Commit db82f709 authored by Oliver O'Halloran's avatar Oliver O'Halloran Committed by Michael Ellerman
Browse files

selftests/powerpc: Hoist helper code out of eeh-basic 



Hoist some of the useful test environment checking and prep code into
eeh-functions.sh so they can be reused in other tests.

Signed-off-by: default avatarOliver O'Halloran <oohall@gmail.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201103044503.917128-1-oohall@gmail.com
parent 718aae91

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

+3 −36
Original line number Diff line number Diff line 
#!/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

eeh_test_prep # NB: may exit



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.
@@ -30,34 +15,16 @@ 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"

	if ! eeh_can_break $dev ; then

		continue;

	fi



	# Skip VFs for now since we don't have a reliable way

	# to break them.

	# 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

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

100755 → 100644
+48 −0
Original line number Diff line number Diff line 
#!/bin/sh

# SPDX-License-Identifier: GPL-2.0-only



export KSELFTESTS_SKIP=4



pe_ok() {

	local dev="$1"

	local path="/sys/bus/pci/devices/$dev/eeh_pe_state"
@@ -39,6 +41,52 @@ eeh_supported() { 
	grep -q 'EEH Subsystem is enabled' /proc/powerpc/eeh

}



eeh_test_prep() {

	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



	# 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

}



eeh_can_break() {

	# skip bridges since we can't recover them (yet...)

	if [ -e "/sys/bus/pci/devices/$dev/pci_bus" ] ; then

		echo "$dev, Skipped: bridge"

		return 1;

	fi



	# The ahci driver doesn't support error recovery. If the ahci device

	# happens to be hosting the root filesystem, and then we go and break

	# it the system will generally go down. We should probably fix that

	# at some point

	if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then

		echo "$dev, Skipped: ahci doesn't support recovery"

		return 1;

	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"

		return 1;

	fi



	return 0

}



eeh_one_dev() {

	local dev="$1"