log "Enabled VFs: $vf_list"
+
+failed=0
+for vf in $vf_list ; do
+	log "Testing $vf"
+
+	if eeh_can_recover $vf ; then
+		log "Driver for $vf supports error recovery. Unbinding..."
+		echo "$vf" > /sys/bus/pci/devices/$vf/driver/unbind
+	fi
+
+	log "Breaking $vf..."
+	if ! eeh_one_dev $vf ; then
+		log "$vf failed to recover"
+		failed="$((failed + 1))"
+	fi
+done
+
+eeh_disable_vfs
+
+test "$failed" != 0
+exit $?;