From 84b114b98452c431299d99c135f751659e517acb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 May 2017 06:56:54 -0700 Subject: tcp: randomize timestamps on syncookies Whole point of randomization was to hide server uptime, but an attacker can simply start a syn flood and TCP generates 'old style' timestamps, directly revealing server jiffies value. Also, TSval sent by the server to a particular remote address vary depending on syncookies being sent or not, potentially triggering PAWS drops for innocent clients. Lets implement proper randomization, including for SYNcookies. Also we do not need to export sysctl_tcp_timestamps, since it is not used from a module. In v2, I added Florian feedback and contribution, adding tsoff to tcp_get_cookie_sock(). v3 removed one unused variable in tcp_v4_connect() as Florian spotted. Fixes: 95a22caee396c ("tcp: randomize tcp timestamp offsets for each connection") Signed-off-by: Eric Dumazet Reviewed-by: Florian Westphal Tested-by: Florian Westphal Cc: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/secure_seq.h | 10 ++++++---- include/net/tcp.h | 5 +++-- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index fe236b3429f0..b94006f6fbdd 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -6,10 +6,12 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, u32 *tsoff); -u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff); +u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); +u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr); +u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport); +u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, diff --git a/include/net/tcp.h b/include/net/tcp.h index 270e5cc43c99..8c0e5a901d64 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -470,7 +470,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst); + struct dst_entry *dst, u32 tsoff); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); @@ -1822,7 +1822,8 @@ struct tcp_request_sock_ops { #endif struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req); - __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff); + u32 (*init_seq)(const struct sk_buff *skb); + u32 (*init_ts_off)(const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, -- cgit v1.2.3 From 2f242bf45370b8ea44f209b22c3c90984655a102 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 5 May 2017 11:53:19 +0200 Subject: mac80211: properly remove RX_ENC_FLAG_40MHZ Somehow I missed this in my RX rate cleanup series, causing some drivers to not report correct bandwidth since this flag isn't used by mac80211 anymore. Fix this, and make hwsim also report higher bandwidths appropriately. Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath9k/ar9003_mac.c | 2 +- drivers/net/wireless/ath/ath9k/mac.c | 4 ++-- drivers/net/wireless/intel/iwlegacy/4965-mac.c | 4 +++- drivers/net/wireless/intel/iwlwifi/dvm/rx.c | 4 +++- drivers/net/wireless/mac80211_hwsim.c | 8 +++++++- include/net/mac80211.h | 2 -- 6 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c index 68fcbe03bce2..b3f20b3c0210 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c @@ -522,7 +522,7 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, rxs->rs_moreaggr = (rxsp->status11 & AR_RxMoreAggr) ? 1 : 0; rxs->rs_antenna = (MS(rxsp->status4, AR_RxAntenna) & 0x7); rxs->enc_flags |= (rxsp->status4 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0; - rxs->enc_flags |= (rxsp->status4 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0; + rxs->bw = (rxsp->status4 & AR_2040) ? RATE_INFO_BW_40 : RATE_INFO_BW_20; rxs->evm0 = rxsp->status6; rxs->evm1 = rxsp->status7; diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 6128c2bb23d8..77c94f9e7b61 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -580,8 +580,8 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds, /* directly mapped flags for ieee80211_rx_status */ rs->enc_flags |= (ads.ds_rxstatus3 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0; - rs->enc_flags |= - (ads.ds_rxstatus3 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0; + rs->bw = (ads.ds_rxstatus3 & AR_2040) ? RATE_INFO_BW_40 : + RATE_INFO_BW_20; if (AR_SREV_9280_20_OR_LATER(ah)) rs->enc_flags |= (ads.ds_rxstatus3 & AR_STBC) ? diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index 5d5faa3cad24..49a2ff15ddae 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -734,7 +734,9 @@ il4965_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb) if (rate_n_flags & RATE_MCS_HT_MSK) rx_status.encoding = RX_ENC_HT; if (rate_n_flags & RATE_MCS_HT40_MSK) - rx_status.enc_flags |= RX_ENC_FLAG_40MHZ; + rx_status.bw = RATE_INFO_BW_40; + else + rx_status.bw = RATE_INFO_BW_20; if (rate_n_flags & RATE_MCS_SGI_MSK) rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI; diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c index 1ee1ba9931a7..adfd6307edca 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c @@ -889,7 +889,9 @@ static void iwlagn_rx_reply_rx(struct iwl_priv *priv, if (rate_n_flags & RATE_MCS_HT_MSK) rx_status.encoding = RX_ENC_HT; if (rate_n_flags & RATE_MCS_HT40_MSK) - rx_status.enc_flags |= RX_ENC_FLAG_40MHZ; + rx_status.bw = RATE_INFO_BW_40; + else + rx_status.bw = RATE_INFO_BW_20; if (rate_n_flags & RATE_MCS_SGI_MSK) rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI; if (rate_n_flags & RATE_MCS_GF_MSK) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 87444af20fc5..002b25cff5b6 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1201,7 +1201,13 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw, rx_status.encoding = RX_ENC_HT; } if (info->control.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) - rx_status.enc_flags |= RX_ENC_FLAG_40MHZ; + rx_status.bw = RATE_INFO_BW_40; + else if (info->control.rates[0].flags & IEEE80211_TX_RC_80_MHZ_WIDTH) + rx_status.bw = RATE_INFO_BW_80; + else if (info->control.rates[0].flags & IEEE80211_TX_RC_160_MHZ_WIDTH) + rx_status.bw = RATE_INFO_BW_160; + else + rx_status.bw = RATE_INFO_BW_20; if (info->control.rates[0].flags & IEEE80211_TX_RC_SHORT_GI) rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI; /* TODO: simulate real signal strength (and optional packet loss) */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4d05a9443344..76ed24a201eb 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1141,7 +1141,6 @@ enum mac80211_rx_flags { * enum mac80211_rx_encoding_flags - MCS & bandwidth flags * * @RX_ENC_FLAG_SHORTPRE: Short preamble was used for this frame - * @RX_ENC_FLAG_40MHZ: HT40 (40 MHz) was used * @RX_ENC_FLAG_SHORT_GI: Short guard interval was used * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, * if the driver fills this value it should add @@ -1153,7 +1152,6 @@ enum mac80211_rx_flags { */ enum mac80211_rx_encoding_flags { RX_ENC_FLAG_SHORTPRE = BIT(0), - RX_ENC_FLAG_40MHZ = BIT(1), RX_ENC_FLAG_SHORT_GI = BIT(2), RX_ENC_FLAG_HT_GF = BIT(3), RX_ENC_FLAG_STBC_MASK = BIT(4) | BIT(5), -- cgit v1.2.3 From 6406c91943a0f29b6e8786921aaa038663e08055 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 2 May 2017 09:33:40 +0200 Subject: cfg80211: fix multi scheduled scan kernel-doc Replace @results_wk with @report_results, which was missed in an earlier patch between revisions thereof. Fixes: b34939b98369 ("cfg80211: add request id to cfg80211_sched_scan_*() api") Signed-off-by: Johannes Berg Acked-by: Arend van Spriel Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 15d6599b8bc6..b083e6cbae8c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1666,7 +1666,7 @@ struct cfg80211_bss_select_adjust { * (others are filtered out). * If ommited, all results are passed. * @n_match_sets: number of match sets - * @results_wk: worker for processing results notification. + * @report_results: indicates that results were reported for this request * @wiphy: the wiphy this was for * @dev: the interface * @scan_start: start time of the scheduled scan -- cgit v1.2.3 From 82486aa6f1b9bc8145e6d0fa2bc0b44307f3b875 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 4 May 2017 14:54:17 -0700 Subject: ipv4: restore rt->fi for reference counting IPv4 dst could use fi->fib_metrics to store metrics but fib_info itself is refcnt'ed, so without taking a refcnt fi and fi->fib_metrics could be freed while dst metrics still points to it. This triggers use-after-free as reported by Andrey twice. This patch reverts commit 2860583fe840 ("ipv4: Kill rt->fi") to restore this reference counting. It is a quick fix for -net and -stable, for -net-next, as Eric suggested, we can consider doing reference counting for metrics itself instead of relying on fib_info. IPv6 is very different, it copies or steals the metrics from mx6_config in fib6_commit_metrics() so probably doesn't need a refcnt. Decnet has already done the refcnt'ing, see dn_fib_semantic_match(). Fixes: 2860583fe840 ("ipv4: Kill rt->fi") Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Signed-off-by: Cong Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/route.h | 1 + net/ipv4/route.c | 18 +++++++++++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 2cc0e14c6359..4335eb72a04c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -69,6 +69,7 @@ struct rtable { struct list_head rt_uncached; struct uncached_list *rt_uncached_list; + struct fib_info *fi; /* for refcnt to shared metrics */ }; static inline bool rt_is_input_route(const struct rtable *rt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 655d9eebe43e..f647310f8e4d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1387,6 +1387,11 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; + if (rt->fi) { + fib_info_put(rt->fi); + rt->fi = NULL; + } + if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1424,6 +1429,16 @@ static bool rt_cache_valid(const struct rtable *rt) !rt_is_expired(rt); } +static void rt_init_metrics(struct rtable *rt, struct fib_info *fi) +{ + if (fi->fib_metrics != (u32 *)dst_default_metrics) { + fib_info_hold(fi); + rt->fi = fi; + } + + dst_init_metrics(&rt->dst, fi->fib_metrics, true); +} + static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, @@ -1438,7 +1453,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, rt->rt_gateway = nh->nh_gw; rt->rt_uses_gateway = 1; } - dst_init_metrics(&rt->dst, fi->fib_metrics, true); + rt_init_metrics(rt, fi); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif @@ -1490,6 +1505,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; + rt->fi = NULL; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; -- cgit v1.2.3 From 1b1fc3fddabfb8739ef2c8f04e05a9858b42c1f7 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 5 May 2017 12:53:23 -0700 Subject: tcp: make congestion control optionally skip slow start after idle Congestion control modules that want full control over congestion control behavior do not want the cwnd modifications controlled by the sysctl_tcp_slow_start_after_idle code path. So skip those code paths for CC modules that use the cong_control() API. As an example, those cwnd effects are not desired for the BBR congestion control algorithm. Fixes: c0402760f565 ("tcp: new CC hook to set sending rate with rate_sample in any CA state") Signed-off-by: Wei Wang Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 4 +++- net/ipv4/tcp_output.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 8c0e5a901d64..38a7427ae902 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1234,10 +1234,12 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; - if (!sysctl_tcp_slow_start_after_idle || tp->packets_out) + if (!sysctl_tcp_slow_start_after_idle || tp->packets_out || + ca_ops->cong_control) return; delta = tcp_time_stamp - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 60111a0fc201..4858e190f6ac 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1514,6 +1514,7 @@ static void tcp_cwnd_application_limited(struct sock *sk) static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the maximum number of outstanding packets in each @@ -1536,7 +1537,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && - (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto) + (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && + !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation -- cgit v1.2.3 From 242d3a49a2a1a71d8eb9f953db1bcaa9d698ce00 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 8 May 2017 10:12:13 -0700 Subject: ipv6: reorder ip6_route_dev_notifier after ipv6_dev_notf For each netns (except init_net), we initialize its null entry in 3 places: 1) The template itself, as we use kmemdup() 2) Code around dst_init_metrics() in ip6_route_net_init() 3) ip6_route_dev_notify(), which is supposed to initialize it after loopback registers Unfortunately the last one still happens in a wrong order because we expect to initialize net->ipv6.ip6_null_entry->rt6i_idev to net->loopback_dev's idev, thus we have to do that after we add idev to loopback. However, this notifier has priority == 0 same as ipv6_dev_notf, and ipv6_dev_notf is registered after ip6_route_dev_notifier so it is called actually after ip6_route_dev_notifier. This is similar to commit 2f460933f58e ("ipv6: initialize route null entry in addrconf_init()") which fixes init_net. Fix it by picking a smaller priority for ip6_route_dev_notifier. Also, we have to release the refcnt accordingly when unregistering loopback_dev because device exit functions are called before subsys exit functions. Acked-by: David Ahern Tested-by: David Ahern Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/addrconf.h | 2 ++ net/ipv6/addrconf.c | 1 + net/ipv6/route.c | 13 +++++++++++-- 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 2452e6449532..b43a4eec3cec 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -20,6 +20,8 @@ #define ADDRCONF_TIMER_FUZZ (HZ / 4) #define ADDRCONF_TIMER_FUZZ_MAX (HZ) +#define ADDRCONF_NOTIFY_PRIORITY 0 + #include #include diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 77a4bd526d6e..8d297a79b568 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3548,6 +3548,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, + .priority = ADDRCONF_NOTIFY_PRIORITY, }; static void addrconf_type_change(struct net_device *dev, unsigned long event) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2f1136627dcb..dc61b0b5e64e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3709,7 +3709,10 @@ static int ip6_route_dev_notify(struct notifier_block *this, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { + if (!(dev->flags & IFF_LOOPBACK)) + return NOTIFY_OK; + + if (event == NETDEV_REGISTER) { net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -3717,6 +3720,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); +#endif + } else if (event == NETDEV_UNREGISTER) { + in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); + in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } @@ -4024,7 +4033,7 @@ static struct pernet_operations ip6_route_net_late_ops = { static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, - .priority = 0, + .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) -- cgit v1.2.3 From 32f1bc0f3d262125169f9212aac306c638e34b54 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 8 May 2017 22:35:32 -0400 Subject: Revert "ipv4: restore rt->fi for reference counting" This reverts commit 82486aa6f1b9bc8145e6d0fa2bc0b44307f3b875. As implemented, this causes dangling netdevice refs. Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/route.h | 1 - net/ipv4/route.c | 18 +----------------- 2 files changed, 1 insertion(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 4335eb72a04c..2cc0e14c6359 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -69,7 +69,6 @@ struct rtable { struct list_head rt_uncached; struct uncached_list *rt_uncached_list; - struct fib_info *fi; /* for refcnt to shared metrics */ }; static inline bool rt_is_input_route(const struct rtable *rt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f647310f8e4d..655d9eebe43e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1387,11 +1387,6 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; - if (rt->fi) { - fib_info_put(rt->fi); - rt->fi = NULL; - } - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1429,16 +1424,6 @@ static bool rt_cache_valid(const struct rtable *rt) !rt_is_expired(rt); } -static void rt_init_metrics(struct rtable *rt, struct fib_info *fi) -{ - if (fi->fib_metrics != (u32 *)dst_default_metrics) { - fib_info_hold(fi); - rt->fi = fi; - } - - dst_init_metrics(&rt->dst, fi->fib_metrics, true); -} - static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, @@ -1453,7 +1438,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, rt->rt_gateway = nh->nh_gw; rt->rt_uses_gateway = 1; } - rt_init_metrics(rt, fi); + dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif @@ -1505,7 +1490,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; - rt->fi = NULL; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; -- cgit v1.2.3