LVS
lvs-devel
Google
 
Web LinuxVirtualServer.org

[PATCH net-next,v3 01/14] ipvs: replace ip_vs_fill_ip4hdr with ip_vs_fil

To: <horms@xxxxxxxxxxxx>, <ja@xxxxxx>, <lvs-devel@xxxxxxxxxxxxxxx>
Subject: [PATCH net-next,v3 01/14] ipvs: replace ip_vs_fill_ip4hdr with ip_vs_fill_iph_skb_off
Cc: <alexgartrell@xxxxxxxxx>, <kernel-team@xxxxxx>, Alex Gartrell <agartrell@xxxxxx>
From: Alex Gartrell <agartrell@xxxxxx>
Date: Tue, 25 Aug 2015 20:49:16 -0700
This removes some duplicated code and makes the ICMPv6 path look more like
the ICMP path.

Signed-off-by: Alex Gartrell <agartrell@xxxxxx>
---
 include/net/ip_vs.h             | 49 +++++++++++++++++------------
 net/netfilter/ipvs/ip_vs_core.c | 70 +++++++++++++++--------------------------
 net/netfilter/ipvs/ip_vs_xmit.c | 15 ++++-----
 3 files changed, 63 insertions(+), 71 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4e3731e..781068c 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -104,6 +104,7 @@ static inline struct net *seq_file_single_net(struct 
seq_file *seq)
 extern int ip_vs_conn_tab_size;
 
 struct ip_vs_iphdr {
+       __u32 off;      /* Where IP or IPv4 header starts */
        __u32 len;      /* IPv4 simply where L4 starts
                         * IPv6 where L4 Transport Header starts */
        __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
@@ -120,48 +121,56 @@ static inline void *frag_safe_skb_hp(const struct sk_buff 
*skb, int offset,
        return skb_header_pointer(skb, offset, len, buffer);
 }
 
-static inline void
-ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
-{
-       const struct iphdr *iph = nh;
-
-       iphdr->len      = iph->ihl * 4;
-       iphdr->fragoffs = 0;
-       iphdr->protocol = iph->protocol;
-       iphdr->saddr.ip = iph->saddr;
-       iphdr->daddr.ip = iph->daddr;
-}
-
 /* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6.
  * IPv6 requires some extra work, as finding proper header position,
  * depend on the IPv6 extension headers.
  */
-static inline void
-ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr 
*iphdr)
+static inline int
+ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset,
+                      struct ip_vs_iphdr *iphdr)
 {
+       iphdr->off = offset;
 #ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6) {
-               const struct ipv6hdr *iph =
-                       (struct ipv6hdr *)skb_network_header(skb);
+               struct ipv6hdr _iph;
+               const struct ipv6hdr *iph = skb_header_pointer(
+                       skb, offset, sizeof(_iph), &_iph);
+               if (!iph)
+                       return 0;
+
                iphdr->saddr.in6 = iph->saddr;
                iphdr->daddr.in6 = iph->daddr;
                /* ipv6_find_hdr() updates len, flags */
-               iphdr->len       = 0;
+               iphdr->len       = offset;
                iphdr->flags     = 0;
                iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
                                                 &iphdr->fragoffs,
                                                 &iphdr->flags);
+               if (iphdr->protocol < 0)
+                       return 0;
        } else
 #endif
        {
-               const struct iphdr *iph =
-                       (struct iphdr *)skb_network_header(skb);
-               iphdr->len      = iph->ihl * 4;
+               struct iphdr _iph;
+               const struct iphdr *iph = skb_header_pointer(
+                       skb, offset, sizeof(_iph), &_iph);
+               if (!iph)
+                       return 0;
+
+               iphdr->len      = offset + iph->ihl * 4;
                iphdr->fragoffs = 0;
                iphdr->protocol = iph->protocol;
                iphdr->saddr.ip = iph->saddr;
                iphdr->daddr.ip = iph->daddr;
        }
+
+       return 1;
+}
+
+static inline int
+ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr 
*iphdr)
+{
+       return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), iphdr);
 }
 
 static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 38fbc19..b831fe8 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -436,7 +436,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff 
*skb,
         * with persistence the connection is created on SYN+ACK.
         */
        if (pptr[0] == FTPDATA) {
-               IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
+               IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off,
                              "Not scheduling FTPDATA");
                return NULL;
        }
@@ -446,7 +446,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff 
*skb,
         */
        if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
            (cp = pp->conn_in_get(svc->af, skb, iph, 1))) {
-               IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
+               IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off,
                              "Not scheduling reply for existing connection");
                __ip_vs_conn_put(cp);
                return NULL;
@@ -934,8 +934,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
        IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
                      "Checking outgoing ICMP for");
 
-       ip_vs_fill_ip4hdr(cih, &ciph);
-       ciph.len += offset;
+       ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph);
+
        /* The embedded headers contain source and dest in reverse order */
        cp = pp->conn_out_get(AF_INET, skb, &ciph, 1);
        if (!cp)
@@ -951,12 +951,11 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int 
*related,
                             unsigned int hooknum, struct ip_vs_iphdr *ipvsh)
 {
        struct icmp6hdr _icmph, *ic;
-       struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */
        struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
        struct ip_vs_conn *cp;
        struct ip_vs_protocol *pp;
        union nf_inet_addr snet;
-       unsigned int writable;
+       unsigned int offset;
 
        *related = 1;
        ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
@@ -984,17 +983,9 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int 
*related,
                  ic->icmp6_type, ntohs(icmpv6_id(ic)),
                  &ipvsh->saddr, &ipvsh->daddr);
 
-       /* Now find the contained IP header */
-       ciph.len = ipvsh->len + sizeof(_icmph);
-       ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
-       if (ip6h == NULL)
+       if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, ipvsh->len + sizeof(_icmph),
+                                   &ciph))
                return NF_ACCEPT; /* The packet looks wrong, ignore */
-       ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */
-       ciph.daddr.in6 = ip6h->daddr;
-       /* skip possible IPv6 exthdrs of contained IPv6 packet */
-       ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
-       if (ciph.protocol < 0)
-               return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
 
        pp = ip_vs_proto_get(ciph.protocol);
        if (!pp)
@@ -1006,9 +997,9 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int 
*related,
                return NF_ACCEPT;
 
        snet.in6 = ciph.saddr.in6;
-       writable = ciph.len;
+       offset = ciph.len;
        return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-                                   pp, writable, sizeof(struct ipv6hdr),
+                                   pp, offset, sizeof(struct ipv6hdr),
                                    hooknum);
 }
 #endif
@@ -1093,7 +1084,7 @@ handle_response(int af, struct sk_buff *skb, struct 
ip_vs_proto_data *pd,
 {
        struct ip_vs_protocol *pp = pd->pp;
 
-       IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
+       IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");
 
        if (!skb_make_writable(skb, iph->len))
                goto drop;
@@ -1130,7 +1121,7 @@ handle_response(int af, struct sk_buff *skb, struct 
ip_vs_proto_data *pd,
        if (ip_vs_route_me_harder(af, skb, hooknum))
                goto drop;
 
-       IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
+       IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT");
 
        ip_vs_out_stats(cp, skb);
        ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
@@ -1221,7 +1212,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int 
af)
                                               ip_vs_defrag_user(hooknum)))
                                return NF_STOLEN;
 
-                       ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
+                       ip_vs_fill_iph_skb(AF_INET, skb, &iph);
                }
 
        /*
@@ -1272,7 +1263,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int 
af)
                        }
                }
        }
-       IP_VS_DBG_PKT(12, af, pp, skb, 0,
+       IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
                      "ip_vs_out: packet continues traversal as normal");
        return NF_ACCEPT;
 }
@@ -1416,9 +1407,9 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned 
int hooknum)
                      "Checking incoming ICMP for");
 
        offset2 = offset;
-       ip_vs_fill_ip4hdr(cih, &ciph);
-       ciph.len += offset;
+       ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph);
        offset = ciph.len;
+
        /* The embedded headers contain source and dest in reverse order.
         * For IPIP this is error for request, not for reply.
         */
@@ -1511,13 +1502,12 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int 
*related,
                            unsigned int hooknum, struct ip_vs_iphdr *iph)
 {
        struct net *net = NULL;
-       struct ipv6hdr _ip6h, *ip6h;
        struct icmp6hdr _icmph, *ic;
        struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
        struct ip_vs_conn *cp;
        struct ip_vs_protocol *pp;
        struct ip_vs_proto_data *pd;
-       unsigned int offs_ciph, writable, verdict;
+       unsigned int offset, verdict;
 
        *related = 1;
 
@@ -1546,18 +1536,9 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int 
*related,
                  ic->icmp6_type, ntohs(icmpv6_id(ic)),
                  &iph->saddr, &iph->daddr);
 
-       /* Now find the contained IP header */
-       ciph.len = iph->len + sizeof(_icmph);
-       offs_ciph = ciph.len; /* Save ip header offset */
-       ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
-       if (ip6h == NULL)
-               return NF_ACCEPT; /* The packet looks wrong, ignore */
-       ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */
-       ciph.daddr.in6 = ip6h->daddr;
-       /* skip possible IPv6 exthdrs of contained IPv6 packet */
-       ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
-       if (ciph.protocol < 0)
-               return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
+       offset = iph->len + sizeof(_icmph);
+       if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, offset, &ciph))
+               return NF_ACCEPT;
 
        net = skb_net(skb);
        pd = ip_vs_proto_data_get(net, ciph.protocol);
@@ -1569,7 +1550,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int 
*related,
        if (ciph.fragoffs)
                return NF_ACCEPT;
 
-       IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph,
+       IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
                      "Checking incoming ICMPv6 for");
 
        /* The embedded headers contain source and dest in reverse order
@@ -1591,12 +1572,12 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int 
*related,
        ip_vs_in_stats(cp, skb);
 
        /* Need to mangle contained IPv6 header in ICMPv6 packet */
-       writable = ciph.len;
+       offset = ciph.len;
        if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
            IPPROTO_SCTP == ciph.protocol)
-               writable += 2 * sizeof(__u16); /* Also mangle ports */
+               offset += 2 * sizeof(__u16); /* Also mangle ports */
 
-       verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph);
+       verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph);
 
        __ip_vs_conn_put(cp);
 
@@ -1720,12 +1701,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int 
af)
                         * is missing module nf_defrag_ipv6
                         */
                        IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
-                       IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment");
+                       IP_VS_DBG_PKT(7, af, pp, skb, iph.off,
+                                     "unhandled fragment");
                }
                return NF_ACCEPT;
        }
 
-       IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
+       IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet");
        /* Check the server status */
        if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
                /* the destination server is not available */
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 258a0b0..9a26f2e 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -723,7 +723,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
                struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
                if (ct && !nf_ct_is_untracked(ct)) {
-                       IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
+                       IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, ipvsh->off,
                                         "ip_vs_nat_xmit(): "
                                         "stopping DNAT to local address");
                        goto tx_error;
@@ -733,8 +733,9 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
        /* From world but DNAT to loopback address? */
        if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
-               IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
-                                "stopping DNAT to loopback address");
+               IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, ipvsh->off,
+                                "ip_vs_nat_xmit(): stopping DNAT to loopback "
+                                "address");
                goto tx_error;
        }
 
@@ -751,7 +752,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
        ip_hdr(skb)->daddr = cp->daddr.ip;
        ip_send_check(ip_hdr(skb));
 
-       IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
+       IP_VS_DBG_PKT(10, AF_INET, pp, skb, ipvsh->off, "After DNAT");
 
        /* FIXME: when application helper enlarges the packet and the length
           is larger than the MTU of outgoing device, there will be still
@@ -812,7 +813,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn 
*cp,
                struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
                if (ct && !nf_ct_is_untracked(ct)) {
-                       IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
+                       IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, ipvsh->off,
                                         "ip_vs_nat_xmit_v6(): "
                                         "stopping DNAT to local address");
                        goto tx_error;
@@ -823,7 +824,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn 
*cp,
        /* From world but DNAT to loopback address? */
        if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
            ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
-               IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
+               IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, ipvsh->off,
                                 "ip_vs_nat_xmit_v6(): "
                                 "stopping DNAT to loopback address");
                goto tx_error;
@@ -841,7 +842,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn 
*cp,
                goto tx_error;
        ipv6_hdr(skb)->daddr = cp->daddr.in6;
 
-       IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
+       IP_VS_DBG_PKT(10, AF_INET6, pp, skb, ipvsh->off, "After DNAT");
 
        /* FIXME: when application helper enlarges the packet and the length
           is larger than the MTU of outgoing device, there will be still
-- 
Alex Gartrell <agartrell@xxxxxx>

--
To unsubscribe from this list: send the line "unsubscribe lvs-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

<Prev in Thread] Current Thread [Next in Thread>