Merge branch 'nexthop-add-support-for-nexthop-objects-offload'

Ido Schimmel says:

====================
nexthop: Add support for nexthop objects offload

This patch set adds support for nexthop objects offload with a dummy
implementation over netdevsim. mlxsw support will be added later.

The general idea is very similar to route offload in that notifications
are sent whenever nexthop objects are changed. A listener can veto the
change and the error will be communicated to user space with extack.

To keep listeners as simple as possible, they not only receive
notifications for the nexthop object that is changed, but also for all
the other objects affected by this change. For example, when a single
nexthop is replaced, a replace notification is sent for the single
nexthop, but also for all the nexthop groups this nexthop is member in.
This relieves listeners from the need to track such dependencies.

To simplify things further for listeners, the notification info does not
contain the raw nexthop data structures (e.g., 'struct nexthop'), but
less complex data structures into which the raw data structures are
parsed into.

Tested with a new selftest over netdevsim and with fib_nexthops.sh:

Tests passed: 164
Tests failed:   0

Patch set overview:

Patches #1-#4 introduce the aforementioned data structures and convert
existing listeners (i.e., the VXLAN driver) to use them.

Patches #5-#6 add a new RTNH_F_TRAP flag and the ability to set it and
RTNH_F_OFFLOAD on nexthops. This flag is used by netdevsim for testing
purposes and will also be used by mlxsw. These flags are consistent with
the existing RTM_F_OFFLOAD and RTM_F_TRAP flags.

Patches #7-#14 gradually add the new nexthop notifications.

Patches #15-#18 add a dummy implementation for nexthop offload over
netdevsim and a selftest to exercise both good and bad flows.

Changes since RFC [1]:

Patch #1: s/is_encap/has_encap/
Patch #3: Add a blank line in __nh_notifier_single_info_init()
Patch #5: Reword commit message
Patch #6: s/nexthop_hw_flags_set/nexthop_set_hw_flags/
Patch #7: Reword commit message
Patch #11: Allocate extack on the stack

Follow-up patch sets:

selftests: forwarding: Add nexthop objects tests
mlxsw: Preparations for nexthop objects support - part 1/2
mlxsw: Preparations for nexthop objects support - part 2/2
mlxsw: Add support for nexthop objects
mlxsw: Add support for blackhole nexthops
mlxsw: Update adjacency index more efficiently

[1] https://lore.kernel.org/netdev/20200908091037.2709823-1-idosch@idosch.org/
====================

Link: https://lore.kernel.org/r/20201104133040.1125369-1-idosch@idosch.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 436 insertions, 0 deletions

diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
new file mode 100755
index 000000000000..be0c1b5ee6b8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
@@ -0,0 +1,436 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the nexthop offload API. It makes use of netdevsim
+# which registers a listener to the nexthop notification chain.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	nexthop_single_add_test
+	nexthop_single_add_err_test
+	nexthop_group_add_test
+	nexthop_group_add_err_test
+	nexthop_group_replace_test
+	nexthop_group_replace_err_test
+	nexthop_single_replace_test
+	nexthop_single_replace_err_test
+	nexthop_single_in_group_replace_test
+	nexthop_single_in_group_replace_err_test
+	nexthop_single_in_group_delete_test
+	nexthop_single_in_group_delete_err_test
+	nexthop_replay_test
+	nexthop_replay_err_test
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+nexthop_check()
+{
+	local nharg="$1"; shift
+	local expected="$1"; shift
+
+	out=$($IP nexthop show ${nharg} | sed -e 's/ *$//')
+	if [[ "$out" != "$expected" ]]; then
+		return 1
+	fi
+
+	return 0
+}
+
+nexthop_resource_check()
+{
+	local expected_occ=$1; shift
+
+	occ=$($DEVLINK -jp resource show $DEVLINK_DEV \
+		| jq '.[][][] | select(.name=="nexthops") | .["occ"]')
+
+	if [ $expected_occ -ne $occ ]; then
+		return 1
+	fi
+
+	return 0
+}
+
+nexthop_resource_set()
+{
+	local size=$1; shift
+
+	$DEVLINK resource set $DEVLINK_DEV path nexthops size $size
+	$DEVLINK dev reload $DEVLINK_DEV
+}
+
+nexthop_single_add_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry"
+
+	nexthop_resource_check 1
+	check_err $? "Wrong nexthop occupancy"
+
+	$IP nexthop del id 1
+	nexthop_resource_check 0
+	check_err $? "Wrong nexthop occupancy after delete"
+
+	log_test "Single nexthop add and delete"
+}
+
+nexthop_single_add_err_test()
+{
+	RET=0
+
+	nexthop_resource_set 1
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1 &> /dev/null
+	check_fail $? "Nexthop addition succeeded when should fail"
+
+	nexthop_resource_check 1
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop add failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_group_add_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	$IP nexthop add id 10 group 1/2
+	nexthop_check "id 10" "id 10 group 1/2 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_resource_check 4
+	check_err $? "Wrong nexthop occupancy"
+
+	$IP nexthop del id 10
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy after delete"
+
+	$IP nexthop add id 10 group 1,20/2,39
+	nexthop_check "id 10" "id 10 group 1,20/2,39 trap"
+	check_err $? "Unexpected weighted nexthop group entry"
+
+	nexthop_resource_check 61
+	check_err $? "Wrong weighted nexthop occupancy"
+
+	$IP nexthop del id 10
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy after delete"
+
+	log_test "Nexthop group add and delete"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_group_add_err_test()
+{
+	RET=0
+
+	nexthop_resource_set 2
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	$IP nexthop add id 10 group 1/2 &> /dev/null
+	check_fail $? "Nexthop group addition succeeded when should fail"
+
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Nexthop group add failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_group_replace_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$IP nexthop replace id 10 group 1/2/3
+	nexthop_check "id 10" "id 10 group 1/2/3 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_resource_check 6
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Nexthop group replace"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_group_replace_err_test()
+{
+	RET=0
+
+	nexthop_resource_set 5
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$IP nexthop replace id 10 group 1/2/3 &> /dev/null
+	check_fail $? "Nexthop group replacement succeeded when should fail"
+
+	nexthop_check "id 10" "id 10 group 1/2 trap"
+	check_err $? "Unexpected nexthop group entry after failure"
+
+	nexthop_resource_check 5
+	check_err $? "Wrong nexthop occupancy after failure"
+
+	log_test "Nexthop group replace failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_single_replace_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+	$IP nexthop replace id 1 via 192.0.2.3 dev dummy1
+	nexthop_check "id 1" "id 1 via 192.0.2.3 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry"
+
+	nexthop_resource_check 1
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop replace"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_single_replace_err_test()
+{
+	RET=0
+
+	# This is supposed to cause the replace to fail because the new nexthop
+	# is programmed before deleting the replaced one.
+	nexthop_resource_set 1
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+	$IP nexthop replace id 1 via 192.0.2.3 dev dummy1 &> /dev/null
+	check_fail $? "Nexthop replace succeeded when should fail"
+
+	nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry after failure"
+
+	nexthop_resource_check 1
+	check_err $? "Wrong nexthop occupancy after failure"
+
+	log_test "Single nexthop replace failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_replace_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$IP nexthop replace id 1 via 192.0.2.4 dev dummy1
+	check_err $? "Failed to replace nexthop when should not"
+
+	nexthop_check "id 10" "id 10 group 1/2 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_resource_check 4
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop replace while in group"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_replace_err_test()
+{
+	RET=0
+
+	nexthop_resource_set 5
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$IP nexthop replace id 1 via 192.0.2.4 dev dummy1 &> /dev/null
+	check_fail $? "Nexthop replacement succeeded when should fail"
+
+	nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry after failure"
+
+	nexthop_check "id 10" "id 10 group 1/2 trap"
+	check_err $? "Unexpected nexthop group entry after failure"
+
+	nexthop_resource_check 4
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop replace while in group failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_delete_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$IP nexthop del id 1
+	nexthop_check "id 10" "id 10 group 2 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop delete while in group"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_delete_err_test()
+{
+	RET=0
+
+	# First, nexthop 1 will be deleted, which will reduce the occupancy to
+	# 5. Afterwards, a replace notification will be sent for nexthop group
+	# 10 with only two nexthops. Since the new group is allocated before
+	# the old is deleted, the replacement will fail as it will result in an
+	# occupancy of 7.
+	nexthop_resource_set 6
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2/3
+
+	$IP nexthop del id 1
+
+	nexthop_resource_check 5
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop delete while in group failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
+nexthop_replay_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	$DEVLINK dev reload $DEVLINK_DEV
+	check_err $? "Failed to reload when should not"
+
+	nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry after reload"
+
+	nexthop_check "id 2" "id 2 via 192.0.2.3 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry after reload"
+
+	nexthop_check "id 10" "id 10 group 1/2 trap"
+	check_err $? "Unexpected nexthop group entry after reload"
+
+	nexthop_resource_check 4
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Nexthop replay"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_replay_err_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2
+
+	# Reduce size of nexthop resource so that reload will fail.
+	$DEVLINK resource set $DEVLINK_DEV path nexthops size 3
+	$DEVLINK dev reload $DEVLINK_DEV &> /dev/null
+	check_fail $? "Reload succeeded when should fail"
+
+	$DEVLINK resource set $DEVLINK_DEV path nexthops size 9999
+	$DEVLINK dev reload $DEVLINK_DEV
+	check_err $? "Failed to reload when should not"
+
+	log_test "Nexthop replay failure"
+
+	$IP nexthop flush &> /dev/null
+}
+
+setup_prepare()
+{
+	local netdev
+
+	modprobe netdevsim &> /dev/null
+
+	echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+	while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+	set -e
+
+	ip netns add testns1
+	devlink dev reload $DEVLINK_DEV netns testns1
+
+	IP="ip -netns testns1"
+	DEVLINK="devlink -N testns1"
+
+	$IP link add name dummy1 up type dummy
+	$IP address add 192.0.2.1/24 dev dummy1
+
+	set +e
+}
+
+cleanup()
+{
+	pre_cleanup
+	ip netns del testns1
+	echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+	modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS