diff options
Diffstat (limited to 'net')
247 files changed, 5958 insertions, 4245 deletions
diff --git a/net/802/tr.c b/net/802/tr.c index d7d8f40c4fed..829deb41ce81 100644 --- a/net/802/tr.c +++ b/net/802/tr.c @@ -164,7 +164,7 @@ static int tr_rebuild_header(struct sk_buff *skb) */ if(trllc->ethertype != htons(ETH_P_IP)) { - printk("tr_rebuild_header: Don't know how to resolve type %04X addresses ?\n",(unsigned int)htons(trllc->ethertype)); + printk("tr_rebuild_header: Don't know how to resolve type %04X addresses ?\n", ntohs(trllc->ethertype)); return 0; } @@ -186,7 +186,7 @@ static int tr_rebuild_header(struct sk_buff *skb) * it via SNAP. */ -unsigned short tr_type_trans(struct sk_buff *skb, struct net_device *dev) +__be16 tr_type_trans(struct sk_buff *skb, struct net_device *dev) { struct trh_hdr *trh=(struct trh_hdr *)skb->data; @@ -229,15 +229,15 @@ unsigned short tr_type_trans(struct sk_buff *skb, struct net_device *dev) */ if (trllc->dsap == EXTENDED_SAP && - (trllc->ethertype == ntohs(ETH_P_IP) || - trllc->ethertype == ntohs(ETH_P_IPV6) || - trllc->ethertype == ntohs(ETH_P_ARP))) + (trllc->ethertype == htons(ETH_P_IP) || + trllc->ethertype == htons(ETH_P_IPV6) || + trllc->ethertype == htons(ETH_P_ARP))) { skb_pull(skb, sizeof(struct trllc)); return trllc->ethertype; } - return ntohs(ETH_P_TR_802_2); + return htons(ETH_P_TR_802_2); } /* diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index da9cfe927158..60a508eb1945 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -62,7 +62,7 @@ int vlan_dev_rebuild_header(struct sk_buff *skb) default: printk(VLAN_DBG "%s: unable to resolve type %X addresses.\n", - dev->name, (int)veth->h_vlan_encapsulated_proto); + dev->name, ntohs(veth->h_vlan_encapsulated_proto)); memcpy(veth->h_source, dev->dev_addr, ETH_ALEN); break; diff --git a/net/Kconfig b/net/Kconfig index 6528a935622c..a81aca43932f 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -231,7 +231,7 @@ config NET_TCPPROBE TCP congestion avoidance modules. If you don't understand what was just said, you don't need it: say N. - Documentation on how to use the packet generator can be found + Documentation on how to use TCP connection probing can be found at http://linux-net.osdl.org/index.php/TcpProbe To compile this code as a module, choose M here: the diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 96dc6bb52d14..708e2e0371af 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1002,7 +1002,7 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, return sum; } -static unsigned short atalk_checksum(const struct sk_buff *skb, int len) +static __be16 atalk_checksum(const struct sk_buff *skb, int len) { unsigned long sum; @@ -1010,7 +1010,7 @@ static unsigned short atalk_checksum(const struct sk_buff *skb, int len) sum = atalk_sum_skb(skb, 4, len-4, 0); /* Use 0xFFFF for 0. 0 itself means none */ - return sum ? htons((unsigned short)sum) : 0xFFFF; + return sum ? htons((unsigned short)sum) : htons(0xFFFF); } static struct proto ddp_proto = { @@ -1289,7 +1289,7 @@ static int handle_ip_over_ddp(struct sk_buff *skb) #endif static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, - struct ddpehdr *ddp, struct ddpebits *ddphv, + struct ddpehdr *ddp, __u16 len_hops, int origlen) { struct atalk_route *rt; @@ -1317,10 +1317,12 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, /* Route the packet */ rt = atrtr_find(&ta); - if (!rt || ddphv->deh_hops == DDP_MAXHOPS) + /* increment hops count */ + len_hops += 1 << 10; + if (!rt || !(len_hops & (15 << 10))) goto free_it; + /* FIXME: use skb->cb to be able to use shared skbs */ - ddphv->deh_hops++; /* * Route goes through another gateway, so set the target to the @@ -1335,11 +1337,10 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, /* Fix up skb->len field */ skb_trim(skb, min_t(unsigned int, origlen, (rt->dev->hard_header_len + - ddp_dl->header_length + ddphv->deh_len))); + ddp_dl->header_length + (len_hops & 1023)))); - /* Mend the byte order */ /* FIXME: use skb->cb to be able to use shared skbs */ - *((__u16 *)ddp) = ntohs(*((__u16 *)ddphv)); + ddp->deh_len_hops = htons(len_hops); /* * Send the buffer onwards @@ -1394,7 +1395,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, struct atalk_iface *atif; struct sockaddr_at tosat; int origlen; - struct ddpebits ddphv; + __u16 len_hops; /* Don't mangle buffer if shared */ if (!(skb = skb_share_check(skb, GFP_ATOMIC))) @@ -1406,16 +1407,11 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, ddp = ddp_hdr(skb); - /* - * Fix up the length field [Ok this is horrible but otherwise - * I end up with unions of bit fields and messy bit field order - * compiler/endian dependencies..] - */ - *((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp)); + len_hops = ntohs(ddp->deh_len_hops); /* Trim buffer in case of stray trailing data */ origlen = skb->len; - skb_trim(skb, min_t(unsigned int, skb->len, ddphv.deh_len)); + skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023)); /* * Size check to see if ddp->deh_len was crap @@ -1430,7 +1426,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, * valid for net byte orders all over the networking code... */ if (ddp->deh_sum && - atalk_checksum(skb, ddphv.deh_len) != ddp->deh_sum) + atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum) /* Not a valid AppleTalk frame - dustbin time */ goto freeit; @@ -1444,7 +1440,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, /* Not ours, so we route the packet via the correct * AppleTalk iface */ - atalk_route_packet(skb, dev, ddp, &ddphv, origlen); + atalk_route_packet(skb, dev, ddp, len_hops, origlen); goto out; } @@ -1489,7 +1485,7 @@ static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev, /* Find our address */ struct atalk_addr *ap = atalk_find_dev_addr(dev); - if (!ap || skb->len < sizeof(struct ddpshdr)) + if (!ap || skb->len < sizeof(__be16) || skb->len > 1023) goto freeit; /* Don't mangle buffer if shared */ @@ -1519,11 +1515,8 @@ static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev, /* * Not sure about this bit... */ - ddp->deh_len = skb->len; - ddp->deh_hops = DDP_MAXHOPS; /* Non routable, so force a drop - if we slip up later */ - /* Mend the byte order */ - *((__u16 *)ddp) = htons(*((__u16 *)ddp)); + /* Non routable, so force a drop if we slip up later */ + ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10)); } skb->h.raw = skb->data; @@ -1622,16 +1615,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk); ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr)); - ddp->deh_pad = 0; - ddp->deh_hops = 0; - ddp->deh_len = len + sizeof(*ddp); - /* - * Fix up the length field [Ok this is horrible but otherwise - * I end up with unions of bit fields and messy bit field order - * compiler/endian dependencies.. - */ - *((__u16 *)ddp) = ntohs(*((__u16 *)ddp)); - + ddp->deh_len_hops = htons(len + sizeof(*ddp)); ddp->deh_dnet = usat->sat_addr.s_net; ddp->deh_snet = at->src_net; ddp->deh_dnode = usat->sat_addr.s_node; @@ -1712,8 +1696,8 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name; struct ddpehdr *ddp; int copied = 0; + int offset = 0; int err = 0; - struct ddpebits ddphv; struct sk_buff *skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) @@ -1721,25 +1705,18 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr /* FIXME: use skb->cb to be able to use shared skbs */ ddp = ddp_hdr(skb); - *((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp)); + copied = ntohs(ddp->deh_len_hops) & 1023; - if (sk->sk_type == SOCK_RAW) { - copied = ddphv.deh_len; - if (copied > size) { - copied = size; - msg->msg_flags |= MSG_TRUNC; - } + if (sk->sk_type != SOCK_RAW) { + offset = sizeof(*ddp); + copied -= offset; + } - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - } else { - copied = ddphv.deh_len - sizeof(*ddp); - if (copied > size) { - copied = size; - msg->msg_flags |= MSG_TRUNC; - } - err = skb_copy_datagram_iovec(skb, sizeof(*ddp), - msg->msg_iov, copied); + if (copied > size) { + copied = size; + msg->msg_flags |= MSG_TRUNC; } + err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied); if (!err) { if (sat) { diff --git a/net/atm/lec.c b/net/atm/lec.c index b4aa489849df..66c57c1091a8 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1,7 +1,7 @@ /* * lec.c: Lan Emulation driver - * Marko Kiiskila mkiiskila@yahoo.com * + * Marko Kiiskila <mkiiskila@yahoo.com> */ #include <linux/kernel.h> @@ -38,7 +38,7 @@ #include <linux/if_bridge.h> #include "../bridge/br_private.h" -static unsigned char bridge_ula_lec[] = {0x01, 0x80, 0xc2, 0x00, 0x00}; +static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; #endif /* Modular too */ @@ -55,38 +55,41 @@ static unsigned char bridge_ula_lec[] = {0x01, 0x80, 0xc2, 0x00, 0x00}; #define DPRINTK(format,args...) #endif -#define DUMP_PACKETS 0 /* 0 = None, - * 1 = 30 first bytes - * 2 = Whole packet - */ +#define DUMP_PACKETS 0 /* + * 0 = None, + * 1 = 30 first bytes + * 2 = Whole packet + */ -#define LEC_UNRES_QUE_LEN 8 /* number of tx packets to queue for a - single destination while waiting for SVC */ +#define LEC_UNRES_QUE_LEN 8 /* + * number of tx packets to queue for a + * single destination while waiting for SVC + */ static int lec_open(struct net_device *dev); static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev); static int lec_close(struct net_device *dev); static struct net_device_stats *lec_get_stats(struct net_device *dev); static void lec_init(struct net_device *dev); -static struct lec_arp_table* lec_arp_find(struct lec_priv *priv, - unsigned char *mac_addr); +static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, + unsigned char *mac_addr); static int lec_arp_remove(struct lec_priv *priv, - struct lec_arp_table *to_remove); + struct lec_arp_table *to_remove); /* LANE2 functions */ -static void lane2_associate_ind (struct net_device *dev, u8 *mac_address, - u8 *tlvs, u32 sizeoftlvs); +static void lane2_associate_ind(struct net_device *dev, u8 *mac_address, + u8 *tlvs, u32 sizeoftlvs); static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, - u8 **tlvs, u32 *sizeoftlvs); -static int lane2_associate_req (struct net_device *dev, u8 *lan_dst, - u8 *tlvs, u32 sizeoftlvs); + u8 **tlvs, u32 *sizeoftlvs); +static int lane2_associate_req(struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs); -static int lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, +static int lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, unsigned long permanent); static void lec_arp_check_empties(struct lec_priv *priv, struct atm_vcc *vcc, struct sk_buff *skb); static void lec_arp_destroy(struct lec_priv *priv); static void lec_arp_init(struct lec_priv *priv); -static struct atm_vcc* lec_arp_resolve(struct lec_priv *priv, +static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, unsigned char *mac_to_find, int is_rdesc, struct lec_arp_table **ret_entry); @@ -100,16 +103,30 @@ static void lec_set_flush_tran_id(struct lec_priv *priv, unsigned long tran_id); static void lec_vcc_added(struct lec_priv *priv, struct atmlec_ioc *ioc_data, struct atm_vcc *vcc, - void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb)); + void (*old_push) (struct atm_vcc *vcc, + struct sk_buff *skb)); static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc); +/* must be done under lec_arp_lock */ +static inline void lec_arp_hold(struct lec_arp_table *entry) +{ + atomic_inc(&entry->usage); +} + +static inline void lec_arp_put(struct lec_arp_table *entry) +{ + if (atomic_dec_and_test(&entry->usage)) + kfree(entry); +} + + static struct lane2_ops lane2_ops = { - lane2_resolve, /* resolve, spec 3.1.3 */ - lane2_associate_req, /* associate_req, spec 3.1.4 */ - NULL /* associate indicator, spec 3.1.5 */ + lane2_resolve, /* resolve, spec 3.1.3 */ + lane2_associate_req, /* associate_req, spec 3.1.4 */ + NULL /* associate indicator, spec 3.1.5 */ }; -static unsigned char bus_mac[ETH_ALEN] = {0xff,0xff,0xff,0xff,0xff,0xff}; +static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; /* Device structures */ static struct net_device *dev_lec[MAX_LEC_ITF]; @@ -117,36 +134,39 @@ static struct net_device *dev_lec[MAX_LEC_ITF]; #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) { - struct ethhdr *eth; - char *buff; - struct lec_priv *priv; - - /* Check if this is a BPDU. If so, ask zeppelin to send - * LE_TOPOLOGY_REQUEST with the same value of Topology Change bit - * as the Config BPDU has */ - eth = (struct ethhdr *)skb->data; - buff = skb->data + skb->dev->hard_header_len; - if (*buff++ == 0x42 && *buff++ == 0x42 && *buff++ == 0x03) { + struct ethhdr *eth; + char *buff; + struct lec_priv *priv; + + /* + * Check if this is a BPDU. If so, ask zeppelin to send + * LE_TOPOLOGY_REQUEST with the same value of Topology Change bit + * as the Config BPDU has + */ + eth = (struct ethhdr *)skb->data; + buff = skb->data + skb->dev->hard_header_len; + if (*buff++ == 0x42 && *buff++ == 0x42 && *buff++ == 0x03) { struct sock *sk; - struct sk_buff *skb2; - struct atmlec_msg *mesg; - - skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); - if (skb2 == NULL) return; - skb2->len = sizeof(struct atmlec_msg); - mesg = (struct atmlec_msg *)skb2->data; - mesg->type = l_topology_change; - buff += 4; - mesg->content.normal.flag = *buff & 0x01; /* 0x01 is topology change */ - - priv = (struct lec_priv *)dev->priv; - atm_force_charge(priv->lecd, skb2->truesize); + struct sk_buff *skb2; + struct atmlec_msg *mesg; + + skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); + if (skb2 == NULL) + return; + skb2->len = sizeof(struct atmlec_msg); + mesg = (struct atmlec_msg *)skb2->data; + mesg->type = l_topology_change; + buff += 4; + mesg->content.normal.flag = *buff & 0x01; /* 0x01 is topology change */ + + priv = (struct lec_priv *)dev->priv; + atm_force_charge(priv->lecd, skb2->truesize); sk = sk_atm(priv->lecd); - skb_queue_tail(&sk->sk_receive_queue, skb2); - sk->sk_data_ready(sk, skb2->len); - } + skb_queue_tail(&sk->sk_receive_queue, skb2); + sk->sk_data_ready(sk, skb2->len); + } - return; + return; } #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ @@ -162,36 +182,35 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) #ifdef CONFIG_TR static unsigned char *get_tr_dst(unsigned char *packet, unsigned char *rdesc) { - struct trh_hdr *trh; - int riflen, num_rdsc; - - trh = (struct trh_hdr *)packet; - if (trh->daddr[0] & (uint8_t)0x80) - return bus_mac; /* multicast */ - - if (trh->saddr[0] & TR_RII) { - riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; - if ((ntohs(trh->rcf) >> 13) != 0) - return bus_mac; /* ARE or STE */ - } - else - return trh->daddr; /* not source routed */ - - if (riflen < 6) - return trh->daddr; /* last hop, source routed */ - - /* riflen is 6 or more, packet has more than one route descriptor */ - num_rdsc = (riflen/2) - 1; - memset(rdesc, 0, ETH_ALEN); - /* offset 4 comes from LAN destination field in LE control frames */ - if (trh->rcf & htons((uint16_t)TR_RCF_DIR_BIT)) - memcpy(&rdesc[4], &trh->rseg[num_rdsc-2], sizeof(uint16_t)); - else { - memcpy(&rdesc[4], &trh->rseg[1], sizeof(uint16_t)); - rdesc[5] = ((ntohs(trh->rseg[0]) & 0x000f) | (rdesc[5] & 0xf0)); - } - - return NULL; + struct trh_hdr *trh; + int riflen, num_rdsc; + + trh = (struct trh_hdr *)packet; + if (trh->daddr[0] & (uint8_t) 0x80) + return bus_mac; /* multicast */ + + if (trh->saddr[0] & TR_RII) { + riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; + if ((ntohs(trh->rcf) >> 13) != 0) + return bus_mac; /* ARE or STE */ + } else + return trh->daddr; /* not source routed */ + + if (riflen < 6) + return trh->daddr; /* last hop, source routed */ + + /* riflen is 6 or more, packet has more than one route descriptor */ + num_rdsc = (riflen / 2) - 1; + memset(rdesc, 0, ETH_ALEN); + /* offset 4 comes from LAN destination field in LE control frames */ + if (trh->rcf & htons((uint16_t) TR_RCF_DIR_BIT)) + memcpy(&rdesc[4], &trh->rseg[num_rdsc - 2], sizeof(uint16_t)); + else { + memcpy(&rdesc[4], &trh->rseg[1], sizeof(uint16_t)); + rdesc[5] = ((ntohs(trh->rseg[0]) & 0x000f) | (rdesc[5] & 0xf0)); + } + + return NULL; } #endif /* CONFIG_TR */ @@ -204,15 +223,14 @@ static unsigned char *get_tr_dst(unsigned char *packet, unsigned char *rdesc) * there is non-reboot way to recover if something goes wrong. */ -static int -lec_open(struct net_device *dev) +static int lec_open(struct net_device *dev) { - struct lec_priv *priv = (struct lec_priv *)dev->priv; - + struct lec_priv *priv = (struct lec_priv *)dev->priv; + netif_start_queue(dev); - memset(&priv->stats,0,sizeof(struct net_device_stats)); - - return 0; + memset(&priv->stats, 0, sizeof(struct net_device_stats)); + + return 0; } static __inline__ void @@ -231,160 +249,166 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb, struct lec_priv *priv) priv->stats.tx_bytes += skb->len; } -static void -lec_tx_timeout(struct net_device *dev) +static void lec_tx_timeout(struct net_device *dev) { printk(KERN_INFO "%s: tx timeout\n", dev->name); dev->trans_start = jiffies; netif_wake_queue(dev); } -static int -lec_start_xmit(struct sk_buff *skb, struct net_device *dev) +static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct sk_buff *skb2; - struct lec_priv *priv = (struct lec_priv *)dev->priv; - struct lecdatahdr_8023 *lec_h; - struct atm_vcc *vcc; + struct sk_buff *skb2; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct lecdatahdr_8023 *lec_h; + struct atm_vcc *vcc; struct lec_arp_table *entry; - unsigned char *dst; + unsigned char *dst; int min_frame_size; #ifdef CONFIG_TR - unsigned char rdesc[ETH_ALEN]; /* Token Ring route descriptor */ + unsigned char rdesc[ETH_ALEN]; /* Token Ring route descriptor */ #endif - int is_rdesc; + int is_rdesc; #if DUMP_PACKETS > 0 - char buf[300]; - int i=0; + char buf[300]; + int i = 0; #endif /* DUMP_PACKETS >0 */ - - DPRINTK("lec_start_xmit called\n"); - if (!priv->lecd) { - printk("%s:No lecd attached\n",dev->name); - priv->stats.tx_errors++; - netif_stop_queue(dev); - return -EUNATCH; - } - - DPRINTK("skbuff head:%lx data:%lx tail:%lx end:%lx\n", - (long)skb->head, (long)skb->data, (long)skb->tail, - (long)skb->end); + + DPRINTK("lec_start_xmit called\n"); + if (!priv->lecd) { + printk("%s:No lecd attached\n", dev->name); + priv->stats.tx_errors++; + netif_stop_queue(dev); + return -EUNATCH; + } + + DPRINTK("skbuff head:%lx data:%lx tail:%lx end:%lx\n", + (long)skb->head, (long)skb->data, (long)skb->tail, + (long)skb->end); #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) - if (memcmp(skb->data, bridge_ula_lec, sizeof(bridge_ula_lec)) == 0) - lec_handle_bridge(skb, dev); + if (memcmp(skb->data, bridge_ula_lec, sizeof(bridge_ula_lec)) == 0) + lec_handle_bridge(skb, dev); #endif - /* Make sure we have room for lec_id */ - if (skb_headroom(skb) < 2) { + /* Make sure we have room for lec_id */ + if (skb_headroom(skb) < 2) { - DPRINTK("lec_start_xmit: reallocating skb\n"); - skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); - kfree_skb(skb); - if (skb2 == NULL) return 0; - skb = skb2; - } - skb_push(skb, 2); + DPRINTK("lec_start_xmit: reallocating skb\n"); + skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); + kfree_skb(skb); + if (skb2 == NULL) + return 0; + skb = skb2; + } + skb_push(skb, 2); - /* Put le header to place, works for TokenRing too */ - lec_h = (struct lecdatahdr_8023*)skb->data; - lec_h->le_header = htons(priv->lecid); + /* Put le header to place, works for TokenRing too */ + lec_h = (struct lecdatahdr_8023 *)skb->data; + lec_h->le_header = htons(priv->lecid); #ifdef CONFIG_TR - /* Ugly. Use this to realign Token Ring packets for - * e.g. PCA-200E driver. */ - if (priv->is_trdev) { - skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); - kfree_skb(skb); - if (skb2 == NULL) return 0; - skb = skb2; - } + /* + * Ugly. Use this to realign Token Ring packets for + * e.g. PCA-200E driver. + */ + if (priv->is_trdev) { + skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); + kfree_skb(skb); + if (skb2 == NULL) + return 0; + skb = skb2; + } #endif #if DUMP_PACKETS > 0 - printk("%s: send datalen:%ld lecid:%4.4x\n", dev->name, - skb->len, priv->lecid); + printk("%s: send datalen:%ld lecid:%4.4x\n", dev->name, + skb->len, priv->lecid); #if DUMP_PACKETS >= 2 - for(i=0;i<skb->len && i <99;i++) { - sprintf(buf+i*3,"%2.2x ",0xff&skb->data[i]); - } + for (i = 0; i < skb->len && i < 99; i++) { + sprintf(buf + i * 3, "%2.2x ", 0xff & skb->data[i]); + } #elif DUMP_PACKETS >= 1 - for(i=0;i<skb->len && i < 30;i++) { - sprintf(buf+i*3,"%2.2x ", 0xff&skb->data[i]); - } + for (i = 0; i < skb->len && i < 30; i++) { + sprintf(buf + i * 3, "%2.2x ", 0xff & skb->data[i]); + } #endif /* DUMP_PACKETS >= 1 */ - if (i==skb->len) - printk("%s\n",buf); - else - printk("%s...\n",buf); + if (i == skb->len) + printk("%s\n", buf); + else + printk("%s...\n", buf); #endif /* DUMP_PACKETS > 0 */ - /* Minimum ethernet-frame size */ + /* Minimum ethernet-frame size */ #ifdef CONFIG_TR - if (priv->is_trdev) - min_frame_size = LEC_MINIMUM_8025_SIZE; + if (priv->is_trdev) + min_frame_size = LEC_MINIMUM_8025_SIZE; else #endif - min_frame_size = LEC_MINIMUM_8023_SIZE; - if (skb->len < min_frame_size) { - if ((skb->len + skb_tailroom(skb)) < min_frame_size) { - skb2 = skb_copy_expand(skb, 0, - min_frame_size - skb->truesize, GFP_ATOMIC); - dev_kfree_skb(skb); - if (skb2 == NULL) { - priv->stats.tx_dropped++; - return 0; - } - skb = skb2; - } + min_frame_size = LEC_MINIMUM_8023_SIZE; + if (skb->len < min_frame_size) { + if ((skb->len + skb_tailroom(skb)) < min_frame_size) { + skb2 = skb_copy_expand(skb, 0, + min_frame_size - skb->truesize, + GFP_ATOMIC); + dev_kfree_skb(skb); + if (skb2 == NULL) { + priv->stats.tx_dropped++; + return 0; + } + skb = skb2; + } skb_put(skb, min_frame_size - skb->len); - } - - /* Send to right vcc */ - is_rdesc = 0; - dst = lec_h->h_dest; + } + + /* Send to right vcc */ + is_rdesc = 0; + dst = lec_h->h_dest; #ifdef CONFIG_TR - if (priv->is_trdev) { - dst = get_tr_dst(skb->data+2, rdesc); - if (dst == NULL) { - dst = rdesc; - is_rdesc = 1; - } - } + if (priv->is_trdev) { + dst = get_tr_dst(skb->data + 2, rdesc); + if (dst == NULL) { + dst = rdesc; + is_rdesc = 1; + } + } #endif - entry = NULL; - vcc = lec_arp_resolve(priv, dst, is_rdesc, &entry); - DPRINTK("%s:vcc:%p vcc_flags:%x, entry:%p\n", dev->name, - vcc, vcc?vcc->flags:0, entry); - if (!vcc || !test_bit(ATM_VF_READY,&vcc->flags)) { - if (entry && (entry->tx_wait.qlen < LEC_UNRES_QUE_LEN)) { - DPRINTK("%s:lec_start_xmit: queuing packet, ", dev->name); - DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", - lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], - lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); - skb_queue_tail(&entry->tx_wait, skb); - } else { - DPRINTK("%s:lec_start_xmit: tx queue full or no arp entry, dropping, ", dev->name); - DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", - lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], - lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); - priv->stats.tx_dropped++; - dev_kfree_skb(skb); - } - return 0; - } - -#if DUMP_PACKETS > 0 - printk("%s:sending to vpi:%d vci:%d\n", dev->name, - vcc->vpi, vcc->vci); + entry = NULL; + vcc = lec_arp_resolve(priv, dst, is_rdesc, &entry); + DPRINTK("%s:vcc:%p vcc_flags:%x, entry:%p\n", dev->name, + vcc, vcc ? vcc->flags : 0, entry); + if (!vcc || !test_bit(ATM_VF_READY, &vcc->flags)) { + if (entry && (entry->tx_wait.qlen < LEC_UNRES_QUE_LEN)) { + DPRINTK("%s:lec_start_xmit: queuing packet, ", + dev->name); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], + lec_h->h_dest[2], lec_h->h_dest[3], + lec_h->h_dest[4], lec_h->h_dest[5]); + skb_queue_tail(&entry->tx_wait, skb); + } else { + DPRINTK + ("%s:lec_start_xmit: tx queue full or no arp entry, dropping, ", + dev->name); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], + lec_h->h_dest[2], lec_h->h_dest[3], + lec_h->h_dest[4], lec_h->h_dest[5]); + priv->stats.tx_dropped++; + dev_kfree_skb(skb); + } + goto out; + } +#if DUMP_PACKETS > 0 + printk("%s:sending to vpi:%d vci:%d\n", dev->name, vcc->vpi, vcc->vci); #endif /* DUMP_PACKETS > 0 */ - - while (entry && (skb2 = skb_dequeue(&entry->tx_wait))) { - DPRINTK("lec.c: emptying tx queue, "); - DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", - lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], - lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); + + while (entry && (skb2 = skb_dequeue(&entry->tx_wait))) { + DPRINTK("lec.c: emptying tx queue, "); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], + lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); lec_send(vcc, skb2, priv); - } + } lec_send(vcc, skb, priv); @@ -404,210 +428,219 @@ lec_start_xmit(struct sk_buff *skb, struct net_device *dev) netif_wake_queue(dev); } +out: + if (entry) + lec_arp_put(entry); dev->trans_start = jiffies; - return 0; + return 0; } /* The inverse routine to net_open(). */ -static int -lec_close(struct net_device *dev) +static int lec_close(struct net_device *dev) { - netif_stop_queue(dev); - return 0; + netif_stop_queue(dev); + return 0; } /* * Get the current statistics. * This may be called with the card open or closed. */ -static struct net_device_stats * -lec_get_stats(struct net_device *dev) +static struct net_device_stats *lec_get_stats(struct net_device *dev) { - return &((struct lec_priv *)dev->priv)->stats; + return &((struct lec_priv *)dev->priv)->stats; } -static int -lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) +static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) { unsigned long flags; - struct net_device *dev = (struct net_device*)vcc->proto_data; - struct lec_priv *priv = (struct lec_priv*)dev->priv; - struct atmlec_msg *mesg; - struct lec_arp_table *entry; - int i; - char *tmp; /* FIXME */ + struct net_device *dev = (struct net_device *)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct atmlec_msg *mesg; + struct lec_arp_table *entry; + int i; + char *tmp; /* FIXME */ atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); - mesg = (struct atmlec_msg *)skb->data; - tmp = skb->data; - tmp += sizeof(struct atmlec_msg); - DPRINTK("%s: msg from zeppelin:%d\n", dev->name, mesg->type); - switch(mesg->type) { - case l_set_mac_addr: - for (i=0;i<6;i++) { - dev->dev_addr[i] = mesg->content.normal.mac_addr[i]; - } - break; - case l_del_mac_addr: - for(i=0;i<6;i++) { - dev->dev_addr[i] = 0; - } - break; - case l_addr_delete: - lec_addr_delete(priv, mesg->content.normal.atm_addr, - mesg->content.normal.flag); - break; - case l_topology_change: - priv->topology_change = mesg->content.normal.flag; - break; - case l_flush_complete: - lec_flush_complete(priv, mesg->content.normal.flag); - break; - case l_narp_req: /* LANE2: see 7.1.35 in the lane2 spec */ + mesg = (struct atmlec_msg *)skb->data; + tmp = skb->data; + tmp += sizeof(struct atmlec_msg); + DPRINTK("%s: msg from zeppelin:%d\n", dev->name, mesg->type); + switch (mesg->type) { + case l_set_mac_addr: + for (i = 0; i < 6; i++) { + dev->dev_addr[i] = mesg->content.normal.mac_addr[i]; + } + break; + case l_del_mac_addr: + for (i = 0; i < 6; i++) { + dev->dev_addr[i] = 0; + } + break; + case l_addr_delete: + lec_addr_delete(priv, mesg->content.normal.atm_addr, + mesg->content.normal.flag); + break; + case l_topology_change: + priv->topology_change = mesg->content.normal.flag; + break; + case l_flush_complete: + lec_flush_complete(priv, mesg->content.normal.flag); + break; + case l_narp_req: /* LANE2: see 7.1.35 in the lane2 spec */ spin_lock_irqsave(&priv->lec_arp_lock, flags); - entry = lec_arp_find(priv, mesg->content.normal.mac_addr); - lec_arp_remove(priv, entry); + entry = lec_arp_find(priv, mesg->content.normal.mac_addr); + lec_arp_remove(priv, entry); spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - if (mesg->content.normal.no_source_le_narp) - break; - /* FALL THROUGH */ - case l_arp_update: - lec_arp_update(priv, mesg->content.normal.mac_addr, - mesg->content.normal.atm_addr, - mesg->content.normal.flag, - mesg->content.normal.targetless_le_arp); - DPRINTK("lec: in l_arp_update\n"); - if (mesg->sizeoftlvs != 0) { /* LANE2 3.1.5 */ - DPRINTK("lec: LANE2 3.1.5, got tlvs, size %d\n", mesg->sizeoftlvs); - lane2_associate_ind(dev, - mesg->content.normal.mac_addr, - tmp, mesg->sizeoftlvs); - } - break; - case l_config: - priv->maximum_unknown_frame_count = - mesg->content.config.maximum_unknown_frame_count; - priv->max_unknown_frame_time = - (mesg->content.config.max_unknown_frame_time*HZ); - priv->max_retry_count = - mesg->content.config.max_retry_count; - priv->aging_time = (mesg->content.config.aging_time*HZ); - priv->forward_delay_time = - (mesg->content.config.forward_delay_time*HZ); - priv->arp_response_time = - (mesg->content.config.arp_response_time*HZ); - priv->flush_timeout = (mesg->content.config.flush_timeout*HZ); - priv->path_switching_delay = - (mesg->content.config.path_switching_delay*HZ); - priv->lane_version = mesg->content.config.lane_version; /* LANE2 */ + if (mesg->content.normal.no_source_le_narp) + break; + /* FALL THROUGH */ + case l_arp_update: + lec_arp_update(priv, mesg->content.normal.mac_addr, + mesg->content.normal.atm_addr, + mesg->content.normal.flag, + mesg->content.normal.targetless_le_arp); + DPRINTK("lec: in l_arp_update\n"); + if (mesg->sizeoftlvs != 0) { /* LANE2 3.1.5 */ + DPRINTK("lec: LANE2 3.1.5, got tlvs, size %d\n", + mesg->sizeoftlvs); + lane2_associate_ind(dev, mesg->content.normal.mac_addr, + tmp, mesg->sizeoftlvs); + } + break; + case l_config: + priv->maximum_unknown_frame_count = + mesg->content.config.maximum_unknown_frame_count; + priv->max_unknown_frame_time = + (mesg->content.config.max_unknown_frame_time * HZ); + priv->max_retry_count = mesg->content.config.max_retry_count; + priv->aging_time = (mesg->content.config.aging_time * HZ); + priv->forward_delay_time = + (mesg->content.config.forward_delay_time * HZ); + priv->arp_response_time = + (mesg->content.config.arp_response_time * HZ); + priv->flush_timeout = (mesg->content.config.flush_timeout * HZ); + priv->path_switching_delay = + (mesg->content.config.path_switching_delay * HZ); + priv->lane_version = mesg->content.config.lane_version; /* LANE2 */ priv->lane2_ops = NULL; if (priv->lane_version > 1) priv->lane2_ops = &lane2_ops; if (dev->change_mtu(dev, mesg->content.config.mtu)) printk("%s: change_mtu to %d failed\n", dev->name, - mesg->content.config.mtu); + mesg->content.config.mtu); priv->is_proxy = mesg->content.config.is_proxy; - break; - case l_flush_tran_id: - lec_set_flush_tran_id(priv, mesg->content.normal.atm_addr, - mesg->content.normal.flag); - break; - case l_set_lecid: - priv->lecid=(unsigned short)(0xffff&mesg->content.normal.flag); - break; - case l_should_bridge: { + break; + case l_flush_tran_id: + lec_set_flush_tran_id(priv, mesg->content.normal.atm_addr, + mesg->content.normal.flag); + break; + case l_set_lecid: + priv->lecid = + (unsigned short)(0xffff & mesg->content.normal.flag); + break; + case l_should_bridge: #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) - struct net_bridge_fdb_entry *f; - - DPRINTK("%s: bridge zeppelin asks about 0x%02x:%02x:%02x:%02x:%02x:%02x\n", - dev->name, - mesg->content.proxy.mac_addr[0], mesg->content.proxy.mac_addr[1], - mesg->content.proxy.mac_addr[2], mesg->content.proxy.mac_addr[3], - mesg->content.proxy.mac_addr[4], mesg->content.proxy.mac_addr[5]); - - if (br_fdb_get_hook == NULL || dev->br_port == NULL) - break; - - f = br_fdb_get_hook(dev->br_port->br, mesg->content.proxy.mac_addr); - if (f != NULL && - f->dst->dev != dev && - f->dst->state == BR_STATE_FORWARDING) { - /* hit from bridge table, send LE_ARP_RESPONSE */ - struct sk_buff *skb2; - struct sock *sk; - - DPRINTK("%s: entry found, responding to zeppelin\n", dev->name); - skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); - if (skb2 == NULL) { - br_fdb_put_hook(f); - break; - } - skb2->len = sizeof(struct atmlec_msg); - memcpy(skb2->data, mesg, sizeof(struct atmlec_msg)); - atm_force_charge(priv->lecd, skb2->truesize); - sk = sk_atm(priv->lecd); - skb_queue_tail(&sk->sk_receive_queue, skb2); - sk->sk_data_ready(sk, skb2->len); - } - if (f != NULL) br_fdb_put_hook(f); + { + struct net_bridge_fdb_entry *f; + + DPRINTK + ("%s: bridge zeppelin asks about 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + dev->name, mesg->content.proxy.mac_addr[0], + mesg->content.proxy.mac_addr[1], + mesg->content.proxy.mac_addr[2], + mesg->content.proxy.mac_addr[3], + mesg->content.proxy.mac_addr[4], + mesg->content.proxy.mac_addr[5]); + + if (br_fdb_get_hook == NULL || dev->br_port == NULL) + break; + + f = br_fdb_get_hook(dev->br_port->br, + mesg->content.proxy.mac_addr); + if (f != NULL && f->dst->dev != dev + && f->dst->state == BR_STATE_FORWARDING) { + /* hit from bridge table, send LE_ARP_RESPONSE */ + struct sk_buff *skb2; + struct sock *sk; + + DPRINTK + ("%s: entry found, responding to zeppelin\n", + dev->name); + skb2 = + alloc_skb(sizeof(struct atmlec_msg), + GFP_ATOMIC); + if (skb2 == NULL) { + br_fdb_put_hook(f); + break; + } + skb2->len = sizeof(struct atmlec_msg); + memcpy(skb2->data, mesg, + sizeof(struct atmlec_msg)); + atm_force_charge(priv->lecd, skb2->truesize); + sk = sk_atm(priv->lecd); + skb_queue_tail(&sk->sk_receive_queue, skb2); + sk->sk_data_ready(sk, skb2->len); + } + if (f != NULL) + br_fdb_put_hook(f); + } #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ - } - break; - default: - printk("%s: Unknown message type %d\n", dev->name, mesg->type); - dev_kfree_skb(skb); - return -EINVAL; - } - dev_kfree_skb(skb); - return 0; + break; + default: + printk("%s: Unknown message type %d\n", dev->name, mesg->type); + dev_kfree_skb(skb); + return -EINVAL; + } + dev_kfree_skb(skb); + return 0; } -static void -lec_atm_close(struct atm_vcc *vcc) +static void lec_atm_close(struct atm_vcc *vcc) { - struct sk_buff *skb; - struct net_device *dev = (struct net_device *)vcc->proto_data; - struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct sk_buff *skb; + struct net_device *dev = (struct net_device *)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv *)dev->priv; - priv->lecd = NULL; - /* Do something needful? */ + priv->lecd = NULL; + /* Do something needful? */ - netif_stop_queue(dev); - lec_arp_destroy(priv); + netif_stop_queue(dev); + lec_arp_destroy(priv); - if (skb_peek(&sk_atm(vcc)->sk_receive_queue)) + if (skb_peek(&sk_atm(vcc)->sk_receive_queue)) printk("%s lec_atm_close: closing with messages pending\n", - dev->name); - while ((skb = skb_dequeue(&sk_atm(vcc)->sk_receive_queue)) != NULL) { - atm_return(vcc, skb->truesize); + dev->name); + while ((skb = skb_dequeue(&sk_atm(vcc)->sk_receive_queue)) != NULL) { + atm_return(vcc, skb->truesize); dev_kfree_skb(skb); - } - + } + printk("%s: Shut down!\n", dev->name); - module_put(THIS_MODULE); + module_put(THIS_MODULE); } static struct atmdev_ops lecdev_ops = { - .close = lec_atm_close, - .send = lec_atm_send + .close = lec_atm_close, + .send = lec_atm_send }; static struct atm_dev lecatm_dev = { - .ops = &lecdev_ops, - .type = "lec", - .number = 999, /* dummy device number */ - .lock = SPIN_LOCK_UNLOCKED + .ops = &lecdev_ops, + .type = "lec", + .number = 999, /* dummy device number */ + .lock = SPIN_LOCK_UNLOCKED }; /* * LANE2: new argument struct sk_buff *data contains * the LE_ARP based TLVs introduced in the LANE2 spec */ -static int -send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, - unsigned char *mac_addr, unsigned char *atm_addr, - struct sk_buff *data) +static int +send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, + unsigned char *mac_addr, unsigned char *atm_addr, + struct sk_buff *data) { struct sock *sk; struct sk_buff *skb; @@ -621,187 +654,193 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, return -1; skb->len = sizeof(struct atmlec_msg); mesg = (struct atmlec_msg *)skb->data; - memset(mesg, 0, sizeof(struct atmlec_msg)); + memset(mesg, 0, sizeof(struct atmlec_msg)); mesg->type = type; - if (data != NULL) - mesg->sizeoftlvs = data->len; + if (data != NULL) + mesg->sizeoftlvs = data->len; if (mac_addr) memcpy(&mesg->content.normal.mac_addr, mac_addr, ETH_ALEN); - else - mesg->content.normal.targetless_le_arp = 1; + else + mesg->content.normal.targetless_le_arp = 1; if (atm_addr) memcpy(&mesg->content.normal.atm_addr, atm_addr, ATM_ESA_LEN); - atm_force_charge(priv->lecd, skb->truesize); + atm_force_charge(priv->lecd, skb->truesize); sk = sk_atm(priv->lecd); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk, skb->len); - if (data != NULL) { - DPRINTK("lec: about to send %d bytes of data\n", data->len); - atm_force_charge(priv->lecd, data->truesize); - skb_queue_tail(&sk->sk_receive_queue, data); - sk->sk_data_ready(sk, skb->len); - } + if (data != NULL) { + DPRINTK("lec: about to send %d bytes of data\n", data->len); + atm_force_charge(priv->lecd, data->truesize); + skb_queue_tail(&sk->sk_receive_queue, data); + sk->sk_data_ready(sk, skb->len); + } - return 0; + return 0; } /* shamelessly stolen from drivers/net/net_init.c */ static int lec_change_mtu(struct net_device *dev, int new_mtu) { - if ((new_mtu < 68) || (new_mtu > 18190)) - return -EINVAL; - dev->mtu = new_mtu; - return 0; + if ((new_mtu < 68) || (new_mtu > 18190)) + return -EINVAL; + dev->mtu = new_mtu; + return 0; } static void lec_set_multicast_list(struct net_device *dev) { - /* by default, all multicast frames arrive over the bus. - * eventually support selective multicast service - */ - return; + /* + * by default, all multicast frames arrive over the bus. + * eventually support selective multicast service + */ + return; } -static void -lec_init(struct net_device *dev) +static void lec_init(struct net_device *dev) { - dev->change_mtu = lec_change_mtu; - dev->open = lec_open; - dev->stop = lec_close; - dev->hard_start_xmit = lec_start_xmit; + dev->change_mtu = lec_change_mtu; + dev->open = lec_open; + dev->stop = lec_close; + dev->hard_start_xmit = lec_start_xmit; dev->tx_timeout = lec_tx_timeout; - dev->get_stats = lec_get_stats; - dev->set_multicast_list = lec_set_multicast_list; - dev->do_ioctl = NULL; - printk("%s: Initialized!\n",dev->name); - return; + dev->get_stats = lec_get_stats; + dev->set_multicast_list = lec_set_multicast_list; + dev->do_ioctl = NULL; + printk("%s: Initialized!\n", dev->name); + return; } static unsigned char lec_ctrl_magic[] = { - 0xff, - 0x00, - 0x01, - 0x01 }; + 0xff, + 0x00, + 0x01, + 0x01 +}; #define LEC_DATA_DIRECT_8023 2 #define LEC_DATA_DIRECT_8025 3 static int lec_is_data_direct(struct atm_vcc *vcc) -{ +{ return ((vcc->sap.blli[0].l3.tr9577.snap[4] == LEC_DATA_DIRECT_8023) || (vcc->sap.blli[0].l3.tr9577.snap[4] == LEC_DATA_DIRECT_8025)); -} +} -static void -lec_push(struct atm_vcc *vcc, struct sk_buff *skb) +static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb) { unsigned long flags; - struct net_device *dev = (struct net_device *)vcc->proto_data; - struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct net_device *dev = (struct net_device *)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv *)dev->priv; #if DUMP_PACKETS >0 - int i=0; - char buf[300]; + int i = 0; + char buf[300]; - printk("%s: lec_push vcc vpi:%d vci:%d\n", dev->name, - vcc->vpi, vcc->vci); + printk("%s: lec_push vcc vpi:%d vci:%d\n", dev->name, + vcc->vpi, vcc->vci); #endif - if (!skb) { - DPRINTK("%s: null skb\n",dev->name); - lec_vcc_close(priv, vcc); - return; - } + if (!skb) { + DPRINTK("%s: null skb\n", dev->name); + lec_vcc_close(priv, vcc); + return; + } #if DUMP_PACKETS > 0 - printk("%s: rcv datalen:%ld lecid:%4.4x\n", dev->name, - skb->len, priv->lecid); + printk("%s: rcv datalen:%ld lecid:%4.4x\n", dev->name, + skb->len, priv->lecid); #if DUMP_PACKETS >= 2 - for(i=0;i<skb->len && i <99;i++) { - sprintf(buf+i*3,"%2.2x ",0xff&skb->data[i]); - } + for (i = 0; i < skb->len && i < 99; i++) { + sprintf(buf + i * 3, "%2.2x ", 0xff & skb->data[i]); + } #elif DUMP_PACKETS >= 1 - for(i=0;i<skb->len && i < 30;i++) { - sprintf(buf+i*3,"%2.2x ", 0xff&skb->data[i]); - } + for (i = 0; i < skb->len && i < 30; i++) { + sprintf(buf + i * 3, "%2.2x ", 0xff & skb->data[i]); + } #endif /* DUMP_PACKETS >= 1 */ - if (i==skb->len) - printk("%s\n",buf); - else - printk("%s...\n",buf); + if (i == skb->len) + printk("%s\n", buf); + else + printk("%s...\n", buf); #endif /* DUMP_PACKETS > 0 */ - if (memcmp(skb->data, lec_ctrl_magic, 4) ==0) { /* Control frame, to daemon*/ + if (memcmp(skb->data, lec_ctrl_magic, 4) == 0) { /* Control frame, to daemon */ struct sock *sk = sk_atm(vcc); - DPRINTK("%s: To daemon\n",dev->name); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); - } else { /* Data frame, queue to protocol handlers */ + DPRINTK("%s: To daemon\n", dev->name); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + } else { /* Data frame, queue to protocol handlers */ struct lec_arp_table *entry; - unsigned char *src, *dst; - - atm_return(vcc,skb->truesize); - if (*(uint16_t *)skb->data == htons(priv->lecid) || - !priv->lecd || - !(dev->flags & IFF_UP)) { - /* Probably looping back, or if lecd is missing, - lecd has gone down */ - DPRINTK("Ignoring frame...\n"); - dev_kfree_skb(skb); - return; - } + unsigned char *src, *dst; + + atm_return(vcc, skb->truesize); + if (*(uint16_t *) skb->data == htons(priv->lecid) || + !priv->lecd || !(dev->flags & IFF_UP)) { + /* + * Probably looping back, or if lecd is missing, + * lecd has gone down + */ + DPRINTK("Ignoring frame...\n"); + dev_kfree_skb(skb); + return; + } #ifdef CONFIG_TR - if (priv->is_trdev) - dst = ((struct lecdatahdr_8025 *) skb->data)->h_dest; - else + if (priv->is_trdev) + dst = ((struct lecdatahdr_8025 *)skb->data)->h_dest; + else #endif - dst = ((struct lecdatahdr_8023 *) skb->data)->h_dest; + dst = ((struct lecdatahdr_8023 *)skb->data)->h_dest; - /* If this is a Data Direct VCC, and the VCC does not match + /* + * If this is a Data Direct VCC, and the VCC does not match * the LE_ARP cache entry, delete the LE_ARP cache entry. */ spin_lock_irqsave(&priv->lec_arp_lock, flags); if (lec_is_data_direct(vcc)) { #ifdef CONFIG_TR if (priv->is_trdev) - src = ((struct lecdatahdr_8025 *) skb->data)->h_source; + src = + ((struct lecdatahdr_8025 *)skb->data)-> + h_source; else #endif - src = ((struct lecdatahdr_8023 *) skb->data)->h_source; + src = + ((struct lecdatahdr_8023 *)skb->data)-> + h_source; entry = lec_arp_find(priv, src); if (entry && entry->vcc != vcc) { lec_arp_remove(priv, entry); - kfree(entry); + lec_arp_put(entry); } } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - if (!(dst[0]&0x01) && /* Never filter Multi/Broadcast */ - !priv->is_proxy && /* Proxy wants all the packets */ + if (!(dst[0] & 0x01) && /* Never filter Multi/Broadcast */ + !priv->is_proxy && /* Proxy wants all the packets */ memcmp(dst, dev->dev_addr, dev->addr_len)) { - dev_kfree_skb(skb); - return; - } - if (priv->lec_arp_empty_ones) { - lec_arp_check_empties(priv, vcc, skb); - } - skb->dev = dev; - skb_pull(skb, 2); /* skip lec_id */ + dev_kfree_skb(skb); + return; + } + if (!hlist_empty(&priv->lec_arp_empty_ones)) { + lec_arp_check_empties(priv, vcc, skb); + } + skb->dev = dev; + skb_pull(skb, 2); /* skip lec_id */ #ifdef CONFIG_TR - if (priv->is_trdev) skb->protocol = tr_type_trans(skb, dev); - else + if (priv->is_trdev) + skb->protocol = tr_type_trans(skb, dev); + else #endif - skb->protocol = eth_type_trans(skb, dev); - priv->stats.rx_packets++; - priv->stats.rx_bytes += skb->len; - memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); - netif_rx(skb); - } + skb->protocol = eth_type_trans(skb, dev); + priv->stats.rx_packets++; + priv->stats.rx_bytes += skb->len; + memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); + netif_rx(skb); + } } -static void -lec_pop(struct atm_vcc *vcc, struct sk_buff *skb) +static void lec_pop(struct atm_vcc *vcc, struct sk_buff *skb) { struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); struct net_device *dev = skb->dev; @@ -820,123 +859,121 @@ lec_pop(struct atm_vcc *vcc, struct sk_buff *skb) } } -static int -lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) +static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) { struct lec_vcc_priv *vpriv; - int bytes_left; - struct atmlec_ioc ioc_data; - - /* Lecd must be up in this case */ - bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); - if (bytes_left != 0) { - printk("lec: lec_vcc_attach, copy from user failed for %d bytes\n", - bytes_left); - } - if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || - !dev_lec[ioc_data.dev_num]) - return -EINVAL; + int bytes_left; + struct atmlec_ioc ioc_data; + + /* Lecd must be up in this case */ + bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); + if (bytes_left != 0) { + printk + ("lec: lec_vcc_attach, copy from user failed for %d bytes\n", + bytes_left); + } + if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || + !dev_lec[ioc_data.dev_num]) + return -EINVAL; if (!(vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL))) return -ENOMEM; vpriv->xoff = 0; vpriv->old_pop = vcc->pop; vcc->user_back = vpriv; vcc->pop = lec_pop; - lec_vcc_added(dev_lec[ioc_data.dev_num]->priv, - &ioc_data, vcc, vcc->push); - vcc->proto_data = dev_lec[ioc_data.dev_num]; - vcc->push = lec_push; - return 0; + lec_vcc_added(dev_lec[ioc_data.dev_num]->priv, + &ioc_data, vcc, vcc->push); + vcc->proto_data = dev_lec[ioc_data.dev_num]; + vcc->push = lec_push; + return 0; } -static int -lec_mcast_attach(struct atm_vcc *vcc, int arg) +static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { - if (arg <0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) - return -EINVAL; - vcc->proto_data = dev_lec[arg]; - return (lec_mcast_make((struct lec_priv*)dev_lec[arg]->priv, vcc)); + if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) + return -EINVAL; + vcc->proto_data = dev_lec[arg]; + return (lec_mcast_make((struct lec_priv *)dev_lec[arg]->priv, vcc)); } /* Initialize device. */ -static int -lecd_attach(struct atm_vcc *vcc, int arg) -{ - int i; - struct lec_priv *priv; - - if (arg<0) - i = 0; - else - i = arg; +static int lecd_attach(struct atm_vcc *vcc, int arg) +{ + int i; + struct lec_priv *priv; + + if (arg < 0) + i = 0; + else + i = arg; #ifdef CONFIG_TR - if (arg >= MAX_LEC_ITF) - return -EINVAL; -#else /* Reserve the top NUM_TR_DEVS for TR */ - if (arg >= (MAX_LEC_ITF-NUM_TR_DEVS)) - return -EINVAL; + if (arg >= MAX_LEC_ITF) + return -EINVAL; +#else /* Reserve the top NUM_TR_DEVS for TR */ + if (arg >= (MAX_LEC_ITF - NUM_TR_DEVS)) + return -EINVAL; #endif - if (!dev_lec[i]) { - int is_trdev, size; + if (!dev_lec[i]) { + int is_trdev, size; - is_trdev = 0; - if (i >= (MAX_LEC_ITF - NUM_TR_DEVS)) - is_trdev = 1; + is_trdev = 0; + if (i >= (MAX_LEC_ITF - NUM_TR_DEVS)) + is_trdev = 1; - size = sizeof(struct lec_priv); + size = sizeof(struct lec_priv); #ifdef CONFIG_TR - if (is_trdev) - dev_lec[i] = alloc_trdev(size); - else + if (is_trdev) + dev_lec[i] = alloc_trdev(size); + else #endif - dev_lec[i] = alloc_etherdev(size); - if (!dev_lec[i]) - return -ENOMEM; - snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i); - if (register_netdev(dev_lec[i])) { - free_netdev(dev_lec[i]); - return -EINVAL; - } - - priv = dev_lec[i]->priv; - priv->is_trdev = is_trdev; - lec_init(dev_lec[i]); - } else { - priv = dev_lec[i]->priv; - if (priv->lecd) - return -EADDRINUSE; - } - lec_arp_init(priv); - priv->itfnum = i; /* LANE2 addition */ - priv->lecd = vcc; - vcc->dev = &lecatm_dev; - vcc_insert_socket(sk_atm(vcc)); - - vcc->proto_data = dev_lec[i]; - set_bit(ATM_VF_META,&vcc->flags); - set_bit(ATM_VF_READY,&vcc->flags); - - /* Set default values to these variables */ - priv->maximum_unknown_frame_count = 1; - priv->max_unknown_frame_time = (1*HZ); - priv->vcc_timeout_period = (1200*HZ); - priv->max_retry_count = 1; - priv->aging_time = (300*HZ); - priv->forward_delay_time = (15*HZ); - priv->topology_change = 0; - priv->arp_response_time = (1*HZ); - priv->flush_timeout = (4*HZ); - priv->path_switching_delay = (6*HZ); - - if (dev_lec[i]->flags & IFF_UP) { - netif_start_queue(dev_lec[i]); - } - __module_get(THIS_MODULE); - return i; + dev_lec[i] = alloc_etherdev(size); + if (!dev_lec[i]) + return -ENOMEM; + snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i); + if (register_netdev(dev_lec[i])) { + free_netdev(dev_lec[i]); + return -EINVAL; + } + + priv = dev_lec[i]->priv; + priv->is_trdev = is_trdev; + lec_init(dev_lec[i]); + } else { + priv = dev_lec[i]->priv; + if (priv->lecd) + return -EADDRINUSE; + } + lec_arp_init(priv); + priv->itfnum = i; /* LANE2 addition */ + priv->lecd = vcc; + vcc->dev = &lecatm_dev; + vcc_insert_socket(sk_atm(vcc)); + + vcc->proto_data = dev_lec[i]; + set_bit(ATM_VF_META, &vcc->flags); + set_bit(ATM_VF_READY, &vcc->flags); + + /* Set default values to these variables */ + priv->maximum_unknown_frame_count = 1; + priv->max_unknown_frame_time = (1 * HZ); + priv->vcc_timeout_period = (1200 * HZ); + priv->max_retry_count = 1; + priv->aging_time = (300 * HZ); + priv->forward_delay_time = (15 * HZ); + priv->topology_change = 0; + priv->arp_response_time = (1 * HZ); + priv->flush_timeout = (4 * HZ); + priv->path_switching_delay = (6 * HZ); + + if (dev_lec[i]->flags & IFF_UP) { + netif_start_queue(dev_lec[i]); + } + __module_get(THIS_MODULE); + return i; } #ifdef CONFIG_PROC_FS -static char* lec_arp_get_status_string(unsigned char status) +static char *lec_arp_get_status_string(unsigned char status) { static char *lec_arp_status_string[] = { "ESI_UNKNOWN ", @@ -966,52 +1003,54 @@ static void lec_info(struct seq_file *seq, struct lec_arp_table *entry) if (entry->vcc) seq_printf(seq, "%3d %3d ", entry->vcc->vpi, entry->vcc->vci); else - seq_printf(seq, " "); + seq_printf(seq, " "); if (entry->recv_vcc) { seq_printf(seq, " %3d %3d", entry->recv_vcc->vpi, entry->recv_vcc->vci); - } - seq_putc(seq, '\n'); + } + seq_putc(seq, '\n'); } - struct lec_state { unsigned long flags; struct lec_priv *locked; - struct lec_arp_table *entry; + struct hlist_node *node; struct net_device *dev; int itf; int arp_table; int misc_table; }; -static void *lec_tbl_walk(struct lec_state *state, struct lec_arp_table *tbl, +static void *lec_tbl_walk(struct lec_state *state, struct hlist_head *tbl, loff_t *l) { - struct lec_arp_table *e = state->entry; + struct hlist_node *e = state->node; + struct lec_arp_table *tmp; if (!e) - e = tbl; + e = tbl->first; if (e == (void *)1) { - e = tbl; + e = tbl->first; --*l; } - for (; e; e = e->next) { + + hlist_for_each_entry_from(tmp, e, next) { if (--*l < 0) break; } - state->entry = e; + state->node = e; + return (*l < 0) ? state : NULL; } static void *lec_arp_walk(struct lec_state *state, loff_t *l, - struct lec_priv *priv) + struct lec_priv *priv) { void *v = NULL; int p; for (p = state->arp_table; p < LEC_ARP_TABLE_SIZE; p++) { - v = lec_tbl_walk(state, priv->lec_arp_tables[p], l); + v = lec_tbl_walk(state, &priv->lec_arp_tables[p], l); if (v) break; } @@ -1022,10 +1061,10 @@ static void *lec_arp_walk(struct lec_state *state, loff_t *l, static void *lec_misc_walk(struct lec_state *state, loff_t *l, struct lec_priv *priv) { - struct lec_arp_table *lec_misc_tables[] = { - priv->lec_arp_empty_ones, - priv->lec_no_forward, - priv->mcast_fwds + struct hlist_head *lec_misc_tables[] = { + &priv->lec_arp_empty_ones, + &priv->lec_no_forward, + &priv->mcast_fwds }; void *v = NULL; int q; @@ -1046,8 +1085,7 @@ static void *lec_priv_walk(struct lec_state *state, loff_t *l, state->locked = priv; spin_lock_irqsave(&priv->lec_arp_lock, state->flags); } - if (!lec_arp_walk(state, l, priv) && - !lec_misc_walk(state, l, priv)) { + if (!lec_arp_walk(state, l, priv) && !lec_misc_walk(state, l, priv)) { spin_unlock_irqrestore(&priv->lec_arp_lock, state->flags); state->locked = NULL; /* Partial state reset for the next time we get called */ @@ -1081,7 +1119,7 @@ static void *lec_get_idx(struct lec_state *state, loff_t l) if (v) break; } - return v; + return v; } static void *lec_seq_start(struct seq_file *seq, loff_t *pos) @@ -1093,9 +1131,9 @@ static void *lec_seq_start(struct seq_file *seq, loff_t *pos) state->locked = NULL; state->arp_table = 0; state->misc_table = 0; - state->entry = (void *)1; + state->node = (void *)1; - return *pos ? lec_get_idx(state, *pos) : (void*)1; + return *pos ? lec_get_idx(state, *pos) : (void *)1; } static void lec_seq_stop(struct seq_file *seq, void *v) @@ -1120,27 +1158,28 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) static int lec_seq_show(struct seq_file *seq, void *v) { - static char lec_banner[] = "Itf MAC ATM destination" - " Status Flags " - "VPI/VCI Recv VPI/VCI\n"; + static char lec_banner[] = "Itf MAC ATM destination" + " Status Flags " + "VPI/VCI Recv VPI/VCI\n"; if (v == (void *)1) seq_puts(seq, lec_banner); else { struct lec_state *state = seq->private; - struct net_device *dev = state->dev; + struct net_device *dev = state->dev; + struct lec_arp_table *entry = hlist_entry(state->node, struct lec_arp_table, next); seq_printf(seq, "%s ", dev->name); - lec_info(seq, state->entry); + lec_info(seq, entry); } return 0; } static struct seq_operations lec_seq_ops = { - .start = lec_seq_start, - .next = lec_seq_next, - .stop = lec_seq_stop, - .show = lec_seq_show, + .start = lec_seq_start, + .next = lec_seq_next, + .stop = lec_seq_stop, + .show = lec_seq_show, }; static int lec_seq_open(struct inode *inode, struct file *file) @@ -1174,11 +1213,11 @@ static int lec_seq_release(struct inode *inode, struct file *file) } static struct file_operations lec_seq_fops = { - .owner = THIS_MODULE, - .open = lec_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = lec_seq_release, + .owner = THIS_MODULE, + .open = lec_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = lec_seq_release, }; #endif @@ -1186,38 +1225,38 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct atm_vcc *vcc = ATM_SD(sock); int err = 0; - + switch (cmd) { - case ATMLEC_CTRL: - case ATMLEC_MCAST: - case ATMLEC_DATA: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - break; - default: - return -ENOIOCTLCMD; + case ATMLEC_CTRL: + case ATMLEC_MCAST: + case ATMLEC_DATA: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + break; + default: + return -ENOIOCTLCMD; } switch (cmd) { - case ATMLEC_CTRL: - err = lecd_attach(vcc, (int) arg); - if (err >= 0) - sock->state = SS_CONNECTED; - break; - case ATMLEC_MCAST: - err = lec_mcast_attach(vcc, (int) arg); - break; - case ATMLEC_DATA: - err = lec_vcc_attach(vcc, (void __user *) arg); - break; + case ATMLEC_CTRL: + err = lecd_attach(vcc, (int)arg); + if (err >= 0) + sock->state = SS_CONNECTED; + break; + case ATMLEC_MCAST: + err = lec_mcast_attach(vcc, (int)arg); + break; + case ATMLEC_DATA: + err = lec_vcc_attach(vcc, (void __user *)arg); + break; } return err; } static struct atm_ioctl lane_ioctl_ops = { - .owner = THIS_MODULE, - .ioctl = lane_ioctl, + .owner = THIS_MODULE, + .ioctl = lane_ioctl, }; static int __init lane_module_init(void) @@ -1231,29 +1270,29 @@ static int __init lane_module_init(void) #endif register_atm_ioctl(&lane_ioctl_ops); - printk("lec.c: " __DATE__ " " __TIME__ " initialized\n"); - return 0; + printk("lec.c: " __DATE__ " " __TIME__ " initialized\n"); + return 0; } static void __exit lane_module_cleanup(void) { - int i; - struct lec_priv *priv; + int i; + struct lec_priv *priv; remove_proc_entry("lec", atm_proc_root); deregister_atm_ioctl(&lane_ioctl_ops); - for (i = 0; i < MAX_LEC_ITF; i++) { - if (dev_lec[i] != NULL) { - priv = (struct lec_priv *)dev_lec[i]->priv; + for (i = 0; i < MAX_LEC_ITF; i++) { + if (dev_lec[i] != NULL) { + priv = (struct lec_priv *)dev_lec[i]->priv; unregister_netdev(dev_lec[i]); - free_netdev(dev_lec[i]); - dev_lec[i] = NULL; - } - } + free_netdev(dev_lec[i]); + dev_lec[i] = NULL; + } + } - return; + return; } module_init(lane_module_init); @@ -1267,34 +1306,34 @@ module_exit(lane_module_cleanup); * If dst_mac == NULL, targetless LE_ARP will be sent */ static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, - u8 **tlvs, u32 *sizeoftlvs) + u8 **tlvs, u32 *sizeoftlvs) { unsigned long flags; - struct lec_priv *priv = (struct lec_priv *)dev->priv; - struct lec_arp_table *table; - struct sk_buff *skb; - int retval; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct lec_arp_table *table; + struct sk_buff *skb; + int retval; - if (force == 0) { + if (force == 0) { spin_lock_irqsave(&priv->lec_arp_lock, flags); - table = lec_arp_find(priv, dst_mac); + table = lec_arp_find(priv, dst_mac); spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - if(table == NULL) - return -1; - - *tlvs = kmalloc(table->sizeoftlvs, GFP_ATOMIC); - if (*tlvs == NULL) - return -1; - - memcpy(*tlvs, table->tlvs, table->sizeoftlvs); - *sizeoftlvs = table->sizeoftlvs; - - return 0; - } + if (table == NULL) + return -1; + + *tlvs = kmalloc(table->sizeoftlvs, GFP_ATOMIC); + if (*tlvs == NULL) + return -1; + + memcpy(*tlvs, table->tlvs, table->sizeoftlvs); + *sizeoftlvs = table->sizeoftlvs; + + return 0; + } if (sizeoftlvs == NULL) retval = send_to_lecd(priv, l_arp_xmt, dst_mac, NULL, NULL); - + else { skb = alloc_skb(*sizeoftlvs, GFP_ATOMIC); if (skb == NULL) @@ -1303,9 +1342,8 @@ static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, memcpy(skb->data, *tlvs, *sizeoftlvs); retval = send_to_lecd(priv, l_arp_xmt, dst_mac, NULL, skb); } - return retval; -} - + return retval; +} /* * LANE2: 3.1.4, LE_ASSOCIATE.request @@ -1314,80 +1352,85 @@ static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, * Returns 1 for success, 0 for failure (out of memory) * */ -static int lane2_associate_req (struct net_device *dev, u8 *lan_dst, - u8 *tlvs, u32 sizeoftlvs) +static int lane2_associate_req(struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs) { - int retval; - struct sk_buff *skb; - struct lec_priv *priv = (struct lec_priv*)dev->priv; - - if (compare_ether_addr(lan_dst, dev->dev_addr)) - return (0); /* not our mac address */ - - kfree(priv->tlvs); /* NULL if there was no previous association */ - - priv->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); - if (priv->tlvs == NULL) - return (0); - priv->sizeoftlvs = sizeoftlvs; - memcpy(priv->tlvs, tlvs, sizeoftlvs); - - skb = alloc_skb(sizeoftlvs, GFP_ATOMIC); - if (skb == NULL) - return 0; - skb->len = sizeoftlvs; - memcpy(skb->data, tlvs, sizeoftlvs); - retval = send_to_lecd(priv, l_associate_req, NULL, NULL, skb); - if (retval != 0) - printk("lec.c: lane2_associate_req() failed\n"); - /* If the previous association has changed we must - * somehow notify other LANE entities about the change - */ - return (1); + int retval; + struct sk_buff *skb; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + + if (compare_ether_addr(lan_dst, dev->dev_addr)) + return (0); /* not our mac address */ + + kfree(priv->tlvs); /* NULL if there was no previous association */ + + priv->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); + if (priv->tlvs == NULL) + return (0); + priv->sizeoftlvs = sizeoftlvs; + memcpy(priv->tlvs, tlvs, sizeoftlvs); + + skb = alloc_skb(sizeoftlvs, GFP_ATOMIC); + if (skb == NULL) + return 0; + skb->len = sizeoftlvs; + memcpy(skb->data, tlvs, sizeoftlvs); + retval = send_to_lecd(priv, l_associate_req, NULL, NULL, skb); + if (retval != 0) + printk("lec.c: lane2_associate_req() failed\n"); + /* + * If the previous association has changed we must + * somehow notify other LANE entities about the change + */ + return (1); } /* * LANE2: 3.1.5, LE_ASSOCIATE.indication * */ -static void lane2_associate_ind (struct net_device *dev, u8 *mac_addr, - u8 *tlvs, u32 sizeoftlvs) +static void lane2_associate_ind(struct net_device *dev, u8 *mac_addr, + u8 *tlvs, u32 sizeoftlvs) { #if 0 - int i = 0; + int i = 0; #endif struct lec_priv *priv = (struct lec_priv *)dev->priv; -#if 0 /* Why have the TLVs in LE_ARP entries since we do not use them? When you - uncomment this code, make sure the TLVs get freed when entry is killed */ - struct lec_arp_table *entry = lec_arp_find(priv, mac_addr); +#if 0 /* + * Why have the TLVs in LE_ARP entries + * since we do not use them? When you + * uncomment this code, make sure the + * TLVs get freed when entry is killed + */ + struct lec_arp_table *entry = lec_arp_find(priv, mac_addr); - if (entry == NULL) - return; /* should not happen */ + if (entry == NULL) + return; /* should not happen */ - kfree(entry->tlvs); + kfree(entry->tlvs); - entry->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); - if (entry->tlvs == NULL) - return; + entry->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); + if (entry->tlvs == NULL) + return; - entry->sizeoftlvs = sizeoftlvs; - memcpy(entry->tlvs, tlvs, sizeoftlvs); + entry->sizeoftlvs = sizeoftlvs; + memcpy(entry->tlvs, tlvs, sizeoftlvs); #endif #if 0 - printk("lec.c: lane2_associate_ind()\n"); - printk("dump of tlvs, sizeoftlvs=%d\n", sizeoftlvs); - while (i < sizeoftlvs) - printk("%02x ", tlvs[i++]); - - printk("\n"); + printk("lec.c: lane2_associate_ind()\n"); + printk("dump of tlvs, sizeoftlvs=%d\n", sizeoftlvs); + while (i < sizeoftlvs) + printk("%02x ", tlvs[i++]); + + printk("\n"); #endif - /* tell MPOA about the TLVs we saw */ - if (priv->lane2_ops && priv->lane2_ops->associate_indicator) { - priv->lane2_ops->associate_indicator(dev, mac_addr, - tlvs, sizeoftlvs); - } - return; + /* tell MPOA about the TLVs we saw */ + if (priv->lane2_ops && priv->lane2_ops->associate_indicator) { + priv->lane2_ops->associate_indicator(dev, mac_addr, + tlvs, sizeoftlvs); + } + return; } /* @@ -1395,7 +1438,6 @@ static void lane2_associate_ind (struct net_device *dev, u8 *mac_addr, * * lec_arpc.c was added here when making * lane client modular. October 1997 - * */ #include <linux/types.h> @@ -1406,7 +1448,6 @@ static void lane2_associate_ind (struct net_device *dev, u8 *mac_addr, #include <linux/inetdevice.h> #include <net/route.h> - #if 0 #define DPRINTK(format,args...) /* @@ -1417,7 +1458,7 @@ static void lane2_associate_ind (struct net_device *dev, u8 *mac_addr, #define LEC_ARP_REFRESH_INTERVAL (3*HZ) -static void lec_arp_check_expire(unsigned long data); +static void lec_arp_check_expire(void *data); static void lec_arp_expire_arp(unsigned long data); /* @@ -1429,474 +1470,397 @@ static void lec_arp_expire_arp(unsigned long data); /* * Initialization of arp-cache */ -static void -lec_arp_init(struct lec_priv *priv) +static void lec_arp_init(struct lec_priv *priv) { - unsigned short i; + unsigned short i; - for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - priv->lec_arp_tables[i] = NULL; - } + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + INIT_HLIST_HEAD(&priv->lec_arp_tables[i]); + } + INIT_HLIST_HEAD(&priv->lec_arp_empty_ones); + INIT_HLIST_HEAD(&priv->lec_no_forward); + INIT_HLIST_HEAD(&priv->mcast_fwds); spin_lock_init(&priv->lec_arp_lock); - init_timer(&priv->lec_arp_timer); - priv->lec_arp_timer.expires = jiffies + LEC_ARP_REFRESH_INTERVAL; - priv->lec_arp_timer.data = (unsigned long)priv; - priv->lec_arp_timer.function = lec_arp_check_expire; - add_timer(&priv->lec_arp_timer); + INIT_WORK(&priv->lec_arp_work, lec_arp_check_expire, priv); + schedule_delayed_work(&priv->lec_arp_work, LEC_ARP_REFRESH_INTERVAL); } -static void -lec_arp_clear_vccs(struct lec_arp_table *entry) +static void lec_arp_clear_vccs(struct lec_arp_table *entry) { - if (entry->vcc) { + if (entry->vcc) { struct atm_vcc *vcc = entry->vcc; struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); - struct net_device *dev = (struct net_device*) vcc->proto_data; + struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; + vcc->pop = vpriv->old_pop; if (vpriv->xoff) netif_wake_queue(dev); kfree(vpriv); vcc->user_back = NULL; - vcc->push = entry->old_push; + vcc->push = entry->old_push; vcc_release_async(vcc, -EPIPE); - vcc = NULL; - } - if (entry->recv_vcc) { - entry->recv_vcc->push = entry->old_recv_push; + entry->vcc = NULL; + } + if (entry->recv_vcc) { + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); - entry->recv_vcc = NULL; - } + entry->recv_vcc = NULL; + } } /* * Insert entry to lec_arp_table * LANE2: Add to the end of the list to satisfy 8.1.13 */ -static inline void -lec_arp_add(struct lec_priv *priv, struct lec_arp_table *to_add) +static inline void +lec_arp_add(struct lec_priv *priv, struct lec_arp_table *entry) { - unsigned short place; - struct lec_arp_table *tmp; - - place = HASH(to_add->mac_addr[ETH_ALEN-1]); - tmp = priv->lec_arp_tables[place]; - to_add->next = NULL; - if (tmp == NULL) - priv->lec_arp_tables[place] = to_add; - - else { /* add to the end */ - while (tmp->next) - tmp = tmp->next; - tmp->next = to_add; - } - - DPRINTK("LEC_ARP: Added entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", - 0xff&to_add->mac_addr[0], 0xff&to_add->mac_addr[1], - 0xff&to_add->mac_addr[2], 0xff&to_add->mac_addr[3], - 0xff&to_add->mac_addr[4], 0xff&to_add->mac_addr[5]); + struct hlist_head *tmp; + + tmp = &priv->lec_arp_tables[HASH(entry->mac_addr[ETH_ALEN - 1])]; + hlist_add_head(&entry->next, tmp); + + DPRINTK("LEC_ARP: Added entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + 0xff & entry->mac_addr[0], 0xff & entry->mac_addr[1], + 0xff & entry->mac_addr[2], 0xff & entry->mac_addr[3], + 0xff & entry->mac_addr[4], 0xff & entry->mac_addr[5]); } /* * Remove entry from lec_arp_table */ -static int -lec_arp_remove(struct lec_priv *priv, - struct lec_arp_table *to_remove) +static int +lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) { - unsigned short place; - struct lec_arp_table *tmp; - int remove_vcc=1; - - if (!to_remove) { - return -1; - } - place = HASH(to_remove->mac_addr[ETH_ALEN-1]); - tmp = priv->lec_arp_tables[place]; - if (tmp == to_remove) { - priv->lec_arp_tables[place] = tmp->next; - } else { - while(tmp && tmp->next != to_remove) { - tmp = tmp->next; - } - if (!tmp) {/* Entry was not found */ - return -1; - } - } - tmp->next = to_remove->next; - del_timer(&to_remove->timer); - - /* If this is the only MAC connected to this VCC, also tear down - the VCC */ - if (to_remove->status >= ESI_FLUSH_PENDING) { - /* - * ESI_FLUSH_PENDING, ESI_FORWARD_DIRECT - */ - for(place = 0; place < LEC_ARP_TABLE_SIZE; place++) { - for(tmp = priv->lec_arp_tables[place]; tmp != NULL; tmp = tmp->next) { - if (memcmp(tmp->atm_addr, to_remove->atm_addr, - ATM_ESA_LEN)==0) { - remove_vcc=0; - break; - } - } - } - if (remove_vcc) - lec_arp_clear_vccs(to_remove); - } - skb_queue_purge(&to_remove->tx_wait); /* FIXME: good place for this? */ - - DPRINTK("LEC_ARP: Removed entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", - 0xff&to_remove->mac_addr[0], 0xff&to_remove->mac_addr[1], - 0xff&to_remove->mac_addr[2], 0xff&to_remove->mac_addr[3], - 0xff&to_remove->mac_addr[4], 0xff&to_remove->mac_addr[5]); - return 0; + struct hlist_node *node; + struct lec_arp_table *entry; + int i, remove_vcc = 1; + + if (!to_remove) { + return -1; + } + + hlist_del(&to_remove->next); + del_timer(&to_remove->timer); + + /* If this is the only MAC connected to this VCC, also tear down the VCC */ + if (to_remove->status >= ESI_FLUSH_PENDING) { + /* + * ESI_FLUSH_PENDING, ESI_FORWARD_DIRECT + */ + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry(entry, node, &priv->lec_arp_tables[i], next) { + if (memcmp(to_remove->atm_addr, + entry->atm_addr, ATM_ESA_LEN) == 0) { + remove_vcc = 0; + break; + } + } + } + if (remove_vcc) + lec_arp_clear_vccs(to_remove); + } + skb_queue_purge(&to_remove->tx_wait); /* FIXME: good place for this? */ + + DPRINTK("LEC_ARP: Removed entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + 0xff & to_remove->mac_addr[0], 0xff & to_remove->mac_addr[1], + 0xff & to_remove->mac_addr[2], 0xff & to_remove->mac_addr[3], + 0xff & to_remove->mac_addr[4], 0xff & to_remove->mac_addr[5]); + return 0; } #if DEBUG_ARP_TABLE -static char* -get_status_string(unsigned char st) +static char *get_status_string(unsigned char st) { - switch(st) { - case ESI_UNKNOWN: - return "ESI_UNKNOWN"; - case ESI_ARP_PENDING: - return "ESI_ARP_PENDING"; - case ESI_VC_PENDING: - return "ESI_VC_PENDING"; - case ESI_FLUSH_PENDING: - return "ESI_FLUSH_PENDING"; - case ESI_FORWARD_DIRECT: - return "ESI_FORWARD_DIRECT"; - default: - return "<UNKNOWN>"; - } + switch (st) { + case ESI_UNKNOWN: + return "ESI_UNKNOWN"; + case ESI_ARP_PENDING: + return "ESI_ARP_PENDING"; + case ESI_VC_PENDING: + return "ESI_VC_PENDING"; + case ESI_FLUSH_PENDING: + return "ESI_FLUSH_PENDING"; + case ESI_FORWARD_DIRECT: + return "ESI_FORWARD_DIRECT"; + default: + return "<UNKNOWN>"; + } } -#endif -static void -dump_arp_table(struct lec_priv *priv) +static void dump_arp_table(struct lec_priv *priv) { -#if DEBUG_ARP_TABLE - int i,j, offset; - struct lec_arp_table *rulla; - char buf[1024]; - struct lec_arp_table **lec_arp_tables = - (struct lec_arp_table **)priv->lec_arp_tables; - struct lec_arp_table *lec_arp_empty_ones = - (struct lec_arp_table *)priv->lec_arp_empty_ones; - struct lec_arp_table *lec_no_forward = - (struct lec_arp_table *)priv->lec_no_forward; - struct lec_arp_table *mcast_fwds = priv->mcast_fwds; - - - printk("Dump %p:\n",priv); - for (i=0;i<LEC_ARP_TABLE_SIZE;i++) { - rulla = lec_arp_tables[i]; - offset = 0; - offset += sprintf(buf,"%d: %p\n",i, rulla); - while (rulla) { - offset += sprintf(buf+offset,"Mac:"); - for(j=0;j<ETH_ALEN;j++) { - offset+=sprintf(buf+offset, - "%2.2x ", - rulla->mac_addr[j]&0xff); - } - offset +=sprintf(buf+offset,"Atm:"); - for(j=0;j<ATM_ESA_LEN;j++) { - offset+=sprintf(buf+offset, - "%2.2x ", - rulla->atm_addr[j]&0xff); - } - offset+=sprintf(buf+offset, - "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", - rulla->vcc?rulla->vcc->vpi:0, - rulla->vcc?rulla->vcc->vci:0, - rulla->recv_vcc?rulla->recv_vcc->vpi:0, - rulla->recv_vcc?rulla->recv_vcc->vci:0, - rulla->last_used, - rulla->timestamp, rulla->no_tries); - offset+=sprintf(buf+offset, - "Flags:%x, Packets_flooded:%x, Status: %s ", - rulla->flags, rulla->packets_flooded, - get_status_string(rulla->status)); - offset+=sprintf(buf+offset,"->%p\n",rulla->next); - rulla = rulla->next; - } - printk("%s",buf); - } - rulla = lec_no_forward; - if (rulla) - printk("No forward\n"); - while(rulla) { - offset=0; - offset += sprintf(buf+offset,"Mac:"); - for(j=0;j<ETH_ALEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->mac_addr[j]&0xff); - } - offset +=sprintf(buf+offset,"Atm:"); - for(j=0;j<ATM_ESA_LEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->atm_addr[j]&0xff); - } - offset+=sprintf(buf+offset, - "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", - rulla->vcc?rulla->vcc->vpi:0, - rulla->vcc?rulla->vcc->vci:0, - rulla->recv_vcc?rulla->recv_vcc->vpi:0, - rulla->recv_vcc?rulla->recv_vcc->vci:0, - rulla->last_used, - rulla->timestamp, rulla->no_tries); - offset+=sprintf(buf+offset, - "Flags:%x, Packets_flooded:%x, Status: %s ", - rulla->flags, rulla->packets_flooded, - get_status_string(rulla->status)); - offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); - rulla = rulla->next; - printk("%s",buf); - } - rulla = lec_arp_empty_ones; - if (rulla) - printk("Empty ones\n"); - while(rulla) { - offset=0; - offset += sprintf(buf+offset,"Mac:"); - for(j=0;j<ETH_ALEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->mac_addr[j]&0xff); - } - offset +=sprintf(buf+offset,"Atm:"); - for(j=0;j<ATM_ESA_LEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->atm_addr[j]&0xff); - } - offset+=sprintf(buf+offset, - "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", - rulla->vcc?rulla->vcc->vpi:0, - rulla->vcc?rulla->vcc->vci:0, - rulla->recv_vcc?rulla->recv_vcc->vpi:0, - rulla->recv_vcc?rulla->recv_vcc->vci:0, - rulla->last_used, - rulla->timestamp, rulla->no_tries); - offset+=sprintf(buf+offset, - "Flags:%x, Packets_flooded:%x, Status: %s ", - rulla->flags, rulla->packets_flooded, - get_status_string(rulla->status)); - offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); - rulla = rulla->next; - printk("%s",buf); - } - - rulla = mcast_fwds; - if (rulla) - printk("Multicast Forward VCCs\n"); - while(rulla) { - offset=0; - offset += sprintf(buf+offset,"Mac:"); - for(j=0;j<ETH_ALEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->mac_addr[j]&0xff); - } - offset +=sprintf(buf+offset,"Atm:"); - for(j=0;j<ATM_ESA_LEN;j++) { - offset+=sprintf(buf+offset,"%2.2x ", - rulla->atm_addr[j]&0xff); - } - offset+=sprintf(buf+offset, - "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", - rulla->vcc?rulla->vcc->vpi:0, - rulla->vcc?rulla->vcc->vci:0, - rulla->recv_vcc?rulla->recv_vcc->vpi:0, - rulla->recv_vcc?rulla->recv_vcc->vci:0, - rulla->last_used, - rulla->timestamp, rulla->no_tries); - offset+=sprintf(buf+offset, - "Flags:%x, Packets_flooded:%x, Status: %s ", - rulla->flags, rulla->packets_flooded, - get_status_string(rulla->status)); - offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); - rulla = rulla->next; - printk("%s",buf); - } + struct hlist_node *node; + struct lec_arp_table *rulla; + char buf[256]; + int i, j, offset; + + printk("Dump %p:\n", priv); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry(rulla, node, &priv->lec_arp_tables[i], next) { + offset = 0; + offset += sprintf(buf, "%d: %p\n", i, rulla); + offset += sprintf(buf + offset, "Mac:"); + for (j = 0; j < ETH_ALEN; j++) { + offset += sprintf(buf + offset, + "%2.2x ", + rulla->mac_addr[j] & 0xff); + } + offset += sprintf(buf + offset, "Atm:"); + for (j = 0; j < ATM_ESA_LEN; j++) { + offset += sprintf(buf + offset, + "%2.2x ", + rulla->atm_addr[j] & 0xff); + } + offset += sprintf(buf + offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc ? rulla->vcc->vpi : 0, + rulla->vcc ? rulla->vcc->vci : 0, + rulla->recv_vcc ? rulla->recv_vcc-> + vpi : 0, + rulla->recv_vcc ? rulla->recv_vcc-> + vci : 0, rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset += + sprintf(buf + offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + printk("%s\n", buf); + } + } + + if (!hlist_empty(&priv->lec_no_forward)) + printk("No forward\n"); + hlist_for_each_entry(rulla, node, &priv->lec_no_forward, next) { + offset = 0; + offset += sprintf(buf + offset, "Mac:"); + for (j = 0; j < ETH_ALEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->mac_addr[j] & 0xff); + } + offset += sprintf(buf + offset, "Atm:"); + for (j = 0; j < ATM_ESA_LEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->atm_addr[j] & 0xff); + } + offset += sprintf(buf + offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc ? rulla->vcc->vpi : 0, + rulla->vcc ? rulla->vcc->vci : 0, + rulla->recv_vcc ? rulla->recv_vcc->vpi : 0, + rulla->recv_vcc ? rulla->recv_vcc->vci : 0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset += sprintf(buf + offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + printk("%s\n", buf); + } + + if (!hlist_empty(&priv->lec_arp_empty_ones)) + printk("Empty ones\n"); + hlist_for_each_entry(rulla, node, &priv->lec_arp_empty_ones, next) { + offset = 0; + offset += sprintf(buf + offset, "Mac:"); + for (j = 0; j < ETH_ALEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->mac_addr[j] & 0xff); + } + offset += sprintf(buf + offset, "Atm:"); + for (j = 0; j < ATM_ESA_LEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->atm_addr[j] & 0xff); + } + offset += sprintf(buf + offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc ? rulla->vcc->vpi : 0, + rulla->vcc ? rulla->vcc->vci : 0, + rulla->recv_vcc ? rulla->recv_vcc->vpi : 0, + rulla->recv_vcc ? rulla->recv_vcc->vci : 0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset += sprintf(buf + offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + printk("%s", buf); + } + + if (!hlist_empty(&priv->mcast_fwds)) + printk("Multicast Forward VCCs\n"); + hlist_for_each_entry(rulla, node, &priv->mcast_fwds, next) { + offset = 0; + offset += sprintf(buf + offset, "Mac:"); + for (j = 0; j < ETH_ALEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->mac_addr[j] & 0xff); + } + offset += sprintf(buf + offset, "Atm:"); + for (j = 0; j < ATM_ESA_LEN; j++) { + offset += sprintf(buf + offset, "%2.2x ", + rulla->atm_addr[j] & 0xff); + } + offset += sprintf(buf + offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc ? rulla->vcc->vpi : 0, + rulla->vcc ? rulla->vcc->vci : 0, + rulla->recv_vcc ? rulla->recv_vcc->vpi : 0, + rulla->recv_vcc ? rulla->recv_vcc->vci : 0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset += sprintf(buf + offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + printk("%s\n", buf); + } -#endif } +#else +#define dump_arp_table(priv) do { } while (0) +#endif /* * Destruction of arp-cache */ -static void -lec_arp_destroy(struct lec_priv *priv) +static void lec_arp_destroy(struct lec_priv *priv) { unsigned long flags; - struct lec_arp_table *entry, *next; - int i; + struct hlist_node *node, *next; + struct lec_arp_table *entry; + int i; + + cancel_rearming_delayed_work(&priv->lec_arp_work); - del_timer_sync(&priv->lec_arp_timer); - - /* - * Remove all entries - */ + /* + * Remove all entries + */ spin_lock_irqsave(&priv->lec_arp_lock, flags); - for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for(entry = priv->lec_arp_tables[i]; entry != NULL; entry=next) { - next = entry->next; - lec_arp_remove(priv, entry); - kfree(entry); - } - } - entry = priv->lec_arp_empty_ones; - while(entry) { - next = entry->next; - del_timer_sync(&entry->timer); - lec_arp_clear_vccs(entry); - kfree(entry); - entry = next; - } - priv->lec_arp_empty_ones = NULL; - entry = priv->lec_no_forward; - while(entry) { - next = entry->next; - del_timer_sync(&entry->timer); - lec_arp_clear_vccs(entry); - kfree(entry); - entry = next; - } - priv->lec_no_forward = NULL; - entry = priv->mcast_fwds; - while(entry) { - next = entry->next; - /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ - lec_arp_clear_vccs(entry); - kfree(entry); - entry = next; - } - priv->mcast_fwds = NULL; - priv->mcast_vcc = NULL; - memset(priv->lec_arp_tables, 0, - sizeof(struct lec_arp_table *) * LEC_ARP_TABLE_SIZE); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_tables[i], next) { + lec_arp_remove(priv, entry); + lec_arp_put(entry); + } + INIT_HLIST_HEAD(&priv->lec_arp_tables[i]); + } + + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_empty_ones, next) { + del_timer_sync(&entry->timer); + lec_arp_clear_vccs(entry); + hlist_del(&entry->next); + lec_arp_put(entry); + } + INIT_HLIST_HEAD(&priv->lec_arp_empty_ones); + + hlist_for_each_entry_safe(entry, node, next, &priv->lec_no_forward, next) { + del_timer_sync(&entry->timer); + lec_arp_clear_vccs(entry); + hlist_del(&entry->next); + lec_arp_put(entry); + } + INIT_HLIST_HEAD(&priv->lec_no_forward); + + hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ + lec_arp_clear_vccs(entry); + hlist_del(&entry->next); + lec_arp_put(entry); + } + INIT_HLIST_HEAD(&priv->mcast_fwds); + priv->mcast_vcc = NULL; spin_unlock_irqrestore(&priv->lec_arp_lock, flags); } - /* * Find entry by mac_address */ -static struct lec_arp_table* -lec_arp_find(struct lec_priv *priv, - unsigned char *mac_addr) +static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, + unsigned char *mac_addr) { - unsigned short place; - struct lec_arp_table *to_return; - - DPRINTK("LEC_ARP: lec_arp_find :%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", - mac_addr[0]&0xff, mac_addr[1]&0xff, mac_addr[2]&0xff, - mac_addr[3]&0xff, mac_addr[4]&0xff, mac_addr[5]&0xff); - place = HASH(mac_addr[ETH_ALEN-1]); - - to_return = priv->lec_arp_tables[place]; - while(to_return) { - if (!compare_ether_addr(mac_addr, to_return->mac_addr)) { - return to_return; - } - to_return = to_return->next; - } - return NULL; + struct hlist_node *node; + struct hlist_head *head; + struct lec_arp_table *entry; + + DPRINTK("LEC_ARP: lec_arp_find :%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + mac_addr[0] & 0xff, mac_addr[1] & 0xff, mac_addr[2] & 0xff, + mac_addr[3] & 0xff, mac_addr[4] & 0xff, mac_addr[5] & 0xff); + + head = &priv->lec_arp_tables[HASH(mac_addr[ETH_ALEN - 1])]; + hlist_for_each_entry(entry, node, head, next) { + if (!compare_ether_addr(mac_addr, entry->mac_addr)) { + return entry; + } + } + return NULL; } -static struct lec_arp_table* -make_entry(struct lec_priv *priv, unsigned char *mac_addr) +static struct lec_arp_table *make_entry(struct lec_priv *priv, + unsigned char *mac_addr) { - struct lec_arp_table *to_return; - - to_return = kzalloc(sizeof(struct lec_arp_table), GFP_ATOMIC); - if (!to_return) { - printk("LEC: Arp entry kmalloc failed\n"); - return NULL; - } - memcpy(to_return->mac_addr, mac_addr, ETH_ALEN); - init_timer(&to_return->timer); - to_return->timer.function = lec_arp_expire_arp; - to_return->timer.data = (unsigned long) to_return; - to_return->last_used = jiffies; - to_return->priv = priv; - skb_queue_head_init(&to_return->tx_wait); - return to_return; + struct lec_arp_table *to_return; + + to_return = kzalloc(sizeof(struct lec_arp_table), GFP_ATOMIC); + if (!to_return) { + printk("LEC: Arp entry kmalloc failed\n"); + return NULL; + } + memcpy(to_return->mac_addr, mac_addr, ETH_ALEN); + INIT_HLIST_NODE(&to_return->next); + init_timer(&to_return->timer); + to_return->timer.function = lec_arp_expire_arp; + to_return->timer.data = (unsigned long)to_return; + to_return->last_used = jiffies; + to_return->priv = priv; + skb_queue_head_init(&to_return->tx_wait); + atomic_set(&to_return->usage, 1); + return to_return; } -/* - * - * Arp sent timer expired - * - */ -static void -lec_arp_expire_arp(unsigned long data) +/* Arp sent timer expired */ +static void lec_arp_expire_arp(unsigned long data) { - struct lec_arp_table *entry; - - entry = (struct lec_arp_table *)data; - - DPRINTK("lec_arp_expire_arp\n"); - if (entry->status == ESI_ARP_PENDING) { - if (entry->no_tries <= entry->priv->max_retry_count) { - if (entry->is_rdesc) - send_to_lecd(entry->priv, l_rdesc_arp_xmt, entry->mac_addr, NULL, NULL); - else - send_to_lecd(entry->priv, l_arp_xmt, entry->mac_addr, NULL, NULL); - entry->no_tries++; - } - mod_timer(&entry->timer, jiffies + (1*HZ)); - } + struct lec_arp_table *entry; + + entry = (struct lec_arp_table *)data; + + DPRINTK("lec_arp_expire_arp\n"); + if (entry->status == ESI_ARP_PENDING) { + if (entry->no_tries <= entry->priv->max_retry_count) { + if (entry->is_rdesc) + send_to_lecd(entry->priv, l_rdesc_arp_xmt, + entry->mac_addr, NULL, NULL); + else + send_to_lecd(entry->priv, l_arp_xmt, + entry->mac_addr, NULL, NULL); + entry->no_tries++; + } + mod_timer(&entry->timer, jiffies + (1 * HZ)); + } } -/* - * - * Unknown/unused vcc expire, remove associated entry - * - */ -static void -lec_arp_expire_vcc(unsigned long data) +/* Unknown/unused vcc expire, remove associated entry */ +static void lec_arp_expire_vcc(unsigned long data) { unsigned long flags; - struct lec_arp_table *to_remove = (struct lec_arp_table*)data; - struct lec_priv *priv = (struct lec_priv *)to_remove->priv; - struct lec_arp_table *entry = NULL; + struct lec_arp_table *to_remove = (struct lec_arp_table *)data; + struct lec_priv *priv = (struct lec_priv *)to_remove->priv; - del_timer(&to_remove->timer); + del_timer(&to_remove->timer); - DPRINTK("LEC_ARP %p %p: lec_arp_expire_vcc vpi:%d vci:%d\n", - to_remove, priv, - to_remove->vcc?to_remove->recv_vcc->vpi:0, - to_remove->vcc?to_remove->recv_vcc->vci:0); - DPRINTK("eo:%p nf:%p\n",priv->lec_arp_empty_ones,priv->lec_no_forward); + DPRINTK("LEC_ARP %p %p: lec_arp_expire_vcc vpi:%d vci:%d\n", + to_remove, priv, + to_remove->vcc ? to_remove->recv_vcc->vpi : 0, + to_remove->vcc ? to_remove->recv_vcc->vci : 0); spin_lock_irqsave(&priv->lec_arp_lock, flags); - if (to_remove == priv->lec_arp_empty_ones) - priv->lec_arp_empty_ones = to_remove->next; - else { - entry = priv->lec_arp_empty_ones; - while (entry && entry->next != to_remove) - entry = entry->next; - if (entry) - entry->next = to_remove->next; - } - if (!entry) { - if (to_remove == priv->lec_no_forward) { - priv->lec_no_forward = to_remove->next; - } else { - entry = priv->lec_no_forward; - while (entry && entry->next != to_remove) - entry = entry->next; - if (entry) - entry->next = to_remove->next; - } - } + hlist_del(&to_remove->next); spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - lec_arp_clear_vccs(to_remove); - kfree(to_remove); + lec_arp_clear_vccs(to_remove); + lec_arp_put(to_remove); } /* @@ -1915,158 +1879,171 @@ lec_arp_expire_vcc(unsigned long data) * to ESI_FORWARD_DIRECT. This causes the flush period to end * regardless of the progress of the flush protocol. */ -static void -lec_arp_check_expire(unsigned long data) +static void lec_arp_check_expire(void *data) { unsigned long flags; - struct lec_priv *priv = (struct lec_priv *)data; - struct lec_arp_table *entry, *next; - unsigned long now; - unsigned long time_to_check; - int i; - - DPRINTK("lec_arp_check_expire %p\n",priv); - DPRINTK("expire: eo:%p nf:%p\n",priv->lec_arp_empty_ones, - priv->lec_no_forward); + struct lec_priv *priv = data; + struct hlist_node *node, *next; + struct lec_arp_table *entry; + unsigned long now; + unsigned long time_to_check; + int i; + + DPRINTK("lec_arp_check_expire %p\n", priv); now = jiffies; +restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); - for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for(entry = priv->lec_arp_tables[i]; entry != NULL; ) { - if ((entry->flags) & LEC_REMOTE_FLAG && + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_tables[i], next) { + if ((entry->flags) & LEC_REMOTE_FLAG && priv->topology_change) time_to_check = priv->forward_delay_time; else time_to_check = priv->aging_time; DPRINTK("About to expire: %lx - %lx > %lx\n", - now,entry->last_used, time_to_check); - if( time_after(now, entry->last_used+ - time_to_check) && - !(entry->flags & LEC_PERMANENT_FLAG) && - !(entry->mac_addr[0] & 0x01) ) { /* LANE2: 7.1.20 */ + now, entry->last_used, time_to_check); + if (time_after(now, entry->last_used + time_to_check) + && !(entry->flags & LEC_PERMANENT_FLAG) + && !(entry->mac_addr[0] & 0x01)) { /* LANE2: 7.1.20 */ /* Remove entry */ DPRINTK("LEC:Entry timed out\n"); - next = entry->next; lec_arp_remove(priv, entry); - kfree(entry); - entry = next; + lec_arp_put(entry); } else { /* Something else */ if ((entry->status == ESI_VC_PENDING || - entry->status == ESI_ARP_PENDING) + entry->status == ESI_ARP_PENDING) && time_after_eq(now, - entry->timestamp + - priv->max_unknown_frame_time)) { + entry->timestamp + + priv-> + max_unknown_frame_time)) { entry->timestamp = jiffies; entry->packets_flooded = 0; if (entry->status == ESI_VC_PENDING) - send_to_lecd(priv, l_svc_setup, entry->mac_addr, entry->atm_addr, NULL); + send_to_lecd(priv, l_svc_setup, + entry->mac_addr, + entry->atm_addr, + NULL); } - if (entry->status == ESI_FLUSH_PENDING - && - time_after_eq(now, entry->timestamp+ - priv->path_switching_delay)) { + if (entry->status == ESI_FLUSH_PENDING + && + time_after_eq(now, entry->timestamp + + priv->path_switching_delay)) { struct sk_buff *skb; + struct atm_vcc *vcc = entry->vcc; + lec_arp_hold(entry); + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); while ((skb = skb_dequeue(&entry->tx_wait)) != NULL) - lec_send(entry->vcc, skb, entry->priv); + lec_send(vcc, skb, entry->priv); entry->last_used = jiffies; - entry->status = - ESI_FORWARD_DIRECT; + entry->status = ESI_FORWARD_DIRECT; + lec_arp_put(entry); + goto restart; } - entry = entry->next; } } } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - mod_timer(&priv->lec_arp_timer, jiffies + LEC_ARP_REFRESH_INTERVAL); + schedule_delayed_work(&priv->lec_arp_work, LEC_ARP_REFRESH_INTERVAL); } + /* * Try to find vcc where mac_address is attached. * */ -static struct atm_vcc* -lec_arp_resolve(struct lec_priv *priv, unsigned char *mac_to_find, - int is_rdesc, struct lec_arp_table **ret_entry) +static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, + unsigned char *mac_to_find, int is_rdesc, + struct lec_arp_table **ret_entry) { unsigned long flags; - struct lec_arp_table *entry; + struct lec_arp_table *entry; struct atm_vcc *found; - if (mac_to_find[0] & 0x01) { - switch (priv->lane_version) { - case 1: - return priv->mcast_vcc; - break; - case 2: /* LANE2 wants arp for multicast addresses */ - if (!compare_ether_addr(mac_to_find, bus_mac)) - return priv->mcast_vcc; - break; - default: - break; - } - } + if (mac_to_find[0] & 0x01) { + switch (priv->lane_version) { + case 1: + return priv->mcast_vcc; + break; + case 2: /* LANE2 wants arp for multicast addresses */ + if (!compare_ether_addr(mac_to_find, bus_mac)) + return priv->mcast_vcc; + break; + default: + break; + } + } spin_lock_irqsave(&priv->lec_arp_lock, flags); - entry = lec_arp_find(priv, mac_to_find); - - if (entry) { - if (entry->status == ESI_FORWARD_DIRECT) { - /* Connection Ok */ - entry->last_used = jiffies; - *ret_entry = entry; - found = entry->vcc; + entry = lec_arp_find(priv, mac_to_find); + + if (entry) { + if (entry->status == ESI_FORWARD_DIRECT) { + /* Connection Ok */ + entry->last_used = jiffies; + lec_arp_hold(entry); + *ret_entry = entry; + found = entry->vcc; goto out; - } - /* If the LE_ARP cache entry is still pending, reset count to 0 + } + /* + * If the LE_ARP cache entry is still pending, reset count to 0 * so another LE_ARP request can be made for this frame. */ if (entry->status == ESI_ARP_PENDING) { entry->no_tries = 0; } - /* Data direct VC not yet set up, check to see if the unknown - frame count is greater than the limit. If the limit has - not been reached, allow the caller to send packet to - BUS. */ - if (entry->status != ESI_FLUSH_PENDING && - entry->packets_flooded<priv->maximum_unknown_frame_count) { - entry->packets_flooded++; - DPRINTK("LEC_ARP: Flooding..\n"); - found = priv->mcast_vcc; + /* + * Data direct VC not yet set up, check to see if the unknown + * frame count is greater than the limit. If the limit has + * not been reached, allow the caller to send packet to + * BUS. + */ + if (entry->status != ESI_FLUSH_PENDING && + entry->packets_flooded < + priv->maximum_unknown_frame_count) { + entry->packets_flooded++; + DPRINTK("LEC_ARP: Flooding..\n"); + found = priv->mcast_vcc; goto out; - } - /* We got here because entry->status == ESI_FLUSH_PENDING + } + /* + * We got here because entry->status == ESI_FLUSH_PENDING * or BUS flood limit was reached for an entry which is * in ESI_ARP_PENDING or ESI_VC_PENDING state. */ - *ret_entry = entry; - DPRINTK("lec: entry->status %d entry->vcc %p\n", entry->status, entry->vcc); - found = NULL; - } else { - /* No matching entry was found */ - entry = make_entry(priv, mac_to_find); - DPRINTK("LEC_ARP: Making entry\n"); - if (!entry) { - found = priv->mcast_vcc; + lec_arp_hold(entry); + *ret_entry = entry; + DPRINTK("lec: entry->status %d entry->vcc %p\n", entry->status, + entry->vcc); + found = NULL; + } else { + /* No matching entry was found */ + entry = make_entry(priv, mac_to_find); + DPRINTK("LEC_ARP: Making entry\n"); + if (!entry) { + found = priv->mcast_vcc; goto out; - } - lec_arp_add(priv, entry); - /* We want arp-request(s) to be sent */ - entry->packets_flooded =1; - entry->status = ESI_ARP_PENDING; - entry->no_tries = 1; - entry->last_used = entry->timestamp = jiffies; - entry->is_rdesc = is_rdesc; - if (entry->is_rdesc) - send_to_lecd(priv, l_rdesc_arp_xmt, mac_to_find, NULL, NULL); - else - send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); - entry->timer.expires = jiffies + (1*HZ); - entry->timer.function = lec_arp_expire_arp; - add_timer(&entry->timer); - found = priv->mcast_vcc; - } + } + lec_arp_add(priv, entry); + /* We want arp-request(s) to be sent */ + entry->packets_flooded = 1; + entry->status = ESI_ARP_PENDING; + entry->no_tries = 1; + entry->last_used = entry->timestamp = jiffies; + entry->is_rdesc = is_rdesc; + if (entry->is_rdesc) + send_to_lecd(priv, l_rdesc_arp_xmt, mac_to_find, NULL, + NULL); + else + send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); + entry->timer.expires = jiffies + (1 * HZ); + entry->timer.function = lec_arp_expire_arp; + add_timer(&entry->timer); + found = priv->mcast_vcc; + } out: spin_unlock_irqrestore(&priv->lec_arp_lock, flags); @@ -2074,30 +2051,30 @@ out: } static int -lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, - unsigned long permanent) +lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, + unsigned long permanent) { unsigned long flags; - struct lec_arp_table *entry, *next; - int i; + struct hlist_node *node, *next; + struct lec_arp_table *entry; + int i; - DPRINTK("lec_addr_delete\n"); + DPRINTK("lec_addr_delete\n"); spin_lock_irqsave(&priv->lec_arp_lock, flags); - for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for(entry = priv->lec_arp_tables[i]; entry != NULL; entry = next) { - next = entry->next; - if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN) - && (permanent || - !(entry->flags & LEC_PERMANENT_FLAG))) { + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_tables[i], next) { + if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN) + && (permanent || + !(entry->flags & LEC_PERMANENT_FLAG))) { lec_arp_remove(priv, entry); - kfree(entry); - } + lec_arp_put(entry); + } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - return 0; - } - } + return 0; + } + } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - return -1; + return -1; } /* @@ -2105,109 +2082,98 @@ lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, */ static void lec_arp_update(struct lec_priv *priv, unsigned char *mac_addr, - unsigned char *atm_addr, unsigned long remoteflag, - unsigned int targetless_le_arp) + unsigned char *atm_addr, unsigned long remoteflag, + unsigned int targetless_le_arp) { unsigned long flags; - struct lec_arp_table *entry, *tmp; - int i; + struct hlist_node *node, *next; + struct lec_arp_table *entry, *tmp; + int i; - DPRINTK("lec:%s", (targetless_le_arp) ? "targetless ": " "); - DPRINTK("lec_arp_update mac:%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", - mac_addr[0],mac_addr[1],mac_addr[2],mac_addr[3], - mac_addr[4],mac_addr[5]); + DPRINTK("lec:%s", (targetless_le_arp) ? "targetless " : " "); + DPRINTK("lec_arp_update mac:%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + mac_addr[0], mac_addr[1], mac_addr[2], mac_addr[3], + mac_addr[4], mac_addr[5]); spin_lock_irqsave(&priv->lec_arp_lock, flags); - entry = lec_arp_find(priv, mac_addr); - if (entry == NULL && targetless_le_arp) - goto out; /* LANE2: ignore targetless LE_ARPs for which - * we have no entry in the cache. 7.1.30 - */ - if (priv->lec_arp_empty_ones) { - entry = priv->lec_arp_empty_ones; - if (!memcmp(entry->atm_addr, atm_addr, ATM_ESA_LEN)) { - priv->lec_arp_empty_ones = entry->next; - } else { - while(entry->next && memcmp(entry->next->atm_addr, - atm_addr, ATM_ESA_LEN)) - entry = entry->next; - if (entry->next) { - tmp = entry; - entry = entry->next; - tmp->next = entry->next; - } else - entry = NULL; - - } - if (entry) { - del_timer(&entry->timer); - tmp = lec_arp_find(priv, mac_addr); - if (tmp) { - del_timer(&tmp->timer); - tmp->status = ESI_FORWARD_DIRECT; - memcpy(tmp->atm_addr, atm_addr, ATM_ESA_LEN); - tmp->vcc = entry->vcc; - tmp->old_push = entry->old_push; - tmp->last_used = jiffies; - del_timer(&entry->timer); - kfree(entry); - entry=tmp; - } else { - entry->status = ESI_FORWARD_DIRECT; - memcpy(entry->mac_addr, mac_addr, ETH_ALEN); - entry->last_used = jiffies; - lec_arp_add(priv, entry); - } - if (remoteflag) - entry->flags|=LEC_REMOTE_FLAG; - else - entry->flags&=~LEC_REMOTE_FLAG; - DPRINTK("After update\n"); - dump_arp_table(priv); - goto out; - } - } - entry = lec_arp_find(priv, mac_addr); - if (!entry) { - entry = make_entry(priv, mac_addr); - if (!entry) + entry = lec_arp_find(priv, mac_addr); + if (entry == NULL && targetless_le_arp) + goto out; /* + * LANE2: ignore targetless LE_ARPs for which + * we have no entry in the cache. 7.1.30 + */ + if (!hlist_empty(&priv->lec_arp_empty_ones)) { + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_empty_ones, next) { + if (memcmp(entry->atm_addr, atm_addr, ATM_ESA_LEN) == 0) { + hlist_del(&entry->next); + del_timer(&entry->timer); + tmp = lec_arp_find(priv, mac_addr); + if (tmp) { + del_timer(&tmp->timer); + tmp->status = ESI_FORWARD_DIRECT; + memcpy(tmp->atm_addr, atm_addr, ATM_ESA_LEN); + tmp->vcc = entry->vcc; + tmp->old_push = entry->old_push; + tmp->last_used = jiffies; + del_timer(&entry->timer); + lec_arp_put(entry); + entry = tmp; + } else { + entry->status = ESI_FORWARD_DIRECT; + memcpy(entry->mac_addr, mac_addr, ETH_ALEN); + entry->last_used = jiffies; + lec_arp_add(priv, entry); + } + if (remoteflag) + entry->flags |= LEC_REMOTE_FLAG; + else + entry->flags &= ~LEC_REMOTE_FLAG; + DPRINTK("After update\n"); + dump_arp_table(priv); + goto out; + } + } + } + + entry = lec_arp_find(priv, mac_addr); + if (!entry) { + entry = make_entry(priv, mac_addr); + if (!entry) goto out; - entry->status = ESI_UNKNOWN; - lec_arp_add(priv, entry); - /* Temporary, changes before end of function */ - } - memcpy(entry->atm_addr, atm_addr, ATM_ESA_LEN); - del_timer(&entry->timer); - for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for(tmp = priv->lec_arp_tables[i]; tmp; tmp=tmp->next) { - if (entry != tmp && - !memcmp(tmp->atm_addr, atm_addr, - ATM_ESA_LEN)) { - /* Vcc to this host exists */ - if (tmp->status > ESI_VC_PENDING) { - /* - * ESI_FLUSH_PENDING, - * ESI_FORWARD_DIRECT - */ - entry->vcc = tmp->vcc; - entry->old_push=tmp->old_push; - } - entry->status=tmp->status; - break; - } - } - } - if (remoteflag) - entry->flags|=LEC_REMOTE_FLAG; - else - entry->flags&=~LEC_REMOTE_FLAG; - if (entry->status == ESI_ARP_PENDING || - entry->status == ESI_UNKNOWN) { - entry->status = ESI_VC_PENDING; - send_to_lecd(priv, l_svc_setup, entry->mac_addr, atm_addr, NULL); - } - DPRINTK("After update2\n"); - dump_arp_table(priv); + entry->status = ESI_UNKNOWN; + lec_arp_add(priv, entry); + /* Temporary, changes before end of function */ + } + memcpy(entry->atm_addr, atm_addr, ATM_ESA_LEN); + del_timer(&entry->timer); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry(tmp, node, &priv->lec_arp_tables[i], next) { + if (entry != tmp && + !memcmp(tmp->atm_addr, atm_addr, ATM_ESA_LEN)) { + /* Vcc to this host exists */ + if (tmp->status > ESI_VC_PENDING) { + /* + * ESI_FLUSH_PENDING, + * ESI_FORWARD_DIRECT + */ + entry->vcc = tmp->vcc; + entry->old_push = tmp->old_push; + } + entry->status = tmp->status; + break; + } + } + } + if (remoteflag) + entry->flags |= LEC_REMOTE_FLAG; + else + entry->flags &= ~LEC_REMOTE_FLAG; + if (entry->status == ESI_ARP_PENDING || entry->status == ESI_UNKNOWN) { + entry->status = ESI_VC_PENDING; + send_to_lecd(priv, l_svc_setup, entry->mac_addr, atm_addr, NULL); + } + DPRINTK("After update2\n"); + dump_arp_table(priv); out: spin_unlock_irqrestore(&priv->lec_arp_lock, flags); } @@ -2217,299 +2183,299 @@ out: */ static void lec_vcc_added(struct lec_priv *priv, struct atmlec_ioc *ioc_data, - struct atm_vcc *vcc, - void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb)) + struct atm_vcc *vcc, + void (*old_push) (struct atm_vcc *vcc, struct sk_buff *skb)) { unsigned long flags; - struct lec_arp_table *entry; - int i, found_entry=0; + struct hlist_node *node; + struct lec_arp_table *entry; + int i, found_entry = 0; spin_lock_irqsave(&priv->lec_arp_lock, flags); - if (ioc_data->receive == 2) { - /* Vcc for Multicast Forward. No timer, LANEv2 7.1.20 and 2.3.5.3 */ + if (ioc_data->receive == 2) { + /* Vcc for Multicast Forward. No timer, LANEv2 7.1.20 and 2.3.5.3 */ - DPRINTK("LEC_ARP: Attaching mcast forward\n"); + DPRINTK("LEC_ARP: Attaching mcast forward\n"); #if 0 - entry = lec_arp_find(priv, bus_mac); - if (!entry) { - printk("LEC_ARP: Multicast entry not found!\n"); + entry = lec_arp_find(priv, bus_mac); + if (!entry) { + printk("LEC_ARP: Multicast entry not found!\n"); goto out; - } - memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - entry->recv_vcc = vcc; - entry->old_recv_push = old_push; + } + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; #endif - entry = make_entry(priv, bus_mac); - if (entry == NULL) + entry = make_entry(priv, bus_mac); + if (entry == NULL) goto out; - del_timer(&entry->timer); - memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - entry->recv_vcc = vcc; - entry->old_recv_push = old_push; - entry->next = priv->mcast_fwds; - priv->mcast_fwds = entry; - goto out; - } else if (ioc_data->receive == 1) { - /* Vcc which we don't want to make default vcc, attach it - anyway. */ - DPRINTK("LEC_ARP:Attaching data direct, not default :%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", - ioc_data->atm_addr[0],ioc_data->atm_addr[1], - ioc_data->atm_addr[2],ioc_data->atm_addr[3], - ioc_data->atm_addr[4],ioc_data->atm_addr[5], - ioc_data->atm_addr[6],ioc_data->atm_addr[7], - ioc_data->atm_addr[8],ioc_data->atm_addr[9], - ioc_data->atm_addr[10],ioc_data->atm_addr[11], - ioc_data->atm_addr[12],ioc_data->atm_addr[13], - ioc_data->atm_addr[14],ioc_data->atm_addr[15], - ioc_data->atm_addr[16],ioc_data->atm_addr[17], - ioc_data->atm_addr[18],ioc_data->atm_addr[19]); - entry = make_entry(priv, bus_mac); - if (entry == NULL) + del_timer(&entry->timer); + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; + hlist_add_head(&entry->next, &priv->mcast_fwds); + goto out; + } else if (ioc_data->receive == 1) { + /* + * Vcc which we don't want to make default vcc, + * attach it anyway. + */ + DPRINTK + ("LEC_ARP:Attaching data direct, not default: " + "%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + ioc_data->atm_addr[0], ioc_data->atm_addr[1], + ioc_data->atm_addr[2], ioc_data->atm_addr[3], + ioc_data->atm_addr[4], ioc_data->atm_addr[5], + ioc_data->atm_addr[6], ioc_data->atm_addr[7], + ioc_data->atm_addr[8], ioc_data->atm_addr[9], + ioc_data->atm_addr[10], ioc_data->atm_addr[11], + ioc_data->atm_addr[12], ioc_data->atm_addr[13], + ioc_data->atm_addr[14], ioc_data->atm_addr[15], + ioc_data->atm_addr[16], ioc_data->atm_addr[17], + ioc_data->atm_addr[18], ioc_data->atm_addr[19]); + entry = make_entry(priv, bus_mac); + if (entry == NULL) goto out; - memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - memset(entry->mac_addr, 0, ETH_ALEN); - entry->recv_vcc = vcc; - entry->old_recv_push = old_push; - entry->status = ESI_UNKNOWN; - entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; - add_timer(&entry->timer); - entry->next = priv->lec_no_forward; - priv->lec_no_forward = entry; + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + memset(entry->mac_addr, 0, ETH_ALEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; + entry->status = ESI_UNKNOWN; + entry->timer.expires = jiffies + priv->vcc_timeout_period; + entry->timer.function = lec_arp_expire_vcc; + hlist_add_head(&entry->next, &priv->lec_no_forward); + add_timer(&entry->timer); dump_arp_table(priv); goto out; - } - DPRINTK("LEC_ARP:Attaching data direct, default:%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", - ioc_data->atm_addr[0],ioc_data->atm_addr[1], - ioc_data->atm_addr[2],ioc_data->atm_addr[3], - ioc_data->atm_addr[4],ioc_data->atm_addr[5], - ioc_data->atm_addr[6],ioc_data->atm_addr[7], - ioc_data->atm_addr[8],ioc_data->atm_addr[9], - ioc_data->atm_addr[10],ioc_data->atm_addr[11], - ioc_data->atm_addr[12],ioc_data->atm_addr[13], - ioc_data->atm_addr[14],ioc_data->atm_addr[15], - ioc_data->atm_addr[16],ioc_data->atm_addr[17], - ioc_data->atm_addr[18],ioc_data->atm_addr[19]); - for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for (entry = priv->lec_arp_tables[i]; entry; entry=entry->next) { - if (memcmp(ioc_data->atm_addr, entry->atm_addr, - ATM_ESA_LEN)==0) { - DPRINTK("LEC_ARP: Attaching data direct\n"); - DPRINTK("Currently -> Vcc: %d, Rvcc:%d\n", - entry->vcc?entry->vcc->vci:0, - entry->recv_vcc?entry->recv_vcc->vci:0); - found_entry=1; - del_timer(&entry->timer); - entry->vcc = vcc; - entry->old_push = old_push; - if (entry->status == ESI_VC_PENDING) { - if(priv->maximum_unknown_frame_count - ==0) - entry->status = - ESI_FORWARD_DIRECT; - else { - entry->timestamp = jiffies; - entry->status = - ESI_FLUSH_PENDING; + } + DPRINTK + ("LEC_ARP:Attaching data direct, default: " + "%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + ioc_data->atm_addr[0], ioc_data->atm_addr[1], + ioc_data->atm_addr[2], ioc_data->atm_addr[3], + ioc_data->atm_addr[4], ioc_data->atm_addr[5], + ioc_data->atm_addr[6], ioc_data->atm_addr[7], + ioc_data->atm_addr[8], ioc_data->atm_addr[9], + ioc_data->atm_addr[10], ioc_data->atm_addr[11], + ioc_data->atm_addr[12], ioc_data->atm_addr[13], + ioc_data->atm_addr[14], ioc_data->atm_addr[15], + ioc_data->atm_addr[16], ioc_data->atm_addr[17], + ioc_data->atm_addr[18], ioc_data->atm_addr[19]); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry(entry, node, &priv->lec_arp_tables[i], next) { + if (memcmp + (ioc_data->atm_addr, entry->atm_addr, + ATM_ESA_LEN) == 0) { + DPRINTK("LEC_ARP: Attaching data direct\n"); + DPRINTK("Currently -> Vcc: %d, Rvcc:%d\n", + entry->vcc ? entry->vcc->vci : 0, + entry->recv_vcc ? entry->recv_vcc-> + vci : 0); + found_entry = 1; + del_timer(&entry->timer); + entry->vcc = vcc; + entry->old_push = old_push; + if (entry->status == ESI_VC_PENDING) { + if (priv->maximum_unknown_frame_count + == 0) + entry->status = + ESI_FORWARD_DIRECT; + else { + entry->timestamp = jiffies; + entry->status = + ESI_FLUSH_PENDING; #if 0 - send_to_lecd(priv,l_flush_xmt, - NULL, - entry->atm_addr, - NULL); + send_to_lecd(priv, l_flush_xmt, + NULL, + entry->atm_addr, + NULL); #endif - } - } else { - /* They were forming a connection - to us, and we to them. Our - ATM address is numerically lower - than theirs, so we make connection - we formed into default VCC (8.1.11). - Connection they made gets torn - down. This might confuse some - clients. Can be changed if - someone reports trouble... */ - ; - } - } - } - } - if (found_entry) { - DPRINTK("After vcc was added\n"); - dump_arp_table(priv); + } + } else { + /* + * They were forming a connection + * to us, and we to them. Our + * ATM address is numerically lower + * than theirs, so we make connection + * we formed into default VCC (8.1.11). + * Connection they made gets torn + * down. This might confuse some + * clients. Can be changed if + * someone reports trouble... + */ + ; + } + } + } + } + if (found_entry) { + DPRINTK("After vcc was added\n"); + dump_arp_table(priv); goto out; - } - /* Not found, snatch address from first data packet that arrives from - this vcc */ - entry = make_entry(priv, bus_mac); - if (!entry) + } + /* + * Not found, snatch address from first data packet that arrives + * from this vcc + */ + entry = make_entry(priv, bus_mac); + if (!entry) goto out; - entry->vcc = vcc; - entry->old_push = old_push; - memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - memset(entry->mac_addr, 0, ETH_ALEN); - entry->status = ESI_UNKNOWN; - entry->next = priv->lec_arp_empty_ones; - priv->lec_arp_empty_ones = entry; - entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; - add_timer(&entry->timer); - DPRINTK("After vcc was added\n"); + entry->vcc = vcc; + entry->old_push = old_push; + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + memset(entry->mac_addr, 0, ETH_ALEN); + entry->status = ESI_UNKNOWN; + hlist_add_head(&entry->next, &priv->lec_arp_empty_ones); + entry->timer.expires = jiffies + priv->vcc_timeout_period; + entry->timer.function = lec_arp_expire_vcc; + add_timer(&entry->timer); + DPRINTK("After vcc was added\n"); dump_arp_table(priv); out: spin_unlock_irqrestore(&priv->lec_arp_lock, flags); } -static void -lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) +static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) { unsigned long flags; - struct lec_arp_table *entry; - int i; - - DPRINTK("LEC:lec_flush_complete %lx\n",tran_id); + struct hlist_node *node; + struct lec_arp_table *entry; + int i; + + DPRINTK("LEC:lec_flush_complete %lx\n", tran_id); +restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); - for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - for (entry = priv->lec_arp_tables[i]; entry; entry=entry->next) { - if (entry->flush_tran_id == tran_id && - entry->status == ESI_FLUSH_PENDING) { - struct sk_buff *skb; - - while ((skb = skb_dequeue(&entry->tx_wait)) != NULL) - lec_send(entry->vcc, skb, entry->priv); - entry->status = ESI_FORWARD_DIRECT; - DPRINTK("LEC_ARP: Flushed\n"); - } - } - } + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry(entry, node, &priv->lec_arp_tables[i], next) { + if (entry->flush_tran_id == tran_id + && entry->status == ESI_FLUSH_PENDING) { + struct sk_buff *skb; + struct atm_vcc *vcc = entry->vcc; + + lec_arp_hold(entry); + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + while ((skb = skb_dequeue(&entry->tx_wait)) != NULL) + lec_send(vcc, skb, entry->priv); + entry->last_used = jiffies; + entry->status = ESI_FORWARD_DIRECT; + lec_arp_put(entry); + DPRINTK("LEC_ARP: Flushed\n"); + goto restart; + } + } + } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - dump_arp_table(priv); + dump_arp_table(priv); } static void lec_set_flush_tran_id(struct lec_priv *priv, - unsigned char *atm_addr, unsigned long tran_id) + unsigned char *atm_addr, unsigned long tran_id) { unsigned long flags; - struct lec_arp_table *entry; - int i; + struct hlist_node *node; + struct lec_arp_table *entry; + int i; spin_lock_irqsave(&priv->lec_arp_lock, flags); - for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) - for(entry = priv->lec_arp_tables[i]; entry; entry=entry->next) - if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN)) { - entry->flush_tran_id = tran_id; - DPRINTK("Set flush transaction id to %lx for %p\n",tran_id,entry); - } + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) + hlist_for_each_entry(entry, node, &priv->lec_arp_tables[i], next) { + if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN)) { + entry->flush_tran_id = tran_id; + DPRINTK("Set flush transaction id to %lx for %p\n", + tran_id, entry); + } + } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); } -static int -lec_mcast_make(struct lec_priv *priv, struct atm_vcc *vcc) +static int lec_mcast_make(struct lec_priv *priv, struct atm_vcc *vcc) { unsigned long flags; - unsigned char mac_addr[] = { - 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - struct lec_arp_table *to_add; + unsigned char mac_addr[] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + }; + struct lec_arp_table *to_add; struct lec_vcc_priv *vpriv; int err = 0; - + if (!(vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL))) return -ENOMEM; vpriv->xoff = 0; vpriv->old_pop = vcc->pop; vcc->user_back = vpriv; - vcc->pop = lec_pop; + vcc->pop = lec_pop; spin_lock_irqsave(&priv->lec_arp_lock, flags); - to_add = make_entry(priv, mac_addr); - if (!to_add) { + to_add = make_entry(priv, mac_addr); + if (!to_add) { vcc->pop = vpriv->old_pop; kfree(vpriv); - err = -ENOMEM; + err = -ENOMEM; goto out; - } - memcpy(to_add->atm_addr, vcc->remote.sas_addr.prv, ATM_ESA_LEN); - to_add->status = ESI_FORWARD_DIRECT; - to_add->flags |= LEC_PERMANENT_FLAG; - to_add->vcc = vcc; - to_add->old_push = vcc->push; - vcc->push = lec_push; - priv->mcast_vcc = vcc; - lec_arp_add(priv, to_add); + } + memcpy(to_add->atm_addr, vcc->remote.sas_addr.prv, ATM_ESA_LEN); + to_add->status = ESI_FORWARD_DIRECT; + to_add->flags |= LEC_PERMANENT_FLAG; + to_add->vcc = vcc; + to_add->old_push = vcc->push; + vcc->push = lec_push; + priv->mcast_vcc = vcc; + lec_arp_add(priv, to_add); out: spin_unlock_irqrestore(&priv->lec_arp_lock, flags); - return err; + return err; } -static void -lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) +static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) { unsigned long flags; - struct lec_arp_table *entry, *next; - int i; + struct hlist_node *node, *next; + struct lec_arp_table *entry; + int i; + + DPRINTK("LEC_ARP: lec_vcc_close vpi:%d vci:%d\n", vcc->vpi, vcc->vci); + dump_arp_table(priv); - DPRINTK("LEC_ARP: lec_vcc_close vpi:%d vci:%d\n",vcc->vpi,vcc->vci); - dump_arp_table(priv); spin_lock_irqsave(&priv->lec_arp_lock, flags); - for(i=0;i<LEC_ARP_TABLE_SIZE;i++) { - for(entry = priv->lec_arp_tables[i];entry; entry=next) { - next = entry->next; - if (vcc == entry->vcc) { - lec_arp_remove(priv, entry); - kfree(entry); - if (priv->mcast_vcc == vcc) { - priv->mcast_vcc = NULL; - } - } - } - } - - entry = priv->lec_arp_empty_ones; - priv->lec_arp_empty_ones = NULL; - while (entry != NULL) { - next = entry->next; - if (entry->vcc == vcc) { /* leave it out from the list */ - lec_arp_clear_vccs(entry); - del_timer(&entry->timer); - kfree(entry); - } - else { /* put it back to the list */ - entry->next = priv->lec_arp_empty_ones; - priv->lec_arp_empty_ones = entry; - } - entry = next; - } - - entry = priv->lec_no_forward; - priv->lec_no_forward = NULL; - while (entry != NULL) { - next = entry->next; - if (entry->recv_vcc == vcc) { - lec_arp_clear_vccs(entry); - del_timer(&entry->timer); - kfree(entry); - } - else { - entry->next = priv->lec_no_forward; - priv->lec_no_forward = entry; - } - entry = next; - } - - entry = priv->mcast_fwds; - priv->mcast_fwds = NULL; - while (entry != NULL) { - next = entry->next; - if (entry->recv_vcc == vcc) { - lec_arp_clear_vccs(entry); - /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ - kfree(entry); - } - else { - entry->next = priv->mcast_fwds; - priv->mcast_fwds = entry; - } - entry = next; - } + + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_tables[i], next) { + if (vcc == entry->vcc) { + lec_arp_remove(priv, entry); + lec_arp_put(entry); + if (priv->mcast_vcc == vcc) { + priv->mcast_vcc = NULL; + } + } + } + } + + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_empty_ones, next) { + if (entry->vcc == vcc) { + lec_arp_clear_vccs(entry); + del_timer(&entry->timer); + hlist_del(&entry->next); + lec_arp_put(entry); + } + } + + hlist_for_each_entry_safe(entry, node, next, &priv->lec_no_forward, next) { + if (entry->recv_vcc == vcc) { + lec_arp_clear_vccs(entry); + del_timer(&entry->timer); + hlist_del(&entry->next); + lec_arp_put(entry); + } + } + + hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + if (entry->recv_vcc == vcc) { + lec_arp_clear_vccs(entry); + /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ + hlist_del(&entry->next); + lec_arp_put(entry); + } + } spin_unlock_irqrestore(&priv->lec_arp_lock, flags); dump_arp_table(priv); @@ -2517,57 +2483,42 @@ lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) static void lec_arp_check_empties(struct lec_priv *priv, - struct atm_vcc *vcc, struct sk_buff *skb) + struct atm_vcc *vcc, struct sk_buff *skb) { - unsigned long flags; - struct lec_arp_table *entry, *prev; - struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; - unsigned char *src; + unsigned long flags; + struct hlist_node *node, *next; + struct lec_arp_table *entry, *tmp; + struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; + unsigned char *src; #ifdef CONFIG_TR - struct lecdatahdr_8025 *tr_hdr = (struct lecdatahdr_8025 *)skb->data; + struct lecdatahdr_8025 *tr_hdr = (struct lecdatahdr_8025 *)skb->data; - if (priv->is_trdev) src = tr_hdr->h_source; - else + if (priv->is_trdev) + src = tr_hdr->h_source; + else #endif - src = hdr->h_source; + src = hdr->h_source; spin_lock_irqsave(&priv->lec_arp_lock, flags); - entry = priv->lec_arp_empty_ones; - if (vcc == entry->vcc) { - del_timer(&entry->timer); - memcpy(entry->mac_addr, src, ETH_ALEN); - entry->status = ESI_FORWARD_DIRECT; - entry->last_used = jiffies; - priv->lec_arp_empty_ones = entry->next; - /* We might have got an entry */ - if ((prev = lec_arp_find(priv,src))) { - lec_arp_remove(priv, prev); - kfree(prev); - } - lec_arp_add(priv, entry); - goto out; - } - prev = entry; - entry = entry->next; - while (entry && entry->vcc != vcc) { - prev= entry; - entry = entry->next; - } - if (!entry) { - DPRINTK("LEC_ARP: Arp_check_empties: entry not found!\n"); - goto out; - } - del_timer(&entry->timer); - memcpy(entry->mac_addr, src, ETH_ALEN); - entry->status = ESI_FORWARD_DIRECT; - entry->last_used = jiffies; - prev->next = entry->next; - if ((prev = lec_arp_find(priv, src))) { - lec_arp_remove(priv, prev); - kfree(prev); - } - lec_arp_add(priv, entry); + hlist_for_each_entry_safe(entry, node, next, &priv->lec_arp_empty_ones, next) { + if (vcc == entry->vcc) { + del_timer(&entry->timer); + memcpy(entry->mac_addr, src, ETH_ALEN); + entry->status = ESI_FORWARD_DIRECT; + entry->last_used = jiffies; + /* We might have got an entry */ + if ((tmp = lec_arp_find(priv, src))) { + lec_arp_remove(priv, tmp); + lec_arp_put(tmp); + } + hlist_del(&entry->next); + lec_arp_add(priv, entry); + goto out; + } + } + DPRINTK("LEC_ARP: Arp_check_empties: entry not found!\n"); out: spin_unlock_irqrestore(&priv->lec_arp_lock, flags); } + MODULE_LICENSE("GPL"); diff --git a/net/atm/lec.h b/net/atm/lec.h index c22a8bfa1f81..877f50939696 100644 --- a/net/atm/lec.h +++ b/net/atm/lec.h @@ -1,9 +1,7 @@ /* - * * Lan Emulation client header file * - * Marko Kiiskila mkiiskila@yahoo.com - * + * Marko Kiiskila <mkiiskila@yahoo.com> */ #ifndef _LEC_H_ @@ -16,18 +14,18 @@ #define LEC_HEADER_LEN 16 struct lecdatahdr_8023 { - unsigned short le_header; - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; - unsigned short h_type; + unsigned short le_header; + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_type; }; struct lecdatahdr_8025 { - unsigned short le_header; - unsigned char ac_pad; - unsigned char fc; - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + unsigned short le_header; + unsigned char ac_pad; + unsigned char fc; + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; }; #define LEC_MINIMUM_8023_SIZE 62 @@ -44,17 +42,18 @@ struct lecdatahdr_8025 { * */ struct lane2_ops { - int (*resolve)(struct net_device *dev, u8 *dst_mac, int force, - u8 **tlvs, u32 *sizeoftlvs); - int (*associate_req)(struct net_device *dev, u8 *lan_dst, - u8 *tlvs, u32 sizeoftlvs); - void (*associate_indicator)(struct net_device *dev, u8 *mac_addr, - u8 *tlvs, u32 sizeoftlvs); + int (*resolve) (struct net_device *dev, u8 *dst_mac, int force, + u8 **tlvs, u32 *sizeoftlvs); + int (*associate_req) (struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs); + void (*associate_indicator) (struct net_device *dev, u8 *mac_addr, + u8 *tlvs, u32 sizeoftlvs); }; /* * ATM LAN Emulation supports both LLC & Dix Ethernet EtherType * frames. + * * 1. Dix Ethernet EtherType frames encoded by placing EtherType * field in h_type field. Data follows immediatelly after header. * 2. LLC Data frames whose total length, including LLC field and data, @@ -70,72 +69,88 @@ struct lane2_ops { #define LEC_ARP_TABLE_SIZE 16 struct lec_priv { - struct net_device_stats stats; - unsigned short lecid; /* Lecid of this client */ - struct lec_arp_table *lec_arp_empty_ones; - /* Used for storing VCC's that don't have a MAC address attached yet */ - struct lec_arp_table *lec_arp_tables[LEC_ARP_TABLE_SIZE]; - /* Actual LE ARP table */ - struct lec_arp_table *lec_no_forward; - /* Used for storing VCC's (and forward packets from) which are to - age out by not using them to forward packets. - This is because to some LE clients there will be 2 VCCs. Only - one of them gets used. */ - struct lec_arp_table *mcast_fwds; - /* With LANEv2 it is possible that BUS (or a special multicast server) - establishes multiple Multicast Forward VCCs to us. This list - collects all those VCCs. LANEv1 client has only one item in this - list. These entries are not aged out. */ - spinlock_t lec_arp_lock; - struct atm_vcc *mcast_vcc; /* Default Multicast Send VCC */ - struct atm_vcc *lecd; - struct timer_list lec_arp_timer; - /* C10 */ - unsigned int maximum_unknown_frame_count; -/* Within the period of time defined by this variable, the client will send - no more than C10 frames to BUS for a given unicast destination. (C11) */ - unsigned long max_unknown_frame_time; -/* If no traffic has been sent in this vcc for this period of time, - vcc will be torn down (C12)*/ - unsigned long vcc_timeout_period; -/* An LE Client MUST not retry an LE_ARP_REQUEST for a - given frame's LAN Destination more than maximum retry count times, - after the first LEC_ARP_REQUEST (C13)*/ - unsigned short max_retry_count; -/* Max time the client will maintain an entry in its arp cache in - absence of a verification of that relationship (C17)*/ - unsigned long aging_time; -/* Max time the client will maintain an entry in cache when - topology change flag is true (C18) */ - unsigned long forward_delay_time; -/* Topology change flag (C19)*/ - int topology_change; -/* Max time the client expects an LE_ARP_REQUEST/LE_ARP_RESPONSE - cycle to take (C20)*/ - unsigned long arp_response_time; -/* Time limit ot wait to receive an LE_FLUSH_RESPONSE after the - LE_FLUSH_REQUEST has been sent before taking recover action. (C21)*/ - unsigned long flush_timeout; -/* The time since sending a frame to the bus after which the - LE Client may assume that the frame has been either discarded or - delivered to the recipient (C22) */ - unsigned long path_switching_delay; + struct net_device_stats stats; + unsigned short lecid; /* Lecid of this client */ + struct hlist_head lec_arp_empty_ones; + /* Used for storing VCC's that don't have a MAC address attached yet */ + struct hlist_head lec_arp_tables[LEC_ARP_TABLE_SIZE]; + /* Actual LE ARP table */ + struct hlist_head lec_no_forward; + /* + * Used for storing VCC's (and forward packets from) which are to + * age out by not using them to forward packets. + * This is because to some LE clients there will be 2 VCCs. Only + * one of them gets used. + */ + struct hlist_head mcast_fwds; + /* + * With LANEv2 it is possible that BUS (or a special multicast server) + * establishes multiple Multicast Forward VCCs to us. This list + * collects all those VCCs. LANEv1 client has only one item in this + * list. These entries are not aged out. + */ + spinlock_t lec_arp_lock; + struct atm_vcc *mcast_vcc; /* Default Multicast Send VCC */ + struct atm_vcc *lecd; + struct work_struct lec_arp_work; /* C10 */ + unsigned int maximum_unknown_frame_count; + /* + * Within the period of time defined by this variable, the client will send + * no more than C10 frames to BUS for a given unicast destination. (C11) + */ + unsigned long max_unknown_frame_time; + /* + * If no traffic has been sent in this vcc for this period of time, + * vcc will be torn down (C12) + */ + unsigned long vcc_timeout_period; + /* + * An LE Client MUST not retry an LE_ARP_REQUEST for a + * given frame's LAN Destination more than maximum retry count times, + * after the first LEC_ARP_REQUEST (C13) + */ + unsigned short max_retry_count; + /* + * Max time the client will maintain an entry in its arp cache in + * absence of a verification of that relationship (C17) + */ + unsigned long aging_time; + /* + * Max time the client will maintain an entry in cache when + * topology change flag is true (C18) + */ + unsigned long forward_delay_time; /* Topology change flag (C19) */ + int topology_change; + /* + * Max time the client expects an LE_ARP_REQUEST/LE_ARP_RESPONSE + * cycle to take (C20) + */ + unsigned long arp_response_time; + /* + * Time limit ot wait to receive an LE_FLUSH_RESPONSE after the + * LE_FLUSH_REQUEST has been sent before taking recover action. (C21) + */ + unsigned long flush_timeout; + /* The time since sending a frame to the bus after which the + * LE Client may assume that the frame has been either discarded or + * delivered to the recipient (C22) + */ + unsigned long path_switching_delay; - u8 *tlvs; /* LANE2: TLVs are new */ - u32 sizeoftlvs; /* The size of the tlv array in bytes */ - int lane_version; /* LANE2 */ - int itfnum; /* e.g. 2 for lec2, 5 for lec5 */ - struct lane2_ops *lane2_ops; /* can be NULL for LANE v1 */ - int is_proxy; /* bridge between ATM and Ethernet */ - int is_trdev; /* Device type, 0 = Ethernet, 1 = TokenRing */ + u8 *tlvs; /* LANE2: TLVs are new */ + u32 sizeoftlvs; /* The size of the tlv array in bytes */ + int lane_version; /* LANE2 */ + int itfnum; /* e.g. 2 for lec2, 5 for lec5 */ + struct lane2_ops *lane2_ops; /* can be NULL for LANE v1 */ + int is_proxy; /* bridge between ATM and Ethernet */ + int is_trdev; /* Device type, 0 = Ethernet, 1 = TokenRing */ }; struct lec_vcc_priv { - void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); + void (*old_pop) (struct atm_vcc *vcc, struct sk_buff *skb); int xoff; }; #define LEC_VCC_PRIV(vcc) ((struct lec_vcc_priv *)((vcc)->user_back)) -#endif /* _LEC_H_ */ - +#endif /* _LEC_H_ */ diff --git a/net/atm/lec_arpc.h b/net/atm/lec_arpc.h index 397448094648..ec67435a40a6 100644 --- a/net/atm/lec_arpc.h +++ b/net/atm/lec_arpc.h @@ -1,92 +1,96 @@ /* * Lec arp cache - * Marko Kiiskila mkiiskila@yahoo.com * + * Marko Kiiskila <mkiiskila@yahoo.com> */ -#ifndef _LEC_ARP_H -#define _LEC_ARP_H +#ifndef _LEC_ARP_H_ +#define _LEC_ARP_H_ #include <linux/atm.h> #include <linux/atmdev.h> #include <linux/if_ether.h> #include <linux/atmlec.h> struct lec_arp_table { - struct lec_arp_table *next; /* Linked entry list */ - unsigned char atm_addr[ATM_ESA_LEN]; /* Atm address */ - unsigned char mac_addr[ETH_ALEN]; /* Mac address */ - int is_rdesc; /* Mac address is a route descriptor */ - struct atm_vcc *vcc; /* Vcc this entry is attached */ - struct atm_vcc *recv_vcc; /* Vcc we receive data from */ - void (*old_push)(struct atm_vcc *vcc,struct sk_buff *skb); - /* Push that leads to daemon */ - void (*old_recv_push)(struct atm_vcc *vcc, struct sk_buff *skb); - /* Push that leads to daemon */ - void (*old_close)(struct atm_vcc *vcc); - /* We want to see when this - * vcc gets closed */ - unsigned long last_used; /* For expiry */ - unsigned long timestamp; /* Used for various timestamping - * things: - * 1. FLUSH started - * (status=ESI_FLUSH_PENDING) - * 2. Counting to - * max_unknown_frame_time - * (status=ESI_ARP_PENDING|| - * status=ESI_VC_PENDING) - */ - unsigned char no_tries; /* No of times arp retry has been - tried */ - unsigned char status; /* Status of this entry */ - unsigned short flags; /* Flags for this entry */ - unsigned short packets_flooded; /* Data packets flooded */ - unsigned long flush_tran_id; /* Transaction id in flush protocol */ - struct timer_list timer; /* Arping timer */ - struct lec_priv *priv; /* Pointer back */ + struct hlist_node next; /* Linked entry list */ + unsigned char atm_addr[ATM_ESA_LEN]; /* Atm address */ + unsigned char mac_addr[ETH_ALEN]; /* Mac address */ + int is_rdesc; /* Mac address is a route descriptor */ + struct atm_vcc *vcc; /* Vcc this entry is attached */ + struct atm_vcc *recv_vcc; /* Vcc we receive data from */ - u8 *tlvs; /* LANE2: Each MAC address can have TLVs */ - u32 sizeoftlvs; /* associated with it. sizeoftlvs tells the */ - /* the length of the tlvs array */ - struct sk_buff_head tx_wait; /* wait queue for outgoing packets */ + void (*old_push) (struct atm_vcc *vcc, struct sk_buff *skb); + /* Push that leads to daemon */ + + void (*old_recv_push) (struct atm_vcc *vcc, struct sk_buff *skb); + /* Push that leads to daemon */ + + unsigned long last_used; /* For expiry */ + unsigned long timestamp; /* Used for various timestamping things: + * 1. FLUSH started + * (status=ESI_FLUSH_PENDING) + * 2. Counting to + * max_unknown_frame_time + * (status=ESI_ARP_PENDING|| + * status=ESI_VC_PENDING) + */ + unsigned char no_tries; /* No of times arp retry has been tried */ + unsigned char status; /* Status of this entry */ + unsigned short flags; /* Flags for this entry */ + unsigned short packets_flooded; /* Data packets flooded */ + unsigned long flush_tran_id; /* Transaction id in flush protocol */ + struct timer_list timer; /* Arping timer */ + struct lec_priv *priv; /* Pointer back */ + u8 *tlvs; + u32 sizeoftlvs; /* + * LANE2: Each MAC address can have TLVs + * associated with it. sizeoftlvs tells the + * the length of the tlvs array + */ + struct sk_buff_head tx_wait; /* wait queue for outgoing packets */ + atomic_t usage; /* usage count */ }; -struct tlv { /* LANE2: Template tlv struct for accessing */ - /* the tlvs in the lec_arp_table->tlvs array*/ - u32 type; - u8 length; - u8 value[255]; +/* + * LANE2: Template tlv struct for accessing + * the tlvs in the lec_arp_table->tlvs array + */ +struct tlv { + u32 type; + u8 length; + u8 value[255]; }; /* Status fields */ -#define ESI_UNKNOWN 0 /* - * Next packet sent to this mac address - * causes ARP-request to be sent - */ -#define ESI_ARP_PENDING 1 /* - * There is no ATM address associated with this - * 48-bit address. The LE-ARP protocol is in - * progress. - */ -#define ESI_VC_PENDING 2 /* - * There is a valid ATM address associated with - * this 48-bit address but there is no VC set - * up to that ATM address. The signaling - * protocol is in process. - */ -#define ESI_FLUSH_PENDING 4 /* - * The LEC has been notified of the FLUSH_START - * status and it is assumed that the flush - * protocol is in process. - */ -#define ESI_FORWARD_DIRECT 5 /* - * Either the Path Switching Delay (C22) has - * elapsed or the LEC has notified the Mapping - * that the flush protocol has completed. In - * either case, it is safe to forward packets - * to this address via the data direct VC. - */ +#define ESI_UNKNOWN 0 /* + * Next packet sent to this mac address + * causes ARP-request to be sent + */ +#define ESI_ARP_PENDING 1 /* + * There is no ATM address associated with this + * 48-bit address. The LE-ARP protocol is in + * progress. + */ +#define ESI_VC_PENDING 2 /* + * There is a valid ATM address associated with + * this 48-bit address but there is no VC set + * up to that ATM address. The signaling + * protocol is in process. + */ +#define ESI_FLUSH_PENDING 4 /* + * The LEC has been notified of the FLUSH_START + * status and it is assumed that the flush + * protocol is in process. + */ +#define ESI_FORWARD_DIRECT 5 /* + * Either the Path Switching Delay (C22) has + * elapsed or the LEC has notified the Mapping + * that the flush protocol has completed. In + * either case, it is safe to forward packets + * to this address via the data direct VC. + */ /* Flag values */ #define LEC_REMOTE_FLAG 0x0001 #define LEC_PERMANENT_FLAG 0x0002 -#endif +#endif /* _LEC_ARP_H_ */ diff --git a/net/atm/mpc.c b/net/atm/mpc.c index b87c2a88bdce..0d2b994af511 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -560,7 +560,6 @@ static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg) struct atmmpc_ioc ioc_data; in_cache_entry *in_entry; uint32_t ipaddr; - unsigned char *ip; bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmmpc_ioc)); if (bytes_left != 0) { @@ -583,9 +582,8 @@ static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg) if (in_entry != NULL) mpc->in_ops->put(in_entry); return -EINVAL; } - ip = (unsigned char*)&in_entry->ctrl_info.in_dst_ip; printk("mpoa: (%s) mpc_vcc_attach: attaching ingress SVC, entry = %u.%u.%u.%u\n", - mpc->dev->name, ip[0], ip[1], ip[2], ip[3]); + mpc->dev->name, NIPQUAD(in_entry->ctrl_info.in_dst_ip)); in_entry->shortcut = vcc; mpc->in_ops->put(in_entry); } else { @@ -616,10 +614,8 @@ static void mpc_vcc_close(struct atm_vcc *vcc, struct net_device *dev) dprintk("mpoa: (%s) mpc_vcc_close:\n", dev->name); in_entry = mpc->in_ops->get_by_vcc(vcc, mpc); if (in_entry) { - unsigned char *ip __attribute__ ((unused)) = - (unsigned char *)&in_entry->ctrl_info.in_dst_ip; dprintk("mpoa: (%s) mpc_vcc_close: ingress SVC closed ip = %u.%u.%u.%u\n", - mpc->dev->name, ip[0], ip[1], ip[2], ip[3]); + mpc->dev->name, NIPQUAD(in_entry->ctrl_info.in_dst_ip)); in_entry->shortcut = NULL; mpc->in_ops->put(in_entry); } @@ -1154,18 +1150,17 @@ static void ingress_purge_rcvd(struct k_message *msg, struct mpoa_client *mpc) { uint32_t dst_ip = msg->content.in_info.in_dst_ip; uint32_t mask = msg->ip_mask; - unsigned char *ip = (unsigned char *)&dst_ip; in_cache_entry *entry = mpc->in_ops->get_with_mask(dst_ip, mpc, mask); if(entry == NULL){ printk("mpoa: (%s) ingress_purge_rcvd: purge for a non-existing entry, ", mpc->dev->name); - printk("ip = %u.%u.%u.%u\n", ip[0], ip[1], ip[2], ip[3]); + printk("ip = %u.%u.%u.%u\n", NIPQUAD(dst_ip)); return; } do { dprintk("mpoa: (%s) ingress_purge_rcvd: removing an ingress entry, ip = %u.%u.%u.%u\n" , - mpc->dev->name, ip[0], ip[1], ip[2], ip[3]); + mpc->dev->name, NIPQUAD(dst_ip)); write_lock_bh(&mpc->ingress_lock); mpc->in_ops->remove_entry(entry, mpc); write_unlock_bh(&mpc->ingress_lock); diff --git a/net/atm/mpoa_caches.c b/net/atm/mpoa_caches.c index 781ed1b9329d..fbf13cdcf46e 100644 --- a/net/atm/mpoa_caches.c +++ b/net/atm/mpoa_caches.c @@ -87,7 +87,6 @@ static in_cache_entry *in_cache_get_by_vcc(struct atm_vcc *vcc, static in_cache_entry *in_cache_add_entry(uint32_t dst_ip, struct mpoa_client *client) { - unsigned char *ip __attribute__ ((unused)) = (unsigned char *)&dst_ip; in_cache_entry* entry = kmalloc(sizeof(in_cache_entry), GFP_KERNEL); if (entry == NULL) { @@ -95,7 +94,7 @@ static in_cache_entry *in_cache_add_entry(uint32_t dst_ip, return NULL; } - dprintk("mpoa: mpoa_caches.c: adding an ingress entry, ip = %u.%u.%u.%u\n", ip[0], ip[1], ip[2], ip[3]); + dprintk("mpoa: mpoa_caches.c: adding an ingress entry, ip = %u.%u.%u.%u\n", NIPQUAD(dst_ip)); memset(entry,0,sizeof(in_cache_entry)); atomic_set(&entry->use, 1); @@ -152,10 +151,7 @@ static int cache_hit(in_cache_entry *entry, struct mpoa_client *mpc) if( entry->count > mpc->parameters.mpc_p1 && entry->entry_state == INGRESS_INVALID){ - unsigned char *ip __attribute__ ((unused)) = - (unsigned char *)&entry->ctrl_info.in_dst_ip; - - dprintk("mpoa: (%s) mpoa_caches.c: threshold exceeded for ip %u.%u.%u.%u, sending MPOA res req\n", mpc->dev->name, ip[0], ip[1], ip[2], ip[3]); + dprintk("mpoa: (%s) mpoa_caches.c: threshold exceeded for ip %u.%u.%u.%u, sending MPOA res req\n", mpc->dev->name, NIPQUAD(entry->ctrl_info.in_dst_ip)); entry->entry_state = INGRESS_RESOLVING; msg.type = SND_MPOA_RES_RQST; memcpy(msg.MPS_ctrl, mpc->mps_ctrl_addr, ATM_ESA_LEN ); @@ -187,11 +183,9 @@ static void in_cache_remove_entry(in_cache_entry *entry, { struct atm_vcc *vcc; struct k_message msg; - unsigned char *ip; vcc = entry->shortcut; - ip = (unsigned char *)&entry->ctrl_info.in_dst_ip; - dprintk("mpoa: mpoa_caches.c: removing an ingress entry, ip = %u.%u.%u.%u\n",ip[0], ip[1], ip[2], ip[3]); + dprintk("mpoa: mpoa_caches.c: removing an ingress entry, ip = %u.%u.%u.%u\n",NIPQUAD(entry->ctrl_info.in_dst_ip)); if (entry->prev != NULL) entry->prev->next = entry->next; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 788ea7a2b744..67df99e2e5c8 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -48,41 +48,56 @@ #define BT_DBG(D...) #endif -#define VERSION "2.10" +#define VERSION "2.11" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 static struct net_proto_family *bt_proto[BT_MAX_PROTO]; +static DEFINE_RWLOCK(bt_proto_lock); int bt_sock_register(int proto, struct net_proto_family *ops) { + int err = 0; + if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; + write_lock(&bt_proto_lock); + if (bt_proto[proto]) - return -EEXIST; + err = -EEXIST; + else + bt_proto[proto] = ops; - bt_proto[proto] = ops; - return 0; + write_unlock(&bt_proto_lock); + + return err; } EXPORT_SYMBOL(bt_sock_register); int bt_sock_unregister(int proto) { + int err = 0; + if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; + write_lock(&bt_proto_lock); + if (!bt_proto[proto]) - return -ENOENT; + err = -ENOENT; + else + bt_proto[proto] = NULL; - bt_proto[proto] = NULL; - return 0; + write_unlock(&bt_proto_lock); + + return err; } EXPORT_SYMBOL(bt_sock_unregister); static int bt_sock_create(struct socket *sock, int proto) { - int err = 0; + int err; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; @@ -92,11 +107,18 @@ static int bt_sock_create(struct socket *sock, int proto) request_module("bt-proto-%d", proto); } #endif + err = -EPROTONOSUPPORT; + + read_lock(&bt_proto_lock); + if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(sock, proto); module_put(bt_proto[proto]->owner); } + + read_unlock(&bt_proto_lock); + return err; } @@ -276,7 +298,7 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { - err = -EAGAIN; + err = -EINPROGRESS; break; } diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index e620061fb50f..4d3424c2421c 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -51,6 +51,7 @@ #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include "bnep.h" @@ -515,6 +516,24 @@ static int bnep_session(void *arg) return 0; } +static struct device *bnep_get_device(struct bnep_session *session) +{ + bdaddr_t *src = &bt_sk(session->sock->sk)->src; + bdaddr_t *dst = &bt_sk(session->sock->sk)->dst; + struct hci_dev *hdev; + struct hci_conn *conn; + + hdev = hci_get_route(dst, src); + if (!hdev) + return NULL; + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); + + hci_dev_put(hdev); + + return conn ? &conn->dev : NULL; +} + int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) { struct net_device *dev; @@ -534,7 +553,6 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) if (!dev) return -ENOMEM; - down_write(&bnep_session_sem); ss = __bnep_get_session(dst); @@ -551,7 +569,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) memcpy(s->eh.h_source, &dst, ETH_ALEN); memcpy(dev->dev_addr, s->eh.h_dest, ETH_ALEN); - s->dev = dev; + s->dev = dev; s->sock = sock; s->role = req->role; s->state = BT_CONNECTED; @@ -568,6 +586,8 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) bnep_set_default_proto_filter(s); #endif + SET_NETDEV_DEV(dev, bnep_get_device(s)); + err = register_netdev(dev); if (err) { goto failed; diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 28c55835422a..5563db1bf526 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -43,6 +43,7 @@ #include <linux/ioctl.h> #include <linux/file.h> #include <linux/init.h> +#include <linux/compat.h> #include <net/sock.h> #include <asm/system.h> @@ -146,24 +147,56 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long return 0; } +#ifdef CONFIG_COMPAT +static int bnep_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == BNEPGETCONNLIST) { + struct bnep_connlist_req cl; + uint32_t uci; + int err; + + if (get_user(cl.cnum, (uint32_t __user *) arg) || + get_user(uci, (u32 __user *) (arg + 4))) + return -EFAULT; + + cl.ci = compat_ptr(uci); + + if (cl.cnum <= 0) + return -EINVAL; + + err = bnep_get_connlist(&cl); + + if (!err && put_user(cl.cnum, (uint32_t __user *) arg)) + err = -EFAULT; + + return err; + } + + return bnep_sock_ioctl(sock, cmd, arg); +} +#endif + static const struct proto_ops bnep_sock_ops = { - .family = PF_BLUETOOTH, - .owner = THIS_MODULE, - .release = bnep_sock_release, - .ioctl = bnep_sock_ioctl, - .bind = sock_no_bind, - .getname = sock_no_getname, - .sendmsg = sock_no_sendmsg, - .recvmsg = sock_no_recvmsg, - .poll = sock_no_poll, - .listen = sock_no_listen, - .shutdown = sock_no_shutdown, - .setsockopt = sock_no_setsockopt, - .getsockopt = sock_no_getsockopt, - .connect = sock_no_connect, - .socketpair = sock_no_socketpair, - .accept = sock_no_accept, - .mmap = sock_no_mmap + .family = PF_BLUETOOTH, + .owner = THIS_MODULE, + .release = bnep_sock_release, + .ioctl = bnep_sock_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = bnep_sock_compat_ioctl, +#endif + .bind = sock_no_bind, + .getname = sock_no_getname, + .sendmsg = sock_no_sendmsg, + .recvmsg = sock_no_recvmsg, + .poll = sock_no_poll, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_no_setsockopt, + .getsockopt = sock_no_getsockopt, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .mmap = sock_no_mmap }; static struct proto bnep_proto = { @@ -181,7 +214,7 @@ static int bnep_sock_create(struct socket *sock, int protocol) if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &bnep_proto, 1); + sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, 1); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c index 10ad7fd91d83..53295d33dc5c 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -34,6 +34,7 @@ #include <linux/socket.h> #include <linux/ioctl.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/sock.h> #include <linux/isdn/capilli.h> @@ -137,11 +138,43 @@ static int cmtp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long return -EINVAL; } +#ifdef CONFIG_COMPAT +static int cmtp_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == CMTPGETCONNLIST) { + struct cmtp_connlist_req cl; + uint32_t uci; + int err; + + if (get_user(cl.cnum, (uint32_t __user *) arg) || + get_user(uci, (u32 __user *) (arg + 4))) + return -EFAULT; + + cl.ci = compat_ptr(uci); + + if (cl.cnum <= 0) + return -EINVAL; + + err = cmtp_get_connlist(&cl); + + if (!err && put_user(cl.cnum, (uint32_t __user *) arg)) + err = -EFAULT; + + return err; + } + + return cmtp_sock_ioctl(sock, cmd, arg); +} +#endif + static const struct proto_ops cmtp_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = cmtp_sock_release, .ioctl = cmtp_sock_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = cmtp_sock_compat_ioctl, +#endif .bind = sock_no_bind, .getname = sock_no_getname, .sendmsg = sock_no_sendmsg, @@ -172,7 +205,7 @@ static int cmtp_sock_create(struct socket *sock, int protocol) if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &cmtp_proto, 1); + sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto, 1); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 420ed4d7e57e..6cd5711fa28a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -51,7 +51,7 @@ #define BT_DBG(D...) #endif -static void hci_acl_connect(struct hci_conn *conn) +void hci_acl_connect(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct inquiry_entry *ie; @@ -63,6 +63,8 @@ static void hci_acl_connect(struct hci_conn *conn) conn->out = 1; conn->link_mode = HCI_LM_MASTER; + conn->attempt++; + memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; @@ -80,10 +82,24 @@ static void hci_acl_connect(struct hci_conn *conn) cp.role_switch = 0x01; else cp.role_switch = 0x00; - + hci_send_cmd(hdev, OGF_LINK_CTL, OCF_CREATE_CONN, sizeof(cp), &cp); } +static void hci_acl_connect_cancel(struct hci_conn *conn) +{ + struct hci_cp_create_conn_cancel cp; + + BT_DBG("%p", conn); + + if (conn->hdev->hci_ver < 2) + return; + + bacpy(&cp.bdaddr, &conn->dst); + hci_send_cmd(conn->hdev, OGF_LINK_CTL, + OCF_CREATE_CONN_CANCEL, sizeof(cp), &cp); +} + void hci_acl_disconn(struct hci_conn *conn, __u8 reason) { struct hci_cp_disconnect cp; @@ -94,7 +110,8 @@ void hci_acl_disconn(struct hci_conn *conn, __u8 reason) cp.handle = __cpu_to_le16(conn->handle); cp.reason = reason; - hci_send_cmd(conn->hdev, OGF_LINK_CTL, OCF_DISCONNECT, sizeof(cp), &cp); + hci_send_cmd(conn->hdev, OGF_LINK_CTL, + OCF_DISCONNECT, sizeof(cp), &cp); } void hci_add_sco(struct hci_conn *conn, __u16 handle) @@ -124,12 +141,20 @@ static void hci_conn_timeout(unsigned long arg) return; hci_dev_lock(hdev); - if (conn->state == BT_CONNECTED) + + switch (conn->state) { + case BT_CONNECT: + hci_acl_connect_cancel(conn); + break; + case BT_CONNECTED: hci_acl_disconn(conn, 0x13); - else + break; + default: conn->state = BT_CLOSED; + break; + } + hci_dev_unlock(hdev); - return; } static void hci_conn_idle(unsigned long arg) @@ -179,6 +204,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); + hci_conn_add_sysfs(conn); + tasklet_enable(&hdev->tx_task); return conn; @@ -211,6 +238,8 @@ int hci_conn_del(struct hci_conn *conn) tasklet_disable(&hdev->tx_task); + hci_conn_del_sysfs(conn); + hci_conn_hash_del(hdev, conn); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); @@ -221,7 +250,9 @@ int hci_conn_del(struct hci_conn *conn) hci_dev_put(hdev); - kfree(conn); + /* will free via device release */ + put_device(&conn->dev); + return 0; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5ed474277903..338ae977a31b 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -206,6 +206,9 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) /* Read Local Supported Features */ hci_send_cmd(hdev, OGF_INFO_PARAM, OCF_READ_LOCAL_FEATURES, 0, NULL); + /* Read Local Version */ + hci_send_cmd(hdev, OGF_INFO_PARAM, OCF_READ_LOCAL_VERSION, 0, NULL); + /* Read Buffer Size (ACL mtu, max pkt, etc.) */ hci_send_cmd(hdev, OGF_INFO_PARAM, OCF_READ_BUFFER_SIZE, 0, NULL); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 3896dabab11d..65f094845719 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -62,6 +62,7 @@ static void hci_cc_link_ctl(struct hci_dev *hdev, __u16 ocf, struct sk_buff *skb switch (ocf) { case OCF_INQUIRY_CANCEL: + case OCF_EXIT_PERIODIC_INQ: status = *((__u8 *) skb->data); if (status) { @@ -297,6 +298,7 @@ static void hci_cc_host_ctl(struct hci_dev *hdev, __u16 ocf, struct sk_buff *skb /* Command Complete OGF INFO_PARAM */ static void hci_cc_info_param(struct hci_dev *hdev, __u16 ocf, struct sk_buff *skb) { + struct hci_rp_read_loc_version *lv; struct hci_rp_read_local_features *lf; struct hci_rp_read_buffer_size *bs; struct hci_rp_read_bd_addr *ba; @@ -304,6 +306,23 @@ static void hci_cc_info_param(struct hci_dev *hdev, __u16 ocf, struct sk_buff *s BT_DBG("%s ocf 0x%x", hdev->name, ocf); switch (ocf) { + case OCF_READ_LOCAL_VERSION: + lv = (struct hci_rp_read_loc_version *) skb->data; + + if (lv->status) { + BT_DBG("%s READ_LOCAL_VERSION failed %d", hdev->name, lf->status); + break; + } + + hdev->hci_ver = lv->hci_ver; + hdev->hci_rev = btohs(lv->hci_rev); + hdev->manufacturer = btohs(lv->manufacturer); + + BT_DBG("%s: manufacturer %d hci_ver %d hci_rev %d", hdev->name, + hdev->manufacturer, hdev->hci_ver, hdev->hci_rev); + + break; + case OCF_READ_LOCAL_FEATURES: lf = (struct hci_rp_read_local_features *) skb->data; @@ -328,7 +347,8 @@ static void hci_cc_info_param(struct hci_dev *hdev, __u16 ocf, struct sk_buff *s if (hdev->features[1] & LMP_HV3) hdev->pkt_type |= (HCI_HV3); - BT_DBG("%s: features 0x%x 0x%x 0x%x", hdev->name, lf->features[0], lf->features[1], lf->features[2]); + BT_DBG("%s: features 0x%x 0x%x 0x%x", hdev->name, + lf->features[0], lf->features[1], lf->features[2]); break; @@ -394,9 +414,12 @@ static inline void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) if (status) { if (conn && conn->state == BT_CONNECT) { - conn->state = BT_CLOSED; - hci_proto_connect_cfm(conn, status); - hci_conn_del(conn); + if (status != 0x0c || conn->attempt > 2) { + conn->state = BT_CLOSED; + hci_proto_connect_cfm(conn, status); + hci_conn_del(conn); + } else + conn->state = BT_CONNECT2; } } else { if (!conn) { @@ -708,7 +731,7 @@ static inline void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *sk static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_complete *ev = (struct hci_ev_conn_complete *) skb->data; - struct hci_conn *conn; + struct hci_conn *conn, *pend; BT_DBG("%s", hdev->name); @@ -757,6 +780,10 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s hci_send_cmd(hdev, OGF_LINK_CTL, OCF_CHANGE_CONN_PTYPE, sizeof(cp), &cp); + } else { + /* Update disconnect timer */ + hci_conn_hold(conn); + hci_conn_put(conn); } } else conn->state = BT_CLOSED; @@ -777,6 +804,10 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (ev->status) hci_conn_del(conn); + pend = hci_conn_hash_lookup_state(hdev, ACL_LINK, BT_CONNECT2); + if (pend) + hci_acl_connect(pend); + hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1a35d343e08a..f26a9eb49945 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -618,7 +618,7 @@ static int hci_sock_create(struct socket *sock, int protocol) sock->ops = &hci_sock_ops; - sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &hci_sk_proto, 1); + sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, 1); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 3987d167f04e..954eb74eb370 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -13,16 +13,32 @@ #define BT_DBG(D...) #endif -static ssize_t show_name(struct device *dev, struct device_attribute *attr, char *buf) +static inline char *typetostr(int type) { - struct hci_dev *hdev = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", hdev->name); + switch (type) { + case HCI_VIRTUAL: + return "VIRTUAL"; + case HCI_USB: + return "USB"; + case HCI_PCCARD: + return "PCCARD"; + case HCI_UART: + return "UART"; + case HCI_RS232: + return "RS232"; + case HCI_PCI: + return "PCI"; + case HCI_SDIO: + return "SDIO"; + default: + return "UNKNOWN"; + } } static ssize_t show_type(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_dev *hdev = dev_get_drvdata(dev); - return sprintf(buf, "%d\n", hdev->type); + return sprintf(buf, "%s\n", typetostr(hdev->type)); } static ssize_t show_address(struct device *dev, struct device_attribute *attr, char *buf) @@ -33,10 +49,22 @@ static ssize_t show_address(struct device *dev, struct device_attribute *attr, c return sprintf(buf, "%s\n", batostr(&bdaddr)); } -static ssize_t show_flags(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_manufacturer(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_dev *hdev = dev_get_drvdata(dev); - return sprintf(buf, "0x%lx\n", hdev->flags); + return sprintf(buf, "%d\n", hdev->manufacturer); +} + +static ssize_t show_hci_version(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_dev *hdev = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", hdev->hci_ver); +} + +static ssize_t show_hci_revision(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_dev *hdev = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", hdev->hci_rev); } static ssize_t show_inquiry_cache(struct device *dev, struct device_attribute *attr, char *buf) @@ -141,10 +169,11 @@ static ssize_t store_sniff_min_interval(struct device *dev, struct device_attrib return count; } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); static DEVICE_ATTR(type, S_IRUGO, show_type, NULL); static DEVICE_ATTR(address, S_IRUGO, show_address, NULL); -static DEVICE_ATTR(flags, S_IRUGO, show_flags, NULL); +static DEVICE_ATTR(manufacturer, S_IRUGO, show_manufacturer, NULL); +static DEVICE_ATTR(hci_version, S_IRUGO, show_hci_version, NULL); +static DEVICE_ATTR(hci_revision, S_IRUGO, show_hci_revision, NULL); static DEVICE_ATTR(inquiry_cache, S_IRUGO, show_inquiry_cache, NULL); static DEVICE_ATTR(idle_timeout, S_IRUGO | S_IWUSR, @@ -155,10 +184,11 @@ static DEVICE_ATTR(sniff_min_interval, S_IRUGO | S_IWUSR, show_sniff_min_interval, store_sniff_min_interval); static struct device_attribute *bt_attrs[] = { - &dev_attr_name, &dev_attr_type, &dev_attr_address, - &dev_attr_flags, + &dev_attr_manufacturer, + &dev_attr_hci_version, + &dev_attr_hci_revision, &dev_attr_inquiry_cache, &dev_attr_idle_timeout, &dev_attr_sniff_max_interval, @@ -166,6 +196,32 @@ static struct device_attribute *bt_attrs[] = { NULL }; +static ssize_t show_conn_type(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_conn *conn = dev_get_drvdata(dev); + return sprintf(buf, "%s\n", conn->type == ACL_LINK ? "ACL" : "SCO"); +} + +static ssize_t show_conn_address(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_conn *conn = dev_get_drvdata(dev); + bdaddr_t bdaddr; + baswap(&bdaddr, &conn->dst); + return sprintf(buf, "%s\n", batostr(&bdaddr)); +} + +#define CONN_ATTR(_name,_mode,_show,_store) \ +struct device_attribute conn_attr_##_name = __ATTR(_name,_mode,_show,_store) + +static CONN_ATTR(type, S_IRUGO, show_conn_type, NULL); +static CONN_ATTR(address, S_IRUGO, show_conn_address, NULL); + +static struct device_attribute *conn_attrs[] = { + &conn_attr_type, + &conn_attr_address, + NULL +}; + struct class *bt_class = NULL; EXPORT_SYMBOL_GPL(bt_class); @@ -177,8 +233,61 @@ static struct platform_device *bt_platform; static void bt_release(struct device *dev) { - struct hci_dev *hdev = dev_get_drvdata(dev); - kfree(hdev); + void *data = dev_get_drvdata(dev); + kfree(data); +} + +static void add_conn(void *data) +{ + struct hci_conn *conn = data; + int i; + + if (device_register(&conn->dev) < 0) { + BT_ERR("Failed to register connection device"); + return; + } + + for (i = 0; conn_attrs[i]; i++) + if (device_create_file(&conn->dev, conn_attrs[i]) < 0) + BT_ERR("Failed to create connection attribute"); +} + +void hci_conn_add_sysfs(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + bdaddr_t *ba = &conn->dst; + + BT_DBG("conn %p", conn); + + conn->dev.parent = &hdev->dev; + conn->dev.release = bt_release; + + snprintf(conn->dev.bus_id, BUS_ID_SIZE, + "%s%2.2X%2.2X%2.2X%2.2X%2.2X%2.2X", + conn->type == ACL_LINK ? "acl" : "sco", + ba->b[5], ba->b[4], ba->b[3], + ba->b[2], ba->b[1], ba->b[0]); + + dev_set_drvdata(&conn->dev, conn); + + INIT_WORK(&conn->work, add_conn, (void *) conn); + + schedule_work(&conn->work); +} + +static void del_conn(void *data) +{ + struct hci_conn *conn = data; + device_del(&conn->dev); +} + +void hci_conn_del_sysfs(struct hci_conn *conn) +{ + BT_DBG("conn %p", conn); + + INIT_WORK(&conn->work, del_conn, (void *) conn); + + schedule_work(&conn->work); } int hci_register_sysfs(struct hci_dev *hdev) @@ -190,11 +299,7 @@ int hci_register_sysfs(struct hci_dev *hdev) BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); dev->class = bt_class; - - if (hdev->parent) - dev->parent = hdev->parent; - else - dev->parent = &bt_platform->dev; + dev->parent = hdev->parent; strlcpy(dev->bus_id, hdev->name, BUS_ID_SIZE); @@ -207,18 +312,17 @@ int hci_register_sysfs(struct hci_dev *hdev) return err; for (i = 0; bt_attrs[i]; i++) - device_create_file(dev, bt_attrs[i]); + if (device_create_file(dev, bt_attrs[i]) < 0) + BT_ERR("Failed to create device attribute"); return 0; } void hci_unregister_sysfs(struct hci_dev *hdev) { - struct device *dev = &hdev->dev; - BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - device_del(dev); + device_del(&hdev->dev); } int __init bt_sysfs_init(void) @@ -245,7 +349,7 @@ int __init bt_sysfs_init(void) return 0; } -void __exit bt_sysfs_cleanup(void) +void bt_sysfs_cleanup(void) { class_destroy(bt_class); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index c6e3a2c27c6e..66782010f82c 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -40,6 +40,7 @@ #include <linux/input.h> #include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include "hidp.h" @@ -506,14 +507,12 @@ static int hidp_session(void *arg) hidp_del_timer(session); - if (intr_sk->sk_state != BT_CONNECTED) - wait_event_timeout(*(ctrl_sk->sk_sleep), (ctrl_sk->sk_state == BT_CLOSED), HZ); - - fput(session->ctrl_sock->file); + fput(session->intr_sock->file); - wait_event_timeout(*(intr_sk->sk_sleep), (intr_sk->sk_state == BT_CLOSED), HZ); + wait_event_timeout(*(ctrl_sk->sk_sleep), + (ctrl_sk->sk_state == BT_CLOSED), msecs_to_jiffies(500)); - fput(session->intr_sock->file); + fput(session->ctrl_sock->file); __hidp_unlink_session(session); @@ -528,6 +527,24 @@ static int hidp_session(void *arg) return 0; } +static struct device *hidp_get_device(struct hidp_session *session) +{ + bdaddr_t *src = &bt_sk(session->ctrl_sock->sk)->src; + bdaddr_t *dst = &bt_sk(session->ctrl_sock->sk)->dst; + struct hci_dev *hdev; + struct hci_conn *conn; + + hdev = hci_get_route(dst, src); + if (!hdev) + return NULL; + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); + + hci_dev_put(hdev); + + return conn ? &conn->dev : NULL; +} + static inline void hidp_setup_input(struct hidp_session *session, struct hidp_connadd_req *req) { struct input_dev *input = session->input; @@ -566,6 +583,8 @@ static inline void hidp_setup_input(struct hidp_session *session, struct hidp_co input->relbit[0] |= BIT(REL_WHEEL); } + input->cdev.dev = hidp_get_device(session); + input->event = hidp_input_event; input_register_device(input); diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 099646e4e2ef..407fba43c1b9 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -35,6 +35,7 @@ #include <linux/ioctl.h> #include <linux/file.h> #include <linux/init.h> +#include <linux/compat.h> #include <net/sock.h> #include "hidp.h" @@ -143,11 +144,88 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long return -EINVAL; } +#ifdef CONFIG_COMPAT +struct compat_hidp_connadd_req { + int ctrl_sock; // Connected control socket + int intr_sock; // Connteted interrupt socket + __u16 parser; + __u16 rd_size; + compat_uptr_t rd_data; + __u8 country; + __u8 subclass; + __u16 vendor; + __u16 product; + __u16 version; + __u32 flags; + __u32 idle_to; + char name[128]; +}; + +static int hidp_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == HIDPGETCONNLIST) { + struct hidp_connlist_req cl; + uint32_t uci; + int err; + + if (get_user(cl.cnum, (uint32_t __user *) arg) || + get_user(uci, (u32 __user *) (arg + 4))) + return -EFAULT; + + cl.ci = compat_ptr(uci); + + if (cl.cnum <= 0) + return -EINVAL; + + err = hidp_get_connlist(&cl); + + if (!err && put_user(cl.cnum, (uint32_t __user *) arg)) + err = -EFAULT; + + return err; + } else if (cmd == HIDPCONNADD) { + struct compat_hidp_connadd_req ca; + struct hidp_connadd_req __user *uca; + + uca = compat_alloc_user_space(sizeof(*uca)); + + if (copy_from_user(&ca, (void *) arg, sizeof(ca))) + return -EFAULT; + + if (put_user(ca.ctrl_sock, &uca->ctrl_sock) || + put_user(ca.intr_sock, &uca->intr_sock) || + put_user(ca.parser, &uca->parser) || + put_user(ca.rd_size, &uca->parser) || + put_user(compat_ptr(ca.rd_data), &uca->rd_data) || + put_user(ca.country, &uca->country) || + put_user(ca.subclass, &uca->subclass) || + put_user(ca.vendor, &uca->vendor) || + put_user(ca.product, &uca->product) || + put_user(ca.version, &uca->version) || + put_user(ca.flags, &uca->flags) || + put_user(ca.idle_to, &uca->idle_to) || + copy_to_user(&uca->name[0], &ca.name[0], 128)) + return -EFAULT; + + arg = (unsigned long) uca; + + /* Fall through. We don't actually write back any _changes_ + to the structure anyway, so there's no need to copy back + into the original compat version */ + } + + return hidp_sock_ioctl(sock, cmd, arg); +} +#endif + static const struct proto_ops hidp_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = hidp_sock_release, .ioctl = hidp_sock_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = hidp_sock_compat_ioctl, +#endif .bind = sock_no_bind, .getname = sock_no_getname, .sendmsg = sock_no_sendmsg, @@ -178,7 +256,7 @@ static int hidp_sock_create(struct socket *sock, int protocol) if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &hidp_proto, 1); + sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, 1); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index d56f60b392ac..2b3dcb8f90fa 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -559,7 +559,7 @@ static int l2cap_sock_create(struct socket *sock, int protocol) sock->ops = &l2cap_sock_ops; - sk = l2cap_sock_alloc(sock, protocol, GFP_KERNEL); + sk = l2cap_sock_alloc(sock, protocol, GFP_ATOMIC); if (!sk) return -ENOMEM; @@ -2216,7 +2216,8 @@ static int __init l2cap_init(void) goto error; } - class_create_file(bt_class, &class_attr_l2cap); + if (class_create_file(bt_class, &class_attr_l2cap) < 0) + BT_ERR("Failed to create L2CAP info file"); BT_INFO("L2CAP ver %s", VERSION); BT_INFO("L2CAP socket layer initialized"); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 332dd8f436ea..ddc4e9d5963e 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -644,7 +644,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst addr.l2_family = AF_BLUETOOTH; addr.l2_psm = htobs(RFCOMM_PSM); *err = sock->ops->connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK); - if (*err == 0 || *err == -EAGAIN) + if (*err == 0 || *err == -EINPROGRESS) return s; rfcomm_session_del(s); @@ -2058,7 +2058,8 @@ static int __init rfcomm_init(void) kernel_thread(rfcomm_run, NULL, CLONE_KERNEL); - class_create_file(bt_class, &class_attr_rfcomm_dlc); + if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0) + BT_ERR("Failed to create RFCOMM info file"); rfcomm_init_sockets(); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 220fee04e7f2..544d65b7baa7 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -336,7 +336,8 @@ static int rfcomm_sock_create(struct socket *sock, int protocol) sock->ops = &rfcomm_sock_ops; - if (!(sk = rfcomm_sock_alloc(sock, protocol, GFP_KERNEL))) + sk = rfcomm_sock_alloc(sock, protocol, GFP_ATOMIC); + if (!sk) return -ENOMEM; rfcomm_sock_init(sk, NULL); @@ -944,7 +945,8 @@ int __init rfcomm_init_sockets(void) if (err < 0) goto error; - class_create_file(bt_class, &class_attr_rfcomm); + if (class_create_file(bt_class, &class_attr_rfcomm) < 0) + BT_ERR("Failed to create RFCOMM info file"); BT_INFO("RFCOMM socket layer initialized"); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index bd8d671a0ba6..b8e3a5f1c8a8 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -38,6 +38,7 @@ #include <linux/skbuff.h> #include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> #include <net/bluetooth/rfcomm.h> #ifndef CONFIG_BT_RFCOMM_DEBUG @@ -161,6 +162,22 @@ static inline struct rfcomm_dev *rfcomm_dev_get(int id) return dev; } +static struct device *rfcomm_get_device(struct rfcomm_dev *dev) +{ + struct hci_dev *hdev; + struct hci_conn *conn; + + hdev = hci_get_route(&dev->dst, &dev->src); + if (!hdev) + return NULL; + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); + + hci_dev_put(hdev); + + return conn ? &conn->dev : NULL; +} + static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) { struct rfcomm_dev *dev; @@ -244,7 +261,7 @@ out: return err; } - tty_register_device(rfcomm_tty_driver, dev->id, NULL); + tty_register_device(rfcomm_tty_driver, dev->id, rfcomm_get_device(dev)); return dev->id; } @@ -748,6 +765,9 @@ static void rfcomm_tty_set_termios(struct tty_struct *tty, struct termios *old) BT_DBG("tty %p termios %p", tty, old); + if (!dev) + return; + /* Handle turning off CRTSCTS */ if ((old->c_cflag & CRTSCTS) && !(new->c_cflag & CRTSCTS)) BT_DBG("Turning off CRTSCTS unsupported"); @@ -992,7 +1012,7 @@ static int rfcomm_tty_tiocmset(struct tty_struct *tty, struct file *filp, unsign /* ---- TTY structure ---- */ -static struct tty_operations rfcomm_ops = { +static const struct tty_operations rfcomm_ops = { .open = rfcomm_tty_open, .close = rfcomm_tty_close, .write = rfcomm_tty_write, diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 7714a2ec3854..5d13d4f31753 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -452,7 +452,8 @@ static int sco_sock_create(struct socket *sock, int protocol) sock->ops = &sco_sock_ops; - if (!(sk = sco_sock_alloc(sock, protocol, GFP_KERNEL))) + sk = sco_sock_alloc(sock, protocol, GFP_ATOMIC); + if (!sk) return -ENOMEM; sco_sock_init(sk, NULL); @@ -967,7 +968,8 @@ static int __init sco_init(void) goto error; } - class_create_file(bt_class, &class_attr_sco); + if (class_create_file(bt_class, &class_attr_sco) < 0) + BT_ERR("Failed to create SCO info file"); BT_INFO("SCO (Voice Link) ver %s", VERSION); BT_INFO("SCO socket layer initialized"); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 3a73b8c94271..d9f04864d15d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -128,7 +128,10 @@ void br_fdb_cleanup(unsigned long _data) mod_timer(&br->gc_timer, jiffies + HZ/10); } -void br_fdb_delete_by_port(struct net_bridge *br, struct net_bridge_port *p) + +void br_fdb_delete_by_port(struct net_bridge *br, + const struct net_bridge_port *p, + int do_all) { int i; @@ -142,6 +145,8 @@ void br_fdb_delete_by_port(struct net_bridge *br, struct net_bridge_port *p) if (f->dst != p) continue; + if (f->is_static && !do_all) + continue; /* * if multiple ports all have the same device address * then when one port is deleted, assign diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index b1211d5342f6..f753c40c11d2 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -163,7 +163,7 @@ static void del_nbp(struct net_bridge_port *p) br_stp_disable_port(p); spin_unlock_bh(&br->lock); - br_fdb_delete_by_port(br, p); + br_fdb_delete_by_port(br, p, 1); list_del_rcu(&p->list); @@ -448,7 +448,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return 0; err2: - br_fdb_delete_by_port(br, p); + br_fdb_delete_by_port(br, p, 1); err1: kobject_del(&p->kobj); err0: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c491fb2f280e..74258d86f256 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -143,7 +143,7 @@ extern void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr); extern void br_fdb_cleanup(unsigned long arg); extern void br_fdb_delete_by_port(struct net_bridge *br, - struct net_bridge_port *p); + const struct net_bridge_port *p, int do_all); extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, const unsigned char *addr); extern struct net_bridge_fdb_entry *br_fdb_get(struct net_bridge *br, diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 14cd025079af..d294224592db 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -113,6 +113,8 @@ void br_stp_disable_port(struct net_bridge_port *p) del_timer(&p->forward_delay_timer); del_timer(&p->hold_timer); + br_fdb_delete_by_port(br, p, 0); + br_configuration_update(br); br_port_state_selection(br); diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c index d19fc4b328dc..0aa7b9910a86 100644 --- a/net/bridge/netfilter/ebt_arpreply.c +++ b/net/bridge/netfilter/ebt_arpreply.c @@ -20,7 +20,7 @@ static int ebt_target_reply(struct sk_buff **pskb, unsigned int hooknr, const void *data, unsigned int datalen) { struct ebt_arpreply_info *info = (struct ebt_arpreply_info *)data; - u32 _sip, *siptr, _dip, *diptr; + __be32 _sip, *siptr, _dip, *diptr; struct arphdr _ah, *ap; unsigned char _sha[ETH_ALEN], *shp; struct sk_buff *skb = *pskb; diff --git a/net/bridge/netfilter/ebt_mark.c b/net/bridge/netfilter/ebt_mark.c index 770c0df972a3..b54306a934e5 100644 --- a/net/bridge/netfilter/ebt_mark.c +++ b/net/bridge/netfilter/ebt_mark.c @@ -22,24 +22,37 @@ static int ebt_target_mark(struct sk_buff **pskb, unsigned int hooknr, const void *data, unsigned int datalen) { struct ebt_mark_t_info *info = (struct ebt_mark_t_info *)data; + int action = info->target & -16; - if ((*pskb)->nfmark != info->mark) + if (action == MARK_SET_VALUE) (*pskb)->nfmark = info->mark; + else if (action == MARK_OR_VALUE) + (*pskb)->nfmark |= info->mark; + else if (action == MARK_AND_VALUE) + (*pskb)->nfmark &= info->mark; + else + (*pskb)->nfmark ^= info->mark; - return info->target; + return info->target | -16; } static int ebt_target_mark_check(const char *tablename, unsigned int hookmask, const struct ebt_entry *e, void *data, unsigned int datalen) { struct ebt_mark_t_info *info = (struct ebt_mark_t_info *)data; + int tmp; if (datalen != EBT_ALIGN(sizeof(struct ebt_mark_t_info))) return -EINVAL; - if (BASE_CHAIN && info->target == EBT_RETURN) + tmp = info->target | -16; + if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; CLEAR_BASE_CHAIN_BIT; - if (INVALID_TARGET) + if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) + return -EINVAL; + tmp = info->target & -16; + if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE && + tmp != MARK_AND_VALUE && tmp != MARK_XOR_VALUE) return -EINVAL; return 0; } diff --git a/net/compat.c b/net/compat.c index d5d69fa15d07..52d32f1bc728 100644 --- a/net/compat.c +++ b/net/compat.c @@ -285,8 +285,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) if (i > 0) { int cmlen = CMSG_COMPAT_LEN(i * sizeof(int)); - if (!err) - err = put_user(SOL_SOCKET, &cm->cmsg_level); + err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) diff --git a/net/core/dev.c b/net/core/dev.c index 14de297d024d..81c426adcd1e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1480,14 +1480,16 @@ gso: if (q->enqueue) { /* Grab device queue */ spin_lock(&dev->queue_lock); + q = dev->qdisc; + if (q->enqueue) { + rc = q->enqueue(skb, q); + qdisc_run(dev); + spin_unlock(&dev->queue_lock); - rc = q->enqueue(skb, q); - - qdisc_run(dev); - + rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; + goto out; + } spin_unlock(&dev->queue_lock); - rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; - goto out; } /* The device has no queue. Common case for software devices: @@ -3500,8 +3502,6 @@ static int __init net_dev_init(void) BUG_ON(!dev_boot_phase); - net_random_init(); - if (dev_proc_init()) goto out; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index e0ca04f38cef..87dc556fd9d6 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -806,13 +806,6 @@ int dev_ethtool(struct ifreq *ifr) int rc; unsigned long old_features; - /* - * XXX: This can be pushed down into the ethtool_* handlers that - * need it. Keep existing behaviour for the moment. - */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (!dev || !netif_device_present(dev)) return -ENODEV; @@ -822,6 +815,27 @@ int dev_ethtool(struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof (ethcmd))) return -EFAULT; + /* Allow some commands to be done by anyone */ + switch(ethcmd) { + case ETHTOOL_GDRVINFO: + case ETHTOOL_GMSGLVL: + case ETHTOOL_GCOALESCE: + case ETHTOOL_GRINGPARAM: + case ETHTOOL_GPAUSEPARAM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GTXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GSTRINGS: + case ETHTOOL_GTSO: + case ETHTOOL_GPERMADDR: + case ETHTOOL_GUFO: + case ETHTOOL_GGSO: + break; + default: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + } + if(dev->ethtool_ops->begin) if ((rc = dev->ethtool_ops->begin(dev)) < 0) return rc; @@ -947,6 +961,10 @@ int dev_ethtool(struct ifreq *ifr) return rc; ioctl: + /* Keep existing behaviour for the moment. */ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (dev->do_ioctl) return dev->do_ioctl(dev, ifr, SIOCETHTOOL); return -EOPNOTSUPP; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a99d87d82b7f..6b0e63cacd93 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -8,7 +8,6 @@ * Authors: Thomas Graf <tgraf@suug.ch> */ -#include <linux/config.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/list.h> diff --git a/net/core/flow.c b/net/core/flow.c index f23e7e386543..b16d31ae5e54 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -85,6 +85,14 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&flow_hash_rnd_timer); } +static void flow_entry_kill(int cpu, struct flow_cache_entry *fle) +{ + if (fle->object) + atomic_dec(fle->object_ref); + kmem_cache_free(flow_cachep, fle); + flow_count(cpu)--; +} + static void __flow_cache_shrink(int cpu, int shrink_to) { struct flow_cache_entry *fle, **flp; @@ -100,10 +108,7 @@ static void __flow_cache_shrink(int cpu, int shrink_to) } while ((fle = *flp) != NULL) { *flp = fle->next; - if (fle->object) - atomic_dec(fle->object_ref); - kmem_cache_free(flow_cachep, fle); - flow_count(cpu)--; + flow_entry_kill(cpu, fle); } } } @@ -220,24 +225,33 @@ void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, nocache: { + int err; void *obj; atomic_t *obj_ref; - resolver(key, family, dir, &obj, &obj_ref); + err = resolver(key, family, dir, &obj, &obj_ref); if (fle) { - fle->genid = atomic_read(&flow_cache_genid); - - if (fle->object) - atomic_dec(fle->object_ref); - - fle->object = obj; - fle->object_ref = obj_ref; - if (obj) - atomic_inc(fle->object_ref); + if (err) { + /* Force security policy check on next lookup */ + *head = fle->next; + flow_entry_kill(cpu, fle); + } else { + fle->genid = atomic_read(&flow_cache_genid); + + if (fle->object) + atomic_dec(fle->object_ref); + + fle->object = obj; + fle->object_ref = obj_ref; + if (obj) + atomic_inc(fle->object_ref); + } } local_bh_enable(); + if (err) + obj = ERR_PTR(err); return obj; } } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b6c69e1463e8..b4b478353b27 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -344,12 +344,12 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, dev) & tbl->hash_mask; + u32 hash_val = tbl->hash(pkey, dev); NEIGH_CACHE_STAT_INC(tbl, lookups); read_lock_bh(&tbl->lock); - for (n = tbl->hash_buckets[hash_val]; n; n = n->next) { + for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { neigh_hold(n); NEIGH_CACHE_STAT_INC(tbl, hits); @@ -364,12 +364,12 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey) { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, NULL) & tbl->hash_mask; + u32 hash_val = tbl->hash(pkey, NULL); NEIGH_CACHE_STAT_INC(tbl, lookups); read_lock_bh(&tbl->lock); - for (n = tbl->hash_buckets[hash_val]; n; n = n->next) { + for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { if (!memcmp(n->primary_key, pkey, key_len)) { neigh_hold(n); NEIGH_CACHE_STAT_INC(tbl, hits); @@ -1079,7 +1079,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, - u16 protocol) + __be16 protocol) { struct hh_cache *hh; struct net_device *dev = dst->dev; @@ -1998,12 +1998,12 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; + read_lock_bh(&tbl->lock); for (h = 0; h <= tbl->hash_mask; h++) { if (h < s_h) continue; if (h > s_h) s_idx = 0; - read_lock_bh(&tbl->lock); for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) { if (idx < s_idx) continue; @@ -2016,8 +2016,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, goto out; } } - read_unlock_bh(&tbl->lock); } + read_unlock_bh(&tbl->lock); rc = skb->len; out: cb->args[1] = h; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 13472762b18b..f47f319bb7dc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -344,8 +344,6 @@ static ssize_t wireless_show(struct class_device *cd, char *buf, if(dev->wireless_handlers && dev->wireless_handlers->get_wireless_stats) iw = dev->wireless_handlers->get_wireless_stats(dev); - else if (dev->get_wireless_stats) - iw = dev->get_wireless_stats(dev); if (iw != NULL) ret = (*format)(iw, buf); } @@ -465,8 +463,7 @@ int netdev_register_sysfs(struct net_device *net) *groups++ = &netstat_group; #ifdef WIRELESS_EXT - if (net->get_wireless_stats - || (net->wireless_handlers && net->wireless_handlers->get_wireless_stats)) + if (net->wireless_handlers && net->wireless_handlers->get_wireless_stats) *groups++ = &wireless_group; #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index ead5920c26d6..9308af060b44 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -335,13 +335,13 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) memcpy(skb->data, msg, len); skb->len += len; - udph = (struct udphdr *) skb_push(skb, sizeof(*udph)); + skb->h.uh = udph = (struct udphdr *) skb_push(skb, sizeof(*udph)); udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); udph->check = 0; - iph = (struct iphdr *)skb_push(skb, sizeof(*iph)); + skb->nh.iph = iph = (struct iphdr *)skb_push(skb, sizeof(*iph)); /* iph->version = 4; iph->ihl = 5; */ put_unaligned(0x45, (unsigned char *)iph); @@ -357,8 +357,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - - eth->h_proto = htons(ETH_P_IP); + skb->mac.raw = skb->data; + skb->protocol = eth->h_proto = htons(ETH_P_IP); memcpy(eth->h_source, np->local_mac, 6); memcpy(eth->h_dest, np->remote_mac, 6); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 72145d4a2600..dd023fd28304 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -109,6 +109,8 @@ * * MPLS support by Steven Whitehouse <steve@chygwyn.com> * + * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com> + * */ #include <linux/sys.h> #include <linux/types.h> @@ -137,6 +139,7 @@ #include <linux/inetdevice.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -157,7 +160,7 @@ #include <asm/div64.h> /* do_div */ #include <asm/timex.h> -#define VERSION "pktgen v2.67: Packet Generator for packet performance testing.\n" +#define VERSION "pktgen v2.68: Packet Generator for packet performance testing.\n" /* #define PG_DEBUG(a) a */ #define PG_DEBUG(a) @@ -178,6 +181,8 @@ #define F_TXSIZE_RND (1<<6) /* Transmit size is random */ #define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ #define F_MPLS_RND (1<<8) /* Random MPLS labels */ +#define F_VID_RND (1<<9) /* Random VLAN ID */ +#define F_SVID_RND (1<<10) /* Random SVLAN ID */ /* Thread control flag bits */ #define T_TERMINATE (1<<0) @@ -198,6 +203,9 @@ static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 +#define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4) +#define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4) + struct flow_state { __u32 cur_daddr; int count; @@ -284,10 +292,23 @@ struct pktgen_dev { __u16 udp_dst_min; /* inclusive, dest UDP port */ __u16 udp_dst_max; /* exclusive, dest UDP port */ + /* DSCP + ECN */ + __u8 tos; /* six most significant bits of (former) IPv4 TOS are for dscp codepoint */ + __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */ + /* MPLS */ unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; + /* VLAN/SVLAN (802.1Q/Q-in-Q) */ + __u8 vlan_p; + __u8 vlan_cfi; + __u16 vlan_id; /* 0xffff means no vlan tag */ + + __u8 svlan_p; + __u8 svlan_cfi; + __u16 svlan_id; /* 0xffff means no svlan tag */ + __u32 src_mac_count; /* How many MACs to iterate through */ __u32 dst_mac_count; /* How many MACs to iterate through */ @@ -644,6 +665,24 @@ static int pktgen_if_show(struct seq_file *seq, void *v) i == pkt_dev->nr_labels-1 ? "\n" : ", "); } + if (pkt_dev->vlan_id != 0xffff) { + seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->vlan_id, pkt_dev->vlan_p, pkt_dev->vlan_cfi); + } + + if (pkt_dev->svlan_id != 0xffff) { + seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->svlan_id, pkt_dev->svlan_p, pkt_dev->svlan_cfi); + } + + if (pkt_dev->tos) { + seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos); + } + + if (pkt_dev->traffic_class) { + seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); + } + seq_printf(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) @@ -673,6 +712,12 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_MACDST_RND) seq_printf(seq, "MACDST_RND "); + if (pkt_dev->flags & F_VID_RND) + seq_printf(seq, "VID_RND "); + + if (pkt_dev->flags & F_SVID_RND) + seq_printf(seq, "SVID_RND "); + seq_puts(seq, "\n"); sa = pkt_dev->started_at; @@ -715,12 +760,12 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } -static int hex32_arg(const char __user *user_buffer, __u32 *num) +static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 *num) { int i = 0; *num = 0; - for(; i < 8; i++) { + for(; i < maxlen; i++) { char c; *num <<= 4; if (get_user(c, &user_buffer[i])) @@ -815,7 +860,7 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; - len = hex32_arg(&buffer[i], &tmp); + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; pkt_dev->labels[n] = htonl(tmp); @@ -1140,11 +1185,27 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!MPLS_RND") == 0) pkt_dev->flags &= ~F_MPLS_RND; + else if (strcmp(f, "VID_RND") == 0) + pkt_dev->flags |= F_VID_RND; + + else if (strcmp(f, "!VID_RND") == 0) + pkt_dev->flags &= ~F_VID_RND; + + else if (strcmp(f, "SVID_RND") == 0) + pkt_dev->flags |= F_SVID_RND; + + else if (strcmp(f, "!SVID_RND") == 0) + pkt_dev->flags &= ~F_SVID_RND; + + else if (strcmp(f, "!IPV6") == 0) + pkt_dev->flags &= ~F_IPV6; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, - "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); + "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -1445,6 +1506,160 @@ static ssize_t pktgen_if_write(struct file *file, offset += sprintf(pg_result + offset, "%08x%s", ntohl(pkt_dev->labels[n]), n == pkt_dev->nr_labels-1 ? "" : ","); + + if (pkt_dev->nr_labels && pkt_dev->vlan_id != 0xffff) { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN auto turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) { + return len; + } + i += len; + if (value <= 4095) { + pkt_dev->vlan_id = value; /* turn on VLAN */ + + if (debug) + printk("pktgen: VLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + printk("pktgen: MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_p = value; + sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p); + } else { + sprintf(pg_result, "ERROR: vlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "vlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_cfi = value; + sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi); + } else { + sprintf(pg_result, "ERROR: vlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "svlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { + pkt_dev->svlan_id = value; /* turn on SVLAN */ + + if (debug) + printk("pktgen: SVLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + printk("pktgen: MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "svlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_p = value; + sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p); + } else { + sprintf(pg_result, "ERROR: svlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "svlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_cfi = value; + sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi); + } else { + sprintf(pg_result, "ERROR: svlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "tos")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) { + return len; + } + i += len; + if (len == 2) { + pkt_dev->tos = tmp_value; + sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos); + } else { + sprintf(pg_result, "ERROR: tos must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "traffic_class")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) { + return len; + } + i += len; + if (len == 2) { + pkt_dev->traffic_class = tmp_value; + sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class); + } else { + sprintf(pg_result, "ERROR: traffic_class must be 00-ff"); + } return count; } @@ -1949,6 +2164,14 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) htonl(0x000fffff)); } + if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_id = pktgen_random() % 4096; + } + + if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_id = pktgen_random() % 4096; + } + if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) pkt_dev->cur_udp_src = @@ -2092,10 +2315,18 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_hdr *pgh = NULL; __be16 protocol = __constant_htons(ETH_P_IP); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + if (pkt_dev->nr_labels) protocol = __constant_htons(ETH_P_MPLS_UC); + if (pkt_dev->vlan_id != 0xffff) + protocol = __constant_htons(ETH_P_8021Q); + /* Update any of the values, used when we're incrementing various * fields. */ @@ -2103,7 +2334,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, datalen = (odev->hard_header_len + 16) & ~0xf; skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + pkt_dev->nr_labels*sizeof(u32) + + VLAN_TAG_SIZE(pkt_dev) + SVLAN_TAG_SIZE(pkt_dev), + GFP_ATOMIC); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2116,6 +2349,24 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if(pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = htons(pkt_dev->svlan_id); + *svlan_tci |= pkt_dev->svlan_p << 5; + *svlan_tci |= pkt_dev->svlan_cfi << 4; + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = htons(pkt_dev->vlan_id); + *vlan_tci |= pkt_dev->vlan_p << 5; + *vlan_tci |= pkt_dev->vlan_cfi << 4; + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = __constant_htons(ETH_P_IP); + } + iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); @@ -2124,7 +2375,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - - pkt_dev->nr_labels*sizeof(u32); + pkt_dev->nr_labels*sizeof(u32) - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); if (datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); @@ -2136,7 +2387,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->ihl = 5; iph->version = 4; iph->ttl = 32; - iph->tos = 0; + iph->tos = pkt_dev->tos; iph->protocol = IPPROTO_UDP; /* UDP */ iph->saddr = pkt_dev->cur_saddr; iph->daddr = pkt_dev->cur_daddr; @@ -2146,7 +2397,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->check = 0; iph->check = ip_fast_csum((void *)iph, iph->ihl); skb->protocol = protocol; - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); + skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); skb->dev = odev; skb->pkt_type = PACKET_HOST; skb->nh.iph = iph; @@ -2218,7 +2470,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, pgh->tv_sec = htonl(timestamp.tv_sec); pgh->tv_usec = htonl(timestamp.tv_usec); } - pkt_dev->seq_num++; return skb; } @@ -2402,17 +2653,26 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct pktgen_hdr *pgh = NULL; __be16 protocol = __constant_htons(ETH_P_IPV6); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ if (pkt_dev->nr_labels) protocol = __constant_htons(ETH_P_MPLS_UC); + if (pkt_dev->vlan_id != 0xffff) + protocol = __constant_htons(ETH_P_8021Q); + /* Update any of the values, used when we're incrementing various * fields. */ mod_cur_headers(pkt_dev); skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + pkt_dev->nr_labels*sizeof(u32) + + VLAN_TAG_SIZE(pkt_dev) + SVLAN_TAG_SIZE(pkt_dev), + GFP_ATOMIC); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2425,16 +2685,34 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if(pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = htons(pkt_dev->svlan_id); + *svlan_tci |= pkt_dev->svlan_p << 5; + *svlan_tci |= pkt_dev->svlan_cfi << 4; + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = htons(pkt_dev->vlan_id); + *vlan_tci |= pkt_dev->vlan_p << 5; + *vlan_tci |= pkt_dev->vlan_cfi << 4; + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = __constant_htons(ETH_P_IPV6); + } + iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr)); udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); memcpy(eth, pkt_dev->hh, 12); - *(u16 *) & eth[12] = __constant_htons(ETH_P_IPV6); + *(u16 *) & eth[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - sizeof(struct ipv6hdr) - sizeof(struct udphdr) - - pkt_dev->nr_labels*sizeof(u32); + pkt_dev->nr_labels*sizeof(u32) - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); if (datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); @@ -2450,6 +2728,11 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, *(u32 *) iph = __constant_htonl(0x60000000); /* Version + flow */ + if (pkt_dev->traffic_class) { + /* Version + traffic class + flow (0) */ + *(u32 *)iph |= htonl(0x60000000 | (pkt_dev->traffic_class << 20)); + } + iph->hop_limit = 32; iph->payload_len = htons(sizeof(struct udphdr) + datalen); @@ -2458,7 +2741,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); + skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; @@ -2531,7 +2815,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, pgh->tv_sec = htonl(timestamp.tv_sec); pgh->tv_usec = htonl(timestamp.tv_usec); } - pkt_dev->seq_num++; + /* pkt_dev->seq_num++; FF: you really mean this? */ return skb; } @@ -3177,6 +3461,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; + pkt_dev->vlan_p = 0; + pkt_dev->vlan_cfi = 0; + pkt_dev->vlan_id = 0xffff; + pkt_dev->svlan_p = 0; + pkt_dev->svlan_cfi = 0; + pkt_dev->svlan_id = 0xffff; + strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); if (!pktgen_setup_dev(pkt_dev)) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d8e25e08cb7e..02f3c7947898 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -562,7 +562,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) - goto errout; + return err; ifm = nlmsg_data(nlh); if (ifm->ifi_index >= 0) { @@ -602,7 +602,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) goto errout; } - err = rtnl_unicast(skb, NETLINK_CB(skb).pid); + err = rtnl_unicast(nskb, NETLINK_CB(skb).pid); errout: kfree(iw_buf); dev_put(dev); diff --git a/net/core/scm.c b/net/core/scm.c index 649d01ef35b6..271cf060ef8c 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -245,8 +245,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) if (i > 0) { int cmlen = CMSG_LEN(i*sizeof(int)); - if (!err) - err = put_user(SOL_SOCKET, &cm->cmsg_level); + err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c448c7f6fde2..3c23760c5827 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -156,7 +156,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, /* Get the DATA. Size must match skb_add_mtu(). */ size = SKB_DATA_ALIGN(size); - data = ____kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + data = kmalloc_track_caller(size + sizeof(struct skb_shared_info), + gfp_mask); if (!data) goto nodata; diff --git a/net/core/sock.c b/net/core/sock.c index b77e155cbe6c..d472db4776c3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -823,7 +823,7 @@ static void inline sock_lock_init(struct sock *sk) af_family_slock_key_strings[sk->sk_family]); lockdep_init_map(&sk->sk_lock.dep_map, af_family_key_strings[sk->sk_family], - af_family_keys + sk->sk_family); + af_family_keys + sk->sk_family, 0); } /** diff --git a/net/core/utils.c b/net/core/utils.c index 2682490777de..d93fe64f6693 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -3,7 +3,7 @@ * * Authors: * net_random Alan Cox - * net_ratelimit Andy Kleen + * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> @@ -30,119 +30,6 @@ #include <asm/system.h> #include <asm/uaccess.h> -/* - This is a maximally equidistributed combined Tausworthe generator - based on code from GNU Scientific Library 1.5 (30 Jun 2004) - - x_n = (s1_n ^ s2_n ^ s3_n) - - s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19)) - s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25)) - s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11)) - - The period of this generator is about 2^88. - - From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe - Generators", Mathematics of Computation, 65, 213 (1996), 203--213. - - This is available on the net from L'Ecuyer's home page, - - http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps - ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps - - There is an erratum in the paper "Tables of Maximally - Equidistributed Combined LFSR Generators", Mathematics of - Computation, 68, 225 (1999), 261--269: - http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps - - ... the k_j most significant bits of z_j must be non- - zero, for each j. (Note: this restriction also applies to the - computer code given in [4], but was mistakenly not mentioned in - that paper.) - - This affects the seeding procedure by imposing the requirement - s1 > 1, s2 > 7, s3 > 15. - -*/ -struct nrnd_state { - u32 s1, s2, s3; -}; - -static DEFINE_PER_CPU(struct nrnd_state, net_rand_state); - -static u32 __net_random(struct nrnd_state *state) -{ -#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b) - - state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12); - state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4); - state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17); - - return (state->s1 ^ state->s2 ^ state->s3); -} - -static void __net_srandom(struct nrnd_state *state, unsigned long s) -{ - if (s == 0) - s = 1; /* default seed is 1 */ - -#define LCG(n) (69069 * n) - state->s1 = LCG(s); - state->s2 = LCG(state->s1); - state->s3 = LCG(state->s2); - - /* "warm it up" */ - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); -} - - -unsigned long net_random(void) -{ - unsigned long r; - struct nrnd_state *state = &get_cpu_var(net_rand_state); - r = __net_random(state); - put_cpu_var(state); - return r; -} - - -void net_srandom(unsigned long entropy) -{ - struct nrnd_state *state = &get_cpu_var(net_rand_state); - __net_srandom(state, state->s1^entropy); - put_cpu_var(state); -} - -void __init net_random_init(void) -{ - int i; - - for_each_possible_cpu(i) { - struct nrnd_state *state = &per_cpu(net_rand_state,i); - __net_srandom(state, i+jiffies); - } -} - -static int net_random_reseed(void) -{ - int i; - unsigned long seed; - - for_each_possible_cpu(i) { - struct nrnd_state *state = &per_cpu(net_rand_state,i); - - get_random_bytes(&seed, sizeof(seed)); - __net_srandom(state, seed); - } - return 0; -} -late_initcall(net_random_reseed); - int net_msg_cost = 5*HZ; int net_msg_burst = 10; @@ -153,10 +40,7 @@ int net_ratelimit(void) { return __printk_ratelimit(net_msg_cost, net_msg_burst); } - -EXPORT_SYMBOL(net_random); EXPORT_SYMBOL(net_ratelimit); -EXPORT_SYMBOL(net_srandom); /* * Convert an ASCII string to binary IP. diff --git a/net/core/wireless.c b/net/core/wireless.c index 3168fca312f7..ffff0da46c6e 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -68,6 +68,14 @@ * * v8 - 17.02.06 - Jean II * o RtNetlink requests support (SET/GET) + * + * v8b - 03.08.06 - Herbert Xu + * o Fix Wireless Event locking issues. + * + * v9 - 14.3.06 - Jean II + * o Change length in ESSID and NICK to strlen() instead of strlen()+1 + * o Make standard_ioctl_num and standard_event_num unsigned + * o Remove (struct net_device *)->get_wireless_stats() */ /***************************** INCLUDES *****************************/ @@ -234,24 +242,24 @@ static const struct iw_ioctl_description standard_ioctl[] = { [SIOCSIWESSID - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_EVENT, }, [SIOCGIWESSID - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_DUMP, }, [SIOCSIWNICKN - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, }, [SIOCGIWNICKN - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, }, [SIOCSIWRATE - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_PARAM, @@ -338,8 +346,8 @@ static const struct iw_ioctl_description standard_ioctl[] = { .max_tokens = sizeof(struct iw_pmksa), }, }; -static const int standard_ioctl_num = (sizeof(standard_ioctl) / - sizeof(struct iw_ioctl_description)); +static const unsigned standard_ioctl_num = (sizeof(standard_ioctl) / + sizeof(struct iw_ioctl_description)); /* * Meta-data about all the additional standard Wireless Extension events @@ -389,8 +397,8 @@ static const struct iw_ioctl_description standard_event[] = { .max_tokens = sizeof(struct iw_pmkid_cand), }, }; -static const int standard_event_num = (sizeof(standard_event) / - sizeof(struct iw_ioctl_description)); +static const unsigned standard_event_num = (sizeof(standard_event) / + sizeof(struct iw_ioctl_description)); /* Size (in bytes) of the various private data types */ static const char iw_priv_type_size[] = { @@ -465,17 +473,6 @@ static inline struct iw_statistics *get_wireless_stats(struct net_device *dev) (dev->wireless_handlers->get_wireless_stats != NULL)) return dev->wireless_handlers->get_wireless_stats(dev); - /* Old location, field to be removed in next WE */ - if(dev->get_wireless_stats) { - static int printed_message; - - if (!printed_message++) - printk(KERN_DEBUG "%s (WE) : Driver using old /proc/net/wireless support, please fix driver !\n", - dev->name); - - return dev->get_wireless_stats(dev); - } - /* Not found */ return (struct iw_statistics *) NULL; } @@ -1843,8 +1840,33 @@ int wireless_rtnetlink_set(struct net_device * dev, */ #ifdef WE_EVENT_RTNETLINK +/* ---------------------------------------------------------------- */ +/* + * Locking... + * ---------- + * + * Thanks to Herbert Xu <herbert@gondor.apana.org.au> for fixing + * the locking issue in here and implementing this code ! + * + * The issue : wireless_send_event() is often called in interrupt context, + * while the Netlink layer can never be called in interrupt context. + * The fully formed RtNetlink events are queued, and then a tasklet is run + * to feed those to Netlink. + * The skb_queue is interrupt safe, and its lock is not held while calling + * Netlink, so there is no possibility of dealock. + * Jean II + */ + static struct sk_buff_head wireless_nlevent_queue; +static int __init wireless_nlevent_init(void) +{ + skb_queue_head_init(&wireless_nlevent_queue); + return 0; +} + +subsys_initcall(wireless_nlevent_init); + static void wireless_nlevent_process(unsigned long data) { struct sk_buff *skb; @@ -1921,13 +1943,6 @@ static inline void rtmsg_iwinfo(struct net_device * dev, tasklet_schedule(&wireless_nlevent_tasklet); } -static int __init wireless_nlevent_init(void) -{ - skb_queue_head_init(&wireless_nlevent_queue); - return 0; -} - -subsys_initcall(wireless_nlevent_init); #endif /* WE_EVENT_RTNETLINK */ /* ---------------------------------------------------------------- */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 66be29b6f508..7e746c4c1688 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -50,7 +50,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct dccp_sock *dp = dccp_sk(sk); const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct rtable *rt; - u32 daddr, nexthop; + __be32 daddr, nexthop; int tmp; int err; @@ -311,7 +311,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } if (sk->sk_state == DCCP_TIME_WAIT) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); return; } @@ -614,7 +614,7 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) bh_lock_sock(nsk); return nsk; } - inet_twsk_put((struct inet_timewait_sock *)nsk); + inet_twsk_put(inet_twsk(nsk)); return NULL; } @@ -980,7 +980,7 @@ discard_and_relse: goto discard_it; do_time_wait: - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 7a47399cf31f..7171a78671aa 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -285,7 +285,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (sk->sk_state == DCCP_TIME_WAIT) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); return; } @@ -663,7 +663,7 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) bh_lock_sock(nsk); return nsk; } - inet_twsk_put((struct inet_timewait_sock *)nsk); + inet_twsk_put(inet_twsk(nsk)); return NULL; } @@ -1109,7 +1109,7 @@ discard_and_relse: goto discard_it; do_time_wait: - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 70e027375682..3456cd331835 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1178,8 +1178,10 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len if (peer) { if ((sock->state != SS_CONNECTED && sock->state != SS_CONNECTING) && - scp->accept_mode == ACC_IMMED) + scp->accept_mode == ACC_IMMED) { + release_sock(sk); return -ENOTCONN; + } memcpy(sa, &scp->peer, sizeof(struct sockaddr_dn)); } else { diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index dd0761e3d280..23489f7232d2 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -267,9 +267,14 @@ static void dn_dst_link_failure(struct sk_buff *skb) static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) { - return memcmp(&fl1->nl_u.dn_u, &fl2->nl_u.dn_u, sizeof(fl1->nl_u.dn_u)) == 0 && - fl1->oif == fl2->oif && - fl1->iif == fl2->iif; + return ((fl1->nl_u.dn_u.daddr ^ fl2->nl_u.dn_u.daddr) | + (fl1->nl_u.dn_u.saddr ^ fl2->nl_u.dn_u.saddr) | +#ifdef CONFIG_DECNET_ROUTE_FWMARK + (fl1->nl_u.dn_u.fwmark ^ fl2->nl_u.dn_u.fwmark) | +#endif + (fl1->nl_u.dn_u.scope ^ fl2->nl_u.dn_u.scope) | + (fl1->oif ^ fl2->oif) | + (fl1->iif ^ fl2->iif)) == 0; } static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp) @@ -1270,7 +1275,6 @@ static int dn_route_input_slow(struct sk_buff *skb) goto e_inval; res.type = RTN_LOCAL; - flags |= RTCF_DIRECTSRC; } else { __le16 src_map = fl.fld_src; free_res = 1; @@ -1341,7 +1345,7 @@ static int dn_route_input_slow(struct sk_buff *skb) goto make_route; /* Packet was intra-ethernet, so we know its on-link */ - if (cb->rt_flags | DN_RT_F_IE) { + if (cb->rt_flags & DN_RT_F_IE) { gateway = cb->src; flags |= RTCF_DIRECTSRC; goto make_route; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 43863933f27f..4bd78c8cfb26 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -223,7 +223,7 @@ static int eth_header_parse(struct sk_buff *skb, unsigned char *haddr) */ int eth_header_cache(struct neighbour *neigh, struct hh_cache *hh) { - unsigned short type = hh->hh_type; + __be16 type = hh->hh_type; struct ethhdr *eth; struct net_device *dev = neigh->dev; diff --git a/net/ieee80211/softmac/ieee80211softmac_wx.c b/net/ieee80211/softmac/ieee80211softmac_wx.c index 75320b6842ab..2aa779d18f38 100644 --- a/net/ieee80211/softmac/ieee80211softmac_wx.c +++ b/net/ieee80211/softmac/ieee80211softmac_wx.c @@ -80,10 +80,10 @@ ieee80211softmac_wx_set_essid(struct net_device *net_dev, * If it's our network, ignore the change, we're already doing it! */ if((sm->associnfo.associating || sm->associated) && - (data->essid.flags && data->essid.length && extra)) { + (data->essid.flags && data->essid.length)) { /* Get the associating network */ n = ieee80211softmac_get_network_by_bssid(sm, sm->associnfo.bssid); - if(n && n->essid.len == (data->essid.length - 1) && + if(n && n->essid.len == data->essid.length && !memcmp(n->essid.data, extra, n->essid.len)) { dprintk(KERN_INFO PFX "Already associating or associated to "MAC_FMT"\n", MAC_ARG(sm->associnfo.bssid)); @@ -109,8 +109,8 @@ ieee80211softmac_wx_set_essid(struct net_device *net_dev, sm->associnfo.static_essid = 0; sm->associnfo.assoc_wait = 0; - if (data->essid.flags && data->essid.length && extra /*required?*/) { - length = min(data->essid.length - 1, IW_ESSID_MAX_SIZE); + if (data->essid.flags && data->essid.length) { + length = min((int)data->essid.length, IW_ESSID_MAX_SIZE); if (length) { memcpy(sm->associnfo.req_essid.data, extra, length); sm->associnfo.static_essid = 1; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 30af4a4dfcc8..5572071af735 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -64,7 +64,7 @@ config ASK_IP_FIB_HASH config IP_FIB_TRIE bool "FIB_TRIE" ---help--- - Use new experimental LC-trie as FIB lookup algoritm. + Use new experimental LC-trie as FIB lookup algorithm. This improves lookup performance if you have a large number of routes. @@ -434,6 +434,15 @@ config INET_XFRM_MODE_TUNNEL If unsure, say Y. +config INET_XFRM_MODE_BEET + tristate "IP: IPsec BEET mode" + default y + select XFRM + ---help--- + Support for IPsec BEET mode. + + If unsure, say Y. + config INET_DIAG tristate "INET: socket monitoring interface" default y @@ -526,7 +535,7 @@ config TCP_CONG_HYBLA ---help--- TCP-Hybla is a sender-side only change that eliminates penalization of long-RTT, large-bandwidth connections, like when satellite legs are - involved, expecially when sharing a common bottleneck with normal + involved, especially when sharing a common bottleneck with normal terrestrial connections. config TCP_CONG_VEGAS @@ -556,7 +565,7 @@ config TCP_CONG_LP default n ---help--- TCP Low Priority (TCP-LP), a distributed algorithm whose goal is - to utiliza only the excess network bandwidth as compared to the + to utilize only the excess network bandwidth as compared to the ``fair share`` of bandwidth as targeted by TCP. See http://www-ece.rice.edu/networks/TCP-LP/ diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f66049e28aeb..15645c51520c 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_INET_AH) += ah4.o obj-$(CONFIG_INET_ESP) += esp4.o obj-$(CONFIG_INET_IPCOMP) += ipcomp.o obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o +obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o obj-$(CONFIG_INET_TUNNEL) += tunnel4.o obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fdd89e37b9aa..edcf0932ac6d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -996,7 +996,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) struct rtable *rt; __u32 old_saddr = inet->saddr; __u32 new_saddr; - __u32 daddr = inet->daddr; + __be32 daddr = inet->daddr; if (inet->opt && inet->opt->srr) daddr = inet->opt->faddr; @@ -1043,7 +1043,7 @@ int inet_sk_rebuild_header(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); - u32 daddr; + __be32 daddr; int err; /* Route is OK, nothing to do. */ @@ -1342,10 +1342,10 @@ static int __init inet_init(void) rc = 0; out: return rc; -out_unregister_tcp_proto: - proto_unregister(&tcp_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); +out_unregister_tcp_proto: + proto_unregister(&tcp_prot); goto out; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c8a3723bc001..cfb5d3de9c84 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1,4 +1,4 @@ -/* linux/net/inet/arp.c +/* linux/net/ipv4/arp.c * * Version: $Id: arp.c,v 1.99 2001/08/30 22:55:42 davem Exp $ * @@ -234,7 +234,7 @@ static u32 arp_hash(const void *pkey, const struct net_device *dev) static int arp_constructor(struct neighbour *neigh) { - u32 addr = *(u32*)neigh->primary_key; + __be32 addr = *(__be32*)neigh->primary_key; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; @@ -330,10 +330,10 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { - u32 saddr = 0; + __be32 saddr = 0; u8 *dst_ha = NULL; struct net_device *dev = neigh->dev; - u32 target = *(u32*)neigh->primary_key; + __be32 target = *(__be32*)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev = in_dev_get(dev); @@ -385,7 +385,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } static int arp_ignore(struct in_device *in_dev, struct net_device *dev, - u32 sip, u32 tip) + __be32 sip, __be32 tip) { int scope; @@ -420,7 +420,7 @@ static int arp_ignore(struct in_device *in_dev, struct net_device *dev, return !inet_confirm_addr(dev, sip, tip, scope); } -static int arp_filter(__u32 sip, __u32 tip, struct net_device *dev) +static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = sip, .saddr = tip } } }; @@ -449,7 +449,7 @@ static int arp_filter(__u32 sip, __u32 tip, struct net_device *dev) * is allowed to use this function, it is scheduled to be removed. --ANK */ -static int arp_set_predefined(int addr_hint, unsigned char * haddr, u32 paddr, struct net_device * dev) +static int arp_set_predefined(int addr_hint, unsigned char * haddr, __be32 paddr, struct net_device * dev) { switch (addr_hint) { case RTN_LOCAL: @@ -470,7 +470,7 @@ static int arp_set_predefined(int addr_hint, unsigned char * haddr, u32 paddr, s int arp_find(unsigned char *haddr, struct sk_buff *skb) { struct net_device *dev = skb->dev; - u32 paddr; + __be32 paddr; struct neighbour *n; if (!skb->dst) { @@ -511,7 +511,7 @@ int arp_bind_neighbour(struct dst_entry *dst) if (dev == NULL) return -EINVAL; if (n == NULL) { - u32 nexthop = ((struct rtable*)dst)->rt_gateway; + __be32 nexthop = ((struct rtable*)dst)->rt_gateway; if (dev->flags&(IFF_LOOPBACK|IFF_POINTOPOINT)) nexthop = 0; n = __neigh_lookup_errno( @@ -560,8 +560,8 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt) * Create an arp packet. If (dest_hw == NULL), we create a broadcast * message. */ -struct sk_buff *arp_create(int type, int ptype, u32 dest_ip, - struct net_device *dev, u32 src_ip, +struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, unsigned char *dest_hw, unsigned char *src_hw, unsigned char *target_hw) { @@ -675,8 +675,8 @@ void arp_xmit(struct sk_buff *skb) /* * Create and send an arp packet. */ -void arp_send(int type, int ptype, u32 dest_ip, - struct net_device *dev, u32 src_ip, +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, unsigned char *dest_hw, unsigned char *src_hw, unsigned char *target_hw) { @@ -710,7 +710,7 @@ static int arp_process(struct sk_buff *skb) unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha, *tha; - u32 sip, tip; + __be32 sip, tip; u16 dev_type = dev->type; int addr_type; struct neighbour *n; @@ -969,13 +969,13 @@ out_of_mem: static int arp_req_set(struct arpreq *r, struct net_device * dev) { - u32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; + __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; int err; if (r->arp_flags&ATF_PUBL) { - u32 mask = ((struct sockaddr_in *) &r->arp_netmask)->sin_addr.s_addr; - if (mask && mask != 0xFFFFFFFF) + __be32 mask = ((struct sockaddr_in *) &r->arp_netmask)->sin_addr.s_addr; + if (mask && mask != htonl(0xFFFFFFFF)) return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr(r->arp_ha.sa_family, r->arp_ha.sa_data); @@ -1063,7 +1063,7 @@ static unsigned arp_state_to_flags(struct neighbour *neigh) static int arp_req_get(struct arpreq *r, struct net_device *dev) { - u32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; + __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; int err = -ENXIO; @@ -1084,13 +1084,13 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) static int arp_req_delete(struct arpreq *r, struct net_device * dev) { int err; - u32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; if (r->arp_flags & ATF_PUBL) { - u32 mask = + __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; - if (mask == 0xFFFFFFFF) + if (mask == htonl(0xFFFFFFFF)) return pneigh_delete(&arp_tbl, &ip, dev); if (mask == 0) { if (dev == NULL) { diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e6ce0b3ba62a..e2077a3aa8c0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -43,6 +43,7 @@ #include <net/tcp.h> #include <net/netlabel.h> #include <net/cipso_ipv4.h> +#include <asm/atomic.h> #include <asm/bug.h> struct cipso_v4_domhsh_entry { @@ -79,7 +80,7 @@ struct cipso_v4_map_cache_entry { unsigned char *key; size_t key_len; - struct netlbl_lsm_cache lsm_data; + struct netlbl_lsm_cache *lsm_data; u32 activity; struct list_head list; @@ -188,13 +189,14 @@ static void cipso_v4_doi_domhsh_free(struct rcu_head *entry) * @entry: the entry to free * * Description: - * This function frees the memory associated with a cache entry. + * This function frees the memory associated with a cache entry including the + * LSM cache data if there are no longer any users, i.e. reference count == 0. * */ static void cipso_v4_cache_entry_free(struct cipso_v4_map_cache_entry *entry) { - if (entry->lsm_data.free) - entry->lsm_data.free(entry->lsm_data.data); + if (entry->lsm_data) + netlbl_secattr_cache_free(entry->lsm_data); kfree(entry->key); kfree(entry); } @@ -315,8 +317,8 @@ static int cipso_v4_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - secattr->cache.free = entry->lsm_data.free; - secattr->cache.data = entry->lsm_data.data; + atomic_inc(&entry->lsm_data->refcount); + secattr->cache = entry->lsm_data; if (prev_entry == NULL) { spin_unlock_bh(&cipso_v4_cache[bkt].lock); return 0; @@ -383,8 +385,8 @@ int cipso_v4_cache_add(const struct sk_buff *skb, memcpy(entry->key, cipso_ptr, cipso_ptr_len); entry->key_len = cipso_ptr_len; entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len); - entry->lsm_data.free = secattr->cache.free; - entry->lsm_data.data = secattr->cache.data; + atomic_inc(&secattr->cache->refcount); + entry->lsm_data = secattr->cache; bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETBITS - 1); spin_lock_bh(&cipso_v4_cache[bkt].lock); @@ -474,6 +476,7 @@ doi_add_failure_rlock: /** * cipso_v4_doi_remove - Remove an existing DOI from the CIPSO protocol engine * @doi: the DOI value + * @audit_secid: the LSM secid to use in the audit message * @callback: the DOI cleanup/free callback * * Description: @@ -483,7 +486,9 @@ doi_add_failure_rlock: * success and negative values on failure. * */ -int cipso_v4_doi_remove(u32 doi, void (*callback) (struct rcu_head * head)) +int cipso_v4_doi_remove(u32 doi, + struct netlbl_audit *audit_info, + void (*callback) (struct rcu_head * head)) { struct cipso_v4_doi *doi_def; struct cipso_v4_domhsh_entry *dom_iter; @@ -502,7 +507,8 @@ int cipso_v4_doi_remove(u32 doi, void (*callback) (struct rcu_head * head)) spin_unlock(&cipso_v4_doi_list_lock); list_for_each_entry_rcu(dom_iter, &doi_def->dom_list, list) if (dom_iter->valid) - netlbl_domhsh_remove(dom_iter->domain); + netlbl_domhsh_remove(dom_iter->domain, + audit_info); cipso_v4_cache_invalidate(); rcu_read_unlock(); @@ -767,13 +773,15 @@ static int cipso_v4_map_cat_rbm_valid(const struct cipso_v4_doi *doi_def, { int cat = -1; u32 bitmap_len_bits = bitmap_len * 8; - u32 cipso_cat_size = doi_def->map.std->cat.cipso_size; - u32 *cipso_array = doi_def->map.std->cat.cipso; + u32 cipso_cat_size; + u32 *cipso_array; switch (doi_def->type) { case CIPSO_V4_MAP_PASS: return 0; case CIPSO_V4_MAP_STD: + cipso_cat_size = doi_def->map.std->cat.cipso_size; + cipso_array = doi_def->map.std->cat.cipso; for (;;) { cat = cipso_v4_bitmap_walk(bitmap, bitmap_len_bits, @@ -819,19 +827,21 @@ static int cipso_v4_map_cat_rbm_hton(const struct cipso_v4_doi *doi_def, u32 net_spot_max = 0; u32 host_clen_bits = host_cat_len * 8; u32 net_clen_bits = net_cat_len * 8; - u32 host_cat_size = doi_def->map.std->cat.local_size; - u32 *host_cat_array = doi_def->map.std->cat.local; + u32 host_cat_size; + u32 *host_cat_array; switch (doi_def->type) { case CIPSO_V4_MAP_PASS: - net_spot_max = host_cat_len - 1; - while (net_spot_max > 0 && host_cat[net_spot_max] == 0) + net_spot_max = host_cat_len; + while (net_spot_max > 0 && host_cat[net_spot_max - 1] == 0) net_spot_max--; if (net_spot_max > net_cat_len) return -EINVAL; memcpy(net_cat, host_cat, net_spot_max); return net_spot_max; case CIPSO_V4_MAP_STD: + host_cat_size = doi_def->map.std->cat.local_size; + host_cat_array = doi_def->map.std->cat.local; for (;;) { host_spot = cipso_v4_bitmap_walk(host_cat, host_clen_bits, @@ -887,8 +897,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, int net_spot = -1; u32 net_clen_bits = net_cat_len * 8; u32 host_clen_bits = host_cat_len * 8; - u32 net_cat_size = doi_def->map.std->cat.cipso_size; - u32 *net_cat_array = doi_def->map.std->cat.cipso; + u32 net_cat_size; + u32 *net_cat_array; switch (doi_def->type) { case CIPSO_V4_MAP_PASS: @@ -897,6 +907,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, memcpy(host_cat, net_cat, net_cat_len); return net_cat_len; case CIPSO_V4_MAP_STD: + net_cat_size = doi_def->map.std->cat.cipso_size; + net_cat_array = doi_def->map.std->cat.cipso; for (;;) { net_spot = cipso_v4_bitmap_walk(net_cat, net_clen_bits, diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index ec5da4fbd9f4..7b068a891953 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -25,7 +25,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *) uaddr; struct rtable *rt; - u32 saddr; + __be32 saddr; int oif; int err; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 8e8d1f17d77a..7602c79a389b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -224,7 +224,7 @@ static void inetdev_destroy(struct in_device *in_dev) call_rcu(&in_dev->rcu_head, in_dev_rcu_put); } -int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b) +int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { rcu_read_lock(); for_primary_ifa(in_dev) { @@ -429,8 +429,8 @@ struct in_device *inetdev_by_index(int ifindex) /* Called only from RTNL semaphored context. No locks. */ -struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix, - u32 mask) +struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, + __be32 mask) { ASSERT_RTNL(); @@ -467,7 +467,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && - ifa->ifa_local != nla_get_u32(tb[IFA_LOCAL])) + ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) @@ -475,7 +475,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || - !inet_ifa_match(nla_get_u32(tb[IFA_ADDRESS]), ifa))) + !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa))) continue; __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid); @@ -540,14 +540,14 @@ static struct in_ifaddr *rtm_to_ifaddr(struct nlmsghdr *nlh) ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = in_dev; - ifa->ifa_local = nla_get_u32(tb[IFA_LOCAL]); - ifa->ifa_address = nla_get_u32(tb[IFA_ADDRESS]); + ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]); + ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) - ifa->ifa_broadcast = nla_get_u32(tb[IFA_BROADCAST]); + ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); if (tb[IFA_ANYCAST]) - ifa->ifa_anycast = nla_get_u32(tb[IFA_ANYCAST]); + ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]); if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); @@ -805,7 +805,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { - u32 old_mask = ifa->ifa_mask; + __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); @@ -876,9 +876,9 @@ out: return done; } -u32 inet_select_addr(const struct net_device *dev, u32 dst, int scope) +__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { - u32 addr = 0; + __be32 addr = 0; struct in_device *in_dev; rcu_read_lock(); @@ -927,11 +927,11 @@ out: return addr; } -static u32 confirm_addr_indev(struct in_device *in_dev, u32 dst, - u32 local, int scope) +static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, + __be32 local, int scope) { int same = 0; - u32 addr = 0; + __be32 addr = 0; for_ifa(in_dev) { if (!addr && @@ -971,9 +971,9 @@ static u32 confirm_addr_indev(struct in_device *in_dev, u32 dst, * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ -u32 inet_confirm_addr(const struct net_device *dev, u32 dst, u32 local, int scope) +__be32 inet_confirm_addr(const struct net_device *dev, __be32 dst, __be32 local, int scope) { - u32 addr = 0; + __be32 addr = 0; struct in_device *in_dev; if (dev) { @@ -1138,16 +1138,16 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (ifa->ifa_address) - NLA_PUT_U32(skb, IFA_ADDRESS, ifa->ifa_address); + NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address); if (ifa->ifa_local) - NLA_PUT_U32(skb, IFA_LOCAL, ifa->ifa_local); + NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local); if (ifa->ifa_broadcast) - NLA_PUT_U32(skb, IFA_BROADCAST, ifa->ifa_broadcast); + NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); if (ifa->ifa_anycast) - NLA_PUT_U32(skb, IFA_ANYCAST, ifa->ifa_anycast); + NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast); if (ifa->ifa_label[0]) NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 13b29360d102..b5c205b57669 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -253,7 +253,8 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) * as per draft-ietf-ipsec-udp-encaps-06, * section 3.1.2 */ - if (x->props.mode == XFRM_MODE_TRANSPORT) + if (x->props.mode == XFRM_MODE_TRANSPORT || + x->props.mode == XFRM_MODE_BEET) skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -271,17 +272,28 @@ static u32 esp4_get_max_size(struct xfrm_state *x, int mtu) { struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_blkcipher_blocksize(esp->conf.tfm), 4); - - if (x->props.mode == XFRM_MODE_TUNNEL) { - mtu = ALIGN(mtu + 2, blksize); - } else { - /* The worst case. */ + int enclen = 0; + + switch (x->props.mode) { + case XFRM_MODE_TUNNEL: + mtu = ALIGN(mtu +2, blksize); + break; + default: + case XFRM_MODE_TRANSPORT: + /* The worst case */ mtu = ALIGN(mtu + 2, 4) + blksize - 4; + break; + case XFRM_MODE_BEET: + /* The worst case. */ + enclen = IPV4_BEET_PHMAXLEN; + mtu = ALIGN(mtu + enclen + 2, blksize); + break; } + if (esp->conf.padlen) mtu = ALIGN(mtu, esp->conf.padlen); - return mtu + x->props.header_len + esp->auth.icv_trunc_len; + return mtu + x->props.header_len + esp->auth.icv_trunc_len - enclen; } static void esp4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cfb527c060e4..af0190d8b6c0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -122,7 +122,7 @@ static void fib_flush(void) * Find the first device with a given source address. */ -struct net_device * ip_dev_find(u32 addr) +struct net_device * ip_dev_find(__be32 addr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; struct fib_result res; @@ -146,7 +146,7 @@ out: return dev; } -unsigned inet_addr_type(u32 addr) +unsigned inet_addr_type(__be32 addr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; struct fib_result res; @@ -180,8 +180,8 @@ unsigned inet_addr_type(u32 addr) - check, that packet arrived from expected physical interface. */ -int fib_validate_source(u32 src, u32 dst, u8 tos, int oif, - struct net_device *dev, u32 *spec_dst, u32 *itag) +int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, + struct net_device *dev, __be32 *spec_dst, u32 *itag) { struct in_device *in_dev; struct flowi fl = { .nl_u = { .ip4_u = @@ -253,7 +253,7 @@ e_inval: #ifndef CONFIG_IP_NOSIOCRT -static inline u32 sk_extract_addr(struct sockaddr *addr) +static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } @@ -273,7 +273,7 @@ static int put_rtax(struct nlattr *mx, int len, int type, u32 value) static int rtentry_to_fib_config(int cmd, struct rtentry *rt, struct fib_config *cfg) { - u32 addr; + __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); @@ -292,7 +292,7 @@ static int rtentry_to_fib_config(int cmd, struct rtentry *rt, plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { - u32 mask = sk_extract_addr(&rt->rt_genmask); + __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) @@ -482,9 +482,7 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); - cfg->fc_family = rtm->rtm_family; cfg->fc_dst_len = rtm->rtm_dst_len; - cfg->fc_src_len = rtm->rtm_src_len; cfg->fc_tos = rtm->rtm_tos; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; @@ -499,22 +497,19 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (attr->nla_type) { case RTA_DST: - cfg->fc_dst = nla_get_u32(attr); - break; - case RTA_SRC: - cfg->fc_src = nla_get_u32(attr); + cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: - cfg->fc_gw = nla_get_u32(attr); + cfg->fc_gw = nla_get_be32(attr); break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: - cfg->fc_prefsrc = nla_get_u32(attr); + cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); @@ -627,8 +622,7 @@ out: only when netlink is already locked. */ -static void fib_magic(int cmd, int type, u32 dst, int dst_len, - struct in_ifaddr *ifa) +static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct fib_table *tb; struct fib_config cfg = { @@ -667,9 +661,9 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; - u32 mask = ifa->ifa_mask; - u32 addr = ifa->ifa_local; - u32 prefix = ifa->ifa_address&mask; + __be32 mask = ifa->ifa_mask; + __be32 addr = ifa->ifa_local; + __be32 prefix = ifa->ifa_address&mask; if (ifa->ifa_flags&IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); @@ -685,7 +679,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) return; /* Add broadcast address, if it is explicitly assigned. */ - if (ifa->ifa_broadcast && ifa->ifa_broadcast != 0xFFFFFFFF) + if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); if (!ZERONET(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) && @@ -707,8 +701,8 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa; - u32 brd = ifa->ifa_address|~ifa->ifa_mask; - u32 any = ifa->ifa_address&ifa->ifa_mask; + __be32 brd = ifa->ifa_address|~ifa->ifa_mask; + __be32 any = ifa->ifa_address&ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 88133b383dc5..107bb6cbb0b3 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -51,7 +51,7 @@ static kmem_cache_t *fn_alias_kmem __read_mostly; struct fib_node { struct hlist_node fn_hash; struct list_head fn_alias; - u32 fn_key; + __be32 fn_key; }; struct fn_zone { @@ -64,7 +64,7 @@ struct fn_zone { #define FZ_HASHMASK(fz) ((fz)->fz_hashmask) int fz_order; /* Zone order */ - u32 fz_mask; + __be32 fz_mask; #define FZ_MASK(fz) ((fz)->fz_mask) }; @@ -77,7 +77,7 @@ struct fn_hash { struct fn_zone *fn_zone_list; }; -static inline u32 fn_hash(u32 key, struct fn_zone *fz) +static inline u32 fn_hash(__be32 key, struct fn_zone *fz) { u32 h = ntohl(key)>>(32 - fz->fz_order); h ^= (h>>20); @@ -87,7 +87,7 @@ static inline u32 fn_hash(u32 key, struct fn_zone *fz) return h; } -static inline u32 fz_key(u32 dst, struct fn_zone *fz) +static inline __be32 fz_key(__be32 dst, struct fn_zone *fz) { return dst & FZ_MASK(fz); } @@ -254,7 +254,7 @@ fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result struct hlist_head *head; struct hlist_node *node; struct fib_node *f; - u32 k = fz_key(flp->fl4_dst, fz); + __be32 k = fz_key(flp->fl4_dst, fz); head = &fz->fz_hash[fn_hash(k, fz)]; hlist_for_each_entry(f, node, head, fn_hash) { @@ -365,7 +365,7 @@ static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f) } /* Return the node in FZ matching KEY. */ -static struct fib_node *fib_find_node(struct fn_zone *fz, u32 key) +static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) { struct hlist_head *head = &fz->fz_hash[fn_hash(key, fz)]; struct hlist_node *node; @@ -387,7 +387,7 @@ static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) struct fn_zone *fz; struct fib_info *fi; u8 tos = cfg->fc_tos; - u32 key; + __be32 key; int err; if (cfg->fc_dst_len > 32) @@ -541,7 +541,7 @@ static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) struct fib_node *f; struct fib_alias *fa, *fa_to_delete; struct fn_zone *fz; - u32 key; + __be32 key; if (cfg->fc_dst_len > 32) return -EINVAL; @@ -966,7 +966,7 @@ static void fib_seq_stop(struct seq_file *seq, void *v) read_unlock(&fib_hash_lock); } -static unsigned fib_flag_trans(int type, u32 mask, struct fib_info *fi) +static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { static const unsigned type2flags[RTN_MAX + 1] = { [7] = RTF_REJECT, [8] = RTF_REJECT, @@ -975,7 +975,7 @@ static unsigned fib_flag_trans(int type, u32 mask, struct fib_info *fi) if (fi && fi->fib_nh->nh_gw) flags |= RTF_GATEWAY; - if (mask == 0xFFFFFFFF) + if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; @@ -991,7 +991,7 @@ static int fib_seq_show(struct seq_file *seq, void *v) { struct fib_iter_state *iter; char bf[128]; - u32 prefix, mask; + __be32 prefix, mask; unsigned flags; struct fib_node *f; struct fib_alias *fa; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index fd6f7769f8ab..0e8b70bad4e1 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -20,16 +20,16 @@ struct fib_alias { /* Exported by fib_semantics.c */ extern int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, __u32 zone, __u32 mask, + struct fib_result *res, __be32 zone, __be32 mask, int prefixlen); extern void fib_release_info(struct fib_info *); extern struct fib_info *fib_create_info(struct fib_config *cfg); extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, u32 dst, + u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); -extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, +extern void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, struct nl_info *info); extern struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 52b2adae4f22..0852b9cd065a 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -40,10 +40,10 @@ struct fib4_rule u8 dst_len; u8 src_len; u8 tos; - u32 src; - u32 srcmask; - u32 dst; - u32 dstmask; + __be32 src; + __be32 srcmask; + __be32 dst; + __be32 dstmask; #ifdef CONFIG_IP_ROUTE_FWMARK u32 fwmark; u32 fwmask; @@ -150,8 +150,8 @@ void fib_select_default(const struct flowi *flp, struct fib_result *res) static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib4_rule *r = (struct fib4_rule *) rule; - u32 daddr = fl->fl4_dst; - u32 saddr = fl->fl4_src; + __be32 daddr = fl->fl4_dst; + __be32 saddr = fl->fl4_src; if (((saddr ^ r->src) & r->srcmask) || ((daddr ^ r->dst) & r->dstmask)) @@ -215,10 +215,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } if (tb[FRA_SRC]) - rule4->src = nla_get_u32(tb[FRA_SRC]); + rule4->src = nla_get_be32(tb[FRA_SRC]); if (tb[FRA_DST]) - rule4->dst = nla_get_u32(tb[FRA_DST]); + rule4->dst = nla_get_be32(tb[FRA_DST]); #ifdef CONFIG_IP_ROUTE_FWMARK if (tb[FRA_FWMARK]) { @@ -277,10 +277,10 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, return 0; #endif - if (tb[FRA_SRC] && (rule4->src != nla_get_u32(tb[FRA_SRC]))) + if (tb[FRA_SRC] && (rule4->src != nla_get_be32(tb[FRA_SRC]))) return 0; - if (tb[FRA_DST] && (rule4->dst != nla_get_u32(tb[FRA_DST]))) + if (tb[FRA_DST] && (rule4->dst != nla_get_be32(tb[FRA_DST]))) return 0; return 1; @@ -305,10 +305,10 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, #endif if (rule4->dst_len) - NLA_PUT_U32(skb, FRA_DST, rule4->dst); + NLA_PUT_BE32(skb, FRA_DST, rule4->dst); if (rule4->src_len) - NLA_PUT_U32(skb, FRA_SRC, rule4->src); + NLA_PUT_BE32(skb, FRA_SRC, rule4->src); #ifdef CONFIG_NET_CLS_ROUTE if (rule4->tclassid) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2ead09543f68..884d176e0082 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -203,7 +203,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) unsigned int val = fi->fib_nhs; val ^= fi->fib_protocol; - val ^= fi->fib_prefsrc; + val ^= (__force u32)fi->fib_prefsrc; val ^= fi->fib_priority; return (val ^ (val >> 7) ^ (val >> 12)) & mask; @@ -248,7 +248,7 @@ static inline unsigned int fib_devindex_hashfn(unsigned int val) Used only by redirect accept routine. */ -int ip_fib_check_default(u32 gw, struct net_device *dev) +int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; struct hlist_node *node; @@ -273,7 +273,7 @@ int ip_fib_check_default(u32 gw, struct net_device *dev) return -1; } -void rtmsg_fib(int event, u32 key, struct fib_alias *fa, +void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, struct nl_info *info) { struct sk_buff *skb; @@ -374,7 +374,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - nh->nh_gw = nla ? nla_get_u32(nla) : 0; + nh->nh_gw = nla ? nla_get_be32(nla) : 0; #ifdef CONFIG_NET_CLS_ROUTE nla = nla_find(attrs, attrlen, RTA_FLOW); nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; @@ -427,7 +427,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - if (nla && nla_get_u32(nla) != nh->nh_gw) + if (nla && nla_get_be32(nla) != nh->nh_gw) return 1; #ifdef CONFIG_NET_CLS_ROUTE nla = nla_find(attrs, attrlen, RTA_FLOW); @@ -568,11 +568,11 @@ out: return 0; } -static inline unsigned int fib_laddr_hashfn(u32 val) +static inline unsigned int fib_laddr_hashfn(__be32 val) { unsigned int mask = (fib_hash_size - 1); - return (val ^ (val >> 7) ^ (val >> 14)) & mask; + return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask; } static struct hlist_head *fib_hash_alloc(int bytes) @@ -847,7 +847,7 @@ failure: /* Note! fib_semantic_match intentionally uses RCU list functions. */ int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, __u32 zone, __u32 mask, + struct fib_result *res, __be32 zone, __be32 mask, int prefixlen) { struct fib_alias *fa; @@ -914,8 +914,7 @@ out_fill_res: res->fi = fa->fa_info; #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED res->netmask = mask; - res->network = zone & - (0xFFFFFFFF >> (32 - prefixlen)); + res->network = zone & inet_make_mask(prefixlen); #endif atomic_inc(&res->fi->fib_clntref); return 0; @@ -923,13 +922,13 @@ out_fill_res: /* Find appropriate source address to this destination */ -u32 __fib_res_prefsrc(struct fib_result *res) +__be32 __fib_res_prefsrc(struct fib_result *res) { return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope); } int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos, + u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) { struct nlmsghdr *nlh; @@ -952,7 +951,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len) - NLA_PUT_U32(skb, RTA_DST, dst); + NLA_PUT_BE32(skb, RTA_DST, dst); if (fi->fib_priority) NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority); @@ -961,11 +960,11 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, goto nla_put_failure; if (fi->fib_prefsrc) - NLA_PUT_U32(skb, RTA_PREFSRC, fi->fib_prefsrc); + NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc); if (fi->fib_nhs == 1) { if (fi->fib_nh->nh_gw) - NLA_PUT_U32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw); + NLA_PUT_BE32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw); if (fi->fib_nh->nh_oif) NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); @@ -993,7 +992,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtnh->rtnh_ifindex = nh->nh_oif; if (nh->nh_gw) - NLA_PUT_U32(skb, RTA_GATEWAY, nh->nh_gw); + NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw); #ifdef CONFIG_NET_CLS_ROUTE if (nh->nh_tclassid) NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); @@ -1018,7 +1017,7 @@ nla_put_failure: - device went down -> we must shutdown all nexthops going via it. */ -int fib_sync_down(u32 local, struct net_device *dev, int force) +int fib_sync_down(__be32 local, struct net_device *dev, int force) { int ret = 0; int scope = RT_SCOPE_NOWHERE; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 9c3ff6ba6e21..d17990ec724f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1834,7 +1834,7 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fi int i, s_i; struct fib_alias *fa; - u32 xkey = htonl(key); + __be32 xkey = htonl(key); s_i = cb->args[4]; i = 0; @@ -2281,7 +2281,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) if (IS_TNODE(n)) { struct tnode *tn = (struct tnode *) n; - t_key prf = ntohl(MASK_PFX(tn->key, tn->pos)); + __be32 prf = htonl(MASK_PFX(tn->key, tn->pos)); if (!NODE_PARENT(n)) { if (iter->trie == trie_local) @@ -2297,7 +2297,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) } else { struct leaf *l = (struct leaf *) n; int i; - u32 val = ntohl(l->key); + __be32 val = htonl(l->key); seq_indent(seq, iter->depth); seq_printf(seq, " |-- %d.%d.%d.%d\n", NIPQUAD(val)); @@ -2360,7 +2360,7 @@ static struct file_operations fib_trie_fops = { .release = seq_release_private, }; -static unsigned fib_flag_trans(int type, u32 mask, const struct fib_info *fi) +static unsigned fib_flag_trans(int type, __be32 mask, const struct fib_info *fi) { static unsigned type2flags[RTN_MAX + 1] = { [7] = RTF_REJECT, [8] = RTF_REJECT, @@ -2369,7 +2369,7 @@ static unsigned fib_flag_trans(int type, u32 mask, const struct fib_info *fi) if (fi && fi->fib_nh->nh_gw) flags |= RTF_GATEWAY; - if (mask == 0xFFFFFFFF) + if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; @@ -2403,7 +2403,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) for (i=32; i>=0; i--) { struct leaf_info *li = find_leaf_info(l, i); struct fib_alias *fa; - u32 mask, prefix; + __be32 mask, prefix; if (!li) continue; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c2ad07e48ab4..b39a37a47545 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -104,7 +104,7 @@ struct icmp_bxm { struct { struct icmphdr icmph; - __u32 times[3]; + __be32 times[3]; } data; int head_len; struct ip_options replyopts; @@ -381,7 +381,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct inet_sock *inet = inet_sk(sk); struct ipcm_cookie ipc; struct rtable *rt = (struct rtable *)skb->dst; - u32 daddr; + __be32 daddr; if (ip_options_echo(&icmp_param->replyopts, skb)) return; @@ -430,14 +430,14 @@ out_unlock: * MUST reply to only the first fragment. */ -void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) +void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct iphdr *iph; int room; struct icmp_bxm icmp_param; struct rtable *rt = (struct rtable *)skb_in->dst; struct ipcm_cookie ipc; - u32 saddr; + __be32 saddr; u8 tos; if (!rt) @@ -895,7 +895,7 @@ static void icmp_address_reply(struct sk_buff *skb) if (in_dev->ifa_list && IN_DEV_LOG_MARTIANS(in_dev) && IN_DEV_FORWARD(in_dev)) { - u32 _mask, *mp; + __be32 _mask, *mp; mp = skb_header_pointer(skb, 0, sizeof(_mask), &_mask); BUG_ON(mp == NULL); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 58be8227b0cb..6eee71647b7c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -138,14 +138,14 @@ time_before(jiffies, (in_dev)->mr_v2_seen))) static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); -static void igmpv3_del_delrec(struct in_device *in_dev, __u32 multiaddr); +static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); -static int ip_mc_add_src(struct in_device *in_dev, __u32 *pmca, int sfmode, - int sfcount, __u32 *psfsrc, int delta); +static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, + int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { @@ -426,7 +426,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, first = 1; psf_prev = NULL; for (psf=*psf_list; psf; psf=psf_next) { - u32 *psrc; + __be32 *psrc; psf_next = psf->sf_next; @@ -439,7 +439,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (isquery) psf->sf_gsresp = 0; - if (AVAILABLE(skb) < sizeof(u32) + + if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ @@ -455,7 +455,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, skb = add_grhead(skb, pmc, type, &pgr); first = 0; } - psrc = (u32 *)skb_put(skb, sizeof(u32)); + psrc = (__be32 *)skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || @@ -630,8 +630,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; - u32 group = pmc ? pmc->multiaddr : 0; - u32 dst; + __be32 group = pmc ? pmc->multiaddr : 0; + __be32 dst; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); @@ -748,7 +748,7 @@ static void igmp_timer_expire(unsigned long data) } /* mark EXCLUDE-mode sources */ -static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) +static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; @@ -775,7 +775,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) return 1; } -static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) +static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; @@ -803,7 +803,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) return 1; } -static void igmp_heard_report(struct in_device *in_dev, u32 group) +static void igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; @@ -828,7 +828,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, struct igmphdr *ih = skb->h.igmph; struct igmpv3_query *ih3 = (struct igmpv3_query *)ih; struct ip_mc_list *im; - u32 group = ih->group; + __be32 group = ih->group; int max_delay; int mark = 0; @@ -862,7 +862,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, ih3 = (struct igmpv3_query *) skb->h.raw; if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) - + ntohs(ih3->nsrcs)*sizeof(__u32))) + + ntohs(ih3->nsrcs)*sizeof(__be32))) return; ih3 = (struct igmpv3_query *) skb->h.raw; } @@ -985,7 +985,7 @@ drop: * Add a filter to a device */ -static void ip_mc_filter_add(struct in_device *in_dev, u32 addr) +static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; @@ -1005,7 +1005,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, u32 addr) * Remove a filter from a device */ -static void ip_mc_filter_del(struct in_device *in_dev, u32 addr) +static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; @@ -1055,7 +1055,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_unlock_bh(&in_dev->mc_tomb_lock); } -static void igmpv3_del_delrec(struct in_device *in_dev, __u32 multiaddr) +static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf, *psf_next; @@ -1193,7 +1193,7 @@ static void igmp_group_added(struct ip_mc_list *im) * A socket has joined a multicast group on device dev. */ -void ip_mc_inc_group(struct in_device *in_dev, u32 addr) +void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { struct ip_mc_list *im; @@ -1252,7 +1252,7 @@ out: * A socket has left a multicast group on device dev */ -void ip_mc_dec_group(struct in_device *in_dev, u32 addr) +void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { struct ip_mc_list *i, **ip; @@ -1402,7 +1402,7 @@ int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, - __u32 *psfsrc) + __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; @@ -1450,8 +1450,8 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #define igmp_ifc_event(x) do { } while (0) #endif -static int ip_mc_del_src(struct in_device *in_dev, __u32 *pmca, int sfmode, - int sfcount, __u32 *psfsrc, int delta) +static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, + int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; @@ -1517,7 +1517,7 @@ out_unlock: * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, - __u32 *psfsrc, int delta) + __be32 *psfsrc, int delta) { struct ip_sf_list *psf, *psf_prev; @@ -1623,8 +1623,8 @@ static int sf_setstate(struct ip_mc_list *pmc) /* * Add multicast source filter list to the interface list */ -static int ip_mc_add_src(struct in_device *in_dev, __u32 *pmca, int sfmode, - int sfcount, __u32 *psfsrc, int delta) +static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, + int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; @@ -1717,7 +1717,7 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) { int err; - u32 addr = imr->imr_multiaddr.s_addr; + __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml=NULL, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); @@ -1791,7 +1791,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml, **imlp; struct in_device *in_dev; - u32 group = imr->imr_multiaddr.s_addr; + __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; @@ -1829,7 +1829,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct { int err; struct ip_mreqn imr; - u32 addr = mreqs->imr_multiaddr; + __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); @@ -1883,7 +1883,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct rv = !0; for (i=0; i<psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, - sizeof(__u32)); + sizeof(__be32)); if (rv == 0) break; } @@ -1935,7 +1935,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i=0; i<psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, - sizeof(__u32)); + sizeof(__be32)); if (rv == 0) break; } @@ -1960,7 +1960,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; - u32 addr = msf->imsf_multiaddr; + __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); @@ -2044,7 +2044,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, { int err, len, count, copycount; struct ip_mreqn imr; - u32 addr = msf->imsf_multiaddr; + __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); @@ -2103,7 +2103,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, { int err, i, count, copycount; struct sockaddr_in *psin; - u32 addr; + __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; @@ -2156,7 +2156,7 @@ done: /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ -int ip_mc_sf_allow(struct sock *sk, u32 loc_addr, u32 rmt_addr, int dif) +int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; @@ -2216,7 +2216,7 @@ void ip_mc_drop_socket(struct sock *sk) rtnl_unlock(); } -int ip_check_mc(struct in_device *in_dev, u32 mc_addr, u32 src_addr, u16 proto) +int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto) { struct ip_mc_list *im; struct ip_sf_list *psf; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 07204391d083..96bbe2a0aa1b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -39,7 +39,7 @@ int sysctl_local_port_range[2] = { 1024, 4999 }; int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb) { - const u32 sk_rcv_saddr = inet_rcv_saddr(sk); + const __be32 sk_rcv_saddr = inet_rcv_saddr(sk); struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; @@ -52,7 +52,7 @@ int inet_csk_bind_conflict(const struct sock *sk, sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) { - const u32 sk2_rcv_saddr = inet_rcv_saddr(sk2); + const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr || sk2_rcv_saddr == sk_rcv_saddr) break; @@ -342,10 +342,10 @@ struct dst_entry* inet_csk_route_req(struct sock *sk, EXPORT_SYMBOL_GPL(inet_csk_route_req); -static inline u32 inet_synq_hash(const u32 raddr, const u16 rport, +static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, const u32 rnd, const u16 synq_hsize) { - return jhash_2words(raddr, (u32)rport, rnd) & (synq_hsize - 1); + return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -356,8 +356,8 @@ static inline u32 inet_synq_hash(const u32 raddr, const u16 rport, struct request_sock *inet_csk_search_req(const struct sock *sk, struct request_sock ***prevp, - const __u16 rport, const __u32 raddr, - const __u32 laddr) + const __be16 rport, const __be32 raddr, + const __be32 laddr) { const struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 492858e6faf0..77761ac4f7bb 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -36,8 +36,8 @@ static const struct inet_diag_handler **inet_diag_table; struct inet_diag_entry { - u32 *saddr; - u32 *daddr; + __be32 *saddr; + __be32 *daddr; u16 sport; u16 dport; u16 family; @@ -294,7 +294,7 @@ out: return err; } -static int bitstring_match(const u32 *a1, const u32 *a2, int bits) +static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits) { int words = bits >> 5; @@ -305,8 +305,8 @@ static int bitstring_match(const u32 *a1, const u32 *a2, int bits) return 0; } if (bits) { - __u32 w1, w2; - __u32 mask; + __be32 w1, w2; + __be32 mask; w1 = a1[words]; w2 = a2[words]; @@ -352,7 +352,7 @@ static int inet_diag_bc_run(const void *bc, int len, case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: { struct inet_diag_hostcond *cond; - u32 *addr; + __be32 *addr; cond = (struct inet_diag_hostcond *)(op + 1); if (cond->port != -1 && diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fb296c9a7f3f..244c4f445c7d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -125,7 +125,7 @@ EXPORT_SYMBOL(inet_listen_wlock); * wildcarded during the search since they can never be otherwise. */ static struct sock *inet_lookup_listener_slow(const struct hlist_head *head, - const u32 daddr, + const __be32 daddr, const unsigned short hnum, const int dif) { @@ -137,7 +137,7 @@ static struct sock *inet_lookup_listener_slow(const struct hlist_head *head, const struct inet_sock *inet = inet_sk(sk); if (inet->num == hnum && !ipv6_only_sock(sk)) { - const __u32 rcv_saddr = inet->rcv_saddr; + const __be32 rcv_saddr = inet->rcv_saddr; int score = sk->sk_family == PF_INET ? 1 : 0; if (rcv_saddr) { @@ -163,7 +163,7 @@ static struct sock *inet_lookup_listener_slow(const struct hlist_head *head, /* Optimize the common listener case. */ struct sock *__inet_lookup_listener(struct inet_hashinfo *hashinfo, - const u32 daddr, const unsigned short hnum, + const __be32 daddr, const unsigned short hnum, const int dif) { struct sock *sk = NULL; @@ -197,11 +197,11 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); - u32 daddr = inet->rcv_saddr; - u32 saddr = inet->daddr; + __be32 daddr = inet->rcv_saddr; + __be32 saddr = inet->daddr; int dif = sk->sk_bound_dev_if; INET_ADDR_COOKIE(acookie, saddr, daddr) - const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); struct sock *sk2; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index a675602ef295..f072f3875af8 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -94,10 +94,8 @@ int inet_peer_minttl = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl = 10 * 60 * HZ; /* usual time to live: 10 min */ static struct inet_peer *inet_peer_unused_head; -/* Exported for inet_putpeer inline function. */ -struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head; -DEFINE_SPINLOCK(inet_peer_unused_lock); -#define PEER_MAX_CLEANUP_WORK 30 +static struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head; +static DEFINE_SPINLOCK(inet_peer_unused_lock); static void peer_check_expire(unsigned long dummy); static DEFINE_TIMER(peer_periodic_timer, peer_check_expire, 0, 0); @@ -163,7 +161,7 @@ static void unlink_from_unused(struct inet_peer *p) for (u = peer_root; u != peer_avl_empty; ) { \ if (daddr == u->v4daddr) \ break; \ - if (daddr < u->v4daddr) \ + if ((__force __u32)daddr < (__force __u32)u->v4daddr) \ v = &u->avl_left; \ else \ v = &u->avl_right; \ @@ -340,7 +338,8 @@ static int cleanup_once(unsigned long ttl) spin_lock_bh(&inet_peer_unused_lock); p = inet_peer_unused_head; if (p != NULL) { - if (time_after(p->dtime + ttl, jiffies)) { + __u32 delta = (__u32)jiffies - p->dtime; + if (delta < ttl) { /* Do not prune fresh entries. */ spin_unlock_bh(&inet_peer_unused_lock); return -1; @@ -368,7 +367,7 @@ static int cleanup_once(unsigned long ttl) } /* Called with or without local BH being disabled. */ -struct inet_peer *inet_getpeer(__u32 daddr, int create) +struct inet_peer *inet_getpeer(__be32 daddr, int create) { struct inet_peer *p, *n; struct inet_peer **stack[PEER_MAXDEPTH], ***stackptr; @@ -432,7 +431,7 @@ out_free: /* Called with local BH disabled. */ static void peer_check_expire(unsigned long dummy) { - int i; + unsigned long now = jiffies; int ttl; if (peer_total >= inet_peer_threshold) @@ -441,7 +440,10 @@ static void peer_check_expire(unsigned long dummy) ttl = inet_peer_maxttl - (inet_peer_maxttl - inet_peer_minttl) / HZ * peer_total / inet_peer_threshold * HZ; - for (i = 0; i < PEER_MAX_CLEANUP_WORK && !cleanup_once(ttl); i++); + while (!cleanup_once(ttl)) { + if (jiffies != now) + break; + } /* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime * interval depending on the total number of entries (more entries, @@ -455,3 +457,16 @@ static void peer_check_expire(unsigned long dummy) peer_total / inet_peer_threshold * HZ; add_timer(&peer_periodic_timer); } + +void inet_putpeer(struct inet_peer *p) +{ + spin_lock_bh(&inet_peer_unused_lock); + if (atomic_dec_and_test(&p->refcnt)) { + p->unused_prevp = inet_peer_unused_tailp; + p->unused_next = NULL; + *inet_peer_unused_tailp = p; + inet_peer_unused_tailp = &p->unused_next; + p->dtime = (__u32)jiffies; + } + spin_unlock_bh(&inet_peer_unused_lock); +} diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 165d72859ddf..74046efdf875 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -77,9 +77,9 @@ struct ipq { struct hlist_node list; struct list_head lru_list; /* lru list member */ u32 user; - u32 saddr; - u32 daddr; - u16 id; + __be32 saddr; + __be32 daddr; + __be16 id; u8 protocol; u8 last_in; #define COMPLETE 4 @@ -123,9 +123,10 @@ static __inline__ void ipq_unlink(struct ipq *ipq) write_unlock(&ipfrag_lock); } -static unsigned int ipqhashfn(u16 id, u32 saddr, u32 daddr, u8 prot) +static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) { - return jhash_3words((u32)id << 16 | prot, saddr, daddr, + return jhash_3words((__force u32)id << 16 | prot, + (__force u32)saddr, (__force u32)daddr, ipfrag_hash_rnd) & (IPQ_HASHSZ - 1); } @@ -387,8 +388,8 @@ out_nomem: static inline struct ipq *ip_find(struct iphdr *iph, u32 user) { __be16 id = iph->id; - __u32 saddr = iph->saddr; - __u32 daddr = iph->daddr; + __be32 saddr = iph->saddr; + __be32 daddr = iph->daddr; __u8 protocol = iph->protocol; unsigned int hash; struct ipq *qp; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f5fba051df3d..d5b5dec075b8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -611,8 +611,8 @@ static int ipgre_rcv(struct sk_buff *skb) * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (flags == 0 && - skb->protocol == __constant_htons(ETH_P_WCCP)) { - skb->protocol = __constant_htons(ETH_P_IP); + skb->protocol == htons(ETH_P_WCCP)) { + skb->protocol = htons(ETH_P_IP); if ((*(h + offset) & 0xF0) != 0x40) offset += 4; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index e7437c091326..8dabbfc31267 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -38,7 +38,7 @@ */ void ip_options_build(struct sk_buff * skb, struct ip_options * opt, - u32 daddr, struct rtable *rt, int is_frag) + __be32 daddr, struct rtable *rt, int is_frag) { unsigned char * iph = skb->nh.raw; @@ -57,7 +57,7 @@ void ip_options_build(struct sk_buff * skb, struct ip_options * opt, ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, rt); if (opt->ts_needtime) { struct timeval tv; - __u32 midtime; + __be32 midtime; do_gettimeofday(&tv); midtime = htonl((tv.tv_sec % 86400) * 1000 + tv.tv_usec / 1000); memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4); @@ -91,7 +91,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) unsigned char *sptr, *dptr; int soffset, doffset; int optlen; - u32 daddr; + __be32 daddr; memset(dopt, 0, sizeof(struct ip_options)); @@ -148,7 +148,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) dopt->ts_needtime = 0; if (soffset + 8 <= optlen) { - __u32 addr; + __be32 addr; memcpy(&addr, sptr+soffset-1, 4); if (inet_addr_type(addr) != RTN_LOCAL) { @@ -165,7 +165,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) } if (sopt->srr) { unsigned char * start = sptr+sopt->srr; - u32 faddr; + __be32 faddr; optlen = start[1]; soffset = start[2]; @@ -362,7 +362,7 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) goto error; } if (optptr[2] <= optlen) { - __u32 * timeptr = NULL; + __be32 *timeptr = NULL; if (optptr[2]+3 > optptr[1]) { pp_ptr = optptr + 2; goto error; @@ -371,7 +371,7 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) case IPOPT_TS_TSONLY: opt->ts = optptr - iph; if (skb) - timeptr = (__u32*)&optptr[optptr[2]-1]; + timeptr = (__be32*)&optptr[optptr[2]-1]; opt->ts_needtime = 1; optptr[2] += 4; break; @@ -383,7 +383,7 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) opt->ts = optptr - iph; if (skb) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); - timeptr = (__u32*)&optptr[optptr[2]+3]; + timeptr = (__be32*)&optptr[optptr[2]+3]; } opt->ts_needaddr = 1; opt->ts_needtime = 1; @@ -396,12 +396,12 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) } opt->ts = optptr - iph; { - u32 addr; + __be32 addr; memcpy(&addr, &optptr[optptr[2]-1], 4); if (inet_addr_type(addr) == RTN_UNICAST) break; if (skb) - timeptr = (__u32*)&optptr[optptr[2]+3]; + timeptr = (__be32*)&optptr[optptr[2]+3]; } opt->ts_needtime = 1; optptr[2] += 8; @@ -415,10 +415,10 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) } if (timeptr) { struct timeval tv; - __u32 midtime; + __be32 midtime; do_gettimeofday(&tv); midtime = htonl((tv.tv_sec % 86400) * 1000 + tv.tv_usec / 1000); - memcpy(timeptr, &midtime, sizeof(__u32)); + memcpy(timeptr, &midtime, sizeof(__be32)); opt->is_changed = 1; } } else { @@ -607,7 +607,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; - u32 nexthop; + __be32 nexthop; struct iphdr *iph = skb->nh.iph; unsigned char * optptr = skb->nh.raw + opt->srr; struct rtable *rt = (struct rtable*)skb->dst; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 97aee76fb746..fc195a44fc2e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -118,7 +118,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * */ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, - u32 saddr, u32 daddr, struct ip_options *opt) + __be32 saddr, __be32 daddr, struct ip_options *opt) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = (struct rtable *)skb->dst; @@ -306,7 +306,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); if (rt == NULL) { - u32 daddr; + __be32 daddr; /* Use correct destination address if we have options. */ daddr = inet->daddr; @@ -1340,7 +1340,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar char data[40]; } replyopts; struct ipcm_cookie ipc; - u32 daddr; + __be32 daddr; struct rtable *rt = (struct rtable*)skb->dst; if (ip_options_echo(&replyopts.opt, skb)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 2d05c4133d3e..4b132953bcc2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -254,7 +254,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct s } void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, - u16 port, u32 info, u8 *payload) + __be16 port, u32 info, u8 *payload) { struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; @@ -283,7 +283,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, kfree_skb(skb); } -void ip_local_error(struct sock *sk, int err, u32 daddr, u16 port, u32 info) +void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 17342430a843..3839b706142e 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -183,7 +183,7 @@ out_ok: static void ipcomp4_err(struct sk_buff *skb, u32 info) { - u32 spi; + __be32 spi; struct iphdr *iph = (struct iphdr *)skb->data; struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; @@ -206,6 +206,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct xfrm_state *t; + u8 mode = XFRM_MODE_TUNNEL; t = xfrm_state_alloc(); if (t == NULL) @@ -216,7 +217,9 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t->id.daddr.a4 = x->id.daddr.a4; memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET; - t->props.mode = XFRM_MODE_TUNNEL; + if (x->props.mode == XFRM_MODE_BEET) + mode = x->props.mode; + t->props.mode = mode; t->props.saddr.a4 = x->props.saddr.a4; t->props.flags = x->props.flags; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 1fbb38415b19..f8ce84759159 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -366,7 +366,7 @@ static int __init ic_defaults(void) */ if (!ic_host_name_set) - sprintf(system_utsname.nodename, "%u.%u.%u.%u", NIPQUAD(ic_myaddr)); + sprintf(init_utsname()->nodename, "%u.%u.%u.%u", NIPQUAD(ic_myaddr)); if (root_server_addr == INADDR_NONE) root_server_addr = ic_servaddr; @@ -805,7 +805,7 @@ static void __init ic_do_bootp_ext(u8 *ext) } break; case 12: /* Host name */ - ic_bootp_string(system_utsname.nodename, ext+1, *ext, __NEW_UTS_LEN); + ic_bootp_string(utsname()->nodename, ext+1, *ext, __NEW_UTS_LEN); ic_host_name_set = 1; break; case 15: /* Domain name (DNS) */ @@ -816,7 +816,7 @@ static void __init ic_do_bootp_ext(u8 *ext) ic_bootp_string(root_server_path, ext+1, *ext, sizeof(root_server_path)); break; case 40: /* NIS Domain name (_not_ DNS) */ - ic_bootp_string(system_utsname.domainname, ext+1, *ext, __NEW_UTS_LEN); + ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); break; } } @@ -1368,7 +1368,7 @@ static int __init ip_auto_config(void) printk(", mask=%u.%u.%u.%u", NIPQUAD(ic_netmask)); printk(", gw=%u.%u.%u.%u", NIPQUAD(ic_gateway)); printk(",\n host=%s, domain=%s, nis-domain=%s", - system_utsname.nodename, ic_domain, system_utsname.domainname); + utsname()->nodename, ic_domain, utsname()->domainname); printk(",\n bootserver=%u.%u.%u.%u", NIPQUAD(ic_servaddr)); printk(", rootserver=%u.%u.%u.%u", NIPQUAD(root_server_addr)); printk(", rootpath=%s", root_server_path); @@ -1478,11 +1478,11 @@ static int __init ip_auto_config_setup(char *addrs) case 4: if ((dp = strchr(ip, '.'))) { *dp++ = '\0'; - strlcpy(system_utsname.domainname, dp, - sizeof(system_utsname.domainname)); + strlcpy(utsname()->domainname, dp, + sizeof(utsname()->domainname)); } - strlcpy(system_utsname.nodename, ip, - sizeof(system_utsname.nodename)); + strlcpy(utsname()->nodename, ip, + sizeof(utsname()->nodename)); ic_host_name_set = 1; break; case 5: diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index ba49588da242..97cfa97c8abb 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -462,7 +462,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock) return 0; } -static struct mfc_cache *ipmr_cache_find(__u32 origin, __u32 mcastgrp) +static struct mfc_cache *ipmr_cache_find(__be32 origin, __be32 mcastgrp) { int line=MFC_HASH(mcastgrp,origin); struct mfc_cache *c; @@ -1097,7 +1097,7 @@ static struct notifier_block ip_mr_notifier={ * important for multicast video. */ -static void ip_encap(struct sk_buff *skb, u32 saddr, u32 daddr) +static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph = (struct iphdr *)skb_push(skb,sizeof(struct iphdr)); diff --git a/net/ipv4/ipvs/Kconfig b/net/ipv4/ipvs/Kconfig index c9820bfc493a..891b9355cf96 100644 --- a/net/ipv4/ipvs/Kconfig +++ b/net/ipv4/ipvs/Kconfig @@ -81,7 +81,7 @@ config IP_VS_PROTO_ESP bool "ESP load balancing support" depends on IP_VS ---help--- - This option enables support for load balancing ESP (Encapsultion + This option enables support for load balancing ESP (Encapsulation Security Payload) transport protocol. Say Y if unsure. config IP_VS_PROTO_AH @@ -204,7 +204,7 @@ config IP_VS_SED connections to the server with the shortest expected delay. The expected delay that the job will experience is (Ci + 1) / Ui if sent to the ith server, in which Ci is the number of connections - on the the ith server and Ui is the fixed service rate (weight) + on the ith server and Ui is the fixed service rate (weight) of the ith server. If you want to compile it in kernel, say Y. To compile it as a diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index 87b83813cf2c..8832eb517d52 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -115,9 +115,9 @@ static inline void ct_write_unlock_bh(unsigned key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(unsigned proto, __u32 addr, __u16 port) +static unsigned int ip_vs_conn_hashkey(unsigned proto, __be32 addr, __be16 port) { - return jhash_3words(addr, port, proto, ip_vs_conn_rnd) + return jhash_3words((__force u32)addr, (__force u32)port, proto, ip_vs_conn_rnd) & IP_VS_CONN_TAB_MASK; } @@ -188,7 +188,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) * d_addr, d_port: pkt dest address (load balancer) */ static inline struct ip_vs_conn *__ip_vs_conn_in_get -(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port) +(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; @@ -215,7 +215,7 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get } struct ip_vs_conn *ip_vs_conn_in_get -(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port) +(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) { struct ip_vs_conn *cp; @@ -234,7 +234,7 @@ struct ip_vs_conn *ip_vs_conn_in_get /* Get reference to connection template */ struct ip_vs_conn *ip_vs_ct_in_get -(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port) +(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; @@ -274,7 +274,7 @@ struct ip_vs_conn *ip_vs_ct_in_get * d_addr, d_port: pkt dest address (foreign host) */ struct ip_vs_conn *ip_vs_conn_out_get -(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port) +(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp, *ret=NULL; @@ -324,7 +324,7 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) /* * Fill a no_client_port connection with a client port number */ -void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __u16 cport) +void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) { if (ip_vs_conn_unhash(cp)) { spin_lock(&cp->lock); @@ -508,10 +508,10 @@ int ip_vs_check_template(struct ip_vs_conn *ct) /* * Invalidate the connection template */ - if (ct->vport != 65535) { + if (ct->vport != htons(0xffff)) { if (ip_vs_conn_unhash(ct)) { - ct->dport = 65535; - ct->vport = 65535; + ct->dport = htons(0xffff); + ct->vport = htons(0xffff); ct->cport = 0; ip_vs_conn_hash(ct); } @@ -596,8 +596,8 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) * Create a new connection entry and hash it into the ip_vs_conn_tab */ struct ip_vs_conn * -ip_vs_conn_new(int proto, __u32 caddr, __u16 cport, __u32 vaddr, __u16 vport, - __u32 daddr, __u16 dport, unsigned flags, +ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport, + __be32 daddr, __be16 dport, unsigned flags, struct ip_vs_dest *dest) { struct ip_vs_conn *cp; diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c index 3f47ad8e1cad..1445bb47fea4 100644 --- a/net/ipv4/ipvs/ip_vs_core.c +++ b/net/ipv4/ipvs/ip_vs_core.c @@ -209,14 +209,14 @@ int ip_vs_make_skb_writable(struct sk_buff **pskb, int writable_len) static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, const struct sk_buff *skb, - __u16 ports[2]) + __be16 ports[2]) { struct ip_vs_conn *cp = NULL; struct iphdr *iph = skb->nh.iph; struct ip_vs_dest *dest; struct ip_vs_conn *ct; - __u16 dport; /* destination port to forward */ - __u32 snet; /* source network of the client, after masking */ + __be16 dport; /* destination port to forward */ + __be32 snet; /* source network of the client, after masking */ /* Mask saddr with the netmask to adjust template granularity */ snet = iph->saddr & svc->netmask; @@ -383,7 +383,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_conn *cp = NULL; struct iphdr *iph = skb->nh.iph; struct ip_vs_dest *dest; - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, iph->ihl*4, sizeof(_ports), _ports); @@ -446,7 +446,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_protocol *pp) { - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; struct iphdr *iph = skb->nh.iph; pptr = skb_header_pointer(skb, iph->ihl*4, @@ -576,7 +576,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, /* the TCP/UDP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol) { - __u16 *ports = (void *)ciph + ciph->ihl*4; + __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; @@ -775,7 +775,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff **pskb, if (sysctl_ip_vs_nat_icmp_send && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP)) { - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, ihl, sizeof(_ports), _ports); @@ -813,6 +813,16 @@ ip_vs_out(unsigned int hooknum, struct sk_buff **pskb, skb->nh.iph->saddr = cp->vaddr; ip_send_check(skb->nh.iph); + /* For policy routing, packets originating from this + * machine itself may be routed differently to packets + * passing through. We want this packet to be routed as + * if it came from this machine itself. So re-compute + * the routing information. + */ + if (ip_route_me_harder(pskb, RTN_LOCAL) != 0) + goto drop; + skb = *pskb; + IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); ip_vs_out_stats(cp, skb); diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 6a28fafe910c..f261616e4602 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -283,7 +283,7 @@ static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0); * Returns hash value for virtual service */ static __inline__ unsigned -ip_vs_svc_hashkey(unsigned proto, __u32 addr, __u16 port) +ip_vs_svc_hashkey(unsigned proto, __be32 addr, __be16 port) { register unsigned porth = ntohs(port); @@ -365,7 +365,7 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) * Get service by {proto,addr,port} in the service table. */ static __inline__ struct ip_vs_service * -__ip_vs_service_get(__u16 protocol, __u32 vaddr, __u16 vport) +__ip_vs_service_get(__u16 protocol, __be32 vaddr, __be16 vport) { unsigned hash; struct ip_vs_service *svc; @@ -410,7 +410,7 @@ static __inline__ struct ip_vs_service *__ip_vs_svc_fwm_get(__u32 fwmark) } struct ip_vs_service * -ip_vs_service_get(__u32 fwmark, __u16 protocol, __u32 vaddr, __u16 vport) +ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport) { struct ip_vs_service *svc; @@ -480,7 +480,7 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest) /* * Returns hash value for real service */ -static __inline__ unsigned ip_vs_rs_hashkey(__u32 addr, __u16 port) +static __inline__ unsigned ip_vs_rs_hashkey(__be32 addr, __be16 port) { register unsigned porth = ntohs(port); @@ -531,7 +531,7 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) * Lookup real service by <proto,addr,port> in the real service table. */ struct ip_vs_dest * -ip_vs_lookup_real_service(__u16 protocol, __u32 daddr, __u16 dport) +ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport) { unsigned hash; struct ip_vs_dest *dest; @@ -562,7 +562,7 @@ ip_vs_lookup_real_service(__u16 protocol, __u32 daddr, __u16 dport) * Lookup destination by {addr,port} in the given service */ static struct ip_vs_dest * -ip_vs_lookup_dest(struct ip_vs_service *svc, __u32 daddr, __u16 dport) +ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) { struct ip_vs_dest *dest; @@ -591,7 +591,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, __u32 daddr, __u16 dport) * scheduling. */ static struct ip_vs_dest * -ip_vs_trash_get_dest(struct ip_vs_service *svc, __u32 daddr, __u16 dport) +ip_vs_trash_get_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) { struct ip_vs_dest *dest, *nxt; @@ -773,8 +773,8 @@ static int ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) { struct ip_vs_dest *dest; - __u32 daddr = udest->addr; - __u16 dport = udest->port; + __be32 daddr = udest->addr; + __be16 dport = udest->port; int ret; EnterFunction(2); @@ -879,8 +879,8 @@ static int ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) { struct ip_vs_dest *dest; - __u32 daddr = udest->addr; - __u16 dport = udest->port; + __be32 daddr = udest->addr; + __be16 dport = udest->port; EnterFunction(2); @@ -991,8 +991,8 @@ static int ip_vs_del_dest(struct ip_vs_service *svc,struct ip_vs_dest_user *udest) { struct ip_vs_dest *dest; - __u32 daddr = udest->addr; - __u16 dport = udest->port; + __be32 daddr = udest->addr; + __be16 dport = udest->port; EnterFunction(2); diff --git a/net/ipv4/ipvs/ip_vs_dh.c b/net/ipv4/ipvs/ip_vs_dh.c index 9fee19c4c617..502111fba872 100644 --- a/net/ipv4/ipvs/ip_vs_dh.c +++ b/net/ipv4/ipvs/ip_vs_dh.c @@ -66,7 +66,7 @@ struct ip_vs_dh_bucket { /* * Returns hash value for IPVS DH entry */ -static inline unsigned ip_vs_dh_hashkey(__u32 addr) +static inline unsigned ip_vs_dh_hashkey(__be32 addr) { return (ntohl(addr)*2654435761UL) & IP_VS_DH_TAB_MASK; } @@ -76,7 +76,7 @@ static inline unsigned ip_vs_dh_hashkey(__u32 addr) * Get ip_vs_dest associated with supplied parameters. */ static inline struct ip_vs_dest * -ip_vs_dh_get(struct ip_vs_dh_bucket *tbl, __u32 addr) +ip_vs_dh_get(struct ip_vs_dh_bucket *tbl, __be32 addr) { return (tbl[ip_vs_dh_hashkey(addr)]).dest; } diff --git a/net/ipv4/ipvs/ip_vs_ftp.c b/net/ipv4/ipvs/ip_vs_ftp.c index 37fafb1fbcff..6d398f10aa91 100644 --- a/net/ipv4/ipvs/ip_vs_ftp.c +++ b/net/ipv4/ipvs/ip_vs_ftp.c @@ -32,6 +32,7 @@ #include <linux/ip.h> #include <net/protocol.h> #include <net/tcp.h> +#include <asm/unaligned.h> #include <net/ip_vs.h> @@ -44,8 +45,8 @@ * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper * First port is set to the default port. */ -static int ports[IP_VS_APP_MAX_PORTS] = {21, 0}; -module_param_array(ports, int, NULL, 0); +static unsigned short ports[IP_VS_APP_MAX_PORTS] = {21, 0}; +module_param_array(ports, ushort, NULL, 0); MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands"); @@ -74,7 +75,7 @@ ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) */ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, const char *pattern, size_t plen, char term, - __u32 *addr, __u16 *port, + __be32 *addr, __be16 *port, char **start, char **end) { unsigned char p[6]; @@ -114,8 +115,8 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, if (i != 5) return -1; - *addr = (p[3]<<24) | (p[2]<<16) | (p[1]<<8) | p[0]; - *port = (p[5]<<8) | p[4]; + *addr = get_unaligned((__be32 *)p); + *port = get_unaligned((__be16 *)(p + 4)); return 1; } @@ -140,8 +141,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct tcphdr *th; char *data, *data_limit; char *start, *end; - __u32 from; - __u16 port; + __be32 from; + __be16 port; struct ip_vs_conn *n_cp; char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */ unsigned buf_len; @@ -199,7 +200,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, from = n_cp->vaddr; port = n_cp->vport; sprintf(buf,"%d,%d,%d,%d,%d,%d", NIPQUAD(from), - port&255, (port>>8)&255); + ntohs(port)&255, (ntohs(port)>>8)&255); buf_len = strlen(buf); /* @@ -243,8 +244,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct tcphdr *th; char *data, *data_start, *data_limit; char *start, *end; - __u32 to; - __u16 port; + __be32 to; + __be16 port; struct ip_vs_conn *n_cp; /* no diff required for incoming packets */ @@ -273,7 +274,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, while (data <= data_limit - 6) { if (strnicmp(data, "PASV\r\n", 6) == 0) { /* Passive mode on */ - IP_VS_DBG(7, "got PASV at %zd of %zd\n", + IP_VS_DBG(7, "got PASV at %td of %td\n", data - data_start, data_limit - data_start); cp->app_data = &ip_vs_ftp_pasv; @@ -365,12 +366,6 @@ static int __init ip_vs_ftp_init(void) for (i=0; i<IP_VS_APP_MAX_PORTS; i++) { if (!ports[i]) continue; - if (ports[i] < 0 || ports[i] > 0xffff) { - IP_VS_WARNING("ip_vs_ftp: Ignoring invalid " - "configuration port[%d] = %d\n", - i, ports[i]); - continue; - } ret = register_ip_vs_app_inc(app, app->protocol, ports[i]); if (ret) break; diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c index 6e5cb92a5c83..524751e031de 100644 --- a/net/ipv4/ipvs/ip_vs_lblc.c +++ b/net/ipv4/ipvs/ip_vs_lblc.c @@ -87,7 +87,7 @@ static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ; */ struct ip_vs_lblc_entry { struct list_head list; - __u32 addr; /* destination IP address */ + __be32 addr; /* destination IP address */ struct ip_vs_dest *dest; /* real server (cache) */ unsigned long lastuse; /* last used time */ }; @@ -160,7 +160,7 @@ static struct ctl_table_header * sysctl_header; * IP address to a server. */ static inline struct ip_vs_lblc_entry * -ip_vs_lblc_new(__u32 daddr, struct ip_vs_dest *dest) +ip_vs_lblc_new(__be32 daddr, struct ip_vs_dest *dest) { struct ip_vs_lblc_entry *en; @@ -195,7 +195,7 @@ static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) /* * Returns hash value for IPVS LBLC entry */ -static inline unsigned ip_vs_lblc_hashkey(__u32 addr) +static inline unsigned ip_vs_lblc_hashkey(__be32 addr) { return (ntohl(addr)*2654435761UL) & IP_VS_LBLC_TAB_MASK; } @@ -234,7 +234,7 @@ ip_vs_lblc_hash(struct ip_vs_lblc_table *tbl, struct ip_vs_lblc_entry *en) * Get ip_vs_lblc_entry associated with supplied parameters. */ static inline struct ip_vs_lblc_entry * -ip_vs_lblc_get(struct ip_vs_lblc_table *tbl, __u32 addr) +ip_vs_lblc_get(struct ip_vs_lblc_table *tbl, __be32 addr) { unsigned hash; struct ip_vs_lblc_entry *en; diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c index 32ba37ba72d8..08990192b6ec 100644 --- a/net/ipv4/ipvs/ip_vs_lblcr.c +++ b/net/ipv4/ipvs/ip_vs_lblcr.c @@ -276,7 +276,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) */ struct ip_vs_lblcr_entry { struct list_head list; - __u32 addr; /* destination IP address */ + __be32 addr; /* destination IP address */ struct ip_vs_dest_set set; /* destination server set */ unsigned long lastuse; /* last used time */ }; @@ -348,7 +348,7 @@ static struct ctl_table_header * sysctl_header; * new/free a ip_vs_lblcr_entry, which is a mapping of a destination * IP address to a server. */ -static inline struct ip_vs_lblcr_entry *ip_vs_lblcr_new(__u32 daddr) +static inline struct ip_vs_lblcr_entry *ip_vs_lblcr_new(__be32 daddr) { struct ip_vs_lblcr_entry *en; @@ -381,7 +381,7 @@ static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) /* * Returns hash value for IPVS LBLCR entry */ -static inline unsigned ip_vs_lblcr_hashkey(__u32 addr) +static inline unsigned ip_vs_lblcr_hashkey(__be32 addr) { return (ntohl(addr)*2654435761UL) & IP_VS_LBLCR_TAB_MASK; } @@ -420,7 +420,7 @@ ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en) * Get ip_vs_lblcr_entry associated with supplied parameters. */ static inline struct ip_vs_lblcr_entry * -ip_vs_lblcr_get(struct ip_vs_lblcr_table *tbl, __u32 addr) +ip_vs_lblcr_get(struct ip_vs_lblcr_table *tbl, __be32 addr) { unsigned hash; struct ip_vs_lblcr_entry *en; diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c index 867d4e9c6594..c4528b5c800d 100644 --- a/net/ipv4/ipvs/ip_vs_proto.c +++ b/net/ipv4/ipvs/ip_vs_proto.c @@ -176,7 +176,7 @@ ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, pp->name, NIPQUAD(ih->saddr), NIPQUAD(ih->daddr)); else { - __u16 _ports[2], *pptr + __be16 _ports[2], *pptr ; pptr = skb_header_pointer(skb, offset + ih->ihl*4, sizeof(_ports), _ports); diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c index 820e8318d10d..bfe779e74590 100644 --- a/net/ipv4/ipvs/ip_vs_proto_tcp.c +++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c @@ -29,7 +29,7 @@ static struct ip_vs_conn * tcp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, const struct iphdr *iph, unsigned int proto_off, int inverse) { - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) @@ -50,7 +50,7 @@ static struct ip_vs_conn * tcp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, const struct iphdr *iph, unsigned int proto_off, int inverse) { - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) @@ -112,12 +112,12 @@ tcp_conn_schedule(struct sk_buff *skb, static inline void -tcp_fast_csum_update(struct tcphdr *tcph, u32 oldip, u32 newip, - u16 oldport, u16 newport) +tcp_fast_csum_update(struct tcphdr *tcph, __be32 oldip, __be32 newip, + __be16 oldport, __be16 newport) { tcph->check = ip_vs_check_diff(~oldip, newip, - ip_vs_check_diff(oldport ^ 0xFFFF, + ip_vs_check_diff(oldport ^ htonl(0xFFFF), newport, tcph->check)); } diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c index 90c8166c0ec1..54aa7603591f 100644 --- a/net/ipv4/ipvs/ip_vs_proto_udp.c +++ b/net/ipv4/ipvs/ip_vs_proto_udp.c @@ -29,7 +29,7 @@ udp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, const struct iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) @@ -54,7 +54,7 @@ udp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, const struct iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; - __u16 _ports[2], *pptr; + __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_ports), _ports); @@ -117,15 +117,15 @@ udp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp, static inline void -udp_fast_csum_update(struct udphdr *uhdr, u32 oldip, u32 newip, - u16 oldport, u16 newport) +udp_fast_csum_update(struct udphdr *uhdr, __be32 oldip, __be32 newip, + __be16 oldport, __be16 newport) { uhdr->check = ip_vs_check_diff(~oldip, newip, - ip_vs_check_diff(oldport ^ 0xFFFF, + ip_vs_check_diff(oldport ^ htonl(0xFFFF), newport, uhdr->check)); if (!uhdr->check) - uhdr->check = 0xFFFF; + uhdr->check = htonl(0xFFFF); } static int @@ -173,7 +173,7 @@ udp_snat_handler(struct sk_buff **pskb, cp->protocol, (*pskb)->csum); if (udph->check == 0) - udph->check = 0xFFFF; + udph->check = htonl(0xFFFF); IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, udph->check, (char*)&(udph->check) - (char*)udph); diff --git a/net/ipv4/ipvs/ip_vs_sh.c b/net/ipv4/ipvs/ip_vs_sh.c index 7775e6cc68be..338668f88fe2 100644 --- a/net/ipv4/ipvs/ip_vs_sh.c +++ b/net/ipv4/ipvs/ip_vs_sh.c @@ -63,7 +63,7 @@ struct ip_vs_sh_bucket { /* * Returns hash value for IPVS SH entry */ -static inline unsigned ip_vs_sh_hashkey(__u32 addr) +static inline unsigned ip_vs_sh_hashkey(__be32 addr) { return (ntohl(addr)*2654435761UL) & IP_VS_SH_TAB_MASK; } @@ -73,7 +73,7 @@ static inline unsigned ip_vs_sh_hashkey(__u32 addr) * Get ip_vs_dest associated with supplied parameters. */ static inline struct ip_vs_dest * -ip_vs_sh_get(struct ip_vs_sh_bucket *tbl, __u32 addr) +ip_vs_sh_get(struct ip_vs_sh_bucket *tbl, __be32 addr) { return (tbl[ip_vs_sh_hashkey(addr)]).dest; } diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index 1bca714bda3d..91a075edd68e 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -48,16 +48,16 @@ struct ip_vs_sync_conn { /* Protocol, addresses and port numbers */ __u8 protocol; /* Which protocol (TCP/UDP) */ - __u16 cport; - __u16 vport; - __u16 dport; - __u32 caddr; /* client address */ - __u32 vaddr; /* virtual address */ - __u32 daddr; /* destination address */ + __be16 cport; + __be16 vport; + __be16 dport; + __be32 caddr; /* client address */ + __be32 vaddr; /* virtual address */ + __be32 daddr; /* destination address */ /* Flags and state transition */ - __u16 flags; /* status flags */ - __u16 state; /* state info */ + __be16 flags; /* status flags */ + __be16 state; /* state info */ /* The sequence options start here */ }; @@ -464,7 +464,7 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) static int bind_mcastif_addr(struct socket *sock, char *ifname) { struct net_device *dev; - u32 addr; + __be32 addr; struct sockaddr_in sin; if ((dev = __dev_get_by_name(ifname)) == NULL) @@ -836,7 +836,7 @@ static int fork_sync_thread(void *startup) int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) { - DECLARE_COMPLETION(startup); + DECLARE_COMPLETION_ONSTACK(startup); pid_t pid; if ((state == IP_VS_STATE_MASTER && sync_master_pid) || diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c index 52c12e9edbbc..e1f77bd7c9a5 100644 --- a/net/ipv4/ipvs/ip_vs_xmit.c +++ b/net/ipv4/ipvs/ip_vs_xmit.c @@ -232,7 +232,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* check if it is a connection of no-client-port */ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { - __u16 _pt, *p; + __be16 _pt, *p; p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt); if (p == NULL) goto tx_error; diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c index d25ec4ae09e5..92b04823e034 100644 --- a/net/ipv4/multipath_wrandom.c +++ b/net/ipv4/multipath_wrandom.c @@ -60,8 +60,8 @@ struct multipath_dest { struct list_head list; const struct fib_nh *nh_info; - __u32 netmask; - __u32 network; + __be32 netmask; + __be32 network; unsigned char prefixlen; struct rcu_head rcu; @@ -76,7 +76,7 @@ struct multipath_route { struct list_head list; int oif; - __u32 gw; + __be32 gw; struct list_head dests; struct rcu_head rcu; @@ -128,8 +128,8 @@ static unsigned char __multipath_lookup_weight(const struct flowi *fl, /* find state entry for destination */ list_for_each_entry_rcu(d, &target_route->dests, list) { - __u32 targetnetwork = fl->fl4_dst & - (0xFFFFFFFF >> (32 - d->prefixlen)); + __be32 targetnetwork = fl->fl4_dst & + inet_make_mask(d->prefixlen); if ((targetnetwork & d->netmask) == d->network) { weight = d->nh_info->nh_weight; @@ -217,8 +217,8 @@ static void wrandom_select_route(const struct flowi *flp, *rp = decision; } -static void wrandom_set_nhinfo(__u32 network, - __u32 netmask, +static void wrandom_set_nhinfo(__be32 network, + __be32 netmask, unsigned char prefixlen, const struct fib_nh *nh) { diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f88347de21a9..e2005c6810a4 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -8,7 +8,7 @@ #include <net/ip.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct sk_buff **pskb) +int ip_route_me_harder(struct sk_buff **pskb, unsigned addr_type) { struct iphdr *iph = (*pskb)->nh.iph; struct rtable *rt; @@ -16,10 +16,13 @@ int ip_route_me_harder(struct sk_buff **pskb) struct dst_entry *odst; unsigned int hh_len; + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(iph->saddr); + /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_IP_LOCAL_OUT hook. */ - if (inet_addr_type(iph->saddr) == RTN_LOCAL) { + if (addr_type == RTN_LOCAL) { fl.nl_u.ip4_u.daddr = iph->daddr; fl.nl_u.ip4_u.saddr = iph->saddr; fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); @@ -128,8 +131,8 @@ EXPORT_SYMBOL(ip_nat_decode_session); */ struct ip_rt_info { - u_int32_t daddr; - u_int32_t saddr; + __be32 daddr; + __be32 saddr; u_int8_t tos; }; @@ -156,7 +159,7 @@ static int nf_ip_reroute(struct sk_buff **pskb, const struct nf_info *info) if (!(iph->tos == rt_info->tos && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(pskb); + return ip_route_me_harder(pskb, RTN_UNSPEC); } return 0; } diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a55b8ff70ded..d88c292f118c 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -373,7 +373,7 @@ config IP_NF_TARGET_ULOG daemon using netlink multicast sockets; unlike the LOG target which can only be viewed through syslog. - The apropriate userspace logging daemon (ulogd) may be obtained from + The appropriate userspace logging daemon (ulogd) may be obtained from <http://www.gnumonks.org/projects/ulogd/> To compile it as a module, choose M here. If unsure, say N. diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 85f0d73ebfb4..0849f1cced13 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -80,7 +80,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr, { char *arpptr = (char *)(arphdr + 1); char *src_devaddr, *tgt_devaddr; - u32 src_ipaddr, tgt_ipaddr; + __be32 src_ipaddr, tgt_ipaddr; int i, ret; #define FWINV(bool,invflg) ((bool) ^ !!(arpinfo->invflags & invflg)) @@ -1196,6 +1196,8 @@ err1: static void __exit arp_tables_fini(void) { nf_unregister_sockopt(&arpt_sockopts); + xt_unregister_target(&arpt_error_target); + xt_unregister_target(&arpt_standard_target); xt_proto_fini(NF_ARP); } diff --git a/net/ipv4/netfilter/ip_conntrack_amanda.c b/net/ipv4/netfilter/ip_conntrack_amanda.c index 0a7bd7f04061..6c7383a8e42b 100644 --- a/net/ipv4/netfilter/ip_conntrack_amanda.c +++ b/net/ipv4/netfilter/ip_conntrack_amanda.c @@ -155,11 +155,11 @@ static int help(struct sk_buff **pskb, exp->tuple.dst.protonum = IPPROTO_TCP; exp->tuple.dst.u.tcp.port = htons(port); - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); exp->mask.dst.protonum = 0xFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.u.tcp.port = htons(0xFFFF); if (ip_nat_amanda_hook) ret = ip_nat_amanda_hook(pskb, ctinfo, off - dataoff, diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index c432b3163609..143c4668538b 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -149,8 +149,8 @@ static unsigned int ip_conntrack_hash_rnd; static u_int32_t __hash_conntrack(const struct ip_conntrack_tuple *tuple, unsigned int size, unsigned int rnd) { - return (jhash_3words(tuple->src.ip, - (tuple->dst.ip ^ tuple->dst.protonum), + return (jhash_3words((__force u32)tuple->src.ip, + ((__force u32)tuple->dst.ip ^ tuple->dst.protonum), (tuple->src.u.all | (tuple->dst.u.all << 16)), rnd) % size); } @@ -1169,9 +1169,9 @@ void __ip_ct_refresh_acct(struct ip_conntrack *ct, int ip_ct_port_tuple_to_nfattr(struct sk_buff *skb, const struct ip_conntrack_tuple *tuple) { - NFA_PUT(skb, CTA_PROTO_SRC_PORT, sizeof(u_int16_t), + NFA_PUT(skb, CTA_PROTO_SRC_PORT, sizeof(__be16), &tuple->src.u.tcp.port); - NFA_PUT(skb, CTA_PROTO_DST_PORT, sizeof(u_int16_t), + NFA_PUT(skb, CTA_PROTO_DST_PORT, sizeof(__be16), &tuple->dst.u.tcp.port); return 0; @@ -1186,9 +1186,9 @@ int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[], return -EINVAL; t->src.u.tcp.port = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_SRC_PORT-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTO_SRC_PORT-1]); t->dst.u.tcp.port = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_DST_PORT-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTO_DST_PORT-1]); return 0; } diff --git a/net/ipv4/netfilter/ip_conntrack_ftp.c b/net/ipv4/netfilter/ip_conntrack_ftp.c index 1d18c863f064..93dcf960662f 100644 --- a/net/ipv4/netfilter/ip_conntrack_ftp.c +++ b/net/ipv4/netfilter/ip_conntrack_ftp.c @@ -425,8 +425,8 @@ static int help(struct sk_buff **pskb, exp->tuple.src.u.tcp.port = 0; /* Don't care. */ exp->tuple.dst.protonum = IPPROTO_TCP; exp->mask = ((struct ip_conntrack_tuple) - { { 0xFFFFFFFF, { 0 } }, - { 0xFFFFFFFF, { .tcp = { 0xFFFF } }, 0xFF }}); + { { htonl(0xFFFFFFFF), { 0 } }, + { htonl(0xFFFFFFFF), { .tcp = { htons(0xFFFF) } }, 0xFF }}); exp->expectfn = NULL; exp->flags = 0; @@ -488,7 +488,7 @@ static int __init ip_conntrack_ftp_init(void) for (i = 0; i < ports_c; i++) { ftp[i].tuple.src.u.tcp.port = htons(ports[i]); ftp[i].tuple.dst.protonum = IPPROTO_TCP; - ftp[i].mask.src.u.tcp.port = 0xFFFF; + ftp[i].mask.src.u.tcp.port = htons(0xFFFF); ftp[i].mask.dst.protonum = 0xFF; ftp[i].max_expected = 1; ftp[i].timeout = 5 * 60; /* 5 minutes */ diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323.c b/net/ipv4/netfilter/ip_conntrack_helper_h323.c index 9a39e2969712..7b7441202bfd 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323.c @@ -49,11 +49,11 @@ MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations " int (*set_h245_addr_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, H245_TransportAddress * addr, - u_int32_t ip, u_int16_t port); + __be32 ip, u_int16_t port); int (*set_h225_addr_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, TransportAddress * addr, - u_int32_t ip, u_int16_t port); + __be32 ip, u_int16_t port); int (*set_sig_addr_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, enum ip_conntrack_info ctinfo, @@ -209,7 +209,7 @@ static int get_tpkt_data(struct sk_buff **pskb, struct ip_conntrack *ct, /****************************************************************************/ static int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, - u_int32_t * ip, u_int16_t * port) + __be32 * ip, u_int16_t * port) { unsigned char *p; @@ -232,7 +232,7 @@ static int expect_rtp_rtcp(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; u_int16_t rtp_port; struct ip_conntrack_expect *rtp_exp; @@ -254,10 +254,10 @@ static int expect_rtp_rtcp(struct sk_buff **pskb, struct ip_conntrack *ct, rtp_exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; rtp_exp->tuple.dst.u.udp.port = htons(rtp_port); rtp_exp->tuple.dst.protonum = IPPROTO_UDP; - rtp_exp->mask.src.ip = 0xFFFFFFFF; + rtp_exp->mask.src.ip = htonl(0xFFFFFFFF); rtp_exp->mask.src.u.udp.port = 0; - rtp_exp->mask.dst.ip = 0xFFFFFFFF; - rtp_exp->mask.dst.u.udp.port = 0xFFFF; + rtp_exp->mask.dst.ip = htonl(0xFFFFFFFF); + rtp_exp->mask.dst.u.udp.port = htons(0xFFFF); rtp_exp->mask.dst.protonum = 0xFF; rtp_exp->flags = 0; @@ -271,10 +271,10 @@ static int expect_rtp_rtcp(struct sk_buff **pskb, struct ip_conntrack *ct, rtcp_exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; rtcp_exp->tuple.dst.u.udp.port = htons(rtp_port + 1); rtcp_exp->tuple.dst.protonum = IPPROTO_UDP; - rtcp_exp->mask.src.ip = 0xFFFFFFFF; + rtcp_exp->mask.src.ip = htonl(0xFFFFFFFF); rtcp_exp->mask.src.u.udp.port = 0; - rtcp_exp->mask.dst.ip = 0xFFFFFFFF; - rtcp_exp->mask.dst.u.udp.port = 0xFFFF; + rtcp_exp->mask.dst.ip = htonl(0xFFFFFFFF); + rtcp_exp->mask.dst.u.udp.port = htons(0xFFFF); rtcp_exp->mask.dst.protonum = 0xFF; rtcp_exp->flags = 0; @@ -325,7 +325,7 @@ static int expect_t120(struct sk_buff **pskb, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp = NULL; @@ -342,10 +342,10 @@ static int expect_t120(struct sk_buff **pskb, exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = IP_CT_EXPECT_PERMANENT; /* Accept multiple channels */ @@ -626,7 +626,7 @@ void ip_conntrack_h245_expect(struct ip_conntrack *new, /****************************************************************************/ int get_h225_addr(unsigned char *data, TransportAddress * addr, - u_int32_t * ip, u_int16_t * port) + __be32 * ip, u_int16_t * port) { unsigned char *p; @@ -648,7 +648,7 @@ static int expect_h245(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp = NULL; @@ -665,10 +665,10 @@ static int expect_h245(struct sk_buff **pskb, struct ip_conntrack *ct, exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = 0; @@ -709,7 +709,7 @@ static int expect_callforwarding(struct sk_buff **pskb, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp = NULL; @@ -751,10 +751,10 @@ static int expect_callforwarding(struct sk_buff **pskb, exp->tuple.dst.ip = ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = 0; @@ -791,7 +791,7 @@ static int process_setup(struct sk_buff **pskb, struct ip_conntrack *ct, int dir = CTINFO2DIR(ctinfo); int ret; int i; - u_int32_t ip; + __be32 ip; u_int16_t port; DEBUGP("ip_ct_q931: Setup\n"); @@ -1188,7 +1188,7 @@ static unsigned char *get_udp_data(struct sk_buff **pskb, int *datalen) /****************************************************************************/ static struct ip_conntrack_expect *find_expect(struct ip_conntrack *ct, - u_int32_t ip, u_int16_t port) + __be32 ip, u_int16_t port) { struct ip_conntrack_expect *exp; struct ip_conntrack_tuple tuple; @@ -1228,7 +1228,7 @@ static int expect_q931(struct sk_buff **pskb, struct ip_conntrack *ct, int dir = CTINFO2DIR(ctinfo); int ret = 0; int i; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp; @@ -1251,10 +1251,10 @@ static int expect_q931(struct sk_buff **pskb, struct ip_conntrack *ct, exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = gkrouted_only ? 0xFFFFFFFF : 0; + exp->mask.src.ip = gkrouted_only ? htonl(0xFFFFFFFF) : 0; exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = IP_CT_EXPECT_PERMANENT; /* Accept multiple calls */ @@ -1307,7 +1307,7 @@ static int process_gcf(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp; @@ -1333,10 +1333,10 @@ static int process_gcf(struct sk_buff **pskb, struct ip_conntrack *ct, exp->tuple.dst.ip = ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_UDP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = 0; exp->expectfn = ip_conntrack_ras_expect; @@ -1477,7 +1477,7 @@ static int process_arq(struct sk_buff **pskb, struct ip_conntrack *ct, { struct ip_ct_h323_master *info = &ct->help.ct_h323_info; int dir = CTINFO2DIR(ctinfo); - u_int32_t ip; + __be32 ip; u_int16_t port; DEBUGP("ip_ct_ras: ARQ\n"); @@ -1513,7 +1513,7 @@ static int process_acf(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp; @@ -1538,10 +1538,10 @@ static int process_acf(struct sk_buff **pskb, struct ip_conntrack *ct, exp->tuple.dst.ip = ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = IP_CT_EXPECT_PERMANENT; exp->expectfn = ip_conntrack_q931_expect; @@ -1581,7 +1581,7 @@ static int process_lcf(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int ret = 0; - u_int32_t ip; + __be32 ip; u_int16_t port; struct ip_conntrack_expect *exp = NULL; @@ -1598,10 +1598,10 @@ static int process_lcf(struct sk_buff **pskb, struct ip_conntrack *ct, exp->tuple.dst.ip = ip; exp->tuple.dst.u.tcp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_TCP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.tcp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.tcp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->flags = IP_CT_EXPECT_PERMANENT; exp->expectfn = ip_conntrack_q931_expect; diff --git a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c index fb0aee691721..a2af5e0c7f99 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c @@ -242,10 +242,10 @@ exp_gre(struct ip_conntrack *ct, exp_orig->tuple.dst.u.gre.key = callid; exp_orig->tuple.dst.protonum = IPPROTO_GRE; - exp_orig->mask.src.ip = 0xffffffff; + exp_orig->mask.src.ip = htonl(0xffffffff); exp_orig->mask.src.u.all = 0; exp_orig->mask.dst.u.gre.key = htons(0xffff); - exp_orig->mask.dst.ip = 0xffffffff; + exp_orig->mask.dst.ip = htonl(0xffffffff); exp_orig->mask.dst.protonum = 0xff; exp_orig->master = ct; diff --git a/net/ipv4/netfilter/ip_conntrack_irc.c b/net/ipv4/netfilter/ip_conntrack_irc.c index 44889075f3b2..75f7c3db1619 100644 --- a/net/ipv4/netfilter/ip_conntrack_irc.c +++ b/net/ipv4/netfilter/ip_conntrack_irc.c @@ -218,7 +218,8 @@ static int help(struct sk_buff **pskb, IPPROTO_TCP }}); exp->mask = ((struct ip_conntrack_tuple) { { 0, { 0 } }, - { 0xFFFFFFFF, { .tcp = { 0xFFFF } }, 0xFF }}); + { htonl(0xFFFFFFFF), + { .tcp = { htons(0xFFFF) } }, 0xFF }}); exp->expectfn = NULL; exp->flags = 0; if (ip_nat_irc_hook) @@ -266,7 +267,7 @@ static int __init ip_conntrack_irc_init(void) hlpr = &irc_helpers[i]; hlpr->tuple.src.u.tcp.port = htons(ports[i]); hlpr->tuple.dst.protonum = IPPROTO_TCP; - hlpr->mask.src.u.tcp.port = 0xFFFF; + hlpr->mask.src.u.tcp.port = htons(0xFFFF); hlpr->mask.dst.protonum = 0xFF; hlpr->max_expected = max_dcc_channels; hlpr->timeout = dcc_timeout; diff --git a/net/ipv4/netfilter/ip_conntrack_netbios_ns.c b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c index 3d0b438783db..a1d6a89f64aa 100644 --- a/net/ipv4/netfilter/ip_conntrack_netbios_ns.c +++ b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c @@ -48,7 +48,7 @@ static int help(struct sk_buff **pskb, struct iphdr *iph = (*pskb)->nh.iph; struct rtable *rt = (struct rtable *)(*pskb)->dst; struct in_device *in_dev; - u_int32_t mask = 0; + __be32 mask = 0; /* we're only interested in locally generated packets */ if ((*pskb)->sk == NULL) @@ -78,12 +78,12 @@ static int help(struct sk_buff **pskb, goto out; exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - exp->tuple.src.u.udp.port = ntohs(NMBD_PORT); + exp->tuple.src.u.udp.port = htons(NMBD_PORT); exp->mask.src.ip = mask; - exp->mask.src.u.udp.port = 0xFFFF; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.udp.port = 0xFFFF; + exp->mask.src.u.udp.port = htons(0xFFFF); + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.udp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->expectfn = NULL; @@ -115,7 +115,7 @@ static struct ip_conntrack_helper helper = { .src = { .u = { .udp = { - .port = 0xFFFF, + .port = __constant_htons(0xFFFF), } } }, diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index 52eddea27e93..262d0d44ec1b 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -44,13 +44,6 @@ MODULE_LICENSE("GPL"); static char __initdata version[] = "0.90"; -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - - static inline int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct ip_conntrack_tuple *tuple, @@ -78,8 +71,8 @@ ctnetlink_dump_tuples_ip(struct sk_buff *skb, { struct nfattr *nest_parms = NFA_NEST(skb, CTA_TUPLE_IP); - NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t), &tuple->src.ip); - NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t), &tuple->dst.ip); + NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(__be32), &tuple->src.ip); + NFA_PUT(skb, CTA_IP_V4_DST, sizeof(__be32), &tuple->dst.ip); NFA_NEST_END(skb, nest_parms); @@ -110,7 +103,7 @@ ctnetlink_dump_tuples(struct sk_buff *skb, static inline int ctnetlink_dump_status(struct sk_buff *skb, const struct ip_conntrack *ct) { - u_int32_t status = htonl((u_int32_t) ct->status); + __be32 status = htonl((u_int32_t) ct->status); NFA_PUT(skb, CTA_STATUS, sizeof(status), &status); return 0; @@ -122,7 +115,7 @@ static inline int ctnetlink_dump_timeout(struct sk_buff *skb, const struct ip_conntrack *ct) { long timeout_l = ct->timeout.expires - jiffies; - u_int32_t timeout; + __be32 timeout; if (timeout_l < 0) timeout = 0; @@ -192,13 +185,13 @@ ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *ct, { enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nfattr *nest_count = NFA_NEST(skb, type); - u_int32_t tmp; + __be32 tmp; tmp = htonl(ct->counters[dir].packets); - NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp); + NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(__be32), &tmp); tmp = htonl(ct->counters[dir].bytes); - NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(u_int32_t), &tmp); + NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(__be32), &tmp); NFA_NEST_END(skb, nest_count); @@ -215,9 +208,9 @@ nfattr_failure: static inline int ctnetlink_dump_mark(struct sk_buff *skb, const struct ip_conntrack *ct) { - u_int32_t mark = htonl(ct->mark); + __be32 mark = htonl(ct->mark); - NFA_PUT(skb, CTA_MARK, sizeof(u_int32_t), &mark); + NFA_PUT(skb, CTA_MARK, sizeof(__be32), &mark); return 0; nfattr_failure: @@ -230,8 +223,8 @@ nfattr_failure: static inline int ctnetlink_dump_id(struct sk_buff *skb, const struct ip_conntrack *ct) { - u_int32_t id = htonl(ct->id); - NFA_PUT(skb, CTA_ID, sizeof(u_int32_t), &id); + __be32 id = htonl(ct->id); + NFA_PUT(skb, CTA_ID, sizeof(__be32), &id); return 0; nfattr_failure: @@ -241,9 +234,9 @@ nfattr_failure: static inline int ctnetlink_dump_use(struct sk_buff *skb, const struct ip_conntrack *ct) { - u_int32_t use = htonl(atomic_read(&ct->ct_general.use)); + __be32 use = htonl(atomic_read(&ct->ct_general.use)); - NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use); + NFA_PUT(skb, CTA_USE, sizeof(__be32), &use); return 0; nfattr_failure: @@ -398,7 +391,6 @@ nfattr_failure: static int ctnetlink_done(struct netlink_callback *cb) { - DEBUGP("entered %s\n", __FUNCTION__); if (cb->args[1]) ip_conntrack_put((struct ip_conntrack *)cb->args[1]); return 0; @@ -411,9 +403,6 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct ip_conntrack_tuple_hash *h; struct list_head *i; - DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, - cb->args[0], *id); - read_lock_bh(&ip_conntrack_lock); last = (struct ip_conntrack *)cb->args[1]; for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++) { @@ -452,13 +441,12 @@ out: if (last) ip_conntrack_put(last); - DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); return skb->len; } static const size_t cta_min_ip[CTA_IP_MAX] = { - [CTA_IP_V4_SRC-1] = sizeof(u_int32_t), - [CTA_IP_V4_DST-1] = sizeof(u_int32_t), + [CTA_IP_V4_SRC-1] = sizeof(__be32), + [CTA_IP_V4_DST-1] = sizeof(__be32), }; static inline int @@ -466,8 +454,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple) { struct nfattr *tb[CTA_IP_MAX]; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_IP_MAX, attr); if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip)) @@ -475,13 +461,11 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple) if (!tb[CTA_IP_V4_SRC-1]) return -EINVAL; - tuple->src.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_SRC-1]); + tuple->src.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_SRC-1]); if (!tb[CTA_IP_V4_DST-1]) return -EINVAL; - tuple->dst.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_DST-1]); - - DEBUGP("leaving\n"); + tuple->dst.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_DST-1]); return 0; } @@ -503,8 +487,6 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr, struct ip_conntrack_protocol *proto; int ret = 0; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_PROTO_MAX, attr); if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto)) @@ -531,8 +513,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple, struct nfattr *tb[CTA_TUPLE_MAX]; int err; - DEBUGP("entered %s\n", __FUNCTION__); - memset(tuple, 0, sizeof(*tuple)); nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]); @@ -557,10 +537,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple, else tuple->dst.dir = IP_CT_DIR_ORIGINAL; - DUMP_TUPLE(tuple); - - DEBUGP("leaving\n"); - return 0; } @@ -577,8 +553,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr, struct nfattr *tb[CTA_PROTONAT_MAX]; struct ip_nat_protocol *npt; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr); if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat)) @@ -597,13 +571,12 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr, ip_nat_proto_put(npt); - DEBUGP("leaving\n"); return 0; } static const size_t cta_min_nat[CTA_NAT_MAX] = { - [CTA_NAT_MINIP-1] = sizeof(u_int32_t), - [CTA_NAT_MAXIP-1] = sizeof(u_int32_t), + [CTA_NAT_MINIP-1] = sizeof(__be32), + [CTA_NAT_MAXIP-1] = sizeof(__be32), }; static inline int @@ -613,8 +586,6 @@ ctnetlink_parse_nat(struct nfattr *nat, struct nfattr *tb[CTA_NAT_MAX]; int err; - DEBUGP("entered %s\n", __FUNCTION__); - memset(range, 0, sizeof(*range)); nfattr_parse_nested(tb, CTA_NAT_MAX, nat); @@ -623,12 +594,12 @@ ctnetlink_parse_nat(struct nfattr *nat, return -EINVAL; if (tb[CTA_NAT_MINIP-1]) - range->min_ip = *(u_int32_t *)NFA_DATA(tb[CTA_NAT_MINIP-1]); + range->min_ip = *(__be32 *)NFA_DATA(tb[CTA_NAT_MINIP-1]); if (!tb[CTA_NAT_MAXIP-1]) range->max_ip = range->min_ip; else - range->max_ip = *(u_int32_t *)NFA_DATA(tb[CTA_NAT_MAXIP-1]); + range->max_ip = *(__be32 *)NFA_DATA(tb[CTA_NAT_MAXIP-1]); if (range->min_ip) range->flags |= IP_NAT_RANGE_MAP_IPS; @@ -640,7 +611,6 @@ ctnetlink_parse_nat(struct nfattr *nat, if (err < 0) return err; - DEBUGP("leaving\n"); return 0; } #endif @@ -650,8 +620,6 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name) { struct nfattr *tb[CTA_HELP_MAX]; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_HELP_MAX, attr); if (!tb[CTA_HELP_NAME-1]) @@ -663,11 +631,11 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name) } static const size_t cta_min[CTA_MAX] = { - [CTA_STATUS-1] = sizeof(u_int32_t), - [CTA_TIMEOUT-1] = sizeof(u_int32_t), - [CTA_MARK-1] = sizeof(u_int32_t), - [CTA_USE-1] = sizeof(u_int32_t), - [CTA_ID-1] = sizeof(u_int32_t) + [CTA_STATUS-1] = sizeof(__be32), + [CTA_TIMEOUT-1] = sizeof(__be32), + [CTA_MARK-1] = sizeof(__be32), + [CTA_USE-1] = sizeof(__be32), + [CTA_ID-1] = sizeof(__be32) }; static int @@ -679,8 +647,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, struct ip_conntrack *ct; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_MAX, cta_min)) return -EINVAL; @@ -698,15 +664,13 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; h = ip_conntrack_find_get(&tuple, NULL); - if (!h) { - DEBUGP("tuple not found in conntrack hash\n"); + if (!h) return -ENOENT; - } ct = tuplehash_to_ctrack(h); if (cda[CTA_ID-1]) { - u_int32_t id = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_ID-1])); + u_int32_t id = ntohl(*(__be32 *)NFA_DATA(cda[CTA_ID-1])); if (ct->id != id) { ip_conntrack_put(ct); return -ENOENT; @@ -716,7 +680,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, ct->timeout.function((unsigned long)ct); ip_conntrack_put(ct); - DEBUGP("leaving\n"); return 0; } @@ -731,8 +694,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2 = NULL; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nlh->nlmsg_flags & NLM_F_DUMP) { struct nfgenmsg *msg = NLMSG_DATA(nlh); u32 rlen; @@ -770,11 +731,9 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; h = ip_conntrack_find_get(&tuple, NULL); - if (!h) { - DEBUGP("tuple not found in conntrack hash"); + if (!h) return -ENOENT; - } - DEBUGP("tuple found\n"); + ct = tuplehash_to_ctrack(h); err = -ENOMEM; @@ -795,7 +754,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) goto out; - DEBUGP("leaving\n"); return 0; free: @@ -808,7 +766,7 @@ static inline int ctnetlink_change_status(struct ip_conntrack *ct, struct nfattr *cda[]) { unsigned long d; - unsigned status = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_STATUS-1])); + unsigned status = ntohl(*(__be32 *)NFA_DATA(cda[CTA_STATUS-1])); d = ct->status ^ status; if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) @@ -866,8 +824,6 @@ ctnetlink_change_helper(struct ip_conntrack *ct, struct nfattr *cda[]) char *helpname; int err; - DEBUGP("entered %s\n", __FUNCTION__); - /* don't change helper of sibling connections */ if (ct->master) return -EINVAL; @@ -903,7 +859,7 @@ ctnetlink_change_helper(struct ip_conntrack *ct, struct nfattr *cda[]) static inline int ctnetlink_change_timeout(struct ip_conntrack *ct, struct nfattr *cda[]) { - u_int32_t timeout = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_TIMEOUT-1])); + u_int32_t timeout = ntohl(*(__be32 *)NFA_DATA(cda[CTA_TIMEOUT-1])); if (!del_timer(&ct->timeout)) return -ETIME; @@ -938,8 +894,6 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[]) { int err; - DEBUGP("entered %s\n", __FUNCTION__); - if (cda[CTA_HELP-1]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) @@ -966,10 +920,9 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[]) #if defined(CONFIG_IP_NF_CONNTRACK_MARK) if (cda[CTA_MARK-1]) - ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); + ct->mark = ntohl(*(__be32 *)NFA_DATA(cda[CTA_MARK-1])); #endif - DEBUGP("all done\n"); return 0; } @@ -981,15 +934,13 @@ ctnetlink_create_conntrack(struct nfattr *cda[], struct ip_conntrack *ct; int err = -EINVAL; - DEBUGP("entered %s\n", __FUNCTION__); - ct = ip_conntrack_alloc(otuple, rtuple); if (ct == NULL || IS_ERR(ct)) return -ENOMEM; if (!cda[CTA_TIMEOUT-1]) goto err; - ct->timeout.expires = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_TIMEOUT-1])); + ct->timeout.expires = ntohl(*(__be32 *)NFA_DATA(cda[CTA_TIMEOUT-1])); ct->timeout.expires = jiffies + ct->timeout.expires * HZ; ct->status |= IPS_CONFIRMED; @@ -1006,7 +957,7 @@ ctnetlink_create_conntrack(struct nfattr *cda[], #if defined(CONFIG_IP_NF_CONNTRACK_MARK) if (cda[CTA_MARK-1]) - ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); + ct->mark = ntohl(*(__be32 *)NFA_DATA(cda[CTA_MARK-1])); #endif ct->helper = ip_conntrack_helper_find_get(rtuple); @@ -1017,7 +968,6 @@ ctnetlink_create_conntrack(struct nfattr *cda[], if (ct->helper) ip_conntrack_helper_put(ct->helper); - DEBUGP("conntrack with id %u inserted\n", ct->id); return 0; err: @@ -1033,8 +983,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct ip_conntrack_tuple_hash *h = NULL; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_MAX, cta_min)) return -EINVAL; @@ -1058,7 +1006,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (h == NULL) { write_unlock_bh(&ip_conntrack_lock); - DEBUGP("no such conntrack, create new\n"); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) err = ctnetlink_create_conntrack(cda, &otuple, &rtuple); @@ -1074,7 +1021,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, /* We manipulate the conntrack inside the global conntrack table lock, * so there's no need to increase the refcount */ - DEBUGP("conntrack found\n"); err = -EEXIST; if (!(nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_conntrack(tuplehash_to_ctrack(h), cda); @@ -1138,8 +1084,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct ip_conntrack_expect *exp) { struct ip_conntrack *master = exp->master; - u_int32_t timeout = htonl((exp->timeout.expires - jiffies) / HZ); - u_int32_t id = htonl(exp->id); + __be32 timeout = htonl((exp->timeout.expires - jiffies) / HZ); + __be32 id = htonl(exp->id); if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nfattr_failure; @@ -1150,8 +1096,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, CTA_EXPECT_MASTER) < 0) goto nfattr_failure; - NFA_PUT(skb, CTA_EXPECT_TIMEOUT, sizeof(timeout), &timeout); - NFA_PUT(skb, CTA_EXPECT_ID, sizeof(u_int32_t), &id); + NFA_PUT(skb, CTA_EXPECT_TIMEOUT, sizeof(__be32), &timeout); + NFA_PUT(skb, CTA_EXPECT_ID, sizeof(__be32), &id); return 0; @@ -1249,8 +1195,6 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct list_head *i; u_int32_t *id = (u_int32_t *) &cb->args[0]; - DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id); - read_lock_bh(&ip_conntrack_lock); list_for_each_prev(i, &ip_conntrack_expect_list) { exp = (struct ip_conntrack_expect *) i; @@ -1266,14 +1210,12 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) out: read_unlock_bh(&ip_conntrack_lock); - DEBUGP("leaving, last id=%llu\n", *id); - return skb->len; } static const size_t cta_min_exp[CTA_EXPECT_MAX] = { - [CTA_EXPECT_TIMEOUT-1] = sizeof(u_int32_t), - [CTA_EXPECT_ID-1] = sizeof(u_int32_t) + [CTA_EXPECT_TIMEOUT-1] = sizeof(__be32), + [CTA_EXPECT_ID-1] = sizeof(__be32) }; static int @@ -1285,8 +1227,6 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) return -EINVAL; @@ -1321,7 +1261,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, return -ENOENT; if (cda[CTA_EXPECT_ID-1]) { - u_int32_t id = *(u_int32_t *)NFA_DATA(cda[CTA_EXPECT_ID-1]); + __be32 id = *(__be32 *)NFA_DATA(cda[CTA_EXPECT_ID-1]); if (exp->id != ntohl(id)) { ip_conntrack_expect_put(exp); return -ENOENT; @@ -1375,8 +1315,8 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, return -ENOENT; if (cda[CTA_EXPECT_ID-1]) { - u_int32_t id = - *(u_int32_t *)NFA_DATA(cda[CTA_EXPECT_ID-1]); + __be32 id = + *(__be32 *)NFA_DATA(cda[CTA_EXPECT_ID-1]); if (exp->id != ntohl(id)) { ip_conntrack_expect_put(exp); return -ENOENT; @@ -1437,8 +1377,6 @@ ctnetlink_create_expect(struct nfattr *cda[]) struct ip_conntrack *ct; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE); if (err < 0) @@ -1490,8 +1428,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, struct ip_conntrack_expect *exp; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) return -EINVAL; @@ -1520,8 +1456,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, err = ctnetlink_change_expect(exp, cda); write_unlock_bh(&ip_conntrack_lock); - DEBUGP("leaving\n"); - return err; } diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index 09c40ebe3345..295b6fa340db 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -261,7 +261,7 @@ icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, static int icmp_tuple_to_nfattr(struct sk_buff *skb, const struct ip_conntrack_tuple *t) { - NFA_PUT(skb, CTA_PROTO_ICMP_ID, sizeof(u_int16_t), + NFA_PUT(skb, CTA_PROTO_ICMP_ID, sizeof(__be16), &t->src.u.icmp.id); NFA_PUT(skb, CTA_PROTO_ICMP_TYPE, sizeof(u_int8_t), &t->dst.u.icmp.type); @@ -287,7 +287,7 @@ static int icmp_nfattr_to_tuple(struct nfattr *tb[], tuple->dst.u.icmp.code = *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_CODE-1]); tuple->src.u.icmp.id = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_ICMP_ID-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTO_ICMP_ID-1]); if (tuple->dst.u.icmp.type >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type]) diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c index b908a4842e18..2443322e4128 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c @@ -210,7 +210,7 @@ static int sctp_print_conntrack(struct seq_file *s, for (offset = skb->nh.iph->ihl * 4 + sizeof(sctp_sctphdr_t), count = 0; \ offset < skb->len && \ (sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch)); \ - offset += (htons(sch->length) + 3) & ~3, count++) + offset += (ntohs(sch->length) + 3) & ~3, count++) /* Some validity checks to make sure the chunks are fine */ static int do_basic_checks(struct ip_conntrack *conntrack, diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index 03ae9a04cb37..06e4e8a6dd9f 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -519,8 +519,8 @@ static void tcp_sack(const struct sk_buff *skb, /* Fast path for timestamp-only option */ if (length == TCPOLEN_TSTAMP_ALIGNED*4 - && *(__u32 *)ptr == - __constant_ntohl((TCPOPT_NOP << 24) + && *(__be32 *)ptr == + __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) @@ -551,7 +551,7 @@ static void tcp_sack(const struct sk_buff *skb, for (i = 0; i < (opsize - TCPOLEN_SACK_BASE); i += TCPOLEN_SACK_PERBLOCK) { - tmp = ntohl(*((u_int32_t *)(ptr+i)+1)); + tmp = ntohl(*((__be32 *)(ptr+i)+1)); if (after(tmp, *sack)) *sack = tmp; diff --git a/net/ipv4/netfilter/ip_conntrack_sip.c b/net/ipv4/netfilter/ip_conntrack_sip.c index 2893e9c74850..f4f75995a9e4 100644 --- a/net/ipv4/netfilter/ip_conntrack_sip.c +++ b/net/ipv4/netfilter/ip_conntrack_sip.c @@ -193,7 +193,7 @@ static int skp_digits_len(const char *dptr, const char *limit, int *shift) /* Simple ipaddr parser.. */ static int parse_ipaddr(const char *cp, const char **endp, - u_int32_t *ipaddr, const char *limit) + __be32 *ipaddr, const char *limit) { unsigned long int val; int i, digit = 0; @@ -227,7 +227,7 @@ static int parse_ipaddr(const char *cp, const char **endp, static int epaddr_len(const char *dptr, const char *limit, int *shift) { const char *aux = dptr; - u_int32_t ip; + __be32 ip; if (parse_ipaddr(dptr, &dptr, &ip, limit) < 0) { DEBUGP("ip: %s parse failed.!\n", dptr); @@ -302,7 +302,7 @@ int ct_sip_get_info(const char *dptr, size_t dlen, static int set_expected_rtp(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo, - u_int32_t ipaddr, u_int16_t port, + __be32 ipaddr, u_int16_t port, const char *dptr) { struct ip_conntrack_expect *exp; @@ -319,10 +319,10 @@ static int set_expected_rtp(struct sk_buff **pskb, exp->tuple.dst.u.udp.port = htons(port); exp->tuple.dst.protonum = IPPROTO_UDP; - exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.ip = htonl(0xFFFFFFFF); exp->mask.src.u.udp.port = 0; - exp->mask.dst.ip = 0xFFFFFFFF; - exp->mask.dst.u.udp.port = 0xFFFF; + exp->mask.dst.ip = htonl(0xFFFFFFFF); + exp->mask.dst.u.udp.port = htons(0xFFFF); exp->mask.dst.protonum = 0xFF; exp->expectfn = NULL; @@ -349,7 +349,7 @@ static int sip_help(struct sk_buff **pskb, const char *dptr; int ret = NF_ACCEPT; int matchoff, matchlen; - u_int32_t ipaddr; + __be32 ipaddr; u_int16_t port; /* No Data ? */ @@ -439,7 +439,7 @@ static int __init init(void) sip[i].tuple.dst.protonum = IPPROTO_UDP; sip[i].tuple.src.u.udp.port = htons(ports[i]); - sip[i].mask.src.u.udp.port = 0xFFFF; + sip[i].mask.src.u.udp.port = htons(0xFFFF); sip[i].mask.dst.protonum = 0xFF; sip[i].max_expected = 2; sip[i].timeout = 3 * 60; /* 3 minutes */ diff --git a/net/ipv4/netfilter/ip_conntrack_tftp.c b/net/ipv4/netfilter/ip_conntrack_tftp.c index 7e33d3bed5e3..fe0b634dd377 100644 --- a/net/ipv4/netfilter/ip_conntrack_tftp.c +++ b/net/ipv4/netfilter/ip_conntrack_tftp.c @@ -70,10 +70,10 @@ static int tftp_help(struct sk_buff **pskb, return NF_DROP; exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - exp->mask.src.ip = 0xffffffff; + exp->mask.src.ip = htonl(0xffffffff); exp->mask.src.u.udp.port = 0; - exp->mask.dst.ip = 0xffffffff; - exp->mask.dst.u.udp.port = 0xffff; + exp->mask.dst.ip = htonl(0xffffffff); + exp->mask.dst.u.udp.port = htons(0xffff); exp->mask.dst.protonum = 0xff; exp->expectfn = NULL; exp->flags = 0; @@ -129,7 +129,7 @@ static int __init ip_conntrack_tftp_init(void) tftp[i].tuple.dst.protonum = IPPROTO_UDP; tftp[i].tuple.src.u.udp.port = htons(ports[i]); tftp[i].mask.dst.protonum = 0xFF; - tftp[i].mask.src.u.udp.port = 0xFFFF; + tftp[i].mask.src.u.udp.port = htons(0xFFFF); tftp[i].max_expected = 1; tftp[i].timeout = 5 * 60; /* 5 minutes */ tftp[i].me = THIS_MODULE; diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index 71f3e09cbc84..4b6260a97408 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -82,7 +82,7 @@ static inline unsigned int hash_by_src(const struct ip_conntrack_tuple *tuple) { /* Original src, to ensure we map it consistently if poss. */ - return jhash_3words(tuple->src.ip, tuple->src.u.all, + return jhash_3words((__force u32)tuple->src.ip, tuple->src.u.all, tuple->dst.protonum, 0) % ip_nat_htable_size; } @@ -190,7 +190,7 @@ find_best_ips_proto(struct ip_conntrack_tuple *tuple, const struct ip_conntrack *conntrack, enum ip_nat_manip_type maniptype) { - u_int32_t *var_ipp; + __be32 *var_ipp; /* Host order */ u_int32_t minip, maxip, j; @@ -217,7 +217,7 @@ find_best_ips_proto(struct ip_conntrack_tuple *tuple, * like this), even across reboots. */ minip = ntohl(range->min_ip); maxip = ntohl(range->max_ip); - j = jhash_2words(tuple->src.ip, tuple->dst.ip, 0); + j = jhash_2words((__force u32)tuple->src.ip, (__force u32)tuple->dst.ip, 0); *var_ipp = htonl(minip + j % (maxip - minip + 1)); } @@ -534,9 +534,9 @@ int ip_nat_port_range_to_nfattr(struct sk_buff *skb, const struct ip_nat_range *range) { - NFA_PUT(skb, CTA_PROTONAT_PORT_MIN, sizeof(u_int16_t), + NFA_PUT(skb, CTA_PROTONAT_PORT_MIN, sizeof(__be16), &range->min.tcp.port); - NFA_PUT(skb, CTA_PROTONAT_PORT_MAX, sizeof(u_int16_t), + NFA_PUT(skb, CTA_PROTONAT_PORT_MAX, sizeof(__be16), &range->max.tcp.port); return 0; @@ -555,7 +555,7 @@ ip_nat_port_nfattr_to_range(struct nfattr *tb[], struct ip_nat_range *range) if (tb[CTA_PROTONAT_PORT_MIN-1]) { ret = 1; range->min.tcp.port = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MIN-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTONAT_PORT_MIN-1]); } if (!tb[CTA_PROTONAT_PORT_MAX-1]) { @@ -564,7 +564,7 @@ ip_nat_port_nfattr_to_range(struct nfattr *tb[], struct ip_nat_range *range) } else { ret = 1; range->max.tcp.port = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MAX-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTONAT_PORT_MAX-1]); } return ret; diff --git a/net/ipv4/netfilter/ip_nat_ftp.c b/net/ipv4/netfilter/ip_nat_ftp.c index 3328fc5c5f50..a71c233d8112 100644 --- a/net/ipv4/netfilter/ip_nat_ftp.c +++ b/net/ipv4/netfilter/ip_nat_ftp.c @@ -34,7 +34,7 @@ MODULE_DESCRIPTION("ftp NAT helper"); static int mangle_rfc959_packet(struct sk_buff **pskb, - u_int32_t newip, + __be32 newip, u_int16_t port, unsigned int matchoff, unsigned int matchlen, @@ -57,7 +57,7 @@ mangle_rfc959_packet(struct sk_buff **pskb, /* |1|132.235.1.2|6275| */ static int mangle_eprt_packet(struct sk_buff **pskb, - u_int32_t newip, + __be32 newip, u_int16_t port, unsigned int matchoff, unsigned int matchlen, @@ -79,7 +79,7 @@ mangle_eprt_packet(struct sk_buff **pskb, /* |1|132.235.1.2|6275| */ static int mangle_epsv_packet(struct sk_buff **pskb, - u_int32_t newip, + __be32 newip, u_int16_t port, unsigned int matchoff, unsigned int matchlen, @@ -98,7 +98,7 @@ mangle_epsv_packet(struct sk_buff **pskb, matchlen, buffer, strlen(buffer)); } -static int (*mangle[])(struct sk_buff **, u_int32_t, u_int16_t, +static int (*mangle[])(struct sk_buff **, __be32, u_int16_t, unsigned int, unsigned int, struct ip_conntrack *, @@ -120,7 +120,7 @@ static unsigned int ip_nat_ftp(struct sk_buff **pskb, struct ip_conntrack_expect *exp, u32 *seq) { - u_int32_t newip; + __be32 newip; u_int16_t port; int dir = CTINFO2DIR(ctinfo); struct ip_conntrack *ct = exp->master; diff --git a/net/ipv4/netfilter/ip_nat_helper.c b/net/ipv4/netfilter/ip_nat_helper.c index 7f6a75984f6c..3bf858480558 100644 --- a/net/ipv4/netfilter/ip_nat_helper.c +++ b/net/ipv4/netfilter/ip_nat_helper.c @@ -189,7 +189,7 @@ ip_nat_mangle_tcp_packet(struct sk_buff **pskb, datalen, 0)); } else tcph->check = nf_proto_csum_update(*pskb, - htons(oldlen) ^ 0xFFFF, + htons(oldlen) ^ htons(0xFFFF), htons(datalen), tcph->check, 1); @@ -267,7 +267,7 @@ ip_nat_mangle_udp_packet(struct sk_buff **pskb, udph->check = -1; } else udph->check = nf_proto_csum_update(*pskb, - htons(oldlen) ^ 0xFFFF, + htons(oldlen) ^ htons(0xFFFF), htons(datalen), udph->check, 1); return 1; @@ -283,27 +283,25 @@ sack_adjust(struct sk_buff *skb, struct ip_nat_seq *natseq) { while (sackoff < sackend) { - struct tcp_sack_block *sack; - u_int32_t new_start_seq, new_end_seq; + struct tcp_sack_block_wire *sack; + __be32 new_start_seq, new_end_seq; sack = (void *)skb->data + sackoff; if (after(ntohl(sack->start_seq) - natseq->offset_before, natseq->correction_pos)) - new_start_seq = ntohl(sack->start_seq) - - natseq->offset_after; + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_after); else - new_start_seq = ntohl(sack->start_seq) - - natseq->offset_before; - new_start_seq = htonl(new_start_seq); + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_before); if (after(ntohl(sack->end_seq) - natseq->offset_before, natseq->correction_pos)) - new_end_seq = ntohl(sack->end_seq) - - natseq->offset_after; + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_after); else - new_end_seq = ntohl(sack->end_seq) - - natseq->offset_before; - new_end_seq = htonl(new_end_seq); + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_before); DEBUGP("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", ntohl(sack->start_seq), new_start_seq, @@ -375,7 +373,8 @@ ip_nat_seq_adjust(struct sk_buff **pskb, enum ip_conntrack_info ctinfo) { struct tcphdr *tcph; - int dir, newseq, newack; + int dir; + __be32 newseq, newack; struct ip_nat_seq *this_way, *other_way; dir = CTINFO2DIR(ctinfo); @@ -388,17 +387,15 @@ ip_nat_seq_adjust(struct sk_buff **pskb, tcph = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; if (after(ntohl(tcph->seq), this_way->correction_pos)) - newseq = ntohl(tcph->seq) + this_way->offset_after; + newseq = htonl(ntohl(tcph->seq) + this_way->offset_after); else - newseq = ntohl(tcph->seq) + this_way->offset_before; - newseq = htonl(newseq); + newseq = htonl(ntohl(tcph->seq) + this_way->offset_before); if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) - newack = ntohl(tcph->ack_seq) - other_way->offset_after; + newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after); else - newack = ntohl(tcph->ack_seq) - other_way->offset_before; - newack = htonl(newack); + newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before); tcph->check = nf_proto_csum_update(*pskb, ~tcph->seq, newseq, tcph->check, 0); diff --git a/net/ipv4/netfilter/ip_nat_helper_h323.c b/net/ipv4/netfilter/ip_nat_helper_h323.c index 419b878fb467..4a7d34466ee2 100644 --- a/net/ipv4/netfilter/ip_nat_helper_h323.c +++ b/net/ipv4/netfilter/ip_nat_helper_h323.c @@ -32,13 +32,13 @@ /****************************************************************************/ static int set_addr(struct sk_buff **pskb, unsigned char **data, int dataoff, - unsigned int addroff, u_int32_t ip, u_int16_t port) + unsigned int addroff, __be32 ip, u_int16_t port) { enum ip_conntrack_info ctinfo; struct ip_conntrack *ct = ip_conntrack_get(*pskb, &ctinfo); struct { - u_int32_t ip; - u_int16_t port; + __be32 ip; + __be16 port; } __attribute__ ((__packed__)) buf; struct tcphdr _tcph, *th; @@ -86,7 +86,7 @@ static int set_addr(struct sk_buff **pskb, static int set_h225_addr(struct sk_buff **pskb, unsigned char **data, int dataoff, TransportAddress * addr, - u_int32_t ip, u_int16_t port) + __be32 ip, u_int16_t port) { return set_addr(pskb, data, dataoff, addr->ipAddress.ip, ip, port); } @@ -95,7 +95,7 @@ static int set_h225_addr(struct sk_buff **pskb, static int set_h245_addr(struct sk_buff **pskb, unsigned char **data, int dataoff, H245_TransportAddress * addr, - u_int32_t ip, u_int16_t port) + __be32 ip, u_int16_t port) { return set_addr(pskb, data, dataoff, addr->unicastAddress.iPAddress.network, ip, port); @@ -110,7 +110,7 @@ static int set_sig_addr(struct sk_buff **pskb, struct ip_conntrack *ct, struct ip_ct_h323_master *info = &ct->help.ct_h323_info; int dir = CTINFO2DIR(ctinfo); int i; - u_int32_t ip; + __be32 ip; u_int16_t port; for (i = 0; i < count; i++) { @@ -164,7 +164,7 @@ static int set_ras_addr(struct sk_buff **pskb, struct ip_conntrack *ct, { int dir = CTINFO2DIR(ctinfo); int i; - u_int32_t ip; + __be32 ip; u_int16_t port; for (i = 0; i < count; i++) { @@ -433,7 +433,7 @@ static int nat_q931(struct sk_buff **pskb, struct ip_conntrack *ct, struct ip_ct_h323_master *info = &ct->help.ct_h323_info; int dir = CTINFO2DIR(ctinfo); u_int16_t nated_port = port; - u_int32_t ip; + __be32 ip; /* Set expectations for NAT */ exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; diff --git a/net/ipv4/netfilter/ip_nat_helper_pptp.c b/net/ipv4/netfilter/ip_nat_helper_pptp.c index 2ff578807123..329fdcd7d702 100644 --- a/net/ipv4/netfilter/ip_nat_helper_pptp.c +++ b/net/ipv4/netfilter/ip_nat_helper_pptp.c @@ -51,7 +51,7 @@ #define IP_NAT_PPTP_VERSION "3.0" -#define REQ_CID(req, off) (*(u_int16_t *)((char *)(req) + (off))) +#define REQ_CID(req, off) (*(__be16 *)((char *)(req) + (off))) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); diff --git a/net/ipv4/netfilter/ip_nat_proto_icmp.c b/net/ipv4/netfilter/ip_nat_proto_icmp.c index ec50cc295317..3f6efc13ac74 100644 --- a/net/ipv4/netfilter/ip_nat_proto_icmp.c +++ b/net/ipv4/netfilter/ip_nat_proto_icmp.c @@ -67,7 +67,7 @@ icmp_manip_pkt(struct sk_buff **pskb, hdr = (struct icmphdr *)((*pskb)->data + hdroff); hdr->checksum = nf_proto_csum_update(*pskb, - hdr->un.echo.id ^ 0xFFFF, + hdr->un.echo.id ^ htons(0xFFFF), tuple->src.u.icmp.id, hdr->checksum, 0); hdr->un.echo.id = tuple->src.u.icmp.id; diff --git a/net/ipv4/netfilter/ip_nat_proto_tcp.c b/net/ipv4/netfilter/ip_nat_proto_tcp.c index 72a6307bd2db..12deb13b93b1 100644 --- a/net/ipv4/netfilter/ip_nat_proto_tcp.c +++ b/net/ipv4/netfilter/ip_nat_proto_tcp.c @@ -24,7 +24,7 @@ tcp_in_range(const struct ip_conntrack_tuple *tuple, const union ip_conntrack_manip_proto *min, const union ip_conntrack_manip_proto *max) { - u_int16_t port; + __be16 port; if (maniptype == IP_NAT_MANIP_SRC) port = tuple->src.u.tcp.port; @@ -42,7 +42,7 @@ tcp_unique_tuple(struct ip_conntrack_tuple *tuple, const struct ip_conntrack *conntrack) { static u_int16_t port; - u_int16_t *portptr; + __be16 *portptr; unsigned int range_size, min, i; if (maniptype == IP_NAT_MANIP_SRC) @@ -93,8 +93,8 @@ tcp_manip_pkt(struct sk_buff **pskb, struct iphdr *iph = (struct iphdr *)((*pskb)->data + iphdroff); struct tcphdr *hdr; unsigned int hdroff = iphdroff + iph->ihl*4; - u32 oldip, newip; - u16 *portptr, newport, oldport; + __be32 oldip, newip; + __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such @@ -130,7 +130,7 @@ tcp_manip_pkt(struct sk_buff **pskb, return 1; hdr->check = nf_proto_csum_update(*pskb, ~oldip, newip, hdr->check, 1); - hdr->check = nf_proto_csum_update(*pskb, oldport ^ 0xFFFF, newport, + hdr->check = nf_proto_csum_update(*pskb, oldport ^ htons(0xFFFF), newport, hdr->check, 0); return 1; } diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c index 5da196ae758c..4bbec7730d18 100644 --- a/net/ipv4/netfilter/ip_nat_proto_udp.c +++ b/net/ipv4/netfilter/ip_nat_proto_udp.c @@ -24,7 +24,7 @@ udp_in_range(const struct ip_conntrack_tuple *tuple, const union ip_conntrack_manip_proto *min, const union ip_conntrack_manip_proto *max) { - u_int16_t port; + __be16 port; if (maniptype == IP_NAT_MANIP_SRC) port = tuple->src.u.udp.port; @@ -42,7 +42,7 @@ udp_unique_tuple(struct ip_conntrack_tuple *tuple, const struct ip_conntrack *conntrack) { static u_int16_t port; - u_int16_t *portptr; + __be16 *portptr; unsigned int range_size, min, i; if (maniptype == IP_NAT_MANIP_SRC) @@ -91,8 +91,8 @@ udp_manip_pkt(struct sk_buff **pskb, struct iphdr *iph = (struct iphdr *)((*pskb)->data + iphdroff); struct udphdr *hdr; unsigned int hdroff = iphdroff + iph->ihl*4; - u32 oldip, newip; - u16 *portptr, newport; + __be32 oldip, newip; + __be16 *portptr, newport; if (!skb_make_writable(pskb, hdroff + sizeof(*hdr))) return 0; @@ -118,7 +118,7 @@ udp_manip_pkt(struct sk_buff **pskb, hdr->check = nf_proto_csum_update(*pskb, ~oldip, newip, hdr->check, 1); hdr->check = nf_proto_csum_update(*pskb, - *portptr ^ 0xFFFF, newport, + *portptr ^ htons(0xFFFF), newport, hdr->check, 0); if (!hdr->check) hdr->check = -1; diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index 7b703839aa58..a176aa3031e0 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -119,7 +119,7 @@ static unsigned int ipt_snat_target(struct sk_buff **pskb, } /* Before 2.6.11 we did implicit source NAT if required. Warn about change. */ -static void warn_if_extra_mangle(u32 dstip, u32 srcip) +static void warn_if_extra_mangle(__be32 dstip, __be32 srcip) { static int warned = 0; struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dstip } } }; @@ -205,7 +205,7 @@ alloc_null_binding(struct ip_conntrack *conntrack, per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). Use reply in case it's already been mangled (eg local packet). */ - u_int32_t ip + __be32 ip = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip : conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip); @@ -222,7 +222,7 @@ alloc_null_binding_confirmed(struct ip_conntrack *conntrack, struct ip_nat_info *info, unsigned int hooknum) { - u_int32_t ip + __be32 ip = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip : conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip); diff --git a/net/ipv4/netfilter/ip_nat_sip.c b/net/ipv4/netfilter/ip_nat_sip.c index 6ffba63adca2..71fc2730a007 100644 --- a/net/ipv4/netfilter/ip_nat_sip.c +++ b/net/ipv4/netfilter/ip_nat_sip.c @@ -60,8 +60,8 @@ static unsigned int ip_nat_sip(struct sk_buff **pskb, enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; unsigned int bufflen, dataoff; - u_int32_t ip; - u_int16_t port; + __be32 ip; + __be16 port; dataoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); @@ -159,7 +159,7 @@ static int mangle_content_len(struct sk_buff **pskb, static unsigned int mangle_sdp(struct sk_buff **pskb, enum ip_conntrack_info ctinfo, struct ip_conntrack *ct, - u_int32_t newip, u_int16_t port, + __be32 newip, u_int16_t port, const char *dptr) { char buffer[sizeof("nnn.nnn.nnn.nnn")]; @@ -195,7 +195,7 @@ static unsigned int ip_nat_sdp(struct sk_buff **pskb, { struct ip_conntrack *ct = exp->master; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - u_int32_t newip; + __be32 newip; u_int16_t port; DEBUGP("ip_nat_sdp():\n"); diff --git a/net/ipv4/netfilter/ip_nat_snmp_basic.c b/net/ipv4/netfilter/ip_nat_snmp_basic.c index 18b7fbdccb61..168f45fa1898 100644 --- a/net/ipv4/netfilter/ip_nat_snmp_basic.c +++ b/net/ipv4/netfilter/ip_nat_snmp_basic.c @@ -1211,7 +1211,7 @@ static int snmp_translate(struct ip_conntrack *ct, struct sk_buff **pskb) { struct iphdr *iph = (*pskb)->nh.iph; - struct udphdr *udph = (struct udphdr *)((u_int32_t *)iph + iph->ihl); + struct udphdr *udph = (struct udphdr *)((__be32 *)iph + iph->ihl); u_int16_t udplen = ntohs(udph->len); u_int16_t paylen = udplen - sizeof(struct udphdr); int dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 9c577db62047..d85d2de50449 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -191,7 +191,7 @@ ip_nat_in(unsigned int hooknum, int (*okfn)(struct sk_buff *)) { unsigned int ret; - u_int32_t daddr = (*pskb)->nh.iph->daddr; + __be32 daddr = (*pskb)->nh.iph->daddr; ret = ip_nat_fn(hooknum, pskb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN @@ -265,7 +265,8 @@ ip_nat_local_fn(unsigned int hooknum, ct->tuplehash[!dir].tuple.src.u.all #endif ) - return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + if (ip_route_me_harder(pskb, RTN_UNSPEC)) + ret = NF_DROP; } return ret; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 78a44b01c035..4b90927619b8 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1932,6 +1932,9 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + switch (cmd) { case IPT_SO_GET_INFO: ret = get_info(user, len, 1); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 41589665fc5d..7a29d6e7baa7 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -52,7 +52,7 @@ struct clusterip_config { atomic_t entries; /* number of entries/rules * referencing us */ - u_int32_t clusterip; /* the IP address */ + __be32 clusterip; /* the IP address */ u_int8_t clustermac[ETH_ALEN]; /* the MAC address */ struct net_device *dev; /* device */ u_int16_t num_total_nodes; /* total number of nodes */ @@ -119,7 +119,7 @@ clusterip_config_entry_put(struct clusterip_config *c) } static struct clusterip_config * -__clusterip_config_find(u_int32_t clusterip) +__clusterip_config_find(__be32 clusterip) { struct list_head *pos; @@ -136,7 +136,7 @@ __clusterip_config_find(u_int32_t clusterip) } static inline struct clusterip_config * -clusterip_config_find_get(u_int32_t clusterip, int entry) +clusterip_config_find_get(__be32 clusterip, int entry) { struct clusterip_config *c; @@ -166,7 +166,7 @@ clusterip_config_init_nodelist(struct clusterip_config *c, } static struct clusterip_config * -clusterip_config_init(struct ipt_clusterip_tgt_info *i, u_int32_t ip, +clusterip_config_init(struct ipt_clusterip_tgt_info *i, __be32 ip, struct net_device *dev) { struct clusterip_config *c; @@ -387,7 +387,7 @@ checkentry(const char *tablename, return 0; } - if (e->ip.dmsk.s_addr != 0xffffffff + if (e->ip.dmsk.s_addr != htonl(0xffffffff) || e->ip.dst.s_addr == 0) { printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); return 0; @@ -476,9 +476,9 @@ static struct ipt_target clusterip_tgt = { /* hardcoded for 48bit ethernet and 32bit ipv4 addresses */ struct arp_payload { u_int8_t src_hw[ETH_ALEN]; - u_int32_t src_ip; + __be32 src_ip; u_int8_t dst_hw[ETH_ALEN]; - u_int32_t dst_ip; + __be32 dst_ip; } __attribute__ ((packed)); #ifdef CLUSTERIP_DEBUG diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 23f9c7ebe7eb..1aa4517fbcdb 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -37,8 +37,8 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) oldtos = iph->tos; iph->tos &= ~IPT_ECN_IP_MASK; iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); - iph->check = nf_csum_update(oldtos ^ 0xFFFF, iph->tos, - iph->check); + iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF), + htons(iph->tos), iph->check); } return 1; } @@ -48,7 +48,7 @@ static inline int set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; - u_int16_t oldval; + __be16 oldval; /* Not enought header? */ tcph = skb_header_pointer(*pskb, (*pskb)->nh.iph->ihl*4, @@ -66,15 +66,15 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) return 0; tcph = (void *)(*pskb)->nh.iph + (*pskb)->nh.iph->ihl*4; - oldval = ((u_int16_t *)tcph)[6]; + oldval = ((__be16 *)tcph)[6]; if (einfo->operation & IPT_ECN_OP_SET_ECE) tcph->ece = einfo->proto.tcp.ece; if (einfo->operation & IPT_ECN_OP_SET_CWR) tcph->cwr = einfo->proto.tcp.cwr; tcph->check = nf_proto_csum_update((*pskb), - oldval ^ 0xFFFF, - ((u_int16_t *)tcph)[6], + oldval ^ htons(0xFFFF), + ((__be16 *)tcph)[6], tcph->check, 0); return 1; } diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index bc65168a3437..3dbfcfac8a84 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -70,7 +70,7 @@ masquerade_target(struct sk_buff **pskb, const struct ip_nat_multi_range_compat *mr; struct ip_nat_range newrange; struct rtable *rt; - u_int32_t newsrc; + __be32 newsrc; IP_NF_ASSERT(hooknum == NF_IP_POST_ROUTING); diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index beb2914225ff..58a88f227108 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -58,7 +58,7 @@ target(struct sk_buff **pskb, { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; - u_int32_t new_ip, netmask; + __be32 new_ip, netmask; const struct ip_nat_multi_range_compat *mr = targinfo; struct ip_nat_range newrange; diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index f03d43671c6d..c0dcfe9d610c 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -61,7 +61,7 @@ redirect_target(struct sk_buff **pskb, { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; - u_int32_t newdst; + __be32 newdst; const struct ip_nat_multi_range_compat *mr = targinfo; struct ip_nat_range newrange; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b81821edd893..ad0312d0e4fd 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -38,76 +38,16 @@ MODULE_DESCRIPTION("iptables REJECT target module"); #define DEBUGP(format, args...) #endif -static inline struct rtable *route_reverse(struct sk_buff *skb, - struct tcphdr *tcph, int hook) -{ - struct iphdr *iph = skb->nh.iph; - struct dst_entry *odst; - struct flowi fl = {}; - struct rtable *rt; - - /* We don't require ip forwarding to be enabled to be able to - * send a RST reply for bridged traffic. */ - if (hook != NF_IP_FORWARD -#ifdef CONFIG_BRIDGE_NETFILTER - || (skb->nf_bridge && skb->nf_bridge->mask & BRNF_BRIDGED) -#endif - ) { - fl.nl_u.ip4_u.daddr = iph->saddr; - if (hook == NF_IP_LOCAL_IN) - fl.nl_u.ip4_u.saddr = iph->daddr; - fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); - - if (ip_route_output_key(&rt, &fl) != 0) - return NULL; - } else { - /* non-local src, find valid iif to satisfy - * rp-filter when calling ip_route_input. */ - fl.nl_u.ip4_u.daddr = iph->daddr; - if (ip_route_output_key(&rt, &fl) != 0) - return NULL; - - odst = skb->dst; - if (ip_route_input(skb, iph->saddr, iph->daddr, - RT_TOS(iph->tos), rt->u.dst.dev) != 0) { - dst_release(&rt->u.dst); - return NULL; - } - dst_release(&rt->u.dst); - rt = (struct rtable *)skb->dst; - skb->dst = odst; - - fl.nl_u.ip4_u.daddr = iph->saddr; - fl.nl_u.ip4_u.saddr = iph->daddr; - fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); - } - - if (rt->u.dst.error) { - dst_release(&rt->u.dst); - return NULL; - } - - fl.proto = IPPROTO_TCP; - fl.fl_ip_sport = tcph->dest; - fl.fl_ip_dport = tcph->source; - security_skb_classify_flow(skb, &fl); - - xfrm_lookup((struct dst_entry **)&rt, &fl, NULL, 0); - - return rt; -} - /* Send RST reply */ static void send_reset(struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; struct iphdr *iph = oldskb->nh.iph; struct tcphdr _otcph, *oth, *tcph; - struct rtable *rt; - u_int16_t tmp_port; - u_int32_t tmp_addr; + __be16 tmp_port; + __be32 tmp_addr; int needs_ack; - int hh_len; + unsigned int addr_type; /* IP header checks: fragment. */ if (oldskb->nh.iph->frag_off & htons(IP_OFFSET)) @@ -126,23 +66,13 @@ static void send_reset(struct sk_buff *oldskb, int hook) if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP)) return; - if ((rt = route_reverse(oldskb, oth, hook)) == NULL) - return; - - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); - /* We need a linear, writeable skb. We also need to expand headroom in case hh_len of incoming interface < hh_len of outgoing interface */ - nskb = skb_copy_expand(oldskb, hh_len, skb_tailroom(oldskb), + nskb = skb_copy_expand(oldskb, LL_MAX_HEADER, skb_tailroom(oldskb), GFP_ATOMIC); - if (!nskb) { - dst_release(&rt->u.dst); + if (!nskb) return; - } - - dst_release(nskb->dst); - nskb->dst = &rt->u.dst; /* This packet will not be the same as the other: clear nf fields */ nf_reset(nskb); @@ -184,6 +114,21 @@ static void send_reset(struct sk_buff *oldskb, int hook) tcph->window = 0; tcph->urg_ptr = 0; + /* Set DF, id = 0 */ + nskb->nh.iph->frag_off = htons(IP_DF); + nskb->nh.iph->id = 0; + + addr_type = RTN_UNSPEC; + if (hook != NF_IP_FORWARD +#ifdef CONFIG_BRIDGE_NETFILTER + || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED) +#endif + ) + addr_type = RTN_LOCAL; + + if (ip_route_me_harder(&nskb, addr_type)) + goto free_nskb; + /* Adjust TCP checksum */ nskb->ip_summed = CHECKSUM_NONE; tcph->check = 0; @@ -192,12 +137,8 @@ static void send_reset(struct sk_buff *oldskb, int hook) nskb->nh.iph->daddr, csum_partial((char *)tcph, sizeof(struct tcphdr), 0)); - - /* Adjust IP TTL, DF */ + /* Adjust IP TTL */ nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT); - /* Set DF, id = 0 */ - nskb->nh.iph->frag_off = htons(IP_DF); - nskb->nh.iph->id = 0; /* Adjust IP checksum */ nskb->nh.iph->check = 0; diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index efbcb1198832..b38b13328d73 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -135,7 +135,8 @@ same_target(struct sk_buff **pskb, { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; - u_int32_t tmpip, aindex, new_ip; + u_int32_t tmpip, aindex; + __be32 new_ip; const struct ipt_same_info *same = targinfo; struct ip_nat_range newrange; const struct ip_conntrack_tuple *t; diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index 4246c4321e5b..108b6b76311f 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -42,7 +42,8 @@ ipt_tcpmss_target(struct sk_buff **pskb, const struct ipt_tcpmss_info *tcpmssinfo = targinfo; struct tcphdr *tcph; struct iphdr *iph; - u_int16_t tcplen, newtotlen, oldval, newmss; + u_int16_t tcplen, newmss; + __be16 newtotlen, oldval; unsigned int i; u_int8_t *opt; @@ -97,7 +98,7 @@ ipt_tcpmss_target(struct sk_buff **pskb, opt[i+3] = (newmss & 0x00ff); tcph->check = nf_proto_csum_update(*pskb, - htons(oldmss)^0xFFFF, + htons(oldmss)^htons(0xFFFF), htons(newmss), tcph->check, 0); return IPT_CONTINUE; @@ -126,7 +127,7 @@ ipt_tcpmss_target(struct sk_buff **pskb, memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); tcph->check = nf_proto_csum_update(*pskb, - htons(tcplen) ^ 0xFFFF, + htons(tcplen) ^ htons(0xFFFF), htons(tcplen + TCPOLEN_MSS), tcph->check, 1); opt[0] = TCPOPT_MSS; @@ -134,18 +135,18 @@ ipt_tcpmss_target(struct sk_buff **pskb, opt[2] = (newmss & 0xff00) >> 8; opt[3] = (newmss & 0x00ff); - tcph->check = nf_proto_csum_update(*pskb, ~0, *((u_int32_t *)opt), + tcph->check = nf_proto_csum_update(*pskb, htonl(~0), *((__be32 *)opt), tcph->check, 0); - oldval = ((u_int16_t *)tcph)[6]; + oldval = ((__be16 *)tcph)[6]; tcph->doff += TCPOLEN_MSS/4; tcph->check = nf_proto_csum_update(*pskb, - oldval ^ 0xFFFF, - ((u_int16_t *)tcph)[6], + oldval ^ htons(0xFFFF), + ((__be16 *)tcph)[6], tcph->check, 0); newtotlen = htons(ntohs(iph->tot_len) + TCPOLEN_MSS); - iph->check = nf_csum_update(iph->tot_len ^ 0xFFFF, + iph->check = nf_csum_update(iph->tot_len ^ htons(0xFFFF), newtotlen, iph->check); iph->tot_len = newtotlen; return IPT_CONTINUE; diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 471a4c438b0a..83b80b3a5d2f 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -38,8 +38,8 @@ target(struct sk_buff **pskb, iph = (*pskb)->nh.iph; oldtos = iph->tos; iph->tos = (iph->tos & IPTOS_PREC_MASK) | tosinfo->tos; - iph->check = nf_csum_update(oldtos ^ 0xFFFF, iph->tos, - iph->check); + iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF), + htons(iph->tos), iph->check); } return IPT_CONTINUE; } diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index 96e79cc6d0f2..ac9517d62af0 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -54,8 +54,8 @@ ipt_ttl_target(struct sk_buff **pskb, } if (new_ttl != iph->ttl) { - iph->check = nf_csum_update(ntohs((iph->ttl << 8)) ^ 0xFFFF, - ntohs(new_ttl << 8), + iph->check = nf_csum_update(htons((iph->ttl << 8)) ^ htons(0xFFFF), + htons(new_ttl << 8), iph->check); iph->ttl = new_ttl; } diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 893dae210b04..7b60eb74788b 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -22,7 +22,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("iptables addrtype match"); -static inline int match_type(u_int32_t addr, u_int16_t mask) +static inline int match_type(__be32 addr, u_int16_t mask) { return !!(mask & (1 << inet_addr_type(addr))); } diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 4f73a61aa3dd..33ccdbf8e794 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -50,11 +50,11 @@ static struct file_operations dl_file_ops; /* hash table crap */ struct dsthash_dst { - u_int32_t src_ip; - u_int32_t dst_ip; + __be32 src_ip; + __be32 dst_ip; /* ports have to be consecutive !!! */ - u_int16_t src_port; - u_int16_t dst_port; + __be16 src_port; + __be16 dst_port; }; struct dsthash_ent { @@ -106,8 +106,10 @@ static inline int dst_cmp(const struct dsthash_ent *ent, struct dsthash_dst *b) static inline u_int32_t hash_dst(const struct ipt_hashlimit_htable *ht, const struct dsthash_dst *dst) { - return (jhash_3words(dst->dst_ip, (dst->dst_port<<16 | dst->src_port), - dst->src_ip, ht->rnd) % ht->cfg.size); + return (jhash_3words((__force u32)dst->dst_ip, + ((__force u32)dst->dst_port<<16 | + (__force u32)dst->src_port), + (__force u32)dst->src_ip, ht->rnd) % ht->cfg.size); } static inline struct dsthash_ent * @@ -406,7 +408,7 @@ hashlimit_match(const struct sk_buff *skb, dst.src_ip = skb->nh.iph->saddr; if (hinfo->cfg.mode & IPT_HASHLIMIT_HASH_DPT ||hinfo->cfg.mode & IPT_HASHLIMIT_HASH_SPT) { - u_int16_t _ports[2], *ports; + __be16 _ports[2], *ports; switch (skb->nh.iph->protocol) { case IPPROTO_TCP: diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 32ae8d7ac506..126db44e71a8 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -50,11 +50,10 @@ MODULE_PARM_DESC(ip_list_perms, "permissions on /proc/net/ipt_recent/* files"); MODULE_PARM_DESC(ip_list_uid,"owner of /proc/net/ipt_recent/* files"); MODULE_PARM_DESC(ip_list_gid,"owning group of /proc/net/ipt_recent/* files"); - struct recent_entry { struct list_head list; struct list_head lru_list; - u_int32_t addr; + __be32 addr; u_int8_t ttl; u_int8_t index; u_int16_t nstamps; @@ -85,17 +84,17 @@ static struct file_operations recent_fops; static u_int32_t hash_rnd; static int hash_rnd_initted; -static unsigned int recent_entry_hash(u_int32_t addr) +static unsigned int recent_entry_hash(__be32 addr) { if (!hash_rnd_initted) { get_random_bytes(&hash_rnd, 4); hash_rnd_initted = 1; } - return jhash_1word(addr, hash_rnd) & (ip_list_hash_size - 1); + return jhash_1word((__force u32)addr, hash_rnd) & (ip_list_hash_size - 1); } static struct recent_entry * -recent_entry_lookup(const struct recent_table *table, u_int32_t addr, u_int8_t ttl) +recent_entry_lookup(const struct recent_table *table, __be32 addr, u_int8_t ttl) { struct recent_entry *e; unsigned int h; @@ -116,7 +115,7 @@ static void recent_entry_remove(struct recent_table *t, struct recent_entry *e) } static struct recent_entry * -recent_entry_init(struct recent_table *t, u_int32_t addr, u_int8_t ttl) +recent_entry_init(struct recent_table *t, __be32 addr, u_int8_t ttl) { struct recent_entry *e; @@ -178,7 +177,7 @@ ipt_recent_match(const struct sk_buff *skb, const struct ipt_recent_info *info = matchinfo; struct recent_table *t; struct recent_entry *e; - u_int32_t addr; + __be32 addr; u_int8_t ttl; int ret = info->invert; @@ -406,7 +405,7 @@ static ssize_t recent_proc_write(struct file *file, const char __user *input, struct recent_table *t = pde->data; struct recent_entry *e; char buf[sizeof("+255.255.255.255")], *c = buf; - u_int32_t addr; + __be32 addr; int add; if (size > sizeof(buf)) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 79336cb42527..b91f3582359b 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -131,7 +131,7 @@ ipt_local_hook(unsigned int hook, { unsigned int ret; u_int8_t tos; - u_int32_t saddr, daddr; + __be32 saddr, daddr; unsigned long nfmark; /* root is playing with raw sockets. */ @@ -157,7 +157,8 @@ ipt_local_hook(unsigned int hook, || (*pskb)->nfmark != nfmark #endif || (*pskb)->nh.iph->tos != tos)) - return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + if (ip_route_me_harder(pskb, RTN_UNSPEC)) + ret = NF_DROP; return ret; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0e935b4c8741..b430cf2a4f66 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -381,8 +381,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct ipcm_cookie ipc; struct rtable *rt = NULL; int free = 0; - u32 daddr; - u32 saddr; + __be32 daddr; + __be32 saddr; u8 tos; int err; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 20ffe8e88c0f..925ee4dfc32c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -261,6 +261,10 @@ static unsigned int rt_hash_code(u32 daddr, u32 saddr) & rt_hash_mask); } +#define rt_hash(daddr, saddr, idx) \ + rt_hash_code((__force u32)(__be32)(daddr),\ + (__force u32)(__be32)(saddr) ^ ((idx) << 5)) + #ifdef CONFIG_PROC_FS struct rt_cache_iter_state { int bucket; @@ -562,9 +566,15 @@ static inline u32 rt_score(struct rtable *rt) static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) { - return memcmp(&fl1->nl_u.ip4_u, &fl2->nl_u.ip4_u, sizeof(fl1->nl_u.ip4_u)) == 0 && - fl1->oif == fl2->oif && - fl1->iif == fl2->iif; + return ((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | + (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) | +#ifdef CONFIG_IP_ROUTE_FWMARK + (fl1->nl_u.ip4_u.fwmark ^ fl2->nl_u.ip4_u.fwmark) | +#endif + (*(u16 *)&fl1->nl_u.ip4_u.tos ^ + *(u16 *)&fl2->nl_u.ip4_u.tos) | + (fl1->oif ^ fl2->oif) | + (fl1->iif ^ fl2->iif)) == 0; } #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED @@ -1074,7 +1084,7 @@ static void ip_select_fb_ident(struct iphdr *iph) u32 salt; spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id(ip_fallback_id ^ iph->daddr); + salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); iph->id = htons(salt & 0xFFFF); ip_fallback_id = salt; spin_unlock_bh(&ip_fb_id_lock); @@ -1118,13 +1128,13 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } -void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, - u32 saddr, struct net_device *dev) +void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, + __be32 saddr, struct net_device *dev) { int i, k; struct in_device *in_dev = in_dev_get(dev); struct rtable *rth, **rthp; - u32 skeys[2] = { saddr, 0 }; + __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; struct netevent_redirect netevent; @@ -1147,8 +1157,7 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, for (i = 0; i < 2; i++) { for (k = 0; k < 2; k++) { - unsigned hash = rt_hash_code(daddr, - skeys[i] ^ (ikeys[k] << 5)); + unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]); rthp=&rt_hash_table[hash].chain; @@ -1260,9 +1269,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) ret = NULL; } else if ((rt->rt_flags & RTCF_REDIRECTED) || rt->u.dst.expires) { - unsigned hash = rt_hash_code(rt->fl.fl4_dst, - rt->fl.fl4_src ^ - (rt->fl.oif << 5)); + unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, + rt->fl.oif); #if RT_CACHE_DEBUG >= 1 printk(KERN_DEBUG "ip_rt_advice: redirect to " "%u.%u.%u.%u/%02x dropped\n", @@ -1397,15 +1405,15 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu) int i; unsigned short old_mtu = ntohs(iph->tot_len); struct rtable *rth; - u32 skeys[2] = { iph->saddr, 0, }; - u32 daddr = iph->daddr; + __be32 skeys[2] = { iph->saddr, 0, }; + __be32 daddr = iph->daddr; unsigned short est_mtu = 0; if (ipv4_config.no_pmtu_disc) return 0; for (i = 0; i < 2; i++) { - unsigned hash = rt_hash_code(daddr, skeys[i]); + unsigned hash = rt_hash(daddr, skeys[i], 0); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -1530,7 +1538,7 @@ static int ip_rt_bug(struct sk_buff *skb) void ip_rt_get_source(u8 *addr, struct rtable *rt) { - u32 src; + __be32 src; struct fib_result res; if (rt->fl.iif == 0) @@ -1596,12 +1604,12 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) rt->rt_type = res->type; } -static int ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr, +static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, int our) { unsigned hash; struct rtable *rth; - u32 spec_dst; + __be32 spec_dst; struct in_device *in_dev = in_dev_get(dev); u32 itag = 0; @@ -1665,7 +1673,7 @@ static int ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr, RT_CACHE_STAT_INC(in_slow_mc); in_dev_put(in_dev); - hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5)); + hash = rt_hash(daddr, saddr, dev->ifindex); return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst); e_nobufs: @@ -1681,8 +1689,8 @@ e_inval: static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, - u32 daddr, - u32 saddr) + __be32 daddr, + __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE @@ -1712,7 +1720,7 @@ static void ip_handle_martian_source(struct net_device *dev, static inline int __mkroute_input(struct sk_buff *skb, struct fib_result* res, struct in_device *in_dev, - u32 daddr, u32 saddr, u32 tos, + __be32 daddr, __be32 saddr, u32 tos, struct rtable **result) { @@ -1720,7 +1728,8 @@ static inline int __mkroute_input(struct sk_buff *skb, int err; struct in_device *out_dev; unsigned flags = 0; - u32 spec_dst, itag; + __be32 spec_dst; + u32 itag; /* get a working reference to the output device */ out_dev = in_dev_get(FIB_RES_DEV(*res)); @@ -1813,7 +1822,7 @@ static inline int ip_mkroute_input_def(struct sk_buff *skb, struct fib_result* res, const struct flowi *fl, struct in_device *in_dev, - u32 daddr, u32 saddr, u32 tos) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable* rth = NULL; int err; @@ -1830,7 +1839,7 @@ static inline int ip_mkroute_input_def(struct sk_buff *skb, return err; /* put it into the cache */ - hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5)); + hash = rt_hash(daddr, saddr, fl->iif); return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst); } @@ -1838,7 +1847,7 @@ static inline int ip_mkroute_input(struct sk_buff *skb, struct fib_result* res, const struct flowi *fl, struct in_device *in_dev, - u32 daddr, u32 saddr, u32 tos) + __be32 daddr, __be32 saddr, u32 tos) { #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED struct rtable* rth = NULL, *rtres; @@ -1871,7 +1880,7 @@ static inline int ip_mkroute_input(struct sk_buff *skb, return err; /* put it into the cache */ - hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5)); + hash = rt_hash(daddr, saddr, fl->iif); err = rt_intern_hash(hash, rth, &rtres); if (err) return err; @@ -1901,7 +1910,7 @@ static inline int ip_mkroute_input(struct sk_buff *skb, * 2. IP spoofing attempts are filtered with 100% of guarantee. */ -static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr, +static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { struct fib_result res; @@ -1920,7 +1929,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr, u32 itag = 0; struct rtable * rth; unsigned hash; - u32 spec_dst; + __be32 spec_dst; int err = -EINVAL; int free_res = 0; @@ -1936,7 +1945,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr, if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr)) goto martian_source; - if (daddr == 0xFFFFFFFF || (saddr == 0 && daddr == 0)) + if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; @@ -2048,7 +2057,7 @@ local_input: rth->rt_flags &= ~RTCF_LOCAL; } rth->rt_type = res.type; - hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5)); + hash = rt_hash(daddr, saddr, fl.iif); err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst); goto done; @@ -2087,7 +2096,7 @@ martian_source: goto e_inval; } -int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr, +int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { struct rtable * rth; @@ -2095,7 +2104,7 @@ int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr, int iif = dev->ifindex; tos &= IPTOS_RT_MASK; - hash = rt_hash_code(daddr, saddr ^ (iif << 5)); + hash = rt_hash(daddr, saddr, iif); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -2169,7 +2178,7 @@ static inline int __mkroute_output(struct rtable **result, if (LOOPBACK(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK)) return -EINVAL; - if (fl->fl4_dst == 0xFFFFFFFF) + if (fl->fl4_dst == htonl(0xFFFFFFFF)) res->type = RTN_BROADCAST; else if (MULTICAST(fl->fl4_dst)) res->type = RTN_MULTICAST; @@ -2293,8 +2302,7 @@ static inline int ip_mkroute_output_def(struct rtable **rp, int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags); unsigned hash; if (err == 0) { - hash = rt_hash_code(oldflp->fl4_dst, - oldflp->fl4_src ^ (oldflp->oif << 5)); + hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif); err = rt_intern_hash(hash, rth, rp); } @@ -2336,9 +2344,8 @@ static inline int ip_mkroute_output(struct rtable** rp, if (err != 0) goto cleanup; - hash = rt_hash_code(oldflp->fl4_dst, - oldflp->fl4_src ^ - (oldflp->oif << 5)); + hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, + oldflp->oif); err = rt_intern_hash(hash, rth, rp); /* forward hop information to multipath impl. */ @@ -2417,7 +2424,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) */ if (oldflp->oif == 0 - && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == 0xFFFFFFFF)) { + && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF))) { /* Special hack: user can direct multicasts and limited broadcast via necessary interface without fiddling with IP_MULTICAST_IF or IP_PKTINFO. @@ -2454,7 +2461,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) goto out; /* Wrong error code */ } - if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == 0xFFFFFFFF) { + if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF)) { if (!fl.fl4_src) fl.fl4_src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); @@ -2567,7 +2574,7 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp) unsigned hash; struct rtable *rth; - hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5)); + hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif); rcu_read_lock_bh(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -2660,11 +2667,11 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - NLA_PUT_U32(skb, RTA_DST, rt->rt_dst); + NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst); if (rt->fl.fl4_src) { r->rtm_src_len = 32; - NLA_PUT_U32(skb, RTA_SRC, rt->fl.fl4_src); + NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src); } if (rt->u.dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex); @@ -2677,12 +2684,12 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, NLA_PUT_U32(skb, RTA_MP_ALGO, rt->rt_multipath_alg); #endif if (rt->fl.iif) - NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_spec_dst); + NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) - NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_src); + NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src); if (rt->rt_dst != rt->rt_gateway) - NLA_PUT_U32(skb, RTA_GATEWAY, rt->rt_gateway); + NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) goto nla_put_failure; @@ -2706,7 +2713,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (rt->fl.iif) { #ifdef CONFIG_IP_MROUTE - u32 dst = rt->rt_dst; + __be32 dst = rt->rt_dst; if (MULTICAST(dst) && !LOCAL_MCAST(dst) && ipv4_devconf.mc_forwarding) { @@ -2740,7 +2747,9 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; - u32 dst, src, iif; + __be32 dst = 0; + __be32 src = 0; + u32 iif; int err; struct sk_buff *skb; @@ -2765,8 +2774,8 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) skb->nh.iph->protocol = IPPROTO_ICMP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); - src = tb[RTA_SRC] ? nla_get_u32(tb[RTA_SRC]) : 0; - dst = tb[RTA_DST] ? nla_get_u32(tb[RTA_DST]) : 0; + src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0; + dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; if (iif) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b3def0df14fb..cf06accbe687 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -935,7 +935,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked; - struct tcp_sack_block *sp = (struct tcp_sack_block *)(ptr+2); + struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2); int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3; int reord = tp->packets_out; int prior_fackets; @@ -2239,13 +2239,12 @@ static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb, return acked; } -static u32 tcp_usrtt(const struct sk_buff *skb) +static u32 tcp_usrtt(struct timeval *tv) { - struct timeval tv, now; + struct timeval now; do_gettimeofday(&now); - skb_get_timestamp(skb, &tv); - return (now.tv_sec - tv.tv_sec) * 1000000 + (now.tv_usec - tv.tv_usec); + return (now.tv_sec - tv->tv_sec) * 1000000 + (now.tv_usec - tv->tv_usec); } /* Remove acknowledged frames from the retransmission queue. */ @@ -2260,6 +2259,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p) u32 pkts_acked = 0; void (*rtt_sample)(struct sock *sk, u32 usrtt) = icsk->icsk_ca_ops->rtt_sample; + struct timeval tv = { .tv_sec = 0, .tv_usec = 0 }; while ((skb = skb_peek(&sk->sk_write_queue)) && skb != sk->sk_send_head) { @@ -2308,8 +2308,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p) seq_rtt = -1; } else if (seq_rtt < 0) { seq_rtt = now - scb->when; - if (rtt_sample) - (*rtt_sample)(sk, tcp_usrtt(skb)); + skb_get_timestamp(skb, &tv); } if (sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= tcp_skb_pcount(skb); @@ -2322,8 +2321,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p) } } else if (seq_rtt < 0) { seq_rtt = now - scb->when; - if (rtt_sample) - (*rtt_sample)(sk, tcp_usrtt(skb)); + skb_get_timestamp(skb, &tv); } tcp_dec_pcount_approx(&tp->fackets_out, skb); tcp_packets_out_dec(tp, skb); @@ -2335,6 +2333,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p) if (acked&FLAG_ACKED) { tcp_ack_update_rtt(sk, acked, seq_rtt); tcp_ack_packets_out(sk, tp); + if (rtt_sample && !(acked & FLAG_RETRANS_DATA_ACKED)) + (*rtt_sample)(sk, tcp_usrtt(&tv)); if (icsk->icsk_ca_ops->pkts_acked) icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked); @@ -2629,7 +2629,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, switch(opcode) { case TCPOPT_MSS: if(opsize==TCPOLEN_MSS && th->syn && !estab) { - u16 in_mss = ntohs(get_unaligned((__u16 *)ptr)); + u16 in_mss = ntohs(get_unaligned((__be16 *)ptr)); if (in_mss) { if (opt_rx->user_mss && opt_rx->user_mss < in_mss) in_mss = opt_rx->user_mss; @@ -2657,8 +2657,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, if ((estab && opt_rx->tstamp_ok) || (!estab && sysctl_tcp_timestamps)) { opt_rx->saw_tstamp = 1; - opt_rx->rcv_tsval = ntohl(get_unaligned((__u32 *)ptr)); - opt_rx->rcv_tsecr = ntohl(get_unaligned((__u32 *)(ptr+4))); + opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr)); + opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4))); } } break; @@ -2695,8 +2695,8 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, return 0; } else if (tp->rx_opt.tstamp_ok && th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) { - __u32 *ptr = (__u32 *)(th + 1); - if (*ptr == ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) + __be32 *ptr = (__be32 *)(th + 1); + if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) { tp->rx_opt.saw_tstamp = 1; ++ptr; @@ -3911,10 +3911,10 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, /* Check timestamp */ if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) { - __u32 *ptr = (__u32 *)(th + 1); + __be32 *ptr = (__be32 *)(th + 1); /* No? Slow path! */ - if (*ptr != ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) + if (*ptr != htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) goto slow_path; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 39b179856082..22ef8bd26620 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -159,7 +159,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct tcp_sock *tp = tcp_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct rtable *rt; - u32 daddr, nexthop; + __be32 daddr, nexthop; int tmp; int err; @@ -355,7 +355,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) return; } if (sk->sk_state == TCP_TIME_WAIT) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); return; } @@ -373,7 +373,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && !between(seq, tp->snd_una, tp->snd_nxt)) { - NET_INC_STATS(LINUX_MIB_OUTOFWINDOWICMPS); + NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -578,7 +578,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, struct tcphdr *th = skb->h.th; struct { struct tcphdr th; - u32 tsopt[3]; + u32 tsopt[TCPOLEN_TSTAMP_ALIGNED >> 2]; } rep; struct ip_reply_arg arg; @@ -734,8 +734,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct inet_request_sock *ireq; struct tcp_options_received tmp_opt; struct request_sock *req; - __u32 saddr = skb->nh.iph->saddr; - __u32 daddr = skb->nh.iph->daddr; + __be32 saddr = skb->nh.iph->saddr; + __be32 daddr = skb->nh.iph->daddr; __u32 isn = TCP_SKB_CB(skb)->when; struct dst_entry *dst = NULL; #ifdef CONFIG_SYN_COOKIES @@ -960,7 +960,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) bh_lock_sock(nsk); return nsk; } - inet_twsk_put((struct inet_timewait_sock *)nsk); + inet_twsk_put(inet_twsk(nsk)); return NULL; } @@ -1154,26 +1154,24 @@ discard_and_relse: do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - inet_twsk_put((struct inet_timewait_sock *) sk); + inet_twsk_put(inet_twsk(sk)); goto discard_it; } if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) { TCP_INC_STATS_BH(TCP_MIB_INERRS); - inet_twsk_put((struct inet_timewait_sock *) sk); + inet_twsk_put(inet_twsk(sk)); goto discard_it; } - switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk, - skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo, skb->nh.iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule((struct inet_timewait_sock *)sk, - &tcp_death_row); - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_put(inet_twsk(sk)); sk = sk2; goto process; } @@ -1763,7 +1761,7 @@ static void get_tcp4_sock(struct sock *sp, char *tmpbuf, int i) static void get_timewait4_sock(struct inet_timewait_sock *tw, char *tmpbuf, int i) { - unsigned int dest, src; + __be32 dest, src; __u16 destp, srcp; int ttd = tw->tw_ttd - jiffies; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 308fb7e071c5..f0ebaf0e21cb 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -31,8 +31,6 @@ * Hung Hing Lun, Mike <hlhung3i@gmail.com> * SourceForge project page: * http://tcp-lp-mod.sourceforge.net/ - * - * Version: $Id: tcp_lp.c,v 1.24 2006/09/05 20:22:53 hswong3i Exp $ */ #include <linux/module.h> @@ -164,7 +162,7 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) out: /* record time for successful remote HZ calc */ - if (rhz > 0) + if ((rhz >> 6) > 0) lp->flag |= LP_VALID_RHZ; else lp->flag &= ~LP_VALID_RHZ; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 061edfae0c29..ca406157724c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -269,14 +269,14 @@ static u16 tcp_select_window(struct sock *sk) return new_win; } -static void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp, +static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp, __u32 tstamp) { if (tp->rx_opt.tstamp_ok) { - *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | - TCPOLEN_TIMESTAMP); + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); *ptr++ = htonl(tstamp); *ptr++ = htonl(tp->rx_opt.ts_recent); } @@ -305,7 +305,7 @@ static void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp, * MAX_SYN_SIZE to match the new maximum number of options that you * can generate. */ -static void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack, +static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack, int offer_wscale, int wscale, __u32 tstamp, __u32 ts_recent) { @@ -325,18 +325,27 @@ static void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack, *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss); if (ts) { if(sack) - *ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | - (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | + (TCPOLEN_SACK_PERM << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); else - *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); *ptr++ = htonl(tstamp); /* TSVAL */ *ptr++ = htonl(ts_recent); /* TSECR */ } else if(sack) - *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | - (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_SACK_PERM << 8) | + TCPOLEN_SACK_PERM); if (offer_wscale) - *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale)); + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_WINDOW << 16) | + (TCPOLEN_WINDOW << 8) | + (wscale)); } /* This routine actually transmits TCP packets queued in by @@ -424,7 +433,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->dest = inet->dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); - *(((__u16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | + *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->flags); if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { @@ -445,7 +454,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { - tcp_syn_build_options((__u32 *)(th + 1), + tcp_syn_build_options((__be32 *)(th + 1), tcp_advertise_mss(sk), (sysctl_flags & SYSCTL_FLAG_TSTAMPS), (sysctl_flags & SYSCTL_FLAG_SACK), @@ -454,7 +463,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, tcb->when, tp->rx_opt.ts_recent); } else { - tcp_build_and_update_options((__u32 *)(th + 1), + tcp_build_and_update_options((__be32 *)(th + 1), tp, tcb->when); TCP_ECN_send(sk, tp, skb, tcp_header_size); } @@ -1087,10 +1096,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ u32 send_win, cong_win, limit, in_flight; if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) - return 0; + goto send_now; if (icsk->icsk_ca_state != TCP_CA_Open) - return 0; + goto send_now; + + /* Defer for less than two clock ticks. */ + if (!tp->tso_deferred && ((jiffies<<1)>>1) - (tp->tso_deferred>>1) > 1) + goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1106,7 +1119,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ /* If a full-sized TSO skb can be sent, do it. */ if (limit >= 65536) - return 0; + goto send_now; if (sysctl_tcp_tso_win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); @@ -1116,7 +1129,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ */ chunk /= sysctl_tcp_tso_win_divisor; if (limit >= chunk) - return 0; + goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized @@ -1124,11 +1137,17 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ * then send now. */ if (limit > tcp_max_burst(tp) * tp->mss_cache) - return 0; + goto send_now; } /* Ok, it looks like it is advisable to defer. */ + tp->tso_deferred = 1 | (jiffies<<1); + return 1; + +send_now: + tp->tso_deferred = 0; + return 0; } /* Create a new MTU probe if we are ready. @@ -2070,7 +2089,7 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->window = htons(req->rcv_wnd); TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok, + tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok, ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale, TCP_SKB_CB(skb)->when, req->ts_recent); diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index dab37d2f65fc..4be336f17883 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -99,8 +99,10 @@ static int jtcp_sendmsg(struct kiocb *iocb, struct sock *sk, } static struct jprobe tcp_send_probe = { - .kp = { .addr = (kprobe_opcode_t *) &tcp_sendmsg, }, - .entry = (kprobe_opcode_t *) &jtcp_sendmsg, + .kp = { + .symbol_name = "tcp_sendmsg", + }, + .entry = JPROBE_ENTRY(jtcp_sendmsg), }; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77e265d7bb8f..865d75214a9a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -243,8 +243,8 @@ static void udp_v4_unhash(struct sock *sk) /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -static struct sock *udp_v4_lookup_longway(u32 saddr, u16 sport, - u32 daddr, u16 dport, int dif) +static struct sock *udp_v4_lookup_longway(__be32 saddr, __be16 sport, + __be32 daddr, __be16 dport, int dif) { struct sock *sk, *result = NULL; struct hlist_node *node; @@ -288,8 +288,8 @@ static struct sock *udp_v4_lookup_longway(u32 saddr, u16 sport, return result; } -static __inline__ struct sock *udp_v4_lookup(u32 saddr, u16 sport, - u32 daddr, u16 dport, int dif) +static __inline__ struct sock *udp_v4_lookup(__be32 saddr, __be16 sport, + __be32 daddr, __be16 dport, int dif) { struct sock *sk; @@ -302,8 +302,8 @@ static __inline__ struct sock *udp_v4_lookup(u32 saddr, u16 sport, } static inline struct sock *udp_v4_mcast_next(struct sock *sk, - u16 loc_port, u32 loc_addr, - u16 rmt_port, u32 rmt_addr, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, int dif) { struct hlist_node *node; @@ -498,7 +498,7 @@ out: } -static unsigned short udp_check(struct udphdr *uh, int len, unsigned long saddr, unsigned long daddr, unsigned long base) +static unsigned short udp_check(struct udphdr *uh, int len, __be32 saddr, __be32 daddr, unsigned long base) { return(csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base)); } @@ -513,8 +513,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct rtable *rt = NULL; int free = 0; int connected = 0; - u32 daddr, faddr, saddr; - u16 dport; + __be32 daddr, faddr, saddr; + __be16 dport; u8 tos; int err; int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; @@ -675,6 +675,8 @@ do_append_data: udp_flush_pending_frames(sk); else if (!corkreq) err = udp_push_pending_frames(sk, up); + else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) + up->pending = 0; release_sock(sk); out: @@ -931,7 +933,7 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb) int iphlen, len; __u8 *udpdata = (__u8 *)uh + sizeof(struct udphdr); - __u32 *udpdata32 = (__u32 *)udpdata; + __be32 *udpdata32 = (__be32 *)udpdata; __u16 encap_type = up->encap_type; /* if we're overly short, let UDP handle it */ @@ -1080,7 +1082,7 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) * so we don't need to lock the hashes. */ static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh, - u32 saddr, u32 daddr) + __be32 saddr, __be32 daddr) { struct sock *sk; int dif; @@ -1121,7 +1123,7 @@ static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh, * including udp header and folding it to skb->csum. */ static void udp_checksum_init(struct sk_buff *skb, struct udphdr *uh, - unsigned short ulen, u32 saddr, u32 daddr) + unsigned short ulen, __be32 saddr, __be32 daddr) { if (uh->check == 0) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1146,8 +1148,8 @@ int udp_rcv(struct sk_buff *skb) struct udphdr *uh; unsigned short ulen; struct rtable *rt = (struct rtable*)skb->dst; - u32 saddr = skb->nh.iph->saddr; - u32 daddr = skb->nh.iph->daddr; + __be32 saddr = skb->nh.iph->saddr; + __be32 daddr = skb->nh.iph->daddr; int len = skb->len; /* @@ -1563,8 +1565,8 @@ void udp_proc_unregister(struct udp_seq_afinfo *afinfo) static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket) { struct inet_sock *inet = inet_sk(sp); - unsigned int dest = inet->daddr; - unsigned int src = inet->rcv_saddr; + __be32 dest = inet->daddr; + __be32 src = inet->rcv_saddr; __u16 destp = ntohs(inet->dport); __u16 srcp = ntohs(inet->sport); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 040e8475f295..8655d038364c 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,7 +23,7 @@ int xfrm4_rcv(struct sk_buff *skb) EXPORT_SYMBOL(xfrm4_rcv); -static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) +static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { switch (nexthdr) { case IPPROTO_IPIP: @@ -55,7 +55,7 @@ drop: int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) { int err; - u32 spi, seq; + __be32 spi, seq; struct xfrm_state *xfrm_vec[XFRM_MAX_DEPTH]; struct xfrm_state *x; int xfrm_nr = 0; diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c new file mode 100644 index 000000000000..89cf59ea7bbe --- /dev/null +++ b/net/ipv4/xfrm4_mode_beet.c @@ -0,0 +1,139 @@ +/* + * xfrm4_mode_beet.c - BEET mode encapsulation for IPv4. + * + * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com> + * Miika Komu <miika@iki.fi> + * Herbert Xu <herbert@gondor.apana.org.au> + * Abhinav Pathak <abhinav.pathak@hiit.fi> + * Jeff Ahrenholz <ahrenholz@gmail.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/dst.h> +#include <net/ip.h> +#include <net/xfrm.h> + +/* Add encapsulation header. + * + * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt. + * The following fields in it shall be filled in by x->type->output: + * tot_len + * check + * + * On exit, skb->h will be set to the start of the payload to be processed + * by x->type->output and skb->nh will be set to the top IP header. + */ +static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct iphdr *iph, *top_iph = NULL; + int hdrlen, optlen; + + iph = skb->nh.iph; + skb->h.ipiph = iph; + + hdrlen = 0; + optlen = iph->ihl * 4 - sizeof(*iph); + if (unlikely(optlen)) + hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); + + skb->nh.raw = skb_push(skb, x->props.header_len + hdrlen); + top_iph = skb->nh.iph; + hdrlen = iph->ihl * 4 - optlen; + skb->h.raw += hdrlen; + + memmove(top_iph, iph, hdrlen); + if (unlikely(optlen)) { + struct ip_beet_phdr *ph; + + BUG_ON(optlen < 0); + + ph = (struct ip_beet_phdr *)skb->h.raw; + ph->padlen = 4 - (optlen & 4); + ph->hdrlen = (optlen + ph->padlen + sizeof(*ph)) / 8; + ph->nexthdr = top_iph->protocol; + + top_iph->protocol = IPPROTO_BEETPH; + top_iph->ihl = sizeof(struct iphdr) / 4; + } + + top_iph->saddr = x->props.saddr.a4; + top_iph->daddr = x->id.daddr.a4; + + return 0; +} + +static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct iphdr *iph = skb->nh.iph; + int phlen = 0; + int optlen = 0; + __u8 ph_nexthdr = 0, protocol = 0; + int err = -EINVAL; + + protocol = iph->protocol; + + if (unlikely(iph->protocol == IPPROTO_BEETPH)) { + struct ip_beet_phdr *ph = (struct ip_beet_phdr*)(iph + 1); + + if (!pskb_may_pull(skb, sizeof(*ph))) + goto out; + + phlen = ph->hdrlen * 8; + optlen = phlen - ph->padlen - sizeof(*ph); + if (optlen < 0 || optlen & 3 || optlen > 250) + goto out; + + if (!pskb_may_pull(skb, phlen)) + goto out; + + ph_nexthdr = ph->nexthdr; + } + + skb_push(skb, sizeof(*iph) - phlen + optlen); + memmove(skb->data, skb->nh.raw, sizeof(*iph)); + skb->nh.raw = skb->data; + + iph = skb->nh.iph; + iph->ihl = (sizeof(*iph) + optlen) / 4; + iph->tot_len = htons(skb->len); + iph->daddr = x->sel.daddr.a4; + iph->saddr = x->sel.saddr.a4; + if (ph_nexthdr) + iph->protocol = ph_nexthdr; + else + iph->protocol = protocol; + iph->check = 0; + iph->check = ip_fast_csum(skb->nh.raw, iph->ihl); + err = 0; +out: + return err; +} + +static struct xfrm_mode xfrm4_beet_mode = { + .input = xfrm4_beet_input, + .output = xfrm4_beet_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_BEET, +}; + +static int __init xfrm4_beet_init(void) +{ + return xfrm_register_mode(&xfrm4_beet_mode, AF_INET); +} + +static void __exit xfrm4_beet_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm4_beet_mode, AF_INET); + BUG_ON(err); +} + +module_init(xfrm4_beet_init); +module_exit(xfrm4_beet_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_BEET); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index eabcd27b1767..1bed0cdf53e3 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -52,7 +52,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) xdst->u.rt.fl.fl4_dst == fl->fl4_dst && xdst->u.rt.fl.fl4_src == fl->fl4_src && xdst->u.rt.fl.fl4_tos == fl->fl4_tos && - xfrm_bundle_ok(xdst, fl, AF_INET, 0)) { + xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) { dst_clone(dst); break; } @@ -221,7 +221,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl) case IPPROTO_ESP: if (pskb_may_pull(skb, xprth + 4 - skb->data)) { - u32 *ehdr = (u32 *)xprth; + __be32 *ehdr = (__be32 *)xprth; fl->fl_ipsec_spi = ehdr[0]; } @@ -229,7 +229,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl) case IPPROTO_AH: if (pskb_may_pull(skb, xprth + 8 - skb->data)) { - u32 *ah_hdr = (u32*)xprth; + __be32 *ah_hdr = (__be32*)xprth; fl->fl_ipsec_spi = ah_hdr[1]; } @@ -237,7 +237,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl) case IPPROTO_COMP: if (pskb_may_pull(skb, xprth + 4 - skb->data)) { - u16 *ipcomp_hdr = (u16 *)xprth; + __be16 *ipcomp_hdr = (__be16 *)xprth; fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); } diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index fe2034494d08..3cc3df0c6ece 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -29,9 +29,9 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->sel.daddr.a4 = fl->fl4_dst; x->sel.saddr.a4 = fl->fl4_src; x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = ~0; + x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = ~0; + x->sel.sport_mask = htons(0xffff); x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->sel.proto = fl->proto; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index a2d211da2aba..6e48f52e197c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -136,6 +136,16 @@ config INET6_XFRM_MODE_TUNNEL If unsure, say Y. +config INET6_XFRM_MODE_BEET + tristate "IPv6: IPsec BEET mode" + depends on IPV6 + default IPV6 + select XFRM + ---help--- + Support for IPsec BEET mode. + + If unsure, say Y. + config INET6_XFRM_MODE_ROUTEOPTIMIZATION tristate "IPv6: MIPv6 route optimization mode (EXPERIMENTAL)" depends on IPV6 && EXPERIMENTAL @@ -143,6 +153,19 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION ---help--- Support for MIPv6 route optimization mode. +config IPV6_SIT + tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)" + depends on IPV6 + default y + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This driver implements encapsulation of IPv6 + into IPv4 packets. This is useful if you want to connect two IPv6 + networks over an IPv4-only path. + + Saying M here will produce a module called sit.ko. If unsure, say Y. + config IPV6_TUNNEL tristate "IPv6: IPv6-in-IPv6 tunnel" select INET6_TUNNEL @@ -152,9 +175,16 @@ config IPV6_TUNNEL If unsure, say N. +config IPV6_MULTIPLE_TABLES + bool "IPv6: Multiple Routing Tables" + depends on IPV6 && EXPERIMENTAL + select FIB_RULES + ---help--- + Support multiple routing tables. + config IPV6_SUBTREES bool "IPv6: source address based routing" - depends on IPV6 && EXPERIMENTAL + depends on IPV6_MULTIPLE_TABLES ---help--- Enable routing by source address or prefix. @@ -166,13 +196,6 @@ config IPV6_SUBTREES If unsure, say N. -config IPV6_MULTIPLE_TABLES - bool "IPv6: Multiple Routing Tables" - depends on IPV6 && EXPERIMENTAL - select FIB_RULES - ---help--- - Support multiple routing tables. - config IPV6_ROUTE_FWMARK bool "IPv6: use netfilter MARK value as routing key" depends on IPV6_MULTIPLE_TABLES && NETFILTER diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 0213c6612b58..addcc011bc01 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_IPV6) += ipv6.o -ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ +ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \ protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \ @@ -26,8 +26,10 @@ obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o +obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o obj-$(CONFIG_NETFILTER) += netfilter/ +obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-y += exthdrs_core.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c18676352397..b312a5f7a759 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -396,8 +396,10 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) ndev->regen_timer.data = (unsigned long) ndev; if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || - dev->type == ARPHRD_NONE || - dev->type == ARPHRD_SIT) { +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) + dev->type == ARPHRD_SIT || +#endif + dev->type == ARPHRD_NONE) { printk(KERN_INFO "%s: Disabled Privacy Extensions\n", dev->name); @@ -1258,8 +1260,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - u32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; - u32 sk2_rcv_saddr = inet_rcv_saddr(sk2); + __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; + __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(sk_rcv_saddr6); @@ -1546,8 +1548,10 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) cfg.fc_flags |= RTF_NONEXTHOP; +#endif ip6_route_add(&cfg); } @@ -1569,6 +1573,7 @@ static void addrconf_add_mroute(struct net_device *dev) ip6_route_add(&cfg); } +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) static void sit_route_add(struct net_device *dev) { struct fib6_config cfg = { @@ -1582,6 +1587,7 @@ static void sit_route_add(struct net_device *dev) /* prefix length - 96 bits "::d.d.d.d" */ ip6_route_add(&cfg); } +#endif static void addrconf_add_lroute(struct net_device *dev) { @@ -1852,6 +1858,7 @@ int addrconf_set_dstaddr(void __user *arg) if (dev == NULL) goto err_exit; +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT) { struct ifreq ifr; mm_segment_t oldfs; @@ -1881,6 +1888,7 @@ int addrconf_set_dstaddr(void __user *arg) err = dev_open(dev); } } +#endif err_exit: rtnl_unlock(); @@ -2010,6 +2018,7 @@ int addrconf_del_ifaddr(void __user *arg) return err; } +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) static void sit_add_v4_addrs(struct inet6_dev *idev) { struct inet6_ifaddr * ifp; @@ -2078,6 +2087,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) } } } +#endif static void init_loopback(struct net_device *dev) { @@ -2141,6 +2151,7 @@ static void addrconf_dev_config(struct net_device *dev) addrconf_add_linklocal(idev, &addr); } +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; @@ -2166,6 +2177,7 @@ static void addrconf_sit_config(struct net_device *dev) } else sit_route_add(dev); } +#endif static inline int ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) @@ -2260,9 +2272,11 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } switch(dev->type) { +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) case ARPHRD_SIT: addrconf_sit_config(dev); break; +#endif case ARPHRD_TUNNEL6: addrconf_ip6_tnl_config(dev); break; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index bf6e8aff19d4..858cae29581c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -246,7 +246,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - __u32 v4addr = 0; + __be32 v4addr = 0; unsigned short snum; int addr_type = 0; int err = 0; @@ -850,7 +850,6 @@ static int __init inet6_init(void) err = addrconf_init(); if (err) goto addrconf_fail; - sit_init(); /* Init v6 extension headers. */ ipv6_rthdr_init(); @@ -927,7 +926,6 @@ static void __exit inet6_exit(void) mip6_fini(); #endif /* Cleanup code parts. */ - sit_cleanup(); ip6_flowlabel_cleanup(); addrconf_cleanup(); ip6_route_cleanup(); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 34f5bfaddfc2..1896ecb52899 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -13,7 +13,6 @@ * Ville Nuorvala <vnuorval@tcs.hut.fi> */ -#include <linux/config.h> #include <linux/netdevice.h> #include <net/fib_rules.h> @@ -118,12 +117,15 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; - if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) + if (r->dst.plen && + !ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) return 0; - if ((flags & RT6_LOOKUP_F_HAS_SADDR) && - !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) - return 0; + if (r->src.plen) { + if (!(flags & RT6_LOOKUP_F_HAS_SADDR) || + !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) + return 0; + } if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff)) return 0; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d2f3fc990bfa..8accd1fbeeda 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -64,7 +64,7 @@ struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, { struct sock *sk; const struct hlist_node *node; - const __u32 ports = INET_COMBINED_PORTS(sport, hnum); + const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ @@ -82,7 +82,7 @@ struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { const struct inet_timewait_sock *tw = inet_twsk(sk); - if(*((__u32 *)&(tw->tw_dport)) == ports && + if(*((__portpair *)&(tw->tw_dport)) == ports && sk->sk_family == PF_INET6) { const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); @@ -171,7 +171,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const struct in6_addr *daddr = &np->rcv_saddr; const struct in6_addr *saddr = &np->daddr; const int dif = sk->sk_bound_dev_if; - const u32 ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); const unsigned int hash = inet6_ehashfn(daddr, inet->num, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); @@ -188,7 +188,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, tw = inet_twsk(sk2); - if(*((__u32 *)&(tw->tw_dport)) == ports && + if(*((__portpair *)&(tw->tw_dport)) == ports && sk2->sk_family == PF_INET6 && ipv6_addr_equal(&tw6->tw_v6_daddr, saddr) && ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) && diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index ad9c6e824e62..71f59f18ede8 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -178,7 +178,7 @@ out_ok: static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __u32 info) { - u32 spi; + __be32 spi; struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ipv6_comp_hdr *ipcomph = (struct ipv6_comp_hdr*)(skb->data+offset); struct xfrm_state *x; @@ -199,6 +199,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct xfrm_state *t = NULL; + u8 mode = XFRM_MODE_TUNNEL; t = xfrm_state_alloc(); if (!t) @@ -212,7 +213,9 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr)); memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET6; - t->props.mode = XFRM_MODE_TUNNEL; + if (x->props.mode == XFRM_MODE_BEET) + mode = x->props.mode; + t->props.mode = mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); if (xfrm_init_state(t)) @@ -234,7 +237,7 @@ static int ipcomp6_tunnel_attach(struct xfrm_state *x) { int err = 0; struct xfrm_state *t = NULL; - u32 spi; + __be32 spi; spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr); if (spi) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4f3bb7fcc8b5..de6b91981b30 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -123,6 +123,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) struct ipv6hdr *ipv6h; struct inet6_protocol *ops; + if (!(features & NETIF_F_HW_CSUM)) + features &= ~NETIF_F_SG; + if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 99d116caecda..7ccdc8fc5a31 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -22,7 +22,6 @@ * Masahide NAKAMURA @USAGI */ -#include <linux/config.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/time.h> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0304b5fe8d6a..41a8a5f06602 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -967,8 +967,6 @@ static void ndisc_recv_na(struct sk_buff *skb) ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp && pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) { /* XXX: idev->cnf.prixy_ndp */ - WARN_ON(skb->dst != NULL && - ((struct rt6_info *)skb->dst)->rt6i_idev); goto out; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d6b4b4f48d18..c953466b7afd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,6 +141,10 @@ struct rt6_info ip6_null_entry = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); +static int ip6_pkt_blk_hole(struct sk_buff *skb); + struct rt6_info ip6_prohibit_entry = { .u = { .dst = { @@ -150,8 +154,8 @@ struct rt6_info ip6_prohibit_entry = { .obsolete = -1, .error = -EACCES, .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, + .input = ip6_pkt_prohibit, + .output = ip6_pkt_prohibit_out, .ops = &ip6_dst_ops, .path = (struct dst_entry*)&ip6_prohibit_entry, } @@ -170,8 +174,8 @@ struct rt6_info ip6_blk_hole_entry = { .obsolete = -1, .error = -EINVAL, .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, + .input = ip6_pkt_blk_hole, + .output = ip6_pkt_blk_hole, .ops = &ip6_dst_ops, .path = (struct dst_entry*)&ip6_blk_hole_entry, } @@ -484,7 +488,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, do { \ if (rt == &ip6_null_entry) { \ struct fib6_node *pn; \ - while (fn) { \ + while (1) { \ if (fn->fn_flags & RTN_TL_ROOT) \ goto out; \ pn = fn->parent; \ @@ -529,13 +533,17 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, .nl_u = { .ip6_u = { .daddr = *daddr, - /* TODO: saddr */ }, }, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; + if (saddr) { + memcpy(&fl.fl6_src, saddr, sizeof(*saddr)); + flags |= RT6_LOOKUP_F_HAS_SADDR; + } + dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup); if (dst->error == 0) return (struct rt6_info *) dst; @@ -614,8 +622,6 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - if (rt->rt6i_flags & RTF_REJECT) - rt->u.dst.error = ort->u.dst.error; rt->u.dst.flags |= DST_HOST; rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); } @@ -697,6 +703,7 @@ out2: void ip6_route_input(struct sk_buff *skb) { struct ipv6hdr *iph = skb->nh.ipv6h; + int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi fl = { .iif = skb->dev->ifindex, .nl_u = { @@ -711,7 +718,9 @@ void ip6_route_input(struct sk_buff *skb) }, .proto = iph->nexthdr, }; - int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0; + + if (rt6_need_strict(&iph->daddr)) + flags |= RT6_LOOKUP_F_IFACE; skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input); } @@ -794,6 +803,9 @@ struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) if (rt6_need_strict(&fl->fl6_dst)) flags |= RT6_LOOKUP_F_IFACE; + if (!ipv6_addr_any(&fl->fl6_src)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + return fib6_rule_lookup(fl, flags, ip6_pol_route_output); } @@ -1345,6 +1357,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, struct in6_addr *gateway, struct net_device *dev) { + int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl = { .fl = { .oif = dev->ifindex, @@ -1357,7 +1370,9 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, .gateway = *gateway, }; - int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0; + + if (rt6_need_strict(dest)) + flags |= RT6_LOOKUP_F_IFACE; return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect); } @@ -1527,6 +1542,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) rt->u.dst.output = ort->u.dst.output; memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); + rt->u.dst.error = ort->u.dst.error; rt->u.dst.dev = ort->u.dst.dev; if (rt->u.dst.dev) dev_hold(rt->u.dst.dev); @@ -1730,24 +1746,50 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) * Drop the packet on the floor */ -static int ip6_pkt_discard(struct sk_buff *skb) +static inline int ip6_pkt_drop(struct sk_buff *skb, int code) { int type = ipv6_addr_type(&skb->nh.ipv6h->daddr); if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) IP6_INC_STATS(IPSTATS_MIB_INADDRERRORS); IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOROUTE, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev); kfree_skb(skb); return 0; } +static int ip6_pkt_discard(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_NOROUTE); +} + static int ip6_pkt_discard_out(struct sk_buff *skb) { skb->dev = skb->dst->dev; return ip6_pkt_discard(skb); } +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + +static int ip6_pkt_prohibit(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED); +} + +static int ip6_pkt_prohibit_out(struct sk_buff *skb) +{ + skb->dev = skb->dst->dev; + return ip6_pkt_prohibit(skb); +} + +static int ip6_pkt_blk_hole(struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} + +#endif + /* * Allocate a dst for local (unicast / anycast) address. */ diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 836eecd7e62b..b481a4d780c2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -850,3 +850,7 @@ int __init sit_init(void) inet_del_protocol(&sit_protocol, IPPROTO_IPV6); goto out; } + +module_init(sit_init); +module_exit(sit_cleanup); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2546fc9f0a78..4c2a7c0cafef 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -329,7 +329,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (sk->sk_state == TCP_TIME_WAIT) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); return; } @@ -653,7 +653,7 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 int tot_len = sizeof(struct tcphdr); if (ts) - tot_len += 3*4; + tot_len += TCPOLEN_TSTAMP_ALIGNED; buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); @@ -749,7 +749,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) bh_lock_sock(nsk); return nsk; } - inet_twsk_put((struct inet_timewait_sock *)nsk); + inet_twsk_put(inet_twsk(nsk)); return NULL; } @@ -1237,7 +1237,7 @@ process: skb->dev = NULL; - bh_lock_sock(sk); + bh_lock_sock_nested(sk); ret = 0; if (!sock_owned_by_user(sk)) { #ifdef CONFIG_NET_DMA @@ -1283,18 +1283,17 @@ discard_and_relse: do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); goto discard_it; } if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { TCP_INC_STATS_BH(TCP_MIB_INERRS); - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); goto discard_it; } - switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk, - skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9662561701d1..e0c3934a7e4b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -546,7 +546,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct in6_addr *daddr, *final_p = NULL, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi *fl = &inet->cork.fl; + struct flowi fl; struct dst_entry *dst; int addr_len = msg->msg_namelen; int ulen = len; @@ -626,19 +626,19 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(fl, 0, sizeof(*fl)); + memset(&fl, 0, sizeof(fl)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl->fl_ip_dport = sin6->sin6_port; + fl.fl_ip_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl->fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); if (flowlabel == NULL) return -EINVAL; daddr = &flowlabel->dst; @@ -656,32 +656,32 @@ do_udp_sendmsg: if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl->oif = sin6->sin6_scope_id; + fl.oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl->fl_ip_dport = inet->dport; + fl.fl_ip_dport = inet->dport; daddr = &np->daddr; - fl->fl6_flowlabel = np->flow_label; + fl.fl6_flowlabel = np->flow_label; connected = 1; } - if (!fl->oif) - fl->oif = sk->sk_bound_dev_if; + if (!fl.oif) + fl.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -695,39 +695,39 @@ do_udp_sendmsg: opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); - fl->proto = IPPROTO_UDP; - ipv6_addr_copy(&fl->fl6_dst, daddr); - if (ipv6_addr_any(&fl->fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl->fl6_src, &np->saddr); - fl->fl_ip_sport = inet->sport; + fl.proto = IPPROTO_UDP; + ipv6_addr_copy(&fl.fl6_dst, daddr); + if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) + ipv6_addr_copy(&fl.fl6_src, &np->saddr); + fl.fl_ip_sport = inet->sport; /* merge ip6_build_xmit from ip6_output */ if (opt && opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl->fl6_dst); - ipv6_addr_copy(&fl->fl6_dst, rt0->addr); + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; connected = 0; } - if (!fl->oif && ipv6_addr_is_multicast(&fl->fl6_dst)) { - fl->oif = np->mcast_oif; + if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { + fl.oif = np->mcast_oif; connected = 0; } - security_sk_classify_flow(sk, fl); + security_sk_classify_flow(sk, &fl); - err = ip6_sk_dst_lookup(sk, &dst, fl); + err = ip6_sk_dst_lookup(sk, &dst, &fl); if (err) goto out; if (final_p) - ipv6_addr_copy(&fl->fl6_dst, final_p); + ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, fl, sk, 0)) < 0) + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) goto out; if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl->fl6_dst)) + if (ipv6_addr_is_multicast(&fl.fl6_dst)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -763,21 +763,23 @@ back_from_confirm: do_append_data: up->len += ulen; err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, fl, + sizeof(struct udphdr), hlimit, tclass, opt, &fl, (struct rt6_info*)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) err = udp_v6_push_pending_frames(sk, up); + else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) + up->pending = 0; if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ? + ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? &np->daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl->fl6_src, &np->saddr) ? + ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? &np->saddr : #endif NULL); diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index a40a05789013..5c8b7a568800 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -16,10 +16,10 @@ #include <net/ipv6.h> #include <net/xfrm.h> -int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi) +int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) { int err; - u32 seq; + __be32 seq; struct xfrm_state *xfrm_vec[XFRM_MAX_DEPTH]; struct xfrm_state *x; int xfrm_nr = 0; diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c new file mode 100644 index 000000000000..edcfffa9e87b --- /dev/null +++ b/net/ipv6/xfrm6_mode_beet.c @@ -0,0 +1,107 @@ +/* + * xfrm6_mode_beet.c - BEET mode encapsulation for IPv6. + * + * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com> + * Miika Komu <miika@iki.fi> + * Herbert Xu <herbert@gondor.apana.org.au> + * Abhinav Pathak <abhinav.pathak@hiit.fi> + * Jeff Ahrenholz <ahrenholz@gmail.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/dsfield.h> +#include <net/dst.h> +#include <net/inet_ecn.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +/* Add encapsulation header. + * + * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt. + * The following fields in it shall be filled in by x->type->output: + * payload_len + * + * On exit, skb->h will be set to the start of the encapsulation header to be + * filled in by x->type->output and skb->nh will be set to the nextheader field + * of the extension header directly preceding the encapsulation header, or in + * its absence, that of the top IP header. The value of skb->data will always + * point to the top IP header. + */ +static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph, *top_iph; + u8 *prevhdr; + int hdr_len; + + skb_push(skb, x->props.header_len); + iph = skb->nh.ipv6h; + + hdr_len = ip6_find_1stfragopt(skb, &prevhdr); + skb->nh.raw = prevhdr - x->props.header_len; + skb->h.raw = skb->data + hdr_len; + memmove(skb->data, iph, hdr_len); + + skb->nh.raw = skb->data; + top_iph = skb->nh.ipv6h; + skb->nh.raw = &top_iph->nexthdr; + skb->h.ipv6h = top_iph + 1; + + ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); + ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + + return 0; +} + +static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *ip6h; + int size = sizeof(struct ipv6hdr); + int err = -EINVAL; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + + skb_push(skb, size); + memmove(skb->data, skb->nh.raw, size); + skb->nh.raw = skb->data; + + skb->mac.raw = memmove(skb->data - skb->mac_len, + skb->mac.raw, skb->mac_len); + + ip6h = skb->nh.ipv6h; + ip6h->payload_len = htons(skb->len - size); + ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6); + ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6); + err = 0; +out: + return err; +} + +static struct xfrm_mode xfrm6_beet_mode = { + .input = xfrm6_beet_input, + .output = xfrm6_beet_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_BEET, +}; + +static int __init xfrm6_beet_init(void) +{ + return xfrm_register_mode(&xfrm6_beet_mode, AF_INET6); +} + +static void __exit xfrm6_beet_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_beet_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_beet_init); +module_exit(xfrm6_beet_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_BEET); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6a252e2134d1..d400f8fae129 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -25,12 +25,14 @@ static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl) +static int xfrm6_dst_lookup(struct xfrm_dst **xdst, struct flowi *fl) { - int err = 0; - *dst = (struct xfrm_dst*)ip6_route_output(NULL, fl); - if (!*dst) - err = -ENETUNREACH; + struct dst_entry *dst = ip6_route_output(NULL, fl); + int err = dst->error; + if (!err) + *xdst = (struct xfrm_dst *) dst; + else + dst_release(dst); return err; } @@ -73,7 +75,7 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) xdst->u.rt6.rt6i_src.plen); if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) && ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) && - xfrm_bundle_ok(xdst, fl, AF_INET6, + xfrm_bundle_ok(policy, xdst, fl, AF_INET6, (xdst->u.rt6.rt6i_dst.plen != 128 || xdst->u.rt6.rt6i_src.plen != 128))) { dst_clone(dst); diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 711bfafb2472..9ddaa9d41539 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -29,9 +29,9 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = ~0; + x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = ~0; + x->sel.sport_mask = htons(0xffff); x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->sel.proto = fl->proto; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 59685ee8f700..7af227bb1551 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -258,7 +258,7 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_tunnel_rcv(struct sk_buff *skb) { struct ipv6hdr *iph = skb->nh.ipv6h; - u32 spi; + __be32 spi; spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr); return xfrm6_rcv_spi(skb, spi); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 17699eeb64d7..7e1aea89ef05 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -132,13 +132,14 @@ static void irda_disconnect_indication(void *instance, void *sap, /* Prevent race conditions with irda_release() and irda_shutdown() */ if (!sock_flag(sk, SOCK_DEAD) && sk->sk_state != TCP_CLOSE) { + lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk->sk_shutdown |= SEND_SHUTDOWN; sk->sk_state_change(sk); - /* Uh-oh... Should use sock_orphan ? */ - sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); + release_sock(sk); /* Close our TSAP. * If we leave it open, IrLMP put it back into the list of @@ -308,7 +309,8 @@ static void irda_connect_response(struct irda_sock *self) IRDA_ASSERT(self != NULL, return;); - skb = alloc_skb(64, GFP_ATOMIC); + skb = alloc_skb(TTP_MAX_HEADER + TTP_SAR_HEADER, + GFP_ATOMIC); if (skb == NULL) { IRDA_DEBUG(0, "%s() Unable to allocate sk_buff!\n", __FUNCTION__); @@ -1212,6 +1214,7 @@ static int irda_release(struct socket *sock) if (sk == NULL) return 0; + lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; sk->sk_state_change(sk); @@ -1221,6 +1224,7 @@ static int irda_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; + release_sock(sk); /* Purge queues (see sock_init_data()) */ skb_queue_purge(&sk->sk_receive_queue); @@ -1353,6 +1357,7 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __FUNCTION__); IRDA_ASSERT(self != NULL, return -1;); + IRDA_ASSERT(!sock_error(sk), return -1;); skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); @@ -1405,6 +1410,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(3, "%s()\n", __FUNCTION__); IRDA_ASSERT(self != NULL, return -1;); + IRDA_ASSERT(!sock_error(sk), return -1;); if (sock->flags & __SO_ACCEPTCON) return(-EINVAL); diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c index 959874b6451f..c8e0d89ee11f 100644 --- a/net/irda/ircomm/ircomm_lmp.c +++ b/net/irda/ircomm/ircomm_lmp.c @@ -81,7 +81,7 @@ static int ircomm_lmp_connect_response(struct ircomm_cb *self, /* Any userdata supplied? */ if (userdata == NULL) { - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (!tx_skb) return -ENOMEM; @@ -115,7 +115,7 @@ static int ircomm_lmp_disconnect_request(struct ircomm_cb *self, IRDA_DEBUG(0, "%s()\n", __FUNCTION__ ); if (!userdata) { - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (!tx_skb) return -ENOMEM; diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 3bcdb467efc5..d50a02030ad7 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -79,7 +79,7 @@ static struct tty_driver *driver; hashbin_t *ircomm_tty = NULL; -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = ircomm_tty_open, .close = ircomm_tty_close, .write = ircomm_tty_write, diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 61128aa05b40..415cf4eec23b 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -345,10 +345,11 @@ static void iriap_disconnect_request(struct iriap_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IAS_MAGIC, return;); - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (tx_skb == NULL) { - IRDA_DEBUG(0, "%s(), Could not allocate an sk_buff of length %d\n", - __FUNCTION__, 64); + IRDA_DEBUG(0, + "%s(), Could not allocate an sk_buff of length %d\n", + __FUNCTION__, LMP_MAX_HEADER); return; } @@ -701,7 +702,7 @@ void iriap_send_ack(struct iriap_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IAS_MAGIC, return;); - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER + 1, GFP_ATOMIC); if (!tx_skb) return; diff --git a/net/irda/iriap_event.c b/net/irda/iriap_event.c index da17395df05a..99b18dc7a0b7 100644 --- a/net/irda/iriap_event.c +++ b/net/irda/iriap_event.c @@ -365,7 +365,7 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event, switch (event) { case IAP_LM_CONNECT_INDICATION: - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (tx_skb == NULL) { IRDA_WARNING("%s: unable to malloc!\n", __FUNCTION__); return; diff --git a/net/irda/irias_object.c b/net/irda/irias_object.c index a154b1d71c0f..56292ab7d652 100644 --- a/net/irda/irias_object.c +++ b/net/irda/irias_object.c @@ -43,7 +43,7 @@ struct ias_value irias_missing = { IAS_MISSING, 0, 0, 0, {0}}; * * Faster, check boundary... Jean II */ -static char *strndup(char *str, int max) +static char *strndup(char *str, size_t max) { char *new_str; int len; diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index 7dd0a2fe1d20..9b962f247714 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -636,7 +636,8 @@ void irlan_get_provider_info(struct irlan_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(64, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER, + GFP_ATOMIC); if (!skb) return; @@ -668,7 +669,10 @@ void irlan_open_data_channel(struct irlan_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(64, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_STRING_PARAMETER_LEN("MEDIA", "802.3") + + IRLAN_STRING_PARAMETER_LEN("ACCESS_TYPE", "DIRECT"), + GFP_ATOMIC); if (!skb) return; @@ -704,7 +708,9 @@ void irlan_close_data_channel(struct irlan_cb *self) if (self->client.tsap_ctrl == NULL) return; - skb = alloc_skb(64, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_BYTE_PARAMETER_LEN("DATA_CHAN"), + GFP_ATOMIC); if (!skb) return; @@ -715,7 +721,7 @@ void irlan_close_data_channel(struct irlan_cb *self) /* Build frame */ frame[0] = CMD_CLOSE_DATA_CHAN; - frame[1] = 0x01; /* Two parameters */ + frame[1] = 0x01; /* One parameter */ irlan_insert_byte_param(skb, "DATA_CHAN", self->dtsap_sel_data); @@ -739,7 +745,11 @@ static void irlan_open_unicast_addr(struct irlan_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(128, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_BYTE_PARAMETER_LEN("DATA_CHAN") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "DIRECTED") + + IRLAN_STRING_PARAMETER_LEN("FILTER_MODE", "FILTER"), + GFP_ATOMIC); if (!skb) return; @@ -777,7 +787,12 @@ void irlan_set_broadcast_filter(struct irlan_cb *self, int status) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(128, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_BYTE_PARAMETER_LEN("DATA_CHAN") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "BROADCAST") + + /* We may waste one byte here...*/ + IRLAN_STRING_PARAMETER_LEN("FILTER_MODE", "FILTER"), + GFP_ATOMIC); if (!skb) return; @@ -816,7 +831,12 @@ void irlan_set_multicast_filter(struct irlan_cb *self, int status) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(128, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_BYTE_PARAMETER_LEN("DATA_CHAN") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "MULTICAST") + + /* We may waste one byte here...*/ + IRLAN_STRING_PARAMETER_LEN("FILTER_MODE", "NONE"), + GFP_ATOMIC); if (!skb) return; @@ -856,7 +876,12 @@ static void irlan_get_unicast_addr(struct irlan_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(128, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_BYTE_PARAMETER_LEN("DATA_CHAN") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "DIRECTED") + + IRLAN_STRING_PARAMETER_LEN("FILTER_OPERATION", + "DYNAMIC"), + GFP_ATOMIC); if (!skb) return; @@ -891,7 +916,10 @@ void irlan_get_media_char(struct irlan_cb *self) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(64, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + IRLAN_STRING_PARAMETER_LEN("MEDIA", "802.3"), + GFP_ATOMIC); + if (!skb) return; diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c index 9c0df86044d7..58efde919667 100644 --- a/net/irda/irlan/irlan_provider.c +++ b/net/irda/irlan/irlan_provider.c @@ -296,7 +296,14 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command, IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); - skb = alloc_skb(128, GFP_ATOMIC); + skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + + /* Bigger param length comes from CMD_GET_MEDIA_CHAR */ + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "DIRECTED") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "BORADCAST") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "MULTICAST") + + IRLAN_STRING_PARAMETER_LEN("ACCESS_TYPE", "HOSTED"), + GFP_ATOMIC); + if (!skb) return; @@ -354,8 +361,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command, } else skb->data[1] = 0x02; /* 2 parameters */ irlan_insert_byte_param(skb, "DATA_CHAN", self->stsap_sel_data); - irlan_insert_array_param(skb, "RECONNECT_KEY", "LINUX RULES!", - 12); + irlan_insert_string_param(skb, "RECONNECT_KEY", "LINUX RULES!"); break; case CMD_FILTER_OPERATION: irlan_filter_request(self, skb); diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index ccb983bf0f4a..dba349c832d0 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -117,7 +117,9 @@ void irlap_send_snrm_frame(struct irlap_cb *self, struct qos_info *qos) IRDA_ASSERT(self->magic == LAP_MAGIC, return;); /* Allocate frame */ - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct snrm_frame) + + IRLAP_NEGOCIATION_PARAMS_LEN, + GFP_ATOMIC); if (!tx_skb) return; @@ -136,7 +138,7 @@ void irlap_send_snrm_frame(struct irlap_cb *self, struct qos_info *qos) * If we are establishing a connection then insert QoS paramerters */ if (qos) { - skb_put(tx_skb, 9); /* 21 left */ + skb_put(tx_skb, 9); /* 25 left */ frame->saddr = cpu_to_le32(self->saddr); frame->daddr = cpu_to_le32(self->daddr); @@ -210,7 +212,9 @@ void irlap_send_ua_response_frame(struct irlap_cb *self, struct qos_info *qos) IRDA_ASSERT(self->magic == LAP_MAGIC, return;); /* Allocate frame */ - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct ua_frame) + + IRLAP_NEGOCIATION_PARAMS_LEN, + GFP_ATOMIC); if (!tx_skb) return; @@ -245,23 +249,23 @@ void irlap_send_ua_response_frame(struct irlap_cb *self, struct qos_info *qos) void irlap_send_dm_frame( struct irlap_cb *self) { struct sk_buff *tx_skb = NULL; - __u8 *frame; + struct dm_frame *frame; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LAP_MAGIC, return;); - tx_skb = alloc_skb(32, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct dm_frame), GFP_ATOMIC); if (!tx_skb) return; - frame = skb_put(tx_skb, 2); + frame = (struct dm_frame *)skb_put(tx_skb, 2); if (self->state == LAP_NDM) - frame[0] = CBROADCAST; + frame->caddr = CBROADCAST; else - frame[0] = self->caddr; + frame->caddr = self->caddr; - frame[1] = DM_RSP | PF_BIT; + frame->control = DM_RSP | PF_BIT; irlap_queue_xmit(self, tx_skb); } @@ -275,21 +279,21 @@ void irlap_send_dm_frame( struct irlap_cb *self) void irlap_send_disc_frame(struct irlap_cb *self) { struct sk_buff *tx_skb = NULL; - __u8 *frame; + struct disc_frame *frame; IRDA_DEBUG(3, "%s()\n", __FUNCTION__); IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LAP_MAGIC, return;); - tx_skb = alloc_skb(16, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct disc_frame), GFP_ATOMIC); if (!tx_skb) return; - frame = skb_put(tx_skb, 2); + frame = (struct disc_frame *)skb_put(tx_skb, 2); - frame[0] = self->caddr | CMD_FRAME; - frame[1] = DISC_CMD | PF_BIT; + frame->caddr = self->caddr | CMD_FRAME; + frame->control = DISC_CMD | PF_BIT; irlap_queue_xmit(self, tx_skb); } @@ -315,7 +319,8 @@ void irlap_send_discovery_xid_frame(struct irlap_cb *self, int S, __u8 s, IRDA_ASSERT(self->magic == LAP_MAGIC, return;); IRDA_ASSERT(discovery != NULL, return;); - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct xid_frame) + IRLAP_DISCOVERY_INFO_LEN, + GFP_ATOMIC); if (!tx_skb) return; @@ -573,18 +578,18 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self, void irlap_send_rr_frame(struct irlap_cb *self, int command) { struct sk_buff *tx_skb; - __u8 *frame; + struct rr_frame *frame; - tx_skb = alloc_skb(16, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct rr_frame), GFP_ATOMIC); if (!tx_skb) return; - frame = skb_put(tx_skb, 2); + frame = (struct rr_frame *)skb_put(tx_skb, 2); - frame[0] = self->caddr; - frame[0] |= (command) ? CMD_FRAME : 0; + frame->caddr = self->caddr; + frame->caddr |= (command) ? CMD_FRAME : 0; - frame[1] = RR | PF_BIT | (self->vr << 5); + frame->control = RR | PF_BIT | (self->vr << 5); irlap_queue_xmit(self, tx_skb); } @@ -598,16 +603,16 @@ void irlap_send_rr_frame(struct irlap_cb *self, int command) void irlap_send_rd_frame(struct irlap_cb *self) { struct sk_buff *tx_skb; - __u8 *frame; + struct rd_frame *frame; - tx_skb = alloc_skb(16, GFP_ATOMIC); + tx_skb = alloc_skb(sizeof(struct rd_frame), GFP_ATOMIC); if (!tx_skb) return; - frame = skb_put(tx_skb, 2); + frame = (struct rd_frame *)skb_put(tx_skb, 2); - frame[0] = self->caddr; - frame[1] = RD_RSP | PF_BIT; + frame->caddr = self->caddr; + frame->caddr = RD_RSP | PF_BIT; irlap_queue_xmit(self, tx_skb); } @@ -1214,7 +1219,7 @@ void irlap_send_test_frame(struct irlap_cb *self, __u8 caddr, __u32 daddr, struct test_frame *frame; __u8 *info; - tx_skb = alloc_skb(cmd->len+sizeof(struct test_frame), GFP_ATOMIC); + tx_skb = alloc_skb(cmd->len + sizeof(struct test_frame), GFP_ATOMIC); if (!tx_skb) return; diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index c440913dee14..5073261b9d0c 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -392,7 +392,7 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel, /* Any userdata? */ if (tx_skb == NULL) { - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (!tx_skb) return -ENOMEM; diff --git a/net/irda/irttp.c b/net/irda/irttp.c index 42acf1cde737..3c2e70b77df1 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -804,12 +804,12 @@ static inline void irttp_give_credit(struct tsap_cb *self) self->send_credit, self->avail_credit, self->remote_credit); /* Give credit to peer */ - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(TTP_MAX_HEADER, GFP_ATOMIC); if (!tx_skb) return; /* Reserve space for LMP, and LAP header */ - skb_reserve(tx_skb, self->max_header_size); + skb_reserve(tx_skb, LMP_MAX_HEADER); /* * Since we can transmit and receive frames concurrently, @@ -1093,7 +1093,8 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, /* Any userdata supplied? */ if (userdata == NULL) { - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(TTP_MAX_HEADER + TTP_SAR_HEADER, + GFP_ATOMIC); if (!tx_skb) return -ENOMEM; @@ -1341,7 +1342,8 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size, /* Any userdata supplied? */ if (userdata == NULL) { - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(TTP_MAX_HEADER + TTP_SAR_HEADER, + GFP_ATOMIC); if (!tx_skb) return -ENOMEM; @@ -1540,14 +1542,14 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata, if (!userdata) { struct sk_buff *tx_skb; - tx_skb = alloc_skb(64, GFP_ATOMIC); + tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC); if (!tx_skb) return -ENOMEM; /* * Reserve space for MUX and LAP header */ - skb_reserve(tx_skb, TTP_MAX_HEADER); + skb_reserve(tx_skb, LMP_MAX_HEADER); userdata = tx_skb; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 83b443ddc72f..20ff7cca1d07 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2140,7 +2140,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.sport) - xp->selector.sport_mask = ~0; + xp->selector.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1], pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.daddr); @@ -2153,7 +2153,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h xp->selector.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.dport) - xp->selector.dport_mask = ~0; + xp->selector.dport_mask = htons(0xffff); sec_ctx = (struct sadb_x_sec_ctx *) ext_hdrs[SADB_X_EXT_SEC_CTX-1]; if (sec_ctx != NULL) { @@ -2243,7 +2243,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.sport) - sel.sport_mask = ~0; + sel.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1], pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); @@ -2251,7 +2251,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.dport) - sel.dport_mask = ~0; + sel.dport_mask = htons(0xffff); sec_ctx = (struct sadb_x_sec_ctx *) ext_hdrs[SADB_X_EXT_SEC_CTX-1]; memset(&tmp, 0, sizeof(struct xfrm_policy)); @@ -2928,11 +2928,6 @@ static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, if (*dir) goto out; } - else { - *dir = security_xfrm_sock_policy_alloc(xp, sk); - if (*dir) - goto out; - } *dir = pol->sadb_x_policy_dir-1; return xp; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0a28d2c5c44f..f619c6527266 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -209,7 +209,9 @@ config NETFILTER_XT_TARGET_SECMARK config NETFILTER_XT_TARGET_CONNSECMARK tristate '"CONNSECMARK" target support' - depends on NETFILTER_XTABLES && (NF_CONNTRACK_SECMARK || IP_NF_CONNTRACK_SECMARK) + depends on NETFILTER_XTABLES && \ + ((NF_CONNTRACK && NF_CONNTRACK_SECMARK) || \ + (IP_NF_CONNTRACK && IP_NF_CONNTRACK_SECMARK)) help The CONNSECMARK target copies security markings from packets to connections, and restores security markings from connections @@ -365,7 +367,7 @@ config NETFILTER_XT_MATCH_MULTIPORT config NETFILTER_XT_MATCH_PHYSDEV tristate '"physdev" match support' - depends on NETFILTER_XTABLES && BRIDGE_NETFILTER + depends on NETFILTER_XTABLES && BRIDGE && BRIDGE_NETFILTER help Physdev packet matching matches against the physical bridge ports the IP packet arrived on or will leave by. diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1721f7c78c77..bd0156a28ecd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -47,13 +47,6 @@ MODULE_LICENSE("GPL"); static char __initdata version[] = "0.93"; -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - - static inline int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, @@ -410,7 +403,6 @@ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); - DEBUGP("entered %s\n", __FUNCTION__); return 0; } @@ -425,9 +417,6 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, - cb->args[0], *id); - read_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { @@ -471,7 +460,6 @@ out: if (last) nf_ct_put(last); - DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); return skb->len; } @@ -482,8 +470,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct nf_conntrack_tuple *tuple) struct nf_conntrack_l3proto *l3proto; int ret = 0; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_IP_MAX, attr); l3proto = nf_ct_l3proto_find_get(tuple->src.l3num); @@ -493,8 +479,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct nf_conntrack_tuple *tuple) nf_ct_l3proto_put(l3proto); - DEBUGP("leaving\n"); - return ret; } @@ -510,8 +494,6 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr, struct nf_conntrack_protocol *proto; int ret = 0; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_PROTO_MAX, attr); if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto)) @@ -538,8 +520,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct nf_conntrack_tuple *tuple, struct nfattr *tb[CTA_TUPLE_MAX]; int err; - DEBUGP("entered %s\n", __FUNCTION__); - memset(tuple, 0, sizeof(*tuple)); nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]); @@ -566,10 +546,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct nf_conntrack_tuple *tuple, else tuple->dst.dir = IP_CT_DIR_ORIGINAL; - NF_CT_DUMP_TUPLE(tuple); - - DEBUGP("leaving\n"); - return 0; } @@ -586,8 +562,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr, struct nfattr *tb[CTA_PROTONAT_MAX]; struct ip_nat_protocol *npt; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr); if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat)) @@ -606,7 +580,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr, ip_nat_proto_put(npt); - DEBUGP("leaving\n"); return 0; } @@ -622,8 +595,6 @@ ctnetlink_parse_nat(struct nfattr *nat, struct nfattr *tb[CTA_NAT_MAX]; int err; - DEBUGP("entered %s\n", __FUNCTION__); - memset(range, 0, sizeof(*range)); nfattr_parse_nested(tb, CTA_NAT_MAX, nat); @@ -649,7 +620,6 @@ ctnetlink_parse_nat(struct nfattr *nat, if (err < 0) return err; - DEBUGP("leaving\n"); return 0; } #endif @@ -659,8 +629,6 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name) { struct nfattr *tb[CTA_HELP_MAX]; - DEBUGP("entered %s\n", __FUNCTION__); - nfattr_parse_nested(tb, CTA_HELP_MAX, attr); if (!tb[CTA_HELP_NAME-1]) @@ -690,8 +658,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_MAX, cta_min)) return -EINVAL; @@ -709,10 +675,8 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; h = nf_conntrack_find_get(&tuple, NULL); - if (!h) { - DEBUGP("tuple not found in conntrack hash\n"); + if (!h) return -ENOENT; - } ct = nf_ct_tuplehash_to_ctrack(h); @@ -727,7 +691,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, ct->timeout.function((unsigned long)ct); nf_ct_put(ct); - DEBUGP("leaving\n"); return 0; } @@ -744,8 +707,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nlh->nlmsg_flags & NLM_F_DUMP) { u32 rlen; @@ -779,11 +740,9 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; h = nf_conntrack_find_get(&tuple, NULL); - if (!h) { - DEBUGP("tuple not found in conntrack hash"); + if (!h) return -ENOENT; - } - DEBUGP("tuple found\n"); + ct = nf_ct_tuplehash_to_ctrack(h); err = -ENOMEM; @@ -804,7 +763,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) goto out; - DEBUGP("leaving\n"); return 0; free: @@ -876,8 +834,6 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[]) char *helpname; int err; - DEBUGP("entered %s\n", __FUNCTION__); - if (!help) { /* FIXME: we need to reallocate and rehash */ return -EBUSY; @@ -954,8 +910,6 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nfattr *cda[]) { int err; - DEBUGP("entered %s\n", __FUNCTION__); - if (cda[CTA_HELP-1]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) @@ -985,7 +939,6 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nfattr *cda[]) ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); #endif - DEBUGP("all done\n"); return 0; } @@ -997,8 +950,6 @@ ctnetlink_create_conntrack(struct nfattr *cda[], struct nf_conn *ct; int err = -EINVAL; - DEBUGP("entered %s\n", __FUNCTION__); - ct = nf_conntrack_alloc(otuple, rtuple); if (ct == NULL || IS_ERR(ct)) return -ENOMEM; @@ -1028,7 +979,6 @@ ctnetlink_create_conntrack(struct nfattr *cda[], add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); - DEBUGP("conntrack with id %u inserted\n", ct->id); return 0; err: @@ -1046,8 +996,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_MAX, cta_min)) return -EINVAL; @@ -1071,7 +1019,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (h == NULL) { write_unlock_bh(&nf_conntrack_lock); - DEBUGP("no such conntrack, create new\n"); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) err = ctnetlink_create_conntrack(cda, &otuple, &rtuple); @@ -1087,7 +1034,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, /* We manipulate the conntrack inside the global conntrack table lock, * so there's no need to increase the refcount */ - DEBUGP("conntrack found\n"); err = -EEXIST; if (!(nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_conntrack(nf_ct_tuplehash_to_ctrack(h), cda); @@ -1268,8 +1214,6 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id); - read_lock_bh(&nf_conntrack_lock); list_for_each_prev(i, &nf_conntrack_expect_list) { exp = (struct nf_conntrack_expect *) i; @@ -1287,8 +1231,6 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) out: read_unlock_bh(&nf_conntrack_lock); - DEBUGP("leaving, last id=%llu\n", *id); - return skb->len; } @@ -1308,8 +1250,6 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) return -EINVAL; @@ -1460,8 +1400,6 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) struct nf_conn_help *help; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); if (err < 0) @@ -1516,8 +1454,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - DEBUGP("entered %s\n", __FUNCTION__); - if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) return -EINVAL; @@ -1546,8 +1482,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, err = ctnetlink_change_expect(exp, cda); write_unlock_bh(&nf_conntrack_lock); - DEBUGP("leaving\n"); - return err; } diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index db9b896e57c8..39e117502bd7 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -68,7 +68,7 @@ static int __init xt_nfqueue_init(void) static void __exit xt_nfqueue_fini(void) { - xt_register_targets(xt_nfqueue_target, ARRAY_SIZE(xt_nfqueue_target)); + xt_unregister_targets(xt_nfqueue_target, ARRAY_SIZE(xt_nfqueue_target)); } module_init(xt_nfqueue_init); diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 92a5726ef237..a8f03057dbde 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -147,7 +147,7 @@ static int __init xt_connmark_init(void) static void __exit xt_connmark_fini(void) { - xt_register_matches(xt_connmark_match, ARRAY_SIZE(xt_connmark_match)); + xt_unregister_matches(xt_connmark_match, ARRAY_SIZE(xt_connmark_match)); } module_init(xt_connmark_init); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 4125a55f469f..a6ce1d6d5c59 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -32,6 +32,7 @@ #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> +#include <linux/audit.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -162,8 +163,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info) int nla_a_rem; int nla_b_rem; - if (!info->attrs[NLBL_CIPSOV4_A_DOI] || - !info->attrs[NLBL_CIPSOV4_A_TAGLST] || + if (!info->attrs[NLBL_CIPSOV4_A_TAGLST] || !info->attrs[NLBL_CIPSOV4_A_MLSLVLLST]) return -EINVAL; @@ -344,8 +344,7 @@ static int netlbl_cipsov4_add_pass(struct genl_info *info) int ret_val; struct cipso_v4_doi *doi_def = NULL; - if (!info->attrs[NLBL_CIPSOV4_A_DOI] || - !info->attrs[NLBL_CIPSOV4_A_TAGLST]) + if (!info->attrs[NLBL_CIPSOV4_A_TAGLST]) return -EINVAL; doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL); @@ -381,21 +380,40 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; - u32 map_type; + u32 type; + u32 doi; + const char *type_str = "(unknown)"; + struct audit_buffer *audit_buf; + struct netlbl_audit audit_info; - if (!info->attrs[NLBL_CIPSOV4_A_MTYPE]) + if (!info->attrs[NLBL_CIPSOV4_A_DOI] || + !info->attrs[NLBL_CIPSOV4_A_MTYPE]) return -EINVAL; - map_type = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE]); - switch (map_type) { + doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); + netlbl_netlink_auditinfo(skb, &audit_info); + + type = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE]); + switch (type) { case CIPSO_V4_MAP_STD: + type_str = "std"; ret_val = netlbl_cipsov4_add_std(info); break; case CIPSO_V4_MAP_PASS: + type_str = "pass"; ret_val = netlbl_cipsov4_add_pass(info); break; } + audit_buf = netlbl_audit_start_common(AUDIT_MAC_CIPSOV4_ADD, + &audit_info); + audit_log_format(audit_buf, + " cipso_doi=%u cipso_type=%s res=%u", + doi, + type_str, + ret_val == 0 ? 1 : 0); + audit_log_end(audit_buf); + return ret_val; } @@ -653,12 +671,27 @@ static int netlbl_cipsov4_listall(struct sk_buff *skb, static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; - u32 doi; + u32 doi = 0; + struct audit_buffer *audit_buf; + struct netlbl_audit audit_info; - if (info->attrs[NLBL_CIPSOV4_A_DOI]) { - doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); - ret_val = cipso_v4_doi_remove(doi, netlbl_cipsov4_doi_free); - } + if (!info->attrs[NLBL_CIPSOV4_A_DOI]) + return -EINVAL; + + doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); + netlbl_netlink_auditinfo(skb, &audit_info); + + ret_val = cipso_v4_doi_remove(doi, + &audit_info, + netlbl_cipsov4_doi_free); + + audit_buf = netlbl_audit_start_common(AUDIT_MAC_CIPSOV4_DEL, + &audit_info); + audit_log_format(audit_buf, + " cipso_doi=%u res=%u", + doi, + ret_val == 0 ? 1 : 0); + audit_log_end(audit_buf); return ret_val; } diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f56d7a8ac7b7..af4371d3b459 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -35,12 +35,14 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/string.h> +#include <linux/audit.h> #include <net/netlabel.h> #include <net/cipso_ipv4.h> #include <asm/bug.h> #include "netlabel_mgmt.h" #include "netlabel_domainhash.h" +#include "netlabel_user.h" struct netlbl_domhsh_tbl { struct list_head *tbl; @@ -186,6 +188,7 @@ int netlbl_domhsh_init(u32 size) /** * netlbl_domhsh_add - Adds a entry to the domain hash table * @entry: the entry to add + * @audit_info: NetLabel audit information * * Description: * Adds a new entry to the domain hash table and handles any updates to the @@ -193,10 +196,13 @@ int netlbl_domhsh_init(u32 size) * negative on failure. * */ -int netlbl_domhsh_add(struct netlbl_dom_map *entry) +int netlbl_domhsh_add(struct netlbl_dom_map *entry, + struct netlbl_audit *audit_info) { int ret_val; u32 bkt; + struct audit_buffer *audit_buf; + char *audit_domain; switch (entry->type) { case NETLBL_NLTYPE_UNLABELED: @@ -236,6 +242,26 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry) spin_unlock(&netlbl_domhsh_def_lock); } else ret_val = -EINVAL; + + if (entry->domain != NULL) + audit_domain = entry->domain; + else + audit_domain = "(default)"; + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_ADD, audit_info); + audit_log_format(audit_buf, " nlbl_domain=%s", audit_domain); + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + audit_log_format(audit_buf, " nlbl_protocol=unlbl"); + break; + case NETLBL_NLTYPE_CIPSOV4: + audit_log_format(audit_buf, + " nlbl_protocol=cipsov4 cipso_doi=%u", + entry->type_def.cipsov4->doi); + break; + } + audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0); + audit_log_end(audit_buf); + rcu_read_unlock(); if (ret_val != 0) { @@ -254,6 +280,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry) /** * netlbl_domhsh_add_default - Adds the default entry to the domain hash table * @entry: the entry to add + * @audit_info: NetLabel audit information * * Description: * Adds a new default entry to the domain hash table and handles any updates @@ -261,14 +288,16 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry) * negative on failure. * */ -int netlbl_domhsh_add_default(struct netlbl_dom_map *entry) +int netlbl_domhsh_add_default(struct netlbl_dom_map *entry, + struct netlbl_audit *audit_info) { - return netlbl_domhsh_add(entry); + return netlbl_domhsh_add(entry, audit_info); } /** * netlbl_domhsh_remove - Removes an entry from the domain hash table * @domain: the domain to remove + * @audit_info: NetLabel audit information * * Description: * Removes an entry from the domain hash table and handles any updates to the @@ -276,10 +305,12 @@ int netlbl_domhsh_add_default(struct netlbl_dom_map *entry) * negative on failure. * */ -int netlbl_domhsh_remove(const char *domain) +int netlbl_domhsh_remove(const char *domain, struct netlbl_audit *audit_info) { int ret_val = -ENOENT; struct netlbl_dom_map *entry; + struct audit_buffer *audit_buf; + char *audit_domain; rcu_read_lock(); if (domain != NULL) @@ -316,6 +347,18 @@ int netlbl_domhsh_remove(const char *domain) ret_val = -ENOENT; spin_unlock(&netlbl_domhsh_def_lock); } + + if (entry->domain != NULL) + audit_domain = entry->domain; + else + audit_domain = "(default)"; + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); + audit_log_format(audit_buf, + " nlbl_domain=%s res=%u", + audit_domain, + ret_val == 0 ? 1 : 0); + audit_log_end(audit_buf); + if (ret_val == 0) call_rcu(&entry->rcu, netlbl_domhsh_free_entry); @@ -326,6 +369,7 @@ remove_return: /** * netlbl_domhsh_remove_default - Removes the default entry from the table + * @audit_info: NetLabel audit information * * Description: * Removes/resets the default entry for the domain hash table and handles any @@ -333,9 +377,9 @@ remove_return: * success, non-zero on failure. * */ -int netlbl_domhsh_remove_default(void) +int netlbl_domhsh_remove_default(struct netlbl_audit *audit_info) { - return netlbl_domhsh_remove(NULL); + return netlbl_domhsh_remove(NULL, audit_info); } /** diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h index 02af72a7877c..3689956c3436 100644 --- a/net/netlabel/netlabel_domainhash.h +++ b/net/netlabel/netlabel_domainhash.h @@ -57,9 +57,11 @@ struct netlbl_dom_map { int netlbl_domhsh_init(u32 size); /* Manipulate the domain hash table */ -int netlbl_domhsh_add(struct netlbl_dom_map *entry); -int netlbl_domhsh_add_default(struct netlbl_dom_map *entry); -int netlbl_domhsh_remove_default(void); +int netlbl_domhsh_add(struct netlbl_dom_map *entry, + struct netlbl_audit *audit_info); +int netlbl_domhsh_add_default(struct netlbl_dom_map *entry, + struct netlbl_audit *audit_info); +int netlbl_domhsh_remove_default(struct netlbl_audit *audit_info); struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain); int netlbl_domhsh_walk(u32 *skip_bkt, u32 *skip_chain, diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 54fb7de3c2b1..ff971103fd0c 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -200,7 +200,7 @@ void netlbl_cache_invalidate(void) int netlbl_cache_add(const struct sk_buff *skb, const struct netlbl_lsm_secattr *secattr) { - if (secattr->cache.data == NULL) + if (secattr->cache == NULL) return -ENOMSG; if (CIPSO_V4_OPTEXIST(skb)) diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 8626c9f678eb..53c9079ad2c3 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -87,11 +87,14 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) struct netlbl_dom_map *entry = NULL; size_t tmp_size; u32 tmp_val; + struct netlbl_audit audit_info; if (!info->attrs[NLBL_MGMT_A_DOMAIN] || !info->attrs[NLBL_MGMT_A_PROTOCOL]) goto add_failure; + netlbl_netlink_auditinfo(skb, &audit_info); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) { ret_val = -ENOMEM; @@ -108,7 +111,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) switch (entry->type) { case NETLBL_NLTYPE_UNLABELED: - ret_val = netlbl_domhsh_add(entry); + ret_val = netlbl_domhsh_add(entry, &audit_info); break; case NETLBL_NLTYPE_CIPSOV4: if (!info->attrs[NLBL_MGMT_A_CV4DOI]) @@ -125,7 +128,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); goto add_failure; } - ret_val = netlbl_domhsh_add(entry); + ret_val = netlbl_domhsh_add(entry, &audit_info); rcu_read_unlock(); break; default: @@ -156,12 +159,15 @@ add_failure: static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info) { char *domain; + struct netlbl_audit audit_info; if (!info->attrs[NLBL_MGMT_A_DOMAIN]) return -EINVAL; + netlbl_netlink_auditinfo(skb, &audit_info); + domain = nla_data(info->attrs[NLBL_MGMT_A_DOMAIN]); - return netlbl_domhsh_remove(domain); + return netlbl_domhsh_remove(domain, &audit_info); } /** @@ -264,10 +270,13 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) int ret_val = -EINVAL; struct netlbl_dom_map *entry = NULL; u32 tmp_val; + struct netlbl_audit audit_info; if (!info->attrs[NLBL_MGMT_A_PROTOCOL]) goto adddef_failure; + netlbl_netlink_auditinfo(skb, &audit_info); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) { ret_val = -ENOMEM; @@ -277,7 +286,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) switch (entry->type) { case NETLBL_NLTYPE_UNLABELED: - ret_val = netlbl_domhsh_add_default(entry); + ret_val = netlbl_domhsh_add_default(entry, &audit_info); break; case NETLBL_NLTYPE_CIPSOV4: if (!info->attrs[NLBL_MGMT_A_CV4DOI]) @@ -294,7 +303,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); goto adddef_failure; } - ret_val = netlbl_domhsh_add_default(entry); + ret_val = netlbl_domhsh_add_default(entry, &audit_info); rcu_read_unlock(); break; default: @@ -322,7 +331,11 @@ adddef_failure: */ static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info) { - return netlbl_domhsh_remove_default(); + struct netlbl_audit audit_info; + + netlbl_netlink_auditinfo(skb, &audit_info); + + return netlbl_domhsh_remove_default(&audit_info); } /** diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 440f5c4e1e2d..1833ad233b39 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -64,6 +64,34 @@ static struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = { }; /* + * Helper Functions + */ + +/** + * netlbl_unlabel_acceptflg_set - Set the unlabeled accept flag + * @value: desired value + * @audit_info: NetLabel audit information + * + * Description: + * Set the value of the unlabeled accept flag to @value. + * + */ +static void netlbl_unlabel_acceptflg_set(u8 value, + struct netlbl_audit *audit_info) +{ + struct audit_buffer *audit_buf; + u8 old_val; + + old_val = atomic_read(&netlabel_unlabel_accept_flg); + atomic_set(&netlabel_unlabel_accept_flg, value); + + audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_ALLOW, + audit_info); + audit_log_format(audit_buf, " unlbl_accept=%u old=%u", value, old_val); + audit_log_end(audit_buf); +} + +/* * NetLabel Command Handlers */ @@ -79,18 +107,19 @@ static struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = { */ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) { - int ret_val = -EINVAL; u8 value; + struct netlbl_audit audit_info; if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { - atomic_set(&netlabel_unlabel_accept_flg, value); - ret_val = 0; + netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_unlabel_acceptflg_set(value, &audit_info); + return 0; } } - return ret_val; + return -EINVAL; } /** @@ -229,16 +258,23 @@ int netlbl_unlabel_defconf(void) { int ret_val; struct netlbl_dom_map *entry; + struct netlbl_audit audit_info; + + /* Only the kernel is allowed to call this function and the only time + * it is called is at bootup before the audit subsystem is reporting + * messages so don't worry to much about these values. */ + security_task_getsecid(current, &audit_info.secid); + audit_info.loginuid = 0; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return -ENOMEM; entry->type = NETLBL_NLTYPE_UNLABELED; - ret_val = netlbl_domhsh_add_default(entry); + ret_val = netlbl_domhsh_add_default(entry, &audit_info); if (ret_val != 0) return ret_val; - atomic_set(&netlabel_unlabel_accept_flg, 1); + netlbl_unlabel_acceptflg_set(1, &audit_info); return 0; } diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index eeb7d768d2bb..98a416381e61 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -32,6 +32,9 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/socket.h> +#include <linux/audit.h> +#include <linux/tty.h> +#include <linux/security.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -74,3 +77,41 @@ int netlbl_netlink_init(void) return 0; } + +/* + * NetLabel Audit Functions + */ + +/** + * netlbl_audit_start_common - Start an audit message + * @type: audit message type + * @audit_info: NetLabel audit information + * + * Description: + * Start an audit message using the type specified in @type and fill the audit + * message with some fields common to all NetLabel audit messages. Returns + * a pointer to the audit buffer on success, NULL on failure. + * + */ +struct audit_buffer *netlbl_audit_start_common(int type, + struct netlbl_audit *audit_info) +{ + struct audit_context *audit_ctx = current->audit_context; + struct audit_buffer *audit_buf; + char *secctx; + u32 secctx_len; + + audit_buf = audit_log_start(audit_ctx, GFP_ATOMIC, type); + if (audit_buf == NULL) + return NULL; + + audit_log_format(audit_buf, "netlabel: auid=%u", audit_info->loginuid); + + if (audit_info->secid != 0 && + security_secid_to_secctx(audit_info->secid, + &secctx, + &secctx_len) == 0) + audit_log_format(audit_buf, " subj=%s", secctx); + + return audit_buf; +} diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index 3f9386b917df..47967ef32964 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -34,6 +34,7 @@ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/capability.h> +#include <linux/audit.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> @@ -71,8 +72,25 @@ static inline void *netlbl_netlink_hdr_put(struct sk_buff *skb, NETLBL_PROTO_VERSION); } +/** + * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg + * @skb: the packet + * @audit_info: NetLabel audit information + */ +static inline void netlbl_netlink_auditinfo(struct sk_buff *skb, + struct netlbl_audit *audit_info) +{ + audit_info->secid = NETLINK_CB(skb).sid; + audit_info->loginuid = NETLINK_CB(skb).loginuid; +} + /* NetLabel NETLINK I/O functions */ int netlbl_netlink_init(void); +/* NetLabel Audit Functions */ + +struct audit_buffer *netlbl_audit_start_common(int type, + struct netlbl_audit *audit_info); + #endif diff --git a/net/rxrpc/transport.c b/net/rxrpc/transport.c index 465efc86fccf..94b2e2fe6fdb 100644 --- a/net/rxrpc/transport.c +++ b/net/rxrpc/transport.c @@ -381,11 +381,10 @@ static int rxrpc_incoming_msg(struct rxrpc_transport *trans, /* allocate a new message record */ ret = -ENOMEM; - msg = kmalloc(sizeof(struct rxrpc_message), GFP_KERNEL); + msg = kmemdup(jumbomsg, sizeof(struct rxrpc_message), GFP_KERNEL); if (!msg) goto error; - memcpy(msg, jumbomsg, sizeof(*msg)); list_add_tail(&msg->link, msgq); /* adjust the jumbo packet */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 7e14f14058e9..37a184021647 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -401,7 +401,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if ((dev = dev_get_by_index(tcm->tcm_ifindex)) == NULL) return skb->len; - read_lock_bh(&qdisc_tree_lock); + read_lock(&qdisc_tree_lock); if (!tcm->tcm_parent) q = dev->qdisc_sleeping; else @@ -458,7 +458,7 @@ errout: if (cl) cops->put(q, cl); out: - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); dev_put(dev); return skb->len; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 86cac49a0531..09fda68c8b39 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -194,7 +194,7 @@ static int basic_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (handle) f->handle = handle; else { - int i = 0x80000000; + unsigned int i = 0x80000000; do { if (++head->hgenerator == 0x7FFFFFFF) head->hgenerator = 1; diff --git a/net/sched/estimator.c b/net/sched/estimator.c deleted file mode 100644 index 0ebc98e9be2d..000000000000 --- a/net/sched/estimator.c +++ /dev/null @@ -1,196 +0,0 @@ -/* - * net/sched/estimator.c Simple rate estimator. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/jiffies.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> -#include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/init.h> -#include <net/sock.h> -#include <net/pkt_sched.h> - -/* - This code is NOT intended to be used for statistics collection, - its purpose is to provide a base for statistical multiplexing - for controlled load service. - If you need only statistics, run a user level daemon which - periodically reads byte counters. - - Unfortunately, rate estimation is not a very easy task. - F.e. I did not find a simple way to estimate the current peak rate - and even failed to formulate the problem 8)8) - - So I preferred not to built an estimator into the scheduler, - but run this task separately. - Ideally, it should be kernel thread(s), but for now it runs - from timers, which puts apparent top bounds on the number of rated - flows, has minimal overhead on small, but is enough - to handle controlled load service, sets of aggregates. - - We measure rate over A=(1<<interval) seconds and evaluate EWMA: - - avrate = avrate*(1-W) + rate*W - - where W is chosen as negative power of 2: W = 2^(-ewma_log) - - The resulting time constant is: - - T = A/(-ln(1-W)) - - - NOTES. - - * The stored value for avbps is scaled by 2^5, so that maximal - rate is ~1Gbit, avpps is scaled by 2^10. - - * Minimal interval is HZ/4=250msec (it is the greatest common divisor - for HZ=100 and HZ=1024 8)), maximal interval - is (HZ*2^EST_MAX_INTERVAL)/4 = 8sec. Shorter intervals - are too expensive, longer ones can be implemented - at user level painlessly. - */ - -#define EST_MAX_INTERVAL 5 - -struct qdisc_estimator -{ - struct qdisc_estimator *next; - struct tc_stats *stats; - spinlock_t *stats_lock; - unsigned interval; - int ewma_log; - u64 last_bytes; - u32 last_packets; - u32 avpps; - u32 avbps; -}; - -struct qdisc_estimator_head -{ - struct timer_list timer; - struct qdisc_estimator *list; -}; - -static struct qdisc_estimator_head elist[EST_MAX_INTERVAL+1]; - -/* Estimator array lock */ -static DEFINE_RWLOCK(est_lock); - -static void est_timer(unsigned long arg) -{ - int idx = (int)arg; - struct qdisc_estimator *e; - - read_lock(&est_lock); - for (e = elist[idx].list; e; e = e->next) { - struct tc_stats *st = e->stats; - u64 nbytes; - u32 npackets; - u32 rate; - - spin_lock(e->stats_lock); - nbytes = st->bytes; - npackets = st->packets; - rate = (nbytes - e->last_bytes)<<(7 - idx); - e->last_bytes = nbytes; - e->avbps += ((long)rate - (long)e->avbps) >> e->ewma_log; - st->bps = (e->avbps+0xF)>>5; - - rate = (npackets - e->last_packets)<<(12 - idx); - e->last_packets = npackets; - e->avpps += ((long)rate - (long)e->avpps) >> e->ewma_log; - e->stats->pps = (e->avpps+0x1FF)>>10; - spin_unlock(e->stats_lock); - } - - mod_timer(&elist[idx].timer, jiffies + ((HZ<<idx)/4)); - read_unlock(&est_lock); -} - -int qdisc_new_estimator(struct tc_stats *stats, spinlock_t *stats_lock, struct rtattr *opt) -{ - struct qdisc_estimator *est; - struct tc_estimator *parm = RTA_DATA(opt); - - if (RTA_PAYLOAD(opt) < sizeof(*parm)) - return -EINVAL; - - if (parm->interval < -2 || parm->interval > 3) - return -EINVAL; - - est = kzalloc(sizeof(*est), GFP_KERNEL); - if (est == NULL) - return -ENOBUFS; - - est->interval = parm->interval + 2; - est->stats = stats; - est->stats_lock = stats_lock; - est->ewma_log = parm->ewma_log; - est->last_bytes = stats->bytes; - est->avbps = stats->bps<<5; - est->last_packets = stats->packets; - est->avpps = stats->pps<<10; - - est->next = elist[est->interval].list; - if (est->next == NULL) { - init_timer(&elist[est->interval].timer); - elist[est->interval].timer.data = est->interval; - elist[est->interval].timer.expires = jiffies + ((HZ<<est->interval)/4); - elist[est->interval].timer.function = est_timer; - add_timer(&elist[est->interval].timer); - } - write_lock_bh(&est_lock); - elist[est->interval].list = est; - write_unlock_bh(&est_lock); - return 0; -} - -void qdisc_kill_estimator(struct tc_stats *stats) -{ - int idx; - struct qdisc_estimator *est, **pest; - - for (idx=0; idx <= EST_MAX_INTERVAL; idx++) { - int killed = 0; - pest = &elist[idx].list; - while ((est=*pest) != NULL) { - if (est->stats != stats) { - pest = &est->next; - continue; - } - - write_lock_bh(&est_lock); - *pest = est->next; - write_unlock_bh(&est_lock); - - kfree(est); - killed++; - } - if (killed && elist[idx].list == NULL) - del_timer(&elist[idx].timer); - } -} - -EXPORT_SYMBOL(qdisc_kill_estimator); -EXPORT_SYMBOL(qdisc_new_estimator); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a19eff12cf78..0b6489291140 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -195,14 +195,14 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; - read_lock_bh(&qdisc_tree_lock); + read_lock(&qdisc_tree_lock); list_for_each_entry(q, &dev->qdisc_list, list) { if (q->handle == handle) { - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); return q; } } - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); return NULL; } @@ -837,7 +837,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) continue; if (idx > s_idx) s_q_idx = 0; - read_lock_bh(&qdisc_tree_lock); + read_lock(&qdisc_tree_lock); q_idx = 0; list_for_each_entry(q, &dev->qdisc_list, list) { if (q_idx < s_q_idx) { @@ -846,12 +846,12 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) } if (tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) { - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); goto done; } q_idx++; } - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); } done: @@ -1074,7 +1074,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - read_lock_bh(&qdisc_tree_lock); + read_lock(&qdisc_tree_lock); list_for_each_entry(q, &dev->qdisc_list, list) { if (t < s_t || !q->ops->cl_ops || (tcm->tcm_parent && @@ -1096,7 +1096,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) break; t++; } - read_unlock_bh(&qdisc_tree_lock); + read_unlock(&qdisc_tree_lock); cb->args[0] = t; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6f9151899795..88c6a99ce53c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -45,11 +45,10 @@ The idea is the following: - enqueue, dequeue are serialized via top level device spinlock dev->queue_lock. - - tree walking is protected by read_lock_bh(qdisc_tree_lock) + - tree walking is protected by read_lock(qdisc_tree_lock) and this lock is used only in process context. - - updates to tree are made under rtnl semaphore or - from softirq context (__qdisc_destroy rcu-callback) - hence this lock needs local bh disabling. + - updates to tree are made only under rtnl semaphore, + hence this lock may be made without local bh disabling. qdisc_tree_lock must be grabbed BEFORE dev->queue_lock! */ @@ -57,14 +56,14 @@ DEFINE_RWLOCK(qdisc_tree_lock); void qdisc_lock_tree(struct net_device *dev) { - write_lock_bh(&qdisc_tree_lock); + write_lock(&qdisc_tree_lock); spin_lock_bh(&dev->queue_lock); } void qdisc_unlock_tree(struct net_device *dev) { spin_unlock_bh(&dev->queue_lock); - write_unlock_bh(&qdisc_tree_lock); + write_unlock(&qdisc_tree_lock); } /* @@ -483,20 +482,6 @@ void qdisc_reset(struct Qdisc *qdisc) static void __qdisc_destroy(struct rcu_head *head) { struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu); - struct Qdisc_ops *ops = qdisc->ops; - -#ifdef CONFIG_NET_ESTIMATOR - gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); -#endif - write_lock(&qdisc_tree_lock); - if (ops->reset) - ops->reset(qdisc); - if (ops->destroy) - ops->destroy(qdisc); - write_unlock(&qdisc_tree_lock); - module_put(ops->owner); - - dev_put(qdisc->dev); kfree((char *) qdisc - qdisc->padded); } @@ -504,32 +489,23 @@ static void __qdisc_destroy(struct rcu_head *head) void qdisc_destroy(struct Qdisc *qdisc) { - struct list_head cql = LIST_HEAD_INIT(cql); - struct Qdisc *cq, *q, *n; + struct Qdisc_ops *ops = qdisc->ops; if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) + !atomic_dec_and_test(&qdisc->refcnt)) return; - if (!list_empty(&qdisc->list)) { - if (qdisc->ops->cl_ops == NULL) - list_del(&qdisc->list); - else - list_move(&qdisc->list, &cql); - } - - /* unlink inner qdiscs from dev->qdisc_list immediately */ - list_for_each_entry(cq, &cql, list) - list_for_each_entry_safe(q, n, &qdisc->dev->qdisc_list, list) - if (TC_H_MAJ(q->parent) == TC_H_MAJ(cq->handle)) { - if (q->ops->cl_ops == NULL) - list_del_init(&q->list); - else - list_move_tail(&q->list, &cql); - } - list_for_each_entry_safe(cq, n, &cql, list) - list_del_init(&cq->list); + list_del(&qdisc->list); +#ifdef CONFIG_NET_ESTIMATOR + gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); +#endif + if (ops->reset) + ops->reset(qdisc); + if (ops->destroy) + ops->destroy(qdisc); + module_put(ops->owner); + dev_put(qdisc->dev); call_rcu(&qdisc->q_rcu, __qdisc_destroy); } @@ -549,15 +525,15 @@ void dev_activate(struct net_device *dev) printk(KERN_INFO "%s: activation failed\n", dev->name); return; } - write_lock_bh(&qdisc_tree_lock); + write_lock(&qdisc_tree_lock); list_add_tail(&qdisc->list, &dev->qdisc_list); - write_unlock_bh(&qdisc_tree_lock); + write_unlock(&qdisc_tree_lock); } else { qdisc = &noqueue_qdisc; } - write_lock_bh(&qdisc_tree_lock); + write_lock(&qdisc_tree_lock); dev->qdisc_sleeping = qdisc; - write_unlock_bh(&qdisc_tree_lock); + write_unlock(&qdisc_tree_lock); } if (!netif_carrier_ok(dev)) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index bb3ddd4784b1..9b9c555c713f 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -786,11 +786,10 @@ static long htb_do_events(struct htb_sched *q, int level) for (i = 0; i < 500; i++) { struct htb_class *cl; long diff; - struct rb_node *p = q->wait_pq[level].rb_node; + struct rb_node *p = rb_first(&q->wait_pq[level]); + if (!p) return 0; - while (p->rb_left) - p = p->rb_left; cl = rb_entry(p, struct htb_class, pq_node); if (time_after(cl->pq_key, q->jiffies)) { diff --git a/net/sctp/input.c b/net/sctp/input.c index 03f65de75d88..64f630102532 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -218,12 +218,6 @@ int sctp_rcv(struct sk_buff *skb) } } - /* SCTP seems to always need a timestamp right now (FIXME) */ - if (skb->tstamp.off_sec == 0) { - __net_timestamp(skb); - sock_enable_timestamp(sk); - } - if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family)) goto discard_release; nf_reset(skb); @@ -388,7 +382,7 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, * pmtu discovery on this transport. */ t->pathmtu = SCTP_DEFAULT_MINSEGMENT; - t->param_flags = (t->param_flags & ~SPP_HB) | + t->param_flags = (t->param_flags & ~SPP_PMTUD) | SPP_PMTUD_DISABLE; } else { t->pathmtu = pmtu; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 249e5033c1a8..78071c6e6cf1 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -215,17 +215,17 @@ static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc, } dst = ip6_route_output(NULL, &fl); - if (dst) { + if (!dst->error) { struct rt6_info *rt; rt = (struct rt6_info *)dst; SCTP_DEBUG_PRINTK( "rt6_dst:" NIP6_FMT " rt6_src:" NIP6_FMT "\n", NIP6(rt->rt6i_dst.addr), NIP6(rt->rt6i_src.addr)); - } else { - SCTP_DEBUG_PRINTK("NO ROUTE\n"); + return dst; } - - return dst; + SCTP_DEBUG_PRINTK("NO ROUTE\n"); + dst_release(dst); + return NULL; } /* Returns the number of consecutive initial bits that match in the 2 ipv6 diff --git a/net/sctp/output.c b/net/sctp/output.c index cdc5a3936766..3ef4351dd956 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -633,7 +633,7 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * data will fit or delay in hopes of bundling a full * sized packet. */ - if (len < asoc->pathmtu - packet->overhead) { + if (len < asoc->frag_point) { retval = SCTP_XMIT_NAGLE_DELAY; goto finish; } @@ -645,7 +645,13 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, /* Keep track of how many bytes are in flight to the receiver. */ asoc->outqueue.outstanding_bytes += datasize; - /* Update our view of the receiver's rwnd. */ + /* Update our view of the receiver's rwnd. Include sk_buff overhead + * while updating peer.rwnd so that it reduces the chances of a + * receiver running out of receive buffer space even when receive + * window is still open. This can happen when a sender is sending + * sending small messages. + */ + datasize += sizeof(struct sk_buff); if (datasize < rwnd) rwnd -= datasize; else diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 37074a39ecbb..739582415bf6 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -416,7 +416,8 @@ void sctp_retransmit_mark(struct sctp_outq *q, * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ - q->asoc->peer.rwnd += sctp_data_size(chunk); + q->asoc->peer.rwnd += (sctp_data_size(chunk) + + sizeof(struct sk_buff)); q->outstanding_bytes -= sctp_data_size(chunk); transport->flight_size -= sctp_data_size(chunk); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index a356d8d310a9..7f49e769080e 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -344,7 +344,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc, sk, sctp_sk(sk)->type, sk->sk_state, assoc->state, hash, assoc->assoc_id, assoc->sndbuf_used, - (sk->sk_rcvbuf - assoc->rwnd), + atomic_read(&assoc->rmem_alloc), sock_i_uid(sk), sock_i_ino(sk), epb->bind_addr.port, assoc->peer.port); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 7745bdea7817..507dff72c585 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1447,8 +1447,16 @@ no_hmac: /* Check to see if the cookie is stale. If there is already * an association, there is no need to check cookie's expiration * for init collision case of lost COOKIE ACK. + * If skb has been timestamped, then use the stamp, otherwise + * use current time. This introduces a small possibility that + * that a cookie may be considered expired, but his would only slow + * down the new association establishment instead of every packet. */ - skb_get_timestamp(skb, &tv); + if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) + skb_get_timestamp(skb, &tv); + else + do_gettimeofday(&tv); + if (!asoc && tv_lt(bear_cookie->expiration, tv)) { __u16 len; /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 79c3e072cf28..9f34dec6ff8e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -821,7 +821,7 @@ out: * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type - * must be used to distengish the address length (note that this + * must be used to distinguish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * @@ -3084,8 +3084,8 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) */ sp->disable_fragments = 0; - /* Turn on/off any Nagle-like algorithm. */ - sp->nodelay = 1; + /* Enable Nagle algorithm by default. */ + sp->nodelay = 0; /* Enable by default. */ sp->v4mapped = 1; @@ -5362,6 +5362,20 @@ static void sctp_wfree(struct sk_buff *skb) sctp_association_put(asoc); } +/* Do accounting for the receive space on the socket. + * Accounting for the association is done in ulpevent.c + * We set this as a destructor for the cloned data skbs so that + * accounting is done at the correct time. + */ +void sctp_sock_rfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct sctp_ulpevent *event = sctp_skb2event(skb); + + atomic_sub(event->rmem_len, &sk->sk_rmem_alloc); +} + + /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len) @@ -5634,10 +5648,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sock_rfree(skb); + sctp_sock_rfree(skb); __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); - skb_set_owner_r(skb, newsk); + sctp_skb_set_owner_r(skb, newsk); } } @@ -5665,10 +5679,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sock_rfree(skb); + sctp_sock_rfree(skb); __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); - skb_set_owner_r(skb, newsk); + sctp_skb_set_owner_r(skb, newsk); } } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index ee236784a6bb..a015283a9087 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -55,10 +55,13 @@ static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event); /* Initialize an ULP event from an given skb. */ -SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event, int msg_flags) +SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event, + int msg_flags, + unsigned int len) { memset(event, 0, sizeof(struct sctp_ulpevent)); event->msg_flags = msg_flags; + event->rmem_len = len; } /* Create a new sctp_ulpevent. */ @@ -73,7 +76,7 @@ SCTP_STATIC struct sctp_ulpevent *sctp_ulpevent_new(int size, int msg_flags, goto fail; event = sctp_skb2event(skb); - sctp_ulpevent_init(event, msg_flags); + sctp_ulpevent_init(event, msg_flags, skb->truesize); return event; @@ -101,17 +104,16 @@ static inline void sctp_ulpevent_set_owner(struct sctp_ulpevent *event, sctp_association_hold((struct sctp_association *)asoc); skb = sctp_event2skb(event); event->asoc = (struct sctp_association *)asoc; - atomic_add(skb->truesize, &event->asoc->rmem_alloc); - skb_set_owner_r(skb, asoc->base.sk); + atomic_add(event->rmem_len, &event->asoc->rmem_alloc); + sctp_skb_set_owner_r(skb, asoc->base.sk); } /* A simple destructor to give up the reference to the association. */ static inline void sctp_ulpevent_release_owner(struct sctp_ulpevent *event) { struct sctp_association *asoc = event->asoc; - struct sk_buff *skb = sctp_event2skb(event); - atomic_sub(skb->truesize, &asoc->rmem_alloc); + atomic_sub(event->rmem_len, &asoc->rmem_alloc); sctp_association_put(asoc); } @@ -372,7 +374,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( /* Embed the event fields inside the cloned skb. */ event = sctp_skb2event(skb); - sctp_ulpevent_init(event, MSG_NOTIFICATION); + sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); sre = (struct sctp_remote_error *) skb_push(skb, sizeof(struct sctp_remote_error)); @@ -464,7 +466,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( /* Embed the event fields inside the cloned skb. */ event = sctp_skb2event(skb); - sctp_ulpevent_init(event, MSG_NOTIFICATION); + sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); ssf = (struct sctp_send_failed *) skb_push(skb, sizeof(struct sctp_send_failed)); @@ -682,8 +684,11 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, /* Embed the event fields inside the cloned skb. */ event = sctp_skb2event(skb); - /* Initialize event with flags 0. */ - sctp_ulpevent_init(event, 0); + /* Initialize event with flags 0 and correct length + * Since this is a clone of the original skb, only account for + * the data of this chunk as other chunks will be accounted separately. + */ + sctp_ulpevent_init(event, 0, skb->len + sizeof(struct sk_buff)); sctp_ulpevent_receive_data(event, asoc); diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 575e556aeb3e..e1d144275f97 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -309,7 +309,7 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *qu if (!new) return NULL; /* try again later */ - new->sk = f_frag->sk; + sctp_skb_set_owner_r(new, f_frag->sk); skb_shinfo(new)->frag_list = pos; } else diff --git a/net/socket.c b/net/socket.c index 1bc4167e0da8..6c9b9b326d76 100644 --- a/net/socket.c +++ b/net/socket.c @@ -95,10 +95,10 @@ #include <linux/netfilter.h> static int sock_no_open(struct inode *irrelevant, struct file *dontcare); -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf, - size_t size, loff_t pos); -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf, - size_t size, loff_t pos); +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); @@ -110,10 +110,6 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_readv(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); -static ssize_t sock_writev(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); @@ -136,8 +132,6 @@ static struct file_operations socket_file_ops = { .open = sock_no_open, /* special open code to disallow open via /proc */ .release = sock_close, .fasync = sock_fasync, - .readv = sock_readv, - .writev = sock_writev, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, }; @@ -664,7 +658,6 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, - char __user *ubuf, size_t size, struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { @@ -675,16 +668,13 @@ static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, } siocb->kiocb = iocb; - siocb->async_iov.iov_base = ubuf; - siocb->async_iov.iov_len = size; - iocb->private = siocb; return siocb; } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -704,43 +694,27 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); } -static ssize_t sock_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb iocb; - struct sock_iocb siocb; - struct msghdr msg; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, ubuf, count, &siocb); + + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -762,39 +736,22 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, return __sock_sendmsg(iocb, sock, msg, size); } -static ssize_t sock_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct msghdr msg; - struct kiocb iocb; - struct sock_iocb siocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb); + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } /* @@ -868,7 +825,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) break; case FIOGETOWN: case SIOCGPGRP: - err = put_user(sock->file->f_owner.pid, + err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 55163af3dcaf..993ff1a5d945 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -331,8 +331,8 @@ rpcauth_unbindcred(struct rpc_task *task) task->tk_msg.rpc_cred = NULL; } -u32 * -rpcauth_marshcred(struct rpc_task *task, u32 *p) +__be32 * +rpcauth_marshcred(struct rpc_task *task, __be32 *p) { struct rpc_cred *cred = task->tk_msg.rpc_cred; @@ -342,8 +342,8 @@ rpcauth_marshcred(struct rpc_task *task, u32 *p) return cred->cr_ops->crmarshal(task, p); } -u32 * -rpcauth_checkverf(struct rpc_task *task, u32 *p) +__be32 * +rpcauth_checkverf(struct rpc_task *task, __be32 *p) { struct rpc_cred *cred = task->tk_msg.rpc_cred; @@ -355,7 +355,7 @@ rpcauth_checkverf(struct rpc_task *task, u32 *p) int rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, - u32 *data, void *obj) + __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_msg.rpc_cred; @@ -369,7 +369,7 @@ rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, int rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, - u32 *data, void *obj) + __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_msg.rpc_cred; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 6eed3e166ba3..b36b9463f5a4 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1,5 +1,5 @@ /* - * linux/net/sunrpc/auth_gss.c + * linux/net/sunrpc/auth_gss/auth_gss.c * * RPCSEC_GSS client authentication. * @@ -826,14 +826,14 @@ out: * Marshal credentials. * Maybe we should keep a cached credential for performance reasons. */ -static u32 * -gss_marshal(struct rpc_task *task, u32 *p) +static __be32 * +gss_marshal(struct rpc_task *task, __be32 *p) { struct rpc_cred *cred = task->tk_msg.rpc_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred); - u32 *cred_len; + __be32 *cred_len; struct rpc_rqst *req = task->tk_rqstp; u32 maj_stat = 0; struct xdr_netobj mic; @@ -894,12 +894,12 @@ gss_refresh(struct rpc_task *task) return 0; } -static u32 * -gss_validate(struct rpc_task *task, u32 *p) +static __be32 * +gss_validate(struct rpc_task *task, __be32 *p) { struct rpc_cred *cred = task->tk_msg.rpc_cred; struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred); - u32 seq; + __be32 seq; struct kvec iov; struct xdr_buf verf_buf; struct xdr_netobj mic; @@ -940,13 +940,14 @@ out_bad: static inline int gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, u32 *p, void *obj) + kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; struct xdr_buf integ_buf; - u32 *integ_len = NULL; + __be32 *integ_len = NULL; struct xdr_netobj mic; - u32 offset, *q; + u32 offset; + __be32 *q; struct kvec *iov; u32 maj_stat = 0; int status = -EIO; @@ -1032,13 +1033,13 @@ out: static inline int gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, u32 *p, void *obj) + kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; u32 offset; u32 maj_stat; int status; - u32 *opaque_len; + __be32 *opaque_len; struct page **inpages; int first; int pad; @@ -1095,7 +1096,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static int gss_wrap_req(struct rpc_task *task, - kxdrproc_t encode, void *rqstp, u32 *p, void *obj) + kxdrproc_t encode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_msg.rpc_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1132,7 +1133,7 @@ out: static inline int gss_unwrap_resp_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - struct rpc_rqst *rqstp, u32 **p) + struct rpc_rqst *rqstp, __be32 **p) { struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; struct xdr_buf integ_buf; @@ -1169,7 +1170,7 @@ gss_unwrap_resp_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static inline int gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - struct rpc_rqst *rqstp, u32 **p) + struct rpc_rqst *rqstp, __be32 **p) { struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; u32 offset; @@ -1198,13 +1199,13 @@ gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static int gss_unwrap_resp(struct rpc_task *task, - kxdrproc_t decode, void *rqstp, u32 *p, void *obj) + kxdrproc_t decode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_msg.rpc_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred); - u32 *savedp = p; + __be32 *savedp = p; struct kvec *head = ((struct rpc_rqst *)rqstp)->rq_rcv_buf.head; int savedlen = head->iov_len; int status = -EIO; diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 2f312164d6d5..08601ee4cd73 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -115,7 +115,7 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, krb5_hdr = ptr - 2; msg_start = krb5_hdr + 24; - *(u16 *)(krb5_hdr + 2) = htons(ctx->signalg); + *(__be16 *)(krb5_hdr + 2) = htons(ctx->signalg); memset(krb5_hdr + 4, 0xff, 4); if (make_checksum(checksum_type, krb5_hdr, 8, text, 0, &md5cksum)) diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index f179415d0c38..cc45c1605f80 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -177,9 +177,9 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset, msg_start = krb5_hdr + 24; /* XXXJBF: */ BUG_ON(buf->head[0].iov_base + offset + headlen != msg_start + blocksize); - *(u16 *)(krb5_hdr + 2) = htons(kctx->signalg); + *(__be16 *)(krb5_hdr + 2) = htons(kctx->signalg); memset(krb5_hdr + 4, 0xff, 4); - *(u16 *)(krb5_hdr + 4) = htons(kctx->sealalg); + *(__be16 *)(krb5_hdr + 4) = htons(kctx->sealalg); make_confounder(msg_start, blocksize); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 94217ec9e2dd..1f0f079ffa65 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -607,7 +607,7 @@ svc_safe_getnetobj(struct kvec *argv, struct xdr_netobj *o) if (argv->iov_len < 4) return -1; - o->len = ntohl(svc_getu32(argv)); + o->len = svc_getnl(argv); l = round_up_to_quad(o->len); if (argv->iov_len < l) return -1; @@ -620,17 +620,17 @@ svc_safe_getnetobj(struct kvec *argv, struct xdr_netobj *o) static inline int svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o) { - u32 *p; + u8 *p; if (resv->iov_len + 4 > PAGE_SIZE) return -1; - svc_putu32(resv, htonl(o->len)); + svc_putnl(resv, o->len); p = resv->iov_base + resv->iov_len; resv->iov_len += round_up_to_quad(o->len); if (resv->iov_len > PAGE_SIZE) return -1; memcpy(p, o->data, o->len); - memset((u8 *)p + o->len, 0, round_up_to_quad(o->len) - o->len); + memset(p + o->len, 0, round_up_to_quad(o->len) - o->len); return 0; } @@ -640,7 +640,7 @@ svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o) */ static int gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, - u32 *rpcstart, struct rpc_gss_wire_cred *gc, u32 *authp) + __be32 *rpcstart, struct rpc_gss_wire_cred *gc, __be32 *authp) { struct gss_ctx *ctx_id = rsci->mechctx; struct xdr_buf rpchdr; @@ -657,7 +657,7 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, *authp = rpc_autherr_badverf; if (argv->iov_len < 4) return SVC_DENIED; - flavor = ntohl(svc_getu32(argv)); + flavor = svc_getnl(argv); if (flavor != RPC_AUTH_GSS) return SVC_DENIED; if (svc_safe_getnetobj(argv, &checksum)) @@ -687,9 +687,9 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, static int gss_write_null_verf(struct svc_rqst *rqstp) { - u32 *p; + __be32 *p; - svc_putu32(rqstp->rq_res.head, htonl(RPC_AUTH_NULL)); + svc_putnl(rqstp->rq_res.head, RPC_AUTH_NULL); p = rqstp->rq_res.head->iov_base + rqstp->rq_res.head->iov_len; /* don't really need to check if head->iov_len > PAGE_SIZE ... */ *p++ = 0; @@ -701,14 +701,14 @@ gss_write_null_verf(struct svc_rqst *rqstp) static int gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq) { - u32 xdr_seq; + __be32 xdr_seq; u32 maj_stat; struct xdr_buf verf_data; struct xdr_netobj mic; - u32 *p; + __be32 *p; struct kvec iov; - svc_putu32(rqstp->rq_res.head, htonl(RPC_AUTH_GSS)); + svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS); xdr_seq = htonl(seq); iov.iov_base = &xdr_seq; @@ -782,7 +782,7 @@ EXPORT_SYMBOL(svcauth_gss_register_pseudoflavor); static inline int read_u32_from_xdr_buf(struct xdr_buf *buf, int base, u32 *obj) { - u32 raw; + __be32 raw; int status; status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); @@ -805,7 +805,7 @@ unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) struct xdr_netobj mic; struct xdr_buf integ_buf; - integ_len = ntohl(svc_getu32(&buf->head[0])); + integ_len = svc_getnl(&buf->head[0]); if (integ_len & 3) goto out; if (integ_len > buf->len) @@ -825,7 +825,7 @@ unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) maj_stat = gss_verify_mic(ctx, &integ_buf, &mic); if (maj_stat != GSS_S_COMPLETE) goto out; - if (ntohl(svc_getu32(&buf->head[0])) != seq) + if (svc_getnl(&buf->head[0]) != seq) goto out; stat = 0; out: @@ -857,7 +857,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs rqstp->rq_sendfile_ok = 0; - priv_len = ntohl(svc_getu32(&buf->head[0])); + priv_len = svc_getnl(&buf->head[0]); if (rqstp->rq_deferred) { /* Already decrypted last time through! The sequence number * check at out_seq is unnecessary but harmless: */ @@ -895,7 +895,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs if (maj_stat != GSS_S_COMPLETE) return -EINVAL; out_seq: - if (ntohl(svc_getu32(&buf->head[0])) != seq) + if (svc_getnl(&buf->head[0]) != seq) return -EINVAL; return 0; } @@ -903,9 +903,9 @@ out_seq: struct gss_svc_data { /* decoded gss client cred: */ struct rpc_gss_wire_cred clcred; - /* pointer to the beginning of the procedure-specific results, - * which may be encrypted/checksummed in svcauth_gss_release: */ - u32 *body_start; + /* save a pointer to the beginning of the encoded verifier, + * for use in encryption/checksumming in svcauth_gss_release: */ + __be32 *verf_start; struct rsc *rsci; }; @@ -946,7 +946,7 @@ gss_write_init_verf(struct svc_rqst *rqstp, struct rsi *rsip) * response here and return SVC_COMPLETE. */ static int -svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) +svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -956,8 +956,8 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) struct rpc_gss_wire_cred *gc; struct rsc *rsci = NULL; struct rsi *rsip, rsikey; - u32 *rpcstart; - u32 *reject_stat = resv->iov_base + resv->iov_len; + __be32 *rpcstart; + __be32 *reject_stat = resv->iov_base + resv->iov_len; int ret; dprintk("RPC: svcauth_gss: argv->iov_len = %zd\n",argv->iov_len); @@ -968,7 +968,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) if (!svcdata) goto auth_err; rqstp->rq_auth_data = svcdata; - svcdata->body_start = NULL; + svcdata->verf_start = NULL; svcdata->rsci = NULL; gc = &svcdata->clcred; @@ -985,12 +985,12 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) if (argv->iov_len < 5 * 4) goto auth_err; - crlen = ntohl(svc_getu32(argv)); - if (ntohl(svc_getu32(argv)) != RPC_GSS_VERSION) + crlen = svc_getnl(argv); + if (svc_getnl(argv) != RPC_GSS_VERSION) goto auth_err; - gc->gc_proc = ntohl(svc_getu32(argv)); - gc->gc_seq = ntohl(svc_getu32(argv)); - gc->gc_svc = ntohl(svc_getu32(argv)); + gc->gc_proc = svc_getnl(argv); + gc->gc_seq = svc_getnl(argv); + gc->gc_svc = svc_getnl(argv); if (svc_safe_getnetobj(argv, &gc->gc_ctx)) goto auth_err; if (crlen != round_up_to_quad(gc->gc_ctx.len) + 5 * 4) @@ -1016,9 +1016,9 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) case RPC_GSS_PROC_CONTINUE_INIT: if (argv->iov_len < 2 * 4) goto auth_err; - if (ntohl(svc_getu32(argv)) != RPC_AUTH_NULL) + if (svc_getnl(argv) != RPC_AUTH_NULL) goto auth_err; - if (ntohl(svc_getu32(argv)) != 0) + if (svc_getnl(argv) != 0) goto auth_err; break; case RPC_GSS_PROC_DATA: @@ -1076,14 +1076,14 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) goto drop; if (resv->iov_len + 4 > PAGE_SIZE) goto drop; - svc_putu32(resv, rpc_success); + svc_putnl(resv, RPC_SUCCESS); if (svc_safe_putnetobj(resv, &rsip->out_handle)) goto drop; if (resv->iov_len + 3 * 4 > PAGE_SIZE) goto drop; - svc_putu32(resv, htonl(rsip->major_status)); - svc_putu32(resv, htonl(rsip->minor_status)); - svc_putu32(resv, htonl(GSS_SEQ_WIN)); + svc_putnl(resv, rsip->major_status); + svc_putnl(resv, rsip->minor_status); + svc_putnl(resv, GSS_SEQ_WIN); if (svc_safe_putnetobj(resv, &rsip->out_token)) goto drop; rqstp->rq_client = NULL; @@ -1093,10 +1093,11 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) set_bit(CACHE_NEGATIVE, &rsci->h.flags); if (resv->iov_len + 4 > PAGE_SIZE) goto drop; - svc_putu32(resv, rpc_success); + svc_putnl(resv, RPC_SUCCESS); goto complete; case RPC_GSS_PROC_DATA: *authp = rpcsec_gsserr_ctxproblem; + svcdata->verf_start = resv->iov_base + resv->iov_len; if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; rqstp->rq_cred = rsci->cred; @@ -1110,18 +1111,16 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp) gc->gc_seq, rsci->mechctx)) goto auth_err; /* placeholders for length and seq. number: */ - svcdata->body_start = resv->iov_base + resv->iov_len; - svc_putu32(resv, 0); - svc_putu32(resv, 0); + svc_putnl(resv, 0); + svc_putnl(resv, 0); break; case RPC_GSS_SVC_PRIVACY: if (unwrap_priv_data(rqstp, &rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto auth_err; /* placeholders for length and seq. number: */ - svcdata->body_start = resv->iov_base + resv->iov_len; - svc_putu32(resv, 0); - svc_putu32(resv, 0); + svc_putnl(resv, 0); + svc_putnl(resv, 0); break; default: goto auth_err; @@ -1147,6 +1146,33 @@ out: return ret; } +static __be32 * +svcauth_gss_prepare_to_wrap(struct xdr_buf *resbuf, struct gss_svc_data *gsd) +{ + __be32 *p; + u32 verf_len; + + p = gsd->verf_start; + gsd->verf_start = NULL; + + /* If the reply stat is nonzero, don't wrap: */ + if (*(p-1) != rpc_success) + return NULL; + /* Skip the verifier: */ + p += 1; + verf_len = ntohl(*p++); + p += XDR_QUADLEN(verf_len); + /* move accept_stat to right place: */ + memcpy(p, p + 2, 4); + /* Also don't wrap if the accept stat is nonzero: */ + if (*p != rpc_success) { + resbuf->head[0].iov_len -= 2 * 4; + return NULL; + } + p++; + return p; +} + static inline int svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) { @@ -1156,21 +1182,13 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) struct xdr_buf integ_buf; struct xdr_netobj mic; struct kvec *resv; - u32 *p; + __be32 *p; int integ_offset, integ_len; int stat = -EINVAL; - p = gsd->body_start; - gsd->body_start = NULL; - /* move accept_stat to right place: */ - memcpy(p, p + 2, 4); - /* Don't wrap in failure case: */ - /* Counting on not getting here if call was not even accepted! */ - if (*p != rpc_success) { - resbuf->head[0].iov_len -= 2 * 4; + p = svcauth_gss_prepare_to_wrap(resbuf, gsd); + if (p == NULL) goto out; - } - p++; integ_offset = (u8 *)(p + 1) - (u8 *)resbuf->head[0].iov_base; integ_len = resbuf->len - integ_offset; BUG_ON(integ_len % 4); @@ -1191,7 +1209,6 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) resbuf->tail[0].iov_base = resbuf->head[0].iov_base + resbuf->head[0].iov_len; resbuf->tail[0].iov_len = 0; - rqstp->rq_restailpage = 0; resv = &resbuf->tail[0]; } else { resv = &resbuf->tail[0]; @@ -1199,7 +1216,7 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) mic.data = (u8 *)resv->iov_base + resv->iov_len + 4; if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic)) goto out_err; - svc_putu32(resv, htonl(mic.len)); + svc_putnl(resv, mic.len); memset(mic.data + mic.len, 0, round_up_to_quad(mic.len) - mic.len); resv->iov_len += XDR_QUADLEN(mic.len) << 2; @@ -1219,28 +1236,20 @@ svcauth_gss_wrap_resp_priv(struct svc_rqst *rqstp) struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *resbuf = &rqstp->rq_res; struct page **inpages = NULL; - u32 *p; - int offset, *len; + __be32 *p, *len; + int offset; int pad; - p = gsd->body_start; - gsd->body_start = NULL; - /* move accept_stat to right place: */ - memcpy(p, p + 2, 4); - /* Don't wrap in failure case: */ - /* Counting on not getting here if call was not even accepted! */ - if (*p != rpc_success) { - resbuf->head[0].iov_len -= 2 * 4; + p = svcauth_gss_prepare_to_wrap(resbuf, gsd); + if (p == NULL) return 0; - } - p++; len = p++; offset = (u8 *)p - (u8 *)resbuf->head[0].iov_base; *p++ = htonl(gc->gc_seq); inpages = resbuf->pages; /* XXX: Would be better to write some xdr helper functions for * nfs{2,3,4}xdr.c that place the data right, instead of copying: */ - if (resbuf->tail[0].iov_base && rqstp->rq_restailpage == 0) { + if (resbuf->tail[0].iov_base) { BUG_ON(resbuf->tail[0].iov_base >= resbuf->head[0].iov_base + PAGE_SIZE); BUG_ON(resbuf->tail[0].iov_base < resbuf->head[0].iov_base); @@ -1258,13 +1267,12 @@ svcauth_gss_wrap_resp_priv(struct svc_rqst *rqstp) resbuf->tail[0].iov_base = resbuf->head[0].iov_base + resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE; resbuf->tail[0].iov_len = 0; - rqstp->rq_restailpage = 0; } if (gss_wrap(gsd->rsci->mechctx, offset, resbuf, inpages)) return -ENOMEM; *len = htonl(resbuf->len - offset); pad = 3 - ((resbuf->len - offset - 1)&3); - p = (u32 *)(resbuf->tail[0].iov_base + resbuf->tail[0].iov_len); + p = (__be32 *)(resbuf->tail[0].iov_base + resbuf->tail[0].iov_len); memset(p, 0, pad); resbuf->tail[0].iov_len += pad; resbuf->len += pad; @@ -1282,7 +1290,7 @@ svcauth_gss_release(struct svc_rqst *rqstp) if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; /* Release can be called twice, but we only wrap once. */ - if (gsd->body_start == NULL) + if (gsd->verf_start == NULL) goto out; /* normally not set till svc_send, but we need it here: */ /* XXX: what for? Do we mess it up the moment we call svc_putu32 diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 2eccffa96ba1..3be257dc32b2 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -60,8 +60,8 @@ nul_match(struct auth_cred *acred, struct rpc_cred *cred, int taskflags) /* * Marshal credential. */ -static u32 * -nul_marshal(struct rpc_task *task, u32 *p) +static __be32 * +nul_marshal(struct rpc_task *task, __be32 *p) { *p++ = htonl(RPC_AUTH_NULL); *p++ = 0; @@ -81,8 +81,8 @@ nul_refresh(struct rpc_task *task) return 0; } -static u32 * -nul_validate(struct rpc_task *task, u32 *p) +static __be32 * +nul_validate(struct rpc_task *task, __be32 *p) { rpc_authflavor_t flavor; u32 size; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 74c7406a1054..f7f990c9afe2 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -137,12 +137,12 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) * Marshal credentials. * Maybe we should keep a cached credential for performance reasons. */ -static u32 * -unx_marshal(struct rpc_task *task, u32 *p) +static __be32 * +unx_marshal(struct rpc_task *task, __be32 *p) { struct rpc_clnt *clnt = task->tk_client; struct unx_cred *cred = (struct unx_cred *) task->tk_msg.rpc_cred; - u32 *base, *hold; + __be32 *base, *hold; int i; *p++ = htonl(RPC_AUTH_UNIX); @@ -178,8 +178,8 @@ unx_refresh(struct rpc_task *task) return 0; } -static u32 * -unx_validate(struct rpc_task *task, u32 *p) +static __be32 * +unx_validate(struct rpc_task *task, __be32 *p) { rpc_authflavor_t flavor; u32 size; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 084a0ad5c64e..78696f2dc7d6 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -60,8 +60,8 @@ static void call_refreshresult(struct rpc_task *task); static void call_timeout(struct rpc_task *task); static void call_connect(struct rpc_task *task); static void call_connect_status(struct rpc_task *task); -static u32 * call_header(struct rpc_task *task); -static u32 * call_verify(struct rpc_task *task); +static __be32 * call_header(struct rpc_task *task); +static __be32 * call_verify(struct rpc_task *task); static int @@ -161,10 +161,10 @@ static struct rpc_clnt * rpc_new_client(struct rpc_xprt *xprt, char *servname, s } /* save the nodename */ - clnt->cl_nodelen = strlen(system_utsname.nodename); + clnt->cl_nodelen = strlen(utsname()->nodename); if (clnt->cl_nodelen > UNX_MAXNODENAME) clnt->cl_nodelen = UNX_MAXNODENAME; - memcpy(clnt->cl_nodename, system_utsname.nodename, clnt->cl_nodelen); + memcpy(clnt->cl_nodename, utsname()->nodename, clnt->cl_nodelen); return clnt; out_no_auth: @@ -782,7 +782,7 @@ call_encode(struct rpc_task *task) struct xdr_buf *rcvbuf = &req->rq_rcv_buf; unsigned int bufsiz; kxdrproc_t encode; - u32 *p; + __be32 *p; dprintk("RPC: %4d call_encode (status %d)\n", task->tk_pid, task->tk_status); @@ -1100,7 +1100,7 @@ call_decode(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; kxdrproc_t decode = task->tk_msg.rpc_proc->p_decode; - u32 *p; + __be32 *p; dprintk("RPC: %4d call_decode (status %d)\n", task->tk_pid, task->tk_status); @@ -1197,12 +1197,12 @@ call_refreshresult(struct rpc_task *task) /* * Call header serialization */ -static u32 * +static __be32 * call_header(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; - u32 *p = req->rq_svec[0].iov_base; + __be32 *p = req->rq_svec[0].iov_base; /* FIXME: check buffer size? */ @@ -1221,12 +1221,13 @@ call_header(struct rpc_task *task) /* * Reply header verification */ -static u32 * +static __be32 * call_verify(struct rpc_task *task) { struct kvec *iov = &task->tk_rqstp->rq_rcv_buf.head[0]; int len = task->tk_rqstp->rq_rcv_buf.len >> 2; - u32 *p = iov->iov_base, n; + __be32 *p = iov->iov_base; + u32 n; int error = -EACCES; if ((task->tk_rqstp->rq_rcv_buf.len & 3) != 0) { @@ -1303,7 +1304,7 @@ call_verify(struct rpc_task *task) printk(KERN_WARNING "call_verify: auth check failed\n"); goto out_garbage; /* bad verifier, retry */ } - len = p - (u32 *)iov->iov_base - 1; + len = p - (__be32 *)iov->iov_base - 1; if (len < 0) goto out_overflow; switch ((n = ntohl(*p++))) { @@ -1358,12 +1359,12 @@ out_overflow: goto out_garbage; } -static int rpcproc_encode_null(void *rqstp, u32 *data, void *obj) +static int rpcproc_encode_null(void *rqstp, __be32 *data, void *obj) { return 0; } -static int rpcproc_decode_null(void *rqstp, u32 *data, void *obj) +static int rpcproc_decode_null(void *rqstp, __be32 *data, void *obj) { return 0; } diff --git a/net/sunrpc/pmap_clnt.c b/net/sunrpc/pmap_clnt.c index c04609d3476a..e52afab413de 100644 --- a/net/sunrpc/pmap_clnt.c +++ b/net/sunrpc/pmap_clnt.c @@ -101,11 +101,13 @@ void rpc_getport(struct rpc_task *task) /* Autobind on cloned rpc clients is discouraged */ BUG_ON(clnt->cl_parent != clnt); - if (xprt_test_and_set_binding(xprt)) { - task->tk_status = -EACCES; /* tell caller to check again */ - rpc_sleep_on(&xprt->binding, task, NULL, NULL); - return; - } + /* Put self on queue before sending rpcbind request, in case + * pmap_getport_done completes before we return from rpc_run_task */ + rpc_sleep_on(&xprt->binding, task, NULL, NULL); + + status = -EACCES; /* tell caller to check again */ + if (xprt_test_and_set_binding(xprt)) + goto bailout_nofree; /* Someone else may have bound if we slept */ status = 0; @@ -134,8 +136,6 @@ void rpc_getport(struct rpc_task *task) goto bailout; rpc_release_task(child); - rpc_sleep_on(&xprt->binding, task, NULL, NULL); - task->tk_xprt->stat.bind_count++; return; @@ -300,7 +300,7 @@ static struct rpc_clnt *pmap_create(char *hostname, struct sockaddr_in *srvaddr, /* * XDR encode/decode functions for PMAP */ -static int xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct portmap_args *map) +static int xdr_encode_mapping(struct rpc_rqst *req, __be32 *p, struct portmap_args *map) { dprintk("RPC: xdr_encode_mapping(%u, %u, %u, %u)\n", map->pm_prog, map->pm_vers, map->pm_prot, map->pm_port); @@ -313,13 +313,13 @@ static int xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct portmap_args return 0; } -static int xdr_decode_port(struct rpc_rqst *req, u32 *p, unsigned short *portp) +static int xdr_decode_port(struct rpc_rqst *req, __be32 *p, unsigned short *portp) { *portp = (unsigned short) ntohl(*p++); return 0; } -static int xdr_decode_bool(struct rpc_rqst *req, u32 *p, unsigned int *boolp) +static int xdr_decode_bool(struct rpc_rqst *req, __be32 *p, unsigned int *boolp) { *boolp = (unsigned int) ntohl(*p++); return 0; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index dfa504fe383f..9a0b41a97f90 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -488,14 +488,13 @@ rpc_get_inode(struct super_block *sb, int mode) return NULL; inode->i_mode = mode; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch(mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; - inode->i_nlink++; + inc_nlink(inode); default: break; } @@ -572,7 +571,7 @@ rpc_populate(struct dentry *parent, if (private) rpc_inode_setowner(inode, private); if (S_ISDIR(mode)) - dir->i_nlink++; + inc_nlink(dir); d_add(dentry, inode); } mutex_unlock(&dir->i_mutex); @@ -594,7 +593,7 @@ __rpc_mkdir(struct inode *dir, struct dentry *dentry) goto out_err; inode->i_ino = iunique(dir->i_sb, 100); d_instantiate(dentry, inode); - dir->i_nlink++; + inc_nlink(dir); inode_dir_notify(dir, DN_CREATE); return 0; out_err: @@ -858,7 +857,6 @@ int register_rpc_pipefs(void) void unregister_rpc_pipefs(void) { - if (kmem_cache_destroy(rpc_inode_cachep)) - printk(KERN_WARNING "RPC: unable to free inode cache\n"); + kmem_cache_destroy(rpc_inode_cachep); unregister_filesystem(&rpc_pipe_fs_type); } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6390461a9756..a1ab4eed41f4 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1059,10 +1059,10 @@ rpc_destroy_mempool(void) mempool_destroy(rpc_buffer_mempool); if (rpc_task_mempool) mempool_destroy(rpc_task_mempool); - if (rpc_task_slabp && kmem_cache_destroy(rpc_task_slabp)) - printk(KERN_INFO "rpc_task: not all structures were freed\n"); - if (rpc_buffer_slabp && kmem_cache_destroy(rpc_buffer_slabp)) - printk(KERN_INFO "rpc_buffers: not all structures were freed\n"); + if (rpc_task_slabp) + kmem_cache_destroy(rpc_task_slabp); + if (rpc_buffer_slabp) + kmem_cache_destroy(rpc_buffer_slabp); } int diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 26c0531d7e25..192dff5dabcb 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -70,6 +70,8 @@ EXPORT_SYMBOL(put_rpccred); /* RPC server stuff */ EXPORT_SYMBOL(svc_create); EXPORT_SYMBOL(svc_create_thread); +EXPORT_SYMBOL(svc_create_pooled); +EXPORT_SYMBOL(svc_set_num_threads); EXPORT_SYMBOL(svc_exit_thread); EXPORT_SYMBOL(svc_destroy); EXPORT_SYMBOL(svc_drop); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index b76a227dd3ad..eb44ec929ca1 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -4,6 +4,10 @@ * High-level RPC service routines * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> + * + * Multiple threads pools and NUMAisation + * Copyright (c) 2006 Silicon Graphics, Inc. + * by Greg Banks <gnb@melbourne.sgi.com> */ #include <linux/linkage.h> @@ -12,6 +16,8 @@ #include <linux/net.h> #include <linux/in.h> #include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/module.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> @@ -23,14 +29,252 @@ #define RPC_PARANOIA 1 /* + * Mode for mapping cpus to pools. + */ +enum { + SVC_POOL_NONE = -1, /* uninitialised, choose one of the others */ + SVC_POOL_GLOBAL, /* no mapping, just a single global pool + * (legacy & UP mode) */ + SVC_POOL_PERCPU, /* one pool per cpu */ + SVC_POOL_PERNODE /* one pool per numa node */ +}; + +/* + * Structure for mapping cpus to pools and vice versa. + * Setup once during sunrpc initialisation. + */ +static struct svc_pool_map { + int mode; /* Note: int not enum to avoid + * warnings about "enumeration value + * not handled in switch" */ + unsigned int npools; + unsigned int *pool_to; /* maps pool id to cpu or node */ + unsigned int *to_pool; /* maps cpu or node to pool id */ +} svc_pool_map = { + .mode = SVC_POOL_NONE +}; + + +/* + * Detect best pool mapping mode heuristically, + * according to the machine's topology. + */ +static int +svc_pool_map_choose_mode(void) +{ + unsigned int node; + + if (num_online_nodes() > 1) { + /* + * Actually have multiple NUMA nodes, + * so split pools on NUMA node boundaries + */ + return SVC_POOL_PERNODE; + } + + node = any_online_node(node_online_map); + if (nr_cpus_node(node) > 2) { + /* + * Non-trivial SMP, or CONFIG_NUMA on + * non-NUMA hardware, e.g. with a generic + * x86_64 kernel on Xeons. In this case we + * want to divide the pools on cpu boundaries. + */ + return SVC_POOL_PERCPU; + } + + /* default: one global pool */ + return SVC_POOL_GLOBAL; +} + +/* + * Allocate the to_pool[] and pool_to[] arrays. + * Returns 0 on success or an errno. + */ +static int +svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) +{ + m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); + if (!m->to_pool) + goto fail; + m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); + if (!m->pool_to) + goto fail_free; + + return 0; + +fail_free: + kfree(m->to_pool); +fail: + return -ENOMEM; +} + +/* + * Initialise the pool map for SVC_POOL_PERCPU mode. + * Returns number of pools or <0 on error. + */ +static int +svc_pool_map_init_percpu(struct svc_pool_map *m) +{ + unsigned int maxpools = highest_possible_processor_id()+1; + unsigned int pidx = 0; + unsigned int cpu; + int err; + + err = svc_pool_map_alloc_arrays(m, maxpools); + if (err) + return err; + + for_each_online_cpu(cpu) { + BUG_ON(pidx > maxpools); + m->to_pool[cpu] = pidx; + m->pool_to[pidx] = cpu; + pidx++; + } + /* cpus brought online later all get mapped to pool0, sorry */ + + return pidx; +}; + + +/* + * Initialise the pool map for SVC_POOL_PERNODE mode. + * Returns number of pools or <0 on error. + */ +static int +svc_pool_map_init_pernode(struct svc_pool_map *m) +{ + unsigned int maxpools = highest_possible_node_id()+1; + unsigned int pidx = 0; + unsigned int node; + int err; + + err = svc_pool_map_alloc_arrays(m, maxpools); + if (err) + return err; + + for_each_node_with_cpus(node) { + /* some architectures (e.g. SN2) have cpuless nodes */ + BUG_ON(pidx > maxpools); + m->to_pool[node] = pidx; + m->pool_to[pidx] = node; + pidx++; + } + /* nodes brought online later all get mapped to pool0, sorry */ + + return pidx; +} + + +/* + * Build the global map of cpus to pools and vice versa. + */ +static unsigned int +svc_pool_map_init(void) +{ + struct svc_pool_map *m = &svc_pool_map; + int npools = -1; + + if (m->mode != SVC_POOL_NONE) + return m->npools; + + m->mode = svc_pool_map_choose_mode(); + + switch (m->mode) { + case SVC_POOL_PERCPU: + npools = svc_pool_map_init_percpu(m); + break; + case SVC_POOL_PERNODE: + npools = svc_pool_map_init_pernode(m); + break; + } + + if (npools < 0) { + /* default, or memory allocation failure */ + npools = 1; + m->mode = SVC_POOL_GLOBAL; + } + m->npools = npools; + + return m->npools; +} + +/* + * Set the current thread's cpus_allowed mask so that it + * will only run on cpus in the given pool. + * + * Returns 1 and fills in oldmask iff a cpumask was applied. + */ +static inline int +svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) +{ + struct svc_pool_map *m = &svc_pool_map; + unsigned int node; /* or cpu */ + + /* + * The caller checks for sv_nrpools > 1, which + * implies that we've been initialized and the + * map mode is not NONE. + */ + BUG_ON(m->mode == SVC_POOL_NONE); + + switch (m->mode) + { + default: + return 0; + case SVC_POOL_PERCPU: + node = m->pool_to[pidx]; + *oldmask = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(node)); + return 1; + case SVC_POOL_PERNODE: + node = m->pool_to[pidx]; + *oldmask = current->cpus_allowed; + set_cpus_allowed(current, node_to_cpumask(node)); + return 1; + } +} + +/* + * Use the mapping mode to choose a pool for a given CPU. + * Used when enqueueing an incoming RPC. Always returns + * a non-NULL pool pointer. + */ +struct svc_pool * +svc_pool_for_cpu(struct svc_serv *serv, int cpu) +{ + struct svc_pool_map *m = &svc_pool_map; + unsigned int pidx = 0; + + /* + * SVC_POOL_NONE happens in a pure client when + * lockd is brought up, so silently treat it the + * same as SVC_POOL_GLOBAL. + */ + + switch (m->mode) { + case SVC_POOL_PERCPU: + pidx = m->to_pool[cpu]; + break; + case SVC_POOL_PERNODE: + pidx = m->to_pool[cpu_to_node(cpu)]; + break; + } + return &serv->sv_pools[pidx % serv->sv_nrpools]; +} + + +/* * Create an RPC service */ -struct svc_serv * -svc_create(struct svc_program *prog, unsigned int bufsize) +static struct svc_serv * +__svc_create(struct svc_program *prog, unsigned int bufsize, int npools, + void (*shutdown)(struct svc_serv *serv)) { struct svc_serv *serv; int vers; unsigned int xdrsize; + unsigned int i; if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; @@ -38,7 +282,11 @@ svc_create(struct svc_program *prog, unsigned int bufsize) serv->sv_program = prog; serv->sv_nrthreads = 1; serv->sv_stats = prog->pg_stats; - serv->sv_bufsz = bufsize? bufsize : 4096; + if (bufsize > RPCSVC_MAXPAYLOAD) + bufsize = RPCSVC_MAXPAYLOAD; + serv->sv_max_payload = bufsize? bufsize : 4096; + serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); + serv->sv_shutdown = shutdown; xdrsize = 0; while (prog) { prog->pg_lovers = prog->pg_nvers-1; @@ -53,20 +301,68 @@ svc_create(struct svc_program *prog, unsigned int bufsize) prog = prog->pg_next; } serv->sv_xdrsize = xdrsize; - INIT_LIST_HEAD(&serv->sv_threads); - INIT_LIST_HEAD(&serv->sv_sockets); INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); + init_timer(&serv->sv_temptimer); spin_lock_init(&serv->sv_lock); + serv->sv_nrpools = npools; + serv->sv_pools = + kcalloc(sizeof(struct svc_pool), serv->sv_nrpools, + GFP_KERNEL); + if (!serv->sv_pools) { + kfree(serv); + return NULL; + } + + for (i = 0; i < serv->sv_nrpools; i++) { + struct svc_pool *pool = &serv->sv_pools[i]; + + dprintk("initialising pool %u for %s\n", + i, serv->sv_name); + + pool->sp_id = i; + INIT_LIST_HEAD(&pool->sp_threads); + INIT_LIST_HEAD(&pool->sp_sockets); + INIT_LIST_HEAD(&pool->sp_all_threads); + spin_lock_init(&pool->sp_lock); + } + + /* Remove any stale portmap registrations */ svc_register(serv, 0, 0); return serv; } +struct svc_serv * +svc_create(struct svc_program *prog, unsigned int bufsize, + void (*shutdown)(struct svc_serv *serv)) +{ + return __svc_create(prog, bufsize, /*npools*/1, shutdown); +} + +struct svc_serv * +svc_create_pooled(struct svc_program *prog, unsigned int bufsize, + void (*shutdown)(struct svc_serv *serv), + svc_thread_fn func, int sig, struct module *mod) +{ + struct svc_serv *serv; + unsigned int npools = svc_pool_map_init(); + + serv = __svc_create(prog, bufsize, npools, shutdown); + + if (serv != NULL) { + serv->sv_function = func; + serv->sv_kill_signal = sig; + serv->sv_module = mod; + } + + return serv; +} + /* - * Destroy an RPC service + * Destroy an RPC service. Should be called with the BKL held */ void svc_destroy(struct svc_serv *serv) @@ -85,12 +381,17 @@ svc_destroy(struct svc_serv *serv) } else printk("svc_destroy: no threads for serv=%p!\n", serv); + del_timer_sync(&serv->sv_temptimer); + while (!list_empty(&serv->sv_tempsocks)) { svsk = list_entry(serv->sv_tempsocks.next, struct svc_sock, sk_list); svc_delete_socket(svsk); } + if (serv->sv_shutdown) + serv->sv_shutdown(serv); + while (!list_empty(&serv->sv_permsocks)) { svsk = list_entry(serv->sv_permsocks.next, struct svc_sock, @@ -102,6 +403,7 @@ svc_destroy(struct svc_serv *serv) /* Unregister service with the portmapper */ svc_register(serv, 0, 0); + kfree(serv->sv_pools); kfree(serv); } @@ -115,21 +417,18 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) int pages; int arghi; - if (size > RPCSVC_MAXPAYLOAD) - size = RPCSVC_MAXPAYLOAD; - pages = 2 + (size+ PAGE_SIZE -1) / PAGE_SIZE; - rqstp->rq_argused = 0; - rqstp->rq_resused = 0; + pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply. + * We assume one is at most one page + */ arghi = 0; BUG_ON(pages > RPCSVC_MAXPAGES); while (pages) { struct page *p = alloc_page(GFP_KERNEL); if (!p) break; - rqstp->rq_argpages[arghi++] = p; + rqstp->rq_pages[arghi++] = p; pages--; } - rqstp->rq_arghi = arghi; return ! pages; } @@ -139,24 +438,25 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) static void svc_release_buffer(struct svc_rqst *rqstp) { - while (rqstp->rq_arghi) - put_page(rqstp->rq_argpages[--rqstp->rq_arghi]); - while (rqstp->rq_resused) { - if (rqstp->rq_respages[--rqstp->rq_resused] == NULL) - continue; - put_page(rqstp->rq_respages[rqstp->rq_resused]); - } - rqstp->rq_argused = 0; + int i; + for (i=0; i<ARRAY_SIZE(rqstp->rq_pages); i++) + if (rqstp->rq_pages[i]) + put_page(rqstp->rq_pages[i]); } /* - * Create a server thread + * Create a thread in the given pool. Caller must hold BKL. + * On a NUMA or SMP machine, with a multi-pool serv, the thread + * will be restricted to run on the cpus belonging to the pool. */ -int -svc_create_thread(svc_thread_fn func, struct svc_serv *serv) +static int +__svc_create_thread(svc_thread_fn func, struct svc_serv *serv, + struct svc_pool *pool) { struct svc_rqst *rqstp; int error = -ENOMEM; + int have_oldmask = 0; + cpumask_t oldmask; rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL); if (!rqstp) @@ -166,12 +466,25 @@ svc_create_thread(svc_thread_fn func, struct svc_serv *serv) if (!(rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL)) || !(rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL)) - || !svc_init_buffer(rqstp, serv->sv_bufsz)) + || !svc_init_buffer(rqstp, serv->sv_max_mesg)) goto out_thread; serv->sv_nrthreads++; + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads++; + list_add(&rqstp->rq_all, &pool->sp_all_threads); + spin_unlock_bh(&pool->sp_lock); rqstp->rq_server = serv; + rqstp->rq_pool = pool; + + if (serv->sv_nrpools > 1) + have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask); + error = kernel_thread((int (*)(void *)) func, rqstp, 0); + + if (have_oldmask) + set_cpus_allowed(current, oldmask); + if (error < 0) goto out_thread; svc_sock_update_bufs(serv); @@ -185,17 +498,136 @@ out_thread: } /* - * Destroy an RPC server thread + * Create a thread in the default pool. Caller must hold BKL. + */ +int +svc_create_thread(svc_thread_fn func, struct svc_serv *serv) +{ + return __svc_create_thread(func, serv, &serv->sv_pools[0]); +} + +/* + * Choose a pool in which to create a new thread, for svc_set_num_threads + */ +static inline struct svc_pool * +choose_pool(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) +{ + if (pool != NULL) + return pool; + + return &serv->sv_pools[(*state)++ % serv->sv_nrpools]; +} + +/* + * Choose a thread to kill, for svc_set_num_threads + */ +static inline struct task_struct * +choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) +{ + unsigned int i; + struct task_struct *task = NULL; + + if (pool != NULL) { + spin_lock_bh(&pool->sp_lock); + } else { + /* choose a pool in round-robin fashion */ + for (i = 0; i < serv->sv_nrpools; i++) { + pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; + spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_all_threads)) + goto found_pool; + spin_unlock_bh(&pool->sp_lock); + } + return NULL; + } + +found_pool: + if (!list_empty(&pool->sp_all_threads)) { + struct svc_rqst *rqstp; + + /* + * Remove from the pool->sp_all_threads list + * so we don't try to kill it again. + */ + rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all); + list_del_init(&rqstp->rq_all); + task = rqstp->rq_task; + } + spin_unlock_bh(&pool->sp_lock); + + return task; +} + +/* + * Create or destroy enough new threads to make the number + * of threads the given number. If `pool' is non-NULL, applies + * only to threads in that pool, otherwise round-robins between + * all pools. Must be called with a svc_get() reference and + * the BKL held. + * + * Destroying threads relies on the service threads filling in + * rqstp->rq_task, which only the nfs ones do. Assumes the serv + * has been created using svc_create_pooled(). + * + * Based on code that used to be in nfsd_svc() but tweaked + * to be pool-aware. + */ +int +svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) +{ + struct task_struct *victim; + int error = 0; + unsigned int state = serv->sv_nrthreads-1; + + if (pool == NULL) { + /* The -1 assumes caller has done a svc_get() */ + nrservs -= (serv->sv_nrthreads-1); + } else { + spin_lock_bh(&pool->sp_lock); + nrservs -= pool->sp_nrthreads; + spin_unlock_bh(&pool->sp_lock); + } + + /* create new threads */ + while (nrservs > 0) { + nrservs--; + __module_get(serv->sv_module); + error = __svc_create_thread(serv->sv_function, serv, + choose_pool(serv, pool, &state)); + if (error < 0) { + module_put(serv->sv_module); + break; + } + } + /* destroy old threads */ + while (nrservs < 0 && + (victim = choose_victim(serv, pool, &state)) != NULL) { + send_sig(serv->sv_kill_signal, victim, 1); + nrservs++; + } + + return error; +} + +/* + * Called from a server thread as it's exiting. Caller must hold BKL. */ void svc_exit_thread(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; svc_release_buffer(rqstp); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); + + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads--; + list_del(&rqstp->rq_all); + spin_unlock_bh(&pool->sp_lock); + kfree(rqstp); /* Release the server */ @@ -215,23 +647,32 @@ svc_register(struct svc_serv *serv, int proto, unsigned short port) unsigned long flags; int i, error = 0, dummy; - progp = serv->sv_program; - - dprintk("RPC: svc_register(%s, %s, %d)\n", - progp->pg_name, proto == IPPROTO_UDP? "udp" : "tcp", port); - if (!port) clear_thread_flag(TIF_SIGPENDING); - for (i = 0; i < progp->pg_nvers; i++) { - if (progp->pg_vers[i] == NULL) - continue; - error = rpc_register(progp->pg_prog, i, proto, port, &dummy); - if (error < 0) - break; - if (port && !dummy) { - error = -EACCES; - break; + for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (i = 0; i < progp->pg_nvers; i++) { + if (progp->pg_vers[i] == NULL) + continue; + + dprintk("RPC: svc_register(%s, %s, %d, %d)%s\n", + progp->pg_name, + proto == IPPROTO_UDP? "udp" : "tcp", + port, + i, + progp->pg_vers[i]->vs_hidden? + " (but not telling portmap)" : ""); + + if (progp->pg_vers[i]->vs_hidden) + continue; + + error = rpc_register(progp->pg_prog, i, proto, port, &dummy); + if (error < 0) + break; + if (port && !dummy) { + error = -EACCES; + break; + } } } @@ -248,19 +689,20 @@ svc_register(struct svc_serv *serv, int proto, unsigned short port) * Process the RPC request. */ int -svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_process(struct svc_rqst *rqstp) { struct svc_program *progp; struct svc_version *versp = NULL; /* compiler food */ struct svc_procedure *procp = NULL; struct kvec * argv = &rqstp->rq_arg.head[0]; struct kvec * resv = &rqstp->rq_res.head[0]; + struct svc_serv *serv = rqstp->rq_server; kxdrproc_t xdr; - u32 *statp; - u32 dir, prog, vers, proc, - auth_stat, rpc_stat; + __be32 *statp; + u32 dir, prog, vers, proc; + __be32 auth_stat, rpc_stat; int auth_res; - u32 *accept_statp; + __be32 *reply_statp; rpc_stat = rpc_success; @@ -270,10 +712,10 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) /* setup response xdr_buf. * Initially it has just one page */ - svc_take_page(rqstp); /* must succeed */ + rqstp->rq_resused = 1; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; - rqstp->rq_res.pages = rqstp->rq_respages+1; + rqstp->rq_res.pages = rqstp->rq_respages + 1; rqstp->rq_res.len = 0; rqstp->rq_res.page_base = 0; rqstp->rq_res.page_len = 0; @@ -284,16 +726,16 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) rqstp->rq_sendfile_ok = 1; /* tcp needs a space for the record length... */ if (rqstp->rq_prot == IPPROTO_TCP) - svc_putu32(resv, 0); + svc_putnl(resv, 0); rqstp->rq_xid = svc_getu32(argv); svc_putu32(resv, rqstp->rq_xid); - dir = ntohl(svc_getu32(argv)); - vers = ntohl(svc_getu32(argv)); + dir = svc_getnl(argv); + vers = svc_getnl(argv); /* First words of reply: */ - svc_putu32(resv, xdr_one); /* REPLY */ + svc_putnl(resv, 1); /* REPLY */ if (dir != 0) /* direction != CALL */ goto err_bad_dir; @@ -301,13 +743,13 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) goto err_bad_rpc; /* Save position in case we later decide to reject: */ - accept_statp = resv->iov_base + resv->iov_len; + reply_statp = resv->iov_base + resv->iov_len; - svc_putu32(resv, xdr_zero); /* ACCEPT */ + svc_putnl(resv, 0); /* ACCEPT */ - rqstp->rq_prog = prog = ntohl(svc_getu32(argv)); /* program number */ - rqstp->rq_vers = vers = ntohl(svc_getu32(argv)); /* version number */ - rqstp->rq_proc = proc = ntohl(svc_getu32(argv)); /* procedure number */ + rqstp->rq_prog = prog = svc_getnl(argv); /* program number */ + rqstp->rq_vers = vers = svc_getnl(argv); /* version number */ + rqstp->rq_proc = proc = svc_getnl(argv); /* procedure number */ progp = serv->sv_program; @@ -361,7 +803,7 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) /* Build the reply header. */ statp = resv->iov_base +resv->iov_len; - svc_putu32(resv, rpc_success); /* RPC_SUCCESS */ + svc_putnl(resv, RPC_SUCCESS); /* Bump per-procedure stats counter */ procp->pc_count++; @@ -386,6 +828,11 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); /* Encode reply */ + if (*statp == rpc_drop_reply) { + if (procp->pc_release) + procp->pc_release(rqstp, NULL, rqstp->rq_resp); + goto dropit; + } if (*statp == rpc_success && (xdr = procp->pc_encode) && !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { dprintk("svc: failed to encode reply\n"); @@ -439,26 +886,26 @@ err_bad_dir: err_bad_rpc: serv->sv_stats->rpcbadfmt++; - svc_putu32(resv, xdr_one); /* REJECT */ - svc_putu32(resv, xdr_zero); /* RPC_MISMATCH */ - svc_putu32(resv, xdr_two); /* Only RPCv2 supported */ - svc_putu32(resv, xdr_two); + svc_putnl(resv, 1); /* REJECT */ + svc_putnl(resv, 0); /* RPC_MISMATCH */ + svc_putnl(resv, 2); /* Only RPCv2 supported */ + svc_putnl(resv, 2); goto sendit; err_bad_auth: dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat)); serv->sv_stats->rpcbadauth++; /* Restore write pointer to location of accept status: */ - xdr_ressize_check(rqstp, accept_statp); - svc_putu32(resv, xdr_one); /* REJECT */ - svc_putu32(resv, xdr_one); /* AUTH_ERROR */ - svc_putu32(resv, auth_stat); /* status */ + xdr_ressize_check(rqstp, reply_statp); + svc_putnl(resv, 1); /* REJECT */ + svc_putnl(resv, 1); /* AUTH_ERROR */ + svc_putnl(resv, ntohl(auth_stat)); /* status */ goto sendit; err_bad_prog: dprintk("svc: unknown program %d\n", prog); serv->sv_stats->rpcbadfmt++; - svc_putu32(resv, rpc_prog_unavail); + svc_putnl(resv, RPC_PROG_UNAVAIL); goto sendit; err_bad_vers: @@ -466,9 +913,9 @@ err_bad_vers: printk("svc: unknown version (%d)\n", vers); #endif serv->sv_stats->rpcbadfmt++; - svc_putu32(resv, rpc_prog_mismatch); - svc_putu32(resv, htonl(progp->pg_lovers)); - svc_putu32(resv, htonl(progp->pg_hivers)); + svc_putnl(resv, RPC_PROG_MISMATCH); + svc_putnl(resv, progp->pg_lovers); + svc_putnl(resv, progp->pg_hivers); goto sendit; err_bad_proc: @@ -476,7 +923,7 @@ err_bad_proc: printk("svc: unknown procedure (%d)\n", proc); #endif serv->sv_stats->rpcbadfmt++; - svc_putu32(resv, rpc_proc_unavail); + svc_putnl(resv, RPC_PROC_UNAVAIL); goto sendit; err_garbage: @@ -486,6 +933,21 @@ err_garbage: rpc_stat = rpc_garbage_args; err_bad: serv->sv_stats->rpcbadfmt++; - svc_putu32(resv, rpc_stat); + svc_putnl(resv, ntohl(rpc_stat)); goto sendit; } + +/* + * Return (transport-specific) limit on the rpc payload. + */ +u32 svc_max_payload(const struct svc_rqst *rqstp) +{ + int max = RPCSVC_MAXPAYLOAD_TCP; + + if (rqstp->rq_sock->sk_sock->type == SOCK_DGRAM) + max = RPCSVC_MAXPAYLOAD_UDP; + if (rqstp->rq_server->sv_max_payload < max) + max = rqstp->rq_server->sv_max_payload; + return max; +} +EXPORT_SYMBOL_GPL(svc_max_payload); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 5b28c6176806..8f2320aded5c 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -35,14 +35,14 @@ static struct auth_ops *authtab[RPC_AUTH_MAXFLAVOR] = { }; int -svc_authenticate(struct svc_rqst *rqstp, u32 *authp) +svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) { rpc_authflavor_t flavor; struct auth_ops *aops; *authp = rpc_auth_ok; - flavor = ntohl(svc_getu32(&rqstp->rq_arg.head[0])); + flavor = svc_getnl(&rqstp->rq_arg.head[0]); dprintk("svc: svc_authenticate (%d)\n", flavor); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 7e5707e2d6b6..e1bd933629fe 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -9,6 +9,7 @@ #include <linux/seq_file.h> #include <linux/hash.h> #include <linux/string.h> +#include <net/sock.h> #define RPCDBG_FACILITY RPCDBG_AUTH @@ -145,7 +146,7 @@ static void ip_map_request(struct cache_detail *cd, { char text_addr[20]; struct ip_map *im = container_of(h, struct ip_map, h); - __u32 addr = im->m_addr.s_addr; + __be32 addr = im->m_addr.s_addr; snprintf(text_addr, 20, "%u.%u.%u.%u", ntohl(addr) >> 24 & 0xff, @@ -249,10 +250,10 @@ static int ip_map_show(struct seq_file *m, seq_printf(m, "%s %d.%d.%d.%d %s\n", im->m_class, - htonl(addr.s_addr) >> 24 & 0xff, - htonl(addr.s_addr) >> 16 & 0xff, - htonl(addr.s_addr) >> 8 & 0xff, - htonl(addr.s_addr) >> 0 & 0xff, + ntohl(addr.s_addr) >> 24 & 0xff, + ntohl(addr.s_addr) >> 16 & 0xff, + ntohl(addr.s_addr) >> 8 & 0xff, + ntohl(addr.s_addr) >> 0 & 0xff, dom ); return 0; @@ -348,12 +349,9 @@ int auth_unix_forget_old(struct auth_domain *dom) struct auth_domain *auth_unix_lookup(struct in_addr addr) { - struct ip_map key, *ipm; + struct ip_map *ipm; struct auth_domain *rv; - strcpy(key.m_class, "nfsd"); - key.m_addr = addr; - ipm = ip_map_lookup("nfsd", addr); if (!ipm) @@ -378,6 +376,44 @@ void svcauth_unix_purge(void) cache_purge(&ip_map_cache); } +static inline struct ip_map * +ip_map_cached_get(struct svc_rqst *rqstp) +{ + struct ip_map *ipm = rqstp->rq_sock->sk_info_authunix; + if (ipm != NULL) { + if (!cache_valid(&ipm->h)) { + /* + * The entry has been invalidated since it was + * remembered, e.g. by a second mount from the + * same IP address. + */ + rqstp->rq_sock->sk_info_authunix = NULL; + cache_put(&ipm->h, &ip_map_cache); + return NULL; + } + cache_get(&ipm->h); + } + return ipm; +} + +static inline void +ip_map_cached_put(struct svc_rqst *rqstp, struct ip_map *ipm) +{ + struct svc_sock *svsk = rqstp->rq_sock; + + if (svsk->sk_sock->type == SOCK_STREAM && svsk->sk_info_authunix == NULL) + svsk->sk_info_authunix = ipm; /* newly cached, keep the reference */ + else + cache_put(&ipm->h, &ip_map_cache); +} + +void +svcauth_unix_info_release(void *info) +{ + struct ip_map *ipm = info; + cache_put(&ipm->h, &ip_map_cache); +} + static int svcauth_unix_set_client(struct svc_rqst *rqstp) { @@ -387,8 +423,10 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) if (rqstp->rq_proc == 0) return SVC_OK; - ipm = ip_map_lookup(rqstp->rq_server->sv_program->pg_class, - rqstp->rq_addr.sin_addr); + ipm = ip_map_cached_get(rqstp); + if (ipm == NULL) + ipm = ip_map_lookup(rqstp->rq_server->sv_program->pg_class, + rqstp->rq_addr.sin_addr); if (ipm == NULL) return SVC_DENIED; @@ -403,14 +441,14 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) case 0: rqstp->rq_client = &ipm->m_client->h; kref_get(&rqstp->rq_client->ref); - cache_put(&ipm->h, &ip_map_cache); + ip_map_cached_put(rqstp, ipm); break; } return SVC_OK; } static int -svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp) +svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -427,7 +465,7 @@ svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp) *authp = rpc_autherr_badcred; return SVC_DENIED; } - if (svc_getu32(argv) != RPC_AUTH_NULL || svc_getu32(argv) != 0) { + if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { dprintk("svc: bad null verf\n"); *authp = rpc_autherr_badverf; return SVC_DENIED; @@ -441,8 +479,8 @@ svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp) return SVC_DROP; /* kmalloc failure - client must retry */ /* Put NULL verifier */ - svc_putu32(resv, RPC_AUTH_NULL); - svc_putu32(resv, 0); + svc_putnl(resv, RPC_AUTH_NULL); + svc_putnl(resv, 0); return SVC_OK; } @@ -472,7 +510,7 @@ struct auth_ops svcauth_null = { static int -svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp) +svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -488,31 +526,31 @@ svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp) svc_getu32(argv); /* length */ svc_getu32(argv); /* time stamp */ - slen = XDR_QUADLEN(ntohl(svc_getu32(argv))); /* machname length */ + slen = XDR_QUADLEN(svc_getnl(argv)); /* machname length */ if (slen > 64 || (len -= (slen + 3)*4) < 0) goto badcred; - argv->iov_base = (void*)((u32*)argv->iov_base + slen); /* skip machname */ + argv->iov_base = (void*)((__be32*)argv->iov_base + slen); /* skip machname */ argv->iov_len -= slen*4; - cred->cr_uid = ntohl(svc_getu32(argv)); /* uid */ - cred->cr_gid = ntohl(svc_getu32(argv)); /* gid */ - slen = ntohl(svc_getu32(argv)); /* gids length */ + cred->cr_uid = svc_getnl(argv); /* uid */ + cred->cr_gid = svc_getnl(argv); /* gid */ + slen = svc_getnl(argv); /* gids length */ if (slen > 16 || (len -= (slen + 2)*4) < 0) goto badcred; cred->cr_group_info = groups_alloc(slen); if (cred->cr_group_info == NULL) return SVC_DROP; for (i = 0; i < slen; i++) - GROUP_AT(cred->cr_group_info, i) = ntohl(svc_getu32(argv)); + GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); - if (svc_getu32(argv) != RPC_AUTH_NULL || svc_getu32(argv) != 0) { + if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; } /* Put NULL verifier */ - svc_putu32(resv, RPC_AUTH_NULL); - svc_putu32(resv, 0); + svc_putnl(resv, RPC_AUTH_NULL); + svc_putnl(resv, 0); return SVC_OK; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 953aff89bcac..96521f16342b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -31,6 +31,7 @@ #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/file.h> #include <net/sock.h> #include <net/checksum.h> #include <net/ip.h> @@ -45,13 +46,16 @@ /* SMP locking strategy: * - * svc_serv->sv_lock protects most stuff for that service. + * svc_pool->sp_lock protects most of the fields of that pool. + * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt. + * when both need to be taken (rare), svc_serv->sv_lock is first. + * BKL protects svc_serv->sv_nrthread. + * svc_sock->sk_defer_lock protects the svc_sock->sk_deferred list + * svc_sock->sk_flags.SK_BUSY prevents a svc_sock being enqueued multiply. * * Some flags can be set to certain values at any time * providing that certain rules are followed: * - * SK_BUSY can be set to 0 at any time. - * svc_sock_enqueue must be called afterwards * SK_CONN, SK_DATA, can be set or cleared at any time. * after a set, svc_sock_enqueue must be called. * after a clear, the socket must be read/accepted @@ -73,23 +77,30 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); +/* apparently the "standard" is that clients close + * idle connections after 5 minutes, servers after + * 6 minutes + * http://www.connectathon.org/talks96/nfstcp.pdf + */ +static int svc_conn_age_period = 6*60; + /* - * Queue up an idle server thread. Must have serv->sv_lock held. + * Queue up an idle server thread. Must have pool->sp_lock held. * Note: this is really a stack rather than a queue, so that we only - * use as many different threads as we need, and the rest don't polute + * use as many different threads as we need, and the rest don't pollute * the cache. */ static inline void -svc_serv_enqueue(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp) { - list_add(&rqstp->rq_list, &serv->sv_threads); + list_add(&rqstp->rq_list, &pool->sp_threads); } /* - * Dequeue an nfsd thread. Must have serv->sv_lock held. + * Dequeue an nfsd thread. Must have pool->sp_lock held. */ static inline void -svc_serv_dequeue(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp) { list_del(&rqstp->rq_list); } @@ -140,7 +151,9 @@ static void svc_sock_enqueue(struct svc_sock *svsk) { struct svc_serv *serv = svsk->sk_server; + struct svc_pool *pool; struct svc_rqst *rqstp; + int cpu; if (!(svsk->sk_flags & ( (1<<SK_CONN)|(1<<SK_DATA)|(1<<SK_CLOSE)|(1<<SK_DEFERRED)) )) @@ -148,10 +161,14 @@ svc_sock_enqueue(struct svc_sock *svsk) if (test_bit(SK_DEAD, &svsk->sk_flags)) return; - spin_lock_bh(&serv->sv_lock); + cpu = get_cpu(); + pool = svc_pool_for_cpu(svsk->sk_server, cpu); + put_cpu(); + + spin_lock_bh(&pool->sp_lock); - if (!list_empty(&serv->sv_threads) && - !list_empty(&serv->sv_sockets)) + if (!list_empty(&pool->sp_threads) && + !list_empty(&pool->sp_sockets)) printk(KERN_ERR "svc_sock_enqueue: threads and sockets both waiting??\n"); @@ -161,73 +178,79 @@ svc_sock_enqueue(struct svc_sock *svsk) goto out_unlock; } - if (test_bit(SK_BUSY, &svsk->sk_flags)) { - /* Don't enqueue socket while daemon is receiving */ + /* Mark socket as busy. It will remain in this state until the + * server has processed all pending data and put the socket back + * on the idle list. We update SK_BUSY atomically because + * it also guards against trying to enqueue the svc_sock twice. + */ + if (test_and_set_bit(SK_BUSY, &svsk->sk_flags)) { + /* Don't enqueue socket while already enqueued */ dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk); goto out_unlock; } + BUG_ON(svsk->sk_pool != NULL); + svsk->sk_pool = pool; set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - if (((svsk->sk_reserved + serv->sv_bufsz)*2 + if (((atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg)*2 > svc_sock_wspace(svsk)) && !test_bit(SK_CLOSE, &svsk->sk_flags) && !test_bit(SK_CONN, &svsk->sk_flags)) { /* Don't enqueue while not enough space for reply */ dprintk("svc: socket %p no space, %d*2 > %ld, not enqueued\n", - svsk->sk_sk, svsk->sk_reserved+serv->sv_bufsz, + svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_max_mesg, svc_sock_wspace(svsk)); + svsk->sk_pool = NULL; + clear_bit(SK_BUSY, &svsk->sk_flags); goto out_unlock; } clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - /* Mark socket as busy. It will remain in this state until the - * server has processed all pending data and put the socket back - * on the idle list. - */ - set_bit(SK_BUSY, &svsk->sk_flags); - if (!list_empty(&serv->sv_threads)) { - rqstp = list_entry(serv->sv_threads.next, + if (!list_empty(&pool->sp_threads)) { + rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); dprintk("svc: socket %p served by daemon %p\n", svsk->sk_sk, rqstp); - svc_serv_dequeue(serv, rqstp); + svc_thread_dequeue(pool, rqstp); if (rqstp->rq_sock) printk(KERN_ERR "svc_sock_enqueue: server %p, rq_sock=%p!\n", rqstp, rqstp->rq_sock); rqstp->rq_sock = svsk; - svsk->sk_inuse++; - rqstp->rq_reserved = serv->sv_bufsz; - svsk->sk_reserved += rqstp->rq_reserved; + atomic_inc(&svsk->sk_inuse); + rqstp->rq_reserved = serv->sv_max_mesg; + atomic_add(rqstp->rq_reserved, &svsk->sk_reserved); + BUG_ON(svsk->sk_pool != pool); wake_up(&rqstp->rq_wait); } else { dprintk("svc: socket %p put into queue\n", svsk->sk_sk); - list_add_tail(&svsk->sk_ready, &serv->sv_sockets); + list_add_tail(&svsk->sk_ready, &pool->sp_sockets); + BUG_ON(svsk->sk_pool != pool); } out_unlock: - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); } /* - * Dequeue the first socket. Must be called with the serv->sv_lock held. + * Dequeue the first socket. Must be called with the pool->sp_lock held. */ static inline struct svc_sock * -svc_sock_dequeue(struct svc_serv *serv) +svc_sock_dequeue(struct svc_pool *pool) { struct svc_sock *svsk; - if (list_empty(&serv->sv_sockets)) + if (list_empty(&pool->sp_sockets)) return NULL; - svsk = list_entry(serv->sv_sockets.next, + svsk = list_entry(pool->sp_sockets.next, struct svc_sock, sk_ready); list_del_init(&svsk->sk_ready); dprintk("svc: socket %p dequeued, inuse=%d\n", - svsk->sk_sk, svsk->sk_inuse); + svsk->sk_sk, atomic_read(&svsk->sk_inuse)); return svsk; } @@ -241,6 +264,7 @@ svc_sock_dequeue(struct svc_serv *serv) static inline void svc_sock_received(struct svc_sock *svsk) { + svsk->sk_pool = NULL; clear_bit(SK_BUSY, &svsk->sk_flags); svc_sock_enqueue(svsk); } @@ -262,10 +286,8 @@ void svc_reserve(struct svc_rqst *rqstp, int space) if (space < rqstp->rq_reserved) { struct svc_sock *svsk = rqstp->rq_sock; - spin_lock_bh(&svsk->sk_server->sv_lock); - svsk->sk_reserved -= (rqstp->rq_reserved - space); + atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved); rqstp->rq_reserved = space; - spin_unlock_bh(&svsk->sk_server->sv_lock); svc_sock_enqueue(svsk); } @@ -277,17 +299,11 @@ void svc_reserve(struct svc_rqst *rqstp, int space) static inline void svc_sock_put(struct svc_sock *svsk) { - struct svc_serv *serv = svsk->sk_server; - - spin_lock_bh(&serv->sv_lock); - if (!--(svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) { - spin_unlock_bh(&serv->sv_lock); + if (atomic_dec_and_test(&svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) { dprintk("svc: releasing dead socket\n"); sock_release(svsk->sk_sock); kfree(svsk); } - else - spin_unlock_bh(&serv->sv_lock); } static void @@ -297,7 +313,7 @@ svc_sock_release(struct svc_rqst *rqstp) svc_release_skb(rqstp); - svc_free_allpages(rqstp); + svc_free_res_pages(rqstp); rqstp->rq_res.page_len = 0; rqstp->rq_res.page_base = 0; @@ -321,25 +337,33 @@ svc_sock_release(struct svc_rqst *rqstp) /* * External function to wake up a server waiting for data + * This really only makes sense for services like lockd + * which have exactly one thread anyway. */ void svc_wake_up(struct svc_serv *serv) { struct svc_rqst *rqstp; - - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&serv->sv_threads)) { - rqstp = list_entry(serv->sv_threads.next, - struct svc_rqst, - rq_list); - dprintk("svc: daemon %p woken up.\n", rqstp); - /* - svc_serv_dequeue(serv, rqstp); - rqstp->rq_sock = NULL; - */ - wake_up(&rqstp->rq_wait); + unsigned int i; + struct svc_pool *pool; + + for (i = 0; i < serv->sv_nrpools; i++) { + pool = &serv->sv_pools[i]; + + spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_threads)) { + rqstp = list_entry(pool->sp_threads.next, + struct svc_rqst, + rq_list); + dprintk("svc: daemon %p woken up.\n", rqstp); + /* + svc_thread_dequeue(pool, rqstp); + rqstp->rq_sock = NULL; + */ + wake_up(&rqstp->rq_wait); + } + spin_unlock_bh(&pool->sp_lock); } - spin_unlock_bh(&serv->sv_lock); } /* @@ -388,7 +412,8 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) /* send head */ if (slen == xdr->head[0].iov_len) flags = 0; - len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags); + len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, + xdr->head[0].iov_len, flags); if (len != xdr->head[0].iov_len) goto out; slen -= xdr->head[0].iov_len; @@ -413,8 +438,9 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) } /* send tail */ if (xdr->tail[0].iov_len) { - result = kernel_sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage], - ((unsigned long)xdr->tail[0].iov_base)& (PAGE_SIZE-1), + result = kernel_sendpage(sock, rqstp->rq_respages[0], + ((unsigned long)xdr->tail[0].iov_base) + & (PAGE_SIZE-1), xdr->tail[0].iov_len, 0); if (result > 0) @@ -429,6 +455,56 @@ out: } /* + * Report socket names for nfsdfs + */ +static int one_sock_name(char *buf, struct svc_sock *svsk) +{ + int len; + + switch(svsk->sk_sk->sk_family) { + case AF_INET: + len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n", + svsk->sk_sk->sk_protocol==IPPROTO_UDP? + "udp" : "tcp", + NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr), + inet_sk(svsk->sk_sk)->num); + break; + default: + len = sprintf(buf, "*unknown-%d*\n", + svsk->sk_sk->sk_family); + } + return len; +} + +int +svc_sock_names(char *buf, struct svc_serv *serv, char *toclose) +{ + struct svc_sock *svsk, *closesk = NULL; + int len = 0; + + if (!serv) + return 0; + spin_lock(&serv->sv_lock); + list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) { + int onelen = one_sock_name(buf+len, svsk); + if (toclose && strcmp(toclose, buf+len) == 0) + closesk = svsk; + else + len += onelen; + } + spin_unlock(&serv->sv_lock); + if (closesk) + /* Should unregister with portmap, but you cannot + * unregister just one protocol... + */ + svc_delete_socket(closesk); + else if (toclose) + return -ENOENT; + return len; +} +EXPORT_SYMBOL(svc_sock_names); + +/* * Check input queue length */ static int @@ -557,11 +633,14 @@ svc_udp_recvfrom(struct svc_rqst *rqstp) /* udp sockets need large rcvbuf as all pending * requests are still in that buffer. sndbuf must * also be large enough that there is enough space - * for one reply per thread. + * for one reply per thread. We count all threads + * rather than threads in a particular pool, which + * provides an upper bound on the number of threads + * which will access the socket. */ svc_sock_setbufsize(svsk->sk_sock, - (serv->sv_nrthreads+3) * serv->sv_bufsz, - (serv->sv_nrthreads+3) * serv->sv_bufsz); + (serv->sv_nrthreads+3) * serv->sv_max_mesg, + (serv->sv_nrthreads+3) * serv->sv_max_mesg); if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) { svc_sock_received(svsk); @@ -631,9 +710,11 @@ svc_udp_recvfrom(struct svc_rqst *rqstp) if (len <= rqstp->rq_arg.head[0].iov_len) { rqstp->rq_arg.head[0].iov_len = len; rqstp->rq_arg.page_len = 0; + rqstp->rq_respages = rqstp->rq_pages+1; } else { rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len; - rqstp->rq_argused += (rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE; + rqstp->rq_respages = rqstp->rq_pages + 1 + + (rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE; } if (serv->sv_stats) @@ -668,8 +749,8 @@ svc_udp_init(struct svc_sock *svsk) * svc_udp_recvfrom will re-adjust if necessary */ svc_sock_setbufsize(svsk->sk_sock, - 3 * svsk->sk_server->sv_bufsz, - 3 * svsk->sk_server->sv_bufsz); + 3 * svsk->sk_server->sv_max_mesg, + 3 * svsk->sk_server->sv_max_mesg); set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */ set_bit(SK_CHNGBUF, &svsk->sk_flags); @@ -844,7 +925,7 @@ svc_tcp_accept(struct svc_sock *svsk) struct svc_sock, sk_list); set_bit(SK_CLOSE, &svsk->sk_flags); - svsk->sk_inuse ++; + atomic_inc(&svsk->sk_inuse); } spin_unlock_bh(&serv->sv_lock); @@ -874,7 +955,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) struct svc_sock *svsk = rqstp->rq_sock; struct svc_serv *serv = svsk->sk_server; int len; - struct kvec vec[RPCSVC_MAXPAGES]; + struct kvec *vec; int pnum, vlen; dprintk("svc: tcp_recv %p data %d conn %d close %d\n", @@ -892,7 +973,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) return 0; } - if (test_bit(SK_CONN, &svsk->sk_flags)) { + if (svsk->sk_sk->sk_state == TCP_LISTEN) { svc_tcp_accept(svsk); svc_sock_received(svsk); return 0; @@ -902,13 +983,18 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) /* sndbuf needs to have room for one request * per thread, otherwise we can stall even when the * network isn't a bottleneck. + * + * We count all threads rather than threads in a + * particular pool, which provides an upper bound + * on the number of threads which will access the socket. + * * rcvbuf just needs to be able to hold a few requests. * Normally they will be removed from the queue * as soon a a complete request arrives. */ svc_sock_setbufsize(svsk->sk_sock, - (serv->sv_nrthreads+3) * serv->sv_bufsz, - 3 * serv->sv_bufsz); + (serv->sv_nrthreads+3) * serv->sv_max_mesg, + 3 * serv->sv_max_mesg); clear_bit(SK_DATA, &svsk->sk_flags); @@ -946,7 +1032,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) } svsk->sk_reclen &= 0x7fffffff; dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen); - if (svsk->sk_reclen > serv->sv_bufsz) { + if (svsk->sk_reclen > serv->sv_max_mesg) { printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx (large)\n", (unsigned long) svsk->sk_reclen); goto err_delete; @@ -967,15 +1053,17 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) len = svsk->sk_reclen; set_bit(SK_DATA, &svsk->sk_flags); + vec = rqstp->rq_vec; vec[0] = rqstp->rq_arg.head[0]; vlen = PAGE_SIZE; pnum = 1; while (vlen < len) { - vec[pnum].iov_base = page_address(rqstp->rq_argpages[rqstp->rq_argused++]); + vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]); vec[pnum].iov_len = PAGE_SIZE; pnum++; vlen += PAGE_SIZE; } + rqstp->rq_respages = &rqstp->rq_pages[pnum]; /* Now receive data */ len = svc_recvfrom(rqstp, vec, pnum, len); @@ -1030,7 +1118,7 @@ svc_tcp_sendto(struct svc_rqst *rqstp) { struct xdr_buf *xbufp = &rqstp->rq_res; int sent; - u32 reclen; + __be32 reclen; /* Set up the first element of the reply kvec. * Any other kvecs that may be in use have been taken @@ -1083,8 +1171,8 @@ svc_tcp_init(struct svc_sock *svsk) * svc_tcp_recvfrom will re-adjust if necessary */ svc_sock_setbufsize(svsk->sk_sock, - 3 * svsk->sk_server->sv_bufsz, - 3 * svsk->sk_server->sv_bufsz); + 3 * svsk->sk_server->sv_max_mesg, + 3 * svsk->sk_server->sv_max_mesg); set_bit(SK_CHNGBUF, &svsk->sk_flags); set_bit(SK_DATA, &svsk->sk_flags); @@ -1117,13 +1205,17 @@ svc_sock_update_bufs(struct svc_serv *serv) } /* - * Receive the next request on any socket. + * Receive the next request on any socket. This code is carefully + * organised not to touch any cachelines in the shared svc_serv + * structure, only cachelines in the local svc_pool. */ int -svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) +svc_recv(struct svc_rqst *rqstp, long timeout) { struct svc_sock *svsk =NULL; - int len; + struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; + int len, i; int pages; struct xdr_buf *arg; DECLARE_WAITQUEUE(wait, current); @@ -1140,27 +1232,22 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) "svc_recv: service %p, wait queue active!\n", rqstp); - /* Initialize the buffers */ - /* first reclaim pages that were moved to response list */ - svc_pushback_allpages(rqstp); /* now allocate needed pages. If we get a failure, sleep briefly */ - pages = 2 + (serv->sv_bufsz + PAGE_SIZE -1) / PAGE_SIZE; - while (rqstp->rq_arghi < pages) { - struct page *p = alloc_page(GFP_KERNEL); - if (!p) { - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - continue; + pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE; + for (i=0; i < pages ; i++) + while (rqstp->rq_pages[i] == NULL) { + struct page *p = alloc_page(GFP_KERNEL); + if (!p) + schedule_timeout_uninterruptible(msecs_to_jiffies(500)); + rqstp->rq_pages[i] = p; } - rqstp->rq_argpages[rqstp->rq_arghi++] = p; - } /* Make arg->head point to first page and arg->pages point to rest */ arg = &rqstp->rq_arg; - arg->head[0].iov_base = page_address(rqstp->rq_argpages[0]); + arg->head[0].iov_base = page_address(rqstp->rq_pages[0]); arg->head[0].iov_len = PAGE_SIZE; - rqstp->rq_argused = 1; - arg->pages = rqstp->rq_argpages + 1; + arg->pages = rqstp->rq_pages + 1; arg->page_base = 0; /* save at least one page for response */ arg->page_len = (pages-2)*PAGE_SIZE; @@ -1172,32 +1259,15 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) if (signalled()) return -EINTR; - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&serv->sv_tempsocks)) { - svsk = list_entry(serv->sv_tempsocks.next, - struct svc_sock, sk_list); - /* apparently the "standard" is that clients close - * idle connections after 5 minutes, servers after - * 6 minutes - * http://www.connectathon.org/talks96/nfstcp.pdf - */ - if (get_seconds() - svsk->sk_lastrecv < 6*60 - || test_bit(SK_BUSY, &svsk->sk_flags)) - svsk = NULL; - } - if (svsk) { - set_bit(SK_BUSY, &svsk->sk_flags); - set_bit(SK_CLOSE, &svsk->sk_flags); - rqstp->rq_sock = svsk; - svsk->sk_inuse++; - } else if ((svsk = svc_sock_dequeue(serv)) != NULL) { + spin_lock_bh(&pool->sp_lock); + if ((svsk = svc_sock_dequeue(pool)) != NULL) { rqstp->rq_sock = svsk; - svsk->sk_inuse++; - rqstp->rq_reserved = serv->sv_bufsz; - svsk->sk_reserved += rqstp->rq_reserved; + atomic_inc(&svsk->sk_inuse); + rqstp->rq_reserved = serv->sv_max_mesg; + atomic_add(rqstp->rq_reserved, &svsk->sk_reserved); } else { /* No data pending. Go to sleep */ - svc_serv_enqueue(serv, rqstp); + svc_thread_enqueue(pool, rqstp); /* * We have to be able to interrupt this wait @@ -1205,26 +1275,26 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) */ set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&rqstp->rq_wait, &wait); - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); schedule_timeout(timeout); try_to_freeze(); - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&pool->sp_lock); remove_wait_queue(&rqstp->rq_wait, &wait); if (!(svsk = rqstp->rq_sock)) { - svc_serv_dequeue(serv, rqstp); - spin_unlock_bh(&serv->sv_lock); + svc_thread_dequeue(pool, rqstp); + spin_unlock_bh(&pool->sp_lock); dprintk("svc: server %p, no data yet\n", rqstp); return signalled()? -EINTR : -EAGAIN; } } - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); - dprintk("svc: server %p, socket %p, inuse=%d\n", - rqstp, svsk, svsk->sk_inuse); + dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n", + rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse)); len = svsk->sk_recvfrom(rqstp); dprintk("svc: got len=%d\n", len); @@ -1235,13 +1305,7 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) return -EAGAIN; } svsk->sk_lastrecv = get_seconds(); - if (test_bit(SK_TEMP, &svsk->sk_flags)) { - /* push active sockets to end of list */ - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&svsk->sk_list)) - list_move_tail(&svsk->sk_list, &serv->sv_tempsocks); - spin_unlock_bh(&serv->sv_lock); - } + clear_bit(SK_OLD, &svsk->sk_flags); rqstp->rq_secure = ntohs(rqstp->rq_addr.sin_port) < 1024; rqstp->rq_chandle.defer = svc_defer; @@ -1301,6 +1365,58 @@ svc_send(struct svc_rqst *rqstp) } /* + * Timer function to close old temporary sockets, using + * a mark-and-sweep algorithm. + */ +static void +svc_age_temp_sockets(unsigned long closure) +{ + struct svc_serv *serv = (struct svc_serv *)closure; + struct svc_sock *svsk; + struct list_head *le, *next; + LIST_HEAD(to_be_aged); + + dprintk("svc_age_temp_sockets\n"); + + if (!spin_trylock_bh(&serv->sv_lock)) { + /* busy, try again 1 sec later */ + dprintk("svc_age_temp_sockets: busy\n"); + mod_timer(&serv->sv_temptimer, jiffies + HZ); + return; + } + + list_for_each_safe(le, next, &serv->sv_tempsocks) { + svsk = list_entry(le, struct svc_sock, sk_list); + + if (!test_and_set_bit(SK_OLD, &svsk->sk_flags)) + continue; + if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags)) + continue; + atomic_inc(&svsk->sk_inuse); + list_move(le, &to_be_aged); + set_bit(SK_CLOSE, &svsk->sk_flags); + set_bit(SK_DETACHED, &svsk->sk_flags); + } + spin_unlock_bh(&serv->sv_lock); + + while (!list_empty(&to_be_aged)) { + le = to_be_aged.next; + /* fiddling the sk_list node is safe 'cos we're SK_DETACHED */ + list_del_init(le); + svsk = list_entry(le, struct svc_sock, sk_list); + + dprintk("queuing svsk %p for closing, %lu seconds old\n", + svsk, get_seconds() - svsk->sk_lastrecv); + + /* a thread will dequeue and close it soon */ + svc_sock_enqueue(svsk); + svc_sock_put(svsk); + } + + mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); +} + +/* * Initialize socket for RPC use and create svc_sock struct * XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF. */ @@ -1337,7 +1453,9 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, svsk->sk_odata = inet->sk_data_ready; svsk->sk_owspace = inet->sk_write_space; svsk->sk_server = serv; + atomic_set(&svsk->sk_inuse, 0); svsk->sk_lastrecv = get_seconds(); + spin_lock_init(&svsk->sk_defer_lock); INIT_LIST_HEAD(&svsk->sk_deferred); INIT_LIST_HEAD(&svsk->sk_ready); mutex_init(&svsk->sk_mutex); @@ -1353,6 +1471,13 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, set_bit(SK_TEMP, &svsk->sk_flags); list_add(&svsk->sk_list, &serv->sv_tempsocks); serv->sv_tmpcnt++; + if (serv->sv_temptimer.function == NULL) { + /* setup timer to age temp sockets */ + setup_timer(&serv->sv_temptimer, svc_age_temp_sockets, + (unsigned long)serv); + mod_timer(&serv->sv_temptimer, + jiffies + svc_conn_age_period * HZ); + } } else { clear_bit(SK_TEMP, &svsk->sk_flags); list_add(&svsk->sk_list, &serv->sv_permsocks); @@ -1367,6 +1492,38 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, return svsk; } +int svc_addsock(struct svc_serv *serv, + int fd, + char *name_return, + int *proto) +{ + int err = 0; + struct socket *so = sockfd_lookup(fd, &err); + struct svc_sock *svsk = NULL; + + if (!so) + return err; + if (so->sk->sk_family != AF_INET) + err = -EAFNOSUPPORT; + else if (so->sk->sk_protocol != IPPROTO_TCP && + so->sk->sk_protocol != IPPROTO_UDP) + err = -EPROTONOSUPPORT; + else if (so->state > SS_UNCONNECTED) + err = -EISCONN; + else { + svsk = svc_setup_socket(serv, so, &err, 1); + if (svsk) + err = 0; + } + if (err) { + sockfd_put(so); + return err; + } + if (proto) *proto = so->sk->sk_protocol; + return one_sock_name(name_return, svsk); +} +EXPORT_SYMBOL_GPL(svc_addsock); + /* * Create socket for RPC service. */ @@ -1393,14 +1550,12 @@ svc_create_socket(struct svc_serv *serv, int protocol, struct sockaddr_in *sin) if ((error = sock_create_kern(PF_INET, type, protocol, &sock)) < 0) return error; - if (sin != NULL) { - if (type == SOCK_STREAM) - sock->sk->sk_reuse = 1; /* allow address reuse */ - error = kernel_bind(sock, (struct sockaddr *) sin, - sizeof(*sin)); - if (error < 0) - goto bummer; - } + if (type == SOCK_STREAM) + sock->sk->sk_reuse = 1; /* allow address reuse */ + error = kernel_bind(sock, (struct sockaddr *) sin, + sizeof(*sin)); + if (error < 0) + goto bummer; if (protocol == IPPROTO_TCP) { if ((error = kernel_listen(sock, 64)) < 0) @@ -1436,15 +1591,27 @@ svc_delete_socket(struct svc_sock *svsk) spin_lock_bh(&serv->sv_lock); - list_del_init(&svsk->sk_list); - list_del_init(&svsk->sk_ready); + if (!test_and_set_bit(SK_DETACHED, &svsk->sk_flags)) + list_del_init(&svsk->sk_list); + /* + * We used to delete the svc_sock from whichever list + * it's sk_ready node was on, but we don't actually + * need to. This is because the only time we're called + * while still attached to a queue, the queue itself + * is about to be destroyed (in svc_destroy). + */ if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags)) if (test_bit(SK_TEMP, &svsk->sk_flags)) serv->sv_tmpcnt--; - if (!svsk->sk_inuse) { + if (!atomic_read(&svsk->sk_inuse)) { spin_unlock_bh(&serv->sv_lock); - sock_release(svsk->sk_sock); + if (svsk->sk_sock->file) + sockfd_put(svsk->sk_sock); + else + sock_release(svsk->sk_sock); + if (svsk->sk_info_authunix != NULL) + svcauth_unix_info_release(svsk->sk_info_authunix); kfree(svsk); } else { spin_unlock_bh(&serv->sv_lock); @@ -1475,7 +1642,6 @@ svc_makesock(struct svc_serv *serv, int protocol, unsigned short port) static void svc_revisit(struct cache_deferred_req *dreq, int too_many) { struct svc_deferred_req *dr = container_of(dreq, struct svc_deferred_req, handle); - struct svc_serv *serv = dreq->owner; struct svc_sock *svsk; if (too_many) { @@ -1486,9 +1652,9 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) dprintk("revisit queued\n"); svsk = dr->svsk; dr->svsk = NULL; - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&svsk->sk_defer_lock); list_add(&dr->handle.recent, &svsk->sk_deferred); - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&svsk->sk_defer_lock); set_bit(SK_DEFERRED, &svsk->sk_flags); svc_sock_enqueue(svsk); svc_sock_put(svsk); @@ -1520,10 +1686,8 @@ svc_defer(struct cache_req *req) dr->argslen = rqstp->rq_arg.len >> 2; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2); } - spin_lock_bh(&rqstp->rq_server->sv_lock); - rqstp->rq_sock->sk_inuse++; + atomic_inc(&rqstp->rq_sock->sk_inuse); dr->svsk = rqstp->rq_sock; - spin_unlock_bh(&rqstp->rq_server->sv_lock); dr->handle.revisit = svc_revisit; return &dr->handle; @@ -1543,6 +1707,7 @@ static int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_prot = dr->prot; rqstp->rq_addr = dr->addr; rqstp->rq_daddr = dr->daddr; + rqstp->rq_respages = rqstp->rq_pages; return dr->argslen<<2; } @@ -1550,11 +1715,10 @@ static int svc_deferred_recv(struct svc_rqst *rqstp) static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk) { struct svc_deferred_req *dr = NULL; - struct svc_serv *serv = svsk->sk_server; if (!test_bit(SK_DEFERRED, &svsk->sk_flags)) return NULL; - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&svsk->sk_defer_lock); clear_bit(SK_DEFERRED, &svsk->sk_flags); if (!list_empty(&svsk->sk_deferred)) { dr = list_entry(svsk->sk_deferred.next, @@ -1563,6 +1727,6 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk) list_del_init(&dr->handle.recent); set_bit(SK_DEFERRED, &svsk->sk_flags); } - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&svsk->sk_defer_lock); return dr; } diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 6ac45103a272..9022eb8b37ed 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -18,8 +18,8 @@ /* * XDR functions for basic NFS types */ -u32 * -xdr_encode_netobj(u32 *p, const struct xdr_netobj *obj) +__be32 * +xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) { unsigned int quadlen = XDR_QUADLEN(obj->len); @@ -29,8 +29,8 @@ xdr_encode_netobj(u32 *p, const struct xdr_netobj *obj) return p + XDR_QUADLEN(obj->len); } -u32 * -xdr_decode_netobj(u32 *p, struct xdr_netobj *obj) +__be32 * +xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) { unsigned int len; @@ -55,7 +55,7 @@ xdr_decode_netobj(u32 *p, struct xdr_netobj *obj) * Returns the updated current XDR buffer position * */ -u32 *xdr_encode_opaque_fixed(u32 *p, const void *ptr, unsigned int nbytes) +__be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int nbytes) { if (likely(nbytes != 0)) { unsigned int quadlen = XDR_QUADLEN(nbytes); @@ -79,21 +79,21 @@ EXPORT_SYMBOL(xdr_encode_opaque_fixed); * * Returns the updated current XDR buffer position */ -u32 *xdr_encode_opaque(u32 *p, const void *ptr, unsigned int nbytes) +__be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes) { *p++ = htonl(nbytes); return xdr_encode_opaque_fixed(p, ptr, nbytes); } EXPORT_SYMBOL(xdr_encode_opaque); -u32 * -xdr_encode_string(u32 *p, const char *string) +__be32 * +xdr_encode_string(__be32 *p, const char *string) { return xdr_encode_array(p, string, strlen(string)); } -u32 * -xdr_decode_string_inplace(u32 *p, char **sp, int *lenp, int maxlen) +__be32 * +xdr_decode_string_inplace(__be32 *p, char **sp, int *lenp, int maxlen) { unsigned int len; @@ -432,7 +432,7 @@ xdr_shift_buf(struct xdr_buf *buf, size_t len) * of the buffer length, and takes care of adjusting the kvec * length for us. */ -void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p) +void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) { struct kvec *iov = buf->head; int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len; @@ -440,8 +440,8 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p) BUG_ON(scratch_len < 0); xdr->buf = buf; xdr->iov = iov; - xdr->p = (uint32_t *)((char *)iov->iov_base + iov->iov_len); - xdr->end = (uint32_t *)((char *)iov->iov_base + scratch_len); + xdr->p = (__be32 *)((char *)iov->iov_base + iov->iov_len); + xdr->end = (__be32 *)((char *)iov->iov_base + scratch_len); BUG_ON(iov->iov_len > scratch_len); if (p != xdr->p && p != NULL) { @@ -465,10 +465,10 @@ EXPORT_SYMBOL(xdr_init_encode); * bytes of data. If so, update the total xdr_buf length, and * adjust the length of the current kvec. */ -uint32_t * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) +__be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) { - uint32_t *p = xdr->p; - uint32_t *q; + __be32 *p = xdr->p; + __be32 *q; /* align nbytes on the next 32-bit boundary */ nbytes += 3; @@ -524,7 +524,7 @@ EXPORT_SYMBOL(xdr_write_pages); * @buf: pointer to XDR buffer from which to decode data * @p: current pointer inside XDR buffer */ -void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p) +void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) { struct kvec *iov = buf->head; unsigned int len = iov->iov_len; @@ -534,7 +534,7 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p) xdr->buf = buf; xdr->iov = iov; xdr->p = p; - xdr->end = (uint32_t *)((char *)iov->iov_base + len); + xdr->end = (__be32 *)((char *)iov->iov_base + len); } EXPORT_SYMBOL(xdr_init_decode); @@ -548,10 +548,10 @@ EXPORT_SYMBOL(xdr_init_decode); * If so return the current pointer, then update the current * pointer position. */ -uint32_t * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) +__be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { - uint32_t *p = xdr->p; - uint32_t *q = p + XDR_QUADLEN(nbytes); + __be32 *p = xdr->p; + __be32 *q = p + XDR_QUADLEN(nbytes); if (unlikely(q > xdr->end || q < p)) return NULL; @@ -599,8 +599,8 @@ void xdr_read_pages(struct xdr_stream *xdr, unsigned int len) * Position current pointer at beginning of tail, and * set remaining message length. */ - xdr->p = (uint32_t *)((char *)iov->iov_base + padding); - xdr->end = (uint32_t *)((char *)iov->iov_base + end); + xdr->p = (__be32 *)((char *)iov->iov_base + padding); + xdr->end = (__be32 *)((char *)iov->iov_base + end); } EXPORT_SYMBOL(xdr_read_pages); @@ -624,8 +624,8 @@ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) */ if (len > PAGE_CACHE_SIZE - xdr->buf->page_base) len = PAGE_CACHE_SIZE - xdr->buf->page_base; - xdr->p = (uint32_t *)(kaddr + xdr->buf->page_base); - xdr->end = (uint32_t *)((char *)xdr->p + len); + xdr->p = (__be32 *)(kaddr + xdr->buf->page_base); + xdr->end = (__be32 *)((char *)xdr->p + len); } EXPORT_SYMBOL(xdr_enter_page); @@ -743,7 +743,7 @@ out: int xdr_decode_word(struct xdr_buf *buf, int base, u32 *obj) { - u32 raw; + __be32 raw; int status; status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); @@ -756,7 +756,7 @@ xdr_decode_word(struct xdr_buf *buf, int base, u32 *obj) int xdr_encode_word(struct xdr_buf *buf, int base, u32 obj) { - u32 raw = htonl(obj); + __be32 raw = htonl(obj); return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj)); } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 1f786f68729d..80857470dc11 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -594,7 +594,7 @@ static void xprt_connect_status(struct rpc_task *task) * @xid: RPC XID of incoming reply * */ -struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid) +struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) { struct list_head *pos; @@ -801,7 +801,7 @@ void xprt_reserve(struct rpc_task *task) spin_unlock(&xprt->reserve_lock); } -static inline u32 xprt_alloc_xid(struct rpc_xprt *xprt) +static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) { return xprt->xid++; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9b62923a9c06..757fc91ef25d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -548,7 +548,8 @@ static void xs_udp_data_ready(struct sock *sk, int len) struct rpc_rqst *rovr; struct sk_buff *skb; int err, repsize, copied; - u32 _xid, *xp; + u32 _xid; + __be32 *xp; read_lock(&sk->sk_callback_lock); dprintk("RPC: xs_udp_data_ready...\n"); @@ -1365,7 +1366,7 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to) if (xprt->slot == NULL) return -ENOMEM; - if (ntohs(addr->sin_port != 0)) + if (ntohs(addr->sin_port) != 0) xprt_set_bound(xprt); xprt->port = xs_get_random_port(); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 75a5968c2139..39744a33bd36 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -2,7 +2,7 @@ * net/tipc/bearer.c: TIPC bearer code * * Copyright (c) 1996-2006, Ericsson AB - * Copyright (c) 2004-2005, Wind River Systems + * Copyright (c) 2004-2006, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -191,14 +191,14 @@ void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a) if ((i < media_count) && (m_ptr->addr2str != NULL)) { char addr_str[MAX_ADDR_STR]; - tipc_printf(pb, "%s(%s) ", m_ptr->name, + tipc_printf(pb, "%s(%s)", m_ptr->name, m_ptr->addr2str(a, addr_str, sizeof(addr_str))); } else { unchar *addr = (unchar *)&a->dev_addr; - tipc_printf(pb, "UNKNOWN(%u):", media_type); + tipc_printf(pb, "UNKNOWN(%u)", media_type); for (i = 0; i < (sizeof(*a) - sizeof(a->type)); i++) { - tipc_printf(pb, "%02x ", addr[i]); + tipc_printf(pb, "-%02x", addr[i]); } } } diff --git a/net/tipc/config.c b/net/tipc/config.c index 285e1bc2d880..ed1351ed05e1 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -2,7 +2,7 @@ * net/tipc/config.c: TIPC configuration management code * * Copyright (c) 2002-2006, Ericsson AB - * Copyright (c) 2004-2005, Wind River Systems + * Copyright (c) 2004-2006, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -613,7 +613,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id); break; default: - rep_tlv_buf = NULL; + rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (unknown command)"); break; } diff --git a/net/tipc/core.c b/net/tipc/core.c index 0539a8362858..6f5b7ee31180 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -57,7 +57,7 @@ void tipc_socket_stop(void); int tipc_netlink_start(void); void tipc_netlink_stop(void); -#define TIPC_MOD_VER "1.6.1" +#define TIPC_MOD_VER "1.6.2" #ifndef CONFIG_TIPC_ZONES #define CONFIG_TIPC_ZONES 3 @@ -90,7 +90,7 @@ int tipc_random; atomic_t tipc_user_count = ATOMIC_INIT(0); const char tipc_alphabet[] = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_"; + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_."; /* configurable TIPC parameters */ diff --git a/net/tipc/core.h b/net/tipc/core.h index 762aac2572be..4638947c2326 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -65,7 +65,7 @@ #define assert(i) BUG_ON(!(i)) struct tipc_msg; -extern struct print_buf *TIPC_CONS, *TIPC_LOG; +extern struct print_buf *TIPC_NULL, *TIPC_CONS, *TIPC_LOG; extern struct print_buf *TIPC_TEE(struct print_buf *, struct print_buf *); void tipc_msg_print(struct print_buf*,struct tipc_msg *,const char*); void tipc_printf(struct print_buf *, const char *fmt, ...); @@ -83,9 +83,9 @@ void tipc_dump(struct print_buf*,const char *fmt, ...); #define warn(fmt, arg...) tipc_printf(TIPC_OUTPUT, KERN_WARNING "TIPC: " fmt, ## arg) #define info(fmt, arg...) tipc_printf(TIPC_OUTPUT, KERN_NOTICE "TIPC: " fmt, ## arg) -#define dbg(fmt, arg...) do {if (DBG_OUTPUT) tipc_printf(DBG_OUTPUT, fmt, ## arg);} while(0) -#define msg_dbg(msg, txt) do {if (DBG_OUTPUT) tipc_msg_print(DBG_OUTPUT, msg, txt);} while(0) -#define dump(fmt, arg...) do {if (DBG_OUTPUT) tipc_dump(DBG_OUTPUT, fmt, ##arg);} while(0) +#define dbg(fmt, arg...) do {if (DBG_OUTPUT != TIPC_NULL) tipc_printf(DBG_OUTPUT, fmt, ## arg);} while(0) +#define msg_dbg(msg, txt) do {if (DBG_OUTPUT != TIPC_NULL) tipc_msg_print(DBG_OUTPUT, msg, txt);} while(0) +#define dump(fmt, arg...) do {if (DBG_OUTPUT != TIPC_NULL) tipc_dump(DBG_OUTPUT, fmt, ##arg);} while(0) /* @@ -94,11 +94,11 @@ void tipc_dump(struct print_buf*,const char *fmt, ...); * here, or on a per .c file basis, by redefining these symbols. The following * print buffer options are available: * - * NULL : Output to null print buffer (i.e. print nowhere) - * TIPC_CONS : Output to system console - * TIPC_LOG : Output to TIPC log buffer - * &buf : Output to user-defined buffer (struct print_buf *) - * TIPC_TEE(&buf_a,&buf_b) : Output to two print buffers (eg. TIPC_TEE(TIPC_CONS,TIPC_LOG) ) + * TIPC_NULL : null buffer (i.e. print nowhere) + * TIPC_CONS : system console + * TIPC_LOG : TIPC log buffer + * &buf : user-defined buffer (struct print_buf *) + * TIPC_TEE(&buf_a,&buf_b) : list of buffers (eg. TIPC_TEE(TIPC_CONS,TIPC_LOG)) */ #ifndef TIPC_OUTPUT @@ -106,7 +106,7 @@ void tipc_dump(struct print_buf*,const char *fmt, ...); #endif #ifndef DBG_OUTPUT -#define DBG_OUTPUT NULL +#define DBG_OUTPUT TIPC_NULL #endif #else @@ -136,7 +136,7 @@ void tipc_dump(struct print_buf*,const char *fmt, ...); #define TIPC_OUTPUT TIPC_CONS #undef DBG_OUTPUT -#define DBG_OUTPUT NULL +#define DBG_OUTPUT TIPC_NULL #endif @@ -275,11 +275,15 @@ static inline void k_term_timer(struct timer_list *timer) /* * TIPC message buffer code * - * TIPC message buffer headroom leaves room for 14 byte Ethernet header, + * TIPC message buffer headroom reserves space for a link-level header + * (in case the message is sent off-node), * while ensuring TIPC header is word aligned for quicker access + * + * The largest header currently supported is 18 bytes, which is used when + * the standard 14 byte Ethernet header has 4 added bytes for VLAN info */ -#define BUF_HEADROOM 16u +#define BUF_HEADROOM 20u struct tipc_skb_cb { void *handle; diff --git a/net/tipc/dbg.c b/net/tipc/dbg.c index 55130655e1ed..d8af4c28695d 100644 --- a/net/tipc/dbg.c +++ b/net/tipc/dbg.c @@ -1,8 +1,8 @@ /* - * net/tipc/dbg.c: TIPC print buffer routines for debuggign + * net/tipc/dbg.c: TIPC print buffer routines for debugging * * Copyright (c) 1996-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005-2006, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -38,11 +38,12 @@ #include "config.h" #include "dbg.h" -#define MAX_STRING 512 - -static char print_string[MAX_STRING]; +static char print_string[TIPC_PB_MAX_STR]; static DEFINE_SPINLOCK(print_lock); +static struct print_buf null_buf = { NULL, 0, NULL, NULL }; +struct print_buf *TIPC_NULL = &null_buf; + static struct print_buf cons_buf = { NULL, 0, NULL, NULL }; struct print_buf *TIPC_CONS = &cons_buf; @@ -62,68 +63,83 @@ struct print_buf *TIPC_LOG = &log_buf; /* * Locking policy when using print buffers. * - * 1) Routines of the form printbuf_XXX() rely on the caller to prevent - * simultaneous use of the print buffer(s) being manipulated. - * 2) tipc_printf() uses 'print_lock' to prevent simultaneous use of - * 'print_string' and to protect its print buffer(s). - * 3) TIPC_TEE() uses 'print_lock' to protect its print buffer(s). - * 4) Routines of the form log_XXX() uses 'print_lock' to protect TIPC_LOG. + * The following routines use 'print_lock' for protection: + * 1) tipc_printf() - to protect its print buffer(s) and 'print_string' + * 2) TIPC_TEE() - to protect its print buffer(s) + * 3) tipc_dump() - to protect its print buffer(s) and 'print_string' + * 4) tipc_log_XXX() - to protect TIPC_LOG + * + * All routines of the form tipc_printbuf_XXX() rely on the caller to prevent + * simultaneous use of the print buffer(s) being manipulated. */ /** * tipc_printbuf_init - initialize print buffer to empty + * @pb: pointer to print buffer structure + * @raw: pointer to character array used by print buffer + * @size: size of character array + * + * Makes the print buffer a null device that discards anything written to it + * if the character array is too small (or absent). */ -void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 sz) +void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) { - if (!pb || !raw || (sz < (MAX_STRING + 1))) - return; - - pb->crs = pb->buf = raw; - pb->size = sz; + pb->buf = raw; + pb->crs = raw; + pb->size = size; pb->next = NULL; - pb->buf[0] = 0; - pb->buf[sz-1] = ~0; + + if (size < TIPC_PB_MIN_SIZE) { + pb->buf = NULL; + } else if (raw) { + pb->buf[0] = 0; + pb->buf[size-1] = ~0; + } } /** * tipc_printbuf_reset - reinitialize print buffer to empty state + * @pb: pointer to print buffer structure */ void tipc_printbuf_reset(struct print_buf *pb) { - if (pb && pb->buf) - tipc_printbuf_init(pb, pb->buf, pb->size); + tipc_printbuf_init(pb, pb->buf, pb->size); } /** * tipc_printbuf_empty - test if print buffer is in empty state + * @pb: pointer to print buffer structure + * + * Returns non-zero if print buffer is empty. */ int tipc_printbuf_empty(struct print_buf *pb) { - return (!pb || !pb->buf || (pb->crs == pb->buf)); + return (!pb->buf || (pb->crs == pb->buf)); } /** * tipc_printbuf_validate - check for print buffer overflow + * @pb: pointer to print buffer structure * * Verifies that a print buffer has captured all data written to it. * If data has been lost, linearize buffer and prepend an error message * - * Returns length of print buffer data string (including trailing NULL) + * Returns length of print buffer data string (including trailing NUL) */ int tipc_printbuf_validate(struct print_buf *pb) { - char *err = " *** PRINT BUFFER WRAPPED AROUND ***\n"; + char *err = "\n\n*** PRINT BUFFER OVERFLOW ***\n\n"; char *cp_buf; struct print_buf cb; - if (!pb || !pb->buf) + if (!pb->buf) return 0; - if (pb->buf[pb->size - 1] == '\0') { + if (pb->buf[pb->size - 1] == 0) { cp_buf = kmalloc(pb->size, GFP_ATOMIC); if (cp_buf != NULL){ tipc_printbuf_init(&cb, cp_buf, pb->size); @@ -141,6 +157,8 @@ int tipc_printbuf_validate(struct print_buf *pb) /** * tipc_printbuf_move - move print buffer contents to another print buffer + * @pb_to: pointer to destination print buffer structure + * @pb_from: pointer to source print buffer structure * * Current contents of destination print buffer (if any) are discarded. * Source print buffer becomes empty if a successful move occurs. @@ -152,21 +170,22 @@ void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) /* Handle the cases where contents can't be moved */ - if (!pb_to || !pb_to->buf) + if (!pb_to->buf) return; - if (!pb_from || !pb_from->buf) { + if (!pb_from->buf) { tipc_printbuf_reset(pb_to); return; } if (pb_to->size < pb_from->size) { tipc_printbuf_reset(pb_to); - tipc_printf(pb_to, "*** PRINT BUFFER OVERFLOW ***"); + tipc_printf(pb_to, "*** PRINT BUFFER MOVE ERROR ***"); return; } /* Copy data from char after cursor to end (if used) */ + len = pb_from->buf + pb_from->size - pb_from->crs - 2; if ((pb_from->buf[pb_from->size-1] == 0) && (len > 0)) { strcpy(pb_to->buf, pb_from->crs + 1); @@ -175,6 +194,7 @@ void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) pb_to->crs = pb_to->buf; /* Copy data from start to cursor (always) */ + len = pb_from->crs - pb_from->buf; strcpy(pb_to->crs, pb_from->buf); pb_to->crs += len; @@ -184,6 +204,8 @@ void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) /** * tipc_printf - append formatted output to print buffer chain + * @pb: pointer to chain of print buffers (may be NULL) + * @fmt: formatted info to be printed */ void tipc_printf(struct print_buf *pb, const char *fmt, ...) @@ -195,8 +217,8 @@ void tipc_printf(struct print_buf *pb, const char *fmt, ...) spin_lock_bh(&print_lock); FORMAT(print_string, chars_to_add, fmt); - if (chars_to_add >= MAX_STRING) - strcpy(print_string, "*** STRING TOO LONG ***"); + if (chars_to_add >= TIPC_PB_MAX_STR) + strcpy(print_string, "*** PRINT BUFFER STRING TOO LONG ***"); while (pb) { if (pb == TIPC_CONS) @@ -206,6 +228,10 @@ void tipc_printf(struct print_buf *pb, const char *fmt, ...) if (chars_to_add <= chars_left) { strcpy(pb->crs, print_string); pb->crs += chars_to_add; + } else if (chars_to_add >= (pb->size - 1)) { + strcpy(pb->buf, print_string + chars_to_add + 1 + - pb->size); + pb->crs = pb->buf + pb->size - 1; } else { strcpy(pb->buf, print_string + chars_left); save_char = print_string[chars_left]; @@ -224,6 +250,10 @@ void tipc_printf(struct print_buf *pb, const char *fmt, ...) /** * TIPC_TEE - perform next output operation on both print buffers + * @b0: pointer to chain of print buffers (may be NULL) + * @b1: pointer to print buffer to add to chain + * + * Returns pointer to print buffer chain. */ struct print_buf *TIPC_TEE(struct print_buf *b0, struct print_buf *b1) @@ -232,8 +262,6 @@ struct print_buf *TIPC_TEE(struct print_buf *b0, struct print_buf *b1) if (!b0 || (b0 == b1)) return b1; - if (!b1) - return b0; spin_lock_bh(&print_lock); while (pb->next) { @@ -256,7 +284,7 @@ static void print_to_console(char *crs, int len) int rest = len; while (rest > 0) { - int sz = rest < MAX_STRING ? rest : MAX_STRING; + int sz = rest < TIPC_PB_MAX_STR ? rest : TIPC_PB_MAX_STR; char c = crs[sz]; crs[sz] = 0; @@ -275,36 +303,48 @@ static void printbuf_dump(struct print_buf *pb) { int len; + if (!pb->buf) { + printk("*** PRINT BUFFER NOT ALLOCATED ***"); + return; + } + /* Dump print buffer from char after cursor to end (if used) */ + len = pb->buf + pb->size - pb->crs - 2; if ((pb->buf[pb->size - 1] == 0) && (len > 0)) print_to_console(pb->crs + 1, len); /* Dump print buffer from start to cursor (always) */ + len = pb->crs - pb->buf; print_to_console(pb->buf, len); } /** * tipc_dump - dump non-console print buffer(s) to console + * @pb: pointer to chain of print buffers */ void tipc_dump(struct print_buf *pb, const char *fmt, ...) { + struct print_buf *pb_next; int len; spin_lock_bh(&print_lock); - FORMAT(TIPC_CONS->buf, len, fmt); - printk(TIPC_CONS->buf); + FORMAT(print_string, len, fmt); + printk(print_string); for (; pb; pb = pb->next) { - if (pb == TIPC_CONS) - continue; - printk("\n---- Start of dump,%s log ----\n\n", - (pb == TIPC_LOG) ? "global" : "local"); - printbuf_dump(pb); - tipc_printbuf_reset(pb); - printk("\n-------- End of dump --------\n"); + if (pb != TIPC_CONS) { + printk("\n---- Start of %s log dump ----\n\n", + (pb == TIPC_LOG) ? "global" : "local"); + printbuf_dump(pb); + tipc_printbuf_reset(pb); + printk("\n---- End of dump ----\n"); + } + pb_next = pb->next; + pb->next = NULL; + pb = pb_next; } spin_unlock_bh(&print_lock); } @@ -324,7 +364,8 @@ void tipc_log_stop(void) } /** - * tipc_log_reinit - set TIPC log print buffer to specified size + * tipc_log_reinit - (re)initialize TIPC log print buffer + * @log_size: print buffer size to use */ void tipc_log_reinit(int log_size) @@ -332,10 +373,11 @@ void tipc_log_reinit(int log_size) tipc_log_stop(); if (log_size) { - if (log_size <= MAX_STRING) - log_size = MAX_STRING + 1; + if (log_size < TIPC_PB_MIN_SIZE) + log_size = TIPC_PB_MIN_SIZE; spin_lock_bh(&print_lock); - tipc_printbuf_init(TIPC_LOG, kmalloc(log_size, GFP_ATOMIC), log_size); + tipc_printbuf_init(TIPC_LOG, kmalloc(log_size, GFP_ATOMIC), + log_size); spin_unlock_bh(&print_lock); } } diff --git a/net/tipc/dbg.h b/net/tipc/dbg.h index 227f050d2a52..467c0bc78a79 100644 --- a/net/tipc/dbg.h +++ b/net/tipc/dbg.h @@ -2,7 +2,7 @@ * net/tipc/dbg.h: Include file for TIPC print buffer routines * * Copyright (c) 1997-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005-2006, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -37,6 +37,14 @@ #ifndef _TIPC_DBG_H #define _TIPC_DBG_H +/** + * struct print_buf - TIPC print buffer structure + * @buf: pointer to character array containing print buffer contents + * @size: size of character array + * @crs: pointer to first unused space in character array (i.e. final NUL) + * @next: used to link print buffers when printing to more than one at a time + */ + struct print_buf { char *buf; u32 size; @@ -44,7 +52,10 @@ struct print_buf { struct print_buf *next; }; -void tipc_printbuf_init(struct print_buf *pb, char *buf, u32 sz); +#define TIPC_PB_MIN_SIZE 64 /* minimum size for a print buffer's array */ +#define TIPC_PB_MAX_STR 512 /* max printable string (with trailing NUL) */ + +void tipc_printbuf_init(struct print_buf *pb, char *buf, u32 size); void tipc_printbuf_reset(struct print_buf *pb); int tipc_printbuf_empty(struct print_buf *pb); int tipc_printbuf_validate(struct print_buf *pb); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index ee94de92ae99..3b0cd12f37da 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -132,6 +132,28 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, } /** + * disc_dupl_alert - issue node address duplication alert + * @b_ptr: pointer to bearer detecting duplication + * @node_addr: duplicated node address + * @media_addr: media address advertised by duplicated node + */ + +static void disc_dupl_alert(struct bearer *b_ptr, u32 node_addr, + struct tipc_media_addr *media_addr) +{ + char node_addr_str[16]; + char media_addr_str[64]; + struct print_buf pb; + + addr_string_fill(node_addr_str, node_addr); + tipc_printbuf_init(&pb, media_addr_str, sizeof(media_addr_str)); + tipc_media_addr_printf(&pb, media_addr); + tipc_printbuf_validate(&pb); + warn("Duplicate %s using %s seen on <%s>\n", + node_addr_str, media_addr_str, b_ptr->publ.name); +} + +/** * tipc_disc_recv_msg - handle incoming link setup message (request or response) * @buf: buffer containing message */ @@ -157,8 +179,11 @@ void tipc_disc_recv_msg(struct sk_buff *buf) return; if (!tipc_addr_node_valid(orig)) return; - if (orig == tipc_own_addr) + if (orig == tipc_own_addr) { + if (memcmp(&media_addr, &b_ptr->publ.addr, sizeof(media_addr))) + disc_dupl_alert(b_ptr, tipc_own_addr, &media_addr); return; + } if (!in_scope(dest, tipc_own_addr)) return; if (is_slave(tipc_own_addr) && is_slave(orig)) @@ -170,7 +195,8 @@ void tipc_disc_recv_msg(struct sk_buff *buf) struct sk_buff *rbuf; struct tipc_media_addr *addr; struct node *n_ptr = tipc_node_find(orig); - int link_up; + int link_fully_up; + dbg(" in own cluster\n"); if (n_ptr == NULL) { n_ptr = tipc_node_create(orig); @@ -190,14 +216,19 @@ void tipc_disc_recv_msg(struct sk_buff *buf) } addr = &link->media_addr; if (memcmp(addr, &media_addr, sizeof(*addr))) { + if (tipc_link_is_up(link) || (!link->started)) { + disc_dupl_alert(b_ptr, orig, &media_addr); + spin_unlock_bh(&n_ptr->lock); + return; + } warn("Resetting link <%s>, peer interface address changed\n", link->name); memcpy(addr, &media_addr, sizeof(*addr)); tipc_link_reset(link); } - link_up = tipc_link_is_up(link); + link_fully_up = (link->state == WORKING_WORKING); spin_unlock_bh(&n_ptr->lock); - if ((type == DSC_RESP_MSG) || link_up) + if ((type == DSC_RESP_MSG) || link_fully_up) return; rbuf = tipc_disc_init_msg(DSC_RESP_MSG, 1, orig, b_ptr); if (rbuf != NULL) { diff --git a/net/tipc/link.c b/net/tipc/link.c index 693f02eca6d6..1bb983c8130b 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -132,7 +132,7 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, * allow the output from multiple links to be intermixed. For this reason * routines of the form "dbg_link_XXX()" have been created that will capture * debug info into a link's personal print buffer, which can then be dumped - * into the TIPC system log (LOG) upon request. + * into the TIPC system log (TIPC_LOG) upon request. * * To enable per-link debugging, use LINK_LOG_BUF_SIZE to specify the size * of the print buffer used by each link. If LINK_LOG_BUF_SIZE is set to 0, @@ -141,7 +141,7 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, * when there is only a single link in the system being debugged. * * Notes: - * - When enabled, LINK_LOG_BUF_SIZE should be set to at least 1000 (bytes) + * - When enabled, LINK_LOG_BUF_SIZE should be set to at least TIPC_PB_MIN_SIZE * - "l_ptr" must be valid when using dbg_link_XXX() macros */ @@ -159,13 +159,13 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, static void dbg_print_link(struct link *l_ptr, const char *str) { - if (DBG_OUTPUT) + if (DBG_OUTPUT != TIPC_NULL) link_print(l_ptr, DBG_OUTPUT, str); } static void dbg_print_buf_chain(struct sk_buff *root_buf) { - if (DBG_OUTPUT) { + if (DBG_OUTPUT != TIPC_NULL) { struct sk_buff *buf = root_buf; while (buf) { @@ -1666,8 +1666,9 @@ static void link_retransmit_failure(struct link *l_ptr, struct sk_buff *buf) char addr_string[16]; tipc_printf(TIPC_OUTPUT, "Msg seq number: %u, ", msg_seqno(msg)); - tipc_printf(TIPC_OUTPUT, "Outstanding acks: %u\n", (u32)TIPC_SKB_CB(buf)->handle); - + tipc_printf(TIPC_OUTPUT, "Outstanding acks: %lu\n", + (unsigned long) TIPC_SKB_CB(buf)->handle); + n_ptr = l_ptr->owner->next; tipc_node_lock(n_ptr); diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index f0b063bcc2a9..03bd659c43ca 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -122,7 +122,7 @@ void tipc_named_publish(struct publication *publ) struct sk_buff *buf; struct distr_item *item; - list_add(&publ->local_list, &publ_root); + list_add_tail(&publ->local_list, &publ_root); publ_cnt++; buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0); diff --git a/net/tipc/node.c b/net/tipc/node.c index fc6d09630ccd..886bda5e88db 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -648,7 +648,7 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network address)"); - if (!tipc_nodes) + if (tipc_mode != TIPC_NET_MODE) return tipc_cfg_reply_none(); /* Get space for all unicast links + multicast link */ diff --git a/net/tipc/port.c b/net/tipc/port.c index b9c8c6b9e94f..c1a1a76759b5 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -505,8 +505,13 @@ static void port_timeout(unsigned long ref) struct port *p_ptr = tipc_port_lock(ref); struct sk_buff *buf = NULL; - if (!p_ptr || !p_ptr->publ.connected) + if (!p_ptr) + return; + + if (!p_ptr->publ.connected) { + tipc_port_unlock(p_ptr); return; + } /* Last probe answered ? */ if (p_ptr->probing_state == PROBING) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 32d778448a00..2a6a5a6b4c12 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2,7 +2,7 @@ * net/tipc/socket.c: TIPC socket API * * Copyright (c) 2001-2006, Ericsson AB - * Copyright (c) 2004-2005, Wind River Systems + * Copyright (c) 2004-2006, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -629,6 +629,9 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, return -ENOTCONN; } + if (unlikely(m->msg_name)) + return -EISCONN; + /* * Send each iovec entry using one or more messages * @@ -641,6 +644,8 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, curr_iovlen = m->msg_iovlen; my_msg.msg_iov = &my_iov; my_msg.msg_iovlen = 1; + my_msg.msg_flags = m->msg_flags; + my_msg.msg_name = NULL; bytes_sent = 0; while (curr_iovlen--) { @@ -941,7 +946,7 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, int sz_to_copy; int sz_copied = 0; int needed; - char *crs = m->msg_iov->iov_base; + char __user *crs = m->msg_iov->iov_base; unsigned char *buf_crs; u32 err; int res; @@ -1203,7 +1208,8 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) atomic_inc(&tipc_queue_size); skb_queue_tail(&sock->sk->sk_receive_queue, buf); - wake_up_interruptible(sock->sk->sk_sleep); + if (waitqueue_active(sock->sk->sk_sleep)) + wake_up_interruptible(sock->sk->sk_sleep); return TIPC_OK; } @@ -1218,7 +1224,8 @@ static void wakeupdispatch(struct tipc_port *tport) { struct tipc_sock *tsock = (struct tipc_sock *)tport->usr_handle; - wake_up_interruptible(tsock->sk.sk_sleep); + if (waitqueue_active(tsock->sk.sk_sleep)) + wake_up_interruptible(tsock->sk.sk_sleep); } /** @@ -1496,7 +1503,7 @@ static int setsockopt(struct socket *sock, return -ENOPROTOOPT; if (ol < sizeof(value)) return -EINVAL; - if ((res = get_user(value, (u32 *)ov))) + if ((res = get_user(value, (u32 __user *)ov))) return res; if (down_interruptible(&tsock->sem)) @@ -1541,7 +1548,7 @@ static int setsockopt(struct socket *sock, */ static int getsockopt(struct socket *sock, - int lvl, int opt, char __user *ov, int *ol) + int lvl, int opt, char __user *ov, int __user *ol) { struct tipc_sock *tsock = tipc_sk(sock->sk); int len; diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index c51600ba5f4a..7a918f12a5df 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -155,7 +155,7 @@ void tipc_subscr_report_overlap(struct subscription *sub, sub->seq.upper, found_lower, found_upper); if (!tipc_subscr_overlap(sub, found_lower, found_upper)) return; - if (!must && (sub->filter != TIPC_SUB_PORTS)) + if (!must && !(sub->filter & TIPC_SUB_PORTS)) return; subscr_send_event(sub, found_lower, found_upper, event, port_ref, node); } @@ -176,6 +176,13 @@ static void subscr_timeout(struct subscription *sub) if (subscriber == NULL) return; + /* Validate timeout (in case subscription is being cancelled) */ + + if (sub->timeout == TIPC_WAIT_FOREVER) { + tipc_ref_unlock(subscriber_ref); + return; + } + /* Unlink subscription from name table */ tipc_nametbl_unsubscribe(sub); @@ -199,6 +206,20 @@ static void subscr_timeout(struct subscription *sub) } /** + * subscr_del - delete a subscription within a subscription list + * + * Called with subscriber locked. + */ + +static void subscr_del(struct subscription *sub) +{ + tipc_nametbl_unsubscribe(sub); + list_del(&sub->subscription_list); + kfree(sub); + atomic_dec(&topsrv.subscription_count); +} + +/** * subscr_terminate - terminate communication with a subscriber * * Called with subscriber locked. Routine must temporarily release this lock @@ -227,12 +248,9 @@ static void subscr_terminate(struct subscriber *subscriber) k_cancel_timer(&sub->timer); k_term_timer(&sub->timer); } - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscription_list); - dbg("Term: Removed sub %u,%u,%u from subscriber %x list\n", + dbg("Term: Removing sub %u,%u,%u from subscriber %x list\n", sub->seq.type, sub->seq.lower, sub->seq.upper, subscriber); - kfree(sub); - atomic_dec(&topsrv.subscription_count); + subscr_del(sub); } /* Sever connection to subscriber */ @@ -253,6 +271,49 @@ static void subscr_terminate(struct subscriber *subscriber) } /** + * subscr_cancel - handle subscription cancellation request + * + * Called with subscriber locked. Routine must temporarily release this lock + * to enable the subscription timeout routine to finish without deadlocking; + * the lock is then reclaimed to allow caller to release it upon return. + * + * Note that fields of 's' use subscriber's endianness! + */ + +static void subscr_cancel(struct tipc_subscr *s, + struct subscriber *subscriber) +{ + struct subscription *sub; + struct subscription *sub_temp; + int found = 0; + + /* Find first matching subscription, exit if not found */ + + list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, + subscription_list) { + if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) { + found = 1; + break; + } + } + if (!found) + return; + + /* Cancel subscription timer (if used), then delete subscription */ + + if (sub->timeout != TIPC_WAIT_FOREVER) { + sub->timeout = TIPC_WAIT_FOREVER; + spin_unlock_bh(subscriber->lock); + k_cancel_timer(&sub->timer); + k_term_timer(&sub->timer); + spin_lock_bh(subscriber->lock); + } + dbg("Cancel: removing sub %u,%u,%u from subscriber %x list\n", + sub->seq.type, sub->seq.lower, sub->seq.upper, subscriber); + subscr_del(sub); +} + +/** * subscr_subscribe - create subscription for subscriber * * Called with subscriber locked @@ -263,6 +324,21 @@ static void subscr_subscribe(struct tipc_subscr *s, { struct subscription *sub; + /* Determine/update subscriber's endianness */ + + if (s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE)) + subscriber->swap = 0; + else + subscriber->swap = 1; + + /* Detect & process a subscription cancellation request */ + + if (s->filter & htohl(TIPC_SUB_CANCEL, subscriber->swap)) { + s->filter &= ~htohl(TIPC_SUB_CANCEL, subscriber->swap); + subscr_cancel(s, subscriber); + return; + } + /* Refuse subscription if global limit exceeded */ if (atomic_read(&topsrv.subscription_count) >= tipc_max_subscriptions) { @@ -281,13 +357,6 @@ static void subscr_subscribe(struct tipc_subscr *s, return; } - /* Determine/update subscriber's endianness */ - - if ((s->filter == TIPC_SUB_PORTS) || (s->filter == TIPC_SUB_SERVICE)) - subscriber->swap = 0; - else - subscriber->swap = 1; - /* Initialize subscription object */ memset(sub, 0, sizeof(*sub)); @@ -296,8 +365,8 @@ static void subscr_subscribe(struct tipc_subscr *s, sub->seq.upper = htohl(s->seq.upper, subscriber->swap); sub->timeout = htohl(s->timeout, subscriber->swap); sub->filter = htohl(s->filter, subscriber->swap); - if ((((sub->filter != TIPC_SUB_PORTS) - && (sub->filter != TIPC_SUB_SERVICE))) + if ((!(sub->filter & TIPC_SUB_PORTS) + == !(sub->filter & TIPC_SUB_SERVICE)) || (sub->seq.lower > sub->seq.upper)) { warn("Subscription rejected, illegal request\n"); kfree(sub); diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index d3abb0b7dc62..d401dc8f05ed 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -41,27 +41,28 @@ static inline unsigned int __xfrm_dst_hash(xfrm_address_t *daddr, xfrm_address_t return (h ^ (h >> 16)) & hmask; } -static inline unsigned __xfrm_src_hash(xfrm_address_t *saddr, +static inline unsigned __xfrm_src_hash(xfrm_address_t *daddr, + xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { unsigned int h = family; switch (family) { case AF_INET: - h ^= __xfrm4_addr_hash(saddr); + h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: - h ^= __xfrm6_addr_hash(saddr); + h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; }; return (h ^ (h >> 16)) & hmask; } static inline unsigned int -__xfrm_spi_hash(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family, +__xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, unsigned int hmask) { - unsigned int h = spi ^ proto; + unsigned int h = (__force u32)spi ^ proto; switch (family) { case AF_INET: h ^= __xfrm4_addr_hash(daddr); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index dfc90bb1cf1f..e8198a2c785d 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -46,7 +46,7 @@ EXPORT_SYMBOL(secpath_dup); /* Fetch spi and seq from ipsec header */ -int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) +int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { int offset, offset_seq; @@ -62,7 +62,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; - *spi = htonl(ntohs(*(u16*)(skb->h.raw + 2))); + *spi = htonl(ntohs(*(__be16*)(skb->h.raw + 2))); *seq = 0; return 0; default: @@ -72,8 +72,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) if (!pskb_may_pull(skb, 16)) return -EINVAL; - *spi = *(u32*)(skb->h.raw + offset); - *seq = *(u32*)(skb->h.raw + offset_seq); + *spi = *(__be32*)(skb->h.raw + offset); + *seq = *(__be32*)(skb->h.raw + offset_seq); return 0; } EXPORT_SYMBOL(xfrm_parse_spi); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b6e2e79d7261..7736b23c3f03 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -778,8 +778,9 @@ void xfrm_policy_flush(u8 type) for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; struct hlist_node *entry; - int i; + int i, killed; + killed = 0; again1: hlist_for_each_entry(pol, entry, &xfrm_policy_inexact[dir], bydst) { @@ -790,6 +791,7 @@ void xfrm_policy_flush(u8 type) write_unlock_bh(&xfrm_policy_lock); xfrm_policy_kill(pol); + killed++; write_lock_bh(&xfrm_policy_lock); goto again1; @@ -807,13 +809,14 @@ void xfrm_policy_flush(u8 type) write_unlock_bh(&xfrm_policy_lock); xfrm_policy_kill(pol); + killed++; write_lock_bh(&xfrm_policy_lock); goto again2; } } - xfrm_policy_count[dir] = 0; + xfrm_policy_count[dir] -= killed; } atomic_inc(&flow_cache_genid); write_unlock_bh(&xfrm_policy_lock); @@ -880,30 +883,32 @@ out: } EXPORT_SYMBOL(xfrm_policy_walk); -/* Find policy to apply to this flow. */ - +/* + * Find policy to apply to this flow. + * + * Returns 0 if policy found, else an -errno. + */ static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl, u8 type, u16 family, int dir) { struct xfrm_selector *sel = &pol->selector; - int match; + int match, ret = -ESRCH; if (pol->family != family || pol->type != type) - return 0; + return ret; match = xfrm_selector_match(sel, fl, family); - if (match) { - if (!security_xfrm_policy_lookup(pol, fl->secid, dir)) - return 1; - } + if (match) + ret = security_xfrm_policy_lookup(pol, fl->secid, dir); - return 0; + return ret; } static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, u16 family, u8 dir) { + int err; struct xfrm_policy *pol, *ret; xfrm_address_t *daddr, *saddr; struct hlist_node *entry; @@ -919,7 +924,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, chain = policy_hash_direct(daddr, saddr, family, dir); ret = NULL; hlist_for_each_entry(pol, entry, chain, bydst) { - if (xfrm_policy_match(pol, fl, type, family, dir)) { + err = xfrm_policy_match(pol, fl, type, family, dir); + if (err) { + if (err == -ESRCH) + continue; + else { + ret = ERR_PTR(err); + goto fail; + } + } else { ret = pol; priority = ret->priority; break; @@ -927,36 +940,53 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, } chain = &xfrm_policy_inexact[dir]; hlist_for_each_entry(pol, entry, chain, bydst) { - if (xfrm_policy_match(pol, fl, type, family, dir) && - pol->priority < priority) { + err = xfrm_policy_match(pol, fl, type, family, dir); + if (err) { + if (err == -ESRCH) + continue; + else { + ret = ERR_PTR(err); + goto fail; + } + } else if (pol->priority < priority) { ret = pol; break; } } if (ret) xfrm_pol_hold(ret); +fail: read_unlock_bh(&xfrm_policy_lock); return ret; } -static void xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, +static int xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, void **objp, atomic_t **obj_refp) { struct xfrm_policy *pol; + int err = 0; #ifdef CONFIG_XFRM_SUB_POLICY pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_SUB, fl, family, dir); - if (pol) + if (IS_ERR(pol)) { + err = PTR_ERR(pol); + pol = NULL; + } + if (pol || err) goto end; #endif pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, fl, family, dir); - + if (IS_ERR(pol)) { + err = PTR_ERR(pol); + pol = NULL; + } #ifdef CONFIG_XFRM_SUB_POLICY end: #endif if ((*objp = (void *) pol) != NULL) *obj_refp = &pol->refcnt; + return err; } static inline int policy_to_flow_dir(int dir) @@ -986,12 +1016,16 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc sk->sk_family); int err = 0; - if (match) - err = security_xfrm_policy_lookup(pol, fl->secid, policy_to_flow_dir(dir)); - - if (match && !err) - xfrm_pol_hold(pol); - else + if (match) { + err = security_xfrm_policy_lookup(pol, fl->secid, + policy_to_flow_dir(dir)); + if (!err) + xfrm_pol_hold(pol); + else if (err == -ESRCH) + pol = NULL; + else + pol = ERR_PTR(err); + } else pol = NULL; } read_unlock_bh(&xfrm_policy_lock); @@ -1283,8 +1317,11 @@ restart: pol_dead = 0; xfrm_nr = 0; - if (sk && sk->sk_policy[1]) + if (sk && sk->sk_policy[1]) { policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); + if (IS_ERR(policy)) + return PTR_ERR(policy); + } if (!policy) { /* To accelerate a bit... */ @@ -1294,6 +1331,8 @@ restart: policy = flow_cache_lookup(fl, dst_orig->ops->family, dir, xfrm_policy_lookup); + if (IS_ERR(policy)) + return PTR_ERR(policy); } if (!policy) @@ -1340,6 +1379,10 @@ restart: fl, family, XFRM_POLICY_OUT); if (pols[1]) { + if (IS_ERR(pols[1])) { + err = PTR_ERR(pols[1]); + goto error; + } if (pols[1]->action == XFRM_POLICY_BLOCK) { err = -EPERM; goto error; @@ -1571,13 +1614,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } pol = NULL; - if (sk && sk->sk_policy[dir]) + if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl); + if (IS_ERR(pol)) + return 0; + } if (!pol) pol = flow_cache_lookup(&fl, family, fl_dir, xfrm_policy_lookup); + if (IS_ERR(pol)) + return 0; + if (!pol) { if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); @@ -1596,6 +1645,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, &fl, family, XFRM_POLICY_IN); if (pols[1]) { + if (IS_ERR(pols[1])) + return 0; pols[1]->curlft.use_time = (unsigned long)xtime.tv_sec; npols ++; } @@ -1703,7 +1754,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok((struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0); + return !xfrm_bundle_ok(NULL, (struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) @@ -1825,7 +1876,8 @@ EXPORT_SYMBOL(xfrm_init_pmtu); * still valid. */ -int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family, int strict) +int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, + struct flowi *fl, int family, int strict) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; @@ -1842,7 +1894,7 @@ int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family, int str if (fl && !xfrm_selector_match(&dst->xfrm->sel, fl, family)) return 0; - if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm)) + if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm, pol)) return 0; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9f63edd39346..84bbf8474f3e 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -63,14 +63,15 @@ static inline unsigned int xfrm_dst_hash(xfrm_address_t *daddr, return __xfrm_dst_hash(daddr, saddr, reqid, family, xfrm_state_hmask); } -static inline unsigned int xfrm_src_hash(xfrm_address_t *addr, +static inline unsigned int xfrm_src_hash(xfrm_address_t *daddr, + xfrm_address_t *saddr, unsigned short family) { - return __xfrm_src_hash(addr, family, xfrm_state_hmask); + return __xfrm_src_hash(daddr, saddr, family, xfrm_state_hmask); } static inline unsigned int -xfrm_spi_hash(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family) +xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { return __xfrm_spi_hash(daddr, spi, proto, family, xfrm_state_hmask); } @@ -92,13 +93,17 @@ static void xfrm_hash_transfer(struct hlist_head *list, nhashmask); hlist_add_head(&x->bydst, ndsttable+h); - h = __xfrm_src_hash(&x->props.saddr, x->props.family, + h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, + x->props.family, nhashmask); hlist_add_head(&x->bysrc, nsrctable+h); - h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, - x->props.family, nhashmask); - hlist_add_head(&x->byspi, nspitable+h); + if (x->id.spi) { + h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, + x->id.proto, x->props.family, + nhashmask); + hlist_add_head(&x->byspi, nspitable+h); + } } } @@ -421,7 +426,7 @@ xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, return 0; } -static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family) +static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { unsigned int h = xfrm_spi_hash(daddr, spi, proto, family); struct xfrm_state *x; @@ -455,7 +460,7 @@ static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 static struct xfrm_state *__xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) { - unsigned int h = xfrm_src_hash(saddr, family); + unsigned int h = xfrm_src_hash(daddr, saddr, family); struct xfrm_state *x; struct hlist_node *entry; @@ -584,7 +589,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, if (km_query(x, tmpl, pol) == 0) { x->km.state = XFRM_STATE_ACQ; hlist_add_head(&x->bydst, xfrm_state_bydst+h); - h = xfrm_src_hash(saddr, family); + h = xfrm_src_hash(daddr, saddr, family); hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); if (x->id.spi) { h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, family); @@ -609,6 +614,14 @@ out: return x; } +static void xfrm_hash_grow_check(int have_hash_collision) +{ + if (have_hash_collision && + (xfrm_state_hmask + 1) < xfrm_state_hashmax && + xfrm_state_num > xfrm_state_hmask) + schedule_work(&xfrm_hash_work); +} + static void __xfrm_state_insert(struct xfrm_state *x) { unsigned int h; @@ -619,10 +632,10 @@ static void __xfrm_state_insert(struct xfrm_state *x) x->props.reqid, x->props.family); hlist_add_head(&x->bydst, xfrm_state_bydst+h); - h = xfrm_src_hash(&x->props.saddr, x->props.family); + h = xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family); hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); - if (xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY)) { + if (x->id.spi) { h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family); @@ -637,10 +650,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) xfrm_state_num++; - if (x->bydst.next != NULL && - (xfrm_state_hmask + 1) < xfrm_state_hashmax && - xfrm_state_num > xfrm_state_hmask) - schedule_work(&xfrm_hash_work); + xfrm_hash_grow_check(x->bydst.next != NULL); } /* xfrm_state_lock is held */ @@ -745,9 +755,13 @@ static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 re x->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; add_timer(&x->timer); hlist_add_head(&x->bydst, xfrm_state_bydst+h); - h = xfrm_src_hash(saddr, family); + h = xfrm_src_hash(daddr, saddr, family); hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); wake_up(&km_waitq); + + xfrm_state_num++; + + xfrm_hash_grow_check(x->bydst.next != NULL); } return x; @@ -916,7 +930,7 @@ err: EXPORT_SYMBOL(xfrm_state_check); struct xfrm_state * -xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, +xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_state *x; @@ -1040,7 +1054,7 @@ u32 xfrm_get_acqseq(void) EXPORT_SYMBOL(xfrm_get_acqseq); void -xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi) +xfrm_alloc_spi(struct xfrm_state *x, __be32 minspi, __be32 maxspi) { unsigned int h; struct xfrm_state *x0; @@ -1057,10 +1071,10 @@ xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi) x->id.spi = minspi; } else { u32 spi = 0; - minspi = ntohl(minspi); - maxspi = ntohl(maxspi); - for (h=0; h<maxspi-minspi+1; h++) { - spi = minspi + net_random()%(maxspi-minspi+1); + u32 low = ntohl(minspi); + u32 high = ntohl(maxspi); + for (h=0; h<high-low+1; h++) { + spi = low + net_random()%(high-low+1); x0 = xfrm_state_lookup(&x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); @@ -1180,11 +1194,10 @@ static void xfrm_replay_timer_handler(unsigned long data) spin_unlock(&x->lock); } -int xfrm_replay_check(struct xfrm_state *x, u32 seq) +int xfrm_replay_check(struct xfrm_state *x, __be32 net_seq) { u32 diff; - - seq = ntohl(seq); + u32 seq = ntohl(net_seq); if (unlikely(seq == 0)) return -EINVAL; @@ -1206,11 +1219,10 @@ int xfrm_replay_check(struct xfrm_state *x, u32 seq) } EXPORT_SYMBOL(xfrm_replay_check); -void xfrm_replay_advance(struct xfrm_state *x, u32 seq) +void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) { u32 diff; - - seq = ntohl(seq); + u32 seq = ntohl(net_seq); if (seq > x->replay.seq) { diff = seq - x->replay.seq; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c59a78d2923a..2b2e59d8ffbc 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -211,6 +211,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, case XFRM_MODE_TRANSPORT: case XFRM_MODE_TUNNEL: case XFRM_MODE_ROUTEOPTIMIZATION: + case XFRM_MODE_BEET: break; default: @@ -1991,15 +1992,6 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, xp->type = XFRM_POLICY_TYPE_MAIN; copy_templates(xp, ut, nr); - if (!xp->security) { - int err = security_xfrm_sock_policy_alloc(xp, sk); - if (err) { - kfree(xp); - *dir = err; - return NULL; - } - } - *dir = p->dir; return xp; |