From ed70fcfcee953a76028bfc3f963d2167c2990020 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 2 May 2014 16:29:38 -0700 Subject: net: Call skb_checksum_init in IPv4 Call skb_checksum_init instead of private functions. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/ip.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 3ec2b0fb9d83..1988cefdbb70 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -342,6 +342,12 @@ static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *d __ip_select_ident(iph, dst, more); } +static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) +{ + return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + skb->len, proto, 0); +} + /* * Map a multicast IP onto multicast MAC for type ethernet. */ -- cgit From 698365fa1874aa7635d51667a34a2842228e9837 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 5 May 2014 15:55:55 -0700 Subject: net: clean up snmp stats code commit 8f0ea0fe3a036a47767f9c80e (snmp: reduce percpu needs by 50%) reduced snmp array size to 1, so technically it doesn't have to be an array any more. What's more, after the following commit: commit 933393f58fef9963eac61db8093689544e29a600 Date: Thu Dec 22 11:58:51 2011 -0600 percpu: Remove irqsafe_cpu_xxx variants We simply say that regular this_cpu use must be safe regardless of preemption and interrupt state. That has no material change for x86 and s390 implementations of this_cpu operations. However, arches that do not provide their own implementation for this_cpu operations will now get code generated that disables interrupts instead of preemption. probably no arch wants to have SNMP_ARRAY_SZ == 2. At least after almost 3 years, no one complains. So, just convert the array to a single pointer and remove snmp_mib_init() and snmp_mib_free() as well. Cc: Christoph Lameter Cc: Eric Dumazet Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/ip.h | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 1988cefdbb70..16146b667ddb 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -196,27 +196,15 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd) -unsigned long snmp_fold_field(void __percpu *mib[], int offt); +unsigned long snmp_fold_field(void __percpu *mib, int offt); #if BITS_PER_LONG==32 -u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off); +u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off); #else -static inline u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_off) +static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off) { return snmp_fold_field(mib, offt); } #endif -int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align); - -static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ]) -{ - int i; - - BUG_ON(ptr == NULL); - for (i = 0; i < SNMP_ARRAY_SZ; i++) { - free_percpu(ptr[i]); - ptr[i] = NULL; - } -} void inet_get_local_port_range(struct net *net, int *low, int *high); -- cgit From 60ff746739bf805a912484643c720b6124826140 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sun, 4 May 2014 16:39:18 -0700 Subject: net: rename local_df to ignore_df MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As suggested by several people, rename local_df to ignore_df, since it means "ignore df bit if it is set". Cc: Maciej Żenczykowski Cc: Florian Westphal Cc: David S. Miller Cc: Eric Dumazet Signed-off-by: Cong Wang Acked-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/net/ip.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 16146b667ddb..55752985c144 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -269,7 +269,7 @@ static inline bool ip_sk_use_pmtu(const struct sock *sk) return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE; } -static inline bool ip_sk_local_df(const struct sock *sk) +static inline bool ip_sk_ignore_df(const struct sock *sk) { return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO || inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT; @@ -304,7 +304,7 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s { struct iphdr *iph = ip_hdr(skb); - if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { + if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { /* This is only to work around buggy Windows95/2000 * VJ compression implementations. If the ID field * does not change, they drop every other packet in @@ -320,7 +320,7 @@ static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *d { struct iphdr *iph = ip_hdr(skb); - if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { + if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); inet_sk(sk)->inet_id += 1 + more; -- cgit From e110861f86094cd78cc85593b873970092deb43a Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Tue, 13 May 2014 10:17:33 -0700 Subject: net: add a sysctl to reflect the fwmark on replies Kernel-originated IP packets that have no user socket associated with them (e.g., ICMP errors and echo replies, TCP RSTs, etc.) are emitted with a mark of zero. Add a sysctl to make them have the same mark as the packet they are replying to. This allows an administrator that wishes to do so to use mark-based routing, firewalling, etc. for these replies by marking the original packets inbound. Tested using user-mode linux: - ICMP/ICMPv6 echo replies and errors. - TCP RST packets (IPv4 and IPv6). Signed-off-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/net/ip.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 55752985c144..14c50a1650ef 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -231,6 +231,9 @@ void ipfrag_init(void); void ip_static_sysctl_init(void); +#define IP4_REPLY_MARK(net, mark) \ + ((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0) + static inline bool ip_is_fragment(const struct iphdr *iph) { return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0; -- cgit From 122ff243f5f104194750ecbc76d5946dd1eec934 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 12 May 2014 16:04:53 -0700 Subject: ipv4: make ip_local_reserved_ports per netns ip_local_port_range is already per netns, so should ip_local_reserved_ports be. And since it is none by default we don't actually need it when we don't enable CONFIG_SYSCTL. By the way, rename inet_is_reserved_local_port() to inet_is_local_reserved_port() Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/ip.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 14c50a1650ef..512bcd5dabac 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -208,11 +208,19 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o void inet_get_local_port_range(struct net *net, int *low, int *high); -extern unsigned long *sysctl_local_reserved_ports; -static inline int inet_is_reserved_local_port(int port) +#if CONFIG_SYSCTL +static inline int inet_is_local_reserved_port(struct net *net, int port) { - return test_bit(port, sysctl_local_reserved_ports); + if (!net->ipv4.sysctl_local_reserved_ports) + return 0; + return test_bit(port, net->ipv4.sysctl_local_reserved_ports); } +#else +static inline int inet_is_local_reserved_port(struct net *net, int port) +{ + return 0; +} +#endif extern int sysctl_ip_nonlocal_bind; -- cgit From fcd77db07dd2b8d35e0db0d1209f2ce1bb05531e Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 15 May 2014 13:43:14 -0400 Subject: net: Fix CONFIG_SYSCTL ifdef test. > include/net/ip.h:211:5: warning: "CONFIG_SYSCTL" is not defined [-Wundef] > #if CONFIG_SYSCTL > ^ Reported-by: Stephen Rothwell Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 512bcd5dabac..2e4947895d75 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -208,7 +208,7 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o void inet_get_local_port_range(struct net *net, int *low, int *high); -#if CONFIG_SYSCTL +#ifdef CONFIG_SYSCTL static inline int inet_is_local_reserved_port(struct net *net, int port) { if (!net->ipv4.sysctl_local_reserved_ports) -- cgit From 73f156a6e8c1074ac6327e0abd1169e95eb66463 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Jun 2014 05:26:03 -0700 Subject: inetpeer: get rid of ip_id_count Ideally, we would need to generate IP ID using a per destination IP generator. linux kernels used inet_peer cache for this purpose, but this had a huge cost on servers disabling MTU discovery. 1) each inet_peer struct consumes 192 bytes 2) inetpeer cache uses a binary tree of inet_peer structs, with a nominal size of ~66000 elements under load. 3) lookups in this tree are hitting a lot of cache lines, as tree depth is about 20. 4) If server deals with many tcp flows, we have a high probability of not finding the inet_peer, allocating a fresh one, inserting it in the tree with same initial ip_id_count, (cf secure_ip_id()) 5) We garbage collect inet_peer aggressively. IP ID generation do not have to be 'perfect' Goal is trying to avoid duplicates in a short period of time, so that reassembly units have a chance to complete reassembly of fragments belonging to one message before receiving other fragments with a recycled ID. We simply use an array of generators, and a Jenkin hash using the dst IP as a key. ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it belongs (it is only used from this file) secure_ip_id() and secure_ipv6_id() no longer are needed. Rename ip_select_ident_more() to ip_select_ident_segs() to avoid unnecessary decrement/increment of the number of segments. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 40 +++++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 17 deletions(-) (limited to 'include/net/ip.h') diff --git a/include/net/ip.h b/include/net/ip.h index 2e4947895d75..0e795df05ec9 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -309,9 +309,19 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } } -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); +#define IP_IDENTS_SZ 2048u +extern atomic_t *ip_idents; -static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) +static inline u32 ip_idents_reserve(u32 hash, int segs) +{ + atomic_t *id_ptr = ip_idents + hash % IP_IDENTS_SZ; + + return atomic_add_return(segs, id_ptr) - segs; +} + +void __ip_select_ident(struct iphdr *iph, int segs); + +static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -321,24 +331,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s * does not change, they drop every other packet in * a TCP stream using header compression. */ - iph->id = (sk && inet_sk(sk)->inet_daddr) ? - htons(inet_sk(sk)->inet_id++) : 0; - } else - __ip_select_ident(iph, dst, 0); -} - -static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) -{ - struct iphdr *iph = ip_hdr(skb); - - if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += 1 + more; - } else + inet_sk(sk)->inet_id += segs; + } else { iph->id = 0; - } else - __ip_select_ident(iph, dst, more); + } + } else { + __ip_select_ident(iph, segs); + } +} + +static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +{ + ip_select_ident_segs(skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) -- cgit