1 files changed, 131 insertions, 41 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c31f74d76ebd..5897b4ea5a3f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -51,6 +51,7 @@
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
 #include <uapi/linux/netdevice.h>
+#include <uapi/linux/if_bonding.h>
 
 struct netpoll_info;
 struct device;
@@ -643,39 +644,40 @@ struct rps_dev_flow_table {
 /*
  * The rps_sock_flow_table contains mappings of flows to the last CPU
  * on which they were processed by the application (set in recvmsg).
+ * Each entry is a 32bit value. Upper part is the high order bits
+ * of flow hash, lower part is cpu number.
+ * rps_cpu_mask is used to partition the space, depending on number of
+ * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
+ * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f,
+ * meaning we use 32-6=26 bits for the hash.
  */
 struct rps_sock_flow_table {
-        unsigned int mask;
-        u16 ents[0];
+        u32     mask;
+
+        u32     ents[0] ____cacheline_aligned_in_smp;
 };
-#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
-    ((_num) * sizeof(u16)))
+#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
 
 #define RPS_NO_CPU 0xffff
 
+extern u32 rps_cpu_mask;
+extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
+
 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;
+                unsigned int index = hash & table->mask;
+                u32 val = hash & ~rps_cpu_mask;
 
                 /* We only give a hint, preemption can change cpu under us */
-                cpu = raw_smp_processor_id();
+                val |= raw_smp_processor_id();
 
-                if (table->ents[index] != cpu)
-                        table->ents[index] = cpu;
+                if (table->ents[index] != val)
+                        table->ents[index] = val;
         }
 }
 
-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 __rcu *rps_sock_flow_table;
-
 #ifdef CONFIG_RFS_ACCEL
 bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
                          u16 filter_id);
@@ -852,11 +854,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *      3. Update dev->stats asynchronously and atomically, and define
  *         neither operation.
  *
- * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid);
+ * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
  *      If device support VLAN filtering this function is called when a
  *      VLAN id is registered.
  *
- * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
  *      If device support VLAN filtering this function is called when a
  *      VLAN id is unregistered.
  *
@@ -1012,12 +1014,15 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *      Callback to use for xmit over the accelerated station. This
  *      is used in place of ndo_start_xmit on accelerated net
  *      devices.
- * bool (*ndo_gso_check) (struct sk_buff *skb,
- *                        struct net_device *dev);
+ * netdev_features_t (*ndo_features_check) (struct sk_buff *skb,
+ *                                          struct net_device *dev
+ *                                          netdev_features_t features);
  *      Called by core transmit path to determine if device is capable of
- *      performing GSO on a packet. The device returns true if it is
- *      able to GSO the packet, false otherwise. If the return value is
- *      false the stack will do software GSO.
+ *      performing offload operations on a given packet. This is to give
+ *      the device an opportunity to implement any restrictions that cannot
+ *      be otherwise expressed by feature flags. The check is called with
+ *      the set of features that the stack has calculated and it returns
+ *      those the driver believes to be appropriate.
  *
  * int (*ndo_switch_parent_id_get)(struct net_device *dev,
  *                                 struct netdev_phys_item_id *psid);
@@ -1151,13 +1156,15 @@ struct net_device_ops {
                                                 int idx);
 
         int                     (*ndo_bridge_setlink)(struct net_device *dev,
-                                                      struct nlmsghdr *nlh);
+                                                      struct nlmsghdr *nlh,
+                                                      u16 flags);
         int                     (*ndo_bridge_getlink)(struct sk_buff *skb,
                                                       u32 pid, u32 seq,
                                                       struct net_device *dev,
                                                       u32 filter_mask);
         int                     (*ndo_bridge_dellink)(struct net_device *dev,
-                                                      struct nlmsghdr *nlh);
+                                                      struct nlmsghdr *nlh,
+                                                      u16 flags);
         int                     (*ndo_change_carrier)(struct net_device *dev,
                                                       bool new_carrier);
         int                     (*ndo_get_phys_port_id)(struct net_device *dev,
@@ -1178,8 +1185,9 @@ struct net_device_ops {
                                                         struct net_device *dev,
                                                         void *priv);
         int                     (*ndo_get_lock_subclass)(struct net_device *dev);
-        bool                    (*ndo_gso_check) (struct sk_buff *skb,
-                                                  struct net_device *dev);
+        netdev_features_t       (*ndo_features_check) (struct sk_buff *skb,
+                                                       struct net_device *dev,
+                                                       netdev_features_t features);
 #ifdef CONFIG_NET_SWITCHDEV
         int                     (*ndo_switch_parent_id_get)(struct net_device *dev,
                                                             struct netdev_phys_item_id *psid);
@@ -1510,6 +1518,8 @@ struct net_device {
         struct list_head        napi_list;
         struct list_head        unreg_list;
         struct list_head        close_list;
+        struct list_head        ptype_all;
+        struct list_head        ptype_specific;
 
         struct {
                 struct list_head upper;
@@ -1913,13 +1923,8 @@ struct napi_gro_cb {
         /* Number of segments aggregated. */
         u16     count;
 
-        /* This is non-zero if the packet may be of the same flow. */
-        u8      same_flow;
-
-        /* Free the skb? */
-        u8      free;
-#define NAPI_GRO_FREE             1
-#define NAPI_GRO_FREE_STOLEN_HEAD 2
+        /* Start offset for remote checksum offload */
+        u16     gro_remcsum_start;
 
         /* jiffies when first packet was created/queued */
         unsigned long age;
@@ -1927,6 +1932,9 @@ struct napi_gro_cb {
         /* Used in ipv6_gro_receive() and foo-over-udp */
         u16     proto;
 
+        /* This is non-zero if the packet may be of the same flow. */
+        u8      same_flow:1;
+
         /* Used in udp_gro_receive */
         u8      udp_mark:1;
 
@@ -1936,9 +1944,16 @@ struct napi_gro_cb {
         /* Number of checksums via CHECKSUM_UNNECESSARY */
         u8      csum_cnt:3;
 
+        /* Free the skb? */
+        u8      free:2;
+#define NAPI_GRO_FREE             1
+#define NAPI_GRO_FREE_STOLEN_HEAD 2
+
         /* Used in foo-over-udp, set in udp[46]_gro_receive */
         u8      is_ipv6:1;
 
+        /* 7 bit hole */
+
         /* used to support CHECKSUM_COMPLETE for tunneling protocols */
         __wsum  csum;
 
@@ -1965,7 +1980,7 @@ struct offload_callbacks {
         struct sk_buff          *(*gso_segment)(struct sk_buff *skb,
                                                 netdev_features_t features);
         struct sk_buff          **(*gro_receive)(struct sk_buff **head,
-                                               struct sk_buff *skb);
+                                                 struct sk_buff *skb);
         int                     (*gro_complete)(struct sk_buff *skb, int nhoff);
 };
 
@@ -1975,10 +1990,21 @@ struct packet_offload {
         struct list_head         list;
 };
 
+struct udp_offload;
+
+struct udp_offload_callbacks {
+        struct sk_buff          **(*gro_receive)(struct sk_buff **head,
+                                                 struct sk_buff *skb,
+                                                 struct udp_offload *uoff);
+        int                     (*gro_complete)(struct sk_buff *skb,
+                                                int nhoff,
+                                                struct udp_offload *uoff);
+};
+
 struct udp_offload {
         __be16                   port;
         u8                       ipproto;
-        struct offload_callbacks callbacks;
+        struct udp_offload_callbacks callbacks;
 };
 
 /* often modified stats are per cpu, other are shared (netdev->stats) */
@@ -2037,6 +2063,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_RESEND_IGMP      0x0016
 #define NETDEV_PRECHANGEMTU     0x0017 /* notify before mtu change happened */
 #define NETDEV_CHANGEINFODATA   0x0018
+#define NETDEV_BONDING_INFO     0x0019
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2081,7 +2108,7 @@ extern rwlock_t				dev_base_lock;		/* Device list lock */
         list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_in_bond_rcu(bond, slave)        \
                 for_each_netdev_rcu(&init_net, slave)   \
-                        if (netdev_master_upper_dev_get_rcu(slave) == bond)
+                        if (netdev_master_upper_dev_get_rcu(slave) == (bond))
 #define net_device_entry(lh)    list_entry(lh, struct net_device, dev_list)
 
 static inline struct net_device *next_net_device(struct net_device *dev)
@@ -2220,11 +2247,20 @@ static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
 
 __sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
 
+static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
+{
+        return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) ==
+                skb_gro_offset(skb));
+}
+
 static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
                                                       bool zero_okay,
                                                       __sum16 check)
 {
-        return (skb->ip_summed != CHECKSUM_PARTIAL &&
+        return ((skb->ip_summed != CHECKSUM_PARTIAL ||
+                skb_checksum_start_offset(skb) <
+                 skb_gro_offset(skb)) &&
+                !skb_at_gro_remcsum_start(skb) &&
                 NAPI_GRO_CB(skb)->csum_cnt == 0 &&
                 (!zero_okay || check));
 }
@@ -2299,6 +2335,49 @@ do {									\
                                            compute_pseudo(skb, proto)); \
 } while (0)
 
+struct gro_remcsum {
+        int offset;
+        __wsum delta;
+};
+
+static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
+{
+        grc->delta = 0;
+}
+
+static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
+                                           int start, int offset,
+                                           struct gro_remcsum *grc,
+                                           bool nopartial)
+{
+        __wsum delta;
+
+        BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
+
+        if (!nopartial) {
+                NAPI_GRO_CB(skb)->gro_remcsum_start =
+                    ((unsigned char *)ptr + start) - skb->head;
+                return;
+        }
+
+        delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);
+
+        /* Adjust skb->csum since we changed the packet */
+        NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+        grc->offset = (ptr + offset) - (void *)skb->head;
+        grc->delta = delta;
+}
+
+static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
+                                           struct gro_remcsum *grc)
+{
+        if (!grc->delta)
+                return;
+
+        remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta);
+}
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
                                   unsigned short type,
                                   const void *daddr, const void *saddr,
@@ -3460,6 +3539,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
                                     netdev_features_t features);
 
+struct netdev_bonding_info {
+        ifslave slave;
+        ifbond  master;
+};
+
+struct netdev_notifier_bonding_info {
+        struct netdev_notifier_info info; /* must be first */
+        struct netdev_bonding_info  bonding_info;
+};
+
+void netdev_bonding_info_change(struct net_device *dev,
+                                struct netdev_bonding_info *bonding_info);
+
 static inline
 struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
 {
@@ -3611,8 +3703,6 @@ static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
                                    netdev_features_t features)
 {
         return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
-                (dev->netdev_ops->ndo_gso_check &&
-                 !dev->netdev_ops->ndo_gso_check(skb, dev)) ||
                 unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
                          (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }