From 086f332167d64b645d37405854f049b9ad7371ab Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 10 Nov 2015 13:39:42 +0100 Subject: netfilter: nf_tables: add clone interface to expression operations With the conversion of the counter expressions to make it percpu, we need to clone the percpu memory area, otherwise we crash when using counters from flow tables. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c9149cc0a02d..4bd7508bedc9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -618,6 +618,8 @@ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + int (*clone)(struct nft_expr *dst, + const struct nft_expr *src); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -660,10 +662,20 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); -static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { + int err; + __module_get(src->ops->type->owner); - memcpy(dst, src, src->ops->size); + if (src->ops->clone) { + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; + } else { + memcpy(dst, src, src->ops->size); + } + return 0; } /** -- cgit v1.2.2 From 02bcf4e082e4dc634409a6a6cb7def8806d6e5e6 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 11 Nov 2015 11:51:08 -0800 Subject: ipv6: Check rt->dst.from for the DST_NOCACHE route All DST_NOCACHE rt6_info used to have rt->dst.from set to its parent. After commit 8e3d5be73681 ("ipv6: Avoid double dst_free"), DST_NOCACHE is also set to rt6_info which does not have a parent (i.e. rt->dst.from is NULL). This patch catches the rt->dst.from == NULL case. Fixes: 8e3d5be73681 ("ipv6: Avoid double dst_free") Signed-off-by: Martin KaFai Lau Cc: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index aaf9700fc9e5..fb961a576abe 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) static inline u32 rt6_get_cookie(const struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; -- cgit v1.2.2 From 00fd38d938db3f1ab1c486549afc450cb7e751b1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Nov 2015 08:43:18 -0800 Subject: tcp: ensure proper barriers in lockless contexts Some functions access TCP sockets without holding a lock and might output non consistent data, depending on compiler and or architecture. tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... Introduce sk_state_load() and sk_state_store() to fix the issues, and more clearly document where this lack of locking is happening. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index bbf7c2cf15b4..7f89e4ba18d1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2226,6 +2226,31 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/** + * sk_state_load - read sk->sk_state for lockless contexts + * @sk: socket pointer + * + * Paired with sk_state_store(). Used in places we do not hold socket lock : + * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... + */ +static inline int sk_state_load(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_state); +} + +/** + * sk_state_store - update sk->sk_state + * @sk: socket pointer + * @newstate: new state + * + * Paired with sk_state_load(). Should be used in contexts where + * state change might impact lockless readers. + */ +static inline void sk_state_store(struct sock *sk, int newstate) +{ + smp_store_release(&sk->sk_state, newstate); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); -- cgit v1.2.2 From b4fe85f9c9146f60457e9512fb6055e69e6a7a65 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 12 Nov 2015 17:35:58 +0100 Subject: ip_tunnel: disable preemption when updating per-cpu tstats Drivers like vxlan use the recently introduced udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the packet, updates the struct stats using the usual u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats). udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch tstats, so drivers like vxlan, immediately after, call iptunnel_xmit_stats, which does the same thing - calls u64_stats_update_begin/end on this_cpu_ptr(dev->tstats). While vxlan is probably fine (I don't know?), calling a similar function from, say, an unbound workqueue, on a fully preemptable kernel causes real issues: [ 188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6 [ 188.435579] caller is debug_smp_processor_id+0x17/0x20 [ 188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2 [ 188.435607] Call Trace: [ 188.435611] [] dump_stack+0x4f/0x7b [ 188.435615] [] check_preemption_disabled+0x19d/0x1c0 [ 188.435619] [] debug_smp_processor_id+0x17/0x20 The solution would be to protect the whole this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with disabling preemption and then reenabling it. Signed-off-by: Jason A. Donenfeld Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 3 ++- include/net/ip_tunnels.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index aaee6fa02cf1..ff788b665277 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else { stats->tx_errors++; stats->tx_aborted_errors++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f6dafec9102c..62a750a6a8f8 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err, struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else if (err < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; -- cgit v1.2.2 From 24cb7055a3066634a0f3fa0cd6a4780652905d35 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Mon, 16 Nov 2015 10:52:48 +0100 Subject: net: switchdev: fix return code of fdb_dump stub rtnl_fdb_dump always expects an index to be returned by the ndo_fdb_dump op, but when CONFIG_NET_SWITCHDEV is off, it returns an error. Fix that by returning the given unmodified idx. A similar fix was 0890cf6cb6ab ("switchdev: fix return value of switchdev_port_fdb_dump in case of error") but for the CONFIG_NET_SWITCHDEV=y case. Fixes: 45d4122ca7cd ("switchdev: add support for fdb add/del/dump via switchdev_port_obj ops.") Signed-off-by: Dragos Tatulea Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bc865e244efe..1d22ce9f352e 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -323,7 +323,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, struct net_device *filter_dev, int idx) { - return -EOPNOTSUPP; + return idx; } static inline void switchdev_port_fwd_mark_set(struct net_device *dev, -- cgit v1.2.2