diff --git a/include/net/dst.h b/include/net/dst.h index d67fda89cd0f..78884429deed 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -61,23 +62,36 @@ 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 }; struct dst_metrics { @@ -225,10 +239,10 @@ 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) @@ -292,7 +306,7 @@ 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); } /** diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6268963d9599..79570cb4ea9c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -217,9 +217,6 @@ struct rt6_info { struct inet6_dev *rt6i_idev; u32 rt6i_flags; - struct list_head rt6i_uncached; - struct uncached_list *rt6i_uncached_list; - /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; }; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 81ee387a1fc4..3556595ce59a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -100,7 +100,7 @@ static inline struct dst_entry *ip6_route_output(struct net *net, static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) { if (!(flags & RT6_LOOKUP_F_DST_NOREF) || - !list_empty(&rt->rt6i_uncached)) + !list_empty(&rt->dst.rt_uncached)) ip6_rt_put(rt); } diff --git a/include/net/route.h b/include/net/route.h index fe00b0a2e475..bcc367cf3aa2 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -78,9 +78,6 @@ struct rtable { /* Miscellaneous cached information */ u32 rt_mtu_locked:1, rt_pmtu:31; - - struct list_head rt_uncached; - struct uncached_list *rt_uncached_list; }; static inline bool rt_is_input_route(const struct rtable *rt) diff --git a/include/net/sock.h b/include/net/sock.h index 573f2bf7e0de..5edf0038867c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2131,7 +2131,7 @@ sk_dst_get(struct sock *sk) rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); - if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + if (dst && !rcuref_get(&dst->__rcuref)) dst = NULL; rcu_read_unlock(); return dst; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 8c69f0c95a8e..98aea5485aae 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -73,7 +73,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; - atomic_set(&rt->dst.__refcnt, 1); + rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; diff --git a/net/core/dst.c b/net/core/dst.c index 31c08a3386d3..3247e84045ca 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -66,7 +66,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->tclassid = 0; #endif dst->lwtstate = NULL; - atomic_set(&dst->__refcnt, initial_ref); + rcuref_init(&dst->__rcuref, initial_ref); dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; @@ -162,31 +162,15 @@ EXPORT_SYMBOL(dst_dev_put); void dst_release(struct dst_entry *dst) { - if (dst) { - int newrefcnt; - - newrefcnt = atomic_dec_return(&dst->__refcnt); - if (WARN_ONCE(newrefcnt < 0, "dst_release underflow")) - net_warn_ratelimited("%s: dst:%p refcnt:%d\n", - __func__, dst, newrefcnt); - if (!newrefcnt) - call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); - } + if (dst && rcuref_put(&dst->__rcuref)) + call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } EXPORT_SYMBOL(dst_release); void dst_release_immediate(struct dst_entry *dst) { - if (dst) { - int newrefcnt; - - newrefcnt = atomic_dec_return(&dst->__refcnt); - if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow")) - net_warn_ratelimited("%s: dst:%p refcnt:%d\n", - __func__, dst, newrefcnt); - if (!newrefcnt) - dst_destroy(dst); - } + if (dst && rcuref_put(&dst->__rcuref)) + dst_destroy(dst); } EXPORT_SYMBOL(dst_release_immediate); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b7b1661d0d56..906aebdc566b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -843,7 +843,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, if (dst) { ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); ci.rta_used = dst->__use; - ci.rta_clntref = atomic_read(&dst->__refcnt); + ci.rta_clntref = rcuref_read(&dst->__rcuref); } if (expires) { unsigned long clock; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a0a0bb452e9..2a3d14d95ada 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1508,20 +1508,20 @@ void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); - rt->rt_uncached_list = ul; + rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); - list_add_tail(&rt->rt_uncached, &ul->head); + list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { - if (!list_empty(&rt->rt_uncached)) { - struct uncached_list *ul = rt->rt_uncached_list; + if (!list_empty(&rt->dst.rt_uncached)) { + struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); - list_del_init(&rt->rt_uncached); + list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } @@ -1546,13 +1546,13 @@ void rt_flush_dev(struct net_device *dev) continue; spin_lock_bh(&ul->lock); - list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) { + list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); - list_move(&rt->rt_uncached, &ul->quarantine); + list_move(&rt->dst.rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); } @@ -1644,7 +1644,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; - INIT_LIST_HEAD(&rt->rt_uncached); + INIT_LIST_HEAD(&rt->dst.rt_uncached); rt->dst.output = ip_output; if (flags & RTCF_LOCAL) @@ -1675,7 +1675,7 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; - INIT_LIST_HEAD(&new_rt->rt_uncached); + INIT_LIST_HEAD(&new_rt->dst.rt_uncached); new_rt->dst.input = rt->dst.input; new_rt->dst.output = rt->dst.output; @@ -2859,7 +2859,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; - INIT_LIST_HEAD(&rt->rt_uncached); + INIT_LIST_HEAD(&rt->dst.rt_uncached); } dst_release(dst_orig); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 3d0dfa6cf9f9..47861c8b7340 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -91,7 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gw6 = rt->rt_gw6; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; - INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + INIT_LIST_HEAD(&xdst->u.rt.dst.rt_uncached); rt_add_uncached_list(&xdst->u.rt); return 0; @@ -121,7 +121,7 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - if (xdst->u.rt.rt_uncached_list) + if (xdst->u.rt.dst.rt_uncached_list) rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 244df77fac87..35085fc0cf15 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -139,20 +139,20 @@ void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); - rt->rt6i_uncached_list = ul; + rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); - list_add_tail(&rt->rt6i_uncached, &ul->head); + list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { - if (!list_empty(&rt->rt6i_uncached)) { - struct uncached_list *ul = rt->rt6i_uncached_list; + if (!list_empty(&rt->dst.rt_uncached)) { + struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); - list_del_init(&rt->rt6i_uncached); + list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } @@ -169,7 +169,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) continue; spin_lock_bh(&ul->lock); - list_for_each_entry_safe(rt, safe, &ul->head, rt6i_uncached) { + list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; @@ -188,7 +188,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) handled = true; } if (handled) - list_move(&rt->rt6i_uncached, + list_move(&rt->dst.rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); @@ -293,7 +293,7 @@ static const struct fib6_info fib6_null_entry_template = { static const struct rt6_info ip6_null_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, @@ -307,7 +307,7 @@ static const struct rt6_info ip6_null_entry_template = { static const struct rt6_info ip6_prohibit_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, @@ -319,7 +319,7 @@ static const struct rt6_info ip6_prohibit_entry_template = { static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, @@ -334,7 +334,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); - INIT_LIST_HEAD(&rt->rt6i_uncached); + INIT_LIST_HEAD(&rt->dst.rt_uncached); } /* allocate dst with ip6_dst_ops */ @@ -2638,7 +2638,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = (struct rt6_info *)dst; /* For dst cached in uncached_list, refcnt is already taken. */ - if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) { + if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } @@ -2748,7 +2748,7 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || - unlikely(!list_empty(&rt->rt6i_uncached)))) + unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); @@ -6477,7 +6477,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); - INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->rt6i_uncached); + INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; @@ -6489,7 +6489,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); - INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->rt6i_uncached); + INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -6499,7 +6499,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); - INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached); + INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index ea435eba3053..2b493f8d0091 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -89,7 +89,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; - INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + INIT_LIST_HEAD(&xdst->u.rt6.dst.rt_uncached); rt6_uncached_list_add(&xdst->u.rt6); return 0; @@ -121,7 +121,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (xdst->u.rt6.rt6i_uncached_list) + if (xdst->u.rt6.dst.rt_uncached_list) rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 80448885c3d7..99c349c0d968 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -339,7 +339,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n", &dest->addr.ip, &dest_dst->dst_saddr.ip, - atomic_read(&rt->dst.__refcnt)); + rcuref_read(&rt->dst.__rcuref)); } if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.ip; @@ -507,7 +507,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", &dest->addr.in6, &dest_dst->dst_saddr.in6, - atomic_read(&rt->dst.__refcnt)); + rcuref_read(&rt->dst.__rcuref)); } if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.in6;