#include <linux/device.h>
#include <linux/percpu.h>
+#include <linux/rculist.h>
#include <linux/dmaengine.h>
#include <linux/workqueue.h>
/* Backlog congestion levels */
#define NET_RX_SUCCESS 0 /* keep 'em coming, baby */
#define NET_RX_DROP 1 /* packet dropped */
-#define NET_RX_CN_LOW 2 /* storm alert, just in case */
-#define NET_RX_CN_MOD 3 /* Storm on its way! */
-#define NET_RX_CN_HIGH 4 /* The storm is here */
-#define NET_RX_BAD 5 /* packet dropped due to kernel error */
/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
* indicates that the device will soon be dropping packets, or already drops
#define net_xmit_eval(e) ((e) == NET_XMIT_CN? 0 : (e))
#define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0)
+/* Driver transmit return codes */
+enum netdev_tx {
+ NETDEV_TX_OK = 0, /* driver took care of packet */
+ NETDEV_TX_BUSY, /* driver tx path was busy*/
+ NETDEV_TX_LOCKED = -1, /* driver tx lock was already taken */
+};
+typedef enum netdev_tx netdev_tx_t;
+
#endif
#define MAX_ADDR_LEN 32 /* Largest hardware address length */
-/* Driver transmit return codes */
-#define NETDEV_TX_OK 0 /* driver took care of packet */
-#define NETDEV_TX_BUSY 1 /* driver tx path was busy*/
-#define NETDEV_TX_LOCKED -1 /* driver tx lock was already taken */
-
#ifdef __KERNEL__
-
/*
* Compute the worst case header length according to the protocols
* used.
# else
# define LL_MAX_HEADER 96
# endif
-#elif defined(CONFIG_TR)
+#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
# define LL_MAX_HEADER 48
#else
# define LL_MAX_HEADER 32
#define dmi_users da_users
#define dmi_gusers da_gusers
+struct netdev_hw_addr {
+ struct list_head list;
+ unsigned char addr[MAX_ADDR_LEN];
+ unsigned char type;
+#define NETDEV_HW_ADDR_T_LAN 1
+#define NETDEV_HW_ADDR_T_SAN 2
+#define NETDEV_HW_ADDR_T_SLAVE 3
+#define NETDEV_HW_ADDR_T_UNICAST 4
+ int refcount;
+ bool synced;
+ struct rcu_head rcu_head;
+};
+
+struct netdev_hw_addr_list {
+ struct list_head list;
+ int count;
+};
+
struct hh_cache
{
struct hh_cache *hh_next; /* Next entry */
};
struct netdev_queue {
+/*
+ * read mostly part
+ */
struct net_device *dev;
struct Qdisc *qdisc;
unsigned long state;
- spinlock_t _xmit_lock;
- int xmit_lock_owner;
struct Qdisc *qdisc_sleeping;
+/*
+ * write mostly part
+ */
+ spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
+ int xmit_lock_owner;
+ /*
+ * please use this field instead of dev->trans_start
+ */
+ unsigned long trans_start;
+ unsigned long tx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_dropped;
} ____cacheline_aligned_in_smp;
* This function is called when network device transistions to the down
* state.
*
- * int (*ndo_start_xmit)(struct sk_buff *skb, struct net_device *dev);
+ * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
+ * struct net_device *dev);
* Called when a packet needs to be transmitted.
- * Must return NETDEV_TX_OK , NETDEV_TX_BUSY, or NETDEV_TX_LOCKED,
+ * Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
+ * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
* Required can not be NULL.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
*
* int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
* This function is called when the Media Access Control address
- * needs to be changed. If not this interface is not defined, the
+ * needs to be changed. If this interface is not defined, the
* mac address can not be changed.
*
* int (*ndo_validate_addr)(struct net_device *dev);
void (*ndo_uninit)(struct net_device *dev);
int (*ndo_open)(struct net_device *dev);
int (*ndo_stop)(struct net_device *dev);
- int (*ndo_start_xmit) (struct sk_buff *skb,
+ netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb,
struct net_device *dev);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb);
void (*ndo_poll_controller)(struct net_device *dev);
#endif
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+ int (*ndo_fcoe_enable)(struct net_device *dev);
+ int (*ndo_fcoe_disable)(struct net_device *dev);
int (*ndo_fcoe_ddp_setup)(struct net_device *dev,
u16 xid,
struct scatterlist *sgl,
#define NETIF_F_GRO 16384 /* Generic receive offload */
#define NETIF_F_LRO 32768 /* large receive offload */
+/* the GSO_MASK reserves bits 16 through 23 */
#define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */
+#define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */
+#define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
unsigned char addr_len; /* hardware address length */
unsigned short dev_id; /* for shared network cards */
- spinlock_t addr_list_lock;
- struct dev_addr_list *uc_list; /* Secondary unicast mac addresses */
- int uc_count; /* Number of installed ucasts */
+ struct netdev_hw_addr_list uc; /* Secondary unicast
+ mac addresses */
int uc_promisc;
+ spinlock_t addr_list_lock;
struct dev_addr_list *mc_list; /* Multicast mac addresses */
int mc_count; /* Number of installed mcasts */
unsigned int promiscuity;
*/
unsigned long last_rx; /* Time of last Rx */
/* Interface address info used in eth_type_trans() */
- unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, (before bcast
- because most packets are unicast) */
+ unsigned char *dev_addr; /* hw address, (before bcast
+ because most packets are
+ unicast) */
+
+ struct netdev_hw_addr_list dev_addrs; /* list of device
+ hw addresses */
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
/* Number of TX queues currently active in device */
unsigned int real_num_tx_queues;
+ /* root qdisc from userspace point of view */
+ struct Qdisc *qdisc;
+
unsigned long tx_queue_len; /* Max frames per queue allowed */
spinlock_t tx_global_lock;
/*
* One part is mostly used on xmit path (device)
*/
/* These may be needed for future network-power-down code. */
+
+ /*
+ * trans_start here is expensive for high speed devices on SMP,
+ * please use netdev_queue->trans_start instead.
+ */
unsigned long trans_start; /* Time (in jiffies) of last Tx */
int watchdog_timeo; /* used by dev_watchdog() */
/* class/net/name entry */
struct device dev;
/* space for optional statistics and wireless sysfs groups */
- struct attribute_group *sysfs_groups[3];
+ const struct attribute_group *sysfs_groups[3];
/* rtnetlink link ops */
const struct rtnl_link_ops *rtnl_link_ops;
/* max exchange id for FCoE LRO by ddp */
unsigned int fcoe_ddp_xid;
#endif
-
-#ifdef CONFIG_COMPAT_NET_DEV_OPS
- struct {
- int (*init)(struct net_device *dev);
- void (*uninit)(struct net_device *dev);
- int (*open)(struct net_device *dev);
- int (*stop)(struct net_device *dev);
- int (*hard_start_xmit) (struct sk_buff *skb,
- struct net_device *dev);
- u16 (*select_queue)(struct net_device *dev,
- struct sk_buff *skb);
- void (*change_rx_flags)(struct net_device *dev,
- int flags);
- void (*set_rx_mode)(struct net_device *dev);
- void (*set_multicast_list)(struct net_device *dev);
- int (*set_mac_address)(struct net_device *dev,
- void *addr);
- int (*validate_addr)(struct net_device *dev);
- int (*do_ioctl)(struct net_device *dev,
- struct ifreq *ifr, int cmd);
- int (*set_config)(struct net_device *dev,
- struct ifmap *map);
- int (*change_mtu)(struct net_device *dev, int new_mtu);
- int (*neigh_setup)(struct net_device *dev,
- struct neigh_parms *);
- void (*tx_timeout) (struct net_device *dev);
- struct net_device_stats* (*get_stats)(struct net_device *dev);
- void (*vlan_rx_register)(struct net_device *dev,
- struct vlan_group *grp);
- void (*vlan_rx_add_vid)(struct net_device *dev,
- unsigned short vid);
- void (*vlan_rx_kill_vid)(struct net_device *dev,
- unsigned short vid);
-#ifdef CONFIG_NET_POLL_CONTROLLER
- void (*poll_controller)(struct net_device *dev);
-#endif
- };
-#endif
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
#define NETDEV_ALIGN 32
-#define NETDEV_ALIGN_CONST (NETDEV_ALIGN - 1)
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
*/
static inline void *netdev_priv(const struct net_device *dev)
{
- return (char *)dev + ((sizeof(struct net_device)
- + NETDEV_ALIGN_CONST)
- & ~NETDEV_ALIGN_CONST);
+ return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
}
/* Set the sysfs physical device reference for the network logical device
*/
#define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev))
+/* Set the sysfs device type for the network logical device to allow
+ * fin grained indentification of different network device types. For
+ * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
+ */
+#define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype))
+
/**
* netif_napi_add - initialize a napi context
* @dev: network device
void netif_napi_del(struct napi_struct *napi);
struct napi_gro_cb {
+ /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
+ void *frag0;
+
+ /* Length of frag0. */
+ unsigned int frag0_len;
+
/* This indicates where we are processing relative to skb->data. */
int data_offset;
#ifdef CONFIG_NETPOLL_TRAP
extern int netpoll_trap(void);
#endif
-extern void *skb_gro_header(struct sk_buff *skb, unsigned int hlen);
extern int skb_gro_receive(struct sk_buff **head,
struct sk_buff *skb);
+extern void skb_gro_reset_offset(struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
NAPI_GRO_CB(skb)->data_offset += len;
}
-static inline void skb_gro_reset_offset(struct sk_buff *skb)
+static inline void *skb_gro_header_fast(struct sk_buff *skb,
+ unsigned int offset)
{
- NAPI_GRO_CB(skb)->data_offset = 0;
+ return NAPI_GRO_CB(skb)->frag0 + offset;
+}
+
+static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
+{
+ return NAPI_GRO_CB(skb)->frag0_len < hlen;
+}
+
+static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
+ unsigned int offset)
+{
+ NAPI_GRO_CB(skb)->frag0 = NULL;
+ NAPI_GRO_CB(skb)->frag0_len = 0;
+ return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
}
static inline void *skb_gro_mac_header(struct sk_buff *skb)
{
- return skb_headlen(skb) ? skb_mac_header(skb) :
- page_address(skb_shinfo(skb)->frags[0].page) +
- skb_shinfo(skb)->frags[0].page_offset;
+ return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb);
}
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
- return skb_headlen(skb) ? skb_network_header(skb) :
- page_address(skb_shinfo(skb)->frags[0].page) +
- skb_shinfo(skb)->frags[0].page_offset + skb_network_offset(skb);
+ return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
+ skb_network_offset(skb);
}
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
{
#ifdef CONFIG_NETPOLL_TRAP
if (netpoll_trap()) {
- clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+ netif_tx_start_queue(dev_queue);
return;
}
#endif
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
- clear_bit(__QUEUE_STATE_XOFF, &txq->state);
+
+ netif_tx_start_queue(txq);
}
/**
if (netpoll_trap())
return;
#endif
- set_bit(__QUEUE_STATE_XOFF, &txq->state);
+ netif_tx_stop_queue(txq);
}
/**
u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
- return test_bit(__QUEUE_STATE_XOFF, &txq->state);
+
+ return netif_tx_queue_stopped(txq);
}
static inline int netif_subqueue_stopped(const struct net_device *dev,
return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}
+extern unsigned long dev_trans_start(struct net_device *dev);
+
extern void __netdev_watchdog_up(struct net_device *dev);
extern void netif_carrier_on(struct net_device *dev);
spin_unlock_bh(&txq->_xmit_lock);
}
+static inline void txq_trans_update(struct netdev_queue *txq)
+{
+ if (txq->xmit_lock_owner != -1)
+ txq->trans_start = jiffies;
+}
+
/**
* netif_tx_lock - grab network device transmit lock
* @dev: network device
* force a schedule.
*/
clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
- if (!test_bit(__QUEUE_STATE_XOFF, &txq->state))
- __netif_schedule(txq->qdisc);
+ netif_schedule_queue(txq);
}
spin_unlock(&dev->tx_global_lock);
}
spin_unlock_bh(&dev->addr_list_lock);
}
+/*
+ * dev_addrs walker. Should be used only for read access. Call with
+ * rcu_read_lock held.
+ */
+#define for_each_dev_addr(dev, ha) \
+ list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
+
/* These functions live elsewhere (drivers/net/net_init.c, but related) */
extern void ether_setup(struct net_device *dev);
alloc_netdev_mq(sizeof_priv, name, setup, 1)
extern int register_netdev(struct net_device *dev);
extern void unregister_netdev(struct net_device *dev);
+
+/* Functions used for device addresses handling */
+extern int dev_addr_add(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type);
+extern int dev_addr_del(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type);
+extern int dev_addr_add_multiple(struct net_device *to_dev,
+ struct net_device *from_dev,
+ unsigned char addr_type);
+extern int dev_addr_del_multiple(struct net_device *to_dev,
+ struct net_device *from_dev,
+ unsigned char addr_type);
+
/* Functions used for secondary unicast and multicast support */
extern void dev_set_rx_mode(struct net_device *dev);
extern void __dev_set_rx_mode(struct net_device *dev);
-extern int dev_unicast_delete(struct net_device *dev, void *addr, int alen);
-extern int dev_unicast_add(struct net_device *dev, void *addr, int alen);
+extern int dev_unicast_delete(struct net_device *dev, void *addr);
+extern int dev_unicast_add(struct net_device *dev, void *addr);
extern int dev_unicast_sync(struct net_device *to, struct net_device *from);
extern void dev_unicast_unsync(struct net_device *to, struct net_device *from);
extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all);
extern int dev_set_promiscuity(struct net_device *dev, int inc);
extern int dev_set_allmulti(struct net_device *dev, int inc);
extern void netdev_state_change(struct net_device *dev);
-extern void netdev_bonding_change(struct net_device *dev);
+extern void netdev_bonding_change(struct net_device *dev,
+ unsigned long event);
extern void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
extern void dev_load(struct net *net, const char *name);
static inline int skb_gso_ok(struct sk_buff *skb, int features)
{
- return net_gso_ok(features, skb_shinfo(skb)->gso_type);
+ return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
+ (!skb_has_frags(skb) || (features & NETIF_F_FRAGLIST));
}
static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
{
return skb_is_gso(skb) &&
(!skb_gso_ok(skb, dev->features) ||
- (skb_shinfo(skb)->frag_list &&
- !(dev->features & NETIF_F_FRAGLIST)) ||
unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
}
dev->gso_max_size = size;
}
+static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
+ struct net_device *master)
+{
+ if (skb->pkt_type == PACKET_HOST) {
+ u16 *dest = (u16 *) eth_hdr(skb)->h_dest;
+
+ memcpy(dest, master->dev_addr, ETH_ALEN);
+ }
+}
+
/* On bonding slaves other than the currently active slave, suppress
* duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
* ARP on active-backup slaves with arp_validate enabled.
if (master->priv_flags & IFF_MASTER_ARPMON)
dev->last_rx = jiffies;
+ if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) {
+ /* Do address unmangle. The local destination address
+ * will be always the one master has. Provides the right
+ * functionality in a bridge.
+ */
+ skb_bond_set_mac_by_master(skb, master);
+ }
+
if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
skb->protocol == __cpu_to_be16(ETH_P_ARP))
}
#endif /* __KERNEL__ */
-#endif /* _LINUX_DEV_H */
+#endif /* _LINUX_NETDEVICE_H */