- 05 1月, 2022 6 次提交
-
-
由 Vladimir Oltean 提交于
dst->ports is accessed most notably by dsa_master_find_slave(), which is invoked in the RX path. dst->lags is accessed by dsa_lag_dev(), which is invoked in the RX path of tag_dsa.c. dst->tag_ops, dst->default_proto and dst->pd don't need to be in the first cache line, so they are moved out by this change. Before: pahole -C dsa_switch_tree net/dsa/slave.o struct dsa_switch_tree { struct list_head list; /* 0 16 */ struct raw_notifier_head nh; /* 16 8 */ unsigned int index; /* 24 4 */ struct kref refcount; /* 28 4 */ bool setup; /* 32 1 */ /* XXX 7 bytes hole, try to pack */ const struct dsa_device_ops * tag_ops; /* 40 8 */ enum dsa_tag_protocol default_proto; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_platform_data * pd; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct list_head ports; /* 64 16 */ struct list_head rtable; /* 80 16 */ struct net_device * * lags; /* 96 8 */ unsigned int lags_len; /* 104 4 */ unsigned int last_switch; /* 108 4 */ /* size: 112, cachelines: 2, members: 13 */ /* sum members: 101, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ }; After: pahole -C dsa_switch_tree net/dsa/slave.o struct dsa_switch_tree { struct list_head list; /* 0 16 */ struct list_head ports; /* 16 16 */ struct raw_notifier_head nh; /* 32 8 */ unsigned int index; /* 40 4 */ struct kref refcount; /* 44 4 */ struct net_device * * lags; /* 48 8 */ bool setup; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ const struct dsa_device_ops * tag_ops; /* 64 8 */ enum dsa_tag_protocol default_proto; /* 72 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_platform_data * pd; /* 80 8 */ struct list_head rtable; /* 88 16 */ unsigned int lags_len; /* 104 4 */ unsigned int last_switch; /* 108 4 */ /* size: 112, cachelines: 2, members: 13 */ /* sum members: 101, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
Currently, num_ports is declared as size_t, which is defined as __kernel_ulong_t, therefore it occupies 8 bytes of memory. Even switches with port numbers in the range of tens are exotic, so there is no need for this amount of storage. Additionally, because the max_num_bridges member right above it is also 4 bytes, it means the compiler needs to add padding between the last 2 fields. By reducing the size, we don't need that padding and can reduce the struct size. Before: pahole -C dsa_switch net/dsa/slave.o struct dsa_switch { struct device * dev; /* 0 8 */ struct dsa_switch_tree * dst; /* 8 8 */ unsigned int index; /* 16 4 */ u32 setup:1; /* 20: 0 4 */ u32 vlan_filtering_is_global:1; /* 20: 1 4 */ u32 needs_standalone_vlan_filtering:1; /* 20: 2 4 */ u32 configure_vlan_while_not_filtering:1; /* 20: 3 4 */ u32 untag_bridge_pvid:1; /* 20: 4 4 */ u32 assisted_learning_on_cpu_port:1; /* 20: 5 4 */ u32 vlan_filtering:1; /* 20: 6 4 */ u32 pcs_poll:1; /* 20: 7 4 */ u32 mtu_enforcement_ingress:1; /* 20: 8 4 */ /* XXX 23 bits hole, try to pack */ struct notifier_block nb; /* 24 24 */ /* XXX last struct has 4 bytes of padding */ void * priv; /* 48 8 */ void * tagger_data; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_chip_data * cd; /* 64 8 */ const struct dsa_switch_ops * ops; /* 72 8 */ u32 phys_mii_mask; /* 80 4 */ /* XXX 4 bytes hole, try to pack */ struct mii_bus * slave_mii_bus; /* 88 8 */ unsigned int ageing_time_min; /* 96 4 */ unsigned int ageing_time_max; /* 100 4 */ struct dsa_8021q_context * tag_8021q_ctx; /* 104 8 */ struct devlink * devlink; /* 112 8 */ unsigned int num_tx_queues; /* 120 4 */ unsigned int num_lag_ids; /* 124 4 */ /* --- cacheline 2 boundary (128 bytes) --- */ unsigned int max_num_bridges; /* 128 4 */ /* XXX 4 bytes hole, try to pack */ size_t num_ports; /* 136 8 */ /* size: 144, cachelines: 3, members: 27 */ /* sum members: 132, holes: 2, sum holes: 8 */ /* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 23 bits */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 16 bytes */ }; After: pahole -C dsa_switch net/dsa/slave.o struct dsa_switch { struct device * dev; /* 0 8 */ struct dsa_switch_tree * dst; /* 8 8 */ unsigned int index; /* 16 4 */ u32 setup:1; /* 20: 0 4 */ u32 vlan_filtering_is_global:1; /* 20: 1 4 */ u32 needs_standalone_vlan_filtering:1; /* 20: 2 4 */ u32 configure_vlan_while_not_filtering:1; /* 20: 3 4 */ u32 untag_bridge_pvid:1; /* 20: 4 4 */ u32 assisted_learning_on_cpu_port:1; /* 20: 5 4 */ u32 vlan_filtering:1; /* 20: 6 4 */ u32 pcs_poll:1; /* 20: 7 4 */ u32 mtu_enforcement_ingress:1; /* 20: 8 4 */ /* XXX 23 bits hole, try to pack */ struct notifier_block nb; /* 24 24 */ /* XXX last struct has 4 bytes of padding */ void * priv; /* 48 8 */ void * tagger_data; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_chip_data * cd; /* 64 8 */ const struct dsa_switch_ops * ops; /* 72 8 */ u32 phys_mii_mask; /* 80 4 */ /* XXX 4 bytes hole, try to pack */ struct mii_bus * slave_mii_bus; /* 88 8 */ unsigned int ageing_time_min; /* 96 4 */ unsigned int ageing_time_max; /* 100 4 */ struct dsa_8021q_context * tag_8021q_ctx; /* 104 8 */ struct devlink * devlink; /* 112 8 */ unsigned int num_tx_queues; /* 120 4 */ unsigned int num_lag_ids; /* 124 4 */ /* --- cacheline 2 boundary (128 bytes) --- */ unsigned int max_num_bridges; /* 128 4 */ unsigned int num_ports; /* 132 4 */ /* size: 136, cachelines: 3, members: 27 */ /* sum members: 128, holes: 1, sum holes: 4 */ /* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 23 bits */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 8 bytes */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
struct dsa_switch has 9 boolean properties, many of which are in fact set by drivers for custom behavior (vlan_filtering_is_global, needs_standalone_vlan_filtering, etc etc). The binary layout of the structure could be improved. For example, the "bool setup" at the beginning introduces a gratuitous 7 byte hole in the first cache line. The change merges all boolean properties into bitfields of an u32, and places that u32 in the first cache line of the structure, since many bools are accessed from the data path (untag_bridge_pvid, vlan_filtering, vlan_filtering_is_global). We place this u32 after the existing ds->index, which is also 4 bytes in size. As a positive side effect, ds->tagger_data now fits into the first cache line too, because 4 bytes are saved. Before: pahole -C dsa_switch net/dsa/slave.o struct dsa_switch { bool setup; /* 0 1 */ /* XXX 7 bytes hole, try to pack */ struct device * dev; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ unsigned int index; /* 24 4 */ /* XXX 4 bytes hole, try to pack */ struct notifier_block nb; /* 32 24 */ /* XXX last struct has 4 bytes of padding */ void * priv; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ void * tagger_data; /* 64 8 */ struct dsa_chip_data * cd; /* 72 8 */ const struct dsa_switch_ops * ops; /* 80 8 */ u32 phys_mii_mask; /* 88 4 */ /* XXX 4 bytes hole, try to pack */ struct mii_bus * slave_mii_bus; /* 96 8 */ unsigned int ageing_time_min; /* 104 4 */ unsigned int ageing_time_max; /* 108 4 */ struct dsa_8021q_context * tag_8021q_ctx; /* 112 8 */ struct devlink * devlink; /* 120 8 */ /* --- cacheline 2 boundary (128 bytes) --- */ unsigned int num_tx_queues; /* 128 4 */ bool vlan_filtering_is_global; /* 132 1 */ bool needs_standalone_vlan_filtering; /* 133 1 */ bool configure_vlan_while_not_filtering; /* 134 1 */ bool untag_bridge_pvid; /* 135 1 */ bool assisted_learning_on_cpu_port; /* 136 1 */ bool vlan_filtering; /* 137 1 */ bool pcs_poll; /* 138 1 */ bool mtu_enforcement_ingress; /* 139 1 */ unsigned int num_lag_ids; /* 140 4 */ unsigned int max_num_bridges; /* 144 4 */ /* XXX 4 bytes hole, try to pack */ size_t num_ports; /* 152 8 */ /* size: 160, cachelines: 3, members: 27 */ /* sum members: 141, holes: 4, sum holes: 19 */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 32 bytes */ }; After: pahole -C dsa_switch net/dsa/slave.o struct dsa_switch { struct device * dev; /* 0 8 */ struct dsa_switch_tree * dst; /* 8 8 */ unsigned int index; /* 16 4 */ u32 setup:1; /* 20: 0 4 */ u32 vlan_filtering_is_global:1; /* 20: 1 4 */ u32 needs_standalone_vlan_filtering:1; /* 20: 2 4 */ u32 configure_vlan_while_not_filtering:1; /* 20: 3 4 */ u32 untag_bridge_pvid:1; /* 20: 4 4 */ u32 assisted_learning_on_cpu_port:1; /* 20: 5 4 */ u32 vlan_filtering:1; /* 20: 6 4 */ u32 pcs_poll:1; /* 20: 7 4 */ u32 mtu_enforcement_ingress:1; /* 20: 8 4 */ /* XXX 23 bits hole, try to pack */ struct notifier_block nb; /* 24 24 */ /* XXX last struct has 4 bytes of padding */ void * priv; /* 48 8 */ void * tagger_data; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_chip_data * cd; /* 64 8 */ const struct dsa_switch_ops * ops; /* 72 8 */ u32 phys_mii_mask; /* 80 4 */ /* XXX 4 bytes hole, try to pack */ struct mii_bus * slave_mii_bus; /* 88 8 */ unsigned int ageing_time_min; /* 96 4 */ unsigned int ageing_time_max; /* 100 4 */ struct dsa_8021q_context * tag_8021q_ctx; /* 104 8 */ struct devlink * devlink; /* 112 8 */ unsigned int num_tx_queues; /* 120 4 */ unsigned int num_lag_ids; /* 124 4 */ /* --- cacheline 2 boundary (128 bytes) --- */ unsigned int max_num_bridges; /* 128 4 */ /* XXX 4 bytes hole, try to pack */ size_t num_ports; /* 136 8 */ /* size: 144, cachelines: 3, members: 27 */ /* sum members: 132, holes: 2, sum holes: 8 */ /* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 23 bits */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 16 bytes */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
Both dsa_port :: type and dsa_port :: index introduce a 4 octet hole after them, so we can group them together and the holes would be eliminated, turning 16 octets of storage into just 8. This makes the cpu_dp pointer fit in the first cache line, which is good, because dsa_slave_to_master(), called by dsa_enqueue_skb(), uses it. Before: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_switch * ds; /* 40 8 */ unsigned int index; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ const char * name; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_port * cpu_dp; /* 64 8 */ u8 mac[6]; /* 72 6 */ u8 stp_state; /* 78 1 */ u8 vlan_filtering:1; /* 79: 0 1 */ u8 learning:1; /* 79: 1 1 */ u8 lag_tx_enabled:1; /* 79: 2 1 */ u8 devlink_port_setup:1; /* 79: 3 1 */ u8 setup:1; /* 79: 4 1 */ /* XXX 3 bits hole, try to pack */ struct device_node * dn; /* 80 8 */ unsigned int ageing_time; /* 88 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_bridge * bridge; /* 96 8 */ struct devlink_port devlink_port; /* 104 288 */ /* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */ struct phylink * pl; /* 392 8 */ struct phylink_config pl_config; /* 400 40 */ struct net_device * lag_dev; /* 440 8 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct net_device * hsr_dev; /* 448 8 */ struct list_head list; /* 456 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 472 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 480 8 */ struct mutex addr_lists_lock; /* 488 32 */ /* --- cacheline 8 boundary (512 bytes) was 8 bytes ago --- */ struct list_head fdbs; /* 520 16 */ struct list_head mdbs; /* 536 16 */ /* size: 552, cachelines: 9, members: 30 */ /* sum members: 539, holes: 3, sum holes: 12 */ /* sum bitfield members: 5 bits, bit holes: 1, sum bit holes: 3 bits */ /* last cacheline: 40 bytes */ }; After: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ struct dsa_switch * ds; /* 32 8 */ unsigned int index; /* 40 4 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 44 4 */ const char * name; /* 48 8 */ struct dsa_port * cpu_dp; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u8 mac[6]; /* 64 6 */ u8 stp_state; /* 70 1 */ u8 vlan_filtering:1; /* 71: 0 1 */ u8 learning:1; /* 71: 1 1 */ u8 lag_tx_enabled:1; /* 71: 2 1 */ u8 devlink_port_setup:1; /* 71: 3 1 */ u8 setup:1; /* 71: 4 1 */ /* XXX 3 bits hole, try to pack */ struct device_node * dn; /* 72 8 */ unsigned int ageing_time; /* 80 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_bridge * bridge; /* 88 8 */ struct devlink_port devlink_port; /* 96 288 */ /* --- cacheline 6 boundary (384 bytes) --- */ struct phylink * pl; /* 384 8 */ struct phylink_config pl_config; /* 392 40 */ struct net_device * lag_dev; /* 432 8 */ struct net_device * hsr_dev; /* 440 8 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct list_head list; /* 448 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 464 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 472 8 */ struct mutex addr_lists_lock; /* 480 32 */ /* --- cacheline 8 boundary (512 bytes) --- */ struct list_head fdbs; /* 512 16 */ struct list_head mdbs; /* 528 16 */ /* size: 544, cachelines: 9, members: 30 */ /* sum members: 539, holes: 1, sum holes: 4 */ /* sum bitfield members: 5 bits, bit holes: 1, sum bit holes: 3 bits */ /* last cacheline: 32 bytes */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
struct dsa_port has 5 bool members which create quite a number of 7 byte holes in the structure layout. By merging them all into bitfields of an u8, and placing that u8 in the 1-byte hole after dp->mac and dp->stp_state, we can reduce the structure size from 576 bytes to 552 bytes on arm64. Before: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_switch * ds; /* 40 8 */ unsigned int index; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ const char * name; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_port * cpu_dp; /* 64 8 */ u8 mac[6]; /* 72 6 */ u8 stp_state; /* 78 1 */ /* XXX 1 byte hole, try to pack */ struct device_node * dn; /* 80 8 */ unsigned int ageing_time; /* 88 4 */ bool vlan_filtering; /* 92 1 */ bool learning; /* 93 1 */ /* XXX 2 bytes hole, try to pack */ struct dsa_bridge * bridge; /* 96 8 */ struct devlink_port devlink_port; /* 104 288 */ /* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */ bool devlink_port_setup; /* 392 1 */ /* XXX 7 bytes hole, try to pack */ struct phylink * pl; /* 400 8 */ struct phylink_config pl_config; /* 408 40 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct net_device * lag_dev; /* 448 8 */ bool lag_tx_enabled; /* 456 1 */ /* XXX 7 bytes hole, try to pack */ struct net_device * hsr_dev; /* 464 8 */ struct list_head list; /* 472 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 488 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 496 8 */ struct mutex addr_lists_lock; /* 504 32 */ /* --- cacheline 8 boundary (512 bytes) was 24 bytes ago --- */ struct list_head fdbs; /* 536 16 */ struct list_head mdbs; /* 552 16 */ bool setup; /* 568 1 */ /* size: 576, cachelines: 9, members: 30 */ /* sum members: 544, holes: 6, sum holes: 25 */ /* padding: 7 */ }; After: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_switch * ds; /* 40 8 */ unsigned int index; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ const char * name; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_port * cpu_dp; /* 64 8 */ u8 mac[6]; /* 72 6 */ u8 stp_state; /* 78 1 */ u8 vlan_filtering:1; /* 79: 0 1 */ u8 learning:1; /* 79: 1 1 */ u8 lag_tx_enabled:1; /* 79: 2 1 */ u8 devlink_port_setup:1; /* 79: 3 1 */ u8 setup:1; /* 79: 4 1 */ /* XXX 3 bits hole, try to pack */ struct device_node * dn; /* 80 8 */ unsigned int ageing_time; /* 88 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_bridge * bridge; /* 96 8 */ struct devlink_port devlink_port; /* 104 288 */ /* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */ struct phylink * pl; /* 392 8 */ struct phylink_config pl_config; /* 400 40 */ struct net_device * lag_dev; /* 440 8 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct net_device * hsr_dev; /* 448 8 */ struct list_head list; /* 456 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 472 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 480 8 */ struct mutex addr_lists_lock; /* 488 32 */ /* --- cacheline 8 boundary (512 bytes) was 8 bytes ago --- */ struct list_head fdbs; /* 520 16 */ struct list_head mdbs; /* 536 16 */ /* size: 552, cachelines: 9, members: 30 */ /* sum members: 539, holes: 3, sum holes: 12 */ /* sum bitfield members: 5 bits, bit holes: 1, sum bit holes: 3 bits */ /* last cacheline: 40 bytes */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
The MAC address of a port is 6 octets in size, and this creates a 2 octet hole after it. There are some other u8 members of struct dsa_port that we can put in that hole. One such member is the stp_state. Before: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_switch * ds; /* 40 8 */ unsigned int index; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ const char * name; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_port * cpu_dp; /* 64 8 */ u8 mac[6]; /* 72 6 */ /* XXX 2 bytes hole, try to pack */ struct device_node * dn; /* 80 8 */ unsigned int ageing_time; /* 88 4 */ bool vlan_filtering; /* 92 1 */ bool learning; /* 93 1 */ u8 stp_state; /* 94 1 */ /* XXX 1 byte hole, try to pack */ struct dsa_bridge * bridge; /* 96 8 */ struct devlink_port devlink_port; /* 104 288 */ /* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */ bool devlink_port_setup; /* 392 1 */ /* XXX 7 bytes hole, try to pack */ struct phylink * pl; /* 400 8 */ struct phylink_config pl_config; /* 408 40 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct net_device * lag_dev; /* 448 8 */ bool lag_tx_enabled; /* 456 1 */ /* XXX 7 bytes hole, try to pack */ struct net_device * hsr_dev; /* 464 8 */ struct list_head list; /* 472 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 488 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 496 8 */ struct mutex addr_lists_lock; /* 504 32 */ /* --- cacheline 8 boundary (512 bytes) was 24 bytes ago --- */ struct list_head fdbs; /* 536 16 */ struct list_head mdbs; /* 552 16 */ bool setup; /* 568 1 */ /* size: 576, cachelines: 9, members: 30 */ /* sum members: 544, holes: 6, sum holes: 25 */ /* padding: 7 */ }; After: pahole -C dsa_port net/dsa/slave.o struct dsa_port { union { struct net_device * master; /* 0 8 */ struct net_device * slave; /* 0 8 */ }; /* 0 8 */ const struct dsa_device_ops * tag_ops; /* 8 8 */ struct dsa_switch_tree * dst; /* 16 8 */ struct sk_buff * (*rcv)(struct sk_buff *, struct net_device *); /* 24 8 */ enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU = 1, DSA_PORT_TYPE_DSA = 2, DSA_PORT_TYPE_USER = 3, } type; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct dsa_switch * ds; /* 40 8 */ unsigned int index; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ const char * name; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct dsa_port * cpu_dp; /* 64 8 */ u8 mac[6]; /* 72 6 */ u8 stp_state; /* 78 1 */ /* XXX 1 byte hole, try to pack */ struct device_node * dn; /* 80 8 */ unsigned int ageing_time; /* 88 4 */ bool vlan_filtering; /* 92 1 */ bool learning; /* 93 1 */ /* XXX 2 bytes hole, try to pack */ struct dsa_bridge * bridge; /* 96 8 */ struct devlink_port devlink_port; /* 104 288 */ /* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */ bool devlink_port_setup; /* 392 1 */ /* XXX 7 bytes hole, try to pack */ struct phylink * pl; /* 400 8 */ struct phylink_config pl_config; /* 408 40 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct net_device * lag_dev; /* 448 8 */ bool lag_tx_enabled; /* 456 1 */ /* XXX 7 bytes hole, try to pack */ struct net_device * hsr_dev; /* 464 8 */ struct list_head list; /* 472 16 */ const struct ethtool_ops * orig_ethtool_ops; /* 488 8 */ const struct dsa_netdevice_ops * netdev_ops; /* 496 8 */ struct mutex addr_lists_lock; /* 504 32 */ /* --- cacheline 8 boundary (512 bytes) was 24 bytes ago --- */ struct list_head fdbs; /* 536 16 */ struct list_head mdbs; /* 552 16 */ bool setup; /* 568 1 */ /* size: 576, cachelines: 9, members: 30 */ /* sum members: 544, holes: 6, sum holes: 25 */ /* padding: 7 */ }; Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 14 12月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
On the NXP Bluebox 3 board which uses a multi-switch setup with sja1105, the mechanism through which the tagger connects to the switch tree is broken, due to improper DSA code design. At the time when tag_ops->connect() is called in dsa_port_parse_cpu(), DSA hasn't finished "touching" all the ports, so it doesn't know how large the tree is and how many ports it has. It has just seen the first CPU port by this time. As a result, this function will call the tagger's ->connect method too early, and the tagger will connect only to the first switch from the tree. This could be perhaps addressed a bit more simply by just moving the tag_ops->connect(dst) call a bit later (for example in dsa_tree_setup), but there is already a design inconsistency at present: on the switch side, the notification is on a per-switch basis, but on the tagger side, it is on a per-tree basis. Furthermore, the persistent storage itself is per switch (ds->tagger_data). And the tagger connect and disconnect procedures (at least the ones that exist currently) could see a fair bit of simplification if they didn't have to iterate through the switches of a tree. To fix the issue, this change transforms tag_ops->connect(dst) into tag_ops->connect(ds) and moves it somewhere where we already iterate over all switches of a tree. That is in dsa_switch_setup_tag_protocol(), which is a good placement because we already have there the connection call to the switch side of things. As for the dsa_tree_bind_tag_proto() method (called from the code path that changes the tag protocol), things are a bit more complicated because we receive the tree as argument, yet when we unwind on errors, it would be nice to not call tag_ops->disconnect(ds) where we didn't previously call tag_ops->connect(ds). We didn't have this problem before because the tag_ops connection operations passed the entire dst before, and this is more fine grained now. To solve the error rewind case using the new API, we have to create yet one more cross-chip notifier for disconnection, and stay connected with the old tag protocol to all the switches in the tree until we've succeeded to connect with the new one as well. So if something fails half way, the whole tree is still connected to the old tagger. But there may still be leaks if the tagger fails to connect to the 2nd out of 3 switches in a tree: somebody needs to tell the tagger to disconnect from the first switch. Nothing comes for free, and this was previously handled privately by the tagging protocol driver before, but now we need to emit a disconnect cross-chip notifier for that, because DSA has to take care of the unwind path. We assume that the tagging protocol has connected to a switch if it has set ds->tagger_data to something, otherwise we avoid calling its disconnection method in the error rewind path. The rest of the changes are in the tagging protocol drivers, and have to do with the replacement of dst with ds. The iteration is removed and the error unwind path is simplified, as mentioned above. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 12 12月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
All current in-tree uses of dp->priv have been replaced with ds->tagger_data, which provides for a safer API especially when the connection isn't the regular 1:1 link between one switch driver and one tagging protocol driver, but could be either one switch to many taggers, or many switches to one tagger. Therefore, we can remove this unused pointer. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Vladimir Oltean 提交于
Ansuel is working on register access over Ethernet for the qca8k switch family. This requires the qca8k tagging protocol driver to receive frames which aren't intended for the network stack, but instead for the qca8k switch driver itself. The dp->priv is currently the prevailing method for passing data back and forth between the tagging protocol driver and the switch driver. However, this method is riddled with caveats. The DSA design allows in principle for any switch driver to return any protocol it desires in ->get_tag_protocol(). The dsa_loop driver can be modified to do just that. But in the current design, the memory behind dp->priv has to be allocated by the switch driver, so if the tagging protocol is paired to an unexpected switch driver, we may end up in NULL pointer dereferences inside the kernel, or worse (a switch driver may allocate dp->priv according to the expectations of a different tagger). The latter possibility is even more plausible considering that DSA switches can dynamically change tagging protocols in certain cases (dsa <-> edsa, ocelot <-> ocelot-8021q), and the current design lends itself to mistakes that are all too easy to make. This patch proposes that the tagging protocol driver should manage its own memory, instead of relying on the switch driver to do so. After analyzing the different in-tree needs, it can be observed that the required tagger storage is per switch, therefore a ds->tagger_data pointer is introduced. In principle, per-port storage could also be introduced, although there is no need for it at the moment. Future changes will replace the current usage of dp->priv with ds->tagger_data. We define a "binding" event between the DSA switch tree and the tagging protocol. During this binding event, the tagging protocol's ->connect() method is called first, and this may allocate some memory for each switch of the tree. Then a cross-chip notifier is emitted for the switches within that tree, and they are given the opportunity to fix up the tagger's memory (for example, they might set up some function pointers that represent virtual methods for consuming packets). Because the memory is owned by the tagger, there exists a ->disconnect() method for the tagger (which is the place to free the resources), but there doesn't exist a ->disconnect() method for the switch driver. This is part of the design. The switch driver should make minimal use of the public part of the tagger data, and only after type-checking it using the supplied "proto" argument. In the code there are in fact two binding events, one is the initial event in dsa_switch_setup_tag_protocol(). At this stage, the cross chip notifier chains aren't initialized, so we call each switch's connect() method by hand. Then there is dsa_tree_bind_tag_proto() during dsa_tree_change_tag_proto(), and here we have an old protocol and a new one. We first connect to the new one before disconnecting from the old one, to simplify error handling a bit and to ensure we remain in a valid state at all times. Co-developed-by: NAnsuel Smith <ansuelsmth@gmail.com> Signed-off-by: NAnsuel Smith <ansuelsmth@gmail.com> Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 09 12月, 2021 7 次提交
-
-
由 Vladimir Oltean 提交于
We don't really need new switch API for these, and with new switches which intend to add support for this feature, it will become cumbersome to maintain. The change consists in restructuring the two drivers that implement this offload (sja1105 and mv88e6xxx) such that the offload is enabled and disabled from the ->port_bridge_{join,leave} methods instead of the old ->port_bridge_tx_fwd_{,un}offload. The only non-trivial change is that mv88e6xxx_map_virtual_bridge_to_pvt() has been moved to avoid a forward declaration, and the mv88e6xxx_reg_lock() calls from inside it have been removed, since locking is now done from mv88e6xxx_port_bridge_{join,leave}. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org> -
由 Vladimir Oltean 提交于
This is a preparation patch for the removal of the DSA switch methods ->port_bridge_tx_fwd_offload() and ->port_bridge_tx_fwd_unoffload(). The plan is for the switch to report whether it offloads TX forwarding directly as a response to the ->port_bridge_join() method. This change deals with the noisy portion of converting all existing function prototypes to take this new boolean pointer argument. The bool is placed in the cross-chip notifier structure for bridge join, and a reference to it is provided to drivers. In the next change, DSA will then actually look at this value instead of calling ->port_bridge_tx_fwd_offload(). Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
由 Vladimir Oltean 提交于
The main desire behind this is to provide coherent bridge information to the fast path without locking. For example, right now we set dp->bridge_dev and dp->bridge_num from separate code paths, it is theoretically possible for a packet transmission to read these two port properties consecutively and find a bridge number which does not correspond with the bridge device. Another desire is to start passing more complex bridge information to dsa_switch_ops functions. For example, with FDB isolation, it is expected that drivers will need to be passed the bridge which requested an FDB/MDB entry to be offloaded, and along with that bridge_dev, the associated bridge_num should be passed too, in case the driver might want to implement an isolation scheme based on that number. We already pass the {bridge_dev, bridge_num} pair to the TX forwarding offload switch API, however we'd like to remove that and squash it into the basic bridge join/leave API. So that means we need to pass this pair to the bridge join/leave API. During dsa_port_bridge_leave, first we unset dp->bridge_dev, then we call the driver's .port_bridge_leave with what used to be our dp->bridge_dev, but provided as an argument. When bridge_dev and bridge_num get folded into a single structure, we need to preserve this behavior in dsa_port_bridge_leave: we need a copy of what used to be in dp->bridge. Switch drivers check bridge membership by comparing dp->bridge_dev with the provided bridge_dev, but now, if we provide the struct dsa_bridge as a pointer, they cannot keep comparing dp->bridge to the provided pointer, since this only points to an on-stack copy. To make this obvious and prevent driver writers from forgetting and doing stupid things, in this new API, the struct dsa_bridge is provided as a full structure (not very large, contains an int and a pointer) instead of a pointer. An explicit comparison function needs to be used to determine bridge membership: dsa_port_offloads_bridge(). Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org> -
由 Vladimir Oltean 提交于
Move the static inline helpers from net/dsa/dsa_priv.h to include/net/dsa.h, so that drivers can call functions such as dsa_port_offloads_bridge_dev(), which will be necessary after the transition to a more complex bridge structure. More functions than are needed right now are being moved, but this is done for uniformity. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
由 Vladimir Oltean 提交于
The location of the bridge device pointer and number is going to change. It is not going to be kept individually per port, but in a common structure allocated dynamically and which will have lockdep validation. Create helpers to access these elements so that we have a migration path to the new organization. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
由 Vladimir Oltean 提交于
The service where DSA assigns a unique bridge number for each forwarding domain is useful even for drivers which do not implement the TX forwarding offload feature. For example, drivers might use the dp->bridge_num for FDB isolation. So rename ds->num_fwd_offloading_bridges to ds->max_num_bridges, and calculate a unique bridge_num for all drivers that set this value. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
由 Vladimir Oltean 提交于
I have seen too many bugs already due to the fact that we must encode an invalid dp->bridge_num as a negative value, because the natural tendency is to check that invalid value using (!dp->bridge_num). Latest example can be seen in commit 1bec0f05 ("net: dsa: fix bridge_num not getting cleared after ports leaving the bridge"). Convert the existing users to assume that dp->bridge_num == 0 is the encoding for invalid, and valid bridge numbers start from 1. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
- 02 12月, 2021 1 次提交
-
-
由 Russell King (Oracle) 提交于
Phylink needs slightly more information than phylink_get_interfaces() allows us to get from the DSA drivers - we need the MAC capabilities. Replace the phylink_get_interfaces() method with phylink_get_caps() to allow DSA drivers to fill in the phylink_config MAC capabilities field as well. Signed-off-by: NRussell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: NMarek Behún <kabel@kernel.org> Reviewed-by: NAndrew Lunn <andrew@lunn.ch> Signed-off-by: NJakub Kicinski <kuba@kernel.org>
-
- 01 11月, 2021 1 次提交
-
-
由 Marek Behún 提交于
Add a new DSA switch operation, phylink_get_interfaces, which should fill in which PHY_INTERFACE_MODE_* are supported by given port. Use this before phylink_create() to fill phylinks supported_interfaces member, allowing phylink to determine which PHY_INTERFACE_MODEs are supported. Signed-off-by: NMarek Behún <kabel@kernel.org> [tweaked patch and description to add more complete support -- rmk] Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk> Signed-off-by: NRussell King (Oracle) <rmk+kernel@armlinux.org.uk> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 25 10月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
Now that the rtnl_mutex is going away for dsa_port_{host_,}fdb_{add,del}, no one is serializing access to the address lists that DSA keeps for the purpose of reference counting on shared ports (CPU and cascade ports). It can happen for one dsa_switch_do_fdb_del to do list_del on a dp->fdbs element while another dsa_switch_do_fdb_{add,del} is traversing dp->fdbs. We need to avoid that. Currently dp->mdbs is not at risk, because dsa_switch_do_mdb_{add,del} still runs under the rtnl_mutex. But it would be nice if it would not depend on that being the case. So let's introduce a mutex per port (the address lists are per port too) and share it between dp->mdbs and dp->fdbs. The place where we put the locking is interesting. It could be tempting to put a DSA-level lock which still serializes calls to .port_fdb_{add,del}, but it would still not avoid concurrency with other driver code paths that are currently under rtnl_mutex (.port_fdb_dump, .port_fast_age). So it would add a very false sense of security (and adding a global switch-wide lock in DSA to resynchronize with the rtnl_lock is also counterproductive and hard). So the locking is intentionally done only where the dp->fdbs and dp->mdbs lists are traversed. That means, from a driver perspective, that .port_fdb_add will be called with the dp->addr_lists_lock mutex held on the CPU port, but not held on user ports. This is done so that driver writers are not encouraged to rely on any guarantee offered by dp->addr_lists_lock. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 David S. Miller 提交于
This reverts commit 965e6b26, reversing changes made to 4d98bb0d.
-
- 24 10月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
Now that the rtnl_mutex is going away for dsa_port_{host_,}fdb_{add,del}, no one is serializing access to the address lists that DSA keeps for the purpose of reference counting on shared ports (CPU and cascade ports). It can happen for one dsa_switch_do_fdb_del to do list_del on a dp->fdbs element while another dsa_switch_do_fdb_{add,del} is traversing dp->fdbs. We need to avoid that. Currently dp->mdbs is not at risk, because dsa_switch_do_mdb_{add,del} still runs under the rtnl_mutex. But it would be nice if it would not depend on that being the case. So let's introduce a mutex per port (the address lists are per port too) and share it between dp->mdbs and dp->fdbs. The place where we put the locking is interesting. It could be tempting to put a DSA-level lock which still serializes calls to .port_fdb_{add,del}, but it would still not avoid concurrency with other driver code paths that are currently under rtnl_mutex (.port_fdb_dump, .port_fast_age). So it would add a very false sense of security (and adding a global switch-wide lock in DSA to resynchronize with the rtnl_lock is also counterproductive and hard). So the locking is intentionally done only where the dp->fdbs and dp->mdbs lists are traversed. That means, from a driver perspective, that .port_fdb_add will be called with the dp->addr_lists_lock mutex held on the CPU port, but not held on user ports. This is done so that driver writers are not encouraged to rely on any guarantee offered by dp->addr_lists_lock. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 21 10月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
Ever since Vivien's conversion of the ds->ports array into a dst->ports list, and the introduction of dsa_to_port, iterations through the ports of a switch became quadratic whenever dsa_to_port was needed. dsa_to_port can either be called directly, or indirectly through the dsa_is_{user,cpu,dsa,unused}_port helpers. Use the newly introduced dsa_switch_for_each_port() iteration macro that works with the iterator variable being a struct dsa_port *dp directly, and not an int i. It is an expensive variable to go from i to dp, but cheap to go from dp to i. This macro iterates through the entire ds->dst->ports list and filters by the ports belonging just to the switch provided as argument. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
Since the DSA conversion from the ds->ports array into the dst->ports list, the DSA API has encouraged driver writers, as well as the core itself, to write inefficient code. Currently, code that wants to filter by a specific type of port when iterating, like {!unused, user, cpu, dsa}, uses the dsa_is_*_port helper. Under the hood, this uses dsa_to_port which iterates again through dst->ports. But the driver iterates through the port list already, so the complexity is quadratic for the typical case of a single-switch tree. This patch introduces some iteration helpers where the iterator is already a struct dsa_port *dp, so that the other variant of the filtering functions, dsa_port_is_{unused,user,cpu_dsa}, can be used directly on the iterator. This eliminates the second lookup. These functions can be used both by the core and by drivers. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 18 10月, 2021 2 次提交
-
-
由 Alvin Šipraga 提交于
This commit implements a basic version of the 8 byte tag protocol used in the Realtek RTL8365MB-VC unmanaged switch, which carries with it a protocol version of 0x04. The implementation itself only handles the parsing of the EtherType value and Realtek protocol version, together with the source or destination port fields. The rest is left unimplemented for now. The tag format is described in a confidential document provided to my company by Realtek Semiconductor Corp. Permission has been granted by the vendor to publish this driver based on that material, together with an extract from the document describing the tag format and its fields. It is hoped that this will help future implementors who do not have access to the material but who wish to extend the functionality of drivers for chips which use this protocol. In addition, two possible values of the REASON field are specified, based on experiments on my end. Realtek does not specify what value this field can take. Signed-off-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Reviewed-by: NVladimir Oltean <olteanv@gmail.com> Reviewed-by: NLinus Walleij <linus.walleij@linaro.org> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Tested-by: NArınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Alvin Šipraga 提交于
Jakub pointed out that we have a new ethtool API for reporting device statistics in a standardized way, via .get_eth_{phy,mac,ctrl}_stats. Add a small amount of plumbing to allow DSA drivers to take advantage of this when exposing statistics. Suggested-by: NJakub Kicinski <kuba@kernel.org> Signed-off-by: NAlvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 19 9月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
Commit 86f8b1c0 ("net: dsa: Do not make user port errors fatal") decided it was fine to ignore errors on certain ports that fail to probe, and go on with the ports that do probe fine. Commit fb6ec87f ("net: dsa: Fix type was not set for devlink port") noticed that devlink_port_type_eth_set(dlp, dp->slave); does not get called, and devlink notices after a timeout of 3600 seconds and prints a WARN_ON. So it went ahead to unregister the devlink port. And because there exists an UNUSED port flavour, we actually re-register the devlink port as UNUSED. Commit 08156ba4 ("net: dsa: Add devlink port regions support to DSA") added devlink port regions, which are set up by the driver and not by DSA. When we trigger the devlink port deregistration and reregistration as unused, devlink now prints another WARN_ON, from here: devlink_port_unregister: WARN_ON(!list_empty(&devlink_port->region_list)); So the port still has regions, which makes sense, because they were set up by the driver, and the driver doesn't know we're unregistering the devlink port. Somebody needs to tear them down, and optionally (actually it would be nice, to be consistent) set them up again for the new devlink port. But DSA's layering stays in our way quite badly here. The options I've considered are: 1. Introduce a function in devlink to just change a port's type and flavour. No dice, devlink keeps a lot of state, it really wants the port to not be registered when you set its parameters, so changing anything can only be done by destroying what we currently have and recreating it. 2. Make DSA cache the parameters passed to dsa_devlink_port_region_create, and the region returned, keep those in a list, then when the devlink port unregister needs to take place, the existing devlink regions are destroyed by DSA, and we replay the creation of new regions using the cached parameters. Problem: mv88e6xxx keeps the region pointers in chip->ports[port].region, and these will remain stale after DSA frees them. There are many things DSA can do, but updating mv88e6xxx's private pointers is not one of them. 3. Just let the driver do it (i.e. introduce a very specific method called ds->ops->port_reinit_as_unused, which unregisters its devlink port devlink regions, then the old devlink port, then registers the new one, then the devlink port regions for it). While it does work, as opposed to the others, it's pretty horrible from an API perspective and we can do better. 4. Introduce a new pair of methods, ->port_setup and ->port_teardown, which in the case of mv88e6xxx must register and unregister the devlink port regions. Call these 2 methods when the port must be reinitialized as unused. Naturally, I went for the 4th approach. Fixes: 08156ba4 ("net: dsa: Add devlink port regions support to DSA") Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Vladimir Oltean 提交于
Lino reports that on his system with bcmgenet as DSA master and KSZ9897 as a switch, rebooting or shutting down never works properly. What does the bcmgenet driver have special to trigger this, that other DSA masters do not? It has an implementation of ->shutdown which simply calls its ->remove implementation. Otherwise said, it unregisters its network interface on shutdown. This message can be seen in a loop, and it hangs the reboot process there: unregister_netdevice: waiting for eth0 to become free. Usage count = 3 So why 3? A usage count of 1 is normal for a registered network interface, and any virtual interface which links itself as an upper of that will increment it via dev_hold. In the case of DSA, this is the call path: dsa_slave_create -> netdev_upper_dev_link -> __netdev_upper_dev_link -> __netdev_adjacent_dev_insert -> dev_hold So a DSA switch with 3 interfaces will result in a usage count elevated by two, and netdev_wait_allrefs will wait until they have gone away. Other stacked interfaces, like VLAN, watch NETDEV_UNREGISTER events and delete themselves, but DSA cannot just vanish and go poof, at most it can unbind itself from the switch devices, but that must happen strictly earlier compared to when the DSA master unregisters its net_device, so reacting on the NETDEV_UNREGISTER event is way too late. It seems that it is a pretty established pattern to have a driver's ->shutdown hook redirect to its ->remove hook, so the same code is executed regardless of whether the driver is unbound from the device, or the system is just shutting down. As Florian puts it, it is quite a big hammer for bcmgenet to unregister its net_device during shutdown, but having a common code path with the driver unbind helps ensure it is well tested. So DSA, for better or for worse, has to live with that and engage in an arms race of implementing the ->shutdown hook too, from all individual drivers, and do something sane when paired with masters that unregister their net_device there. The only sane thing to do, of course, is to unlink from the master. However, complications arise really quickly. The pattern of redirecting ->shutdown to ->remove is not unique to bcmgenet or even to net_device drivers. In fact, SPI controllers do it too (see dspi_shutdown -> dspi_remove), and presumably, I2C controllers and MDIO controllers do it too (this is something I have not researched too deeply, but even if this is not the case today, it is certainly plausible to happen in the future, and must be taken into consideration). Since DSA switches might be SPI devices, I2C devices, MDIO devices, the insane implication is that for the exact same DSA switch device, we might have both ->shutdown and ->remove getting called. So we need to do something with that insane environment. The pattern I've come up with is "if this, then not that", so if either ->shutdown or ->remove gets called, we set the device's drvdata to NULL, and in the other hook, we check whether the drvdata is NULL and just do nothing. This is probably not necessary for platform devices, just for devices on buses, but I would really insist for consistency among drivers, because when code is copy-pasted, it is not always copy-pasted from the best sources. So depending on whether the DSA switch's ->remove or ->shutdown will get called first, we cannot really guarantee even for the same driver if rebooting will result in the same code path on all platforms. But nonetheless, we need to do something minimally reasonable on ->shutdown too to fix the bug. Of course, the ->remove will do more (a full teardown of the tree, with all data structures freed, and this is why the bug was not caught for so long). The new ->shutdown method is kept separate from dsa_unregister_switch not because we couldn't have unregistered the switch, but simply in the interest of doing something quick and to the point. The big question is: does the DSA switch's ->shutdown get called earlier than the DSA master's ->shutdown? If not, there is still a risk that we might still trigger the WARN_ON in unregister_netdevice that says we are attempting to unregister a net_device which has uppers. That's no good. Although the reference to the master net_device won't physically go away even if DSA's ->shutdown comes afterwards, remember we have a dev_hold on it. The answer to that question lies in this comment above device_link_add: * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). so the fact that DSA uses device_link_add towards its master is not exactly for nothing. device_shutdown() walks devices_kset from the back, so this is our guarantee that DSA's shutdown happens before the master's shutdown. Fixes: 2f1e8ea7 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/Reported-by: NLino Sanfilippo <LinoSanfilippo@gmx.de> Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Tested-by: NAndrew Lunn <andrew@lunn.ch> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 16 9月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
Sometimes when unbinding the mv88e6xxx driver on Turris MOX, these error messages appear: mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 0 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 100 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 0 from fdb: -2 (and similarly for other ports) What happens is that DSA has a policy "even if there are bugs, let's at least not leak memory" and dsa_port_teardown() clears the dp->fdbs and dp->mdbs lists, which are supposed to be empty. But deleting that cleanup code, the warnings go away. => the FDB and MDB lists (used for refcounting on shared ports, aka CPU and DSA ports) will eventually be empty, but are not empty by the time we tear down those ports. Aka we are deleting them too soon. The addresses that DSA complains about are host-trapped addresses: the local addresses of the ports, and the MAC address of the bridge device. The problem is that offloading those entries happens from a deferred work item scheduled by the SWITCHDEV_FDB_DEL_TO_DEVICE handler, and this races with the teardown of the CPU and DSA ports where the refcounting is kept. In fact, not only it races, but fundamentally speaking, if we iterate through the port list linearly, we might end up tearing down the shared ports even before we delete a DSA user port which has a bridge upper. So as it turns out, we need to first tear down the user ports (and the unused ones, for no better place of doing that), then the shared ports (the CPU and DSA ports). In between, we need to ensure that all work items scheduled by our switchdev handlers (which only run for user ports, hence the reason why we tear them down first) have finished. Fixes: 161ca59d ("net: dsa: reference count the MDB entries at the cross-chip notifier level") Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20210914134726.2305133-1-vladimir.oltean@nxp.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>
-
- 24 8月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
As explained in commit e358bef7 ("net: dsa: Give drivers the chance to veto certain upper devices"), the hellcreek driver uses some tricks to comply with the network stack expectations: it enforces port separation in standalone mode using VLANs. For untagged traffic, bridging between ports is prevented by using different PVIDs, and for VLAN-tagged traffic, it never accepts 8021q uppers with the same VID on two ports, so packets with one VLAN cannot leak from one port to another. That is almost fine*, and has worked because hellcreek relied on an implicit behavior of the DSA core that was changed by the previous patch: the standalone ports declare the 'rx-vlan-filter' feature as 'on [fixed]'. Since most of the DSA drivers are actually VLAN-unaware in standalone mode, that feature was actually incorrectly reflecting the hardware/driver state, so there was a desire to fix it. This leaves the hellcreek driver in a situation where it has to explicitly request this behavior from the DSA framework. We configure the ports as follows: - Standalone: 'rx-vlan-filter' is on. An 8021q upper on top of a standalone hellcreek port will go through dsa_slave_vlan_rx_add_vid and will add a VLAN to the hardware tables, giving the driver the opportunity to refuse it through .port_prechangeupper. - Bridged with vlan_filtering=0: 'rx-vlan-filter' is off. An 8021q upper on top of a bridged hellcreek port will not go through dsa_slave_vlan_rx_add_vid, because there will not be any attempt to offload this VLAN. The driver already disables VLAN awareness, so that upper should receive the traffic it needs. - Bridged with vlan_filtering=1: 'rx-vlan-filter' is on. An 8021q upper on top of a bridged hellcreek port will call dsa_slave_vlan_rx_add_vid, and can again be vetoed through .port_prechangeupper. *It is not actually completely fine, because if I follow through correctly, we can have the following situation: ip link add br0 type bridge vlan_filtering 0 ip link set lan0 master br0 # lan0 now becomes VLAN-unaware ip link set lan0 nomaster # lan0 fails to become VLAN-aware again, therefore breaking isolation This patch fixes that corner case by extending the DSA core logic, based on this requested attribute, to change the VLAN awareness state of the switch (port) when it leaves the bridge. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Acked-by: NKurt Kanzenbach <kurt@linutronix.de> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 23 8月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
Right now, cross-tree bridging setups work somewhat by mistake. In the case of cross-tree bridging with sja1105, all switch instances need to agree upon a common VLAN ID for forwarding a packet that belongs to a certain bridging domain. With TX forwarding offload, the VLAN ID is the bridge VLAN for VLAN-aware bridging, and the tag_8021q TX forwarding offload VID (a VLAN which has non-zero VBID bits) for VLAN-unaware bridging. The VBID for VLAN-unaware bridging is derived from the dp->bridge_num value calculated by DSA independently for each switch tree. If ports from one tree join one bridge, and ports from another tree join another bridge, DSA will assign them the same bridge_num, even though the bridges are different. If cross-tree bridging is supported, this is an issue. Modify DSA to calculate the bridge_num globally across all switch trees. This has the implication for a driver that the dp->bridge_num value that DSA will assign to its ports might not be contiguous, if there are boards with multiple DSA drivers instantiated. Additionally, all bridge_num values eat up towards each switch's ds->num_fwd_offloading_bridges maximum, which is potentially unfortunate, and can be seen as a limitation introduced by this patch. However, that is the lesser evil for now. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 09 8月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
Now that DSA keeps track of the port learning state, it becomes superfluous to keep an additional variable with this information in the sja1105 driver. Remove it. The DSA core's learning state is present in struct dsa_port *dp. To avoid the antipattern where we iterate through a DSA switch's ports and then call dsa_to_port to obtain the "dp" reference (which is bad because dsa_to_port iterates through the DSA switch tree once again), just iterate through the dst->ports and operate on those directly. The sja1105 had an extra use of priv->learn_ena on non-user ports. DSA does not touch the learning state of those ports - drivers are free to do what they wish on them. Mark that information with a comment in struct dsa_port and let sja1105 set dp->learning for cascade ports. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Vladimir Oltean 提交于
Currently DSA leaves it down to device drivers to fast age the FDB on a port when address learning is disabled on it. There are 2 reasons for doing that in the first place: - when address learning is disabled by user space, through IFLA_BRPORT_LEARNING or the brport_attr_learning sysfs, what user space typically wants to achieve is to operate in a mode with no dynamic FDB entry on that port. But if the port is already up, some addresses might have been already learned on it, and it seems silly to wait for 5 minutes for them to expire until something useful can be done. - when a port leaves a bridge and becomes standalone, DSA turns off address learning on it. This also has the nice side effect of flushing the dynamically learned bridge FDB entries on it, which is a good idea because standalone ports should not have bridge FDB entries on them. We let drivers manage fast ageing under this condition because if DSA were to do it, it would need to track each port's learning state, and act upon the transition, which it currently doesn't. But there are 2 reasons why doing it is better after all: - drivers might get it wrong and not do it (see b53_port_set_learning) - we would like to flush the dynamic entries from the software bridge too, and letting drivers do that would be another pain point So track the port learning state and trigger a fast age process automatically within DSA. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 06 8月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
Commit 08cc83cc ("net: dsa: add support for BRIDGE_MROUTER attribute") added an option for users to turn off multicast flooding towards the CPU if they turn off the IGMP querier on a bridge which already has enslaved ports (echo 0 > /sys/class/net/br0/bridge/multicast_router). And commit a8b659e7 ("net: dsa: act as passthrough for bridge port flags") simply papered over that issue, because it moved the decision to flood the CPU with multicast (or not) from the DSA core down to individual drivers, instead of taking a more radical position then. The truth is that disabling multicast flooding to the CPU is simply something we are not prepared to do now, if at all. Some reasons: - ICMP6 neighbor solicitation messages are unregistered multicast packets as far as the bridge is concerned. So if we stop flooding multicast, the outside world cannot ping the bridge device's IPv6 link-local address. - There might be foreign interfaces bridged with our DSA switch ports (sending a packet towards the host does not necessarily equal termination, but maybe software forwarding). So if there is no one interested in that multicast traffic in the local network stack, that doesn't mean nobody is. - PTP over L4 (IPv4, IPv6) is multicast, but is unregistered as far as the bridge is concerned. This should reach the CPU port. - The switch driver might not do FDB partitioning. And since we don't even bother to do more fine-grained flood disabling (such as "disable flooding _from_port_N_ towards the CPU port" as opposed to "disable flooding _from_any_port_ towards the CPU port"), this breaks standalone ports, or even multiple bridges where one has an IGMP querier and one doesn't. Reverting the logic makes all of the above work. Fixes: a8b659e7 ("net: dsa: act as passthrough for bridge port flags") Fixes: 08cc83cc ("net: dsa: add support for BRIDGE_MROUTER attribute") Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 02 8月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
No tagging driver uses this. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 28 7月, 2021 1 次提交
-
-
由 Arnd Bergmann 提交于
Most users of ndo_do_ioctl are ethernet drivers that implement the MII commands SIOCGMIIPHY/SIOCGMIIREG/SIOCSMIIREG, or hardware timestamping with SIOCSHWTSTAMP/SIOCGHWTSTAMP. Separate these from the few drivers that use ndo_do_ioctl to implement SIOCBOND, SIOCBR and SIOCWANDEV commands. This is a purely cosmetic change intended to help readers find their way through the implementation. Cc: Doug Ledford <dledford@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jay Vosburgh <j.vosburgh@gmail.com> Cc: Veaceslav Falico <vfalico@gmail.com> Cc: Andy Gospodarek <andy@greyhouse.net> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Vivien Didelot <vivien.didelot@gmail.com> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: Vladimir Oltean <olteanv@gmail.com> Cc: Leon Romanovsky <leon@kernel.org> Cc: linux-rdma@vger.kernel.org Signed-off-by: NArnd Bergmann <arnd@arndb.de> Acked-by: NJason Gunthorpe <jgg@nvidia.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 27 7月, 2021 1 次提交
-
-
由 Vladimir Oltean 提交于
This reverts commit cc1939e4. Currently 2 classes of DSA drivers are able to send/receive packets directly through the DSA master: - drivers with DSA_TAG_PROTO_NONE - sja1105 Now that sja1105 has gained the ability to perform traffic termination even under the tricky case (VLAN-aware bridge), and that is much more functional (we can perform VLAN-aware bridging with foreign interfaces), there is no reason to keep this code in the receive path of the network core. So delete it. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 23 7月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
For a DSA switch, to offload the forwarding process of a bridge device means to send the packets coming from the software bridge as data plane packets. This is contrary to everything that DSA has done so far, because the current taggers only know to send control packets (ones that target a specific destination port), whereas data plane packets are supposed to be forwarded according to the FDB lookup, much like packets ingressing on any regular ingress port. If the FDB lookup process returns multiple destination ports (flooding, multicast), then replication is also handled by the switch hardware - the bridge only sends a single packet and avoids the skb_clone(). DSA keeps for each bridge port a zero-based index (the number of the bridge). Multiple ports performing TX forwarding offload to the same bridge have the same dp->bridge_num value, and ports not offloading the TX data plane of a bridge have dp->bridge_num = -1. The tagger can check if the packet that is being transmitted on has skb->offload_fwd_mark = true or not. If it does, it can be sure that the packet belongs to the data plane of a bridge, further information about which can be obtained based on dp->bridge_dev and dp->bridge_num. It can then compose a DSA tag for injecting a data plane packet into that bridge number. For the switch driver side, we offer two new dsa_switch_ops methods, called .port_bridge_fwd_offload_{add,del}, which are modeled after .port_bridge_{join,leave}. These methods are provided in case the driver needs to configure the hardware to treat packets coming from that bridge software interface as data plane packets. The switchdev <-> bridge interaction happens during the netdev_master_upper_dev_link() call, so to switch drivers, the effect is that the .port_bridge_fwd_offload_add() method is called immediately after .port_bridge_join(). If the bridge number exceeds the number of bridges for which the switch driver can offload the TX data plane (and this includes the case where the driver can offload none), DSA falls back to simply returning tx_fwd_offload = false in the switchdev_bridge_port_offload() call. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net> -
由 Vladimir Oltean 提交于
In preparation of supporting data plane forwarding on behalf of a software bridge, some drivers might need to view bridges as virtual switches behind the CPU port in a cross-chip topology. Give them some help and let them know how many physical switches there are in the tree, so that they can count the virtual switches starting from that number on. Note that the first dsa_switch_ops method where this information is reliably available is .setup(). This is because of how DSA works: in a tree with 3 switches, each calling dsa_register_switch(), the first 2 will advance until dsa_tree_setup() -> dsa_tree_setup_routing_table() and exit with error code 0 because the topology is not complete. Since probing is parallel at this point, one switch does not know about the existence of the other. Then the third switch comes, and for it, dsa_tree_setup_routing_table() returns complete = true. This switch goes ahead and calls dsa_tree_setup_switches() for everybody else, calling their .setup() methods too. This acts as the synchronization point. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 20 7月, 2021 2 次提交
-
-
由 Vladimir Oltean 提交于
Make tag_8021q a more central element of DSA and move the 2 driver specific operations outside of struct dsa_8021q_context (which is supposed to hold dynamic data and not really constant function pointers). Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Vladimir Oltean 提交于
The basic problem description is as follows: Be there 3 switches in a daisy chain topology: | sw0p0 sw0p1 sw0p2 sw0p3 sw0p4 [ user ] [ user ] [ user ] [ dsa ] [ cpu ] | +---------+ | sw1p0 sw1p1 sw1p2 sw1p3 sw1p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] | +---------+ | sw2p0 sw2p1 sw2p2 sw2p3 sw2p4 [ user ] [ user ] [ user ] [ user ] [ dsa ] The CPU will not be able to ping through the user ports of the bottom-most switch (like for example sw2p0), simply because tag_8021q was not coded up for this scenario - it has always assumed DSA switch trees with a single switch. To add support for the topology above, we must admit that the RX VLAN of sw2p0 must be added on some ports of switches 0 and 1 as well. This is in fact a textbook example of thing that can use the cross-chip notifier framework that DSA has set up in switch.c. There is only one problem: core DSA (switch.c) is not able right now to make the connection between a struct dsa_switch *ds and a struct dsa_8021q_context *ctx. Right now, it is drivers who call into tag_8021q.c and always provide a struct dsa_8021q_context *ctx pointer, and tag_8021q.c calls them back with the .tag_8021q_vlan_{add,del} methods. But with cross-chip notifiers, it is possible for tag_8021q to call drivers without drivers having ever asked for anything. A good example is right above: when sw2p0 wants to set itself up for tag_8021q, the .tag_8021q_vlan_add method needs to be called for switches 1 and 0, so that they transport sw2p0's VLANs towards the CPU without dropping them. So instead of letting drivers manage the tag_8021q context, add a tag_8021q_ctx pointer inside of struct dsa_switch, which will be populated when dsa_tag_8021q_register() returns success. The patch is fairly long-winded because we are partly reverting commit 5899ee36 ("net: dsa: tag_8021q: add a context structure") which made the driver-facing tag_8021q API use "ctx" instead of "ds". Now that we can access "ctx" directly from "ds", this is no longer needed. Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-