Merge branch 'mlxsw-miscellaneous-fixes'

Petr Machata says:

====================
mlxsw: Miscellaneous fixes

This patchset is a bric-a-brac of fixes for bugs impacting mlxsw.

- Patches #1 and #2 fix issues in ACL handling error paths.
- Patch #3 fixes stack corruption in ACL code that a recent FW update
  has uncovered.

- Patch #4 fixes an issue in handling of IPIP next hops.

- Patch #5 fixes a typo in a the qos_pfc selftest
- Patch #6 fixes the same selftest to work with 8-lane ports.
====================

Link: https://lore.kernel.org/r/cover.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c

@@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 			     unsigned long *p_index)
 {
 	unsigned int num_rows, entry_size;
+	unsigned long index;
 
 	/* We only allow allocations of entire rows */
 	if (num_erps % erp_core->num_erp_banks != 0)
@@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 	entry_size = erp_core->erpt_entries_size[region_type];
 	num_rows = num_erps / erp_core->num_erp_banks;
 
-	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
-	if (*p_index == 0)
+	index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (!index)
 		return -ENOBUFS;
-	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	*p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
 
 	return 0;
 }

drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c

@@ -681,13 +681,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
+	struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl);
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
-					region->id);
+	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 	kfree(region);
 }
 
@@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						  ACL_MAX_GROUP_SIZE);
+	tcam->max_group_size = min_t(unsigned int, tcam->max_group_size,
+				     MLXSW_REG_PAGT_ACL_MAX_NUM);
 
 	err = ops->init(mlxsw_sp, tcam->priv, tcam);
 	if (err)

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -11472,6 +11472,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_netevent_notifier;
 
+	mlxsw_sp->router->netdevice_nb.notifier_call =
+		mlxsw_sp_router_netdevice_event;
+	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					      &mlxsw_sp->router->netdevice_nb);
+	if (err)
+		goto err_register_netdev_notifier;
+
 	mlxsw_sp->router->nexthop_nb.notifier_call =
 		mlxsw_sp_nexthop_obj_event;
 	err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
@@ -11487,22 +11494,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_fib_notifier;
 
-	mlxsw_sp->router->netdevice_nb.notifier_call =
-		mlxsw_sp_router_netdevice_event;
-	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					      &mlxsw_sp->router->netdevice_nb);
-	if (err)
-		goto err_register_netdev_notifier;
-
 	return 0;
 
-err_register_netdev_notifier:
-	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),
-				&mlxsw_sp->router->fib_nb);
 err_register_fib_notifier:
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &mlxsw_sp->router->nexthop_nb);
 err_register_nexthop_notifier:
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
+err_register_netdev_notifier:
 	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
 err_register_netevent_notifier:
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
@@ -11550,11 +11550,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_router *router = mlxsw_sp->router;
 
-	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					  &router->netdevice_nb);
 	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb);
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &router->nexthop_nb);
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
 	unregister_netevent_notifier(&router->netevent_nb);
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
 	unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb);

tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh

@@ -40,7 +40,6 @@
 # |   + $swp1          $swp3 +                    + $swp4                     |
 # |   | iPOOL1        iPOOL0 |                    | iPOOL2                    |
 # |   | ePOOL4        ePOOL5 |                    | ePOOL4                    |
-# |   |                1Gbps |                    | 1Gbps                     |
 # |   |        PFC:enabled=1 |                    | PFC:enabled=1             |
 # | +-|----------------------|-+                +-|------------------------+  |
 # | | + $swp1.111  $swp3.111 + |                | + $swp4.111              |  |
@@ -120,6 +119,9 @@ h2_destroy()
 
 switch_create()
 {
+	local lanes_swp4
+	local pg1_size
+
 	# pools
 	# -----
 
@@ -229,7 +231,20 @@ switch_create()
 	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
+	pg1_size=$_100KB
+
+	setup_wait_dev_with_timeout $swp4
+
+	lanes_swp4=$(ethtool $swp4 | grep 'Lanes:')
+	lanes_swp4=${lanes_swp4#*"Lanes: "}
+
+	# 8-lane ports use two buffers among which the configured buffer
+	# is split, so double the size to get twice (20K + 80K).
+	if [[ $lanes_swp4 -eq 8 ]]; then
+		pg1_size=$((pg1_size * 2))
+	fi
+
+	dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size
 
 	# bridges
 	# -------

tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh

@@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
-	bloom_simple_test bloom_complex_test bloom_delta_test"
+	bloom_simple_test bloom_complex_test bloom_delta_test \
+	max_erp_entries_test max_group_size_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -983,6 +984,109 @@ bloom_delta_test()
 	log_test "bloom delta test ($tcflags)"
 }
 
+max_erp_entries_test()
+{
+	# The number of eRP entries is limited. Once the maximum number of eRPs
+	# has been reached, filters cannot be added. This test verifies that
+	# when this limit is reached, inserstion fails without crashing.
+
+	RET=0
+
+	local num_masks=32
+	local num_regions=15
+	local chain_failed
+	local mask_failed
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_regions; i++)); do
+		for ((j=$num_masks; j >= 0; j--)); do
+			tc filter add dev $h2 ingress chain $i protocol ip \
+				pref $i	handle $j flower $tcflags \
+				dst_ip 192.1.0.0/$j &> /dev/null
+			ret=$?
+
+			if [ $ret -ne 0 ]; then
+				chain_failed=$i
+				mask_failed=$j
+				break 2
+			fi
+		done
+	done
+
+	# We expect to exceed the maximum number of eRP entries, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of eRP entries"
+
+	for ((; i >= 1; i--)); do
+		for ((j=0; j <= $num_masks; j++)); do
+			tc filter del dev $h2 ingress chain $i protocol ip \
+				pref $i handle $j flower &> /dev/null
+		done
+	done
+
+	log_test "max eRP entries test ($tcflags). " \
+		"max chain $chain_failed, mask $mask_failed"
+}
+
+max_group_size_test()
+{
+	# The number of ACLs in an ACL group is limited. Once the maximum
+	# number of ACLs has been reached, filters cannot be added. This test
+	# verifies that when this limit is reached, insertion fails without
+	# crashing.
+
+	RET=0
+
+	local num_acls=32
+	local max_size
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_acls; i++)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter add dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter add dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+
+		ret=$?
+		[[ $ret -ne 0 ]] && max_size=$((i - 1)) && break
+	done
+
+	# We expect to exceed the maximum number of ACLs in a group, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of ACLs in a group"
+
+	for ((; i >= 1; i--)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter del dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter del dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+	done
+
+	log_test "max ACL group size test ($tcflags). max size $max_size"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}