diff options
Diffstat (limited to 'include/net/dst.h')
| -rw-r--r-- | include/net/dst.h | 117 |
1 files changed, 77 insertions, 40 deletions
diff --git a/include/net/dst.h b/include/net/dst.h index 8ea8812b0b41..78c78cdce0e9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -16,8 +16,10 @@ #include <linux/bug.h> #include <linux/jiffies.h> #include <linux/refcount.h> +#include <linux/rcuref.h> #include <net/neighbour.h> #include <asm/processor.h> +#include <linux/indirect_call_wrapper.h> struct sk_buff; @@ -60,21 +62,35 @@ struct dst_entry { unsigned short trailer_len; /* space to reserve at tail */ /* - * __refcnt wants to be on a different cache line from + * __rcuref wants to be on a different cache line from * input/output/ops or performance tanks badly */ #ifdef CONFIG_64BIT - atomic_t __refcnt; /* 64-bit offset 64 */ + rcuref_t __rcuref; /* 64-bit offset 64 */ #endif int __use; unsigned long lastuse; - struct lwtunnel_state *lwtstate; struct rcu_head rcu_head; short error; short __pad; __u32 tclassid; #ifndef CONFIG_64BIT - atomic_t __refcnt; /* 32-bit offset 64 */ + struct lwtunnel_state *lwtstate; + rcuref_t __rcuref; /* 32-bit offset 64 */ +#endif + netdevice_tracker dev_tracker; + + /* + * Used by rtable and rt6_info. Moves lwtstate into the next cache + * line on 64bit so that lwtstate does not cause false sharing with + * __rcuref under contention of __rcuref. This also puts the + * frequently accessed members of rtable and rt6_info out of the + * __rcuref cache line. + */ + struct list_head rt_uncached; + struct uncached_list *rt_uncached_list; +#ifdef CONFIG_64BIT + struct lwtunnel_state *lwtstate; #endif }; @@ -193,9 +209,11 @@ dst_feature(const struct dst_entry *dst, u32 feature) return dst_metric(dst, RTAX_FEATURES) & feature; } +INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); +INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); static inline u32 dst_mtu(const struct dst_entry *dst) { - return dst->ops->mtu(dst); + return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ @@ -204,13 +222,6 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr return msecs_to_jiffies(dst_metric(dst, metric)); } -static inline u32 -dst_allfrag(const struct dst_entry *dst) -{ - int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - return ret; -} - static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { @@ -221,10 +232,10 @@ static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check - * the placement of __refcnt in struct dst_entry + * the placement of __rcuref in struct dst_entry */ - BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); - WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); + BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63); + WARN_ON(!rcuref_get(&dst->__rcuref)); } static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) @@ -235,12 +246,6 @@ static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) } } -static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time) -{ - dst_hold(dst); - dst_use_noref(dst, time); -} - static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) @@ -274,6 +279,7 @@ static inline void skb_dst_drop(struct sk_buff *skb) static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { + nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); @@ -293,7 +299,7 @@ static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb */ static inline bool dst_hold_safe(struct dst_entry *dst) { - return atomic_inc_not_zero(&dst->__refcnt); + return rcuref_get(&dst->__rcuref); } /** @@ -301,7 +307,7 @@ static inline bool dst_hold_safe(struct dst_entry *dst) * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. - * Returns true if dst is refcounted. + * Returns: true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { @@ -313,6 +319,7 @@ static inline bool skb_dst_force(struct sk_buff *skb) dst = NULL; skb->_skb_refdst = (unsigned long)dst; + skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; @@ -334,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ @@ -356,9 +363,8 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { - /* TODO : stats should be SMP safe */ - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + DEV_STATS_INC(dev, rx_packets); + DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } @@ -379,12 +385,11 @@ static inline int dst_discard(struct sk_buff *skb) { return dst_discard_out(&init_net, skb->sk, skb); } -void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags); void dst_init(struct dst_entry *dst, struct dst_ops *ops, - struct net_device *dev, int initial_ref, int initial_obsolete, + struct net_device *dev, int initial_obsolete, unsigned short flags); -struct dst_entry *dst_destroy(struct dst_entry *dst); void dst_dev_put(struct dst_entry *dst); static inline void dst_confirm(struct dst_entry *dst) @@ -400,14 +405,12 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - struct neighbour *n = NULL; + struct neighbour *n; - /* The packets from tunnel devices (eg bareudp) may have only - * metadata in the dst pointer of skb. Hence a pointer check of - * neigh_lookup is needed. - */ - if (dst->ops->neigh_lookup) - n = dst->ops->neigh_lookup(dst, skb, NULL); + if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) + return NULL; + + n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } @@ -437,22 +440,45 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) dst->expires = expires; } +static inline unsigned int dst_dev_overhead(struct dst_entry *dst, + struct sk_buff *skb) +{ + if (likely(dst)) + return LL_RESERVED_SPACE(dst->dev); + + return skb->mac_len; +} + +INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, + struct sk_buff *)); /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return skb_dst(skb)->output(net, sk, skb); + return INDIRECT_CALL_INET(skb_dst(skb)->output, + ip6_output, ip_output, + net, sk, skb); } +INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { - return skb_dst(skb)->input(skb); + return INDIRECT_CALL_INET(skb_dst(skb)->input, + ip6_input, ip_local_deliver, skb); } +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, + u32)); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { if (dst->obsolete) - dst = dst->ops->check(dst, cookie); + dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, + ipv4_dst_check, dst, cookie); return dst; } @@ -535,4 +561,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, bool confirm_neigh); +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); +unsigned int dst_blackhole_mtu(const struct dst_entry *dst); + #endif /* _NET_DST_H */ |