Re: [PACKET]: Add PACKET_AUXDATA cmsg
On Wed, Jan 10, 2007 at 01:54:35PM +1100, Herbert Xu wrote: [PACKET]: Add optional checksum computation for recvmsg Unfortunately I missed the fact the skb-cb is already used to store the sockaddr. This patch fixes it up. [PACKET]: Fix skb-cb clobbering between aux and sockaddr Both aux data and sockaddr tries to use the same buffer which obviously doesn't work. We just happen to have 4 bytes free in the skb-cb if you take away the maximum length of sockaddr_ll. That's just enough to store the one piece of info from aux data that we can't generate at recvmsg(2) time. This is what the following patch does. Signed-off-by: Herbert Xu [EMAIL PROTECTED] Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmVHI~} [EMAIL PROTECTED] Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt -- diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index dab117e..4c7f9d7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -60,6 +60,7 @@ #include linux/netdevice.h #include linux/if_packet.h #include linux/wireless.h +#include linux/kernel.h #include linux/kmod.h #include net/ip.h #include net/protocol.h @@ -215,7 +216,15 @@ struct packet_sock { #endif }; -#define PACKET_SKB_CB(__skb) ((struct tpacket_auxdata *)((__skb)-cb)) +struct packet_skb_cb { + unsigned int origlen; + union { + struct sockaddr_pkt pkt; + struct sockaddr_ll ll; + } sa; +}; + +#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)-cb)) #ifdef CONFIG_PACKET_MMAP @@ -296,7 +305,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct /* drop conntrack reference */ nf_reset(skb); - spkt = (struct sockaddr_pkt*)skb-cb; + spkt = PACKET_SKB_CB(skb)-sa.pkt; skb_push(skb, skb-data-skb-mac.raw); @@ -471,7 +480,6 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet u8 * skb_head = skb-data; int skb_len = skb-len; unsigned snaplen; - struct tpacket_auxdata *aux; if (skb-pkt_type == PACKET_LOOPBACK) goto drop; @@ -519,7 +527,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet skb = nskb; } - sll = (struct sockaddr_ll*)skb-cb; + BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 +sizeof(skb-cb)); + + sll = PACKET_SKB_CB(skb)-sa.ll; sll-sll_family = AF_PACKET; sll-sll_hatype = dev-type; sll-sll_protocol = skb-protocol; @@ -530,14 +541,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet if (dev-hard_header_parse) sll-sll_halen = dev-hard_header_parse(skb, sll-sll_addr); - aux = PACKET_SKB_CB(skb); - aux-tp_status = TP_STATUS_USER; - if (skb-ip_summed == CHECKSUM_PARTIAL) - aux-tp_status |= TP_STATUS_CSUMNOTREADY; - aux-tp_len = skb-len; - aux-tp_snaplen = snaplen; - aux-tp_mac = 0; - aux-tp_net = skb-nh.raw - skb-data; + PACKET_SKB_CB(skb)-origlen = skb-len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; @@ -1106,7 +1110,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * it in now. */ - sll = (struct sockaddr_ll*)skb-cb; + sll = PACKET_SKB_CB(skb)-sa.ll; if (sock-type == SOCK_PACKET) msg-msg_namelen = sizeof(struct sockaddr_pkt); else @@ -1131,11 +1135,21 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_timestamp(msg, sk, skb); if (msg-msg_name) - memcpy(msg-msg_name, skb-cb, msg-msg_namelen); + memcpy(msg-msg_name, PACKET_SKB_CB(skb)-sa, + msg-msg_namelen); if (pkt_sk(sk)-auxdata) { - struct tpacket_auxdata *aux = PACKET_SKB_CB(skb); - put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(*aux), aux); + struct tpacket_auxdata aux; + + aux.tp_status = TP_STATUS_USER; + if (skb-ip_summed == CHECKSUM_PARTIAL) + aux.tp_status |= TP_STATUS_CSUMNOTREADY; + aux.tp_len = PACKET_SKB_CB(skb)-origlen; + aux.tp_snaplen = skb-len; + aux.tp_mac = 0; + aux.tp_net = skb-nh.raw - skb-data; + + put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), aux); } /* - To unsubscribe from this list: send the line unsubscribe netdev in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PACKET]: Add PACKET_AUXDATA cmsg
From: Herbert Xu [EMAIL PROTECTED] Date: Wed, 10 Jan 2007 13:54:35 +1100 [PACKET]: Add optional checksum computation for recvmsg This looks good, thanks Herbert. I'll queue it up for 2.6.21 - To unsubscribe from this list: send the line unsubscribe netdev in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PACKET]: Add PACKET_AUXDATA cmsg
Hi Dave: [PACKET]: Add optional checksum computation for recvmsg This patch is needed to make ISC's DHCP server (and probably other DHCP servers/clients using AF_PACKET) to be able to serve another client on the same Xen host. The problem is that packets between different domains on the same Xen host only have partial checksums. Unfortunately this piece of information is not passed along in AF_PACKET unless you're using the mmap interface. Since dhcpd doesn't support packet-mmap, UDP packets from the same host come out with apparently bogus checksums. This patch adds a mechanism for AF_PACKET recvmsg(2) to return the status along with the packet. It does so by adding a new cmsg that contains this information along with some other relevant data such as the original packet length. I didn't include the time stamp information since there is already a cmsg for that. This patch also changes the mmap code to set the CSUMNOTREADY flag on all packets instead of just outoing packets on cooked sockets. Signed-off-by: Herbert Xu [EMAIL PROTECTED] Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmVHI~} [EMAIL PROTECTED] Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt -- diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 99393ef..f3de05c 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -41,6 +41,7 @@ struct sockaddr_ll #define PACKET_RX_RING 5 #define PACKET_STATISTICS 6 #define PACKET_COPY_THRESH 7 +#define PACKET_AUXDATA 8 struct tpacket_stats { @@ -48,6 +49,15 @@ struct tpacket_stats unsigned inttp_drops; }; +struct tpacket_auxdata +{ + __u32 tp_status; + __u32 tp_len; + __u32 tp_snaplen; + __u16 tp_mac; + __u16 tp_net; +}; + struct tpacket_hdr { unsigned long tp_status; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index da73e8a..dab117e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -200,7 +200,8 @@ struct packet_sock { #endif struct packet_type prot_hook; spinlock_t bind_lock; - charrunning;/* prot_hook is attached*/ + unsigned intrunning:1, /* prot_hook is attached*/ + auxdata:1; int ifindex;/* bound device */ __be16 num; #ifdef CONFIG_PACKET_MULTICAST @@ -214,6 +215,8 @@ struct packet_sock { #endif }; +#define PACKET_SKB_CB(__skb) ((struct tpacket_auxdata *)((__skb)-cb)) + #ifdef CONFIG_PACKET_MMAP static inline char *packet_lookup_frame(struct packet_sock *po, unsigned int position) @@ -468,6 +471,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet u8 * skb_head = skb-data; int skb_len = skb-len; unsigned snaplen; + struct tpacket_auxdata *aux; if (skb-pkt_type == PACKET_LOOPBACK) goto drop; @@ -526,6 +530,15 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet if (dev-hard_header_parse) sll-sll_halen = dev-hard_header_parse(skb, sll-sll_addr); + aux = PACKET_SKB_CB(skb); + aux-tp_status = TP_STATUS_USER; + if (skb-ip_summed == CHECKSUM_PARTIAL) + aux-tp_status |= TP_STATUS_CSUMNOTREADY; + aux-tp_len = skb-len; + aux-tp_snaplen = snaplen; + aux-tp_mac = 0; + aux-tp_net = skb-nh.raw - skb-data; + if (pskb_trim(skb, snaplen)) goto drop_n_acct; @@ -585,11 +598,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe else if (skb-pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb-nh.raw - skb-data); - if (skb-ip_summed == CHECKSUM_PARTIAL) - status |= TP_STATUS_CSUMNOTREADY; } } + if (skb-ip_summed == CHECKSUM_PARTIAL) + status |= TP_STATUS_CSUMNOTREADY; + snaplen = skb-len; if (run_filter(skb, sk, snaplen) 0) @@ -1119,6 +1133,11 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, if (msg-msg_name) memcpy(msg-msg_name, skb-cb, msg-msg_namelen); + if (pkt_sk(sk)-auxdata) { + struct tpacket_auxdata *aux = PACKET_SKB_CB(skb); + put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(*aux), aux); + } + /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. @@ -1317,6 +1336,7 @@ static int packet_setsockopt(struct