net: dsa: move dsa_port :: type near dsa_port :: index

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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/dsa.h

@@ -246,6 +246,10 @@ struct dsa_port {
 	struct dsa_switch_tree *dst;
 	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev);
 
+	struct dsa_switch	*ds;
+
+	unsigned int		index;
+
 	enum {
 		DSA_PORT_TYPE_UNUSED = 0,
 		DSA_PORT_TYPE_CPU,
@@ -253,8 +257,6 @@ struct dsa_port {
 		DSA_PORT_TYPE_USER,
 	} type;
 
-	struct dsa_switch	*ds;
-	unsigned int		index;
 	const char		*name;
 	struct dsa_port		*cpu_dp;
 	u8			mac[ETH_ALEN];