net: dsa: merge all bools of struct dsa_port into a single u8

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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Vladimir Oltean 2022-01-05 15:21:36 +02:00 committed by David S. Miller
parent b08db33dab
commit bde82f389a

View File

@ -261,18 +261,23 @@ struct dsa_port {
u8 stp_state;
u8 vlan_filtering:1,
/* Managed by DSA on user ports and by
* drivers on CPU and DSA ports
*/
learning:1,
lag_tx_enabled:1,
devlink_port_setup:1,
setup:1;
struct device_node *dn;
unsigned int ageing_time;
bool vlan_filtering;
/* Managed by DSA on user ports and by drivers on CPU and DSA ports */
bool learning;
struct dsa_bridge *bridge;
struct devlink_port devlink_port;
bool devlink_port_setup;
struct phylink *pl;
struct phylink_config pl_config;
struct net_device *lag_dev;
bool lag_tx_enabled;
struct net_device *hsr_dev;
struct list_head list;
@ -293,8 +298,6 @@ struct dsa_port {
struct mutex addr_lists_lock;
struct list_head fdbs;
struct list_head mdbs;
bool setup;
};
/* TODO: ideally DSA ports would have a single dp->link_dp member,