diff options
Diffstat (limited to 'net/ipv4')
66 files changed, 2089 insertions, 2636 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index d183262943d..20f1cb5c8ab 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -262,8 +262,8 @@ config ARPD bool "IP: ARP daemon support" ---help--- The kernel maintains an internal cache which maps IP addresses to - hardware addresses on the local network, so that Ethernet/Token Ring/ - etc. frames are sent to the proper address on the physical networking + hardware addresses on the local network, so that Ethernet + frames are sent to the proper address on the physical networking layer. Normally, kernel uses the ARP protocol to resolve these mappings. @@ -312,7 +312,7 @@ config SYN_COOKIES config INET_AH tristate "IP: AH transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_HMAC select CRYPTO_MD5 @@ -324,7 +324,7 @@ config INET_AH config INET_ESP tristate "IP: ESP transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_AUTHENC select CRYPTO_HMAC diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f7b5670744f..c8f7aee587d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -65,6 +65,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv4: " fmt + #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> @@ -89,7 +91,6 @@ #include <linux/slab.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/inet.h> #include <linux/igmp.h> @@ -349,7 +350,7 @@ lookup_protocol: err = 0; sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) - sk->sk_reuse = 1; + sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -381,6 +382,7 @@ lookup_protocol: inet->mc_all = 1; inet->mc_index = 0; inet->mc_list = NULL; + inet->rcv_tos = 0; sk_refcnt_debug_inc(sk); @@ -539,7 +541,7 @@ out: } EXPORT_SYMBOL(inet_bind); -int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, +int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; @@ -1084,13 +1086,11 @@ out: return; out_permanent: - printk(KERN_ERR "Attempt to override permanent protocol %d.\n", - protocol); + pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: - printk(KERN_ERR - "Ignoring attempt to register invalid socket type %d.\n", + pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } @@ -1099,8 +1099,7 @@ EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { - printk(KERN_ERR - "Attempt to unregister permanent protocol %d.\n", + pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw_lock); @@ -1149,8 +1148,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; if (sysctl_ip_dynaddr > 1) { - printk(KERN_INFO "%s(): shifting inet->saddr from %pI4 to %pI4\n", - __func__, &old_saddr, &new_saddr); + pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", + __func__, &old_saddr, &new_saddr); } inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; @@ -1679,14 +1678,14 @@ static int __init inet_init(void) */ if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) - printk(KERN_CRIT "inet_init: Cannot add ICMP protocol\n"); + pr_crit("%s: Cannot add ICMP protocol\n", __func__); if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) - printk(KERN_CRIT "inet_init: Cannot add UDP protocol\n"); + pr_crit("%s: Cannot add UDP protocol\n", __func__); if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) - printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n"); + pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) - printk(KERN_CRIT "inet_init: Cannot add IGMP protocol\n"); + pr_crit("%s: Cannot add IGMP protocol\n", __func__); #endif /* Register the socket-side information for inet_create. */ @@ -1733,14 +1732,14 @@ static int __init inet_init(void) */ #if defined(CONFIG_IP_MROUTE) if (ip_mr_init()) - printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n"); + pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif /* * Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) - printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); + pr_crit("%s: Cannot init ipv4 mibs\n", __func__); ipv4_proc_init(); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 36d14406261..e8f2617ecd4 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) "IPsec: " fmt + #include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> @@ -75,7 +77,7 @@ static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr) { - unsigned char * optptr = (unsigned char*)(iph+1); + unsigned char *optptr = (unsigned char *)(iph+1); int l = iph->ihl*4 - sizeof(struct iphdr); int optlen; @@ -404,8 +406,8 @@ static void ah4_err(struct sk_buff *skb, u32 info) ah->spi, IPPROTO_AH, AF_INET); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n", - ntohl(ah->spi), ntohl(iph->daddr)); + pr_debug("pmtu discovery on SA AH/%08x/%08x\n", + ntohl(ah->spi), ntohl(iph->daddr)); xfrm_state_put(x); } @@ -445,9 +447,10 @@ static int ah_init_state(struct xfrm_state *x) if (aalg_desc->uinfo.auth.icv_fullbits/8 != crypto_ahash_digestsize(ahash)) { - printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_ahash_digestsize(ahash), - aalg_desc->uinfo.auth.icv_fullbits/8); + pr_info("%s: %s digestsize %u != %hu\n", + __func__, x->aalg->alg_name, + crypto_ahash_digestsize(ahash), + aalg_desc->uinfo.auth.icv_fullbits / 8); goto error; } @@ -510,11 +513,11 @@ static const struct net_protocol ah4_protocol = { static int __init ah4_init(void) { if (xfrm_register_type(&ah_type, AF_INET) < 0) { - printk(KERN_INFO "ip ah init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) { - printk(KERN_INFO "ip ah init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah_type, AF_INET); return -EAGAIN; } @@ -524,9 +527,9 @@ static int __init ah4_init(void) static void __exit ah4_fini(void) { if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0) - printk(KERN_INFO "ip ah close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah_type, AF_INET) < 0) - printk(KERN_INFO "ip ah close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(ah4_init); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 63e49890ad3..cda37be02f8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -73,6 +73,8 @@ * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> @@ -89,7 +91,6 @@ #include <linux/etherdevice.h> #include <linux/fddidevice.h> #include <linux/if_arp.h> -#include <linux/trdevice.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -113,7 +114,6 @@ #include <net/ax25.h> #include <net/netrom.h> -#include <asm/system.h> #include <linux/uaccess.h> #include <linux/netfilter_arp.h> @@ -194,9 +194,6 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) case ARPHRD_IEEE802: ip_eth_mc_map(addr, haddr); return 0; - case ARPHRD_IEEE802_TR: - ip_tr_mc_map(addr, haddr); - return 0; case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; @@ -365,8 +362,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) probes -= neigh->parms->ucast_probes; if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) - printk(KERN_DEBUG - "trying to ucast probe in NUD_INVALID\n"); + pr_debug("trying to ucast probe in NUD_INVALID\n"); dst_ha = neigh->ha; read_lock_bh(&neigh->lock); } else { @@ -453,7 +449,7 @@ static int arp_set_predefined(int addr_hint, unsigned char *haddr, { switch (addr_hint) { case RTN_LOCAL: - printk(KERN_DEBUG "ARP: arp called for own IP address\n"); + pr_debug("arp called for own IP address\n"); memcpy(haddr, dev->dev_addr, dev->addr_len); return 1; case RTN_MULTICAST: @@ -474,7 +470,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) struct neighbour *n; if (!skb_dst(skb)) { - printk(KERN_DEBUG "arp_find is called with dst==NULL\n"); + pr_debug("arp_find is called with dst==NULL\n"); kfree_skb(skb); return 1; } @@ -649,12 +645,6 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp->ar_pro = htons(ETH_P_IP); break; #endif -#if IS_ENABLED(CONFIG_TR) - case ARPHRD_IEEE802_TR: - arp->ar_hrd = htons(ARPHRD_IEEE802); - arp->ar_pro = htons(ETH_P_IP); - break; -#endif } arp->ar_hln = dev->addr_len; @@ -752,11 +742,10 @@ static int arp_process(struct sk_buff *skb) goto out; break; case ARPHRD_ETHER: - case ARPHRD_IEEE802_TR: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* - * ETHERNET, Token Ring and Fibre Channel (which are IEEE 802 + * ETHERNET, and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that @@ -889,7 +878,7 @@ static int arp_process(struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); - if (IPV4_DEVCONF_ALL(dev_net(dev), ARP_ACCEPT)) { + if (IN_DEV_ARP_ACCEPT(in_dev)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) @@ -1060,7 +1049,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { - unsigned state = NUD_STALE; + unsigned int state = NUD_STALE; if (r->arp_flags & ATF_PERM) state = NUD_PERMANENT; err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? @@ -1072,7 +1061,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, return err; } -static unsigned arp_state_to_flags(struct neighbour *neigh) +static unsigned int arp_state_to_flags(struct neighbour *neigh) { if (neigh->nud_state&NUD_PERMANENT) return ATF_PERM | ATF_COM; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 86f3b885b4f..c48adc565e9 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1857,11 +1857,6 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } -static void opt_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_options_rcu, rcu)); -} - /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket @@ -1938,7 +1933,7 @@ int cipso_v4_sock_setattr(struct sock *sk, } rcu_assign_pointer(sk_inet->inet_opt, opt); if (old) - call_rcu(&old->rcu, opt_kfree_rcu); + kfree_rcu(old, rcu); return 0; @@ -2005,7 +2000,7 @@ int cipso_v4_req_setattr(struct request_sock *req, req_inet = inet_rsk(req); opt = xchg(&req_inet->opt, opt); if (opt) - call_rcu(&opt->rcu, opt_kfree_rcu); + kfree_rcu(opt, rcu); return 0; @@ -2075,7 +2070,7 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) * remove the entire option struct */ *opt_ptr = NULL; hdr_delta = opt->opt.optlen; - call_rcu(&opt->rcu, opt_kfree_rcu); + kfree_rcu(opt, rcu); } return hdr_delta; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e41c40f48cf..10e15a144e9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -27,7 +27,6 @@ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> @@ -218,8 +217,7 @@ void in_dev_finish_destroy(struct in_device *idev) WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG - printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n", - idev, dev ? dev->name : "NIL"); + pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif dev_put(dev); if (!idev->dead) @@ -1079,6 +1077,7 @@ __be32 inet_confirm_addr(struct in_device *in_dev, return addr; } +EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier @@ -1125,7 +1124,7 @@ skip: } } -static inline bool inetdev_valid_mtu(unsigned mtu) +static inline bool inetdev_valid_mtu(unsigned int mtu) { return mtu >= 68; } @@ -1174,7 +1173,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: - printk(KERN_DEBUG "inetdev_event: bug\n"); + pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: @@ -1266,17 +1265,15 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - if (ifa->ifa_address) - NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address); - - if (ifa->ifa_local) - NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local); - - if (ifa->ifa_broadcast) - NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); - - if (ifa->ifa_label[0]) - NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); + if ((ifa->ifa_address && + nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || + (ifa->ifa_local && + nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) || + (ifa->ifa_broadcast && + nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || + (ifa->ifa_label[0] && + nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1587,7 +1584,6 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write, static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; - char *dev_name; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", @@ -1629,16 +1625,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, { int i; struct devinet_sysctl_table *t; - -#define DEVINET_CTL_PATH_DEV 3 - - struct ctl_path devinet_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "conf", }, - { /* to be set */ }, - { }, - }; + char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL); if (!t) @@ -1650,27 +1637,15 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, t->devinet_vars[i].extra2 = net; } - /* - * Make a copy of dev_name, because '.procname' is regarded as const - * by sysctl and we wouldn't want anyone to change it under our feet - * (see SIOCSIFNAME). - */ - t->dev_name = kstrdup(dev_name, GFP_KERNEL); - if (!t->dev_name) - goto free; - - devinet_ctl_path[DEVINET_CTL_PATH_DEV].procname = t->dev_name; + snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); - t->sysctl_header = register_net_sysctl_table(net, devinet_ctl_path, - t->devinet_vars); + t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) - goto free_procname; + goto free; p->sysctl = t; return 0; -free_procname: - kfree(t->dev_name); free: kfree(t); out: @@ -1686,7 +1661,6 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); - kfree(t->dev_name); kfree(t); } @@ -1716,12 +1690,6 @@ static struct ctl_table ctl_forward_entry[] = { }, { }, }; - -static __net_initdata struct ctl_path net_ipv4_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; #endif static __net_init int devinet_init_net(struct net *net) @@ -1767,7 +1735,7 @@ static __net_init int devinet_init_net(struct net *net) goto err_reg_dflt; err = -ENOMEM; - forw_hdr = register_net_sysctl_table(net, net_ipv4_path, tbl); + forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); if (forw_hdr == NULL) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index a5b413416da..cb982a61536 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) "IPsec: " fmt + #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> @@ -457,28 +459,22 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4); u32 align = max_t(u32, blksize, esp->padlen); - u32 rem; - - mtu -= x->props.header_len + crypto_aead_authsize(esp->aead); - rem = mtu & (align - 1); - mtu &= ~(align - 1); + unsigned int net_adj; switch (x->props.mode) { - case XFRM_MODE_TUNNEL: - break; - default: case XFRM_MODE_TRANSPORT: - /* The worst case */ - mtu -= blksize - 4; - mtu += min_t(u32, blksize - 4, rem); - break; case XFRM_MODE_BEET: - /* The worst case. */ - mtu += min_t(u32, IPV4_BEET_PHMAXLEN, rem); + net_adj = sizeof(struct iphdr); + break; + case XFRM_MODE_TUNNEL: + net_adj = 0; break; + default: + BUG(); } - return mtu - 2; + return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - + net_adj) & ~(align - 1)) + (net_adj - 2); } static void esp4_err(struct sk_buff *skb, u32 info) @@ -706,11 +702,11 @@ static const struct net_protocol esp4_protocol = { static int __init esp4_init(void) { if (xfrm_register_type(&esp_type, AF_INET) < 0) { - printk(KERN_INFO "ip esp init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) { - printk(KERN_INFO "ip esp init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp_type, AF_INET); return -EAGAIN; } @@ -720,9 +716,9 @@ static int __init esp4_init(void) static void __exit esp4_fini(void) { if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0) - printk(KERN_INFO "ip esp close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp_type, AF_INET) < 0) - printk(KERN_INFO "ip esp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(esp4_init); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 92fc5f69f5d..3854411fa37 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -15,7 +15,6 @@ #include <linux/module.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> @@ -137,13 +136,13 @@ static void fib_flush(struct net *net) * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ -static inline unsigned __inet_dev_addr_type(struct net *net, - const struct net_device *dev, - __be32 addr) +static inline unsigned int __inet_dev_addr_type(struct net *net, + const struct net_device *dev, + __be32 addr) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; - unsigned ret = RTN_BROADCAST; + unsigned int ret = RTN_BROADCAST; struct fib_table *local_table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) @@ -695,7 +694,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (prim == NULL) { - printk(KERN_WARNING "fib_add_ifaddr: bug: prim == NULL\n"); + pr_warn("%s: bug: prim == NULL\n", __func__); return; } } @@ -741,7 +740,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 - unsigned ok = 0; + unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ @@ -749,11 +748,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (prim == NULL) { - printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n"); + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { - printk(KERN_WARNING "fib_del_ifaddr: bug: iprim != prim\n"); + pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 799fc790b3c..2d043f71ef7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -221,15 +221,15 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->src_len = rule4->src_len; frh->tos = rule4->tos; - if (rule4->dst_len) - NLA_PUT_BE32(skb, FRA_DST, rule4->dst); - - if (rule4->src_len) - NLA_PUT_BE32(skb, FRA_SRC, rule4->src); - + if ((rule4->dst_len && + nla_put_be32(skb, FRA_DST, rule4->dst)) || + (rule4->src_len && + nla_put_be32(skb, FRA_SRC, rule4->src))) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (rule4->tclassid) - NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid); + if (rule4->tclassid && + nla_put_u32(skb, FRA_FLOW, rule4->tclassid)) + goto nla_put_failure; #endif return 0; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 80106d89d54..e5b7182fa09 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -14,7 +14,6 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> @@ -146,6 +145,12 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + change_nexthops(fi) { + if (nexthop_nh->nh_dev) + dev_put(nexthop_nh->nh_dev); + } endfor_nexthops(fi); + + release_net(fi->fib_net); if (fi->fib_metrics != (u32 *) dst_default_metrics) kfree(fi->fib_metrics); kfree(fi); @@ -154,16 +159,10 @@ static void free_fib_info_rcu(struct rcu_head *head) void free_fib_info(struct fib_info *fi) { if (fi->fib_dead == 0) { - pr_warning("Freeing alive fib_info %p\n", fi); + pr_warn("Freeing alive fib_info %p\n", fi); return; } - change_nexthops(fi) { - if (nexthop_nh->nh_dev) - dev_put(nexthop_nh->nh_dev); - nexthop_nh->nh_dev = NULL; - } endfor_nexthops(fi); fib_info_cnt--; - release_net(fi->fib_net); call_rcu(&fi->rcu, free_fib_info_rcu); } @@ -932,33 +931,36 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; - NLA_PUT_U32(skb, RTA_TABLE, tb_id); + if (nla_put_u32(skb, RTA_TABLE, tb_id)) + goto nla_put_failure; rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; - if (rtm->rtm_dst_len) - NLA_PUT_BE32(skb, RTA_DST, dst); - - if (fi->fib_priority) - NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority); - + if (rtm->rtm_dst_len && + nla_put_be32(skb, RTA_DST, dst)) + goto nla_put_failure; + if (fi->fib_priority && + nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) + goto nla_put_failure; if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) goto nla_put_failure; - if (fi->fib_prefsrc) - NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc); - + if (fi->fib_prefsrc && + nla_put_be32(skb, RTA_PREFSRC, fi->fib_prefsrc)) + goto nla_put_failure; if (fi->fib_nhs == 1) { - if (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); + if (fi->fib_nh->nh_gw && + nla_put_be32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) + goto nla_put_failure; + if (fi->fib_nh->nh_oif && + nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (fi->fib_nh[0].nh_tclassid) - NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); + if (fi->fib_nh[0].nh_tclassid && + nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) + goto nla_put_failure; #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -979,11 +981,13 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtnh->rtnh_hops = nh->nh_weight - 1; rtnh->rtnh_ifindex = nh->nh_oif; - if (nh->nh_gw) - NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw); + if (nh->nh_gw && + nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid) - NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); + if (nh->nh_tclassid && + nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) + goto nla_put_failure; #endif /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2b555a5521e..30b88d7b4bd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -51,7 +51,6 @@ #define VERSION "0.409" #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> @@ -1170,9 +1169,8 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) } if (tp && tp->pos + tp->bits > 32) - pr_warning("fib_trie" - " tp=%p pos=%d, bits=%d, key=%0x plen=%d\n", - tp, tp->pos, tp->bits, key, plen); + pr_warn("fib_trie tp=%p pos=%d, bits=%d, key=%0x plen=%d\n", + tp, tp->pos, tp->bits, key, plen); /* Rebalance the trie */ @@ -1372,6 +1370,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; + if (fi->fib_dead) + continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index 8cb1ebb7cd7..42a491055c7 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -10,6 +10,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/kmod.h> @@ -118,10 +120,10 @@ static const struct net_protocol net_gre_protocol = { static int __init gre_init(void) { - pr_info("GRE over IPv4 demultiplexor driver"); + pr_info("GRE over IPv4 demultiplexor driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { - pr_err("gre: can't add protocol\n"); + pr_err("can't add protocol\n"); return -EAGAIN; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ab188ae12fd..c75efbdc71c 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -62,6 +62,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/jiffies.h> @@ -89,7 +91,6 @@ #include <linux/errno.h> #include <linux/timer.h> #include <linux/init.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <net/checksum.h> #include <net/xfrm.h> @@ -670,7 +671,7 @@ static void icmp_unreach(struct sk_buff *skb) break; case ICMP_FRAG_NEEDED: if (ipv4_config.no_pmtu_disc) { - LIMIT_NETDEBUG(KERN_INFO "ICMP: %pI4: fragmentation needed and DF set.\n", + LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); } else { info = ip_rt_frag_needed(net, iph, @@ -681,7 +682,7 @@ static void icmp_unreach(struct sk_buff *skb) } break; case ICMP_SR_FAILED: - LIMIT_NETDEBUG(KERN_INFO "ICMP: %pI4: Source Route Failed.\n", + LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"), &iph->daddr); break; default: @@ -712,14 +713,10 @@ static void icmp_unreach(struct sk_buff *skb) if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { - if (net_ratelimit()) - printk(KERN_WARNING "%pI4 sent an invalid ICMP " - "type %u, code %u " - "error to a broadcast: %pI4 on %s\n", - &ip_hdr(skb)->saddr, - icmph->type, icmph->code, - &iph->daddr, - skb->dev->name); + net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", + &ip_hdr(skb)->saddr, + icmph->type, icmph->code, + &iph->daddr, skb->dev->name); goto out; } @@ -908,8 +905,7 @@ out_err: static void icmp_address(struct sk_buff *skb) { #if 0 - if (net_ratelimit()) - printk(KERN_DEBUG "a guy asks for address mask. Who is it?\n"); + net_dbg_ratelimited("a guy asks for address mask. Who is it?\n"); #endif } @@ -945,10 +941,10 @@ static void icmp_address_reply(struct sk_buff *skb) inet_ifa_match(ip_hdr(skb)->saddr, ifa)) break; } - if (!ifa && net_ratelimit()) { - printk(KERN_INFO "Wrong address mask %pI4 from %s/%pI4\n", - mp, dev->name, &ip_hdr(skb)->saddr); - } + if (!ifa) + net_info_ratelimited("Wrong address mask %pI4 from %s/%pI4\n", + mp, + dev->name, &ip_hdr(skb)->saddr); } } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 450e5d21ed2..6699f23e6f5 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -73,7 +73,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> @@ -345,10 +344,10 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(pip, &rt->dst, NULL); - ((u8*)&pip[1])[0] = IPOPT_RA; - ((u8*)&pip[1])[1] = 4; - ((u8*)&pip[1])[2] = 0; - ((u8*)&pip[1])[3] = 0; + ((u8 *)&pip[1])[0] = IPOPT_RA; + ((u8 *)&pip[1])[1] = 4; + ((u8 *)&pip[1])[2] = 0; + ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); @@ -689,10 +688,10 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(iph, &rt->dst, NULL); - ((u8*)&iph[1])[0] = IPOPT_RA; - ((u8*)&iph[1])[1] = 4; - ((u8*)&iph[1])[2] = 0; - ((u8*)&iph[1])[3] = 0; + ((u8 *)&iph[1])[0] = IPOPT_RA; + ((u8 *)&iph[1])[1] = 4; + ((u8 *)&iph[1])[2] = 0; + ((u8 *)&iph[1])[3] = 0; ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); ih->type = type; @@ -775,7 +774,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) - continue; + break; if (srcs[i] == psf->sf_inaddr) { scount++; break; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 19d66cefd7d..f9ee7417f6a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -42,7 +42,8 @@ EXPORT_SYMBOL(sysctl_local_reserved_ports); void inet_get_local_port_range(int *low, int *high) { - unsigned seq; + unsigned int seq; + do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -53,7 +54,7 @@ void inet_get_local_port_range(int *low, int *high) EXPORT_SYMBOL(inet_get_local_port_range); int inet_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb) + const struct inet_bind_bucket *tb, bool relax) { struct sock *sk2; struct hlist_node *node; @@ -79,6 +80,14 @@ int inet_csk_bind_conflict(const struct sock *sk, sk2_rcv_saddr == sk_rcv_saddr(sk)) break; } + if (!relax && reuse && sk2->sk_reuse && + sk2->sk_state != TCP_LISTEN) { + const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); + + if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || + sk2_rcv_saddr == sk_rcv_saddr(sk)) + break; + } } } return node != NULL; @@ -122,12 +131,13 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && + !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { snum = smallest_rover; goto tb_found; } } - if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { snum = rover; goto tb_found; } @@ -172,18 +182,22 @@ have_snum: goto tb_not_found; tb_found: if (!hlist_empty(&tb->owners)) { + if (sk->sk_reuse == SK_FORCE_REUSE) + goto success; + if (tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN && smallest_size == -1) { goto success; } else { ret = 1; - if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; } + goto fail_unlock; } } @@ -363,7 +377,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, - sk->sk_protocol, inet_sk_flowi_flags(sk), + sk->sk_protocol, + inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS, (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); security_req_classify_flow(req, flowi4_to_flowi(fl4)); @@ -514,7 +529,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. - * If synack was not acknowledged for 3 seconds, it means + * If synack was not acknowledged for 1 second, it means * one of the following things: synack was lost, ack was lost, * rtt is high or nobody planned to ack (i.e. synflood). * When server is a bit loaded, queue is populated with old @@ -555,8 +570,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, syn_ack_recalc(req, thresh, max_retries, queue->rskq_defer_accept, &expire, &resend); - if (req->rsk_ops->syn_ack_timeout) - req->rsk_ops->syn_ack_timeout(parent, req); + req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index fcf281819cd..46d1e7199a8 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -141,7 +141,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto rtattr_failure; if (icsk == NULL) { - r->idiag_rqueue = r->idiag_wqueue = 0; + handler->idiag_get_info(sk, r, NULL); goto out; } @@ -960,9 +960,12 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; } - - return netlink_dump_start(sock_diag_nlsk, skb, nlh, - inet_diag_dump_compat, NULL, 0); + { + struct netlink_dump_control c = { + .dump = inet_diag_dump_compat, + }; + return netlink_dump_start(sock_diag_nlsk, skb, nlh, &c); + } } return inet_diag_get_exact_compat(skb, nlh); @@ -985,20 +988,23 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; } - - return netlink_dump_start(sock_diag_nlsk, skb, h, - inet_diag_dump, NULL, 0); + { + struct netlink_dump_control c = { + .dump = inet_diag_dump, + }; + return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + } } return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h)); } -static struct sock_diag_handler inet_diag_handler = { +static const struct sock_diag_handler inet_diag_handler = { .family = AF_INET, .dump = inet_diag_handler_dump, }; -static struct sock_diag_handler inet6_diag_handler = { +static const struct sock_diag_handler inet6_diag_handler = { .family = AF_INET6, .dump = inet_diag_handler_dump, }; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 984ec656b03..7880af97020 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -217,7 +217,7 @@ begin: } EXPORT_SYMBOL_GPL(__inet_lookup_listener); -struct sock * __inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 89168c6351f..2784db3155f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -89,8 +89,8 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { - printk(KERN_DEBUG "%s timewait_sock %p refcnt=%d\n", - tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); + pr_debug("%s timewait_sock %p refcnt=%d\n", + tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); } #endif while (refcnt) { @@ -263,7 +263,7 @@ rescan: void inet_twdr_hangman(unsigned long data) { struct inet_timewait_death_row *twdr; - int unsigned need_timer; + unsigned int need_timer; twdr = (struct inet_timewait_death_row *)data; spin_lock(&twdr->death_lock); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 29a07b6c716..e5c44fc586a 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -41,7 +41,7 @@ static int ip_forward_finish(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); @@ -55,7 +55,7 @@ int ip_forward(struct sk_buff *skb) { struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1f23a57aa9e..9dbd3dd6022 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -20,6 +20,8 @@ * Patrick McHardy : LRU queue of frag heads for evictor. */ +#define pr_fmt(fmt) "IPv4: " fmt + #include <linux/compiler.h> #include <linux/module.h> #include <linux/types.h> @@ -146,17 +148,17 @@ static unsigned int ip4_hashfn(struct inet_frag_queue *q) return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); } -static int ip4_frag_match(struct inet_frag_queue *q, void *a) +static bool ip4_frag_match(struct inet_frag_queue *q, void *a) { struct ipq *qp; struct ip4_create_arg *arg = a; qp = container_of(q, struct ipq, q); return qp->id == arg->iph->id && - qp->saddr == arg->iph->saddr && - qp->daddr == arg->iph->daddr && - qp->protocol == arg->iph->protocol && - qp->user == arg->user; + qp->saddr == arg->iph->saddr && + qp->daddr == arg->iph->daddr && + qp->protocol == arg->iph->protocol && + qp->user == arg->user; } /* Memory Tracking Functions. */ @@ -299,7 +301,7 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) return container_of(q, struct ipq, q); out_nomem: - LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n"); + LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n")); return NULL; } @@ -543,6 +545,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; + int sum_truesize; u8 ecn; ipq_kill(qp); @@ -567,7 +570,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, skb_morph(head, qp->q.fragments); head->next = qp->q.fragments->next; - kfree_skb(qp->q.fragments); + consume_skb(qp->q.fragments); qp->q.fragments = head; } @@ -609,19 +612,32 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, atomic_add(clone->truesize, &qp->q.net->mem); } - skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; + + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; } - atomic_sub(head->truesize, &qp->q.net->mem); + atomic_sub(sum_truesize, &qp->q.net->mem); head->next = NULL; head->dev = dev; @@ -637,14 +653,12 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, return 0; out_nomem: - LIMIT_NETDEBUG(KERN_ERR "IP: queue_glue: no memory for gluing " - "queue %p\n", qp); + LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"), + qp); err = -ENOMEM; goto out_fail; out_oversize: - if (net_ratelimit()) - printk(KERN_INFO "Oversized IP packet from %pI4.\n", - &qp->saddr); + net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr); out_fail: IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; @@ -781,7 +795,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[2].data = &net->ipv4.frags.timeout; } - hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); + hdr = register_net_sysctl(net, "net/ipv4", table); if (hdr == NULL) goto err_reg; @@ -806,7 +820,7 @@ static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) static void ip4_frags_ctl_register(void) { - register_net_sysctl_rotable(net_ipv4_ctl_path, ip4_frags_ctl_table); + register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table); } #else static inline int ip4_frags_ns_ctl_register(struct net *net) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 38673d2860e..f49047b7960 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -10,6 +10,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> @@ -167,37 +169,56 @@ struct ipgre_net { /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; -static struct net_device_stats *ipgre_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) { - struct pcpu_tstats sum = { 0 }; int i; for_each_possible_cpu(i) { const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; } - dev->stats.rx_packets = sum.rx_packets; - dev->stats.rx_bytes = sum.rx_bytes; - dev->stats.tx_packets = sum.tx_packets; - dev->stats.tx_bytes = sum.tx_bytes; - return &dev->stats; + + tot->multicast = dev->stats.multicast; + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; } /* Given src, dst and key, find appropriate for input tunnel. */ -static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, - __be32 remote, __be32 local, - __be32 key, __be16 gre_proto) +static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, + __be32 remote, __be32 local, + __be32 key, __be16 gre_proto) { struct net *net = dev_net(dev); int link = dev->ifindex; @@ -462,7 +483,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) */ const struct iphdr *iph = (const struct iphdr *)skb->data; - __be16 *p = (__be16*)(skb->data+(iph->ihl<<2)); + __be16 *p = (__be16 *)(skb->data+(iph->ihl<<2)); int grehlen = (iph->ihl<<2) + 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -572,7 +593,7 @@ static int ipgre_rcv(struct sk_buff *skb) iph = ip_hdr(skb); h = skb->data; - flags = *(__be16*)h; + flags = *(__be16 *)h; if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) { /* - Version must be 0. @@ -596,11 +617,11 @@ static int ipgre_rcv(struct sk_buff *skb) offset += 4; } if (flags&GRE_KEY) { - key = *(__be32*)(h + offset); + key = *(__be32 *)(h + offset); offset += 4; } if (flags&GRE_SEQ) { - seqno = ntohl(*(__be32*)(h + offset)); + seqno = ntohl(*(__be32 *)(h + offset)); offset += 4; } } @@ -670,8 +691,10 @@ static int ipgre_rcv(struct sk_buff *skb) } tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); __skb_tunnel_rx(skb, tunnel->dev); @@ -730,15 +753,16 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); - if ((dst = rt->rt_gateway) == 0) - goto tx_error_icmp; + dst = rt->rt_gateway; } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb)); const struct in6_addr *addr6; + struct neighbour *neigh; + bool do_tx_error_icmp; int addr_type; + neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (neigh == NULL) goto tx_error; @@ -751,9 +775,14 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) + do_tx_error_icmp = true; + else { + do_tx_error_icmp = false; + dst = addr6->s6_addr32[3]; + } + neigh_release(neigh); + if (do_tx_error_icmp) goto tx_error_icmp; - - dst = addr6->s6_addr32[3]; } #endif else @@ -892,7 +921,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev htons(ETH_P_TEB) : skb->protocol; if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) { - __be32 *ptr = (__be32*)(((u8*)iph) + tunnel->hlen - 4); + __be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4); if (tunnel->parms.o_flags&GRE_SEQ) { ++tunnel->o_seqno; @@ -905,7 +934,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } if (tunnel->parms.o_flags&GRE_CSUM) { *ptr = 0; - *(__sum16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); } } @@ -914,9 +943,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; +#if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); - +#endif tx_error: dev->stats.tx_errors++; dev_kfree_skb(skb); @@ -1160,7 +1190,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen); - __be16 *p = (__be16*)(iph+1); + __be16 *p = (__be16 *)(iph+1); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); p[0] = t->parms.o_flags; @@ -1244,7 +1274,7 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_start_xmit = ipgre_tunnel_xmit, .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ipgre_tunnel_change_mtu, - .ndo_get_stats = ipgre_get_stats, + .ndo_get_stats64 = ipgre_get_stats64, }; static void ipgre_dev_free(struct net_device *dev) @@ -1498,7 +1528,7 @@ static const struct net_device_ops ipgre_tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ipgre_tunnel_change_mtu, - .ndo_get_stats = ipgre_get_stats, + .ndo_get_stats64 = ipgre_get_stats64, }; static void ipgre_tap_setup(struct net_device *dev) @@ -1529,7 +1559,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla return -EEXIST; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); mtu = ipgre_tunnel_bind_dev(dev); if (!tb[IFLA_MTU]) @@ -1645,17 +1675,18 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; - NLA_PUT_U32(skb, IFLA_GRE_LINK, p->link); - NLA_PUT_BE16(skb, IFLA_GRE_IFLAGS, p->i_flags); - NLA_PUT_BE16(skb, IFLA_GRE_OFLAGS, p->o_flags); - NLA_PUT_BE32(skb, IFLA_GRE_IKEY, p->i_key); - NLA_PUT_BE32(skb, IFLA_GRE_OKEY, p->o_key); - NLA_PUT_BE32(skb, IFLA_GRE_LOCAL, p->iph.saddr); - NLA_PUT_BE32(skb, IFLA_GRE_REMOTE, p->iph.daddr); - NLA_PUT_U8(skb, IFLA_GRE_TTL, p->iph.ttl); - NLA_PUT_U8(skb, IFLA_GRE_TOS, p->iph.tos); - NLA_PUT_U8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))); - + if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || + nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) || + nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || + nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || + nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || + nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) || + nla_put_be32(skb, IFLA_GRE_REMOTE, p->iph.daddr) || + nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || + nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || + nla_put_u8(skb, IFLA_GRE_PMTUDISC, + !!(p->iph.frag_off & htons(IP_DF)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -1709,7 +1740,7 @@ static int __init ipgre_init(void) { int err; - printk(KERN_INFO "GRE over IPv4 tunneling driver\n"); + pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) @@ -1717,7 +1748,7 @@ static int __init ipgre_init(void) err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { - printk(KERN_INFO "ipgre init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } @@ -1746,7 +1777,7 @@ static void __exit ipgre_fini(void) rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) - printk(KERN_INFO "ipgre close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); unregister_pernet_device(&ipgre_net_ops); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 073a9b01c40..8590144ca33 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -113,7 +113,8 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/system.h> +#define pr_fmt(fmt) "IPv4: " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -148,7 +149,7 @@ /* * Process Router Attention IP option (RFC 2113) */ -int ip_call_ra_chain(struct sk_buff *skb) +bool ip_call_ra_chain(struct sk_buff *skb) { struct ip_ra_chain *ra; u8 protocol = ip_hdr(skb)->protocol; @@ -167,7 +168,7 @@ int ip_call_ra_chain(struct sk_buff *skb) net_eq(sock_net(sk), dev_net(dev))) { if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) - return 1; + return true; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -180,9 +181,9 @@ int ip_call_ra_chain(struct sk_buff *skb) if (last) { raw_rcv(last, skb); - return 1; + return true; } - return 0; + return false; } static int ip_local_deliver_finish(struct sk_buff *skb) @@ -209,9 +210,8 @@ static int ip_local_deliver_finish(struct sk_buff *skb) int ret; if (!net_eq(net, &init_net) && !ipprot->netns_ok) { - if (net_ratelimit()) - printk("%s: proto %d isn't netns-ready\n", - __func__, protocol); + net_info_ratelimited("%s: proto %d isn't netns-ready\n", + __func__, protocol); kfree_skb(skb); goto out; } @@ -265,7 +265,7 @@ int ip_local_deliver(struct sk_buff *skb) ip_local_deliver_finish); } -static inline int ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb) { struct ip_options *opt; const struct iphdr *iph; @@ -297,10 +297,10 @@ static inline int ip_rcv_options(struct sk_buff *skb) if (in_dev) { if (!IN_DEV_SOURCE_ROUTE(in_dev)) { - if (IN_DEV_LOG_MARTIANS(in_dev) && - net_ratelimit()) - printk(KERN_INFO "source route option %pI4 -> %pI4\n", - &iph->saddr, &iph->daddr); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_info_ratelimited("source route option %pI4 -> %pI4\n", + &iph->saddr, + &iph->daddr); goto drop; } } @@ -309,9 +309,9 @@ static inline int ip_rcv_options(struct sk_buff *skb) goto drop; } - return 0; + return false; drop: - return -1; + return true; } static int ip_rcv_finish(struct sk_buff *skb) diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 42dd1a90ede..708b99494e2 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -9,6 +9,8 @@ * */ +#define pr_fmt(fmt) "IPv4: " fmt + #include <linux/capability.h> #include <linux/module.h> #include <linux/slab.h> @@ -208,10 +210,10 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) * Simple and stupid 8), but the most efficient way. */ -void ip_options_fragment(struct sk_buff * skb) +void ip_options_fragment(struct sk_buff *skb) { unsigned char *optptr = skb_network_header(skb) + sizeof(struct iphdr); - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); int l = opt->optlen; int optlen; @@ -246,13 +248,13 @@ void ip_options_fragment(struct sk_buff * skb) */ int ip_options_compile(struct net *net, - struct ip_options * opt, struct sk_buff * skb) + struct ip_options *opt, struct sk_buff *skb) { int l; - unsigned char * iph; - unsigned char * optptr; + unsigned char *iph; + unsigned char *optptr; int optlen; - unsigned char * pp_ptr = NULL; + unsigned char *pp_ptr = NULL; struct rtable *rt = NULL; if (skb != NULL) { @@ -411,7 +413,7 @@ int ip_options_compile(struct net *net, opt->is_changed = 1; } } else { - unsigned overflow = optptr[3]>>4; + unsigned int overflow = optptr[3]>>4; if (overflow == 15) { pp_ptr = optptr + 3; goto error; @@ -471,20 +473,20 @@ EXPORT_SYMBOL(ip_options_compile); * Undo all the changes done by ip_options_compile(). */ -void ip_options_undo(struct ip_options * opt) +void ip_options_undo(struct ip_options *opt) { if (opt->srr) { - unsigned char * optptr = opt->__data+opt->srr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr); memmove(optptr+7, optptr+3, optptr[1]-7); memcpy(optptr+3, &opt->faddr, 4); } if (opt->rr_needaddr) { - unsigned char * optptr = opt->__data+opt->rr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr); optptr[2] -= 4; memset(&optptr[optptr[2]-1], 0, 4); } if (opt->ts) { - unsigned char * optptr = opt->__data+opt->ts-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr); if (opt->ts_needtime) { optptr[2] -= 4; memset(&optptr[optptr[2]-1], 0, 4); @@ -547,8 +549,8 @@ int ip_options_get(struct net *net, struct ip_options_rcu **optp, void ip_forward_options(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); - unsigned char * optptr; + struct ip_options *opt = &(IPCB(skb)->opt); + unsigned char *optptr; struct rtable *rt = skb_rtable(skb); unsigned char *raw = skb_network_header(skb); @@ -576,8 +578,10 @@ void ip_forward_options(struct sk_buff *skb) ip_hdr(skb)->daddr = opt->nexthop; ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; - } else if (net_ratelimit()) - printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); + } else { + net_crit_ratelimited("%s(): Argh! Destination lost!\n", + __func__); + } if (opt->ts_needaddr) { optptr = raw + opt->ts; ip_rt_get_source(&optptr[optptr[2]-9], skb, rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ff302bde889..451f97c42eb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -43,7 +43,6 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -215,8 +214,8 @@ static inline int ip_finish_output2(struct sk_buff *skb) } rcu_read_unlock(); - if (net_ratelimit()) - printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); + net_dbg_ratelimited("%s: No header cache and no neighbour!\n", + __func__); kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8aa87c19fa0..0d11f234d61 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -90,7 +90,7 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; - struct ip_options * opt = (struct ip_options *)optbuf; + struct ip_options *opt = (struct ip_options *)optbuf; if (IPCB(skb)->opt.optlen == 0) return; @@ -147,7 +147,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(skb->sk); - unsigned flags = inet->cmsg_flags; + unsigned int flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ if (flags & 1) @@ -445,11 +445,6 @@ out: } -static void opt_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_options_rcu, rcu)); -} - /* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. @@ -469,6 +464,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) || + optname == IP_UNICAST_IF || optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_ALL || optname == IP_MULTICAST_LOOP || @@ -525,7 +521,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } rcu_assign_pointer(inet->inet_opt, opt); if (old) - call_rcu(&old->rcu, opt_kfree_rcu); + kfree_rcu(old, rcu); break; } case IP_PKTINFO: @@ -628,6 +624,35 @@ static int do_ip_setsockopt(struct sock *sk, int level, goto e_inval; inet->mc_loop = !!val; break; + case IP_UNICAST_IF: + { + struct net_device *dev = NULL; + int ifindex; + + if (optlen != sizeof(int)) + goto e_inval; + + ifindex = (__force int)ntohl((__force __be32)val); + if (ifindex == 0) { + inet->uc_index = 0; + err = 0; + break; + } + + dev = dev_get_by_index(sock_net(sk), ifindex); + err = -EADDRNOTAVAIL; + if (!dev) + break; + dev_put(dev); + + err = -EINVAL; + if (sk->sk_bound_dev_if) + break; + + inet->uc_index = ifindex; + err = 0; + break; + } case IP_MULTICAST_IF: { struct ip_mreqn mreq; @@ -648,10 +673,15 @@ static int do_ip_setsockopt(struct sock *sk, int level, break; } else { memset(&mreq, 0, sizeof(mreq)); - if (optlen >= sizeof(struct in_addr) && - copy_from_user(&mreq.imr_address, optval, - sizeof(struct in_addr))) - break; + if (optlen >= sizeof(struct ip_mreq)) { + if (copy_from_user(&mreq, optval, + sizeof(struct ip_mreq))) + break; + } else if (optlen >= sizeof(struct in_addr)) { + if (copy_from_user(&mreq.imr_address, optval, + sizeof(struct in_addr))) + break; + } } if (!mreq.imr_ifindex) { @@ -1069,7 +1099,7 @@ EXPORT_SYMBOL(compat_ip_setsockopt); */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen, unsigned flags) + char __user *optval, int __user *optlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int val; @@ -1178,6 +1208,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MULTICAST_LOOP: val = inet->mc_loop; break; + case IP_UNICAST_IF: + val = (__force int)htonl((__u32) inet->uc_index); + break; case IP_MULTICAST_IF: { struct in_addr addr; @@ -1256,6 +1289,10 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, int hlim = inet->mc_ttl; put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } + if (inet->cmsg_flags & IP_CMSG_TOS) { + int tos = inet->rcv_tos; + put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); + } len -= msg.msg_controllen; return put_user(len, optlen); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index c857f6f49b0..63b64c45a82 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -156,11 +156,11 @@ static const struct net_protocol ipcomp4_protocol = { static int __init ipcomp4_init(void) { if (xfrm_register_type(&ipcomp_type, AF_INET) < 0) { - printk(KERN_INFO "ipcomp init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) { - printk(KERN_INFO "ipcomp init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp_type, AF_INET); return -EAGAIN; } @@ -170,9 +170,9 @@ static int __init ipcomp4_init(void) static void __exit ipcomp4_fini(void) { if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) - printk(KERN_INFO "ip ipcomp close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0) - printk(KERN_INFO "ip ipcomp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(ipcomp4_init); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 6e412a60a91..67e8a6b086e 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -214,7 +214,7 @@ static int __init ic_open_devs(void) if (!(dev->flags & IFF_LOOPBACK)) continue; if (dev_change_flags(dev, dev->flags | IFF_UP) < 0) - printk(KERN_ERR "IP-Config: Failed to open %s\n", dev->name); + pr_err("IP-Config: Failed to open %s\n", dev->name); } for_each_netdev(&init_net, dev) { @@ -223,7 +223,8 @@ static int __init ic_open_devs(void) if (dev->mtu >= 364) able |= IC_BOOTP; else - printk(KERN_WARNING "DHCP/BOOTP: Ignoring device %s, MTU %d too small", dev->name, dev->mtu); + pr_warn("DHCP/BOOTP: Ignoring device %s, MTU %d too small", + dev->name, dev->mtu); if (!(dev->flags & IFF_NOARP)) able |= IC_RARP; able &= ic_proto_enabled; @@ -231,7 +232,8 @@ static int __init ic_open_devs(void) continue; oflags = dev->flags; if (dev_change_flags(dev, oflags | IFF_UP) < 0) { - printk(KERN_ERR "IP-Config: Failed to open %s\n", dev->name); + pr_err("IP-Config: Failed to open %s\n", + dev->name); continue; } if (!(d = kmalloc(sizeof(struct ic_device), GFP_KERNEL))) { @@ -273,9 +275,10 @@ have_carrier: if (!ic_first_dev) { if (user_dev_name[0]) - printk(KERN_ERR "IP-Config: Device `%s' not found.\n", user_dev_name); + pr_err("IP-Config: Device `%s' not found\n", + user_dev_name); else - printk(KERN_ERR "IP-Config: No network devices available.\n"); + pr_err("IP-Config: No network devices available\n"); return -ENODEV; } return 0; @@ -359,17 +362,20 @@ static int __init ic_setup_if(void) strcpy(ir.ifr_ifrn.ifrn_name, ic_dev->name); set_sockaddr(sin, ic_myaddr, 0); if ((err = ic_devinet_ioctl(SIOCSIFADDR, &ir)) < 0) { - printk(KERN_ERR "IP-Config: Unable to set interface address (%d).\n", err); + pr_err("IP-Config: Unable to set interface address (%d)\n", + err); return -1; } set_sockaddr(sin, ic_netmask, 0); if ((err = ic_devinet_ioctl(SIOCSIFNETMASK, &ir)) < 0) { - printk(KERN_ERR "IP-Config: Unable to set interface netmask (%d).\n", err); + pr_err("IP-Config: Unable to set interface netmask (%d)\n", + err); return -1; } set_sockaddr(sin, ic_myaddr | ~ic_netmask, 0); if ((err = ic_devinet_ioctl(SIOCSIFBRDADDR, &ir)) < 0) { - printk(KERN_ERR "IP-Config: Unable to set interface broadcast address (%d).\n", err); + pr_err("IP-Config: Unable to set interface broadcast address (%d)\n", + err); return -1; } /* Handle the case where we need non-standard MTU on the boot link (a network @@ -380,8 +386,8 @@ static int __init ic_setup_if(void) strcpy(ir.ifr_name, ic_dev->name); ir.ifr_mtu = ic_dev_mtu; if ((err = ic_dev_ioctl(SIOCSIFMTU, &ir)) < 0) - printk(KERN_ERR "IP-Config: Unable to set interface mtu to %d (%d).\n", - ic_dev_mtu, err); + pr_err("IP-Config: Unable to set interface mtu to %d (%d)\n", + ic_dev_mtu, err); } return 0; } @@ -396,7 +402,7 @@ static int __init ic_setup_routes(void) memset(&rm, 0, sizeof(rm)); if ((ic_gateway ^ ic_myaddr) & ic_netmask) { - printk(KERN_ERR "IP-Config: Gateway not on directly connected network.\n"); + pr_err("IP-Config: Gateway not on directly connected network\n"); return -1; } set_sockaddr((struct sockaddr_in *) &rm.rt_dst, 0, 0); @@ -404,7 +410,8 @@ static int __init ic_setup_routes(void) set_sockaddr((struct sockaddr_in *) &rm.rt_gateway, ic_gateway, 0); rm.rt_flags = RTF_UP | RTF_GATEWAY; if ((err = ic_route_ioctl(SIOCADDRT, &rm)) < 0) { - printk(KERN_ERR "IP-Config: Cannot add default route (%d).\n", err); + pr_err("IP-Config: Cannot add default route (%d)\n", + err); return -1; } } @@ -437,8 +444,8 @@ static int __init ic_defaults(void) else if (IN_CLASSC(ntohl(ic_myaddr))) ic_netmask = htonl(IN_CLASSC_NET); else { - printk(KERN_ERR "IP-Config: Unable to guess netmask for address %pI4\n", - &ic_myaddr); + pr_err("IP-Config: Unable to guess netmask for address %pI4\n", + &ic_myaddr); return -1; } printk("IP-Config: Guessing netmask %pI4\n", &ic_netmask); @@ -688,8 +695,8 @@ ic_dhcp_init_options(u8 *options) e += len; } if (*vendor_class_identifier) { - printk(KERN_INFO "DHCP: sending class identifier \"%s\"\n", - vendor_class_identifier); + pr_info("DHCP: sending class identifier \"%s\"\n", + vendor_class_identifier); *e++ = 60; /* Class-identifier */ len = strlen(vendor_class_identifier); *e++ = len; @@ -801,8 +808,6 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d b->op = BOOTP_REQUEST; if (dev->type < 256) /* check for false types */ b->htype = dev->type; - else if (dev->type == ARPHRD_IEEE802_TR) /* fix for token ring */ - b->htype = ARPHRD_IEEE802; else if (dev->type == ARPHRD_FDDI) b->htype = ARPHRD_ETHER; else { @@ -948,9 +953,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Fragments are not supported */ if (ip_is_fragment(h)) { - if (net_ratelimit()) - printk(KERN_ERR "DHCP/BOOTP: Ignoring fragmented " - "reply.\n"); + net_err_ratelimited("DHCP/BOOTP: Ignoring fragmented reply\n"); goto drop; } @@ -998,17 +1001,14 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Is it a reply to our BOOTP request? */ if (b->op != BOOTP_REPLY || b->xid != d->xid) { - if (net_ratelimit()) - printk(KERN_ERR "DHCP/BOOTP: Reply not for us, " - "op[%x] xid[%x]\n", - b->op, b->xid); + net_err_ratelimited("DHCP/BOOTP: Reply not for us, op[%x] xid[%x]\n", + b->op, b->xid); goto drop_unlock; } /* Is it a reply for the device we are configuring? */ if (b->xid != ic_dev_xid) { - if (net_ratelimit()) - printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet\n"); + net_err_ratelimited("DHCP/BOOTP: Ignoring delayed packet\n"); goto drop_unlock; } @@ -1146,17 +1146,17 @@ static int __init ic_dynamic(void) * are missing, and without DHCP/BOOTP/RARP we are unable to get it. */ if (!ic_proto_enabled) { - printk(KERN_ERR "IP-Config: Incomplete network configuration information.\n"); + pr_err("IP-Config: Incomplete network configuration information\n"); return -1; } #ifdef IPCONFIG_BOOTP if ((ic_proto_enabled ^ ic_proto_have_if) & IC_BOOTP) - printk(KERN_ERR "DHCP/BOOTP: No suitable device found.\n"); + pr_err("DHCP/BOOTP: No suitable device found\n"); #endif #ifdef IPCONFIG_RARP if ((ic_proto_enabled ^ ic_proto_have_if) & IC_RARP) - printk(KERN_ERR "RARP: No suitable device found.\n"); + pr_err("RARP: No suitable device found\n"); #endif if (!ic_proto_have_if) @@ -1183,17 +1183,17 @@ static int __init ic_dynamic(void) * [Actually we could now, but the nothing else running note still * applies.. - AC] */ - printk(KERN_NOTICE "Sending %s%s%s requests .", - do_bootp - ? ((ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP") : "", - (do_bootp && do_rarp) ? " and " : "", - do_rarp ? "RARP" : ""); + pr_notice("Sending %s%s%s requests .", + do_bootp + ? ((ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP") : "", + (do_bootp && do_rarp) ? " and " : "", + do_rarp ? "RARP" : ""); start_jiffies = jiffies; d = ic_first_dev; retries = CONF_SEND_RETRIES; get_random_bytes(&timeout, sizeof(timeout)); - timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned) CONF_TIMEOUT_RANDOM); + timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned int) CONF_TIMEOUT_RANDOM); for (;;) { /* Track the device we are configuring */ ic_dev_xid = d->xid; @@ -1216,13 +1216,13 @@ static int __init ic_dynamic(void) (ic_proto_enabled & IC_USE_DHCP) && ic_dhcp_msgtype != DHCPACK) { ic_got_reply = 0; - printk(KERN_CONT ","); + pr_cont(","); continue; } #endif /* IPCONFIG_DHCP */ if (ic_got_reply) { - printk(KERN_CONT " OK\n"); + pr_cont(" OK\n"); break; } @@ -1230,7 +1230,7 @@ static int __init ic_dynamic(void) continue; if (! --retries) { - printk(KERN_CONT " timed out!\n"); + pr_cont(" timed out!\n"); break; } @@ -1240,7 +1240,7 @@ static int __init ic_dynamic(void) if (timeout > CONF_TIMEOUT_MAX) timeout = CONF_TIMEOUT_MAX; - printk(KERN_CONT "."); + pr_cont("."); } #ifdef IPCONFIG_BOOTP @@ -1260,8 +1260,8 @@ static int __init ic_dynamic(void) printk("IP-Config: Got %s answer from %pI4, ", ((ic_got_reply & IC_RARP) ? "RARP" : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), - &ic_servaddr); - printk(KERN_CONT "my address is %pI4\n", &ic_myaddr); + &ic_servaddr); + pr_cont("my address is %pI4\n", &ic_myaddr); return 0; } @@ -1437,24 +1437,22 @@ static int __init ip_auto_config(void) */ #ifdef CONFIG_ROOT_NFS if (ROOT_DEV == Root_NFS) { - printk(KERN_ERR - "IP-Config: Retrying forever (NFS root)...\n"); + pr_err("IP-Config: Retrying forever (NFS root)...\n"); goto try_try_again; } #endif if (--retries) { - printk(KERN_ERR - "IP-Config: Reopening network devices...\n"); + pr_err("IP-Config: Reopening network devices...\n"); goto try_try_again; } /* Oh, well. At least we tried. */ - printk(KERN_ERR "IP-Config: Auto-configuration of network failed.\n"); + pr_err("IP-Config: Auto-configuration of network failed\n"); return -1; } #else /* !DYNAMIC */ - printk(KERN_ERR "IP-Config: Incomplete network configuration information.\n"); + pr_err("IP-Config: Incomplete network configuration information\n"); ic_close_devs(); return -1; #endif /* IPCONFIG_DYNAMIC */ @@ -1492,19 +1490,16 @@ static int __init ip_auto_config(void) /* * Clue in the operator. */ - printk("IP-Config: Complete:\n"); - printk(" device=%s", ic_dev->name); - printk(KERN_CONT ", addr=%pI4", &ic_myaddr); - printk(KERN_CONT ", mask=%pI4", &ic_netmask); - printk(KERN_CONT ", gw=%pI4", &ic_gateway); - printk(KERN_CONT ",\n host=%s, domain=%s, nis-domain=%s", - utsname()->nodename, ic_domain, utsname()->domainname); - printk(KERN_CONT ",\n bootserver=%pI4", &ic_servaddr); - printk(KERN_CONT ", rootserver=%pI4", &root_server_addr); - printk(KERN_CONT ", rootpath=%s", root_server_path); + pr_info("IP-Config: Complete:\n"); + pr_info(" device=%s, addr=%pI4, mask=%pI4, gw=%pI4\n", + ic_dev->name, &ic_myaddr, &ic_netmask, &ic_gateway); + pr_info(" host=%s, domain=%s, nis-domain=%s\n", + utsname()->nodename, ic_domain, utsname()->domainname); + pr_info(" bootserver=%pI4, rootserver=%pI4, rootpath=%s", + &ic_servaddr, &root_server_addr, root_server_path); if (ic_dev_mtu) - printk(KERN_CONT ", mtu=%d", ic_dev_mtu); - printk(KERN_CONT "\n"); + pr_cont(", mtu=%d", ic_dev_mtu); + pr_cont("\n"); #endif /* !SILENT */ return 0; @@ -1626,22 +1621,21 @@ static int __init ip_auto_config_setup(char *addrs) return 1; } +__setup("ip=", ip_auto_config_setup); static int __init nfsaddrs_config_setup(char *addrs) { return ip_auto_config_setup(addrs); } +__setup("nfsaddrs=", nfsaddrs_config_setup); static int __init vendor_class_identifier_setup(char *addrs) { if (strlcpy(vendor_class_identifier, addrs, sizeof(vendor_class_identifier)) >= sizeof(vendor_class_identifier)) - printk(KERN_WARNING "DHCP: vendorclass too long, truncated to \"%s\"", - vendor_class_identifier); + pr_warn("DHCP: vendorclass too long, truncated to \"%s\"", + vendor_class_identifier); return 1; } - -__setup("ip=", ip_auto_config_setup); -__setup("nfsaddrs=", nfsaddrs_config_setup); __setup("dhcpclass=", vendor_class_identifier_setup); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 22a19931530..2d0f99bf61b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -144,33 +144,48 @@ static void ipip_dev_free(struct net_device *dev); /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; -static struct net_device_stats *ipip_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) { - struct pcpu_tstats sum = { 0 }; int i; for_each_possible_cpu(i) { const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; } - dev->stats.rx_packets = sum.rx_packets; - dev->stats.rx_bytes = sum.rx_bytes; - dev->stats.tx_packets = sum.tx_packets; - dev->stats.tx_bytes = sum.tx_bytes; - return &dev->stats; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + tot->collisions = dev->stats.collisions; + + return tot; } -static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, +static struct ip_tunnel *ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) { unsigned int h0 = HASH(remote); @@ -245,7 +260,7 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) rcu_assign_pointer(*tp, t); } -static struct ip_tunnel * ipip_tunnel_locate(struct net *net, +static struct ip_tunnel *ipip_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; @@ -404,8 +419,10 @@ static int ipip_rcv(struct sk_buff *skb) skb->pkt_type = PACKET_HOST; tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); __skb_tunnel_rx(skb, tunnel->dev); @@ -454,8 +471,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_fifo_errors++; goto tx_error; } - if ((dst = rt->rt_gateway) == 0) - goto tx_error_icmp; + dst = rt->rt_gateway; } rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, @@ -731,7 +747,7 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_start_xmit = ipip_tunnel_xmit, .ndo_do_ioctl = ipip_tunnel_ioctl, .ndo_change_mtu = ipip_tunnel_change_mtu, - .ndo_get_stats = ipip_get_stats, + .ndo_get_stats64 = ipip_get_stats64, }; static void ipip_dev_free(struct net_device *dev) @@ -893,7 +909,7 @@ static int __init ipip_init(void) err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { unregister_pernet_device(&ipip_net_ops); - printk(KERN_INFO "ipip init: can't register tunnel\n"); + pr_info("%s: can't register tunnel\n", __func__); } return err; } @@ -901,7 +917,7 @@ static int __init ipip_init(void) static void __exit ipip_fini(void) { if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) - printk(KERN_INFO "ipip close: can't deregister tunnel\n"); + pr_info("%s: can't deregister tunnel\n", __func__); unregister_pernet_device(&ipip_net_ops); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7bc2db6db8d..a9e519ad6db 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -26,7 +26,6 @@ * */ -#include <asm/system.h> #include <asm/uaccess.h> #include <linux/types.h> #include <linux/capability.h> @@ -950,8 +949,7 @@ static int ipmr_cache_report(struct mr_table *mrt, ret = sock_queue_rcv_skb(mroute_sk, skb); rcu_read_unlock(); if (ret < 0) { - if (net_ratelimit()) - printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); + net_warn_ratelimited("mroute: pending queue full, dropping entries\n"); kfree_skb(skb); } @@ -2120,15 +2118,16 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, rtm->rtm_src_len = 32; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; - NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + if (nla_put_u32(skb, RTA_TABLE, mrt->id)) + goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = RTPROT_UNSPEC; rtm->rtm_flags = 0; - NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin); - NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp); - + if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) || + nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp)) + goto nla_put_failure; if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0) goto nla_put_failure; @@ -2538,7 +2537,7 @@ int __init ip_mr_init(void) goto reg_notif_fail; #ifdef CONFIG_IP_PIMSM_V2 if (inet_add_protocol(&pim_protocol, IPPROTO_PIM) < 0) { - printk(KERN_ERR "ip_mr_init: can't add PIM protocol\n"); + pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 4f47e064e26..ed1b3678319 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -12,7 +12,7 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) +int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) { struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); @@ -237,13 +237,3 @@ static void ipv4_netfilter_fini(void) module_init(ipv4_netfilter_init); module_exit(ipv4_netfilter_fini); - -#ifdef CONFIG_SYSCTL -struct ctl_path nf_net_ipv4_netfilter_sysctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "netfilter", }, - { } -}; -EXPORT_SYMBOL_GPL(nf_net_ipv4_netfilter_sysctl_path); -#endif /* CONFIG_SYSCTL */ diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 74dfc9e5211..fcc543cd987 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -123,15 +123,6 @@ config IP_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_LOG - tristate "LOG target support" - default m if NETFILTER_ADVANCED=n - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_ULOG tristate "ULOG target support" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 213a462b739..c20674dc945 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -54,7 +54,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o # targets obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o -obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o @@ -67,6 +66,3 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o # just filtering instance of ARP tables for now obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o - -obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o - diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index fd7a3f68917..97e61eadf58 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -221,9 +221,8 @@ static inline int arp_checkentry(const struct arpt_arp *arp) static unsigned int arpt_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - pr_err("arp_tables: error: '%s'\n", - (const char *)par->targinfo); + net_err_ratelimited("arp_tables: error: '%s'\n", + (const char *)par->targinfo); return NF_DROP; } @@ -303,7 +302,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { - verdict = (unsigned)(-v) - 1; + verdict = (unsigned int)(-v) - 1; break; } e = back; diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c deleted file mode 100644 index 94d45e1f888..00000000000 --- a/net/ipv4/netfilter/ip_queue.c +++ /dev/null @@ -1,639 +0,0 @@ -/* - * This is a module which is used for queueing IPv4 packets and - * communicating with userspace via netlink. - * - * (C) 2000-2002 James Morris <jmorris@intercode.com.au> - * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/ip.h> -#include <linux/notifier.h> -#include <linux/netdevice.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_queue.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netlink.h> -#include <linux/spinlock.h> -#include <linux/sysctl.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/security.h> -#include <linux/net.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <net/net_namespace.h> -#include <net/sock.h> -#include <net/route.h> -#include <net/netfilter/nf_queue.h> -#include <net/ip.h> - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip_queue" -#define NET_IPQ_QMAX 2088 -#define NET_IPQ_QMAX_NAME "ip_queue_maxlen" - -typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); - -static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; -static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; -static DEFINE_SPINLOCK(queue_lock); -static int peer_pid __read_mostly; -static unsigned int copy_range __read_mostly; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl __read_mostly; -static LIST_HEAD(queue_list); -static DEFINE_MUTEX(ipqnl_mutex); - -static inline void -__ipq_enqueue_entry(struct nf_queue_entry *entry) -{ - list_add_tail(&entry->list, &queue_list); - queue_total++; -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - if (range > 0xFFFF) - range = 0xFFFF; - copy_range = range; - copy_mode = mode; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data); - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NULL, 0); -} - -static struct nf_queue_entry * -ipq_find_dequeue_entry(unsigned long id) -{ - struct nf_queue_entry *entry = NULL, *i; - - spin_lock_bh(&queue_lock); - - list_for_each_entry(i, &queue_list, list) { - if ((unsigned long)i == id) { - entry = i; - break; - } - } - - if (entry) { - list_del(&entry->list); - queue_total--; - } - - spin_unlock_bh(&queue_lock); - return entry; -} - -static void -__ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - struct nf_queue_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &queue_list, list) { - if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue_total--; - nf_reinject(entry, NF_DROP); - } - } -} - -static void -ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - spin_lock_bh(&queue_lock); - __ipq_flush(cmpfn, data); - spin_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) -{ - sk_buff_data_t old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - struct timeval tv; - - switch (ACCESS_ONCE(copy_mode)) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_PARTIAL && - (*errp = skb_checksum_help(entry->skb))) - return NULL; - - data_len = ACCESS_ONCE(copy_range); - if (data_len == 0 || data_len > entry->skb->len) - data_len = entry->skb->len; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - return NULL; - } - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - tv = ktime_to_timeval(entry->skb->tstamp); - pmsg->timestamp_sec = tv.tv_sec; - pmsg->timestamp_usec = tv.tv_usec; - pmsg->mark = entry->skb->mark; - pmsg->hook = entry->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->indev) - strcpy(pmsg->indev_name, entry->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->outdev) - strcpy(pmsg->outdev_name, entry->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->indev && entry->skb->dev && - entry->skb->mac_header != entry->skb->network_header) { - pmsg->hw_type = entry->skb->dev->type; - pmsg->hw_addrlen = dev_parse_header(entry->skb, - pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) -{ - int status = -EINVAL; - struct sk_buff *nskb; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - return status; - - spin_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip_queue: full at %d entries, " - "dropping packets(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - spin_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct nf_queue_entry *e) -{ - int diff; - struct iphdr *user_iph = (struct iphdr *)v->payload; - struct sk_buff *nskb; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) { - if (pskb_trim(e->skb, v->data_len)) - return -ENOMEM; - } else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), - diff, GFP_ATOMIC); - if (!nskb) { - printk(KERN_WARNING "ip_queue: error " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - kfree_skb(e->skb); - e->skb = nskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(e->skb, v->data_len)) - return -ENOMEM; - skb_copy_to_linear_data(e->skb, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct nf_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN) - return -EINVAL; - - entry = ipq_find_dequeue_entry(vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv4(vmsg, entry) < 0) - verdict = NF_DROP; - - nf_reinject(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - spin_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) -{ - if (entry->indev) - if (entry->indev->ifindex == ifindex) - return 1; - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) - return 1; -#ifdef CONFIG_BRIDGE_NETFILTER - if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) - return 1; - } -#endif - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - ipq_flush(dev_cmp, ifindex); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -__ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags; - unsigned int nlmsglen, skblen; - struct nlmsghdr *nlh; - bool enable_timestamp = false; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = nlmsg_hdr(skb); - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (!capable(CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - spin_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - spin_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - enable_timestamp = true; - peer_pid = pid; - } - - spin_unlock_bh(&queue_lock); - if (enable_timestamp) - net_enable_timestamp(); - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - nlmsglen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); -} - -static void -ipq_rcv_skb(struct sk_buff *skb) -{ - mutex_lock(&ipqnl_mutex); - __ipq_rcv_skb(skb); - mutex_unlock(&ipqnl_mutex); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { - spin_lock_bh(&queue_lock); - if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) - __ipq_reset(); - spin_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { } -}; -#endif - -#ifdef CONFIG_PROC_FS -static int ip_queue_show(struct seq_file *m, void *v) -{ - spin_lock_bh(&queue_lock); - - seq_printf(m, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netlink dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - spin_unlock_bh(&queue_lock); - return 0; -} - -static int ip_queue_open(struct inode *inode, struct file *file) -{ - return single_open(file, ip_queue_show, NULL); -} - -static const struct file_operations ip_queue_proc_fops = { - .open = ip_queue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; -#endif - -static const struct nf_queue_handler nfqh = { - .name = "ip_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int __init ip_queue_init(void) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc __maybe_unused; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(&init_net, NETLINK_FIREWALL, 0, - ipq_rcv_skb, NULL, THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - -#ifdef CONFIG_PROC_FS - proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net, - &ip_queue_proc_fops); - if (!proc) { - printk(KERN_ERR "ip_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } -#endif - register_netdevice_notifier(&ipq_dev_notifier); -#ifdef CONFIG_SYSCTL - ipq_sysctl_header = register_sysctl_paths(net_ipv4_ctl_path, ipq_table); -#endif - status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup_sysctl: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); -cleanup_ipqnl: __maybe_unused - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static void __exit ip_queue_fini(void) -{ - nf_unregister_queue_handlers(&nfqh); - - ipq_flush(NULL, 0); - -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - - netlink_unregister_notifier(&ipq_nl_notifier); -} - -MODULE_DESCRIPTION("IPv4 packet queue handler"); -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_FIREWALL); - -module_init(ip_queue_init); -module_exit(ip_queue_fini); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 24e556e83a3..170b1fdd6b7 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -153,8 +153,7 @@ ip_checkentry(const struct ipt_ip *ip) static unsigned int ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - pr_info("error: `%s'\n", (const char *)par->targinfo); + net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } @@ -377,7 +376,7 @@ ipt_do_table(struct sk_buff *skb, if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { - verdict = (unsigned)(-v) - 1; + verdict = (unsigned int)(-v) - 1; break; } if (*stackptr <= origptr) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index a639967eb72..fe5daea5214 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -246,8 +246,7 @@ clusterip_hashfn(const struct sk_buff *skb, dport = ports[1]; } } else { - if (net_ratelimit()) - pr_info("unknown protocol %u\n", iph->protocol); + net_info_ratelimited("unknown protocol %u\n", iph->protocol); } switch (config->hash_mode) { diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c deleted file mode 100644 index d76d6c9ed94..00000000000 --- a/net/ipv4/netfilter/ipt_LOG.c +++ /dev/null @@ -1,516 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/route.h> - -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ipt_LOG.h> -#include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog"); - -/* One level of recursion won't kill us */ -static void dump_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, - unsigned int iphoff) -{ - struct iphdr _iph; - const struct iphdr *ih; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Important fields: - * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ - /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - sb_add(m, "SRC=%pI4 DST=%pI4 ", - &ih->saddr, &ih->daddr); - - /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ - sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, - ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); - - /* Max length: 6 "CE DF MF " */ - if (ntohs(ih->frag_off) & IP_CE) - sb_add(m, "CE "); - if (ntohs(ih->frag_off) & IP_DF) - sb_add(m, "DF "); - if (ntohs(ih->frag_off) & IP_MF) - sb_add(m, "MF "); - - /* Max length: 11 "FRAG:65535 " */ - if (ntohs(ih->frag_off) & IP_OFFSET) - sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - - if ((logflags & IPT_LOG_IPOPT) && - ih->ihl * 4 > sizeof(struct iphdr)) { - const unsigned char *op; - unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; - unsigned int i, optsize; - - optsize = ih->ihl * 4 - sizeof(struct iphdr); - op = skb_header_pointer(skb, iphoff+sizeof(_iph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - - switch (ih->protocol) { - case IPPROTO_TCP: { - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IPT_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3F " */ - sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IPT_LOG_TCPOPT) && - th->doff * 4 > sizeof(struct tcphdr)) { - unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; - const unsigned char *op; - unsigned int i, optsize; - - optsize = th->doff * 4 - sizeof(struct tcphdr); - op = skb_header_pointer(skb, - iphoff+ih->ihl*4+sizeof(_tcph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - break; - } - case IPPROTO_UDP: - case IPPROTO_UDPLITE: { - struct udphdr _udph; - const struct udphdr *uh; - - if (ih->protocol == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP " ); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMP: { - struct icmphdr _icmph; - const struct icmphdr *ich; - static const size_t required_len[NR_ICMP_TYPES+1] - = { [ICMP_ECHOREPLY] = 4, - [ICMP_DEST_UNREACH] - = 8 + sizeof(struct iphdr), - [ICMP_SOURCE_QUENCH] - = 8 + sizeof(struct iphdr), - [ICMP_REDIRECT] - = 8 + sizeof(struct iphdr), - [ICMP_ECHO] = 4, - [ICMP_TIME_EXCEEDED] - = 8 + sizeof(struct iphdr), - [ICMP_PARAMETERPROB] - = 8 + sizeof(struct iphdr), - [ICMP_TIMESTAMP] = 20, - [ICMP_TIMESTAMPREPLY] = 20, - [ICMP_ADDRESS] = 12, - [ICMP_ADDRESSREPLY] = 12 }; - - /* Max length: 11 "PROTO=ICMP " */ - sb_add(m, "PROTO=ICMP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_icmph), &_icmph); - if (ich == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES && - required_len[ich->type] && - skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - switch (ich->type) { - case ICMP_ECHOREPLY: - case ICMP_ECHO: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ich->un.echo.id), - ntohs(ich->un.echo.sequence)); - break; - - case ICMP_PARAMETERPROB: - /* Max length: 14 "PARAMETER=255 " */ - sb_add(m, "PARAMETER=%u ", - ntohl(ich->un.gateway) >> 24); - break; - case ICMP_REDIRECT: - /* Max length: 24 "GATEWAY=255.255.255.255 " */ - sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); - /* Fall through */ - case ICMP_DEST_UNREACH: - case ICMP_SOURCE_QUENCH: - case ICMP_TIME_EXCEEDED: - /* Max length: 3+maxlen */ - if (!iphoff) { /* Only recurse once. */ - sb_add(m, "["); - dump_packet(m, info, skb, - iphoff + ih->ihl*4+sizeof(_icmph)); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH && - ich->code == ICMP_FRAG_NEEDED) - sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); - } - break; - } - /* Max Length */ - case IPPROTO_AH: { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 9 "PROTO=AH " */ - sb_add(m, "PROTO=AH "); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ah = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_ahdr), &_ahdr); - if (ah == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - break; - } - case IPPROTO_ESP: { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 10 "PROTO=ESP " */ - sb_add(m, "PROTO=ESP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - eh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_esph), &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); - break; - } - /* Max length: 10 "PROTO 255 " */ - default: - sb_add(m, "PROTO=%u ", ih->protocol); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - sb_add(m, "UID=%u GID=%u ", - skb->sk->sk_socket->file->f_cred->fsuid, - skb->sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!iphoff && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); - - /* Proto Max log string length */ - /* IP: 40+46+6+11+127 = 230 */ - /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ - /* UDP: 10+max(25,20) = 35 */ - /* UDPLITE: 14+max(25,20) = 39 */ - /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ - /* ESP: 10+max(25)+15 = 50 */ - /* AH: 9+max(25)+15 = 49 */ - /* unknown: 10 */ - - /* (ICMP allows recursion one level deep) */ - /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ - /* maxlen = 230+ 91 + 230 + 252 = 803 */ -} - -static void dump_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & IPT_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int i; - - sb_add(m, "%02x", *p++); - for (i = 1; i < dev->hard_header_len; i++, p++) - sb_add(m, ":%02x", *p); - } - sb_add(m, " "); -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ipt_log_packet(u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge) { - const struct net_device *physindev; - const struct net_device *physoutdev; - - physindev = skb->nf_bridge->physindev; - if (physindev && in != physindev) - sb_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = skb->nf_bridge->physoutdev; - if (physoutdev && out != physoutdev) - sb_add(m, "PHYSOUT=%s ", physoutdev->name); - } -#endif - - if (in != NULL) - dump_mac_header(m, loginfo, skb); - - dump_packet(m, loginfo, skb, 0); - - sb_close(m); -} - -static unsigned int -log_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, par->out, &li, - loginfo->prefix); - return XT_CONTINUE; -} - -static int log_tg_check(const struct xt_tgchk_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - - if (loginfo->level >= 8) { - pr_debug("level %u >= 8\n", loginfo->level); - return -EINVAL; - } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("prefix is not null-terminated\n"); - return -EINVAL; - } - return 0; -} - -static struct xt_target log_tg_reg __read_mostly = { - .name = "LOG", - .family = NFPROTO_IPV4, - .target = log_tg, - .targetsize = sizeof(struct ipt_log_info), - .checkentry = log_tg_check, - .me = THIS_MODULE, -}; - -static struct nf_logger ipt_log_logger __read_mostly = { - .name = "ipt_LOG", - .logfn = &ipt_log_packet, - .me = THIS_MODULE, -}; - -static int __init log_tg_init(void) -{ - int ret; - - ret = xt_register_target(&log_tg_reg); - if (ret < 0) - return ret; - nf_log_register(NFPROTO_IPV4, &ipt_log_logger); - return 0; -} - -static void __exit log_tg_exit(void) -{ - nf_log_unregister(&ipt_log_logger); - xt_unregister_target(&log_tg_reg); -} - -module_init(log_tg_init); -module_exit(log_tg_exit); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 0e58f09e59f..851acec852d 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -52,7 +52,7 @@ iptable_filter_hook(unsigned int hook, struct sk_buff *skb, static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ -static bool forward = NF_ACCEPT; +static bool forward = true; module_param(forward, bool, 0000); static int __net_init iptable_filter_net_init(struct net *net) @@ -64,7 +64,7 @@ static int __net_init iptable_filter_net_init(struct net *net) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ipt_standard *)repl->entries)[1].target.verdict = - -forward - 1; + forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; net->ipv4.iptable_filter = ipt_register_table(net, &packet_filter, repl); @@ -88,11 +88,6 @@ static int __init iptable_filter_init(void) { int ret; - if (forward < 0 || forward > NF_MAX_VERDICT) { - pr_err("iptables forward must be 0 or 1\n"); - return -EINVAL; - } - ret = register_pernet_subsys(&iptable_filter_net_ops); if (ret < 0) return ret; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index de9da21113a..91747d4ebc2 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -74,16 +74,24 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (iph == NULL) - return -NF_DROP; + return -NF_ACCEPT; /* Conntrack defragments packets, we might still see fragments * inside ICMP packets though. */ if (iph->frag_off & htons(IP_OFFSET)) - return -NF_DROP; + return -NF_ACCEPT; *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; + /* Check bogus IP headers */ + if (*dataoff > skb->len) { + pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: " + "nhoff %u, ihl %u, skblen %u\n", + nhoff, iph->ihl << 2, skb->len); + return -NF_ACCEPT; + } + return NF_ACCEPT; } @@ -303,8 +311,9 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - NLA_PUT_BE32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip); - NLA_PUT_BE32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip); + if (nla_put_be32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || + nla_put_be32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) + goto nla_put_failure; return 0; nla_put_failure: @@ -356,7 +365,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .nla_policy = ipv4_nla_policy, #endif #if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - .ctl_table_path = nf_net_ipv4_netfilter_sysctl_path, + .ctl_table_path = "net/ipv4/netfilter", .ctl_table = ip_ct_sysctl_table, #endif .me = THIS_MODULE, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index ab5b27a2916..0847e373d33 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -75,25 +75,31 @@ static int icmp_print_tuple(struct seq_file *s, ntohs(tuple->src.u.icmp.id)); } +static unsigned int *icmp_get_timeouts(struct net *net) +{ + return &nf_ct_icmp_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ static int icmp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeout) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, @@ -222,10 +228,10 @@ icmp_error(struct net *net, struct nf_conn *tmpl, static int icmp_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { - NLA_PUT_BE16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id); - NLA_PUT_U8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type); - NLA_PUT_U8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code); - + if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; return 0; nla_put_failure: @@ -263,6 +269,44 @@ static int icmp_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; + } else { + /* Set default ICMP timeout. */ + *timeout = nf_ct_icmp_timeout; + } + return 0; +} + +static int +icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { + [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *icmp_sysctl_header; static struct ctl_table icmp_sysctl_table[] = { @@ -298,6 +342,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .invert_tuple = icmp_invert_tuple, .print_tuple = icmp_print_tuple, .packet = icmp_packet, + .get_timeouts = icmp_get_timeouts, .new = icmp_new, .error = icmp_error, .destroy = NULL, @@ -308,6 +353,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmp_timeout_nlattr_to_obj, + .obj_to_nlattr = icmp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &icmp_sysctl_header, .ctl_table = icmp_sysctl_table, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index a708933dc23..abb52adf5ac 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -686,6 +686,11 @@ static struct pernet_operations nf_nat_net_ops = { .exit = nf_nat_net_exit, }; +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + static int __init nf_nat_init(void) { size_t i; @@ -717,6 +722,8 @@ static int __init nf_nat_init(void) l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); + nf_ct_helper_expectfn_register(&follow_master_nat); + BUG_ON(nf_nat_seq_adjust_hook != NULL); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); @@ -736,6 +743,7 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_l3proto_put(l3proto); nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); RCU_INIT_POINTER(nf_ct_nat_offset, NULL); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index dc1dd912baf..cad29c12131 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -42,9 +42,7 @@ static int set_addr(struct sk_buff *skb, if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: nf_nat_mangle_tcp_packet" - " error\n"); + net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_tcp_packet error\n"); return -1; } @@ -58,9 +56,7 @@ static int set_addr(struct sk_buff *skb, if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: nf_nat_mangle_udp_packet" - " error\n"); + net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n"); return -1; } /* nf_nat_mangle_udp_packet uses skb_make_writable() to copy @@ -214,8 +210,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /* Run out of expectations */ if (i >= H323_RTP_CHANNEL_MAX) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of expectations\n"); + net_notice_ratelimited("nf_nat_h323: out of expectations\n"); return 0; } @@ -244,8 +239,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of RTP ports\n"); + net_notice_ratelimited("nf_nat_h323: out of RTP ports\n"); return 0; } @@ -308,8 +302,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_h323: out of TCP ports\n"); return 0; } @@ -365,8 +358,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_q931: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; } @@ -456,8 +448,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_ras: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_ras: out of TCP ports\n"); return 0; } @@ -545,8 +536,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_q931: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; } @@ -568,6 +558,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, return 0; } +static struct nf_ct_helper_expectfn q931_nat = { + .name = "Q.931", + .expectfn = ip_nat_q931_expect, +}; + +static struct nf_ct_helper_expectfn callforwarding_nat = { + .name = "callforwarding", + .expectfn = ip_nat_callforwarding_expect, +}; + /****************************************************************************/ static int __init init(void) { @@ -590,6 +590,8 @@ static int __init init(void) RCU_INIT_POINTER(nat_h245_hook, nat_h245); RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding); RCU_INIT_POINTER(nat_q931_hook, nat_q931); + nf_ct_helper_expectfn_register(&q931_nat); + nf_ct_helper_expectfn_register(&callforwarding_nat); return 0; } @@ -605,6 +607,8 @@ static void __exit fini(void) RCU_INIT_POINTER(nat_h245_hook, NULL); RCU_INIT_POINTER(nat_callforwarding_hook, NULL); RCU_INIT_POINTER(nat_q931_hook, NULL); + nf_ct_helper_expectfn_unregister(&q931_nat); + nf_ct_helper_expectfn_unregister(&callforwarding_nat); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index d0319f96269..ea4a23813d2 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -283,7 +283,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, __be32 newip; u_int16_t port; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; - unsigned buflen; + unsigned int buflen; /* Connection will come from reply */ if (ct->tuplehash[dir].tuple.src.u3.ip == ct->tuplehash[!dir].tuple.dst.u3.ip) @@ -526,6 +526,11 @@ err1: return NF_DROP; } +static struct nf_ct_helper_expectfn sip_nat = { + .name = "sip", + .expectfn = ip_nat_sip_expected, +}; + static void __exit nf_nat_sip_fini(void) { RCU_INIT_POINTER(nf_nat_sip_hook, NULL); @@ -535,6 +540,7 @@ static void __exit nf_nat_sip_fini(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); + nf_ct_helper_expectfn_unregister(&sip_nat); synchronize_rcu(); } @@ -554,6 +560,7 @@ static int __init nf_nat_sip_init(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); + nf_ct_helper_expectfn_register(&sip_nat); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 2133c30a4a5..746edec8b86 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1206,8 +1206,7 @@ static int snmp_translate(struct nf_conn *ct, if (!snmp_parse_mangle((unsigned char *)udph + sizeof(struct udphdr), paylen, &map, &udph->check)) { - if (net_ratelimit()) - printk(KERN_WARNING "bsalg: parser failed\n"); + net_warn_ratelimited("bsalg: parser failed\n"); return NF_DROP; } return NF_ACCEPT; @@ -1241,9 +1240,8 @@ static int help(struct sk_buff *skb, unsigned int protoff, * can mess around with the payload. */ if (ntohs(udph->len) != skb->len - (iph->ihl << 2)) { - if (net_ratelimit()) - printk(KERN_WARNING "SNMP: dropping malformed packet src=%pI4 dst=%pI4\n", - &iph->saddr, &iph->daddr); + net_warn_ratelimited("SNMP: dropping malformed packet src=%pI4 dst=%pI4\n", + &iph->saddr, &iph->daddr); return NF_DROP; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b072386cee2..2c00e8bf684 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -20,7 +20,6 @@ * */ -#include <asm/system.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/fcntl.h> @@ -52,15 +51,16 @@ static struct ping_table ping_table; static u16 ping_port_rover; -static inline int ping_hashfn(struct net *net, unsigned num, unsigned mask) +static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int mask) { int res = (num + net_hash_mix(net)) & mask; + pr_debug("hash(%d) = %d\n", num, res); return res; } static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, - struct net *net, unsigned num) + struct net *net, unsigned int num) { return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; } @@ -156,7 +156,7 @@ static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr, struct hlist_nulls_node *hnode; pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", - (int)ident, &daddr, dif); + (int)ident, &daddr, dif); read_lock_bh(&ping_table.lock); ping_portaddr_for_each_entry(sk, hnode, hslot) { @@ -189,7 +189,8 @@ static void inet_get_ping_group_range_net(struct net *net, gid_t *low, gid_t *high) { gid_t *data = net->ipv4.sysctl_ping_group_range; - unsigned seq; + unsigned int seq; + do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -206,17 +207,22 @@ static int ping_init_sock(struct sock *sk) gid_t range[2]; struct group_info *group_info = get_current_groups(); int i, j, count = group_info->ngroups; + kgid_t low, high; inet_get_ping_group_range_net(net, range, range+1); + low = make_kgid(&init_user_ns, range[0]); + high = make_kgid(&init_user_ns, range[1]); + if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low)) + return -EACCES; + if (range[0] <= group && group <= range[1]) return 0; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); - for (j = 0; j < cp_count; j++) { - group = group_info->blocks[i][j]; - if (range[0] <= group && group <= range[1]) + kgid_t gid = group_info->blocks[i][j]; + if (gid_lte(low, gid) && gid_lte(gid, high)) return 0; } @@ -229,7 +235,7 @@ static int ping_init_sock(struct sock *sk) static void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", - inet_sk(sk), inet_sk(sk)->inet_num); + inet_sk(sk), inet_sk(sk)->inet_num); pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter); sk_common_release(sk); @@ -252,7 +258,7 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EINVAL; pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n", - sk, addr->sin_addr.s_addr, ntohs(addr->sin_port)); + sk, addr->sin_addr.s_addr, ntohs(addr->sin_port)); chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) @@ -280,9 +286,9 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n", - (int)isk->inet_num, - &isk->inet_rcv_saddr, - (int)sk->sk_bound_dev_if); + (int)isk->inet_num, + &isk->inet_rcv_saddr, + (int)sk->sk_bound_dev_if); err = 0; if (isk->inet_rcv_saddr) @@ -335,7 +341,7 @@ void ping_err(struct sk_buff *skb, u32 info) return; pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type, - code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); + code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); sk = ping_v4_lookup(net, iph->daddr, iph->saddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); @@ -411,7 +417,7 @@ struct pingfakehdr { __wsum wcheck; }; -static int ping_getfrag(void *from, char * to, +static int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *skb) { struct pingfakehdr *pfh = (struct pingfakehdr *)from; @@ -556,7 +562,8 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, @@ -678,7 +685,7 @@ out: static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", - inet_sk(sk), inet_sk(sk)->inet_num, skb); + inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); @@ -704,7 +711,7 @@ void ping_rcv(struct sk_buff *skb) /* We assume the packet has already been checked by icmp_rcv */ pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n", - skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); + skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); /* Push ICMP header back */ skb_push(skb, skb->data - (u8 *)icmph); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6afc807ee2a..8af0d44e4e2 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -256,6 +256,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES), SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP), + SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL), + SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 3ccda5ae8a2..4032b818f3e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -288,7 +288,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_unlock(&raw_v4_hashinfo.lock); } -static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) +static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { /* Charge it to the socket. */ @@ -491,11 +491,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_namelen < sizeof(*usin)) goto out; if (usin->sin_family != AF_INET) { - static int complained; - if (!complained++) - printk(KERN_INFO "%s forgot to set AF_INET in " - "raw sendmsg. Fix it!\n", - current->comm); + pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n", + __func__, current->comm); err = -EAFNOSUPPORT; if (usin->sin_family) goto out; @@ -563,7 +560,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 01977479617..98b30d08efe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -62,9 +62,10 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv4: " fmt + #include <linux/module.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> @@ -108,6 +109,7 @@ #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> +#include <linux/kmemleak.h> #endif #include <net/secure_seq.h> @@ -228,7 +230,7 @@ const __u8 ip_tos2prio[16] = { TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; - +EXPORT_SYMBOL(ip_tos2prio); /* * Route cache. @@ -295,7 +297,7 @@ static inline void rt_hash_lock_init(void) #endif static struct rt_hash_bucket *rt_hash_table __read_mostly; -static unsigned rt_hash_mask __read_mostly; +static unsigned int rt_hash_mask __read_mostly; static unsigned int rt_hash_log __read_mostly; static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); @@ -958,8 +960,7 @@ void rt_cache_flush_batch(struct net *net) static void rt_emergency_hash_rebuild(struct net *net) { - if (net_ratelimit()) - printk(KERN_WARNING "Route hash chain too long!\n"); + net_warn_ratelimited("Route hash chain too long!\n"); rt_cache_invalidate(net); } @@ -1082,8 +1083,7 @@ static int rt_garbage_collect(struct dst_ops *ops) goto out; if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size) goto out; - if (net_ratelimit()) - printk(KERN_WARNING "dst cache overflow\n"); + net_warn_ratelimited("dst cache overflow\n"); RT_CACHE_STAT_INC(gc_dst_overflow); return 1; @@ -1116,12 +1116,17 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo static const __be32 inaddr_any = 0; struct net_device *dev = dst->dev; const __be32 *pkey = daddr; + const struct rtable *rt; struct neighbour *n; + rt = (const struct rtable *) dst; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) pkey = &inaddr_any; + else if (rt->rt_gateway) + pkey = (const __be32 *) &rt->rt_gateway; - n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey); + n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey); if (n) return n; return neigh_create(&arp_tbl, pkey, dev); @@ -1137,7 +1142,7 @@ static int rt_bind_neighbour(struct rtable *rt) return 0; } -static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt, +static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt, struct sk_buff *skb, int ifindex) { struct rtable *rth, *cand; @@ -1175,9 +1180,7 @@ restart: if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = rt_bind_neighbour(rt); if (err) { - if (net_ratelimit()) - printk(KERN_WARNING - "Neighbour table failure & not caching routes.\n"); + net_warn_ratelimited("Neighbour table failure & not caching routes\n"); ip_rt_put(rt); return ERR_PTR(err); } @@ -1253,7 +1256,7 @@ restart: struct net *net = dev_net(rt->dst.dev); int num = ++net->ipv4.current_rt_cache_rebuild_count; if (!rt_caching(net)) { - printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n", + pr_warn("%s: %d rebuilds is over limit, route caching disabled\n", rt->dst.dev->name, num); } rt_emergency_hash_rebuild(net); @@ -1293,8 +1296,7 @@ restart: goto restart; } - if (net_ratelimit()) - printk(KERN_WARNING "ipv4: Neighbour table overflow.\n"); + net_warn_ratelimited("Neighbour table overflow\n"); rt_drop(rt); return ERR_PTR(-ENOBUFS); } @@ -1372,14 +1374,13 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) return; } } else if (!rt) - printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", - __builtin_return_address(0)); + pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0)); ip_select_fb_ident(iph); } EXPORT_SYMBOL(__ip_select_ident); -static void rt_del(unsigned hash, struct rtable *rt) +static void rt_del(unsigned int hash, struct rtable *rt) { struct rtable __rcu **rthp; struct rtable *aux; @@ -1497,11 +1498,11 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.\n" - " Advised path = %pI4 -> %pI4\n", - &old_gw, dev->name, &new_gw, - &saddr, &daddr); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" + " Advised path = %pI4 -> %pI4\n", + &old_gw, dev->name, &new_gw, + &saddr, &daddr); #endif ; } @@ -1533,7 +1534,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) ip_rt_put(rt); ret = NULL; } else if (rt->rt_flags & RTCF_REDIRECTED) { - unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, + unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, rt->rt_oif, rt_genid(dev_net(dst->dev))); rt_del(hash, rt); @@ -1611,11 +1612,10 @@ void ip_rt_send_redirect(struct sk_buff *skb) ++peer->rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number && - net_ratelimit()) - printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", - &ip_hdr(skb)->saddr, rt->rt_iif, - &rt->rt_dst, &rt->rt_gateway); + peer->rate_tokens == ip_rt_redirect_number) + net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", + &ip_hdr(skb)->saddr, rt->rt_iif, + &rt->rt_dst, &rt->rt_gateway); #endif } } @@ -1838,9 +1838,9 @@ static void ipv4_link_failure(struct sk_buff *skb) static int ip_rt_bug(struct sk_buff *skb) { - printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n", - &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, - skb->dev ? skb->dev->name : "?"); + pr_debug("%s: %pI4 -> %pI4, %s\n", + __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, + skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; @@ -2036,7 +2036,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err < 0) goto e_err; } - rth = rt_dst_alloc(init_net.loopback_dev, + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; @@ -2100,18 +2100,13 @@ static void ip_handle_martian_source(struct net_device *dev, * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ - printk(KERN_WARNING "martian source %pI4 from %pI4, on dev %s\n", + pr_warn("martian source %pI4 from %pI4, on dev %s\n", &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { - int i; - const unsigned char *p = skb_mac_header(skb); - printk(KERN_WARNING "ll header: "); - for (i = 0; i < dev->hard_header_len; i++, p++) { - printk("%02x", *p); - if (i < (dev->hard_header_len - 1)) - printk(":"); - } - printk("\n"); + print_hex_dump(KERN_WARNING, "ll header: ", + DUMP_PREFIX_OFFSET, 16, 1, + skb_mac_header(skb), + dev->hard_header_len, true); } } #endif @@ -2134,9 +2129,7 @@ static int __mkroute_input(struct sk_buff *skb, /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); if (out_dev == NULL) { - if (net_ratelimit()) - printk(KERN_CRIT "Bug in ip_route_input" \ - "_slow(). Please, report\n"); + net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } @@ -2216,9 +2209,9 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable* rth = NULL; + struct rtable *rth = NULL; int err; - unsigned hash; + unsigned int hash; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) @@ -2256,13 +2249,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct flowi4 fl4; - unsigned flags = 0; + unsigned int flags = 0; u32 itag = 0; - struct rtable * rth; - unsigned hash; + struct rtable *rth; + unsigned int hash; __be32 spec_dst; int err = -EINVAL; - struct net * net = dev_net(dev); + struct net *net = dev_net(dev); /* IP on this device is disabled. */ @@ -2407,9 +2400,9 @@ no_route: martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n", - &daddr, &saddr, dev->name); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", + &daddr, &saddr, dev->name); #endif e_hostunreach: @@ -2434,8 +2427,8 @@ martian_source_keep_err: int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, bool noref) { - struct rtable * rth; - unsigned hash; + struct rtable *rth; + unsigned int hash; int iif = dev->ifindex; struct net *net; int res; @@ -2973,7 +2966,8 @@ static int rt_fill_info(struct net *net, r->rtm_src_len = 0; r->rtm_tos = rt->rt_key_tos; r->rtm_table = RT_TABLE_MAIN; - NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); + if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) + goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; @@ -2981,31 +2975,38 @@ static int rt_fill_info(struct net *net, if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst); - + if (nla_put_be32(skb, RTA_DST, rt->rt_dst)) + goto nla_put_failure; if (rt->rt_key_src) { r->rtm_src_len = 32; - NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src); + if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src)) + goto nla_put_failure; } - if (rt->dst.dev) - NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); + if (rt->dst.dev && + nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (rt->dst.tclassid) - NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); + if (rt->dst.tclassid && + nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) + goto nla_put_failure; #endif - if (rt_is_input_route(rt)) - NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); - else if (rt->rt_src != rt->rt_key_src) - NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src); - - if (rt->rt_dst != rt->rt_gateway) - NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); + if (rt_is_input_route(rt)) { + if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst)) + goto nla_put_failure; + } else if (rt->rt_src != rt->rt_key_src) { + if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src)) + goto nla_put_failure; + } + if (rt->rt_dst != rt->rt_gateway && + nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) + goto nla_put_failure; if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - if (rt->rt_mark) - NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark); + if (rt->rt_mark && + nla_put_be32(skb, RTA_MARK, rt->rt_mark)) + goto nla_put_failure; error = rt->dst.error; if (peer) { @@ -3046,7 +3047,8 @@ static int rt_fill_info(struct net *net, } } else #endif - NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif); + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage, @@ -3060,7 +3062,7 @@ nla_put_failure: return -EMSGSIZE; } -static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(in_skb->sk); struct rtmsg *rtm; @@ -3335,23 +3337,6 @@ static ctl_table ipv4_route_table[] = { { } }; -static struct ctl_table empty[1]; - -static struct ctl_table ipv4_skeleton[] = -{ - { .procname = "route", - .mode = 0555, .child = ipv4_route_table}, - { .procname = "neigh", - .mode = 0555, .child = empty}, - { } -}; - -static __net_initdata struct ctl_path ipv4_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; - static struct ctl_table ipv4_route_flush_table[] = { { .procname = "flush", @@ -3362,13 +3347,6 @@ static struct ctl_table ipv4_route_flush_table[] = { { }, }; -static __net_initdata struct ctl_path ipv4_route_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "route", }, - { }, -}; - static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; @@ -3381,8 +3359,7 @@ static __net_init int sysctl_route_net_init(struct net *net) } tbl[0].extra1 = net; - net->ipv4.route_hdr = - register_net_sysctl_table(net, ipv4_route_path, tbl); + net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); if (net->ipv4.route_hdr == NULL) goto err_reg; return 0; @@ -3431,9 +3408,15 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; static __initdata unsigned long rhash_entries; static int __init set_rhash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - rhash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &rhash_entries); + if (ret) + return 0; + return 1; } __setup("rhash_entries=", set_rhash_entries); @@ -3469,6 +3452,7 @@ int __init ip_rt_init(void) 0, &rt_hash_log, &rt_hash_mask, + 0, rhash_entries ? 0 : 512 * 1024); memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); rt_hash_lock_init(); @@ -3485,7 +3469,7 @@ int __init ip_rt_init(void) net_random() % ip_rt_gc_interval + ip_rt_gc_interval); if (ip_rt_proc_init()) - printk(KERN_ERR "Unable to create route proc files\n"); + pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(ip_rt_max_size); @@ -3506,6 +3490,6 @@ int __init ip_rt_init(void) */ void __init ip_static_sysctl_init(void) { - register_sysctl_paths(ipv4_path, ipv4_skeleton); + register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7a7724da9bf..ef32956ed65 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include <net/tcp_memcontrol.h> static int zero; +static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -78,7 +79,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) { gid_t *data = table->data; - unsigned seq; + unsigned int seq; do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -677,6 +678,15 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_early_retrans", + .data = &sysctl_tcp_early_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -768,13 +778,6 @@ static struct ctl_table ipv4_net_table[] = { { } }; -struct ctl_path net_ipv4_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; -EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); - static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; @@ -815,8 +818,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) tcp_init_mem(net); - net->ipv4.ipv4_hdr = register_net_sysctl_table(net, - net_ipv4_ctl_path, table); + net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; @@ -857,12 +859,12 @@ static __init int sysctl_ipv4_init(void) if (!i->procname) return -EINVAL; - hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table); + hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); if (hdr == NULL) return -ENOMEM; if (register_pernet_subsys(&ipv4_sysctl_ops)) { - unregister_sysctl_table(hdr); + unregister_net_sysctl_table(hdr); return -ENOMEM; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 22ef5f9fd2f..3ba605f60e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -245,6 +245,8 @@ * TCP_CLOSE socket is finished */ +#define pr_fmt(fmt) "TCP: " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -361,6 +363,71 @@ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) return period; } +/* Address-family independent initialization for a tcp_sock. + * + * NOTE: A lot of things set to zero explicitly by call to + * sk_alloc() so need not be done here. + */ +void tcp_init_sock(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + skb_queue_head_init(&tp->out_of_order_queue); + tcp_init_xmit_timers(sk); + tcp_prequeue_init(tp); + + icsk->icsk_rto = TCP_TIMEOUT_INIT; + tp->mdev = TCP_TIMEOUT_INIT; + + /* So many TCP implementations out there (incorrectly) count the + * initial SYN frame in their delayed-ACK and congestion control + * algorithms that we must have the following bandaid to talk + * efficiently to them. -DaveM + */ + tp->snd_cwnd = TCP_INIT_CWND; + + /* See draft-stevens-tcpca-spec-01 for discussion of the + * initialization of these values. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tp->snd_cwnd_clamp = ~0; + tp->mss_cache = TCP_MSS_DEFAULT; + + tp->reordering = sysctl_tcp_reordering; + tcp_enable_early_retrans(tp); + icsk->icsk_ca_ops = &tcp_init_congestion_ops; + + sk->sk_state = TCP_CLOSE; + + sk->sk_write_space = sk_stream_write_space; + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + icsk->icsk_sync_mss = tcp_sync_mss; + + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ + sk->sk_sndbuf = sysctl_tcp_wmem[1]; + sk->sk_rcvbuf = sysctl_tcp_rmem[1]; + + local_bh_disable(); + sock_update_memcg(sk); + sk_sockets_allocated_inc(sk); + local_bh_enable(); +} +EXPORT_SYMBOL(tcp_init_sock); + /* * Wait for a TCP event. * @@ -526,7 +593,7 @@ static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) tp->pushed_seq = tp->write_seq; } -static inline int forced_push(const struct tcp_sock *tp) +static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } @@ -699,11 +766,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); if (skb) { if (sk_wmem_schedule(sk, skb->truesize)) { + skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb_reserve(skb, skb_tailroom(skb) - size); + skb->avail_size = size; return skb; } __kfree_skb(skb); @@ -781,9 +849,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse while (psize > 0) { struct sk_buff *skb = tcp_write_queue_tail(sk); struct page *page = pages[poffset / PAGE_SIZE]; - int copy, i, can_coalesce; + int copy, i; int offset = poffset % PAGE_SIZE; int size = min_t(size_t, psize, PAGE_SIZE - offset); + bool can_coalesce; if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) { new_segment: @@ -848,8 +917,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -858,7 +926,7 @@ wait_for_memory: } out: - if (copied) + if (copied && !(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle); return copied; @@ -916,7 +984,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int iovlen, flags, err, copied; - int mss_now, size_goal; + int mss_now = 0, size_goal; bool sg; long timeo; @@ -930,6 +998,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_err; + if (unlikely(tp->repair)) { + if (tp->repair_queue == TCP_RECV_QUEUE) { + copied = tcp_send_rcvq(sk, msg, size); + goto out; + } + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) + goto out_err; + + /* 'common' sending to sendq */ + } + /* This should be in poll */ clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -993,15 +1074,14 @@ new_segment: copy = seglen; /* Where to copy to? */ - if (skb_tailroom(skb) > 0) { + if (skb_availroom(skb) > 0) { /* We have some space in skb head. Superb! */ - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, from, copy); if (err) goto do_fault; } else { - int merge = 0; + bool merge = false; int i = skb_shinfo(skb)->nr_frags; struct page *page = sk->sk_sndmsg_page; int off; @@ -1015,7 +1095,7 @@ new_segment: off != PAGE_SIZE) { /* We can extend the last page * fragment. */ - merge = 1; + merge = true; } else if (i == MAX_SKB_FRAGS || !sg) { /* Need to add new fragment and cannot * do this because interface is non-SG, @@ -1087,7 +1167,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < max || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { @@ -1100,7 +1180,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) + if (copied && likely(!tp->repair)) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) @@ -1111,7 +1191,7 @@ wait_for_memory: } out: - if (copied) + if (copied && likely(!tp->repair)) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); return copied; @@ -1185,6 +1265,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) return -EAGAIN; } +static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) +{ + struct sk_buff *skb; + int copied = 0, err = 0; + + /* XXX -- need to support SO_PEEK_OFF */ + + skb_queue_walk(&sk->sk_write_queue, skb) { + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len); + if (err) + break; + + copied += skb->len; + } + + return err ?: copied; +} + /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the @@ -1194,7 +1292,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); - int time_to_ack = 0; + bool time_to_ack = false; struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); @@ -1220,7 +1318,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !icsk->icsk_ack.pingpong)) && !atomic_read(&sk->sk_rmem_alloc))) - time_to_ack = 1; + time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window @@ -1242,7 +1340,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) - time_to_ack = 1; + time_to_ack = true; } } if (time_to_ack) @@ -1374,11 +1472,11 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } if (tcp_hdr(skb)->fin) { - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); ++seq; break; } - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); if (!desc->count) break; tp->copied_seq = seq; @@ -1414,7 +1512,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - int copied_early = 0; + bool copied_early = false; struct sk_buff *skb; u32 urg_hole = 0; @@ -1430,6 +1528,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto recv_urg; + if (unlikely(tp->repair)) { + err = -EPERM; + if (!(flags & MSG_PEEK)) + goto out; + + if (tp->repair_queue == TCP_SEND_QUEUE) + goto recv_sndq; + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) + goto out; + + /* 'common' recv queue MSG_PEEK-ing */ + } + seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_seq = tp->copied_seq; @@ -1450,7 +1563,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((available < target) && (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && !sysctl_tcp_low_latency && - dma_find_channel(DMA_MEMCPY)) { + net_dma_find_channel()) { preempt_enable_no_resched(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); @@ -1631,9 +1744,9 @@ do_prequeue: } if ((flags & MSG_PEEK) && (peek_seq - copied - urg_hole != tp->copied_seq)) { - if (net_ratelimit()) - printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n", - current->comm, task_pid_nr(current)); + net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", + current->comm, + task_pid_nr(current)); peek_seq = tp->copied_seq; } continue; @@ -1665,7 +1778,7 @@ do_prequeue: if (!(flags & MSG_TRUNC)) { #ifdef CONFIG_NET_DMA if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) { tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec( @@ -1675,7 +1788,8 @@ do_prequeue: if (tp->ucopy.dma_cookie < 0) { - printk(KERN_ALERT "dma_cookie < 0\n"); + pr_alert("%s: dma_cookie < 0\n", + __func__); /* Exception. Bailout! */ if (!copied) @@ -1686,7 +1800,7 @@ do_prequeue: dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); if ((offset + used) == skb->len) - copied_early = 1; + copied_early = true; } else #endif @@ -1720,7 +1834,7 @@ skip_copy: goto found_fin_ok; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } continue; @@ -1729,7 +1843,7 @@ skip_copy: ++*seq; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } break; } while (len > 0); @@ -1780,6 +1894,10 @@ out: recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; + +recv_sndq: + err = tcp_peek_sndq(sk, msg, len); + goto out; } EXPORT_SYMBOL(tcp_recvmsg); @@ -1883,10 +2001,10 @@ bool tcp_check_oom(struct sock *sk, int shift) too_many_orphans = tcp_too_many_orphans(sk, shift); out_of_socket_memory = tcp_out_of_memory(sk); - if (too_many_orphans && net_ratelimit()) - pr_info("TCP: too many orphaned sockets\n"); - if (out_of_socket_memory && net_ratelimit()) - pr_info("TCP: out of memory -- consider tuning tcp_mem\n"); + if (too_many_orphans) + net_info_ratelimited("too many orphaned sockets\n"); + if (out_of_socket_memory) + net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } @@ -1932,7 +2050,9 @@ void tcp_close(struct sock *sk, long timeout) * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ - if (data_was_unread) { + if (unlikely(tcp_sk(sk)->repair)) { + sk->sk_prot->disconnect(sk, 0); + } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); @@ -2050,7 +2170,7 @@ EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ -static inline int tcp_need_reset(int state) +static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | @@ -2071,6 +2191,8 @@ int tcp_disconnect(struct sock *sk, int flags) /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); + } else if (unlikely(tp->repair)) { + sk->sk_err = ECONNABORTED; } else if (tcp_need_reset(old_state) || (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { @@ -2122,6 +2244,54 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); +static inline bool tcp_can_repair_sock(const struct sock *sk) +{ + return capable(CAP_NET_ADMIN) && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); +} + +static int tcp_repair_options_est(struct tcp_sock *tp, + struct tcp_repair_opt __user *optbuf, unsigned int len) +{ + struct tcp_repair_opt opt; + + while (len >= sizeof(opt)) { + if (copy_from_user(&opt, optbuf, sizeof(opt))) + return -EFAULT; + + optbuf++; + len -= sizeof(opt); + + switch (opt.opt_code) { + case TCPOPT_MSS: + tp->rx_opt.mss_clamp = opt.opt_val; + break; + case TCPOPT_WINDOW: + if (opt.opt_val > 14) + return -EFBIG; + + tp->rx_opt.snd_wscale = opt.opt_val; + break; + case TCPOPT_SACK_PERM: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.sack_ok |= TCP_SACK_SEEN; + if (sysctl_tcp_fack) + tcp_enable_fack(tp); + break; + case TCPOPT_TIMESTAMP: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.tstamp_ok = 1; + break; + } + } + + return 0; +} + /* * Socket option code for TCP. */ @@ -2292,6 +2462,55 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EINVAL; else tp->thin_dupack = val; + if (tp->thin_dupack) + tcp_disable_early_retrans(tp); + break; + + case TCP_REPAIR: + if (!tcp_can_repair_sock(sk)) + err = -EPERM; + else if (val == 1) { + tp->repair = 1; + sk->sk_reuse = SK_FORCE_REUSE; + tp->repair_queue = TCP_NO_QUEUE; + } else if (val == 0) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; + tcp_send_window_probe(sk); + } else + err = -EINVAL; + + break; + + case TCP_REPAIR_QUEUE: + if (!tp->repair) + err = -EPERM; + else if (val < TCP_QUEUES_NR) + tp->repair_queue = val; + else + err = -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (sk->sk_state != TCP_CLOSE) + err = -EPERM; + else if (tp->repair_queue == TCP_SEND_QUEUE) + tp->write_seq = val; + else if (tp->repair_queue == TCP_RECV_QUEUE) + tp->rcv_nxt = val; + else + err = -EINVAL; + break; + + case TCP_REPAIR_OPTIONS: + if (!tp->repair) + err = -EINVAL; + else if (sk->sk_state == TCP_ESTABLISHED) + err = tcp_repair_options_est(tp, + (struct tcp_repair_opt __user *)optval, + optlen); + else + err = -EPERM; break; case TCP_CORK: @@ -2527,6 +2746,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->mss_cache; if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; + if (tp->repair) + val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); @@ -2629,6 +2850,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->thin_dupack; break; + case TCP_REPAIR: + val = tp->repair; + break; + + case TCP_REPAIR_QUEUE: + if (tp->repair) + val = tp->repair_queue; + else + return -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (tp->repair_queue == TCP_SEND_QUEUE) + val = tp->write_seq; + else if (tp->repair_queue == TCP_RECV_QUEUE) + val = tp->rcv_nxt; + else + return -EINVAL; + break; + case TCP_USER_TIMEOUT: val = jiffies_to_msecs(icsk->icsk_user_timeout); break; @@ -2672,7 +2913,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; - unsigned thlen; + unsigned int thlen; unsigned int seq; __be32 delta; unsigned int oldlen; @@ -2930,13 +3171,13 @@ out_free: struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk) { struct tcp_md5sig_pool __percpu *pool; - int alloc = 0; + bool alloc = false; retry: spin_lock_bh(&tcp_md5sig_pool_lock); pool = tcp_md5sig_pool; if (tcp_md5sig_users++ == 0) { - alloc = 1; + alloc = true; spin_unlock_bh(&tcp_md5sig_pool_lock); } else if (!pool) { tcp_md5sig_users--; @@ -3030,9 +3271,9 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, struct scatterlist sg; const struct tcphdr *tp = tcp_hdr(skb); struct hash_desc *desc = &hp->md5_desc; - unsigned i; - const unsigned head_data_len = skb_headlen(skb) > header_len ? - skb_headlen(skb) - header_len : 0; + unsigned int i; + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); struct sk_buff *frag_iter; @@ -3220,9 +3461,15 @@ extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - thash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &thash_entries); + if (ret) + return 0; + return 1; } __setup("thash_entries=", set_thash_entries); @@ -3240,7 +3487,7 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int max_share, cnt; + int max_rshare, max_wshare, cnt; unsigned int i; unsigned long jiffy = jiffies; @@ -3267,6 +3514,7 @@ void __init tcp_init(void) 0, NULL, &tcp_hashinfo.ehash_mask, + 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); @@ -3283,6 +3531,7 @@ void __init tcp_init(void) 0, &tcp_hashinfo.bhash_size, NULL, + 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { @@ -3299,21 +3548,20 @@ void __init tcp_init(void) tcp_init_mem(&init_net); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); - limit = max(limit, 128UL); - max_share = min(4UL*1024*1024, limit); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); + max_wshare = min(4UL*1024*1024, limit); + max_rshare = min(6UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; sysctl_tcp_wmem[1] = 16*1024; - sysctl_tcp_wmem[2] = max(64*1024, max_share); + sysctl_tcp_wmem[2] = max(64*1024, max_wshare); sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; sysctl_tcp_rmem[1] = 87380; - sysctl_tcp_rmem[2] = max(87380, max_share); + sysctl_tcp_rmem[2] = max(87380, max_rshare); - printk(KERN_INFO "TCP: Hash tables configured " - "(established %u bind %u)\n", - tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); + pr_info("Hash tables configured (established %u bind %u)\n", + tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_register_congestion_control(&tcp_reno); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index fc6d475f488..04dbd7ae7c6 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -6,6 +6,8 @@ * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org> */ +#define pr_fmt(fmt) "TCP: " fmt + #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> @@ -41,18 +43,17 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) /* all algorithms must implement ssthresh and cong_avoid ops */ if (!ca->ssthresh || !ca->cong_avoid) { - printk(KERN_ERR "TCP %s does not implement required ops\n", - ca->name); + pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } spin_lock(&tcp_cong_list_lock); if (tcp_ca_find(ca->name)) { - printk(KERN_NOTICE "TCP %s already registered\n", ca->name); + pr_notice("%s already registered\n", ca->name); ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); - printk(KERN_INFO "TCP %s registered\n", ca->name); + pr_info("%s registered\n", ca->name); } spin_unlock(&tcp_cong_list_lock); @@ -279,19 +280,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) /* RFC2861 Check whether we are limited by application or congestion window * This is the inverse of cwnd check in tcp_tso_should_defer */ -int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) +bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) { const struct tcp_sock *tp = tcp_sk(sk); u32 left; if (in_flight >= tp->snd_cwnd) - return 1; + return true; left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && left * tp->mss_cache < sk->sk_gso_max_size) - return 1; + return true; return left <= tcp_max_tso_deferred_mss(tp); } EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited); diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index fe3ecf484b4..57bdd17dff4 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -15,7 +15,7 @@ /* Tcp Hybla structure. */ struct hybla { - u8 hybla_en; + bool hybla_en; u32 snd_cwnd_cents; /* Keeps increment values when it is <1, <<7 */ u32 rho; /* Rho parameter, integer part */ u32 rho2; /* Rho * Rho, integer part */ @@ -24,8 +24,7 @@ struct hybla { u32 minrtt; /* Minimum smoothed round trip time value seen */ }; -/* Hybla reference round trip time (default= 1/40 sec = 25 ms), - expressed in jiffies */ +/* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ static int rtt0 = 25; module_param(rtt0, int, 0644); MODULE_PARM_DESC(rtt0, "reference rout trip time (ms)"); @@ -39,7 +38,7 @@ static inline void hybla_recalc_param (struct sock *sk) ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; - ca->rho2 = ca->rho2_7ls >>7; + ca->rho2 = ca->rho2_7ls >> 7; } static void hybla_init(struct sock *sk) @@ -52,7 +51,7 @@ static void hybla_init(struct sock *sk) ca->rho_3ls = 0; ca->rho2_7ls = 0; ca->snd_cwnd_cents = 0; - ca->hybla_en = 1; + ca->hybla_en = true; tp->snd_cwnd = 2; tp->snd_cwnd_clamp = 65535; @@ -67,6 +66,7 @@ static void hybla_init(struct sock *sk) static void hybla_state(struct sock *sk, u8 ca_state) { struct hybla *ca = inet_csk_ca(sk); + ca->hybla_en = (ca_state == TCP_CA_Open); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b5e315f1364..b224eb8bce8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -61,6 +61,8 @@ * Pasi Sarolahti: F-RTO for dealing with spurious RTOs */ +#define pr_fmt(fmt) "TCP: " fmt + #include <linux/mm.h> #include <linux/slab.h> #include <linux/module.h> @@ -83,7 +85,7 @@ int sysctl_tcp_ecn __read_mostly = 2; EXPORT_SYMBOL(sysctl_tcp_ecn); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; -int sysctl_tcp_adv_win_scale __read_mostly = 2; +int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); int sysctl_tcp_stdurg __read_mostly; @@ -97,6 +99,7 @@ int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; int sysctl_tcp_abc __read_mostly; +int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@ -173,7 +176,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) static void tcp_incr_quickack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - unsigned quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); + unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); if (quickacks == 0) quickacks = 2; @@ -193,9 +196,10 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline int tcp_in_quickack_mode(const struct sock *sk) +static inline bool tcp_in_quickack_mode(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; } @@ -250,11 +254,11 @@ static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th) tp->ecn_flags &= ~TCP_ECN_OK; } -static inline int TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) +static bool TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) { if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK)) - return 1; - return 0; + return true; + return false; } /* Buffer size and advertised window tuning. @@ -333,6 +337,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) incr = __tcp_grow_window(sk, skb); if (incr) { + incr = max_t(int, incr, 2 * skb->len); tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp); inet_csk(sk)->icsk_ack.quick |= 1; @@ -472,8 +477,11 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) if (!win_dep) { m -= (new_sample >> 3); new_sample += m; - } else if (m < new_sample) - new_sample = m << 3; + } else { + m <<= 3; + if (m < new_sample) + new_sample = m; + } } else { /* No previous measure. */ new_sample = m << 3; @@ -489,7 +497,7 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - tcp_rcv_rtt_update(tp, jiffies - tp->rcv_rtt_est.time, 1); + tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1); new_measure: tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd; @@ -900,6 +908,7 @@ static void tcp_init_metrics(struct sock *sk) if (dst_metric(dst, RTAX_REORDERING) && tp->reordering != dst_metric(dst, RTAX_REORDERING)) { tcp_disable_fack(tp); + tcp_disable_early_retrans(tp); tp->reordering = dst_metric(dst, RTAX_REORDERING); } @@ -931,7 +940,7 @@ static void tcp_init_metrics(struct sock *sk) tcp_set_rto(sk); reset: if (tp->srtt == 0) { - /* RFC2988bis: We've failed to get a valid RTT sample from + /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious @@ -941,7 +950,7 @@ reset: inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been - * retransmitted. In light of RFC2988bis' more aggressive 1sec + * retransmitted. In light of RFC6298 more aggressive 1sec * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK * retransmission has occurred. */ @@ -973,15 +982,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric, NET_INC_STATS_BH(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 - printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n", - tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, - tp->reordering, - tp->fackets_out, - tp->sacked_out, - tp->undo_marker ? tp->undo_retrans : 0); + pr_debug("Disorder%d %d %u f%u s%u rr%d\n", + tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, + tp->reordering, + tp->fackets_out, + tp->sacked_out, + tp->undo_marker ? tp->undo_retrans : 0); #endif tcp_disable_fack(tp); } + + if (metric > 0) + tcp_disable_early_retrans(tp); } /* This must be called before lost_out is incremented */ @@ -1112,36 +1124,36 @@ static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, * the exact amount is rather hard to quantify. However, tp->max_window can * be used as an exaggerated estimate. */ -static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack, - u32 start_seq, u32 end_seq) +static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, + u32 start_seq, u32 end_seq) { /* Too far in future, or reversed (interpretation is ambiguous) */ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq)) - return 0; + return false; /* Nasty start_seq wrap-around check (see comments above) */ if (!before(start_seq, tp->snd_nxt)) - return 0; + return false; /* In outstanding window? ...This is valid exit for D-SACKs too. * start_seq == snd_una is non-sensical (see comments above) */ if (after(start_seq, tp->snd_una)) - return 1; + return true; if (!is_dsack || !tp->undo_marker) - return 0; + return false; /* ...Then it's D-SACK, and must reside below snd_una completely */ if (after(end_seq, tp->snd_una)) - return 0; + return false; if (!before(start_seq, tp->undo_marker)) - return 1; + return true; /* Too old */ if (!after(end_seq, tp->undo_marker)) - return 0; + return false; /* Undo_marker boundary crossing (overestimates a lot). Known already: * start_seq < undo_marker and end_seq >= undo_marker. @@ -1213,17 +1225,17 @@ static void tcp_mark_lost_retrans(struct sock *sk) tp->lost_retrans_low = new_low_seq; } -static int tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, - struct tcp_sack_block_wire *sp, int num_sacks, - u32 prior_snd_una) +static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, + struct tcp_sack_block_wire *sp, int num_sacks, + u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq); u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq); - int dup_sack = 0; + bool dup_sack = false; if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) { - dup_sack = 1; + dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKRECV); } else if (num_sacks > 1) { @@ -1232,7 +1244,7 @@ static int tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, if (!after(end_seq_0, end_seq_1) && !before(start_seq_0, start_seq_1)) { - dup_sack = 1; + dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV); @@ -1263,9 +1275,10 @@ struct tcp_sacktag_state { * FIXME: this could be merged to shift decision code */ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, - u32 start_seq, u32 end_seq) + u32 start_seq, u32 end_seq) { - int in_sack, err; + int err; + bool in_sack; unsigned int pkt_len; unsigned int mss; @@ -1311,7 +1324,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount) + bool dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1391,10 +1404,10 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, - struct tcp_sacktag_state *state, - unsigned int pcount, int shifted, int mss, - int dup_sack) +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_sacktag_state *state, + unsigned int pcount, int shifted, int mss, + bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); @@ -1444,7 +1457,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (skb->len > 0) { BUG_ON(!tcp_skb_pcount(skb)); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTED); - return 0; + return false; } /* Whole SKB was eaten :-) */ @@ -1467,7 +1480,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKMERGED); - return 1; + return true; } /* I wish gso_size would have a bit more sane initialization than @@ -1490,7 +1503,7 @@ static int skb_can_shift(const struct sk_buff *skb) static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, - int dup_sack) + bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev; @@ -1629,14 +1642,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, - int dup_sack_in) + bool dup_sack_in) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; tcp_for_write_queue_from(skb, sk) { int in_sack = 0; - int dup_sack = dup_sack_in; + bool dup_sack = dup_sack_in; if (skb == tcp_send_head(sk)) break; @@ -1651,7 +1664,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, next_dup->start_seq, next_dup->end_seq); if (in_sack > 0) - dup_sack = 1; + dup_sack = true; } /* skb reference here is a bit tricky to get right, since @@ -1756,7 +1769,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, struct sk_buff *skb; int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3); int used_sacks; - int found_dup_sack = 0; + bool found_dup_sack = false; int i, j; int first_sack_index; @@ -1787,7 +1800,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, used_sacks = 0; first_sack_index = 0; for (i = 0; i < num_sacks; i++) { - int dup_sack = !i && found_dup_sack; + bool dup_sack = !i && found_dup_sack; sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq); sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq); @@ -1854,7 +1867,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, while (i < used_sacks) { u32 start_seq = sp[i].start_seq; u32 end_seq = sp[i].end_seq; - int dup_sack = (found_dup_sack && (i == first_sack_index)); + bool dup_sack = (found_dup_sack && (i == first_sack_index)); struct tcp_sack_block *next_dup = NULL; if (found_dup_sack && ((i + 1) == first_sack_index)) @@ -1956,9 +1969,9 @@ out: } /* Limits sacked_out so that sum with lost_out isn't ever larger than - * packets_out. Returns zero if sacked_out adjustement wasn't necessary. + * packets_out. Returns false if sacked_out adjustement wasn't necessary. */ -static int tcp_limit_reno_sacked(struct tcp_sock *tp) +static bool tcp_limit_reno_sacked(struct tcp_sock *tp) { u32 holes; @@ -1967,9 +1980,9 @@ static int tcp_limit_reno_sacked(struct tcp_sock *tp) if ((tp->sacked_out + holes) > tp->packets_out) { tp->sacked_out = tp->packets_out - holes; - return 1; + return true; } - return 0; + return false; } /* If we receive more dupacks than we expected counting segments @@ -2023,40 +2036,40 @@ static int tcp_is_sackfrto(const struct tcp_sock *tp) /* F-RTO can only be used if TCP has never retransmitted anything other than * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here) */ -int tcp_use_frto(struct sock *sk) +bool tcp_use_frto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb; if (!sysctl_tcp_frto) - return 0; + return false; /* MTU probe and F-RTO won't really play nicely along currently */ if (icsk->icsk_mtup.probe_size) - return 0; + return false; if (tcp_is_sackfrto(tp)) - return 1; + return true; /* Avoid expensive walking of rexmit queue if possible */ if (tp->retrans_out > 1) - return 0; + return false; skb = tcp_write_queue_head(sk); if (tcp_skb_is_last(sk, skb)) - return 1; + return true; skb = tcp_write_queue_next(sk, skb); /* Skips head */ tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) break; if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - return 0; + return false; /* Short-circuit when first non-SACKed skb has been checked */ if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) break; } - return 1; + return true; } /* RTO occurred, but do not yet enter Loss state. Instead, defer RTO @@ -2292,7 +2305,7 @@ void tcp_enter_loss(struct sock *sk, int how) * * Do processing similar to RTO timeout. */ -static int tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int flag) { if (flag & FLAG_SACK_RENEGING) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2303,9 +2316,9 @@ static int tcp_check_sack_reneging(struct sock *sk, int flag) tcp_retransmit_skb(sk, tcp_write_queue_head(sk)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - return 1; + return true; } - return 0; + return false; } static inline int tcp_fackets_out(const struct tcp_sock *tp) @@ -2333,6 +2346,27 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } +static bool tcp_pause_early_retransmit(struct sock *sk, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned long delay; + + /* Delay early retransmit and entering fast recovery for + * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples + * available, or RTO is scheduled to fire first. + */ + if (sysctl_tcp_early_retrans < 2 || (flag & FLAG_ECE) || !tp->srtt) + return false; + + delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) + return false; + + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + tp->early_retrans_delayed = 1; + return true; +} + static inline int tcp_skb_timedout(const struct sock *sk, const struct sk_buff *skb) { @@ -2440,28 +2474,28 @@ static inline int tcp_head_timedout(const struct sock *sk) * Main question: may we further continue forward transmission * with the same cwnd? */ -static int tcp_time_to_recover(struct sock *sk) +static bool tcp_time_to_recover(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out; /* Do not perform any recovery during F-RTO algorithm */ if (tp->frto_counter) - return 0; + return false; /* Trick#1: The loss is proven. */ if (tp->lost_out) - return 1; + return true; /* Not-A-Trick#2 : Classic rule... */ if (tcp_dupack_heuristics(tp) > tp->reordering) - return 1; + return true; /* Trick#3 : when we use RFC2988 timer restart, fast * retransmit can be triggered by timeout of queue head. */ if (tcp_is_fack(tp) && tcp_head_timedout(sk)) - return 1; + return true; /* Trick#4: It is still not OK... But will it be useful to delay * recovery more? @@ -2473,7 +2507,7 @@ static int tcp_time_to_recover(struct sock *sk) /* We have nothing to send. This connection is limited * either by receiver window or by application. */ - return 1; + return true; } /* If a thin stream is detected, retransmit after first @@ -2484,9 +2518,19 @@ static int tcp_time_to_recover(struct sock *sk) if ((tp->thin_dupack || sysctl_tcp_thin_dupack) && tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 && tcp_is_sack(tp) && !tcp_send_head(sk)) - return 1; + return true; - return 0; + /* Trick#6: TCP early retransmit, per RFC5827. To avoid spurious + * retransmissions due to small network reorderings, we implement + * Mitigation A.3 in the RFC and delay the retransmission for a short + * interval if appropriate. + */ + if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out && + (tp->packets_out == (tp->sacked_out + 1) && tp->packets_out < 4) && + !tcp_may_send_now(sk)) + return !tcp_pause_early_retransmit(sk, flag); + + return false; } /* New heuristics: it is possible only after we switched to restart timer @@ -2674,22 +2718,22 @@ static void DBGUNDO(struct sock *sk, const char *msg) struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", - msg, - &inet->inet_daddr, ntohs(inet->inet_dport), - tp->snd_cwnd, tcp_left_out(tp), - tp->snd_ssthresh, tp->prior_ssthresh, - tp->packets_out); + pr_debug("Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", + msg, + &inet->inet_daddr, ntohs(inet->inet_dport), + tp->snd_cwnd, tcp_left_out(tp), + tp->snd_ssthresh, tp->prior_ssthresh, + tp->packets_out); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", - msg, - &np->daddr, ntohs(inet->inet_dport), - tp->snd_cwnd, tcp_left_out(tp), - tp->snd_ssthresh, tp->prior_ssthresh, - tp->packets_out); + pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", + msg, + &np->daddr, ntohs(inet->inet_dport), + tp->snd_cwnd, tcp_left_out(tp), + tp->snd_ssthresh, tp->prior_ssthresh, + tp->packets_out); } #endif } @@ -2725,7 +2769,7 @@ static inline int tcp_may_undo(const struct tcp_sock *tp) } /* People celebrate: "We love our President!" */ -static int tcp_try_undo_recovery(struct sock *sk) +static bool tcp_try_undo_recovery(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2750,10 +2794,10 @@ static int tcp_try_undo_recovery(struct sock *sk) * is ACKed. For Reno it is MUST to prevent false * fast retransmits (RFC2582). SACK TCP is safe. */ tcp_moderate_cwnd(tp); - return 1; + return true; } tcp_set_ca_state(sk, TCP_CA_Open); - return 0; + return false; } /* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */ @@ -2783,19 +2827,19 @@ static void tcp_try_undo_dsack(struct sock *sk) * that successive retransmissions of a segment must not advance * retrans_stamp under any conditions. */ -static int tcp_any_retrans_done(const struct sock *sk) +static bool tcp_any_retrans_done(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (tp->retrans_out) - return 1; + return true; skb = tcp_write_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) - return 1; + return true; - return 0; + return false; } /* Undo during fast recovery after partial ACK. */ @@ -2829,7 +2873,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked) } /* Undo during loss recovery after partial ACK. */ -static int tcp_try_undo_loss(struct sock *sk) +static bool tcp_try_undo_loss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2851,9 +2895,9 @@ static int tcp_try_undo_loss(struct sock *sk) tp->undo_marker = 0; if (tcp_is_sack(tp)) tcp_set_ca_state(sk, TCP_CA_Open); - return 1; + return true; } - return 0; + return false; } static inline void tcp_complete_cwr(struct sock *sk) @@ -2862,11 +2906,14 @@ static inline void tcp_complete_cwr(struct sock *sk) /* Do not moderate cwnd if it's already undone in cwr or recovery. */ if (tp->undo_marker) { - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - else /* PRR */ + tp->snd_cwnd_stamp = tcp_time_stamp; + } else if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH) { + /* PRR algorithm. */ tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_time_stamp; + } } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -3016,6 +3063,38 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } +static void tcp_enter_recovery(struct sock *sk, bool ece_ack) +{ + struct tcp_sock *tp = tcp_sk(sk); + int mib_idx; + + if (tcp_is_reno(tp)) + mib_idx = LINUX_MIB_TCPRENORECOVERY; + else + mib_idx = LINUX_MIB_TCPSACKRECOVERY; + + NET_INC_STATS_BH(sock_net(sk), mib_idx); + + tp->high_seq = tp->snd_nxt; + tp->prior_ssthresh = 0; + tp->undo_marker = tp->snd_una; + tp->undo_retrans = tp->retrans_out; + + if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!ece_ack) + tp->prior_ssthresh = tcp_current_ssthresh(sk); + tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); + TCP_ECN_queue_cwr(tp); + } + + tp->bytes_acked = 0; + tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; + tcp_set_ca_state(sk, TCP_CA_Recovery); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -3035,7 +3114,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, struct tcp_sock *tp = tcp_sk(sk); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - int fast_rexmit = 0, mib_idx; + int fast_rexmit = 0; if (WARN_ON(!tp->packets_out && tp->sacked_out)) tp->sacked_out = 0; @@ -3119,7 +3198,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); - if (!tcp_time_to_recover(sk)) { + if (!tcp_time_to_recover(sk, flag)) { tcp_try_to_open(sk, flag); return; } @@ -3136,32 +3215,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } /* Otherwise enter Recovery state */ - - if (tcp_is_reno(tp)) - mib_idx = LINUX_MIB_TCPRENORECOVERY; - else - mib_idx = LINUX_MIB_TCPSACKRECOVERY; - - NET_INC_STATS_BH(sock_net(sk), mib_idx); - - tp->high_seq = tp->snd_nxt; - tp->prior_ssthresh = 0; - tp->undo_marker = tp->snd_una; - tp->undo_retrans = tp->retrans_out; - - if (icsk->icsk_ca_state < TCP_CA_CWR) { - if (!(flag & FLAG_ECE)) - tp->prior_ssthresh = tcp_current_ssthresh(sk); - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - TCP_ECN_queue_cwr(tp); - } - - tp->bytes_acked = 0; - tp->snd_cwnd_cnt = 0; - tp->prior_cwnd = tp->snd_cwnd; - tp->prr_delivered = 0; - tp->prr_out = 0; - tcp_set_ca_state(sk, TCP_CA_Recovery); + tcp_enter_recovery(sk, (flag & FLAG_ECE)); fast_rexmit = 1; } @@ -3243,16 +3297,47 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* Restart timer after forward progress on connection. * RFC2988 recommends to restart timer to now+rto. */ -static void tcp_rearm_rto(struct sock *sk) +void tcp_rearm_rto(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); } else { - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + u32 rto = inet_csk(sk)->icsk_rto; + /* Offset the time elapsed after installing regular RTO */ + if (tp->early_retrans_delayed) { + struct sk_buff *skb = tcp_write_queue_head(sk); + const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto; + s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); + /* delta may not be positive if the socket is locked + * when the delayed ER timer fires and is rescheduled. + */ + if (delta > 0) + rto = delta; + } + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, + TCP_RTO_MAX); } + tp->early_retrans_delayed = 0; +} + +/* This function is called when the delayed ER timer fires. TCP enters + * fast recovery and performs fast-retransmit. + */ +void tcp_resume_early_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_rearm_rto(sk); + + /* Stop if ER is disabled after the delayed ER timer is scheduled */ + if (!tp->do_early_retrans) + return; + + tcp_enter_recovery(sk, false); + tcp_update_scoreboard(sk, 1); + tcp_xmit_retransmit_queue(sk); } /* If we get here, the whole TSO packet has not been acked. */ @@ -3287,7 +3372,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb; u32 now = tcp_time_stamp; - int fully_acked = 1; + int fully_acked = true; int flag = 0; u32 pkts_acked = 0; u32 reord = tp->packets_out; @@ -3311,7 +3396,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!acked_pcount) break; - fully_acked = 0; + fully_acked = false; } else { acked_pcount = tcp_skb_pcount(skb); } @@ -3428,18 +3513,18 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!tp->packets_out && tcp_is_sack(tp)) { icsk = inet_csk(sk); if (tp->lost_out) { - printk(KERN_DEBUG "Leak l=%u %d\n", - tp->lost_out, icsk->icsk_ca_state); + pr_debug("Leak l=%u %d\n", + tp->lost_out, icsk->icsk_ca_state); tp->lost_out = 0; } if (tp->sacked_out) { - printk(KERN_DEBUG "Leak s=%u %d\n", - tp->sacked_out, icsk->icsk_ca_state); + pr_debug("Leak s=%u %d\n", + tp->sacked_out, icsk->icsk_ca_state); tp->sacked_out = 0; } if (tp->retrans_out) { - printk(KERN_DEBUG "Leak r=%u %d\n", - tp->retrans_out, icsk->icsk_ca_state); + pr_debug("Leak r=%u %d\n", + tp->retrans_out, icsk->icsk_ca_state); tp->retrans_out = 0; } } @@ -3590,7 +3675,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag) * to prove that the RTO is indeed spurious. It transfers the control * from F-RTO to the conventional RTO recovery */ -static int tcp_process_frto(struct sock *sk, int flag) +static bool tcp_process_frto(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -3606,7 +3691,7 @@ static int tcp_process_frto(struct sock *sk, int flag) if (!before(tp->snd_una, tp->frto_highmark)) { tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag); - return 1; + return true; } if (!tcp_is_sackfrto(tp)) { @@ -3615,19 +3700,19 @@ static int tcp_process_frto(struct sock *sk, int flag) * data, winupdate */ if (!(flag & FLAG_ANY_PROGRESS) && (flag & FLAG_NOT_DUP)) - return 1; + return true; if (!(flag & FLAG_DATA_ACKED)) { tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3), flag); - return 1; + return true; } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); - return 1; + return true; } if ((tp->frto_counter >= 2) && @@ -3637,10 +3722,10 @@ static int tcp_process_frto(struct sock *sk, int flag) /* RFC4138 shortcoming (see comment above) */ if (!(flag & FLAG_FORWARD_PROGRESS) && (flag & FLAG_NOT_DUP)) - return 1; + return true; tcp_enter_frto_loss(sk, 3, flag); - return 1; + return true; } } @@ -3652,7 +3737,7 @@ static int tcp_process_frto(struct sock *sk, int flag) if (!tcp_may_send_now(sk)) tcp_enter_frto_loss(sk, 2, flag); - return 1; + return true; } else { switch (sysctl_tcp_frto_response) { case 2: @@ -3669,7 +3754,7 @@ static int tcp_process_frto(struct sock *sk, int flag) tp->undo_marker = 0; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); } - return 0; + return false; } /* This routine deals with incoming acks, but not outgoing ones. */ @@ -3687,7 +3772,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_sacked = tp->sacked_out; int pkts_acked = 0; int newly_acked_sacked = 0; - int frto_cwnd = 0; + bool frto_cwnd = false; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3701,6 +3786,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; + if (tp->early_retrans_delayed) + tcp_rearm_rto(sk); + if (after(ack, prior_snd_una)) flag |= FLAG_SND_UNA_ADVANCED; @@ -3866,10 +3954,9 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { - if (net_ratelimit()) - printk(KERN_INFO "tcp_parse_options: Illegal window " - "scaling value %d >14 received.\n", - snd_wscale); + net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n", + __func__, + snd_wscale); snd_wscale = 14; } opt_rx->snd_wscale = snd_wscale; @@ -3940,7 +4027,7 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o } EXPORT_SYMBOL(tcp_parse_options); -static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) +static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) { const __be32 *ptr = (const __be32 *)(th + 1); @@ -3951,31 +4038,31 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; tp->rx_opt.rcv_tsecr = ntohl(*ptr); - return 1; + return true; } - return 0; + return false; } /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static int tcp_fast_parse_options(const struct sk_buff *skb, - const struct tcphdr *th, - struct tcp_sock *tp, const u8 **hvpp) +static bool tcp_fast_parse_options(const struct sk_buff *skb, + const struct tcphdr *th, + struct tcp_sock *tp, const u8 **hvpp) { /* In the spirit of fast parsing, compare doff directly to constant * values. Because equality is used, short doff can be ignored here. */ if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; - return 0; + return false; } else if (tp->rx_opt.tstamp_ok && th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) - return 1; + return true; } tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); - return 1; + return true; } #ifdef CONFIG_TCP_MD5SIG @@ -4191,7 +4278,7 @@ static void tcp_fin(struct sock *sk) /* Only TCP_LISTEN and TCP_CLOSE are left, in these * cases we should never reach this piece of code. */ - printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n", + pr_err("%s: Impossible, sk->sk_state=%d\n", __func__, sk->sk_state); break; } @@ -4216,7 +4303,7 @@ static void tcp_fin(struct sock *sk) } } -static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, +static inline bool tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq) { if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) { @@ -4224,9 +4311,9 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, sp->start_seq = seq; if (after(end_seq, sp->end_seq)) sp->end_seq = end_seq; - return 1; + return true; } - return 0; + return false; } static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) @@ -4422,10 +4509,10 @@ static void tcp_ofo_queue(struct sock *sk) } } -static int tcp_prune_ofo_queue(struct sock *sk); +static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || !sk_rmem_schedule(sk, size)) { @@ -4444,11 +4531,225 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) return 0; } +/** + * tcp_try_coalesce - try to merge skb to prior one + * @sk: socket + * @to: prior buffer + * @from: buffer to add in queue + * @fragstolen: pointer to boolean + * + * Before queueing skb @from after @to, try to merge them + * to reduce overall memory use and queue lengths, if cost is small. + * Packets in ofo or receive queues can stay a long time. + * Better try to coalesce them right now to avoid future collapses. + * Returns true if caller should free @from instead of queueing it + */ +static bool tcp_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + int delta; + + *fragstolen = false; + + if (tcp_hdr(from)->fin) + return false; + + /* Its possible this segment overlaps with prior segment in queue */ + if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) + return false; + + if (!skb_try_coalesce(to, from, fragstolen, &delta)) + return false; + + atomic_add(delta, &sk->sk_rmem_alloc); + sk_mem_charge(sk, delta); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE); + TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq; + TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq; + return true; +} + +static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb1; + u32 seq, end_seq; + + TCP_ECN_check_ce(tp, skb); + + if (tcp_try_rmem_schedule(sk, skb->truesize)) { + /* TODO: should increment a counter */ + __kfree_skb(skb); + return; + } + + /* Disable header prediction. */ + tp->pred_flags = 0; + inet_csk_schedule_ack(sk); + + SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", + tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + + skb1 = skb_peek_tail(&tp->out_of_order_queue); + if (!skb1) { + /* Initial out of order segment, build 1 SACK. */ + if (tcp_is_sack(tp)) { + tp->rx_opt.num_sacks = 1; + tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; + tp->selective_acks[0].end_seq = + TCP_SKB_CB(skb)->end_seq; + } + __skb_queue_head(&tp->out_of_order_queue, skb); + goto end; + } + + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; + + if (seq == TCP_SKB_CB(skb1)->end_seq) { + bool fragstolen; + + if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { + __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + } else { + kfree_skb_partial(skb, fragstolen); + skb = NULL; + } + + if (!tp->rx_opt.num_sacks || + tp->selective_acks[0].end_seq != seq) + goto add_sack; + + /* Common case: data arrive in order after hole. */ + tp->selective_acks[0].end_seq = end_seq; + goto end; + } + + /* Find place to insert this segment. */ + while (1) { + if (!after(TCP_SKB_CB(skb1)->seq, seq)) + break; + if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { + skb1 = NULL; + break; + } + skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); + } + + /* Do skb overlap to previous one? */ + if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + __kfree_skb(skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, + TCP_SKB_CB(skb1)->end_seq); + } else { + if (skb_queue_is_first(&tp->out_of_order_queue, + skb1)) + skb1 = NULL; + else + skb1 = skb_queue_prev( + &tp->out_of_order_queue, + skb1); + } + } + if (!skb1) + __skb_queue_head(&tp->out_of_order_queue, skb); + else + __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + + /* And clean segments covered by new one as whole. */ + while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { + skb1 = skb_queue_next(&tp->out_of_order_queue, skb); + + if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) + break; + if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, + end_seq); + break; + } + __skb_unlink(skb1, &tp->out_of_order_queue); + tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + __kfree_skb(skb1); + } + +add_sack: + if (tcp_is_sack(tp)) + tcp_sack_new_ofo_skb(sk, seq, end_seq); +end: + if (skb) + skb_set_owner_r(skb, sk); +} + +static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen, + bool *fragstolen) +{ + int eaten; + struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue); + + __skb_pull(skb, hdrlen); + eaten = (tail && + tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; + tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + if (!eaten) { + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); + } + return eaten; +} + +int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct sk_buff *skb; + struct tcphdr *th; + bool fragstolen; + + if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) + goto err; + + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); + if (!skb) + goto err; + + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); + skb_reset_transport_header(skb); + memset(th, 0, sizeof(*th)); + + if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size)) + goto err_free; + + TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt; + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size; + TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1; + + if (tcp_queue_rcv(sk, skb, sizeof(*th), &fragstolen)) { + WARN_ON_ONCE(fragstolen); /* should not happen */ + __kfree_skb(skb); + } + return size; + +err_free: + kfree_skb(skb); +err: + return -ENOMEM; +} + static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct tcp_sock *tp = tcp_sk(sk); int eaten = -1; + bool fragstolen = false; if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) goto drop; @@ -4493,8 +4794,7 @@ queue_and_out: tcp_try_rmem_schedule(sk, skb->truesize)) goto drop; - skb_set_owner_r(skb, sk); - __skb_queue_tail(&sk->sk_receive_queue, skb); + eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; if (skb->len) @@ -4518,7 +4818,7 @@ queue_and_out: tcp_fast_path_check(sk); if (eaten > 0) - __kfree_skb(skb); + kfree_skb_partial(skb, fragstolen); else if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, 0); return; @@ -4559,105 +4859,7 @@ drop: goto queue_and_out; } - TCP_ECN_check_ce(tp, skb); - - if (tcp_try_rmem_schedule(sk, skb->truesize)) - goto drop; - - /* Disable header prediction. */ - tp->pred_flags = 0; - inet_csk_schedule_ack(sk); - - SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); - - skb_set_owner_r(skb, sk); - - if (!skb_peek(&tp->out_of_order_queue)) { - /* Initial out of order segment, build 1 SACK. */ - if (tcp_is_sack(tp)) { - tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; - } - __skb_queue_head(&tp->out_of_order_queue, skb); - } else { - struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue); - u32 seq = TCP_SKB_CB(skb)->seq; - u32 end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; - return; - } - - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; - } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); - } - - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - __kfree_skb(skb); - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; - } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); - } - } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); - - if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) - break; - if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, - end_seq); - break; - } - __skb_unlink(skb1, &tp->out_of_order_queue); - tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, - TCP_SKB_CB(skb1)->end_seq); - __kfree_skb(skb1); - } - -add_sack: - if (tcp_is_sack(tp)) - tcp_sack_new_ofo_skb(sk, seq, end_seq); - } + tcp_data_queue_ofo(sk, skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, @@ -4836,10 +5038,10 @@ static void tcp_collapse_ofo_queue(struct sock *sk) * Purge the out-of-order queue. * Return true if queue was pruned. */ -static int tcp_prune_ofo_queue(struct sock *sk) +static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - int res = 0; + bool res = false; if (!skb_queue_empty(&tp->out_of_order_queue)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_OFOPRUNED); @@ -4853,7 +5055,7 @@ static int tcp_prune_ofo_queue(struct sock *sk) if (tp->rx_opt.sack_ok) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); - res = 1; + res = true; } return res; } @@ -4930,7 +5132,7 @@ void tcp_cwnd_application_limited(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } -static int tcp_should_expand_sndbuf(const struct sock *sk) +static bool tcp_should_expand_sndbuf(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4938,21 +5140,21 @@ static int tcp_should_expand_sndbuf(const struct sock *sk) * not modify it. */ if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) - return 0; + return false; /* If we are under global TCP memory pressure, do not expand. */ if (sk_under_memory_pressure(sk)) - return 0; + return false; /* If we are under soft global TCP memory pressure, do not expand. */ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) - return 0; + return false; /* If we filled the congestion window, do not expand. */ if (tp->packets_out >= tp->snd_cwnd) - return 0; + return false; - return 1; + return true; } /* When incoming ACK allowed to free some skb from write_queue, @@ -5178,19 +5380,19 @@ static inline int tcp_checksum_complete_user(struct sock *sk, } #ifdef CONFIG_NET_DMA -static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, +static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); int chunk = skb->len - hlen; int dma_cookie; - int copied_early = 0; + bool copied_early = false; if (tp->ucopy.wakeup) - return 0; + return false; if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) { @@ -5203,7 +5405,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, goto out; tp->ucopy.dma_cookie = dma_cookie; - copied_early = 1; + copied_early = true; tp->ucopy.len -= chunk; tp->copied_seq += chunk; @@ -5395,6 +5597,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, } else { int eaten = 0; int copied_early = 0; + bool fragstolen = false; if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { @@ -5452,10 +5655,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - __skb_pull(skb, tcp_header_len); - __skb_queue_tail(&sk->sk_receive_queue, skb); - skb_set_owner_r(skb, sk); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + eaten = tcp_queue_rcv(sk, skb, tcp_header_len, + &fragstolen); } tcp_event_data_recv(sk, skb); @@ -5477,7 +5678,7 @@ no_ack: else #endif if (eaten) - __kfree_skb(skb); + kfree_skb_partial(skb, fragstolen); else sk->sk_data_ready(sk, 0); return 0; @@ -5521,6 +5722,44 @@ discard: } EXPORT_SYMBOL(tcp_rcv_established); +void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_set_state(sk, TCP_ESTABLISHED); + + if (skb != NULL) + security_inet_conn_established(sk, skb); + + /* Make sure socket is routed, for correct metrics. */ + icsk->icsk_af_ops->rebuild_header(sk); + + tcp_init_metrics(sk); + + tcp_init_congestion_control(sk); + + /* Prevent spurious tcp_cwnd_restart() on first data + * packet. + */ + tp->lsndtime = tcp_time_stamp; + + tcp_init_buffer_space(sk); + + if (sock_flag(sk, SOCK_KEEPOPEN)) + inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); + + if (!tp->rx_opt.snd_wscale) + __tcp_fast_path_on(tp, tp->snd_wnd); + else + tp->pred_flags = 0; + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_state_change(sk); + sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); + } +} + static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { @@ -5653,36 +5892,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, } smp_mb(); - tcp_set_state(sk, TCP_ESTABLISHED); - - security_inet_conn_established(sk, skb); - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - - tcp_init_congestion_control(sk); - - /* Prevent spurious tcp_cwnd_restart() on first data - * packet. - */ - tp->lsndtime = tcp_time_stamp; - - tcp_init_buffer_space(sk); - - if (sock_flag(sk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); - - if (!tp->rx_opt.snd_wscale) - __tcp_fast_path_on(tp, tp->snd_wnd); - else - tp->pred_flags = 0; - - if (!sock_flag(sk, SOCK_DEAD)) { - sk->sk_state_change(sk); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); - } + tcp_finish_connect(sk, skb); if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || @@ -5696,8 +5907,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, */ inet_csk_schedule_ack(sk); icsk->icsk_ack.lrcvtime = tcp_time_stamp; - icsk->icsk_ack.ato = TCP_ATO_MIN; - tcp_incr_quickack(sk); tcp_enter_quickack_mode(sk); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd54c5f8a25..c8d28c433b2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -50,6 +50,7 @@ * a single port at the same time. */ +#define pr_fmt(fmt) "TCP: " fmt #include <linux/bottom_half.h> #include <linux/types.h> @@ -90,16 +91,8 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency); #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, - __be32 addr); -static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); -#else -static inline -struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) -{ - return NULL; -} #endif struct inet_hashinfo tcp_hashinfo; @@ -145,6 +138,14 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_SYMBOL_GPL(tcp_twsk_unique); +static int tcp_repair_connect(struct sock *sk) +{ + tcp_connect_init(sk); + tcp_finish_connect(sk, NULL); + + return 0; +} + /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -203,7 +204,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + if (likely(!tp->repair)) + tp->write_seq = 0; } if (tcp_death_row.sysctl_tw_recycle && @@ -254,7 +256,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, @@ -262,7 +264,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = tp->write_seq ^ jiffies; - err = tcp_connect(sk); + if (likely(!tp->repair)) + err = tcp_connect(sk); + else + err = tcp_repair_connect(sk); + rt = NULL; if (err) goto failure; @@ -601,6 +607,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; + const __u8 *hash_location = NULL; + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; #endif struct net *net; @@ -631,7 +641,36 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); #ifdef CONFIG_TCP_MD5SIG - key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL; + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, ip_hdr(skb)->daddr, + ntohs(th->source), inet_iif(skb)); + /* don't send rst if it can't find key */ + if (!sk1) + return; + rcu_read_lock(); + key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + if (!key) + goto release_sk1; + + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, + AF_INET) : NULL; + } + if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -664,6 +703,14 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); + +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states @@ -764,7 +811,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, 0, - tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr), + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } @@ -776,7 +824,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + u16 queue_mapping) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -792,6 +841,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); + skb_set_queue_mapping(skb, queue_mapping); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, ireq->opt); @@ -806,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp); + return tcp_v4_send_synack(sk, NULL, req, rvp, 0); } /* @@ -818,14 +868,14 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) } /* - * Return 1 if a syncookie should be sent + * Return true if a syncookie should be sent */ -int tcp_syn_flood_action(struct sock *sk, +bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, const char *proto) { const char *msg = "Dropping request"; - int want_cookie = 0; + bool want_cookie = false; struct listen_sock *lopt; @@ -833,7 +883,7 @@ int tcp_syn_flood_action(struct sock *sk, #ifdef CONFIG_SYN_COOKIES if (sysctl_tcp_syncookies) { msg = "Sending cookies"; - want_cookie = 1; + want_cookie = true; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); } else #endif @@ -842,8 +892,7 @@ int tcp_syn_flood_action(struct sock *sk, lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; if (!lopt->synflood_warned) { lopt->synflood_warned = 1; - pr_info("%s: Possible SYN flooding on port %d. %s. " - " Check SNMP counters.\n", + pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); } return want_cookie; @@ -881,153 +930,138 @@ static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk, */ /* Find the Key structure for an address. */ -static struct tcp_md5sig_key * - tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) +struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, + const union tcp_md5_addr *addr, + int family) { struct tcp_sock *tp = tcp_sk(sk); - int i; - - if (!tp->md5sig_info || !tp->md5sig_info->entries4) + struct tcp_md5sig_key *key; + struct hlist_node *pos; + unsigned int size = sizeof(struct in_addr); + struct tcp_md5sig_info *md5sig; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); + if (!md5sig) return NULL; - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) - return &tp->md5sig_info->keys4[i].base; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + size = sizeof(struct in6_addr); +#endif + hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + if (key->family != family) + continue; + if (!memcmp(&key->addr, addr, size)) + return key; } return NULL; } +EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr); + union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr; + return tcp_md5_do_lookup(sk, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk, struct request_sock *req) { - return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr); + union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr; + return tcp_md5_do_lookup(sk, addr, AF_INET); } /* This can be called on a newly created socket, from other files */ -int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, - u8 *newkey, u8 newkeylen) +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); - struct tcp4_md5sig_key *keys; + struct tcp_md5sig_info *md5sig; - key = tcp_v4_md5_do_lookup(sk, addr); + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); if (key) { /* Pre-existing entry - just update that one. */ - kfree(key->key); - key->key = newkey; + memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; - } else { - struct tcp_md5sig_info *md5sig; - - if (!tp->md5sig_info) { - tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), - GFP_ATOMIC); - if (!tp->md5sig_info) { - kfree(newkey); - return -ENOMEM; - } - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } + return 0; + } - md5sig = tp->md5sig_info; - if (md5sig->entries4 == 0 && - tcp_alloc_md5sig_pool(sk) == NULL) { - kfree(newkey); + md5sig = rcu_dereference_protected(tp->md5sig_info, + sock_owned_by_user(sk)); + if (!md5sig) { + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) return -ENOMEM; - } - if (md5sig->alloced4 == md5sig->entries4) { - keys = kmalloc((sizeof(*keys) * - (md5sig->entries4 + 1)), GFP_ATOMIC); - if (!keys) { - kfree(newkey); - if (md5sig->entries4 == 0) - tcp_free_md5sig_pool(); - return -ENOMEM; - } - - if (md5sig->entries4) - memcpy(keys, md5sig->keys4, - sizeof(*keys) * md5sig->entries4); + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + } - /* Free old key list, and reference new one */ - kfree(md5sig->keys4); - md5sig->keys4 = keys; - md5sig->alloced4++; - } - md5sig->entries4++; - md5sig->keys4[md5sig->entries4 - 1].addr = addr; - md5sig->keys4[md5sig->entries4 - 1].base.key = newkey; - md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen; + key = sock_kmalloc(sk, sizeof(*key), gfp); + if (!key) + return -ENOMEM; + if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) { + sock_kfree_s(sk, key, sizeof(*key)); + return -ENOMEM; } - return 0; -} -EXPORT_SYMBOL(tcp_v4_md5_do_add); -static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk, - u8 *newkey, u8 newkeylen) -{ - return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr, - newkey, newkeylen); + memcpy(key->key, newkey, newkeylen); + key->keylen = newkeylen; + key->family = family; + memcpy(&key->addr, addr, + (family == AF_INET6) ? sizeof(struct in6_addr) : + sizeof(struct in_addr)); + hlist_add_head_rcu(&key->node, &md5sig->head); + return 0; } +EXPORT_SYMBOL(tcp_md5_do_add); -int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) { struct tcp_sock *tp = tcp_sk(sk); - int i; - - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) { - /* Free the key */ - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4--; - - if (tp->md5sig_info->entries4 == 0) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; - tcp_free_md5sig_pool(); - } else if (tp->md5sig_info->entries4 != i) { - /* Need to do some manipulation */ - memmove(&tp->md5sig_info->keys4[i], - &tp->md5sig_info->keys4[i+1], - (tp->md5sig_info->entries4 - i) * - sizeof(struct tcp4_md5sig_key)); - } - return 0; - } - } - return -ENOENT; + struct tcp_md5sig_key *key; + struct tcp_md5sig_info *md5sig; + + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); + if (!key) + return -ENOENT; + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); + md5sig = rcu_dereference_protected(tp->md5sig_info, + sock_owned_by_user(sk)); + if (hlist_empty(&md5sig->head)) + tcp_free_md5sig_pool(); + return 0; } -EXPORT_SYMBOL(tcp_v4_md5_do_del); +EXPORT_SYMBOL(tcp_md5_do_del); -static void tcp_v4_clear_md5_list(struct sock *sk) +void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + struct hlist_node *pos, *n; + struct tcp_md5sig_info *md5sig; - /* Free each key, then the set of key keys, - * the crypto element, and then decrement our - * hold on the last resort crypto. - */ - if (tp->md5sig_info->entries4) { - int i; - for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4 = 0; + md5sig = rcu_dereference_protected(tp->md5sig_info, 1); + + if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - } - if (tp->md5sig_info->keys4) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; + hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); } } @@ -1036,7 +1070,6 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; - u8 *newkey; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1047,32 +1080,16 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; - if (!cmd.tcpm_key || !cmd.tcpm_keylen) { - if (!tcp_sk(sk)->md5sig_info) - return -ENOENT; - return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr); - } + if (!cmd.tcpm_key || !cmd.tcpm_keylen) + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - if (!tcp_sk(sk)->md5sig_info) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p; - - p = kzalloc(sizeof(*p), sk->sk_allocation); - if (!p) - return -EINVAL; - - tp->md5sig_info = p; - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } - - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); - if (!newkey) - return -ENOMEM; - return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr, - newkey, cmd.tcpm_keylen); + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + GFP_KERNEL); } static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, @@ -1098,7 +1115,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp)); } -static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; @@ -1181,7 +1198,7 @@ clear_hash_noput: } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); -static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1198,21 +1215,22 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) int genhash; unsigned char newhash[16]; - hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr); + hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, + AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return 1; + return true; } if (!hash_expected && hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - return 1; + return true; } /* Okay, so this is hash_expected and hash_location - @@ -1223,15 +1241,14 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) NULL, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", - &iph->saddr, ntohs(th->source), - &iph->daddr, ntohs(th->dest), - genhash ? " tcp_v4_calc_md5_hash failed" : ""); - } - return 1; + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest), + genhash ? " tcp_v4_calc_md5_hash failed" + : ""); + return true; } - return 0; + return false; } #endif @@ -1265,7 +1282,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - int want_cookie = 0; + bool want_cookie = false; /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1324,7 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) while (l-- > 0) *c++ ^= *hash_location++; - want_cookie = 0; /* not our kind of cookie */ + want_cookie = false; /* not our kind of cookie */ tmp_ext.cookie_out_never = 0; /* false */ tmp_ext.cookie_plus = tmp_opt.cookie_plus; } else if (!tp->rx_opt.cookie_in_always) { @@ -1352,7 +1369,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, tcp_hdr(skb)); + TCP_ECN_create_request(req, skb); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -1396,7 +1413,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * to destinations, already remembered * to the moment of synflood. */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI4/%u\n", + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"), &saddr, ntohs(tcp_hdr(skb)->source)); goto drop_and_release; } @@ -1407,7 +1424,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_synack = tcp_time_stamp; if (tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext) || + (struct request_values *)&tmp_ext, + skb_get_queue_mapping(skb)) || want_cookie) goto drop_and_free; @@ -1461,6 +1479,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; + newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; @@ -1490,7 +1509,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr); + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET); if (key != NULL) { /* * We're using one, so create a matching key @@ -1498,10 +1518,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); - if (newkey != NULL) - tcp_v4_md5_do_add(newsk, newinet->inet_daddr, - newkey, key->keylen); + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1727,7 +1745,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v4_do_rcv(sk, skb); else @@ -1736,7 +1754,8 @@ process: if (!tcp_prequeue(sk, skb)) ret = tcp_v4_do_rcv(sk, skb); } - } else if (unlikely(sk_add_backlog(sk, skb))) { + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { bh_unlock_sock(sk); NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); goto discard_and_relse; @@ -1862,7 +1881,6 @@ EXPORT_SYMBOL(ipv4_specific); static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, - .md5_add = tcp_v4_md5_add_func, .md5_parse = tcp_v4_parse_md5_keys, }; #endif @@ -1873,64 +1891,15 @@ static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = TCP_INIT_CWND; - - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = TCP_MSS_DEFAULT; - - tp->reordering = sysctl_tcp_reordering; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - - sk->sk_state = TCP_CLOSE; - - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; - icsk->icsk_sync_mss = tcp_sync_mss; + #ifdef CONFIG_TCP_MD5SIG - tp->af_specific = &tcp_sock_ipv4_specific; + tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif - /* TCP Cookie Transactions */ - if (sysctl_tcp_cookie_size > 0) { - /* Default, cookies without s_data_payload. */ - tp->cookie_values = - kzalloc(sizeof(*tp->cookie_values), - sk->sk_allocation); - if (tp->cookie_values != NULL) - kref_init(&tp->cookie_values->kref); - } - /* Presumed zeroed, in order of appearance: - * cookie_in_always, cookie_out_never, - * s_data_constant, s_data_in, s_data_out - */ - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - local_bh_disable(); - sock_update_memcg(sk); - sk_sockets_allocated_inc(sk); - local_bh_enable(); - return 0; } @@ -1951,8 +1920,8 @@ void tcp_v4_destroy_sock(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { - tcp_v4_clear_md5_list(sk); - kfree(tp->md5sig_info); + tcp_clear_md5_list(sk); + kfree_rcu(tp->md5sig_info, rcu); tp->md5sig_info = NULL; } #endif @@ -2107,7 +2076,7 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) return rc; } -static inline int empty_bucket(struct tcp_iter_state *st) +static inline bool empty_bucket(struct tcp_iter_state *st) { return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) && hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 49978788a9d..b6f3583ddfe 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -6,37 +6,6 @@ #include <linux/memcontrol.h> #include <linux/module.h> -static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft); -static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft, - const char *buffer); -static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event); - -static struct cftype tcp_files[] = { - { - .name = "kmem.tcp.limit_in_bytes", - .write_string = tcp_cgroup_write, - .read_u64 = tcp_cgroup_read, - .private = RES_LIMIT, - }, - { - .name = "kmem.tcp.usage_in_bytes", - .read_u64 = tcp_cgroup_read, - .private = RES_USAGE, - }, - { - .name = "kmem.tcp.failcnt", - .private = RES_FAILCNT, - .trigger = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, - { - .name = "kmem.tcp.max_usage_in_bytes", - .private = RES_MAX_USAGE, - .trigger = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, -}; - static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) { return container_of(cg_proto, struct tcp_memcontrol, cg_proto); @@ -49,7 +18,7 @@ static void memcg_tcp_enter_memory_pressure(struct sock *sk) } EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); -int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { /* * The root cgroup does not use res_counters, but rather, @@ -59,13 +28,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) struct res_counter *res_parent = NULL; struct cg_proto *cg_proto, *parent_cg; struct tcp_memcontrol *tcp; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup *parent = parent_mem_cgroup(memcg); struct net *net = current->nsproxy->net_ns; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) - goto create_files; + return 0; tcp = tcp_from_cgproto(cg_proto); @@ -88,15 +56,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; cg_proto->memcg = memcg; -create_files: - return cgroup_add_files(cgrp, ss, tcp_files, - ARRAY_SIZE(tcp_files)); + return 0; } EXPORT_SYMBOL(tcp_init_cgroup); -void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +void tcp_destroy_cgroup(struct mem_cgroup *memcg) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct cg_proto *cg_proto; struct tcp_memcontrol *tcp; u64 val; @@ -109,9 +74,6 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) percpu_counter_destroy(&tcp->tcp_sockets_allocated); val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); - - if (val != RESOURCE_MAX) - jump_label_dec(&memcg_socket_limit_enabled); } EXPORT_SYMBOL(tcp_destroy_cgroup); @@ -142,10 +104,33 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, net->ipv4.sysctl_tcp_mem[i]); - if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX) - jump_label_dec(&memcg_socket_limit_enabled); - else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX) - jump_label_inc(&memcg_socket_limit_enabled); + if (val == RESOURCE_MAX) + clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + else if (val != RESOURCE_MAX) { + /* + * The active bit needs to be written after the static_key + * update. This is what guarantees that the socket activation + * function is the last one to run. See sock_update_memcg() for + * details, and note that we don't mark any socket as belonging + * to this memcg until that flag is up. + * + * We need to do this, because static_keys will span multiple + * sites, but we can't control their order. If we mark a socket + * as accounted, but the accounting functions are not patched in + * yet, we'll lose accounting. + * + * We never race with the readers in sock_update_memcg(), + * because when this value change, the code to process it is not + * patched in yet. + * + * The activated bit is used to guarantee that no two writers + * will do the update in the same memcg. Without that, we can't + * properly shutdown the static key. + */ + if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) + static_key_slow_inc(&memcg_socket_limit_enabled); + set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + } return 0; } @@ -270,3 +255,37 @@ void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx) tcp->tcp_prot_mem[idx] = val; } + +static struct cftype tcp_files[] = { + { + .name = "kmem.tcp.limit_in_bytes", + .write_string = tcp_cgroup_write, + .read_u64 = tcp_cgroup_read, + .private = RES_LIMIT, + }, + { + .name = "kmem.tcp.usage_in_bytes", + .read_u64 = tcp_cgroup_read, + .private = RES_USAGE, + }, + { + .name = "kmem.tcp.failcnt", + .private = RES_FAILCNT, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, + { + .name = "kmem.tcp.max_usage_in_bytes", + .private = RES_MAX_USAGE, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, + { } /* terminate */ +}; + +static int __init tcp_memcontrol_init(void) +{ + WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files)); + return 0; +} +__initcall(tcp_memcontrol_init); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 550e755747e..b85d9fe7d66 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(tcp_death_row); * state. */ -static int tcp_remember_stamp(struct sock *sk) +static bool tcp_remember_stamp(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -72,13 +72,13 @@ static int tcp_remember_stamp(struct sock *sk) } if (release_it) inet_putpeer(peer); - return 1; + return true; } - return 0; + return false; } -static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) +static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) { struct sock *sk = (struct sock *) tw; struct inet_peer *peer; @@ -94,17 +94,17 @@ static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) peer->tcp_ts = tcptw->tw_ts_recent; } inet_putpeer(peer); - return 1; + return true; } - return 0; + return false; } -static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) +static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) - return 1; + return true; if (after(end_seq, s_win) && before(seq, e_win)) - return 1; + return true; return seq == e_win && seq == end_seq; } @@ -143,7 +143,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; const u8 *hash_location; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); - int paws_reject = 0; + bool paws_reject = false; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { @@ -316,7 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct inet_timewait_sock *tw = NULL; const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); - int recycle_ok = 0; + bool recycle_ok = false; if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) recycle_ok = tcp_remember_stamp(sk); @@ -359,13 +359,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) */ do { struct tcp_md5sig_key *key; - memset(tcptw->tw_md5_key, 0, sizeof(tcptw->tw_md5_key)); - tcptw->tw_md5_keylen = 0; + tcptw->tw_md5_key = NULL; key = tp->af_specific->md5_lookup(sk, sk); if (key != NULL) { - memcpy(&tcptw->tw_md5_key, key->key, key->keylen); - tcptw->tw_md5_keylen = key->keylen; - if (tcp_alloc_md5sig_pool(sk) == NULL) + tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); + if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL) BUG(); } } while (0); @@ -405,8 +403,10 @@ void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_keylen) + if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); + kfree_rcu(twsk->tw_md5_key, rcu); + } #endif } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); @@ -482,6 +482,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->sacked_out = 0; newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tcp_enable_early_retrans(newtp); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -574,7 +575,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); - int paws_reject = 0; + bool paws_reject = false; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4ff3b6dc74f..803cbfe82fb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -34,6 +34,8 @@ * */ +#define pr_fmt(fmt) "TCP: " fmt + #include <net/tcp.h> #include <linux/compiler.h> @@ -78,9 +80,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) tp->frto_counter = 3; tp->packets_out += tcp_skb_pcount(skb); - if (!prior_packets) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + if (!prior_packets || tp->early_retrans_delayed) + tcp_rearm_rto(sk); } /* SND.NXT, if window was not shrunk. @@ -369,7 +370,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) TCP_SKB_CB(skb)->end_seq = seq; } -static inline int tcp_urg_mode(const struct tcp_sock *tp) +static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } @@ -563,13 +564,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ -static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; - unsigned remaining = MAX_TCP_OPTION_SPACE; + unsigned int remaining = MAX_TCP_OPTION_SPACE; u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : 0; @@ -663,15 +664,15 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } /* Set up TCP options for SYN-ACKs. */ -static unsigned tcp_synack_options(struct sock *sk, +static unsigned int tcp_synack_options(struct sock *sk, struct request_sock *req, - unsigned mss, struct sk_buff *skb, + unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5, struct tcp_extend_values *xvp) { struct inet_request_sock *ireq = inet_rsk(req); - unsigned remaining = MAX_TCP_OPTION_SPACE; + unsigned int remaining = MAX_TCP_OPTION_SPACE; u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? xvp->cookie_plus : 0; @@ -742,13 +743,13 @@ static unsigned tcp_synack_options(struct sock *sk, /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ -static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL; struct tcp_sock *tp = tcp_sk(sk); - unsigned size = 0; + unsigned int size = 0; unsigned int eff_sacks; #ifdef CONFIG_TCP_MD5SIG @@ -770,9 +771,9 @@ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { - const unsigned remaining = MAX_TCP_OPTION_SPACE - size; + const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; opts->num_sack_blocks = - min_t(unsigned, eff_sacks, + min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + @@ -801,7 +802,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; - unsigned tcp_options_size, tcp_header_size; + unsigned int tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; struct tcphdr *th; int err; @@ -1096,6 +1097,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); + skb->avail_size -= eat; len -= eat; if (!len) return; @@ -1149,7 +1151,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) } /* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(const struct sock *sk, int pmtu) +int tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1160,6 +1162,14 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mss_now -= icsk->icsk_af_ops->net_frag_header_len; + } + /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1178,7 +1188,7 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu) } /* Inverse of above */ -int tcp_mss_to_mtu(const struct sock *sk, int mss) +int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1189,6 +1199,13 @@ int tcp_mss_to_mtu(const struct sock *sk, int mss) icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mtu += icsk->icsk_af_ops->net_frag_header_len; + } return mtu; } @@ -1258,7 +1275,7 @@ unsigned int tcp_current_mss(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; - unsigned header_len; + unsigned int header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; @@ -1374,33 +1391,33 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb, } /* Minshall's variant of the Nagle send check. */ -static inline int tcp_minshall_check(const struct tcp_sock *tp) +static inline bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } -/* Return 0, if packet can be sent now without violation Nagle's rules: +/* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ -static inline int tcp_nagle_check(const struct tcp_sock *tp, +static inline bool tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned mss_now, int nonagle) + unsigned int mss_now, int nonagle) { return skb->len < mss_now && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } -/* Return non-zero if the Nagle test allows this packet to be +/* Return true if the Nagle test allows this packet to be * sent now. */ -static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned int cur_mss, int nonagle) +static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, + unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). @@ -1409,24 +1426,25 @@ static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) - return 1; + return true; /* Don't use the nagle rule for urgent data (or for the final FIN). * Nagle can be ignored during F-RTO too (see RFC4138). */ if (tcp_urg_mode(tp) || (tp->frto_counter == 2) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) - return 1; + return true; if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) - return 1; + return true; - return 0; + return false; } /* Does at least the first segment of SKB fit into the send window? */ -static inline int tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned int cur_mss) +static bool tcp_snd_wnd_test(const struct tcp_sock *tp, + const struct sk_buff *skb, + unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -1459,7 +1477,7 @@ static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, } /* Test if sending is allowed right now. */ -int tcp_may_send_now(struct sock *sk) +bool tcp_may_send_now(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); @@ -1529,7 +1547,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, * * This algorithm is from John Heffner. */ -static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) +static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1589,11 +1607,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* Ok, it looks like it is advisable to defer. */ tp->tso_deferred = 1 | (jiffies << 1); - return 1; + return true; send_now: tp->tso_deferred = 0; - return 0; + return false; } /* Create a new MTU probe if we are ready. @@ -1735,11 +1753,11 @@ static int tcp_mtu_probe(struct sock *sk) * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * - * Returns 1, if no segments are in flight and we have queued segments, but - * cannot send anything now because of SWS or another problem. + * Returns true, if no segments are in flight and we have queued segments, + * but cannot send anything now because of SWS or another problem. */ -static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, - int push_one, gfp_t gfp) +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -1753,7 +1771,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { - return 0; + return false; } else if (result > 0) { sent_pkts = 1; } @@ -1812,7 +1830,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (likely(sent_pkts)) { tcp_cwnd_validate(sk); - return 0; + return false; } return !tp->packets_out && tcp_send_head(sk); } @@ -2011,22 +2029,22 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } /* Check if coalescing SKBs is legal. */ -static int tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) +static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) - return 0; + return false; /* TODO: SACK collapsing could be used to remove this condition */ if (skb_shinfo(skb)->nr_frags != 0) - return 0; + return false; if (skb_cloned(skb)) - return 0; + return false; if (skb == tcp_send_head(sk)) - return 0; + return false; /* Some heurestics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - return 0; + return false; - return 1; + return true; } /* Collapse packets in the retransmit queue to make to create @@ -2037,7 +2055,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; - int first = 1; + bool first = true; if (!sysctl_tcp_retrans_collapse) return; @@ -2051,7 +2069,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, space -= skb->len; if (first) { - first = 0; + first = false; continue; } @@ -2060,7 +2078,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, /* Punt if not enough space exists in the first SKB for * the data in the second */ - if (skb->len > skb_tailroom(to)) + if (skb->len > skb_availroom(to)) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) @@ -2166,8 +2184,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - if (net_ratelimit()) - printk(KERN_DEBUG "retrans_out leaked.\n"); + net_dbg_ratelimited("retrans_out leaked\n"); } #endif if (!tp->retrans_out) @@ -2192,18 +2209,18 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) /* Check if we forward retransmits are possible in the current * window/congestion state. */ -static int tcp_can_forward_retransmit(struct sock *sk) +static bool tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); /* Forward retransmissions are possible only during Recovery. */ if (icsk->icsk_ca_state != TCP_CA_Recovery) - return 0; + return false; /* No forward retransmissions in Reno are possible. */ if (tcp_is_reno(tp)) - return 0; + return false; /* Yeah, we have to make difficult choice between forward transmission * and retransmission... Both ways have their merits... @@ -2214,9 +2231,9 @@ static int tcp_can_forward_retransmit(struct sock *sk) */ if (tcp_may_send_now(sk)) - return 0; + return false; - return 1; + return true; } /* This gets called after a retransmit timeout, and the initially @@ -2306,8 +2323,10 @@ begin_fwd: if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; - if (tcp_retransmit_skb(sk, skb)) + if (tcp_retransmit_skb(sk, skb)) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); return; + } NET_INC_STATS_BH(sock_net(sk), mib_idx); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) @@ -2399,7 +2418,7 @@ int tcp_send_synack(struct sock *sk) skb = tcp_write_queue_head(sk); if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n"); + pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { @@ -2559,7 +2578,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, EXPORT_SYMBOL(tcp_make_synack); /* Do all connect socket setups that can be done AF independent. */ -static void tcp_connect_init(struct sock *sk) +void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -2614,9 +2633,12 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->rcv_nxt = 0; - tp->rcv_wup = 0; - tp->copied_seq = 0; + tp->snd_nxt = tp->write_seq; + + if (likely(!tp->repair)) + tp->rcv_nxt = 0; + tp->rcv_wup = tp->rcv_nxt; + tp->copied_seq = tp->rcv_nxt; inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; inet_csk(sk)->icsk_retransmits = 0; @@ -2639,7 +2661,6 @@ int tcp_connect(struct sock *sk) /* Reserve space for headers. */ skb_reserve(buff, MAX_TCP_HEADER); - tp->snd_nxt = tp->write_seq; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); TCP_ECN_send_syn(sk, buff); @@ -2788,6 +2809,15 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } +void tcp_send_window_probe(struct sock *sk) +{ + if (sk->sk_state == TCP_ESTABLISHED) { + tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; + tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq; + tcp_xmit_probe_skb(sk, 0); + } +} + /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk) { diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 85ee7eb7e38..4526fe68e60 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -18,6 +18,8 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/kprobes.h> #include <linux/socket.h> @@ -89,7 +91,7 @@ static inline int tcp_probe_avail(void) * Note: arguments must match tcp_rcv_established()! */ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned len) + struct tcphdr *th, unsigned int len) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_sock *inet = inet_sk(sk); @@ -136,7 +138,7 @@ static struct jprobe tcp_jprobe = { .entry = jtcp_rcv_established, }; -static int tcpprobe_open(struct inode * inode, struct file * file) +static int tcpprobe_open(struct inode *inode, struct file *file) { /* Reset (empty) log */ spin_lock_bh(&tcp_probe.lock); @@ -239,7 +241,7 @@ static __init int tcpprobe_init(void) if (ret) goto err1; - pr_info("TCP probe registered (port=%d) bufsize=%u\n", port, bufsize); + pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize); return 0; err1: proc_net_remove(&init_net, procname); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index cd2e0723266..e911e6c523e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -319,6 +319,11 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + if (tp->early_retrans_delayed) { + tcp_resume_early_retransmit(sk); + return; + } + if (!tp->packets_out) goto out; @@ -333,16 +338,18 @@ void tcp_retransmit_timer(struct sock *sk) */ struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &inet->inet_daddr, ntohs(inet->inet_dport), - inet->inet_num, tp->snd_una, tp->snd_nxt); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), + &inet->inet_daddr, + ntohs(inet->inet_dport), inet->inet_num, + tp->snd_una, tp->snd_nxt); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &np->daddr, ntohs(inet->inet_dport), - inet->inet_num, tp->snd_una, tp->snd_nxt); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), + &np->daddr, + ntohs(inet->inet_dport), inet->inet_num, + tp->snd_una, tp->snd_nxt); } #endif if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 01775983b99..0d017183062 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -164,12 +164,12 @@ static const struct net_protocol tunnel64_protocol = { static int __init tunnel4_init(void) { if (inet_add_protocol(&tunnel4_protocol, IPPROTO_IPIP)) { - printk(KERN_ERR "tunnel4 init: can't add protocol\n"); + pr_err("%s: can't add protocol\n", __func__); return -EAGAIN; } #if IS_ENABLED(CONFIG_IPV6) if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) { - printk(KERN_ERR "tunnel64 init: can't add protocol\n"); + pr_err("tunnel64 init: can't add protocol\n"); inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP); return -EAGAIN; } @@ -181,10 +181,10 @@ static void __exit tunnel4_fini(void) { #if IS_ENABLED(CONFIG_IPV6) if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6)) - printk(KERN_ERR "tunnel64 close: can't remove protocol\n"); + pr_err("tunnel64 close: can't remove protocol\n"); #endif if (inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP)) - printk(KERN_ERR "tunnel4 close: can't remove protocol\n"); + pr_err("tunnel4 close: can't remove protocol\n"); } module_init(tunnel4_init); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5d075b5f70f..eaca73644e7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -77,7 +77,8 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/system.h> +#define pr_fmt(fmt) "UDP: " fmt + #include <asm/uaccess.h> #include <asm/ioctls.h> #include <linux/bootmem.h> @@ -106,6 +107,7 @@ #include <net/checksum.h> #include <net/xfrm.h> #include <trace/events/udp.h> +#include <linux/static_key.h> #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -205,7 +207,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, if (!snum) { int low, high, remaining; - unsigned rand; + unsigned int rand; unsigned short first, last; DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); @@ -845,7 +847,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_in * usin = (struct sockaddr_in *)msg->msg_name; + struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -917,7 +919,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (!saddr) saddr = inet->mc_addr; connected = 0; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); @@ -974,7 +977,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n")); err = -EINVAL; goto out; } @@ -1053,7 +1056,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n"); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n")); return -EINVAL; } @@ -1166,7 +1169,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; unsigned int ulen, copied; - int peeked; + int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); bool slow; @@ -1182,7 +1185,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); + &peeked, &off, &err); if (!skb) goto out; @@ -1377,6 +1380,14 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } +static struct static_key udp_encap_needed __read_mostly; +void udp_encap_enable(void) +{ + if (!static_key_enabled(&udp_encap_needed)) + static_key_slow_inc(&udp_encap_needed); +} +EXPORT_SYMBOL(udp_encap_enable); + /* returns: * -1: error * 0: success @@ -1398,7 +1409,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; nf_reset(skb); - if (up->encap_type) { + if (static_key_false(&udp_encap_needed) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -1446,9 +1457,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * provided by the application." */ if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage " - "%d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); + LIMIT_NETDEBUG(KERN_WARNING "UDPLite: partial coverage %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } /* The next case involves violating the min. coverage requested @@ -1458,9 +1468,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * Therefore the above ...()->partial_cov statement is essential. */ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING - "UDPLITE: coverage %d too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + LIMIT_NETDEBUG(KERN_WARNING "UDPLite: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } @@ -1470,7 +1479,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; - if (sk_rcvqueues_full(sk, skb)) + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) goto drop; rc = 0; @@ -1479,7 +1488,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) rc = __udp_queue_rcv_skb(sk, skb); - else if (sk_add_backlog(sk, skb)) { + else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { bh_unlock_sock(sk); goto drop; } @@ -1688,13 +1697,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, short_packet: LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - &saddr, - ntohs(uh->source), - ulen, - skb->len, - &daddr, - ntohs(uh->dest)); + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), + ulen, skb->len, + &daddr, ntohs(uh->dest)); goto drop; csum_error: @@ -1703,11 +1709,8 @@ csum_error: * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - &saddr, - ntohs(uh->source), - &daddr, - ntohs(uh->dest), + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), ulen); drop: UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); @@ -1766,6 +1769,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, /* FALLTHROUGH */ case UDP_ENCAP_L2TPINUDP: up->encap_type = val; + udp_encap_enable(); break; default: err = -ENOPROTOOPT; @@ -2169,9 +2173,15 @@ void udp4_proc_exit(void) static __initdata unsigned long uhash_entries; static int __init set_uhash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - uhash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &uhash_entries); + if (ret) + return 0; + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) uhash_entries = UDP_HTABLE_SIZE_MIN; return 1; @@ -2182,26 +2192,16 @@ void __init udp_table_init(struct udp_table *table, const char *name) { unsigned int i; - if (!CONFIG_BASE_SMALL) - table->hash = alloc_large_system_hash(name, - 2 * sizeof(struct udp_hslot), - uhash_entries, - 21, /* one slot per 2 MB */ - 0, - &table->log, - &table->mask, - 64 * 1024); - /* - * Make sure hash table has the minimum size - */ - if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { - table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * - 2 * sizeof(struct udp_hslot), GFP_KERNEL); - if (!table->hash) - panic(name); - table->log = ilog2(UDP_HTABLE_SIZE_MIN); - table->mask = UDP_HTABLE_SIZE_MIN - 1; - } + table->hash = alloc_large_system_hash(name, + 2 * sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + UDP_HTABLE_SIZE_MIN, + 64 * 1024); + table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 8a949f19deb..a7f86a3cd50 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -146,9 +146,17 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return udp_dump_one(&udp_table, in_skb, nlh, req); } +static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *info) +{ + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); +} + static const struct inet_diag_handler udp_diag_handler = { .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, }; @@ -167,6 +175,7 @@ static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr * static const struct inet_diag_handler udplite_diag_handler = { .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, }; diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index aaad650d47d..5a681e298b9 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -25,7 +25,7 @@ extern int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); extern int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -extern int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb); +extern int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); extern void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 12e9499a1a6..2c46acd4cc3 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -10,6 +10,9 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ + +#define pr_fmt(fmt) "UDPLite: " fmt + #include <linux/export.h> #include "udp_impl.h" @@ -129,11 +132,11 @@ void __init udplite4_register(void) inet_register_protosw(&udplite4_protosw); if (udplite4_proc_init()) - printk(KERN_ERR "%s: Cannot register /proc!\n", __func__); + pr_err("%s: Cannot register /proc!\n", __func__); return; out_unregister_proto: proto_unregister(&udplite_prot); out_register_err: - printk(KERN_CRIT "%s: Cannot add UDP-Lite protocol.\n", __func__); + pr_crit("%s: Cannot add UDP-Lite protocol\n", __func__); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index a0b4c5da8d4..0d3426cb5c4 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -152,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_AH: if (pskb_may_pull(skb, xprth + 8 - skb->data)) { - __be32 *ah_hdr = (__be32*)xprth; + __be32 *ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; } @@ -298,8 +298,8 @@ void __init xfrm4_init(int rt_max_size) xfrm4_state_init(); xfrm4_policy_init(); #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path, - xfrm4_policy_table); + sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4", + xfrm4_policy_table); #endif } diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 9247d9d70e9..05a5df2febc 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -3,6 +3,8 @@ * Copyright (C) 2003 David S. Miller (davem@redhat.com) */ +#define pr_fmt(fmt) "IPsec: " fmt + #include <linux/skbuff.h> #include <linux/module.h> #include <linux/mutex.h> @@ -75,18 +77,18 @@ static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = { static int __init ipip_init(void) { if (xfrm_register_type(&ipip_type, AF_INET) < 0) { - printk(KERN_INFO "ipip init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (xfrm4_tunnel_register(&xfrm_tunnel_handler, AF_INET)) { - printk(KERN_INFO "ipip init: can't add xfrm handler for AF_INET\n"); + pr_info("%s: can't add xfrm handler for AF_INET\n", __func__); xfrm_unregister_type(&ipip_type, AF_INET); return -EAGAIN; } #if IS_ENABLED(CONFIG_IPV6) if (xfrm4_tunnel_register(&xfrm64_tunnel_handler, AF_INET6)) { - printk(KERN_INFO "ipip init: can't add xfrm handler for AF_INET6\n"); + pr_info("%s: can't add xfrm handler for AF_INET6\n", __func__); xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET); xfrm_unregister_type(&ipip_type, AF_INET); return -EAGAIN; @@ -99,12 +101,14 @@ static void __exit ipip_fini(void) { #if IS_ENABLED(CONFIG_IPV6) if (xfrm4_tunnel_deregister(&xfrm64_tunnel_handler, AF_INET6)) - printk(KERN_INFO "ipip close: can't remove xfrm handler for AF_INET6\n"); + pr_info("%s: can't remove xfrm handler for AF_INET6\n", + __func__); #endif if (xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET)) - printk(KERN_INFO "ipip close: can't remove xfrm handler for AF_INET\n"); + pr_info("%s: can't remove xfrm handler for AF_INET\n", + __func__); if (xfrm_unregister_type(&ipip_type, AF_INET) < 0) - printk(KERN_INFO "ipip close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(ipip_init); |