1 files changed, 192 insertions, 104 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa8b47637997..a1bff6518166 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -31,6 +31,7 @@
 #include <linux/if_link.h>
 
 #ifdef __KERNEL__
+#include <linux/pm_qos_params.h>
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
@@ -218,34 +219,6 @@ struct neighbour;
 struct neigh_parms;
 struct sk_buff;
 
-struct netif_rx_stats {
-        unsigned total;
-        unsigned dropped;
-        unsigned time_squeeze;
-        unsigned cpu_collision;
-};
-
-DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat);
-
-struct dev_addr_list {
-        struct dev_addr_list    *next;
-        u8                      da_addr[MAX_ADDR_LEN];
-        u8                      da_addrlen;
-        u8                      da_synced;
-        int                     da_users;
-        int                     da_gusers;
-};
-
-/*
- *      We tag multicasts with these structures.
- */
-
-#define dev_mc_list     dev_addr_list
-#define dmi_addr        da_addr
-#define dmi_addrlen     da_addrlen
-#define dmi_users       da_users
-#define dmi_gusers      da_gusers
-
 struct netdev_hw_addr {
         struct list_head        list;
         unsigned char           addr[MAX_ADDR_LEN];
@@ -254,8 +227,10 @@ struct netdev_hw_addr {
 #define NETDEV_HW_ADDR_T_SAN            2
 #define NETDEV_HW_ADDR_T_SLAVE          3
 #define NETDEV_HW_ADDR_T_UNICAST        4
+#define NETDEV_HW_ADDR_T_MULTICAST      5
         int                     refcount;
         bool                    synced;
+        bool                    global_use;
         struct rcu_head         rcu_head;
 };
 
@@ -264,16 +239,20 @@ struct netdev_hw_addr_list {
         int                     count;
 };
 
-#define netdev_uc_count(dev) ((dev)->uc.count)
-#define netdev_uc_empty(dev) ((dev)->uc.count == 0)
-#define netdev_for_each_uc_addr(ha, dev) \
-        list_for_each_entry(ha, &dev->uc.list, list)
+#define netdev_hw_addr_list_count(l) ((l)->count)
+#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0)
+#define netdev_hw_addr_list_for_each(ha, l) \
+        list_for_each_entry(ha, &(l)->list, list)
 
-#define netdev_mc_count(dev) ((dev)->mc_count)
-#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0)
+#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc)
+#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc)
+#define netdev_for_each_uc_addr(ha, dev) \
+        netdev_hw_addr_list_for_each(ha, &(dev)->uc)
 
-#define netdev_for_each_mc_addr(mclist, dev) \
-        for (mclist = dev->mc_list; mclist; mclist = mclist->next)
+#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
+#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
+#define netdev_for_each_mc_addr(ha, dev) \
+        netdev_hw_addr_list_for_each(ha, &(dev)->mc)
 
 struct hh_cache {
         struct hh_cache *hh_next;       /* Next entry                        */
@@ -530,6 +509,85 @@ struct netdev_queue {
         unsigned long           tx_dropped;
 } ____cacheline_aligned_in_smp;
 
+#ifdef CONFIG_RPS
+/*
+ * This structure holds an RPS map which can be of variable length.  The
+ * map is an array of CPUs.
+ */
+struct rps_map {
+        unsigned int len;
+        struct rcu_head rcu;
+        u16 cpus[0];
+};
+#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16)))
+
+/*
+ * The rps_dev_flow structure contains the mapping of a flow to a CPU and the
+ * tail pointer for that CPU's input queue at the time of last enqueue.
+ */
+struct rps_dev_flow {
+        u16 cpu;
+        u16 fill;
+        unsigned int last_qtail;
+};
+
+/*
+ * The rps_dev_flow_table structure contains a table of flow mappings.
+ */
+struct rps_dev_flow_table {
+        unsigned int mask;
+        struct rcu_head rcu;
+        struct work_struct free_work;
+        struct rps_dev_flow flows[0];
+};
+#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
+    (_num * sizeof(struct rps_dev_flow)))
+
+/*
+ * The rps_sock_flow_table contains mappings of flows to the last CPU
+ * on which they were processed by the application (set in recvmsg).
+ */
+struct rps_sock_flow_table {
+        unsigned int mask;
+        u16 ents[0];
+};
+#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
+    (_num * sizeof(u16)))
+
+#define RPS_NO_CPU 0xffff
+
+static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
+                                        u32 hash)
+{
+        if (table && hash) {
+                unsigned int cpu, index = hash & table->mask;
+
+                /* We only give a hint, preemption can change cpu under us */
+                cpu = raw_smp_processor_id();
+
+                if (table->ents[index] != cpu)
+                        table->ents[index] = cpu;
+        }
+}
+
+static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
+                                       u32 hash)
+{
+        if (table && hash)
+                table->ents[hash & table->mask] = RPS_NO_CPU;
+}
+
+extern struct rps_sock_flow_table *rps_sock_flow_table;
+
+/* This structure contains an instance of an RX queue. */
+struct netdev_rx_queue {
+        struct rps_map *rps_map;
+        struct rps_dev_flow_table *rps_flow_table;
+        struct kobject kobj;
+        struct netdev_rx_queue *first;
+        atomic_t count;
+} ____cacheline_aligned_in_smp;
+#endif /* CONFIG_RPS */
 
 /*
  * This structure defines the management hooks for network devices.
@@ -629,6 +687,9 @@ struct netdev_queue {
  * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate);
  * int (*ndo_get_vf_config)(struct net_device *dev,
  *                          int vf, struct ifla_vf_info *ivf);
+ * int (*ndo_set_vf_port)(struct net_device *dev, int vf,
+ *                        struct nlattr *port[]);
+ * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
  */
 #define HAVE_NET_DEVICE_OPS
 struct net_device_ops {
@@ -667,6 +728,7 @@ struct net_device_ops {
                                                         unsigned short vid);
 #ifdef CONFIG_NET_POLL_CONTROLLER
         void                    (*ndo_poll_controller)(struct net_device *dev);
+        void                    (*ndo_netpoll_cleanup)(struct net_device *dev);
 #endif
         int                     (*ndo_set_vf_mac)(struct net_device *dev,
                                                   int queue, u8 *mac);
@@ -677,6 +739,11 @@ struct net_device_ops {
         int                     (*ndo_get_vf_config)(struct net_device *dev,
                                                      int vf,
                                                      struct ifla_vf_info *ivf);
+        int                     (*ndo_set_vf_port)(struct net_device *dev,
+                                                   int vf,
+                                                   struct nlattr *port[]);
+        int                     (*ndo_get_vf_port)(struct net_device *dev,
+                                                   int vf, struct sk_buff *skb);
 #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
         int                     (*ndo_fcoe_enable)(struct net_device *dev);
         int                     (*ndo_fcoe_disable)(struct net_device *dev);
@@ -711,6 +778,9 @@ struct net_device {
          * the interface.
          */
         char                    name[IFNAMSIZ];
+
+        struct pm_qos_request_list *pm_qos_req;
+
         /* device name hash chain */
         struct hlist_node       name_hlist;
         /* snmp alias */
@@ -764,6 +834,7 @@ struct net_device {
 #define NETIF_F_SCTP_CSUM       (1 << 25) /* SCTP checksum offload */
 #define NETIF_F_FCOE_MTU        (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
 #define NETIF_F_NTUPLE          (1 << 27) /* N-tuple filters supported */
+#define NETIF_F_RXHASH          (1 << 28) /* Receive hashing offload */
 
         /* Segmentation offload features */
 #define NETIF_F_GSO_SHIFT       16
@@ -820,7 +891,7 @@ struct net_device {
         unsigned char           operstate; /* RFC2863 operstate */
         unsigned char           link_mode; /* mapping policy to operstate */
 
-        unsigned                mtu;    /* interface MTU value          */
+        unsigned int            mtu;    /* interface MTU value          */
         unsigned short          type;   /* interface hardware type      */
         unsigned short          hard_header_len;        /* hardware hdr length  */
 
@@ -840,12 +911,10 @@ struct net_device {
         unsigned char           addr_len;       /* hardware address length      */
         unsigned short          dev_id;         /* for shared network cards */
 
-        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   */
+        struct netdev_hw_addr_list      uc;     /* Unicast mac addresses */
+        struct netdev_hw_addr_list      mc;     /* Multicast mac addresses */
+        int                     uc_promisc;
         unsigned int            promiscuity;
         unsigned int            allmulti;
 
@@ -878,6 +947,15 @@ struct net_device {
 
         unsigned char           broadcast[MAX_ADDR_LEN];        /* hw bcast add */
 
+#ifdef CONFIG_RPS
+        struct kset             *queues_kset;
+
+        struct netdev_rx_queue  *_rx;
+
+        /* Number of RX queues allocated at alloc_netdev_mq() time  */
+        unsigned int            num_rx_queues;
+#endif
+
         struct netdev_queue     rx_queue;
 
         struct netdev_queue     *_tx ____cacheline_aligned_in_smp;
@@ -1306,19 +1384,44 @@ static inline int unregister_gifconf(unsigned int family)
 }
 
 /*
- * Incoming packets are placed on per-cpu queues so that
- * no locking is needed.
+ * Incoming packets are placed on per-cpu queues
  */
 struct softnet_data {
         struct Qdisc            *output_queue;
-        struct sk_buff_head     input_pkt_queue;
+        struct Qdisc            **output_queue_tailp;
         struct list_head        poll_list;
         struct sk_buff          *completion_queue;
-
+        struct sk_buff_head     process_queue;
+
+        /* stats */
+        unsigned int            processed;
+        unsigned int            time_squeeze;
+        unsigned int            cpu_collision;
+        unsigned int            received_rps;
+
+#ifdef CONFIG_RPS
+        struct softnet_data     *rps_ipi_list;
+
+        /* Elements below can be accessed between CPUs for RPS */
+        struct call_single_data csd ____cacheline_aligned_in_smp;
+        struct softnet_data     *rps_ipi_next;
+        unsigned int            cpu;
+        unsigned int            input_queue_head;
+#endif
+        unsigned                dropped;
+        struct sk_buff_head     input_pkt_queue;
         struct napi_struct      backlog;
 };
 
-DECLARE_PER_CPU(struct softnet_data,softnet_data);
+static inline void input_queue_head_add(struct softnet_data *sd,
+                                        unsigned int len)
+{
+#ifdef CONFIG_RPS
+        sd->input_queue_head += len;
+#endif
+}
+
+DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
 #define HAVE_NETIF_QUEUE
 
@@ -1945,6 +2048,22 @@ extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
 extern int              register_netdev(struct net_device *dev);
 extern void             unregister_netdev(struct net_device *dev);
 
+/* General hardware address lists handling functions */
+extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
+                                  struct netdev_hw_addr_list *from_list,
+                                  int addr_len, unsigned char addr_type);
+extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
+                                   struct netdev_hw_addr_list *from_list,
+                                   int addr_len, unsigned char addr_type);
+extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
+                          struct netdev_hw_addr_list *from_list,
+                          int addr_len);
+extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
+                             struct netdev_hw_addr_list *from_list,
+                             int addr_len);
+extern void __hw_addr_flush(struct netdev_hw_addr_list *list);
+extern void __hw_addr_init(struct netdev_hw_addr_list *list);
+
 /* Functions used for device addresses handling */
 extern int dev_addr_add(struct net_device *dev, unsigned char *addr,
                         unsigned char addr_type);
@@ -1956,26 +2075,34 @@ extern int dev_addr_add_multiple(struct net_device *to_dev,
 extern int dev_addr_del_multiple(struct net_device *to_dev,
                                  struct net_device *from_dev,
                                  unsigned char addr_type);
+extern void dev_addr_flush(struct net_device *dev);
+extern int dev_addr_init(struct net_device *dev);
+
+/* Functions used for unicast addresses handling */
+extern int dev_uc_add(struct net_device *dev, unsigned char *addr);
+extern int dev_uc_del(struct net_device *dev, unsigned char *addr);
+extern int dev_uc_sync(struct net_device *to, struct net_device *from);
+extern void dev_uc_unsync(struct net_device *to, struct net_device *from);
+extern void dev_uc_flush(struct net_device *dev);
+extern void dev_uc_init(struct net_device *dev);
+
+/* Functions used for multicast addresses handling */
+extern int dev_mc_add(struct net_device *dev, unsigned char *addr);
+extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr);
+extern int dev_mc_del(struct net_device *dev, unsigned char *addr);
+extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr);
+extern int dev_mc_sync(struct net_device *to, struct net_device *from);
+extern void dev_mc_unsync(struct net_device *to, struct net_device *from);
+extern void dev_mc_flush(struct net_device *dev);
+extern void dev_mc_init(struct net_device *dev);
 
 /* 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);
-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_mc_add(struct net_device *dev, void *addr, int alen, int newonly);
-extern int              dev_mc_sync(struct net_device *to, struct net_device *from);
-extern void             dev_mc_unsync(struct net_device *to, struct net_device *from);
-extern int              __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all);
-extern int              __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly);
-extern int              __dev_addr_sync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count);
-extern void             __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count);
 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 int              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 */
@@ -1985,6 +2112,7 @@ extern const struct net_device_stats *dev_get_stats(struct net_device *dev);
 extern void             dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats);
 
 extern int              netdev_max_backlog;
+extern int              netdev_tstamp_prequeue;
 extern int              weight_p;
 extern int              netdev_set_master(struct net_device *dev, struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb);
@@ -2045,54 +2173,14 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
         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;
+extern int __skb_bond_should_drop(struct sk_buff *skb,
+                                  struct net_device *master);
 
-                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.
- */
 static inline int skb_bond_should_drop(struct sk_buff *skb,
                                        struct net_device *master)
 {
-        if (master) {
-                struct net_device *dev = skb->dev;
-
-                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))
-                                return 0;
-
-                        if (master->priv_flags & IFF_MASTER_ALB) {
-                                if (skb->pkt_type != PACKET_BROADCAST &&
-                                    skb->pkt_type != PACKET_MULTICAST)
-                                        return 0;
-                        }
-                        if (master->priv_flags & IFF_MASTER_8023AD &&
-                            skb->protocol == __cpu_to_be16(ETH_P_SLOW))
-                                return 0;
-
-                        return 1;
-                }
-        }
+        if (master)
+                return __skb_bond_should_drop(skb, master);
         return 0;
 }