diff options
59 files changed, 2406 insertions, 1099 deletions
diff --git a/include/linux/ip.h b/include/linux/ip.h index 8438c68591f..31e7cedd9f8 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -81,6 +81,7 @@ #ifdef __KERNEL__ #include <linux/config.h> #include <linux/types.h> +#include <net/request_sock.h> #include <net/sock.h> #include <linux/igmp.h> #include <net/flow.h> @@ -107,6 +108,26 @@ struct ip_options { #define optlength(opt) (sizeof(struct ip_options) + opt->optlen) +struct inet_request_sock { + struct request_sock req; + u32 loc_addr; + u32 rmt_addr; + u16 rmt_port; + u16 snd_wscale : 4, + rcv_wscale : 4, + tstamp_ok : 1, + sack_ok : 1, + wscale_ok : 1, + ecn_ok : 1, + acked : 1; + struct ip_options *opt; +}; + +static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) +{ + return (struct inet_request_sock *)sk; +} + struct ipv6_pinfo; struct inet_sock { diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ab0d0efbf24..6fcd6a0ade2 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -193,6 +193,19 @@ struct inet6_skb_parm { #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) +struct tcp6_request_sock { + struct tcp_request_sock req; + struct in6_addr loc_addr; + struct in6_addr rmt_addr; + struct sk_buff *pktopts; + int iif; +}; + +static inline struct tcp6_request_sock *tcp6_rsk(const struct request_sock *sk) +{ + return (struct tcp6_request_sock *)sk; +} + /** * struct ipv6_pinfo - ipv6 private area * diff --git a/include/linux/netlink.h b/include/linux/netlink.h index b2738ac8bc9..e38407a23d0 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -156,7 +156,7 @@ struct netlink_notify }; static __inline__ struct nlmsghdr * -__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len) +__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = NLMSG_LENGTH(len); @@ -164,15 +164,31 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len) nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; - nlh->nlmsg_flags = 0; + nlh->nlmsg_flags = flags; nlh->nlmsg_pid = pid; nlh->nlmsg_seq = seq; return nlh; } +#define NLMSG_NEW(skb, pid, seq, type, len, flags) \ +({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) \ + goto nlmsg_failure; \ + __nlmsg_put(skb, pid, seq, type, len, flags); }) + #define NLMSG_PUT(skb, pid, seq, type, len) \ -({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) goto nlmsg_failure; \ - __nlmsg_put(skb, pid, seq, type, len); }) + NLMSG_NEW(skb, pid, seq, type, len, 0) + +#define NLMSG_NEW_ANSWER(skb, cb, type, len, flags) \ + NLMSG_NEW(skb, NETLINK_CB((cb)->skb).pid, \ + (cb)->nlh->nlmsg_seq, type, len, flags) + +#define NLMSG_END(skb, nlh) \ +({ (nlh)->nlmsg_len = (skb)->tail - (unsigned char *) (nlh); \ + (skb)->len; }) + +#define NLMSG_CANCEL(skb, nlh) \ +({ skb_trim(skb, (unsigned char *) (nlh) - (skb)->data); \ + -1; }) extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 91ac97c2077..e68dbf0bf57 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -89,6 +89,13 @@ enum { RTM_GETANYCAST = 62, #define RTM_GETANYCAST RTM_GETANYCAST + RTM_NEWNEIGHTBL = 64, +#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL + RTM_GETNEIGHTBL = 66, +#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL + RTM_SETNEIGHTBL, +#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -493,6 +500,106 @@ struct nda_cacheinfo __u32 ndm_refcnt; }; + +/***************************************************************** + * Neighbour tables specific messages. + * + * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the + * NLM_F_DUMP flag set. Every neighbour table configuration is + * spread over multiple messages to avoid running into message + * size limits on systems with many interfaces. The first message + * in the sequence transports all not device specific data such as + * statistics, configuration, and the default parameter set. + * This message is followed by 0..n messages carrying device + * specific parameter sets. + * Although the ordering should be sufficient, NDTA_NAME can be + * used to identify sequences. The initial message can be identified + * by checking for NDTA_CONFIG. The device specific messages do + * not contain this TLV but have NDTPA_IFINDEX set to the + * corresponding interface index. + * + * To change neighbour table attributes, send RTM_SETNEIGHTBL + * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], + * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked + * otherwise. Device specific parameter sets can be changed by + * setting NDTPA_IFINDEX to the interface index of the corresponding + * device. + ****/ + +struct ndt_stats +{ + __u64 ndts_allocs; + __u64 ndts_destroys; + __u64 ndts_hash_grows; + __u64 ndts_res_failed; + __u64 ndts_lookups; + __u64 ndts_hits; + __u64 ndts_rcv_probes_mcast; + __u64 ndts_rcv_probes_ucast; + __u64 ndts_periodic_gc_runs; + __u64 ndts_forced_gc_runs; +}; + +enum { + NDTPA_UNSPEC, + NDTPA_IFINDEX, /* u32, unchangeable */ + NDTPA_REFCNT, /* u32, read-only */ + NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ + NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ + NDTPA_RETRANS_TIME, /* u64, msecs */ + NDTPA_GC_STALETIME, /* u64, msecs */ + NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ + NDTPA_QUEUE_LEN, /* u32 */ + NDTPA_APP_PROBES, /* u32 */ + NDTPA_UCAST_PROBES, /* u32 */ + NDTPA_MCAST_PROBES, /* u32 */ + NDTPA_ANYCAST_DELAY, /* u64, msecs */ + NDTPA_PROXY_DELAY, /* u64, msecs */ + NDTPA_PROXY_QLEN, /* u32 */ + NDTPA_LOCKTIME, /* u64, msecs */ + __NDTPA_MAX +}; +#define NDTPA_MAX (__NDTPA_MAX - 1) + +struct ndtmsg +{ + __u8 ndtm_family; + __u8 ndtm_pad1; + __u16 ndtm_pad2; +}; + +struct ndt_config +{ + __u16 ndtc_key_len; + __u16 ndtc_entry_size; + __u32 ndtc_entries; + __u32 ndtc_last_flush; /* delta to now in msecs */ + __u32 ndtc_last_rand; /* delta to now in msecs */ + __u32 ndtc_hash_rnd; + __u32 ndtc_hash_mask; + __u32 ndtc_hash_chain_gc; + __u32 ndtc_proxy_qlen; +}; + +enum { + NDTA_UNSPEC, + NDTA_NAME, /* char *, unchangeable */ + NDTA_THRESH1, /* u32 */ + NDTA_THRESH2, /* u32 */ + NDTA_THRESH3, /* u32 */ + NDTA_CONFIG, /* struct ndt_config, read-only */ + NDTA_PARMS, /* nested TLV NDTPA_* */ + NDTA_STATS, /* struct ndt_stats, read-only */ + NDTA_GC_INTERVAL, /* u64, msecs */ + __NDTA_MAX +}; +#define NDTA_MAX (__NDTA_MAX - 1) + +#define NDTA_RTA(r) ((struct rtattr*)(((char*)(r)) + \ + NLMSG_ALIGN(sizeof(struct ndtmsg)))) +#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndtmsg)) + + /**** * General form of address family dependent message. ****/ @@ -789,6 +896,75 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi ({ if (unlikely(skb_tailroom(skb) < (int)(attrlen))) \ goto rtattr_failure; \ memcpy(skb_put(skb, RTA_ALIGN(attrlen)), data, attrlen); }) + +#define RTA_PUT_U8(skb, attrtype, value) \ +({ u8 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u8), &_tmp); }) + +#define RTA_PUT_U16(skb, attrtype, value) \ +({ u16 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u16), &_tmp); }) + +#define RTA_PUT_U32(skb, attrtype, value) \ +({ u32 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u32), &_tmp); }) + +#define RTA_PUT_U64(skb, attrtype, value) \ +({ u64 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u64), &_tmp); }) + +#define RTA_PUT_SECS(skb, attrtype, value) \ + RTA_PUT_U64(skb, attrtype, (value) / HZ) + +#define RTA_PUT_MSECS(skb, attrtype, value) \ + RTA_PUT_U64(skb, attrtype, jiffies_to_msecs(value)) + +#define RTA_PUT_STRING(skb, attrtype, value) \ + RTA_PUT(skb, attrtype, strlen(value) + 1, value) + +#define RTA_PUT_FLAG(skb, attrtype) \ + RTA_PUT(skb, attrtype, 0, NULL); + +#define RTA_NEST(skb, type) \ +({ struct rtattr *__start = (struct rtattr *) (skb)->tail; \ + RTA_PUT(skb, type, 0, NULL); \ + __start; }) + +#define RTA_NEST_END(skb, start) \ +({ (start)->rta_len = ((skb)->tail - (unsigned char *) (start)); \ + (skb)->len; }) + +#define RTA_NEST_CANCEL(skb, start) \ +({ if (start) \ + skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ + -1; }) + +#define RTA_GET_U8(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u8)) \ + goto rtattr_failure; \ + *(u8 *) RTA_DATA(rta); }) + +#define RTA_GET_U16(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u16)) \ + goto rtattr_failure; \ + *(u16 *) RTA_DATA(rta); }) + +#define RTA_GET_U32(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u32)) \ + goto rtattr_failure; \ + *(u32 *) RTA_DATA(rta); }) + +#define RTA_GET_U64(rta) \ +({ u64 _tmp; \ + if (!rta || RTA_PAYLOAD(rta) < sizeof(u64)) \ + goto rtattr_failure; \ + memcpy(&_tmp, RTA_DATA(rta), sizeof(_tmp)); \ + _tmp; }) + +#define RTA_GET_FLAG(rta) (!!(rta)) + +#define RTA_GET_SECS(rta) ((unsigned long) RTA_GET_U64(rta) * HZ) +#define RTA_GET_MSECS(rta) (msecs_to_jiffies((unsigned long) RTA_GET_U64(rta))) static inline struct rtattr * __rta_reserve(struct sk_buff *skb, int attrtype, int attrlen) diff --git a/include/linux/slab.h b/include/linux/slab.h index 7d66385ae75..76cf7e60216 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -64,6 +64,7 @@ extern int kmem_cache_shrink(kmem_cache_t *); extern void *kmem_cache_alloc(kmem_cache_t *, unsigned int __nocast); extern void kmem_cache_free(kmem_cache_t *, void *); extern unsigned int kmem_cache_size(kmem_cache_t *); +extern const char *kmem_cache_name(kmem_cache_t *); extern kmem_cache_t *kmem_find_general_cachep(size_t size, int gfpflags); /* Size description struct for general caches. */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 14a55e3e3a5..97a7c9e03df 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -230,6 +230,17 @@ struct tcp_options_received { __u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ }; +struct tcp_request_sock { + struct inet_request_sock req; + __u32 rcv_isn; + __u32 snt_isn; +}; + +static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) +{ + return (struct tcp_request_sock *)req; +} + struct tcp_sock { /* inet_sock has to be the first member of tcp_sock */ struct inet_sock inet; @@ -368,22 +379,7 @@ struct tcp_sock { __u32 total_retrans; /* Total retransmits for entire connection */ - /* The syn_wait_lock is necessary only to avoid proc interface having - * to grab the main lock sock while browsing the listening hash - * (otherwise it's deadlock prone). - * This lock is acquired in read mode only from listening_get_next() - * and it's acquired in write mode _only_ from code that is actively - * changing the syn_wait_queue. All readers that are holding - * the master sock lock don't need to grab this lock in read mode - * too as the syn_wait_queue writes are always protected from - * the main sock lock. - */ - rwlock_t syn_wait_lock; - struct tcp_listen_opt *listen_opt; - - /* FIFO of established children */ - struct open_request *accept_queue; - struct open_request *accept_queue_tail; + struct request_sock_queue accept_queue; /* FIFO of established children */ unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index fd2ef742a9f..d68391a9b9f 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -174,6 +174,8 @@ enum xfrm_attr_type_t { XFRMA_ALG_COMP, /* struct xfrm_algo */ XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */ XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */ + XFRMA_SA, + XFRMA_POLICY, __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -257,5 +259,7 @@ struct xfrm_usersa_flush { #define XFRMGRP_ACQUIRE 1 #define XFRMGRP_EXPIRE 2 +#define XFRMGRP_SA 4 +#define XFRMGRP_POLICY 8 #endif /* _LINUX_XFRM_H */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 4f33bbc21e7..89809891e5a 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -65,11 +65,10 @@ struct neighbour; struct neigh_parms { + struct net_device *dev; struct neigh_parms *next; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; - int entries; - void *priv; void *sysctl_table; @@ -192,7 +191,6 @@ struct neigh_table atomic_t entries; rwlock_t lock; unsigned long last_rand; - struct neigh_parms *parms_list; kmem_cache_t *kmem_cachep; struct neigh_statistics *stats; struct neighbour **hash_buckets; @@ -252,6 +250,9 @@ extern int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); extern int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); extern void neigh_app_ns(struct neighbour *n); +extern int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb); +extern int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); + extern void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); extern void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); extern void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); diff --git a/include/net/request_sock.h b/include/net/request_sock.h new file mode 100644 index 00000000000..72fd6f5e86b --- /dev/null +++ b/include/net/request_sock.h @@ -0,0 +1,255 @@ +/* + * NET Generic infrastructure for Network protocols. + * + * Definitions for request_sock + * + * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * + * From code originally in include/net/tcp.h + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _REQUEST_SOCK_H +#define _REQUEST_SOCK_H + +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <net/sock.h> + +struct request_sock; +struct sk_buff; +struct dst_entry; +struct proto; + +struct request_sock_ops { + int family; + kmem_cache_t *slab; + int obj_size; + int (*rtx_syn_ack)(struct sock *sk, + struct request_sock *req, + struct dst_entry *dst); + void (*send_ack)(struct sk_buff *skb, + struct request_sock *req); + void (*send_reset)(struct sk_buff *skb); + void (*destructor)(struct request_sock *req); +}; + +/* struct request_sock - mini sock to represent a connection request + */ +struct request_sock { + struct request_sock *dl_next; /* Must be first member! */ + u16 mss; + u8 retrans; + u8 __pad; + /* The following two fields can be easily recomputed I think -AK */ + u32 window_clamp; /* window clamp at creation time */ + u32 rcv_wnd; /* rcv_wnd offered first time */ + u32 ts_recent; + unsigned long expires; + struct request_sock_ops *rsk_ops; + struct sock *sk; +}; + +static inline struct request_sock *reqsk_alloc(struct request_sock_ops *ops) +{ + struct request_sock *req = kmem_cache_alloc(ops->slab, SLAB_ATOMIC); + + if (req != NULL) + req->rsk_ops = ops; + + return req; +} + +static inline void __reqsk_free(struct request_sock *req) +{ + kmem_cache_free(req->rsk_ops->slab, req); +} + +static inline void reqsk_free(struct request_sock *req) +{ + req->rsk_ops->destructor(req); + __reqsk_free(req); +} + +extern int sysctl_max_syn_backlog; + +/** struct listen_sock - listen state + * + * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs + */ +struct listen_sock { + u8 max_qlen_log; + /* 3 bytes hole, try to use */ + int qlen; + int qlen_young; + int clock_hand; + u32 hash_rnd; + struct request_sock *syn_table[0]; +}; + +/** struct request_sock_queue - queue of request_socks + * + * @rskq_accept_head - FIFO head of established children + * @rskq_accept_tail - FIFO tail of established children + * @syn_wait_lock - serializer + * + * %syn_wait_lock is necessary only to avoid proc interface having to grab the main + * lock sock while browsing the listening hash (otherwise it's deadlock prone). + * + * This lock is acquired in read mode only from listening_get_next() seq_file + * op and it's acquired in write mode _only_ from code that is actively + * changing rskq_accept_head. All readers that are holding the master sock lock + * don't need to grab this lock in read mode too as rskq_accept_head. writes + * are always protected from the main sock lock. + */ +struct request_sock_queue { + struct request_sock *rskq_accept_head; + struct request_sock *rskq_accept_tail; + rwlock_t syn_wait_lock; + struct listen_sock *listen_opt; +}; + +extern int reqsk_queue_alloc(struct request_sock_queue *queue, + const int nr_table_entries); + +static inline struct listen_sock *reqsk_queue_yank_listen_sk(struct request_sock_queue *queue) +{ + struct listen_sock *lopt; + + write_lock_bh(&queue->syn_wait_lock); + lopt = queue->listen_opt; + queue->listen_opt = NULL; + write_unlock_bh(&queue->syn_wait_lock); + + return lopt; +} + +static inline void reqsk_queue_destroy(struct request_sock_queue *queue) +{ + kfree(reqsk_queue_yank_listen_sk(queue)); +} + +static inline struct request_sock * + reqsk_queue_yank_acceptq(struct request_sock_queue *queue) +{ + struct request_sock *req = queue->rskq_accept_head; + + queue->rskq_accept_head = queue->rskq_accept_head = NULL; + return req; +} + +static inline int reqsk_queue_empty(struct request_sock_queue *queue) +{ + return queue->rskq_accept_head == NULL; +} + +static inline void reqsk_queue_unlink(struct request_sock_queue *queue, + struct request_sock *req, + struct request_sock **prev_req) +{ + write_lock(&queue->syn_wait_lock); + *prev_req = req->dl_next; + write_unlock(&queue->syn_wait_lock); +} + +static inline void reqsk_queue_add(struct request_sock_queue *queue, + struct request_sock *req, + struct sock *parent, + struct sock *child) +{ + req->sk = child; + sk_acceptq_added(parent); + + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_head = req; + else + queue->rskq_accept_tail->dl_next = req; + + queue->rskq_accept_tail = req; + req->dl_next = NULL; +} + +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue) +{ + struct request_sock *req = queue->rskq_accept_head; + + BUG_TRAP(req != NULL); + + queue->rskq_accept_head = req->dl_next; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + + return req; +} + +static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue, + struct sock *parent) +{ + struct request_sock *req = reqsk_queue_remove(queue); + struct sock *child = req->sk; + + BUG_TRAP(child != NULL); + + sk_acceptq_removed(parent); + __reqsk_free(req); + return child; +} + +static inline int reqsk_queue_removed(struct request_sock_queue *queue, + struct request_sock *req) +{ + struct listen_sock *lopt = queue->listen_opt; + + if (req->retrans == 0) + --lopt->qlen_young; + + return --lopt->qlen; +} + +static inline int reqsk_queue_added(struct request_sock_queue *queue) +{ + struct listen_sock *lopt = queue->listen_opt; + const int prev_qlen = lopt->qlen; + + lopt->qlen_young++; + lopt->qlen++; + return prev_qlen; +} + +static inline int reqsk_queue_len(struct request_sock_queue *queue) +{ + return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; +} + +static inline int reqsk_queue_len_young(struct request_sock_queue *queue) +{ + return queue->listen_opt->qlen_young; +} + +static inline int reqsk_queue_is_full(struct request_sock_queue *queue) +{ + return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; +} + +static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned timeout) +{ + struct listen_sock *lopt = queue->listen_opt; + + req->expires = jiffies + timeout; + req->retrans = 0; + req->sk = NULL; + req->dl_next = lopt->syn_table[hash]; + + write_lock(&queue->syn_wait_lock); + lopt->syn_table[hash] = req; + write_unlock(&queue->syn_wait_lock); +} + +#endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c57504b3b51..7b97405e2db 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -172,4 +172,126 @@ tcf_destroy(struct tcf_proto *tp) kfree(tp); } +static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff_head *list) +{ + __skb_queue_tail(list, skb); + sch->qstats.backlog += skb->len; + sch->bstats.bytes += skb->len; + sch->bstats.packets++; + + return NET_XMIT_SUCCESS; +} + +static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +{ + return __qdisc_enqueue_tail(skb, sch, &sch->q); +} + +static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch, + struct sk_buff_head *list) +{ + struct sk_buff *skb = __skb_dequeue(list); + + if (likely(skb != NULL)) + sch->qstats.backlog -= skb->len; + + return skb; +} + +static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) +{ + return __qdisc_dequeue_head(sch, &sch->q); +} + +static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch, + struct sk_buff_head *list) +{ + struct sk_buff *skb = __skb_dequeue_tail(list); + + if (likely(skb != NULL)) + sch->qstats.backlog -= skb->len; + + return skb; +} + +static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch) +{ + return __qdisc_dequeue_tail(sch, &sch->q); +} + +static inline int __qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff_head *list) +{ + __skb_queue_head(list, skb); + sch->qstats.backlog += skb->len; + sch->qstats.requeues++; + + return NET_XMIT_SUCCESS; +} + +static inline int qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch) +{ + return __qdisc_requeue(skb, sch, &sch->q); +} + +static inline void __qdisc_reset_queue(struct Qdisc *sch, + struct sk_buff_head *list) +{ + /* + * We do not know the backlog in bytes of this list, it + * is up to the caller to correct it + */ + skb_queue_purge(list); +} + +static inline void qdisc_reset_queue(struct Qdisc *sch) +{ + __qdisc_reset_queue(sch, &sch->q); + sch->qstats.backlog = 0; +} + +static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch, + struct sk_buff_head *list) +{ + struct sk_buff *skb = __qdisc_dequeue_tail(sch, list); + + if (likely(skb != NULL)) { + unsigned int len = skb->len; + kfree_skb(skb); + return len; + } + + return 0; +} + +static inline unsigned int qdisc_queue_drop(struct Qdisc *sch) +{ + return __qdisc_queue_drop(sch, &sch->q); +} + +static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) +{ + kfree_skb(skb); + sch->qstats.drops++; + + return NET_XMIT_DROP; +} + +static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch) +{ + sch->qstats.drops++; + +#ifdef CONFIG_NET_CLS_POLICE + if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) + goto drop; + + return NET_XMIT_SUCCESS; + +drop: +#endif + kfree_skb(skb); + return NET_XMIT_DROP; +} + #endif diff --git a/include/net/sock.h b/include/net/sock.h index a9ef3a6a13f..e593af5b1ec 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -484,6 +484,8 @@ extern void sk_stream_kill_queues(struct sock *sk); extern int sk_wait_data(struct sock *sk, long *timeo); +struct request_sock_ops; + /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface * transport -> network interface is defined by struct inet_proto @@ -547,6 +549,8 @@ struct proto { kmem_cache_t *slab; unsigned int obj_size; + struct request_sock_ops *rsk_prot; + struct module *owner; char name[32]; diff --git a/include/net/tcp.h b/include/net/tcp.h index e71f8ba3e10..f730935b824 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -31,6 +31,7 @@ #include <linux/cache.h> #include <linux/percpu.h> #include <net/checksum.h> +#include <net/request_sock.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> @@ -563,7 +564,6 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk) #define TCP_NAGLE_PUSH 4 /* Cork is overriden for already queued data */ /* sysctl variables for tcp */ -extern int sysctl_max_syn_backlog; extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; @@ -613,74 +613,6 @@ extern atomic_t tcp_memory_allocated; extern atomic_t tcp_sockets_allocated; extern int tcp_memory_pressure; -struct open_request; - -struct or_calltable { - int family; - int (*rtx_syn_ack) (struct sock *sk, struct open_request *req, struct dst_entry*); - void (*send_ack) (struct sk_buff *skb, struct open_request *req); - void (*destructor) (struct open_request *req); - void (*send_reset) (struct sk_buff *skb); -}; - -struct tcp_v4_open_req { - __u32 loc_addr; - __u32 rmt_addr; - struct ip_options *opt; -}; - -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) -struct tcp_v6_open_req { - struct in6_addr loc_addr; - struct in6_addr rmt_addr; - struct sk_buff *pktopts; - int iif; -}; -#endif - -/* this structure is too big */ -struct open_request { - struct open_request *dl_next; /* Must be first member! */ - __u32 rcv_isn; - __u32 snt_isn; - __u16 rmt_port; - __u16 mss; - __u8 retrans; - __u8 __pad; - __u16 snd_wscale : 4, - rcv_wscale : 4, - tstamp_ok : 1, - sack_ok : 1, - wscale_ok : 1, - ecn_ok : 1, - acked : 1; - /* The following two fields can be easily recomputed I think -AK */ - __u32 window_clamp; /* window clamp at creation time */ - __u32 rcv_wnd; /* rcv_wnd offered first time */ - __u32 ts_recent; - unsigned long expires; - struct or_calltable *class; - struct sock *sk; - union { - struct tcp_v4_open_req v4_req; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - struct tcp_v6_open_req v6_req; -#endif - } af; -}; - -/* SLAB cache for open requests. */ -extern kmem_cache_t *tcp_openreq_cachep; - -#define tcp_openreq_alloc() kmem_cache_alloc(tcp_openreq_cachep, SLAB_ATOMIC) -#define tcp_openreq_fastfree(req) kmem_cache_free(tcp_openreq_cachep, req) - -static inline void tcp_openreq_free(struct open_request *req) -{ - req->class->destructor(req); - tcp_openreq_fastfree(req); -} - #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #define TCP_INET_FAMILY(fam) ((fam) == AF_INET) #else @@ -708,7 +640,7 @@ struct tcp_func { struct sock * (*syn_recv_sock) (struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst); int (*remember_stamp) (struct sock *sk); @@ -852,8 +784,8 @@ extern enum tcp_tw_status tcp_timewait_state_process(struct tcp_tw_bucket *tw, unsigned len); extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, - struct open_request *req, - struct open_request **prev); + struct request_sock *req, + struct request_sock **prev); extern int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); @@ -903,12 +835,12 @@ extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); extern struct sock * tcp_create_openreq_child(struct sock *sk, - struct open_request *req, + struct request_sock *req, struct sk_buff *skb); extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst); extern int tcp_v4_do_rcv(struct sock *sk, @@ -922,7 +854,7 @@ extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct open_request *req); + struct request_sock *req); extern int tcp_disconnect(struct sock *sk, int flags); @@ -1750,99 +1682,71 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_acceptq_queue(struct sock *sk, struct open_request *req, +static inline void tcp_acceptq_queue(struct sock *sk, struct request_sock *req, struct sock *child) { - struct tcp_sock *tp = tcp_sk(sk); - - req->sk = child; - sk_acceptq_added(sk); - - if (!tp->accept_queue_tail) { - tp->accept_queue = req; - } else { - tp->accept_queue_tail->dl_next = req; - } - tp->accept_queue_tail = req; - req->dl_next = NULL; + reqsk_queue_add(&tcp_sk(sk)->accept_queue, req, sk, child); } -struct tcp_listen_opt -{ - u8 max_qlen_log; /* log_2 of maximal queued SYNs */ - int qlen; - int qlen_young; - int clock_hand; - u32 hash_rnd; - struct open_request *syn_table[TCP_SYNQ_HSIZE]; -}; - static inline void -tcp_synq_removed(struct sock *sk, struct open_request *req) +tcp_synq_removed(struct sock *sk, struct request_sock *req) { - struct tcp_listen_opt *lopt = tcp_sk(sk)->listen_opt; - - if (--lopt->qlen == 0) + if (reqsk_queue_removed(&tcp_sk(sk)->accept_queue, req) == 0) tcp_delete_keepalive_timer(sk); - if (req->retrans == 0) - lopt->qlen_young--; } static inline void tcp_synq_added(struct sock *sk) { - struct tcp_listen_opt *lopt = tcp_sk(sk)->listen_opt; - - if (lopt->qlen++ == 0) + if (reqsk_queue_added(&tcp_sk(sk)->accept_queue) == 0) tcp_reset_keepalive_timer(sk, TCP_TIMEOUT_INIT); - lopt->qlen_young++; } static inline int tcp_synq_len(struct sock *sk) { - return tcp_sk(sk)->listen_opt->qlen; + return reqsk_queue_len(&tcp_sk(sk)->accept_queue); } static inline int tcp_synq_young(struct sock *sk) { - return tcp_sk(sk)->listen_opt->qlen_young; + return reqsk_queue_len_young(&tcp_sk(sk)->accept_queue); } static inline int tcp_synq_is_full(struct sock *sk) { - return tcp_synq_len(sk) >> tcp_sk(sk)->listen_opt->max_qlen_log; + return reqsk_queue_is_full(&tcp_sk(sk)->accept_queue); } -static inline void tcp_synq_unlink(struct tcp_sock *tp, struct open_request *req, - struct open_request **prev) +static inline void tcp_synq_unlink(struct tcp_sock *tp, struct request_sock *req, + struct request_sock **prev) { - write_lock(&tp->syn_wait_lock); - *prev = req->dl_next; - write_unlock(&tp->syn_wait_lock); + reqsk_queue_unlink(&tp->accept_queue, req, prev); } -static inline void tcp_synq_drop(struct sock *sk, struct open_request *req, - struct open_request **prev) +static inline void tcp_synq_drop(struct sock *sk, struct request_sock *req, + struct request_sock **prev) { tcp_synq_unlink(tcp_sk(sk), req, prev); tcp_synq_removed(sk, req); - tcp_openreq_free(req); + reqsk_free(req); } -static __inline__ void tcp_openreq_init(struct open_request *req, +static __inline__ void tcp_openreq_init(struct request_sock *req, struct tcp_options_received *rx_opt, struct sk_buff *skb) { + struct inet_request_sock *ireq = inet_rsk(req); + req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - req->tstamp_ok = rx_opt->tstamp_ok; - req->sack_ok = rx_opt->sack_ok; - req->snd_wscale = rx_opt->snd_wscale; - req->wscale_ok = rx_opt->wscale_ok; - req->acked = 0; - req->ecn_ok = 0; - req->rmt_port = skb->h.th->source; + ireq->tstamp_ok = rx_opt->tstamp_ok; + ireq->sack_ok = rx_opt->sack_ok; + ireq->snd_wscale = rx_opt->snd_wscale; + ireq->wscale_ok = rx_opt->wscale_ok; + ireq->acked = 0; + ireq->ecn_ok = 0; + ireq->rmt_port = skb->h.th->source; } extern void tcp_enter_memory_pressure(void); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index dc1456389a9..64980ee8c92 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -2,6 +2,7 @@ #define _NET_TCP_ECN_H_ 1 #include <net/inet_ecn.h> +#include <net/request_sock.h> #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH)) @@ -38,9 +39,9 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct tcp_sock *tp, } static __inline__ void -TCP_ECN_make_synack(struct open_request *req, struct tcphdr *th) +TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th) { - if (req->ecn_ok) + if (inet_rsk(req)->ecn_ok) th->ece = 1; } @@ -111,16 +112,16 @@ static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th) } static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, - struct open_request *req) + struct request_sock *req) { - tp->ecn_flags = req->ecn_ok ? TCP_ECN_OK : 0; + tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0; } static __inline__ void -TCP_ECN_create_request(struct open_request *req, struct tcphdr *th) +TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th) { if (sysctl_tcp_ecn && th->ece && th->cwr) - req->ecn_ok = 1; + inet_rsk(req)->ecn_ok = 1; } #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d675836ba6c..0e65e02b7a1 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -158,6 +158,20 @@ enum { XFRM_STATE_DEAD }; +/* callback structure passed from either netlink or pfkey */ +struct km_event +{ + union { + u32 hard; + u32 proto; + u32 byid; + } data; + + u32 seq; + u32 pid; + u32 event; +}; + struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { @@ -179,6 +193,8 @@ struct xfrm_policy_afinfo { extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo); extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo); +extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c); +extern void km_state_notify(struct xfrm_state *x, struct km_event *c); #define XFRM_ACQ_EXPIRES 30 @@ -290,11 +306,11 @@ struct xfrm_mgr { struct list_head list; char *id; - int (*notify)(struct xfrm_state *x, int event); + int (*notify)(struct xfrm_state *x, struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir); struct xfrm_policy *(*compile_policy)(u16 family, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport); - int (*notify_policy)(struct xfrm_policy *x, int dir, int event); + int (*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c); }; extern int xfrm_register_km(struct xfrm_mgr *km); @@ -656,7 +672,7 @@ static inline int xfrm_sk_clone_policy(struct sock *sk) return 0; } -extern void xfrm_policy_delete(struct xfrm_policy *pol, int dir); +extern int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { @@ -817,7 +833,7 @@ extern int xfrm_state_add(struct xfrm_state *x); extern int xfrm_state_update(struct xfrm_state *x); extern struct xfrm_state *xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family); extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq); -extern void xfrm_state_delete(struct xfrm_state *x); +extern int xfrm_state_delete(struct xfrm_state *x); extern void xfrm_state_flush(u8 proto); extern int xfrm_replay_check(struct xfrm_state *x, u32 seq); extern void xfrm_replay_advance(struct xfrm_state *x, u32 seq); diff --git a/mm/slab.c b/mm/slab.c index 84074264115..c78d343b3c5 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2620,6 +2620,12 @@ unsigned int kmem_cache_size(kmem_cache_t *cachep) } EXPORT_SYMBOL(kmem_cache_size); +const char *kmem_cache_name(kmem_cache_t *cachep) +{ + return cachep->name; +} +EXPORT_SYMBOL_GPL(kmem_cache_name); + struct ccupdate_struct { kmem_cache_t *cachep; struct array_cache *new[NR_CPUS]; diff --git a/net/core/Makefile b/net/core/Makefile index 81f03243fe2..5e0c56b7f60 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -2,7 +2,8 @@ # Makefile for the Linux networking core. # -obj-y := sock.o skbuff.o iovec.o datagram.o stream.o scm.o gen_stats.o gen_estimator.o +obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ + gen_stats.o gen_estimator.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 43bdc521e20..f6bdcad47da 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1276,9 +1276,14 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, INIT_RCU_HEAD(&p->rcu_head); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); - if (dev && dev->neigh_setup && dev->neigh_setup(dev, p)) { - kfree(p); - return NULL; + if (dev) { + if (dev->neigh_setup && dev->neigh_setup(dev, p)) { + kfree(p); + return NULL; + } + + dev_hold(dev); + p->dev = dev; } p->sysctl_table = NULL; write_lock_bh(&tbl->lock); @@ -1309,6 +1314,8 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) *p = parms->next; parms->dead = 1; write_unlock_bh(&tbl->lock); + if (parms->dev) + dev_put(parms->dev); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); return; } @@ -1546,20 +1553,323 @@ out: return err; } +static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) +{ + struct rtattr *nest = NULL; + + nest = RTA_NEST(skb, NDTA_PARMS); + + if (parms->dev) + RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); + + RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); + RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); + RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); + RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); + RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); + RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); + RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, + parms->base_reachable_time); + RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); + RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); + RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); + RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); + RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); + RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); + + return RTA_NEST_END(skb, nest); + +rtattr_failure: + return RTA_NEST_CANCEL(skb, nest); +} + +static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlmsghdr *nlh; + struct ndtmsg *ndtmsg; + + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), + NLM_F_MULTI); + + ndtmsg = NLMSG_DATA(nlh); + + read_lock_bh(&tbl->lock); + ndtmsg->ndtm_family = tbl->family; + + RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); + RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); + RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); + RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); + RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); + + { + unsigned long now = jiffies; + unsigned int flush_delta = now - tbl->last_flush; + unsigned int rand_delta = now - tbl->last_rand; + + struct ndt_config ndc = { + .ndtc_key_len = tbl->key_len, + .ndtc_entry_size = tbl->entry_size, + .ndtc_entries = atomic_read(&tbl->entries), + .ndtc_last_flush = jiffies_to_msecs(flush_delta), + .ndtc_last_rand = jiffies_to_msecs(rand_delta), + .ndtc_hash_rnd = tbl->hash_rnd, + .ndtc_hash_mask = tbl->hash_mask, + .ndtc_hash_chain_gc = tbl->hash_chain_gc, + .ndtc_proxy_qlen = tbl->proxy_queue.qlen, + }; + + RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + } + + { + int cpu; + struct ndt_stats ndst; + + memset(&ndst, 0, sizeof(ndst)); + + for (cpu = 0; cpu < NR_CPUS; cpu++) { + struct neigh_statistics *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(tbl->stats, cpu); + ndst.ndts_allocs += st->allocs; + ndst.ndts_destroys += st->destroys; + ndst.ndts_hash_grows += st->hash_grows; + ndst.ndts_res_failed += st->res_failed; + ndst.ndts_lookups += st->lookups; + ndst.ndts_hits += st->hits; + ndst.ndts_rcv_probes_mcast += st->rcv_probes_mcast; + ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; + ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; + ndst.ndts_forced_gc_runs += st->forced_gc_runs; + } + + RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + } + + BUG_ON(tbl->parms.dev); + if (neightbl_fill_parms(skb, &tbl->parms) < 0) + goto rtattr_failure; + + read_unlock_bh(&tbl->lock); + return NLMSG_END(skb, nlh); + +rtattr_failure: + read_unlock_bh(&tbl->lock); + return NLMSG_CANCEL(skb, nlh); + +nlmsg_failure: + return -1; +} + +static int neightbl_fill_param_info(struct neigh_table *tbl, + struct neigh_parms *parms, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct ndtmsg *ndtmsg; + struct nlmsghdr *nlh; + + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), + NLM_F_MULTI); + + ndtmsg = NLMSG_DATA(nlh); + + read_lock_bh(&tbl->lock); + ndtmsg->ndtm_family = tbl->family; + RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); + + if (neightbl_fill_parms(skb, parms) < 0) + goto rtattr_failure; + + read_unlock_bh(&tbl->lock); + return NLMSG_END(skb, nlh); + +rtattr_failure: + read_unlock_bh(&tbl->lock); + return NLMSG_CANCEL(skb, nlh); + +nlmsg_failure: + return -1; +} + +static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, + int ifindex) +{ + struct neigh_parms *p; + + for (p = &tbl->parms; p; p = p->next) + if ((p->dev && p->dev->ifindex == ifindex) || + (!p->dev && !ifindex)) + return p; + + return NULL; +} + +int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct neigh_table *tbl; + struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); + struct rtattr **tb = arg; + int err = -EINVAL; + + if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) + return -EINVAL; + + read_lock(&neigh_tbl_lock); + for (tbl = neigh_tables; tbl; tbl = tbl->next) { + if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) + continue; + + if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + break; + } + + if (tbl == NULL) { + err = -ENOENT; + goto errout; + } + + /* + * We acquire tbl->lock to be nice to the periodic timers and + * make sure they always see a consistent set of values. + */ + write_lock_bh(&tbl->lock); + + if (tb[NDTA_THRESH1 - 1]) + tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); + + if (tb[NDTA_THRESH2 - 1]) + tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); + + if (tb[NDTA_THRESH3 - 1]) + tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); + + if (tb[NDTA_GC_INTERVAL - 1]) + tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); + + if (tb[NDTA_PARMS - 1]) { + struct rtattr *tbp[NDTPA_MAX]; + struct neigh_parms *p; + u32 ifindex = 0; + + if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) + goto rtattr_failure; + + if (tbp[NDTPA_IFINDEX - 1]) + ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + + p = lookup_neigh_params(tbl, ifindex); + if (p == NULL) { + err = -ENOENT; + goto rtattr_failure; + } + + if (tbp[NDTPA_QUEUE_LEN - 1]) + p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); + + if (tbp[NDTPA_PROXY_QLEN - 1]) + p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); + + if (tbp[NDTPA_APP_PROBES - 1]) + p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); + + if (tbp[NDTPA_UCAST_PROBES - 1]) + p->ucast_probes = + RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); + + if (tbp[NDTPA_MCAST_PROBES - 1]) + p->mcast_probes = + RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); + + if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) + p->base_reachable_time = + RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); + + if (tbp[NDTPA_GC_STALETIME - 1]) + p->gc_staletime = + RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + + if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) + p->delay_probe_time = + RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + + if (tbp[NDTPA_RETRANS_TIME - 1]) + p->retrans_time = + RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + + if (tbp[NDTPA_ANYCAST_DELAY - 1]) + p->anycast_delay = + RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + + if (tbp[NDTPA_PROXY_DELAY - 1]) + p->proxy_delay = + RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); + + if (tbp[NDTPA_LOCKTIME - 1]) + p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); + } + + err = 0; + +rtattr_failure: + write_unlock_bh(&tbl->lock); +errout: + read_unlock(&neigh_tbl_lock); + return err; +} + +int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx, family; + int s_idx = cb->args[0]; + struct neigh_table *tbl; + + family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + + read_lock(&neigh_tbl_lock); + for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + struct neigh_parms *p; + + if (idx < s_idx || (family && tbl->family != family)) + continue; + + if (neightbl_fill_info(tbl, skb, cb) <= 0) + break; + + for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { + if (idx < s_idx) + continue; + + if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + goto out; + } + + } +out: + read_unlock(&neigh_tbl_lock); + cb->args[0] = idx; + + return skb->len; +} static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { unsigned long now = jiffies; unsigned char *b = skb->tail; struct nda_cacheinfo ci; int locked = 0; u32 probes; - struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq, event, - sizeof(struct ndmsg)); + struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event, + sizeof(struct ndmsg), flags); struct ndmsg *ndm = NLMSG_DATA(nlh); - nlh->nlmsg_flags = pid ? NLM_F_MULTI : 0; ndm->ndm_family = n->ops->family; ndm->ndm_flags = n->flags; ndm->ndm_type = n->type; @@ -1609,7 +1919,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWNEIGH) <= 0) { + RTM_NEWNEIGH, + NLM_F_MULTI) <= 0) { read_unlock_bh(&tbl->lock); rc = -1; goto out; @@ -2018,7 +2329,7 @@ void neigh_app_ns(struct neighbour *n) if (!skb) return; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH) < 0) { + if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) { kfree_skb(skb); return; } @@ -2037,7 +2348,7 @@ static void neigh_app_notify(struct neighbour *n) if (!skb) return; - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH) < 0) { + if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) { kfree_skb(skb); return; } @@ -2352,6 +2663,8 @@ EXPORT_SYMBOL(neigh_update); EXPORT_SYMBOL(neigh_update_hhs); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); +EXPORT_SYMBOL(neightbl_dump_info); +EXPORT_SYMBOL(neightbl_set); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/request_sock.c b/net/core/request_sock.c new file mode 100644 index 00000000000..bb55675f068 --- /dev/null +++ b/net/core/request_sock.c @@ -0,0 +1,64 @@ +/* + * NET Generic infrastructure for Network protocols. + * + * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * + * From code originally in include/net/tcp.h + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/string.h> + +#include <net/request_sock.h> + +/* + * Maximum number of SYN_RECV sockets in queue per LISTEN socket. + * One SYN_RECV socket costs about 80bytes on a 32bit machine. + * It would be better to replace it with a global counter for all sockets + * but then some measure against one socket starving all other sockets + * would be needed. + * + * It was 128 by default. Experiments with real servers show, that + * it is absolutely not enough even at 100conn/sec. 256 cures most + * of problems. This value is adjusted to 128 for very small machines + * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). + * Further increasing requires to change hash table size. + */ +int sysctl_max_syn_backlog = 256; +EXPORT_SYMBOL(sysctl_max_syn_backlog); + +int reqsk_queue_alloc(struct request_sock_queue *queue, + const int nr_table_entries) +{ + const int lopt_size = sizeof(struct listen_sock) + + nr_table_entries * sizeof(struct request_sock *); + struct listen_sock *lopt = kmalloc(lopt_size, GFP_KERNEL); + + if (lopt == NULL) + return -ENOMEM; + + memset(lopt, 0, lopt_size); + + for (lopt->max_qlen_log = 6; + (1 << lopt->max_qlen_log) < sysctl_max_syn_backlog; + lopt->max_qlen_log++); + + get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); + rwlock_init(&queue->syn_wait_lock); + queue->rskq_accept_head = queue->rskq_accept_head = NULL; + + write_lock_bh(&queue->syn_wait_lock); + queue->listen_opt = lopt; + write_unlock_bh(&queue->syn_wait_lock); + + return 0; +} + +EXPORT_SYMBOL(reqsk_queue_alloc); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 00caf4b318b..e013d836a7a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -100,6 +100,7 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), + [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), }; static const int rta_max[RTM_NR_FAMILIES] = @@ -113,6 +114,7 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, + [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) @@ -176,14 +178,14 @@ rtattr_failure: static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, - int type, u32 pid, u32 seq, u32 change) + int type, u32 pid, u32 seq, u32 change, + unsigned int flags) { struct ifinfomsg *r; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, type, sizeof(*r)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags); r = NLMSG_DATA(nlh); r->ifi_family = AF_UNSPEC; r->ifi_type = dev->type; @@ -273,7 +275,10 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { if (idx < s_idx) continue; - if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, 0) <= 0) + if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI) <= 0) break; } read_unlock(&dev_base_lock); @@ -447,7 +452,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) if (!skb) return; - if (rtnetlink_fill_ifinfo(skb, dev, type, 0, 0, change) < 0) { + if (rtnetlink_fill_ifinfo(skb, dev, type, current->pid, 0, change, 0) < 0) { kfree_skb(skb); return; } @@ -649,14 +654,16 @@ static void rtnetlink_rcv(struct sock *sk, int len) static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, - [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, - [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, + [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, + [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, + [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, + [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, }; static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) diff --git a/net/core/sock.c b/net/core/sock.c index 96e00b08698..a6ec3ada7f9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -118,6 +118,7 @@ #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> +#include <net/request_sock.h> #include <net/sock.h> #include <net/xfrm.h> #include <linux/ipsec.h> @@ -1363,6 +1364,7 @@ static LIST_HEAD(proto_list); int proto_register(struct proto *prot, int alloc_slab) { + char *request_sock_slab_name; int rc = -ENOBUFS; if (alloc_slab) { @@ -1374,6 +1376,25 @@ int proto_register(struct proto *prot, int alloc_slab) prot->name); goto out; } + + if (prot->rsk_prot != NULL) { + static const char mask[] = "request_sock_%s"; + + request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL); + if (request_sock_slab_name == NULL) + goto out_free_sock_slab; + + sprintf(request_sock_slab_name, mask, prot->name); + prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name, + prot->rsk_prot->obj_size, 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + + if (prot->rsk_prot->slab == NULL) { + printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", + prot->name); + goto out_free_request_sock_slab_name; + } + } } write_lock(&proto_list_lock); @@ -1382,6 +1403,12 @@ int proto_register(struct proto *prot, int alloc_slab) rc = 0; out: return rc; +out_free_request_sock_slab_name: + kfree(request_sock_slab_name); +out_free_sock_slab: + kmem_cache_destroy(prot->slab); + prot->slab = NULL; + goto out; } EXPORT_SYMBOL(proto_register); @@ -1395,6 +1422,14 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; } + if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) { + const char *name = kmem_cache_name(prot->rsk_prot->slab); + + kmem_cache_destroy(prot->rsk_prot->slab); + kfree(name); + prot->rsk_prot->slab = NULL; + } + list_del(&prot->node); write_unlock(&proto_list_lock); } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index ee7bf46eb78..00233ecbc9c 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -716,13 +716,13 @@ static int dn_dev_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *a } static int dn_dev_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_DECnet; @@ -755,7 +755,7 @@ static void rtmsg_ifa(int event, struct dn_ifaddr *ifa) netlink_set_err(rtnl, 0, RTMGRP_DECnet_IFADDR, ENOBUFS); return; } - if (dn_dev_fill_ifaddr(skb, ifa, 0, 0, event) < 0) { + if (dn_dev_fill_ifaddr(skb, ifa, 0, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_DECnet_IFADDR, EINVAL); return; @@ -790,7 +790,8 @@ static int dn_dev_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) if (dn_dev_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWADDR) <= 0) + RTM_NEWADDR, + NLM_F_MULTI) <= 0) goto done; } } diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index f6dfe96f45b..f32dba9e26f 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -101,7 +101,6 @@ struct neigh_table dn_neigh_table = { .id = "dn_neigh_cache", .parms ={ .tbl = &dn_neigh_table, - .entries = 0, .base_reachable_time = 30 * HZ, .retrans_time = 1 * HZ, .gc_staletime = 60 * HZ, diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 1e7b5c3ea21..2399fa8a3f8 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1465,7 +1465,8 @@ int dn_route_input(struct sk_buff *skb) return dn_route_input_slow(skb); } -static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait) +static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, + int event, int nowait, unsigned int flags) { struct dn_route *rt = (struct dn_route *)skb->dst; struct rtmsg *r; @@ -1473,9 +1474,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, int unsigned char *b = skb->tail; struct rta_cacheinfo ci; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r)); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); r = NLMSG_DATA(nlh); - nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; r->rtm_family = AF_DECnet; r->rtm_dst_len = 16; r->rtm_src_len = 0; @@ -1596,7 +1596,7 @@ int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0); + err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err == 0) goto out_free; @@ -1644,7 +1644,8 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; skb->dst = dst_clone(&rt->u.dst); if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1) <= 0) { + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + 1, NLM_F_MULTI) <= 0) { dst_release(xchg(&skb->dst, NULL)); rcu_read_unlock_bh(); goto done; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 597587d170d..1060de70bc0 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -342,14 +342,15 @@ static struct notifier_block dn_fib_rules_notifier = { .notifier_call = dn_fib_rules_event, }; -static int dn_fib_fill_rule(struct sk_buff *skb, struct dn_fib_rule *r, struct netlink_callback *cb) +static int dn_fib_fill_rule(struct sk_buff *skb, struct dn_fib_rule *r, + struct netlink_callback *cb, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, NETLINK_CREDS(cb->skb)->pid, cb->nlh->nlmsg_seq, RTM_NEWRULE, sizeof(*rtm)); + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_DECnet; rtm->rtm_dst_len = r->r_dst_len; @@ -394,7 +395,7 @@ int dn_fib_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) for(r = dn_fib_rules, idx = 0; r; r = r->r_next, idx++) { if (idx < s_idx) continue; - if (dn_fib_fill_rule(skb, r, cb) < 0) + if (dn_fib_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; } read_unlock(&dn_fib_rules_lock); diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index dad5603912b..28ba5777a25 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -270,13 +270,13 @@ static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, - struct dn_fib_info *fi) + struct dn_fib_info *fi, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*rtm)); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_DECnet; rtm->rtm_dst_len = dst_len; @@ -345,7 +345,7 @@ static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, int tb_id, if (dn_fib_dump_info(skb, pid, nlh->nlmsg_seq, event, tb_id, f->fn_type, f->fn_scope, &f->fn_key, z, - DN_FIB_INFO(f)) < 0) { + DN_FIB_INFO(f), 0) < 0) { kfree_skb(skb); return; } @@ -377,7 +377,7 @@ static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, tb->n, (f->fn_state & DN_S_ZOMBIE) ? 0 : f->fn_type, f->fn_scope, &f->fn_key, dz->dz_order, - f->fn_info) < 0) { + f->fn_info, NLM_F_MULTI) < 0) { cb->args[3] = i; return -1; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 478a30179a5..650dcb12d9a 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1030,14 +1030,13 @@ static struct notifier_block ip_netdev_notifier = { }; static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; @@ -1090,7 +1089,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) continue; if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWADDR) <= 0) { + RTM_NEWADDR, NLM_F_MULTI) <= 0) { rcu_read_unlock(); goto done; } @@ -1113,7 +1112,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa) if (!skb) netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, ENOBUFS); - else if (inet_fill_ifaddr(skb, ifa, 0, 0, event) < 0) { + else if (inet_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, EINVAL); } else { diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 6506dcc01b4..b10d6bb5ef3 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -703,7 +703,8 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, &f->fn_key, fz->fz_order, fa->fa_tos, - fa->fa_info) < 0) { + fa->fa_info, + NLM_F_MULTI) < 0) { cb->args[3] = i; return -1; } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index ac4485f75e9..b729d97cfa9 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -30,7 +30,8 @@ extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, struct kern_rta *rta, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u8 tb_id, u8 type, u8 scope, void *dst, - int dst_len, u8 tos, struct fib_info *fi); + int dst_len, u8 tos, struct fib_info *fi, + unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, int z, int tb_id, struct nlmsghdr *n, struct netlink_skb_parms *req); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 39d0aadb9a2..0b298bbc151 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -367,13 +367,14 @@ static struct notifier_block fib_rules_notifier = { static __inline__ int inet_fill_rule(struct sk_buff *skb, struct fib_rule *r, - struct netlink_callback *cb) + struct netlink_callback *cb, + unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, NETLINK_CREDS(cb->skb)->pid, cb->nlh->nlmsg_seq, RTM_NEWRULE, sizeof(*rtm)); + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = r->r_dst_len; @@ -422,7 +423,7 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) for (r=fib_rules, idx=0; r; r = r->r_next, idx++) { if (idx < s_idx) continue; - if (inet_fill_rule(skb, r, cb) < 0) + if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; } read_unlock(&fib_rules_lock); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 029362d6613..c886b28ba9f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -276,7 +276,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alias *fa, struct nlmsghdr *n, struct netlink_skb_parms *req) { struct sk_buff *skb; - u32 pid = req ? req->pid : 0; + u32 pid = req ? req->pid : n->nlmsg_pid; int size = NLMSG_SPACE(sizeof(struct rtmsg)+256); skb = alloc_skb(size, GFP_KERNEL); @@ -286,7 +286,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alias *fa, if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id, fa->fa_type, fa->fa_scope, &key, z, fa->fa_tos, - fa->fa_info) < 0) { + fa->fa_info, 0) < 0) { kfree_skb(skb); return; } @@ -932,13 +932,13 @@ u32 __fib_res_prefsrc(struct fib_result *res) int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, - struct fib_info *fi) + struct fib_info *fi, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*rtm)); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = dst_len; @@ -1035,7 +1035,7 @@ fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, } nl->nlmsg_flags = NLM_F_REQUEST; - nl->nlmsg_pid = 0; + nl->nlmsg_pid = current->pid; nl->nlmsg_seq = 0; nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm)); if (cmd == SIOCDELRT) { diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 47012b93cad..f8b172f8981 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -360,14 +360,14 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) err = copied; /* Reset and regenerate socket error */ - spin_lock_irq(&sk->sk_error_queue.lock); + spin_lock_bh(&sk->sk_error_queue.lock); sk->sk_err = 0; if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); sk->sk_error_report(sk); } else - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); out_free_skb: kfree_skb(skb); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5b1ec586bae..d1835b1bc8c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -259,7 +259,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int raw_send_hdrinc(struct sock *sk, void *from, int length, +static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, struct rtable *rt, unsigned int flags) { @@ -298,7 +298,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, int length, goto error_fault; /* We don't modify invalid header */ - if (length >= sizeof(*iph) && iph->ihl * 4 <= length) { + if (length >= sizeof(*iph) && iph->ihl * 4U <= length) { if (!iph->saddr) iph->saddr = rt->rt_src; iph->check = 0; @@ -332,7 +332,7 @@ static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg) u8 __user *type = NULL; u8 __user *code = NULL; int probed = 0; - int i; + unsigned int i; if (!msg->msg_iov) return; @@ -384,7 +384,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int err; err = -EMSGSIZE; - if (len < 0 || len > 0xFFFF) + if (len > 0xFFFF) goto out; /* @@ -514,7 +514,10 @@ done: kfree(ipc.opt); ip_rt_put(rt); -out: return err < 0 ? err : len; +out: + if (err < 0) + return err; + return len; do_confirm: dst_confirm(&rt->u.dst); @@ -610,7 +613,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, copied = skb->len; done: skb_free_datagram(sk, skb); -out: return err ? err : copied; +out: + if (err) + return err; + return copied; } static int raw_init(struct sock *sk) @@ -691,11 +697,11 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) struct sk_buff *skb; int amount = 0; - spin_lock_irq(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) amount = skb->len; - spin_unlock_irq(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a682d28e247..f4d53c91986 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2581,7 +2581,7 @@ int ip_route_output_key(struct rtable **rp, struct flowi *flp) } static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - int nowait) + int nowait, unsigned int flags) { struct rtable *rt = (struct rtable*)skb->dst; struct rtmsg *r; @@ -2591,9 +2591,8 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, #ifdef CONFIG_IP_MROUTE struct rtattr *eptr; #endif - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r)); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); r = NLMSG_DATA(nlh); - nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; @@ -2744,7 +2743,7 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, - RTM_NEWROUTE, 0); + RTM_NEWROUTE, 0, 0); if (!err) goto out_free; if (err < 0) { @@ -2781,8 +2780,8 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; skb->dst = dst_clone(&rt->u.dst); if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, 1) <= 0) { + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + 1, NLM_F_MULTI) <= 0) { dst_release(xchg(&skb->dst, NULL)); rcu_read_unlock_bh(); goto done; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index e923d2f021a..72d01444218 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -169,10 +169,10 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) return mssind < NUM_MSS ? msstab[mssind] + 1 : 0; } -extern struct or_calltable or_ipv4; +extern struct request_sock_ops tcp_request_sock_ops; static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { struct tcp_sock *tp = tcp_sk(sk); @@ -182,7 +182,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, if (child) tcp_acceptq_queue(sk, req, child); else - tcp_openreq_free(req); + reqsk_free(req); return child; } @@ -190,10 +190,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { + struct inet_request_sock *ireq; + struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); __u32 cookie = ntohl(skb->h.th->ack_seq) - 1; struct sock *ret = sk; - struct open_request *req; + struct request_sock *req; int mss; struct rtable *rt; __u8 rcv_wscale; @@ -209,19 +211,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV); - req = tcp_openreq_alloc(); ret = NULL; + req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) goto out; - req->rcv_isn = htonl(skb->h.th->seq) - 1; - req->snt_isn = cookie; + ireq = inet_rsk(req); + treq = tcp_rsk(req); + treq->rcv_isn = htonl(skb->h.th->seq) - 1; + treq->snt_isn = cookie; req->mss = mss; - req->rmt_port = skb->h.th->source; - req->af.v4_req.loc_addr = skb->nh.iph->daddr; - req->af.v4_req.rmt_addr = skb->nh.iph->saddr; - req->class = &or_ipv4; /* for savety */ - req->af.v4_req.opt = NULL; + ireq->rmt_port = skb->h.th->source; + ireq->loc_addr = skb->nh.iph->daddr; + ireq->rmt_addr = skb->nh.iph->saddr; + ireq->opt = NULL; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -229,17 +232,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, if (opt && opt->optlen) { int opt_size = sizeof(struct ip_options) + opt->optlen; - req->af.v4_req.opt = kmalloc(opt_size, GFP_ATOMIC); - if (req->af.v4_req.opt) { - if (ip_options_echo(req->af.v4_req.opt, skb)) { - kfree(req->af.v4_req.opt); - req->af.v4_req.opt = NULL; - } + ireq->opt = kmalloc(opt_size, GFP_ATOMIC); + if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) { + kfree(ireq->opt); + ireq->opt = NULL; } } - req->snd_wscale = req->rcv_wscale = req->tstamp_ok = 0; - req->wscale_ok = req->sack_ok = 0; + ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0; + ireq->wscale_ok = ireq->sack_ok = 0; req->expires = 0UL; req->retrans = 0; @@ -253,15 +254,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : - req->af.v4_req.rmt_addr), - .saddr = req->af.v4_req.loc_addr, + ireq->rmt_addr), + .saddr = ireq->loc_addr, .tos = RT_CONN_FLAGS(sk) } }, .proto = IPPROTO_TCP, .uli_u = { .ports = { .sport = skb->h.th->dest, .dport = skb->h.th->source } } }; if (ip_route_output_key(&rt, &fl)) { - tcp_openreq_free(req); + reqsk_free(req); goto out; } } @@ -272,7 +273,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, &req->rcv_wnd, &req->window_clamp, 0, &rcv_wscale); /* BTW win scale with syncookies is 0 by definition */ - req->rcv_wscale = rcv_wscale; + ireq->rcv_wscale = rcv_wscale; ret = get_cookie_sock(sk, skb, req, &rt->u.dst); out: return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d9a4fd5f1a..674bbd8cfd3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -271,7 +271,6 @@ int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics); -kmem_cache_t *tcp_openreq_cachep; kmem_cache_t *tcp_bucket_cachep; kmem_cache_t *tcp_timewait_cachep; @@ -317,7 +316,7 @@ EXPORT_SYMBOL(tcp_enter_memory_pressure); static __inline__ unsigned int tcp_listen_poll(struct sock *sk, poll_table *wait) { - return tcp_sk(sk)->accept_queue ? (POLLIN | POLLRDNORM) : 0; + return !reqsk_queue_empty(&tcp_sk(sk)->accept_queue) ? (POLLIN | POLLRDNORM) : 0; } /* @@ -463,28 +462,15 @@ int tcp_listen_start(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt; + int rc = reqsk_queue_alloc(&tp->accept_queue, TCP_SYNQ_HSIZE); + + if (rc != 0) + return rc; sk->sk_max_ack_backlog = 0; sk->sk_ack_backlog = 0; - tp->accept_queue = tp->accept_queue_tail = NULL; - rwlock_init(&tp->syn_wait_lock); tcp_delack_init(tp); - lopt = kmalloc(sizeof(struct tcp_listen_opt), GFP_KERNEL); - if (!lopt) - return -ENOMEM; - - memset(lopt, 0, sizeof(struct tcp_listen_opt)); - for (lopt->max_qlen_log = 6; ; lopt->max_qlen_log++) - if ((1 << lopt->max_qlen_log) >= sysctl_max_syn_backlog) - break; - get_random_bytes(&lopt->hash_rnd, 4); - - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = lopt; - write_unlock_bh(&tp->syn_wait_lock); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only @@ -501,10 +487,7 @@ int tcp_listen_start(struct sock *sk) } sk->sk_state = TCP_CLOSE; - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = NULL; - write_unlock_bh(&tp->syn_wait_lock); - kfree(lopt); + reqsk_queue_destroy(&tp->accept_queue); return -EADDRINUSE; } @@ -516,25 +499,23 @@ int tcp_listen_start(struct sock *sk) static void tcp_listen_stop (struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *acc_req = tp->accept_queue; - struct open_request *req; + struct listen_sock *lopt; + struct request_sock *acc_req; + struct request_sock *req; int i; tcp_delete_keepalive_timer(sk); /* make all the listen_opt local to us */ - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = NULL; - write_unlock_bh(&tp->syn_wait_lock); - tp->accept_queue = tp->accept_queue_tail = NULL; + lopt = reqsk_queue_yank_listen_sk(&tp->accept_queue); + acc_req = reqsk_queue_yank_acceptq(&tp->accept_queue); if (lopt->qlen) { for (i = 0; i < TCP_SYNQ_HSIZE; i++) { while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; lopt->qlen--; - tcp_openreq_free(req); + reqsk_free(req); /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -574,7 +555,7 @@ static void tcp_listen_stop (struct sock *sk) sock_put(child); sk_acceptq_removed(sk); - tcp_openreq_fastfree(req); + __reqsk_free(req); } BUG_TRAP(!sk->sk_ack_backlog); } @@ -1345,7 +1326,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, cleanup_rbuf(sk, copied); - if (tp->ucopy.task == user_recv) { + if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) { /* Install new reader */ if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) { user_recv = current; @@ -1868,11 +1849,11 @@ static int wait_for_connect(struct sock *sk, long timeo) prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); release_sock(sk); - if (!tp->accept_queue) + if (reqsk_queue_empty(&tp->accept_queue)) timeo = schedule_timeout(timeo); lock_sock(sk); err = 0; - if (tp->accept_queue) + if (!reqsk_queue_empty(&tp->accept_queue)) break; err = -EINVAL; if (sk->sk_state != TCP_LISTEN) @@ -1895,7 +1876,6 @@ static int wait_for_connect(struct sock *sk, long timeo) struct sock *tcp_accept(struct sock *sk, int flags, int *err) { struct tcp_sock *tp = tcp_sk(sk); - struct open_request *req; struct sock *newsk; int error; @@ -1906,37 +1886,31 @@ struct sock *tcp_accept(struct sock *sk, int flags, int *err) */ error = -EINVAL; if (sk->sk_state != TCP_LISTEN) - goto out; + goto out_err; /* Find already established connection */ - if (!tp->accept_queue) { + if (reqsk_queue_empty(&tp->accept_queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; if (!timeo) - goto out; + goto out_err; error = wait_for_connect(sk, timeo); if (error) - goto out; + goto out_err; } - req = tp->accept_queue; - if ((tp->accept_queue = req->dl_next) == NULL) - tp->accept_queue_tail = NULL; - - newsk = req->sk; - sk_acceptq_removed(sk); - tcp_openreq_fastfree(req); + newsk = reqsk_queue_get_child(&tp->accept_queue, sk); BUG_TRAP(newsk->sk_state != TCP_SYN_RECV); - release_sock(sk); - return newsk; - out: release_sock(sk); + return newsk; +out_err: + newsk = NULL; *err = error; - return NULL; + goto out; } /* @@ -2271,13 +2245,6 @@ void __init tcp_init(void) __skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb), sizeof(skb->cb)); - tcp_openreq_cachep = kmem_cache_create("tcp_open_request", - sizeof(struct open_request), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!tcp_openreq_cachep) - panic("tcp_init: Cannot alloc open_request cache."); - tcp_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct tcp_bind_bucket), 0, SLAB_HWCACHE_ALIGN, @@ -2374,7 +2341,6 @@ EXPORT_SYMBOL(tcp_destroy_sock); EXPORT_SYMBOL(tcp_disconnect); EXPORT_SYMBOL(tcp_getsockopt); EXPORT_SYMBOL(tcp_ioctl); -EXPORT_SYMBOL(tcp_openreq_cachep); EXPORT_SYMBOL(tcp_poll); EXPORT_SYMBOL(tcp_read_sock); EXPORT_SYMBOL(tcp_recvmsg); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 8faa8948f75..634befc0792 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -455,9 +455,10 @@ static int tcpdiag_dump_sock(struct sk_buff *skb, struct sock *sk, } static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, - struct open_request *req, + struct request_sock *req, u32 pid, u32 seq) { + const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *inet = inet_sk(sk); unsigned char *b = skb->tail; struct tcpdiagmsg *r; @@ -482,9 +483,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, tmo = 0; r->id.tcpdiag_sport = inet->sport; - r->id.tcpdiag_dport = req->rmt_port; - r->id.tcpdiag_src[0] = req->af.v4_req.loc_addr; - r->id.tcpdiag_dst[0] = req->af.v4_req.rmt_addr; + r->id.tcpdiag_dport = ireq->rmt_port; + r->id.tcpdiag_src[0] = ireq->loc_addr; + r->id.tcpdiag_dst[0] = ireq->rmt_addr; r->tcpdiag_expires = jiffies_to_msecs(tmo), r->tcpdiag_rqueue = 0; r->tcpdiag_wqueue = 0; @@ -493,9 +494,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, #ifdef CONFIG_IP_TCPDIAG_IPV6 if (r->tcpdiag_family == AF_INET6) { ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_src, - &req->af.v6_req.loc_addr); + &tcp6_rsk(req)->loc_addr); ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_dst, - &req->af.v6_req.rmt_addr); + &tcp6_rsk(req)->rmt_addr); } #endif nlh->nlmsg_len = skb->tail - b; @@ -513,7 +514,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct tcpdiag_entry entry; struct tcpdiagreq *r = NLMSG_DATA(cb->nlh); struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt; + struct listen_sock *lopt; struct rtattr *bc = NULL; struct inet_sock *inet = inet_sk(sk); int j, s_j; @@ -528,9 +529,9 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.family = sk->sk_family; - read_lock_bh(&tp->syn_wait_lock); + read_lock_bh(&tp->accept_queue.syn_wait_lock); - lopt = tp->listen_opt; + lopt = tp->accept_queue.listen_opt; if (!lopt || !lopt->qlen) goto out; @@ -541,13 +542,15 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, } for (j = s_j; j < TCP_SYNQ_HSIZE; j++) { - struct open_request *req, *head = lopt->syn_table[j]; + struct request_sock *req, *head = lopt->syn_table[j]; reqnum = 0; for (req = head; req; reqnum++, req = req->dl_next) { + struct inet_request_sock *ireq = inet_rsk(req); + if (reqnum < s_reqnum) continue; - if (r->id.tcpdiag_dport != req->rmt_port && + if (r->id.tcpdiag_dport != ireq->rmt_port && r->id.tcpdiag_dport) continue; @@ -555,16 +558,16 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.saddr = #ifdef CONFIG_IP_TCPDIAG_IPV6 (entry.family == AF_INET6) ? - req->af.v6_req.loc_addr.s6_addr32 : + tcp6_rsk(req)->loc_addr.s6_addr32 : #endif - &req->af.v4_req.loc_addr; + &ireq->loc_addr; entry.daddr = #ifdef CONFIG_IP_TCPDIAG_IPV6 (entry.family == AF_INET6) ? - req->af.v6_req.rmt_addr.s6_addr32 : + tcp6_rsk(req)->rmt_addr.s6_addr32 : #endif - &req->af.v4_req.rmt_addr; - entry.dport = ntohs(req->rmt_port); + &ireq->rmt_addr; + entry.dport = ntohs(ireq->rmt_port); if (!tcpdiag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) @@ -585,7 +588,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, } out: - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); return err; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index dad98e4a504..2d41d5d6ad1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -36,7 +36,7 @@ * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the - * open_request handling and moved + * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen sematics. @@ -869,21 +869,23 @@ static __inline__ u32 tcp_v4_synq_hash(u32 raddr, u16 rport, u32 rnd) return (jhash_2words(raddr, (u32) rport, rnd) & (TCP_SYNQ_HSIZE - 1)); } -static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, - struct open_request ***prevp, +static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp, + struct request_sock ***prevp, __u16 rport, __u32 raddr, __u32 laddr) { - struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *req, **prev; + struct listen_sock *lopt = tp->accept_queue.listen_opt; + struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; prev = &req->dl_next) { - if (req->rmt_port == rport && - req->af.v4_req.rmt_addr == raddr && - req->af.v4_req.loc_addr == laddr && - TCP_INET_FAMILY(req->class->family)) { + const struct inet_request_sock *ireq = inet_rsk(req); + + if (ireq->rmt_port == rport && + ireq->rmt_addr == raddr && + ireq->loc_addr == laddr && + TCP_INET_FAMILY(req->rsk_ops->family)) { BUG_TRAP(!req->sk); *prevp = prev; break; @@ -893,21 +895,13 @@ static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, return req; } -static void tcp_v4_synq_add(struct sock *sk, struct open_request *req) +static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; - u32 h = tcp_v4_synq_hash(req->af.v4_req.rmt_addr, req->rmt_port, lopt->hash_rnd); - - req->expires = jiffies + TCP_TIMEOUT_INIT; - req->retrans = 0; - req->sk = NULL; - req->dl_next = lopt->syn_table[h]; - - write_lock(&tp->syn_wait_lock); - lopt->syn_table[h] = req; - write_unlock(&tp->syn_wait_lock); + struct listen_sock *lopt = tp->accept_queue.listen_opt; + u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); + reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT); tcp_synq_added(sk); } @@ -1050,7 +1044,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) } switch (sk->sk_state) { - struct open_request *req, **prev; + struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; @@ -1065,7 +1059,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) */ BUG_TRAP(!req->sk); - if (seq != req->snt_isn) { + if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -1254,28 +1248,29 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_tw_put(tw); } -static void tcp_v4_or_send_ack(struct sk_buff *skb, struct open_request *req) +static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) { - tcp_v4_send_ack(skb, req->snt_isn + 1, req->rcv_isn + 1, req->rcv_wnd, + tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } static struct dst_entry* tcp_v4_route_req(struct sock *sk, - struct open_request *req) + struct request_sock *req) { struct rtable *rt; - struct ip_options *opt = req->af.v4_req.opt; + const struct inet_request_sock *ireq = inet_rsk(req); + struct ip_options *opt = inet_rsk(req)->opt; struct flowi fl = { .oif = sk->sk_bound_dev_if, .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : - req->af.v4_req.rmt_addr), - .saddr = req->af.v4_req.loc_addr, + ireq->rmt_addr), + .saddr = ireq->loc_addr, .tos = RT_CONN_FLAGS(sk) } }, .proto = IPPROTO_TCP, .uli_u = { .ports = { .sport = inet_sk(sk)->sport, - .dport = req->rmt_port } } }; + .dport = ireq->rmt_port } } }; if (ip_route_output_flow(&rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); @@ -1291,12 +1286,13 @@ static struct dst_entry* tcp_v4_route_req(struct sock *sk, /* * Send a SYN-ACK after having received an ACK. - * This still operates on a open_request only, not on a big + * This still operates on a request_sock only, not on a big * socket. */ -static int tcp_v4_send_synack(struct sock *sk, struct open_request *req, +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { + const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; struct sk_buff * skb; @@ -1310,14 +1306,14 @@ static int tcp_v4_send_synack(struct sock *sk, struct open_request *req, struct tcphdr *th = skb->h.th; th->check = tcp_v4_check(th, skb->len, - req->af.v4_req.loc_addr, - req->af.v4_req.rmt_addr, + ireq->loc_addr, + ireq->rmt_addr, csum_partial((char *)th, skb->len, skb->csum)); - err = ip_build_and_send_pkt(skb, sk, req->af.v4_req.loc_addr, - req->af.v4_req.rmt_addr, - req->af.v4_req.opt); + err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, + ireq->rmt_addr, + ireq->opt); if (err == NET_XMIT_CN) err = 0; } @@ -1328,12 +1324,12 @@ out: } /* - * IPv4 open_request destructor. + * IPv4 request_sock destructor. */ -static void tcp_v4_or_free(struct open_request *req) +static void tcp_v4_reqsk_destructor(struct request_sock *req) { - if (req->af.v4_req.opt) - kfree(req->af.v4_req.opt); + if (inet_rsk(req)->opt) + kfree(inet_rsk(req)->opt); } static inline void syn_flood_warning(struct sk_buff *skb) @@ -1349,7 +1345,7 @@ static inline void syn_flood_warning(struct sk_buff *skb) } /* - * Save and compile IPv4 options into the open_request if needed. + * Save and compile IPv4 options into the request_sock if needed. */ static inline struct ip_options *tcp_v4_save_options(struct sock *sk, struct sk_buff *skb) @@ -1370,33 +1366,20 @@ static inline struct ip_options *tcp_v4_save_options(struct sock *sk, return dopt; } -/* - * Maximum number of SYN_RECV sockets in queue per LISTEN socket. - * One SYN_RECV socket costs about 80bytes on a 32bit machine. - * It would be better to replace it with a global counter for all sockets - * but then some measure against one socket starving all other sockets - * would be needed. - * - * It was 128 by default. Experiments with real servers show, that - * it is absolutely not enough even at 100conn/sec. 256 cures most - * of problems. This value is adjusted to 128 for very small machines - * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). - * Further increasing requires to change hash table size. - */ -int sysctl_max_syn_backlog = 256; - -struct or_calltable or_ipv4 = { +struct request_sock_ops tcp_request_sock_ops = { .family = PF_INET, + .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_v4_send_synack, - .send_ack = tcp_v4_or_send_ack, - .destructor = tcp_v4_or_free, + .send_ack = tcp_v4_reqsk_send_ack, + .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { + struct inet_request_sock *ireq; struct tcp_options_received tmp_opt; - struct open_request *req; + struct request_sock *req; __u32 saddr = skb->nh.iph->saddr; __u32 daddr = skb->nh.iph->daddr; __u32 isn = TCP_SKB_CB(skb)->when; @@ -1433,7 +1416,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(); + req = reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; @@ -1461,10 +1444,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); - req->af.v4_req.loc_addr = daddr; - req->af.v4_req.rmt_addr = saddr; - req->af.v4_req.opt = tcp_v4_save_options(sk, skb); - req->class = &or_ipv4; + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->opt = tcp_v4_save_options(sk, skb); if (!want_cookie) TCP_ECN_create_request(req, skb->h.th); @@ -1523,20 +1506,20 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(sk, skb); } - req->snt_isn = isn; + tcp_rsk(req)->snt_isn = isn; if (tcp_v4_send_synack(sk, req, dst)) goto drop_and_free; if (want_cookie) { - tcp_openreq_free(req); + reqsk_free(req); } else { tcp_v4_synq_add(sk, req); } return 0; drop_and_free: - tcp_openreq_free(req); + reqsk_free(req); drop: TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; @@ -1548,9 +1531,10 @@ drop: * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { + struct inet_request_sock *ireq; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1570,11 +1554,12 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); - newinet->daddr = req->af.v4_req.rmt_addr; - newinet->rcv_saddr = req->af.v4_req.loc_addr; - newinet->saddr = req->af.v4_req.loc_addr; - newinet->opt = req->af.v4_req.opt; - req->af.v4_req.opt = NULL; + ireq = inet_rsk(req); + newinet->daddr = ireq->rmt_addr; + newinet->rcv_saddr = ireq->loc_addr; + newinet->saddr = ireq->loc_addr; + newinet->opt = ireq->opt; + ireq->opt = NULL; newinet->mc_index = tcp_v4_iif(skb); newinet->mc_ttl = skb->nh.iph->ttl; newtp->ext_header_len = 0; @@ -1605,9 +1590,9 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) struct iphdr *iph = skb->nh.iph; struct tcp_sock *tp = tcp_sk(sk); struct sock *nsk; - struct open_request **prev; + struct request_sock **prev; /* Find possible connection requests. */ - struct open_request *req = tcp_v4_search_req(tp, &prev, th->source, + struct request_sock *req = tcp_v4_search_req(tp, &prev, th->source, iph->saddr, iph->daddr); if (req) return tcp_check_req(sk, skb, req, prev); @@ -2144,13 +2129,13 @@ static void *listening_get_next(struct seq_file *seq, void *cur) ++st->num; if (st->state == TCP_SEQ_STATE_OPENREQ) { - struct open_request *req = cur; + struct request_sock *req = cur; tp = tcp_sk(st->syn_wait_sk); req = req->dl_next; while (1) { while (req) { - if (req->class->family == st->family) { + if (req->rsk_ops->family == st->family) { cur = req; goto out; } @@ -2159,17 +2144,17 @@ static void *listening_get_next(struct seq_file *seq, void *cur) if (++st->sbucket >= TCP_SYNQ_HSIZE) break; get_req: - req = tp->listen_opt->syn_table[st->sbucket]; + req = tp->accept_queue.listen_opt->syn_table[st->sbucket]; } sk = sk_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } else { tp = tcp_sk(sk); - read_lock_bh(&tp->syn_wait_lock); - if (tp->listen_opt && tp->listen_opt->qlen) + read_lock_bh(&tp->accept_queue.syn_wait_lock); + if (reqsk_queue_len(&tp->accept_queue)) goto start_req; - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); sk = sk_next(sk); } get_sk: @@ -2179,8 +2164,8 @@ get_sk: goto out; } tp = tcp_sk(sk); - read_lock_bh(&tp->syn_wait_lock); - if (tp->listen_opt && tp->listen_opt->qlen) { + read_lock_bh(&tp->accept_queue.syn_wait_lock); + if (reqsk_queue_len(&tp->accept_queue)) { start_req: st->uid = sock_i_uid(sk); st->syn_wait_sk = sk; @@ -2188,7 +2173,7 @@ start_req: st->sbucket = 0; goto get_req; } - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } if (++st->bucket < TCP_LHTABLE_SIZE) { sk = sk_head(&tcp_listening_hash[st->bucket]); @@ -2375,7 +2360,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_OPENREQ: if (v) { struct tcp_sock *tp = tcp_sk(st->syn_wait_sk); - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) @@ -2451,18 +2436,19 @@ void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo) memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); } -static void get_openreq4(struct sock *sk, struct open_request *req, +static void get_openreq4(struct sock *sk, struct request_sock *req, char *tmpbuf, int i, int uid) { + const struct inet_request_sock *ireq = inet_rsk(req); int ttd = req->expires - jiffies; sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p", i, - req->af.v4_req.loc_addr, + ireq->loc_addr, ntohs(inet_sk(sk)->sport), - req->af.v4_req.rmt_addr, - ntohs(req->rmt_port), + ireq->rmt_addr, + ntohs(ireq->rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ @@ -2618,6 +2604,7 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), + .rsk_prot = &tcp_request_sock_ops, }; @@ -2660,7 +2647,6 @@ EXPORT_SYMBOL(tcp_proc_register); EXPORT_SYMBOL(tcp_proc_unregister); #endif EXPORT_SYMBOL(sysctl_local_port_range); -EXPORT_SYMBOL(sysctl_max_syn_backlog); EXPORT_SYMBOL(sysctl_tcp_low_latency); EXPORT_SYMBOL(sysctl_tcp_tw_reuse); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index eea1a17a9ac..b3943e7562f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -684,7 +684,7 @@ out: * Actually, we could lots of memory writes here. tp of listening * socket contains all necessary default parameters. */ -struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, struct sk_buff *skb) +struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) { /* allocate the newsk from the same slab of the master sock, * if not, at sk_free time we'll try to free it from the wrong @@ -692,6 +692,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, struct sock *newsk = sk_alloc(PF_INET, GFP_ATOMIC, sk->sk_prot, 0); if(newsk != NULL) { + struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_request_sock *treq = tcp_rsk(req); struct tcp_sock *newtp; struct sk_filter *filter; @@ -703,7 +705,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, tcp_sk(newsk)->bind_hash = NULL; /* Clone the TCP header template */ - inet_sk(newsk)->dport = req->rmt_port; + inet_sk(newsk)->dport = ireq->rmt_port; sock_lock_init(newsk); bh_lock_sock(newsk); @@ -739,14 +741,14 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, /* Now setup tcp_sock */ newtp = tcp_sk(newsk); newtp->pred_flags = 0; - newtp->rcv_nxt = req->rcv_isn + 1; - newtp->snd_nxt = req->snt_isn + 1; - newtp->snd_una = req->snt_isn + 1; - newtp->snd_sml = req->snt_isn + 1; + newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->snd_nxt = treq->snt_isn + 1; + newtp->snd_una = treq->snt_isn + 1; + newtp->snd_sml = treq->snt_isn + 1; tcp_prequeue_init(newtp); - tcp_init_wl(newtp, req->snt_isn, req->rcv_isn); + tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn); newtp->retransmits = 0; newtp->backoff = 0; @@ -775,10 +777,10 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, tcp_set_ca_state(newtp, TCP_CA_Open); tcp_init_xmit_timers(newsk); skb_queue_head_init(&newtp->out_of_order_queue); - newtp->rcv_wup = req->rcv_isn + 1; - newtp->write_seq = req->snt_isn + 1; + newtp->rcv_wup = treq->rcv_isn + 1; + newtp->write_seq = treq->snt_isn + 1; newtp->pushed_seq = newtp->write_seq; - newtp->copied_seq = req->rcv_isn + 1; + newtp->copied_seq = treq->rcv_isn + 1; newtp->rx_opt.saw_tstamp = 0; @@ -788,10 +790,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, newtp->probes_out = 0; newtp->rx_opt.num_sacks = 0; newtp->urg_data = 0; - newtp->listen_opt = NULL; - newtp->accept_queue = newtp->accept_queue_tail = NULL; - /* Deinitialize syn_wait_lock to trap illegal accesses. */ - memset(&newtp->syn_wait_lock, 0, sizeof(newtp->syn_wait_lock)); + /* Deinitialize accept_queue to trap illegal accesses. */ + memset(&newtp->accept_queue, 0, sizeof(newtp->accept_queue)); /* Back to base struct sock members. */ newsk->sk_err = 0; @@ -808,18 +808,18 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, newsk->sk_socket = NULL; newsk->sk_sleep = NULL; - newtp->rx_opt.tstamp_ok = req->tstamp_ok; - if((newtp->rx_opt.sack_ok = req->sack_ok) != 0) { + newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; + if((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) { if (sysctl_tcp_fack) newtp->rx_opt.sack_ok |= 2; } newtp->window_clamp = req->window_clamp; newtp->rcv_ssthresh = req->rcv_wnd; newtp->rcv_wnd = req->rcv_wnd; - newtp->rx_opt.wscale_ok = req->wscale_ok; + newtp->rx_opt.wscale_ok = ireq->wscale_ok; if (newtp->rx_opt.wscale_ok) { - newtp->rx_opt.snd_wscale = req->snd_wscale; - newtp->rx_opt.rcv_wscale = req->rcv_wscale; + newtp->rx_opt.snd_wscale = ireq->snd_wscale; + newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; } else { newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; newtp->window_clamp = min(newtp->window_clamp, 65535U); @@ -851,12 +851,12 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, /* * Process an incoming packet for SYN_RECV sockets represented - * as an open_request. + * as a request_sock. */ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, - struct open_request *req, - struct open_request **prev) + struct request_sock *req, + struct request_sock **prev) { struct tcphdr *th = skb->h.th; struct tcp_sock *tp = tcp_sk(sk); @@ -881,7 +881,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, } /* Check for pure retransmitted SYN. */ - if (TCP_SKB_CB(skb)->seq == req->rcv_isn && + if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn && flg == TCP_FLAG_SYN && !paws_reject) { /* @@ -901,7 +901,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. */ - req->class->rtx_syn_ack(sk, req, NULL); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; } @@ -959,7 +959,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, * Invalid ACK: reset will be sent by listening socket */ if ((flg & TCP_FLAG_ACK) && - (TCP_SKB_CB(skb)->ack_seq != req->snt_isn+1)) + (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) return sk; /* Also, it would be not so bad idea to check rcv_tsecr, which @@ -970,10 +970,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - req->rcv_isn+1, req->rcv_isn+1+req->rcv_wnd)) { + tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) - req->class->send_ack(skb, req); + req->rsk_ops->send_ack(skb, req); if (paws_reject) NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED); return NULL; @@ -981,12 +981,12 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* In sequence, PAWS is OK. */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, req->rcv_isn+1)) + if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1)) req->ts_recent = tmp_opt.rcv_tsval; - if (TCP_SKB_CB(skb)->seq == req->rcv_isn) { + if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting - at req->rcv_isn+1. */ + at tcp_rsk(req)->rcv_isn + 1. */ flg &= ~TCP_FLAG_SYN; } @@ -1003,8 +1003,8 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, return NULL; /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ - if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == req->rcv_isn+1) { - req->acked = 1; + if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; return NULL; } @@ -1026,14 +1026,14 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, listen_overflow: if (!sysctl_tcp_abort_on_overflow) { - req->acked = 1; + inet_rsk(req)->acked = 1; return NULL; } embryonic_reset: NET_INC_STATS_BH(LINUX_MIB_EMBRYONICRSTS); if (!(flg & TCP_FLAG_RST)) - req->class->send_reset(skb); + req->rsk_ops->send_reset(skb); tcp_synq_drop(sk, req, prev); return NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fa24e7ae1f4..f17c6577e33 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1356,8 +1356,9 @@ int tcp_send_synack(struct sock *sk) * Prepare a SYN-ACK. */ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct open_request *req) + struct request_sock *req) { + struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; int tcp_header_size; @@ -1373,47 +1374,47 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb->dst = dst_clone(dst); tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS + - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) + - (req->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) + + (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) + + (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) + /* SACK_PERM is in the place of NOP NOP of TS */ - ((req->sack_ok && !req->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0)); + ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0)); skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size); memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; if (dst->dev->features&NETIF_F_TSO) - req->ecn_ok = 0; + ireq->ecn_ok = 0; TCP_ECN_make_synack(req, th); th->source = inet_sk(sk)->sport; - th->dest = req->rmt_port; - TCP_SKB_CB(skb)->seq = req->snt_isn; + th->dest = ireq->rmt_port; + TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1; TCP_SKB_CB(skb)->sacked = 0; skb_shinfo(skb)->tso_segs = 1; skb_shinfo(skb)->tso_size = 0; th->seq = htonl(TCP_SKB_CB(skb)->seq); - th->ack_seq = htonl(req->rcv_isn + 1); + th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */ __u8 rcv_wscale; /* Set this up on the first call only */ req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(tcp_full_space(sk), - dst_metric(dst, RTAX_ADVMSS) - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), + dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rcv_wnd, &req->window_clamp, - req->wscale_ok, + ireq->wscale_ok, &rcv_wscale); - req->rcv_wscale = rcv_wscale; + ireq->rcv_wscale = rcv_wscale; } /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(req->rcv_wnd); TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), req->tstamp_ok, - req->sack_ok, req->wscale_ok, req->rcv_wscale, + tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok, + ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale, TCP_SKB_CB(skb)->when, req->ts_recent); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 799ebe061e2..b127b449856 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -464,11 +464,11 @@ out_unlock: static void tcp_synack_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; + struct listen_sock *lopt = tp->accept_queue.listen_opt; int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries; int thresh = max_retries; unsigned long now = jiffies; - struct open_request **reqp, *req; + struct request_sock **reqp, *req; int i, budget; if (lopt == NULL || lopt->qlen == 0) @@ -513,8 +513,8 @@ static void tcp_synack_timer(struct sock *sk) while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { if ((req->retrans < thresh || - (req->acked && req->retrans < max_retries)) - && !req->class->rtx_syn_ack(sk, req, NULL)) { + (inet_rsk(req)->acked && req->retrans < max_retries)) + && !req->rsk_ops->rtx_syn_ack(sk, req, NULL)) { unsigned long timeo; if (req->retrans++ == 0) @@ -527,13 +527,9 @@ static void tcp_synack_timer(struct sock *sk) } /* Drop this request */ - write_lock(&tp->syn_wait_lock); - *reqp = req->dl_next; - write_unlock(&tp->syn_wait_lock); - lopt->qlen--; - if (req->retrans == 0) - lopt->qlen_young--; - tcp_openreq_free(req); + tcp_synq_unlink(tp, req, reqp); + reqsk_queue_removed(&tp->accept_queue, req); + reqsk_free(req); continue; } reqp = &req->dl_next; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2720899d516..47a30c3188e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -131,7 +131,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); static int addrconf_ifdown(struct net_device *dev, int how); -static void addrconf_dad_start(struct inet6_ifaddr *ifp, int flags); +static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); static void addrconf_dad_timer(unsigned long data); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); static void addrconf_rs_timer(unsigned long data); @@ -492,7 +492,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, - int scope, unsigned flags) + int scope, u32 flags) { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; @@ -1320,7 +1320,7 @@ static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad static void addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, - unsigned long expires, unsigned flags) + unsigned long expires, u32 flags) { struct in6_rtmsg rtmsg; @@ -2229,7 +2229,7 @@ out: /* * Duplicate Address Detection */ -static void addrconf_dad_start(struct inet6_ifaddr *ifp, int flags) +static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; @@ -2622,15 +2622,14 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; struct ifa_cacheinfo ci; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_INET6; ifm->ifa_prefixlen = ifa->prefix_len; @@ -2672,15 +2671,14 @@ rtattr_failure: } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, u16 flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; struct ifa_cacheinfo ci; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_INET6; ifm->ifa_prefixlen = 128; @@ -2709,15 +2707,14 @@ rtattr_failure: } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; struct ifa_cacheinfo ci; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_INET6; ifm->ifa_prefixlen = 128; @@ -2786,7 +2783,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, continue; if ((err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWADDR)) <= 0) + cb->nlh->nlmsg_seq, RTM_NEWADDR, + NLM_F_MULTI)) <= 0) goto done; } /* temp addr */ @@ -2797,7 +2795,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, continue; if ((err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWADDR)) <= 0) + cb->nlh->nlmsg_seq, RTM_NEWADDR, + NLM_F_MULTI)) <= 0) goto done; } #endif @@ -2810,7 +2809,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, continue; if ((err = inet6_fill_ifmcaddr(skb, ifmca, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_GETMULTICAST)) <= 0) + cb->nlh->nlmsg_seq, RTM_GETMULTICAST, + NLM_F_MULTI)) <= 0) goto done; } break; @@ -2822,7 +2822,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, continue; if ((err = inet6_fill_ifacaddr(skb, ifaca, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_GETANYCAST)) <= 0) + cb->nlh->nlmsg_seq, RTM_GETANYCAST, + NLM_F_MULTI)) <= 0) goto done; } break; @@ -2872,7 +2873,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFADDR, ENOBUFS); return; } - if (inet6_fill_ifaddr(skb, ifa, 0, 0, event) < 0) { + if (inet6_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFADDR, EINVAL); return; @@ -2907,7 +2908,7 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; __s32 *array = NULL; @@ -2918,8 +2919,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, __u32 mtu = dev->mtu; struct ifla_cacheinfo ci; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); r = NLMSG_DATA(nlh); r->ifi_family = AF_INET6; r->ifi_type = dev->type; @@ -2986,7 +2986,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if ((idev = in6_dev_get(dev)) == NULL) continue; err = inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWLINK); + cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); in6_dev_put(idev); if (err <= 0) break; @@ -3008,7 +3008,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFINFO, ENOBUFS); return; } - if (inet6_fill_ifinfo(skb, idev, 0, 0, event) < 0) { + if (inet6_fill_ifinfo(skb, idev, current->pid, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFINFO, EINVAL); return; @@ -3018,18 +3018,15 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, - struct prefix_info *pinfo, u32 pid, u32 seq, int event) + struct prefix_info *pinfo, u32 pid, u32 seq, + int event, unsigned int flags) { struct prefixmsg *pmsg; struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct prefix_cacheinfo ci; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*pmsg)); - - if (pid) - nlh->nlmsg_flags |= NLM_F_MULTI; - + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*pmsg), flags); pmsg = NLMSG_DATA(nlh); pmsg->prefix_family = AF_INET6; pmsg->prefix_ifindex = idev->dev->ifindex; @@ -3068,7 +3065,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, netlink_set_err(rtnl, 0, RTMGRP_IPV6_PREFIX, ENOBUFS); return; } - if (inet6_fill_prefix(skb, idev, pinfo, 0, 0, event) < 0) { + if (inet6_fill_prefix(skb, idev, pinfo, current->pid, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV6_PREFIX, EINVAL); return; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 65b9375df57..5229365cd8b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -353,14 +353,14 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) err = copied; /* Reset and regenerate socket error */ - spin_lock_irq(&sk->sk_error_queue.lock); + spin_lock_bh(&sk->sk_error_queue.lock); sk->sk_err = 0; if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); sk->sk_error_report(sk); } else { - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); } out_free_skb: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 617645bc5ed..e2b848ec985 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -434,12 +434,12 @@ csum_copy_err: /* Clear queue. */ if (flags&MSG_PEEK) { int clear = 0; - spin_lock_irq(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_receive_queue.lock); if (skb == skb_peek(&sk->sk_receive_queue)) { __skb_unlink(skb, &sk->sk_receive_queue); clear = 1; } - spin_unlock_irq(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk->sk_receive_queue.lock); if (clear) kfree_skb(skb); } @@ -971,11 +971,11 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) struct sk_buff *skb; int amount = 0; - spin_lock_irq(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) amount = skb->tail - skb->h.raw; - spin_unlock_irq(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3bf8a0254f8..1f5b226c357 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1570,7 +1570,8 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, - struct nlmsghdr *in_nlh, int prefix) + struct nlmsghdr *in_nlh, int prefix, + unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; @@ -1588,7 +1589,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, pid = in_nlh->nlmsg_pid; } - nlh = NLMSG_PUT(skb, pid, seq, type, sizeof(*rtm)); + nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt->rt6i_dst.plen; @@ -1674,7 +1675,7 @@ static int rt6_dump_route(struct rt6_info *rt, void *p_arg) return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, - NULL, prefix); + NULL, prefix, NLM_F_MULTI); } static int fib6_dump_node(struct fib6_walker_t *w) @@ -1822,7 +1823,7 @@ int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, - nlh->nlmsg_seq, nlh, 0); + nlh->nlmsg_seq, nlh, 0, 0); if (err < 0) { err = -EMSGSIZE; goto out_free; @@ -1848,7 +1849,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh) netlink_set_err(rtnl, 0, RTMGRP_IPV6_ROUTE, ENOBUFS); return; } - if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, 0, 0, nlh, 0) < 0) { + if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, 0, 0, nlh, 0, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV6_ROUTE, EINVAL); return; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0f69e800a0a..2414937f2a8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -65,7 +65,7 @@ #include <linux/seq_file.h> static void tcp_v6_send_reset(struct sk_buff *skb); -static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req); +static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, struct sk_buff *skb); @@ -394,24 +394,26 @@ static u32 tcp_v6_synq_hash(struct in6_addr *raddr, u16 rport, u32 rnd) return c & (TCP_SYNQ_HSIZE - 1); } -static struct open_request *tcp_v6_search_req(struct tcp_sock *tp, - struct open_request ***prevp, +static struct request_sock *tcp_v6_search_req(struct tcp_sock *tp, + struct request_sock ***prevp, __u16 rport, struct in6_addr *raddr, struct in6_addr *laddr, int iif) { - struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *req, **prev; + struct listen_sock *lopt = tp->accept_queue.listen_opt; + struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; prev = &req->dl_next) { - if (req->rmt_port == rport && - req->class->family == AF_INET6 && - ipv6_addr_equal(&req->af.v6_req.rmt_addr, raddr) && - ipv6_addr_equal(&req->af.v6_req.loc_addr, laddr) && - (!req->af.v6_req.iif || req->af.v6_req.iif == iif)) { + const struct tcp6_request_sock *treq = tcp6_rsk(req); + + if (inet_rsk(req)->rmt_port == rport && + req->rsk_ops->family == AF_INET6 && + ipv6_addr_equal(&treq->rmt_addr, raddr) && + ipv6_addr_equal(&treq->loc_addr, laddr) && + (!treq->iif || treq->iif == iif)) { BUG_TRAP(req->sk == NULL); *prevp = prev; return req; @@ -906,9 +908,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_err_convert(type, code, &err); - /* Might be for an open_request */ + /* Might be for an request_sock */ switch (sk->sk_state) { - struct open_request *req, **prev; + struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; @@ -923,7 +925,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ BUG_TRAP(req->sk == NULL); - if (seq != req->snt_isn) { + if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -957,9 +959,10 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { + struct tcp6_request_sock *treq = tcp6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; struct ipv6_txoptions *opt = NULL; @@ -969,19 +972,19 @@ static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &req->af.v6_req.loc_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); + ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.fl6_flowlabel = 0; - fl.oif = req->af.v6_req.iif; - fl.fl_ip_dport = req->rmt_port; + fl.oif = treq->iif; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; if (dst == NULL) { opt = np->opt; if (opt == NULL && np->rxopt.bits.srcrt == 2 && - req->af.v6_req.pktopts) { - struct sk_buff *pktopts = req->af.v6_req.pktopts; + treq->pktopts) { + struct sk_buff *pktopts = treq->pktopts; struct inet6_skb_parm *rxopt = IP6CB(pktopts); if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt)); @@ -1008,10 +1011,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, struct tcphdr *th = skb->h.th; th->check = tcp_v6_check(th, skb->len, - &req->af.v6_req.loc_addr, &req->af.v6_req.rmt_addr, + &treq->loc_addr, &treq->rmt_addr, csum_partial((char *)th, skb->len, skb->csum)); - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); err = ip6_xmit(sk, skb, &fl, opt, 0); if (err == NET_XMIT_CN) err = 0; @@ -1024,17 +1027,18 @@ done: return err; } -static void tcp_v6_or_free(struct open_request *req) +static void tcp_v6_reqsk_destructor(struct request_sock *req) { - if (req->af.v6_req.pktopts) - kfree_skb(req->af.v6_req.pktopts); + if (tcp6_rsk(req)->pktopts) + kfree_skb(tcp6_rsk(req)->pktopts); } -static struct or_calltable or_ipv6 = { +static struct request_sock_ops tcp6_request_sock_ops = { .family = AF_INET6, + .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_v6_send_synack, - .send_ack = tcp_v6_or_send_ack, - .destructor = tcp_v6_or_free, + .send_ack = tcp_v6_reqsk_send_ack, + .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset }; @@ -1219,15 +1223,15 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_tw_put(tw); } -static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req) +static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) { - tcp_v6_send_ack(skb, req->snt_isn+1, req->rcv_isn+1, req->rcv_wnd, req->ts_recent); + tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { - struct open_request *req, **prev; + struct request_sock *req, **prev; struct tcphdr *th = skb->h.th; struct tcp_sock *tp = tcp_sk(sk); struct sock *nsk; @@ -1260,21 +1264,13 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) return sk; } -static void tcp_v6_synq_add(struct sock *sk, struct open_request *req) +static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; - u32 h = tcp_v6_synq_hash(&req->af.v6_req.rmt_addr, req->rmt_port, lopt->hash_rnd); - - req->sk = NULL; - req->expires = jiffies + TCP_TIMEOUT_INIT; - req->retrans = 0; - req->dl_next = lopt->syn_table[h]; - - write_lock(&tp->syn_wait_lock); - lopt->syn_table[h] = req; - write_unlock(&tp->syn_wait_lock); + struct listen_sock *lopt = tp->accept_queue.listen_opt; + u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); + reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT); tcp_synq_added(sk); } @@ -1284,10 +1280,11 @@ static void tcp_v6_synq_add(struct sock *sk, struct open_request *req) */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { + struct tcp6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct open_request *req = NULL; + struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; if (skb->protocol == htons(ETH_P_IP)) @@ -1308,7 +1305,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(); + req = reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) goto drop; @@ -1321,28 +1318,28 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); - req->class = &or_ipv6; - ipv6_addr_copy(&req->af.v6_req.rmt_addr, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&req->af.v6_req.loc_addr, &skb->nh.ipv6h->daddr); + treq = tcp6_rsk(req); + ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr); + ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr); TCP_ECN_create_request(req, skb->h.th); - req->af.v6_req.pktopts = NULL; + treq->pktopts = NULL; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxhlim) { atomic_inc(&skb->users); - req->af.v6_req.pktopts = skb; + treq->pktopts = skb; } - req->af.v6_req.iif = sk->sk_bound_dev_if; + treq->iif = sk->sk_bound_dev_if; /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && - ipv6_addr_type(&req->af.v6_req.rmt_addr) & IPV6_ADDR_LINKLOCAL) - req->af.v6_req.iif = tcp_v6_iif(skb); + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = tcp_v6_iif(skb); if (isn == 0) isn = tcp_v6_init_sequence(sk,skb); - req->snt_isn = isn; + tcp_rsk(req)->snt_isn = isn; if (tcp_v6_send_synack(sk, req, NULL)) goto drop; @@ -1353,16 +1350,17 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) drop: if (req) - tcp_openreq_free(req); + reqsk_free(req); TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; /* don't send reset */ } static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { + struct tcp6_request_sock *treq = tcp6_rsk(req); struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; @@ -1426,10 +1424,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto out_overflow; if (np->rxopt.bits.srcrt == 2 && - opt == NULL && req->af.v6_req.pktopts) { - struct inet6_skb_parm *rxopt = IP6CB(req->af.v6_req.pktopts); + opt == NULL && treq->pktopts) { + struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts); if (rxopt->srcrt) - opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(req->af.v6_req.pktopts->nh.raw+rxopt->srcrt)); + opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt)); } if (dst == NULL) { @@ -1438,16 +1436,16 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); if (opt && opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; } - ipv6_addr_copy(&fl.fl6_src, &req->af.v6_req.loc_addr); + ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = req->rmt_port; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; if (ip6_dst_lookup(sk, &dst, &fl)) @@ -1482,10 +1480,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &req->af.v6_req.rmt_addr); - ipv6_addr_copy(&newnp->saddr, &req->af.v6_req.loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &req->af.v6_req.loc_addr); - newsk->sk_bound_dev_if = req->af.v6_req.iif; + ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); + ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); + ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... @@ -1498,11 +1496,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (req->af.v6_req.pktopts) { - newnp->pktoptions = skb_clone(req->af.v6_req.pktopts, - GFP_ATOMIC); - kfree_skb(req->af.v6_req.pktopts); - req->af.v6_req.pktopts = NULL; + if (treq->pktopts != NULL) { + newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); + kfree_skb(treq->pktopts); + treq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); } @@ -2050,7 +2047,7 @@ static int tcp_v6_destroy_sock(struct sock *sk) /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct sock *sk, struct open_request *req, int i, int uid) + struct sock *sk, struct request_sock *req, int i, int uid) { struct in6_addr *dest, *src; int ttd = req->expires - jiffies; @@ -2058,8 +2055,8 @@ static void get_openreq6(struct seq_file *seq, if (ttd < 0) ttd = 0; - src = &req->af.v6_req.loc_addr; - dest = &req->af.v6_req.rmt_addr; + src = &tcp6_rsk(req)->loc_addr; + dest = &tcp6_rsk(req)->rmt_addr; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", @@ -2069,7 +2066,7 @@ static void get_openreq6(struct seq_file *seq, ntohs(inet_sk(sk)->sport), dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], - ntohs(req->rmt_port), + ntohs(inet_rsk(req)->rmt_port), TCP_SYN_RECV, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ @@ -2239,6 +2236,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), + .rsk_prot = &tcp6_request_sock_ops, }; static struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e251d0ba4f3..eff050ac704 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -300,12 +300,12 @@ csum_copy_err: /* Clear queue. */ if (flags&MSG_PEEK) { int clear = 0; - spin_lock_irq(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_receive_queue.lock); if (skb == skb_peek(&sk->sk_receive_queue)) { __skb_unlink(skb, &sk->sk_receive_queue); clear = 1; } - spin_unlock_irq(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk->sk_receive_queue.lock); if (clear) kfree_skb(skb); } diff --git a/net/key/af_key.c b/net/key/af_key.c index ce980aa94ed..98b72f2024f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -656,13 +656,18 @@ static struct sk_buff * pfkey_xfrm_state2msg(struct xfrm_state *x, int add_keys, sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = x->props.replay_window; - sa->sadb_sa_state = SADB_SASTATE_DYING; - if (x->km.state == XFRM_STATE_VALID && !x->km.dying) - sa->sadb_sa_state = SADB_SASTATE_MATURE; - else if (x->km.state == XFRM_STATE_ACQ) + switch (x->km.state) { + case XFRM_STATE_VALID: + sa->sadb_sa_state = x->km.dying ? + SADB_SASTATE_DYING : SADB_SASTATE_MATURE; + break; + case XFRM_STATE_ACQ: sa->sadb_sa_state = SADB_SASTATE_LARVAL; - else if (x->km.state == XFRM_STATE_EXPIRED) + break; + default: sa->sadb_sa_state = SADB_SASTATE_DEAD; + break; + } sa->sadb_sa_auth = 0; if (x->aalg) { struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0); @@ -1240,13 +1245,78 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, struct sadb_msg * return 0; } +static inline int event2poltype(int event) +{ + switch (event) { + case XFRM_MSG_DELPOLICY: + return SADB_X_SPDDELETE; + case XFRM_MSG_NEWPOLICY: + return SADB_X_SPDADD; + case XFRM_MSG_UPDPOLICY: + return SADB_X_SPDUPDATE; + case XFRM_MSG_POLEXPIRE: + // return SADB_X_SPDEXPIRE; + default: + printk("pfkey: Unknown policy event %d\n", event); + break; + } + + return 0; +} + +static inline int event2keytype(int event) +{ + switch (event) { + case XFRM_MSG_DELSA: + return SADB_DELETE; + case XFRM_MSG_NEWSA: + return SADB_ADD; + case XFRM_MSG_UPDSA: + return SADB_UPDATE; + case XFRM_MSG_EXPIRE: + return SADB_EXPIRE; + default: + printk("pfkey: Unknown SA event %d\n", event); + break; + } + + return 0; +} + +/* ADD/UPD/DEL */ +static int key_notify_sa(struct xfrm_state *x, struct km_event *c) +{ + struct sk_buff *skb; + struct sadb_msg *hdr; + int hsc = 3; + + if (c->event == XFRM_MSG_DELSA) + hsc = 0; + + skb = pfkey_xfrm_state2msg(x, 0, hsc); + + if (IS_ERR(skb)) + return PTR_ERR(skb); + + hdr = (struct sadb_msg *) skb->data; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_type = event2keytype(c->event); + hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); + hdr->sadb_msg_errno = 0; + hdr->sadb_msg_reserved = 0; + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL); + + return 0; +} static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; struct xfrm_state *x; int err; + struct km_event c; xfrm_probe_algs(); @@ -1254,6 +1324,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, if (IS_ERR(x)) return PTR_ERR(x); + xfrm_state_hold(x); if (hdr->sadb_msg_type == SADB_ADD) err = xfrm_state_add(x); else @@ -1262,30 +1333,26 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, if (err < 0) { x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); - return err; + goto out; } - out_skb = pfkey_xfrm_state2msg(x, 0, 3); - if (IS_ERR(out_skb)) - return PTR_ERR(out_skb); /* XXX Should we return 0 here ? */ - - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_reserved = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); - - return 0; + if (hdr->sadb_msg_type == SADB_ADD) + c.event = XFRM_MSG_NEWSA; + else + c.event = XFRM_MSG_UPDSA; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + km_state_notify(x, &c); +out: + xfrm_state_put(x); + return err; } static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { struct xfrm_state *x; + struct km_event c; + int err; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], @@ -1301,13 +1368,19 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h return -EPERM; } - xfrm_state_delete(x); - xfrm_state_put(x); + err = xfrm_state_delete(x); + if (err < 0) { + xfrm_state_put(x); + return err; + } - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_ALL, sk); + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_MSG_DELSA; + km_state_notify(x, &c); + xfrm_state_put(x); - return 0; + return err; } static int pfkey_get(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) @@ -1445,28 +1518,42 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, struct sadb_msg return 0; } +static int key_notify_sa_flush(struct km_event *c) +{ + struct sk_buff *skb; + struct sadb_msg *hdr; + + skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); + if (!skb) + return -ENOBUFS; + hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_errno = (uint8_t) 0; + hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL); + + return 0; +} + static int pfkey_flush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { unsigned proto; - struct sk_buff *skb_out; - struct sadb_msg *hdr_out; + struct km_event c; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; - skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); - if (!skb_out) - return -ENOBUFS; - xfrm_state_flush(proto); - - hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); - pfkey_hdr_dup(hdr_out, hdr); - hdr_out->sadb_msg_errno = (uint8_t) 0; - hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - - pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL); + c.data.proto = proto; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_MSG_FLUSHSA; + km_state_notify(NULL, &c); return 0; } @@ -1859,6 +1946,35 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i hdr->sadb_msg_reserved = atomic_read(&xp->refcnt); } +static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + struct sk_buff *out_skb; + struct sadb_msg *out_hdr; + int err; + + out_skb = pfkey_xfrm_policy2msg_prep(xp); + if (IS_ERR(out_skb)) { + err = PTR_ERR(out_skb); + goto out; + } + pfkey_xfrm_policy2msg(out_skb, xp, dir); + + out_hdr = (struct sadb_msg *) out_skb->data; + out_hdr->sadb_msg_version = PF_KEY_V2; + + if (c->data.byid && c->event == XFRM_MSG_DELPOLICY) + out_hdr->sadb_msg_type = SADB_X_SPDDELETE2; + else + out_hdr->sadb_msg_type = event2poltype(c->event); + out_hdr->sadb_msg_errno = 0; + out_hdr->sadb_msg_seq = c->seq; + out_hdr->sadb_msg_pid = c->pid; + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL); +out: + return 0; + +} + static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { int err; @@ -1866,8 +1982,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; + struct km_event c; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || @@ -1935,31 +2050,23 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h (err = parse_ipsecrequests(xp, pol)) < 0) goto out; - out_skb = pfkey_xfrm_policy2msg_prep(xp); - if (IS_ERR(out_skb)) { - err = PTR_ERR(out_skb); - goto out; - } - err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); if (err) { - kfree_skb(out_skb); - goto out; + kfree(xp); + return err; } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); + if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) + c.event = XFRM_MSG_UPDPOLICY; + else + c.event = XFRM_MSG_NEWPOLICY; - xfrm_pol_put(xp); + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = 0; - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + xfrm_pol_put(xp); return 0; out: @@ -1973,9 +2080,8 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; struct xfrm_selector sel; + struct km_event c; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || @@ -2010,25 +2116,40 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg err = 0; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_MSG_DELPOLICY; + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + + xfrm_pol_put(xp); + return err; +} + +static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, struct sadb_msg *hdr, int dir) +{ + int err; + struct sk_buff *out_skb; + struct sadb_msg *out_hdr; + err = 0; + out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) { err = PTR_ERR(out_skb); goto out; } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); + pfkey_xfrm_policy2msg(out_skb, xp, dir); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = SADB_X_SPDDELETE; + out_hdr->sadb_msg_type = hdr->sadb_msg_type; out_hdr->sadb_msg_satype = 0; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk); err = 0; out: - xfrm_pol_put(xp); return err; } @@ -2037,8 +2158,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h int err; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; + struct km_event c; if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL) return -EINVAL; @@ -2050,24 +2170,16 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h err = 0; - out_skb = pfkey_xfrm_policy2msg_prep(xp); - if (IS_ERR(out_skb)) { - err = PTR_ERR(out_skb); - goto out; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + if (hdr->sadb_msg_type == SADB_X_SPDDELETE2) { + c.data.byid = 1; + c.event = XFRM_MSG_DELPOLICY; + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + } else { + err = key_pol_get_resp(sk, xp, hdr, pol->sadb_x_policy_dir-1); } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); - - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = 0; - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); - err = 0; -out: xfrm_pol_put(xp); return err; } @@ -2102,22 +2214,34 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg * return xfrm_policy_walk(dump_sp, &data); } -static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) +static int key_notify_policy_flush(struct km_event *c) { struct sk_buff *skb_out; - struct sadb_msg *hdr_out; + struct sadb_msg *hdr; - skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); + skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; + hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_errno = (uint8_t) 0; + hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL); + return 0; - xfrm_policy_flush(); +} + +static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) +{ + struct km_event c; - hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); - pfkey_hdr_dup(hdr_out, hdr); - hdr_out->sadb_msg_errno = (uint8_t) 0; - hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL); + xfrm_policy_flush(); + c.event = XFRM_MSG_FLUSHPOLICY; + c.pid = hdr->sadb_msg_pid; + c.seq = hdr->sadb_msg_seq; + km_policy_notify(NULL, 0, &c); return 0; } @@ -2317,11 +2441,23 @@ static void dump_esp_combs(struct sk_buff *skb, struct xfrm_tmpl *t) } } -static int pfkey_send_notify(struct xfrm_state *x, int hard) +static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c) +{ + return 0; +} + +static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; - int hsc = (hard ? 2 : 1); + int hard; + int hsc; + + hard = c->data.hard; + if (hard) + hsc = 2; + else + hsc = 1; out_skb = pfkey_xfrm_state2msg(x, 0, hsc); if (IS_ERR(out_skb)) @@ -2340,6 +2476,44 @@ static int pfkey_send_notify(struct xfrm_state *x, int hard) return 0; } +static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) +{ + switch (c->event) { + case XFRM_MSG_EXPIRE: + return key_notify_sa_expire(x, c); + case XFRM_MSG_DELSA: + case XFRM_MSG_NEWSA: + case XFRM_MSG_UPDSA: + return key_notify_sa(x, c); + case XFRM_MSG_FLUSHSA: + return key_notify_sa_flush(c); + default: + printk("pfkey: Unknown SA event %d\n", c->event); + break; + } + + return 0; +} + +static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + switch (c->event) { + case XFRM_MSG_POLEXPIRE: + return key_notify_policy_expire(xp, c); + case XFRM_MSG_DELPOLICY: + case XFRM_MSG_NEWPOLICY: + case XFRM_MSG_UPDPOLICY: + return key_notify_policy(xp, dir, c); + case XFRM_MSG_FLUSHPOLICY: + return key_notify_policy_flush(c); + default: + printk("pfkey: Unknown policy event %d\n", c->event); + break; + } + + return 0; +} + static u32 get_acqseq(void) { u32 res; @@ -2856,6 +3030,7 @@ static struct xfrm_mgr pfkeyv2_mgr = .acquire = pfkey_send_acquire, .compile_policy = pfkey_compile_policy, .new_mapping = pfkey_send_new_mapping, + .notify_policy = pfkey_send_policy_notify, }; static void __exit ipsec_pfkey_exit(void) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e41ce458c2a..70bcd4744d9 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1095,8 +1095,7 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = __nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLMSG_DONE, sizeof(int)); - nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW_ANSWER(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); memcpy(NLMSG_DATA(nlh), &len, sizeof(len)); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk, skb->len); @@ -1107,6 +1106,9 @@ static int netlink_dump(struct sock *sk) netlink_destroy_callback(cb); return 0; + +nlmsg_failure: + return -ENOBUFS; } int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, @@ -1178,7 +1180,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) } rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, - NLMSG_ERROR, sizeof(struct nlmsgerr)); + NLMSG_ERROR, sizeof(struct nlmsgerr), 0); errmsg = NLMSG_DATA(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(struct nlmsghdr)); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 914c85ff8fe..9594206e603 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -428,15 +428,15 @@ errout: static int tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq, - unsigned flags, int event, int bind, int ref) + u16 flags, int event, int bind, int ref) { struct tcamsg *t; struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct rtattr *x; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*t)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); + t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; @@ -669,7 +669,7 @@ err: } static int tcf_add_notify(struct tc_action *a, u32 pid, u32 seq, int event, - unsigned flags) + u16 flags) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -684,8 +684,7 @@ static int tcf_add_notify(struct tc_action *a, u32 pid, u32 seq, int event, b = (unsigned char *)skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*t)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 56e66c3fe0f..1616bf5c962 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -322,14 +322,13 @@ errout: static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm_ifindex = tp->q->dev->ifindex; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 07977f8f267..97c1c75d5c7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -760,15 +760,14 @@ graft: } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct gnet_dump d; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm_ifindex = q->dev->ifindex; @@ -997,7 +996,7 @@ out: static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1005,8 +1004,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm_ifindex = q->dev->ifindex; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index d8bd2a569c7..13e0e7b3856 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -31,7 +31,7 @@ #endif -#define PRIV(sch) qdisc_priv(sch) +#define PRIV(sch) ((struct dsmark_qdisc_data *) qdisc_priv(sch)) /* @@ -55,24 +55,38 @@ struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto *filter_list; - __u8 *mask; /* "owns" the array */ - __u8 *value; - __u16 indices; - __u32 default_index; /* index range is 0...0xffff */ + u8 *mask; /* "owns" the array */ + u8 *value; + u16 indices; + u32 default_index; /* index range is 0...0xffff */ int set_tc_index; }; +static inline int dsmark_valid_indices(u16 indices) +{ + while (indices != 1) { + if (indices & 1) + return 0; + indices >>= 1; + } + + return 1; +} -/* ------------------------- Class/flow operations ------------------------- */ +static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) +{ + return (index <= p->indices && index > 0); +} +/* ------------------------- Class/flow operations ------------------------- */ -static int dsmark_graft(struct Qdisc *sch,unsigned long arg, - struct Qdisc *new,struct Qdisc **old) +static int dsmark_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old) { struct dsmark_qdisc_data *p = PRIV(sch); - DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n",sch,p,new, - old); + DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n", + sch, p, new, old); if (new == NULL) { new = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops); @@ -81,91 +95,95 @@ static int dsmark_graft(struct Qdisc *sch,unsigned long arg, } sch_tree_lock(sch); - *old = xchg(&p->q,new); - if (*old) - qdisc_reset(*old); + *old = xchg(&p->q, new); + qdisc_reset(*old); sch->q.qlen = 0; - sch_tree_unlock(sch); /* @@@ move up ? */ + sch_tree_unlock(sch); + return 0; } - static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) { - struct dsmark_qdisc_data *p = PRIV(sch); - - return p->q; + return PRIV(sch)->q; } - -static unsigned long dsmark_get(struct Qdisc *sch,u32 classid) +static unsigned long dsmark_get(struct Qdisc *sch, u32 classid) { - struct dsmark_qdisc_data *p __attribute__((unused)) = PRIV(sch); + DPRINTK("dsmark_get(sch %p,[qdisc %p],classid %x)\n", + sch, PRIV(sch), classid); - DPRINTK("dsmark_get(sch %p,[qdisc %p],classid %x)\n",sch,p,classid); - return TC_H_MIN(classid)+1; + return TC_H_MIN(classid) + 1; } - static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) + unsigned long parent, u32 classid) { - return dsmark_get(sch,classid); + return dsmark_get(sch, classid); } - static void dsmark_put(struct Qdisc *sch, unsigned long cl) { } - static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct rtattr **tca, unsigned long *arg) + struct rtattr **tca, unsigned long *arg) { struct dsmark_qdisc_data *p = PRIV(sch); struct rtattr *opt = tca[TCA_OPTIONS-1]; struct rtattr *tb[TCA_DSMARK_MAX]; + int err = -EINVAL; + u8 mask = 0; DPRINTK("dsmark_change(sch %p,[qdisc %p],classid %x,parent %x)," - "arg 0x%lx\n",sch,p,classid,parent,*arg); - if (*arg > p->indices) - return -ENOENT; - if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt)) - return -EINVAL; - if (tb[TCA_DSMARK_MASK-1]) { - if (!RTA_PAYLOAD(tb[TCA_DSMARK_MASK-1])) - return -EINVAL; - p->mask[*arg-1] = *(__u8 *) RTA_DATA(tb[TCA_DSMARK_MASK-1]); - } - if (tb[TCA_DSMARK_VALUE-1]) { - if (!RTA_PAYLOAD(tb[TCA_DSMARK_VALUE-1])) - return -EINVAL; - p->value[*arg-1] = *(__u8 *) RTA_DATA(tb[TCA_DSMARK_VALUE-1]); + "arg 0x%lx\n", sch, p, classid, parent, *arg); + + if (!dsmark_valid_index(p, *arg)) { + err = -ENOENT; + goto rtattr_failure; } - return 0; -} + if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt)) + goto rtattr_failure; + + if (tb[TCA_DSMARK_MASK-1]) + mask = RTA_GET_U8(tb[TCA_DSMARK_MASK-1]); + + if (tb[TCA_DSMARK_VALUE-1]) + p->value[*arg-1] = RTA_GET_U8(tb[TCA_DSMARK_VALUE-1]); + + if (tb[TCA_DSMARK_MASK-1]) + p->mask[*arg-1] = mask; + + err = 0; -static int dsmark_delete(struct Qdisc *sch,unsigned long arg) +rtattr_failure: + return err; +} + +static int dsmark_delete(struct Qdisc *sch, unsigned long arg) { struct dsmark_qdisc_data *p = PRIV(sch); - if (!arg || arg > p->indices) + if (!dsmark_valid_index(p, arg)) return -EINVAL; + p->mask[arg-1] = 0xff; p->value[arg-1] = 0; + return 0; } - static void dsmark_walk(struct Qdisc *sch,struct qdisc_walker *walker) { struct dsmark_qdisc_data *p = PRIV(sch); int i; - DPRINTK("dsmark_walk(sch %p,[qdisc %p],walker %p)\n",sch,p,walker); + DPRINTK("dsmark_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + if (walker->stop) return; + for (i = 0; i < p->indices; i++) { if (p->mask[i] == 0xff && !p->value[i]) goto ignore; @@ -180,26 +198,20 @@ ignore: } } - static struct tcf_proto **dsmark_find_tcf(struct Qdisc *sch,unsigned long cl) { - struct dsmark_qdisc_data *p = PRIV(sch); - - return &p->filter_list; + return &PRIV(sch)->filter_list; } - /* --------------------------- Qdisc operations ---------------------------- */ - static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); - struct tcf_result res; - int result; - int ret = NET_XMIT_POLICED; + int err; + + D2PRINTK("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - D2PRINTK("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); if (p->set_tc_index) { /* FIXME: Safe with non-linear skbs? --RR */ switch (skb->protocol) { @@ -216,17 +228,21 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) break; }; } - result = TC_POLICE_OK; /* be nice to gcc */ - if (TC_H_MAJ(skb->priority) == sch->handle) { + + if (TC_H_MAJ(skb->priority) == sch->handle) skb->tc_index = TC_H_MIN(skb->priority); - } else { - result = tc_classify(skb,p->filter_list,&res); - D2PRINTK("result %d class 0x%04x\n",result,res.classid); + else { + struct tcf_result res; + int result = tc_classify(skb, p->filter_list, &res); + + D2PRINTK("result %d class 0x%04x\n", result, res.classid); + switch (result) { #ifdef CONFIG_NET_CLS_POLICE case TC_POLICE_SHOT: kfree_skb(skb); - break; + sch->qstats.drops++; + return NET_XMIT_POLICED; #if 0 case TC_POLICE_RECLASSIFY: /* FIXME: what to do here ??? */ @@ -243,43 +259,45 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) break; }; } - if ( -#ifdef CONFIG_NET_CLS_POLICE - result == TC_POLICE_SHOT || -#endif - ((ret = p->q->enqueue(skb,p->q)) != 0)) { + err = p->q->enqueue(skb,p->q); + if (err != NET_XMIT_SUCCESS) { sch->qstats.drops++; - return ret; + return err; } + sch->bstats.bytes += skb->len; sch->bstats.packets++; sch->q.qlen++; - return ret; -} + return NET_XMIT_SUCCESS; +} static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); struct sk_buff *skb; - int index; + u32 index; + + D2PRINTK("dsmark_dequeue(sch %p,[qdisc %p])\n", sch, p); - D2PRINTK("dsmark_dequeue(sch %p,[qdisc %p])\n",sch,p); skb = p->q->ops->dequeue(p->q); - if (!skb) + if (skb == NULL) return NULL; + sch->q.qlen--; - index = skb->tc_index & (p->indices-1); - D2PRINTK("index %d->%d\n",skb->tc_index,index); + + index = skb->tc_index & (p->indices - 1); + D2PRINTK("index %d->%d\n", skb->tc_index, index); + switch (skb->protocol) { case __constant_htons(ETH_P_IP): - ipv4_change_dsfield(skb->nh.iph, - p->mask[index],p->value[index]); + ipv4_change_dsfield(skb->nh.iph, p->mask[index], + p->value[index]); break; case __constant_htons(ETH_P_IPV6): - ipv6_change_dsfield(skb->nh.ipv6h, - p->mask[index],p->value[index]); + ipv6_change_dsfield(skb->nh.ipv6h, p->mask[index], + p->value[index]); break; default: /* @@ -293,152 +311,162 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) htons(skb->protocol)); break; }; + return skb; } - static int dsmark_requeue(struct sk_buff *skb,struct Qdisc *sch) { - int ret; struct dsmark_qdisc_data *p = PRIV(sch); + int err; - D2PRINTK("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - if ((ret = p->q->ops->requeue(skb, p->q)) == 0) { - sch->q.qlen++; - sch->qstats.requeues++; - return 0; + D2PRINTK("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + + err = p->q->ops->requeue(skb, p->q); + if (err != NET_XMIT_SUCCESS) { + sch->qstats.drops++; + return err; } - sch->qstats.drops++; - return ret; -} + sch->q.qlen++; + sch->qstats.requeues++; + + return NET_XMIT_SUCCESS; +} static unsigned int dsmark_drop(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); unsigned int len; - DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n",sch,p); - if (!p->q->ops->drop) - return 0; - if (!(len = p->q->ops->drop(p->q))) + DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + + if (p->q->ops->drop == NULL) return 0; - sch->q.qlen--; + + len = p->q->ops->drop(p->q); + if (len) + sch->q.qlen--; + return len; } - -static int dsmark_init(struct Qdisc *sch,struct rtattr *opt) +static int dsmark_init(struct Qdisc *sch, struct rtattr *opt) { struct dsmark_qdisc_data *p = PRIV(sch); struct rtattr *tb[TCA_DSMARK_MAX]; - __u16 tmp; - - DPRINTK("dsmark_init(sch %p,[qdisc %p],opt %p)\n",sch,p,opt); - if (!opt || - rtattr_parse(tb,TCA_DSMARK_MAX,RTA_DATA(opt),RTA_PAYLOAD(opt)) < 0 || - !tb[TCA_DSMARK_INDICES-1] || - RTA_PAYLOAD(tb[TCA_DSMARK_INDICES-1]) < sizeof(__u16)) - return -EINVAL; - p->indices = *(__u16 *) RTA_DATA(tb[TCA_DSMARK_INDICES-1]); - if (!p->indices) - return -EINVAL; - for (tmp = p->indices; tmp != 1; tmp >>= 1) { - if (tmp & 1) - return -EINVAL; - } - p->default_index = NO_DEFAULT_INDEX; - if (tb[TCA_DSMARK_DEFAULT_INDEX-1]) { - if (RTA_PAYLOAD(tb[TCA_DSMARK_DEFAULT_INDEX-1]) < sizeof(__u16)) - return -EINVAL; - p->default_index = - *(__u16 *) RTA_DATA(tb[TCA_DSMARK_DEFAULT_INDEX-1]); + int err = -EINVAL; + u32 default_index = NO_DEFAULT_INDEX; + u16 indices; + u8 *mask; + + DPRINTK("dsmark_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); + + if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt) < 0) + goto errout; + + indices = RTA_GET_U16(tb[TCA_DSMARK_INDICES-1]); + if (!indices || !dsmark_valid_indices(indices)) + goto errout; + + if (tb[TCA_DSMARK_DEFAULT_INDEX-1]) + default_index = RTA_GET_U16(tb[TCA_DSMARK_DEFAULT_INDEX-1]); + + mask = kmalloc(indices * 2, GFP_KERNEL); + if (mask == NULL) { + err = -ENOMEM; + goto errout; } - p->set_tc_index = !!tb[TCA_DSMARK_SET_TC_INDEX-1]; - p->mask = kmalloc(p->indices*2,GFP_KERNEL); - if (!p->mask) - return -ENOMEM; - p->value = p->mask+p->indices; - memset(p->mask,0xff,p->indices); - memset(p->value,0,p->indices); - if (!(p->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops))) + + p->mask = mask; + memset(p->mask, 0xff, indices); + + p->value = p->mask + indices; + memset(p->value, 0, indices); + + p->indices = indices; + p->default_index = default_index; + p->set_tc_index = RTA_GET_FLAG(tb[TCA_DSMARK_SET_TC_INDEX-1]); + + p->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops); + if (p->q == NULL) p->q = &noop_qdisc; - DPRINTK("dsmark_init: qdisc %p\n",&p->q); - return 0; -} + DPRINTK("dsmark_init: qdisc %p\n", p->q); + + err = 0; +errout: +rtattr_failure: + return err; +} static void dsmark_reset(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); - DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); qdisc_reset(p->q); sch->q.qlen = 0; } - static void dsmark_destroy(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); struct tcf_proto *tp; - DPRINTK("dsmark_destroy(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p); + while (p->filter_list) { tp = p->filter_list; p->filter_list = tp->next; tcf_destroy(tp); } + qdisc_destroy(p->q); kfree(p->mask); } - static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) + struct sk_buff *skb, struct tcmsg *tcm) { struct dsmark_qdisc_data *p = PRIV(sch); - unsigned char *b = skb->tail; - struct rtattr *rta; + struct rtattr *opts = NULL; + + DPRINTK("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n", sch, p, cl); - DPRINTK("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n",sch,p,cl); - if (!cl || cl > p->indices) + if (!dsmark_valid_index(p, cl)) return -EINVAL; - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle),cl-1); - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_DSMARK_MASK,1,&p->mask[cl-1]); - RTA_PUT(skb,TCA_DSMARK_VALUE,1,&p->value[cl-1]); - rta->rta_len = skb->tail-b; - return skb->len; + + tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + + opts = RTA_NEST(skb, TCA_OPTIONS); + RTA_PUT_U8(skb,TCA_DSMARK_MASK, p->mask[cl-1]); + RTA_PUT_U8(skb,TCA_DSMARK_VALUE, p->value[cl-1]); + + return RTA_NEST_END(skb, opts); rtattr_failure: - skb_trim(skb,b-skb->data); - return -1; + return RTA_NEST_CANCEL(skb, opts); } static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) { struct dsmark_qdisc_data *p = PRIV(sch); - unsigned char *b = skb->tail; - struct rtattr *rta; + struct rtattr *opts = NULL; - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_DSMARK_INDICES,sizeof(__u16),&p->indices); - if (p->default_index != NO_DEFAULT_INDEX) { - __u16 tmp = p->default_index; + opts = RTA_NEST(skb, TCA_OPTIONS); + RTA_PUT_U16(skb, TCA_DSMARK_INDICES, p->indices); + + if (p->default_index != NO_DEFAULT_INDEX) + RTA_PUT_U16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index); - RTA_PUT(skb,TCA_DSMARK_DEFAULT_INDEX, sizeof(__u16), &tmp); - } if (p->set_tc_index) - RTA_PUT(skb, TCA_DSMARK_SET_TC_INDEX, 0, NULL); - rta->rta_len = skb->tail-b; - return skb->len; + RTA_PUT_FLAG(skb, TCA_DSMARK_SET_TC_INDEX); + + return RTA_NEST_END(skb, opts); rtattr_failure: - skb_trim(skb,b-skb->data); - return -1; + return RTA_NEST_CANCEL(skb, opts); } static struct Qdisc_class_ops dsmark_class_ops = { @@ -476,10 +504,13 @@ static int __init dsmark_module_init(void) { return register_qdisc(&dsmark_qdisc_ops); } + static void __exit dsmark_module_exit(void) { unregister_qdisc(&dsmark_qdisc_ops); } + module_init(dsmark_module_init) module_exit(dsmark_module_exit) + MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 4888305c96d..033083bf0e7 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -11,131 +11,38 @@ #include <linux/config.h> #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> #include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> #include <net/pkt_sched.h> /* 1 band FIFO pseudo-"scheduler" */ struct fifo_sched_data { - unsigned limit; + u32 limit; }; -static int -bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) { struct fifo_sched_data *q = qdisc_priv(sch); - if (sch->qstats.backlog + skb->len <= q->limit) { - __skb_queue_tail(&sch->q, skb); - sch->qstats.backlog += skb->len; - sch->bstats.bytes += skb->len; - sch->bstats.packets++; - return 0; - } - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE - if (sch->reshape_fail==NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - return NET_XMIT_DROP; -} - -static int -bfifo_requeue(struct sk_buff *skb, struct Qdisc* sch) -{ - __skb_queue_head(&sch->q, skb); - sch->qstats.backlog += skb->len; - sch->qstats.requeues++; - return 0; -} - -static struct sk_buff * -bfifo_dequeue(struct Qdisc* sch) -{ - struct sk_buff *skb; + if (likely(sch->qstats.backlog + skb->len <= q->limit)) + return qdisc_enqueue_tail(skb, sch); - skb = __skb_dequeue(&sch->q); - if (skb) - sch->qstats.backlog -= skb->len; - return skb; + return qdisc_reshape_fail(skb, sch); } -static unsigned int -fifo_drop(struct Qdisc* sch) -{ - struct sk_buff *skb; - - skb = __skb_dequeue_tail(&sch->q); - if (skb) { - unsigned int len = skb->len; - sch->qstats.backlog -= len; - kfree_skb(skb); - return len; - } - return 0; -} - -static void -fifo_reset(struct Qdisc* sch) -{ - skb_queue_purge(&sch->q); - sch->qstats.backlog = 0; -} - -static int -pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) { struct fifo_sched_data *q = qdisc_priv(sch); - if (sch->q.qlen < q->limit) { - __skb_queue_tail(&sch->q, skb); - sch->bstats.bytes += skb->len; - sch->bstats.packets++; - return 0; - } - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE - if (sch->reshape_fail==NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - return NET_XMIT_DROP; -} - -static int -pfifo_requeue(struct sk_buff *skb, struct Qdisc* sch) -{ - __skb_queue_head(&sch->q, skb); - sch->qstats.requeues++; - return 0; -} - + if (likely(skb_queue_len(&sch->q) < q->limit)) + return qdisc_enqueue_tail(skb, sch); -static struct sk_buff * -pfifo_dequeue(struct Qdisc* sch) -{ - return __skb_dequeue(&sch->q); + return qdisc_reshape_fail(skb, sch); } static int fifo_init(struct Qdisc *sch, struct rtattr *opt) @@ -143,66 +50,59 @@ static int fifo_init(struct Qdisc *sch, struct rtattr *opt) struct fifo_sched_data *q = qdisc_priv(sch); if (opt == NULL) { - unsigned int limit = sch->dev->tx_queue_len ? : 1; + u32 limit = sch->dev->tx_queue_len ? : 1; if (sch->ops == &bfifo_qdisc_ops) - q->limit = limit*sch->dev->mtu; - else - q->limit = limit; + limit *= sch->dev->mtu; + + q->limit = limit; } else { struct tc_fifo_qopt *ctl = RTA_DATA(opt); - if (opt->rta_len < RTA_LENGTH(sizeof(*ctl))) + + if (RTA_PAYLOAD(opt) < sizeof(*ctl)) return -EINVAL; + q->limit = ctl->limit; } + return 0; } static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fifo_sched_data *q = qdisc_priv(sch); - unsigned char *b = skb->tail; - struct tc_fifo_qopt opt; + struct tc_fifo_qopt opt = { .limit = q->limit }; - opt.limit = q->limit; RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); - return skb->len; rtattr_failure: - skb_trim(skb, b - skb->data); return -1; } struct Qdisc_ops pfifo_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "pfifo", .priv_size = sizeof(struct fifo_sched_data), .enqueue = pfifo_enqueue, - .dequeue = pfifo_dequeue, - .requeue = pfifo_requeue, - .drop = fifo_drop, + .dequeue = qdisc_dequeue_head, + .requeue = qdisc_requeue, + .drop = qdisc_queue_drop, .init = fifo_init, - .reset = fifo_reset, - .destroy = NULL, + .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; struct Qdisc_ops bfifo_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "bfifo", .priv_size = sizeof(struct fifo_sched_data), .enqueue = bfifo_enqueue, - .dequeue = bfifo_dequeue, - .requeue = bfifo_requeue, - .drop = fifo_drop, + .dequeue = qdisc_dequeue_head, + .requeue = qdisc_requeue, + .drop = qdisc_queue_drop, .init = fifo_init, - .reset = fifo_reset, - .destroy = NULL, + .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 87e48a4e105..7683b34dc6a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -243,31 +243,27 @@ static void dev_watchdog_down(struct net_device *dev) cheaper. */ -static int -noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc) +static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc) { kfree_skb(skb); return NET_XMIT_CN; } -static struct sk_buff * -noop_dequeue(struct Qdisc * qdisc) +static struct sk_buff *noop_dequeue(struct Qdisc * qdisc) { return NULL; } -static int -noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc) +static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc) { if (net_ratelimit()) - printk(KERN_DEBUG "%s deferred output. It is buggy.\n", skb->dev->name); + printk(KERN_DEBUG "%s deferred output. It is buggy.\n", + skb->dev->name); kfree_skb(skb); return NET_XMIT_CN; } struct Qdisc_ops noop_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "noop", .priv_size = 0, .enqueue = noop_enqueue, @@ -285,8 +281,6 @@ struct Qdisc noop_qdisc = { }; static struct Qdisc_ops noqueue_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "noqueue", .priv_size = 0, .enqueue = noop_enqueue, @@ -311,97 +305,87 @@ static const u8 prio2band[TC_PRIO_MAX+1] = generic prio+fifo combination. */ -static int -pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +#define PFIFO_FAST_BANDS 3 + +static inline struct sk_buff_head *prio2list(struct sk_buff *skb, + struct Qdisc *qdisc) { struct sk_buff_head *list = qdisc_priv(qdisc); + return list + prio2band[skb->priority & TC_PRIO_MAX]; +} - list += prio2band[skb->priority&TC_PRIO_MAX]; +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +{ + struct sk_buff_head *list = prio2list(skb, qdisc); - if (list->qlen < qdisc->dev->tx_queue_len) { - __skb_queue_tail(list, skb); + if (skb_queue_len(list) < qdisc->dev->tx_queue_len) { qdisc->q.qlen++; - qdisc->bstats.bytes += skb->len; - qdisc->bstats.packets++; - return 0; + return __qdisc_enqueue_tail(skb, qdisc, list); } - qdisc->qstats.drops++; - kfree_skb(skb); - return NET_XMIT_DROP; + + return qdisc_drop(skb, qdisc); } -static struct sk_buff * -pfifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) { int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - struct sk_buff *skb; - for (prio = 0; prio < 3; prio++, list++) { - skb = __skb_dequeue(list); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++, list++) { + struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list); if (skb) { qdisc->q.qlen--; return skb; } } + return NULL; } -static int -pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) +static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) { - struct sk_buff_head *list = qdisc_priv(qdisc); - - list += prio2band[skb->priority&TC_PRIO_MAX]; - - __skb_queue_head(list, skb); qdisc->q.qlen++; - qdisc->qstats.requeues++; - return 0; + return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc)); } -static void -pfifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc* qdisc) { int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - for (prio=0; prio < 3; prio++) - skb_queue_purge(list+prio); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + __qdisc_reset_queue(qdisc, list + prio); + + qdisc->qstats.backlog = 0; qdisc->q.qlen = 0; } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { - unsigned char *b = skb->tail; - struct tc_prio_qopt opt; + struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - opt.bands = 3; memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; rtattr_failure: - skb_trim(skb, b - skb->data); return -1; } static int pfifo_fast_init(struct Qdisc *qdisc, struct rtattr *opt) { - int i; + int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - for (i=0; i<3; i++) - skb_queue_head_init(list+i); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + skb_queue_head_init(list + prio); return 0; } static struct Qdisc_ops pfifo_fast_ops = { - .next = NULL, - .cl_ops = NULL, .id = "pfifo_fast", - .priv_size = 3 * sizeof(struct sk_buff_head), + .priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .requeue = pfifo_fast_requeue, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 2a3c0e08a09..e6926cb1942 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4368,15 +4368,11 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, * However, this function was corrent in any case. 8) */ if (flags & MSG_PEEK) { - unsigned long cpu_flags; - - sctp_spin_lock_irqsave(&sk->sk_receive_queue.lock, - cpu_flags); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) atomic_inc(&skb->users); - sctp_spin_unlock_irqrestore(&sk->sk_receive_queue.lock, - cpu_flags); + spin_unlock_bh(&sk->sk_receive_queue.lock); } else { skb = skb_dequeue(&sk->sk_receive_queue); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d07f5ce3182..0a4260719a1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -216,8 +216,8 @@ out: expired: read_unlock(&xp->lock); - km_policy_expired(xp, dir, 1); - xfrm_policy_delete(xp, dir); + if (!xfrm_policy_delete(xp, dir)) + km_policy_expired(xp, dir, 1); xfrm_pol_put(xp); } @@ -555,7 +555,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, return NULL; } -void xfrm_policy_delete(struct xfrm_policy *pol, int dir) +int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { write_lock_bh(&xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); @@ -564,7 +564,9 @@ void xfrm_policy_delete(struct xfrm_policy *pol, int dir) if (dir < XFRM_POLICY_MAX) atomic_inc(&flow_cache_genid); xfrm_policy_kill(pol); + return 0; } + return -ENOENT; } int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d11747c2a76..2537f26f097 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -50,7 +50,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); static int xfrm_state_gc_flush_bundles; -static void __xfrm_state_delete(struct xfrm_state *x); +static int __xfrm_state_delete(struct xfrm_state *x); static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family); static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo); @@ -154,6 +154,7 @@ static void xfrm_timer_handler(unsigned long data) next = tmo; } + x->km.dying = warn; if (warn) km_state_expired(x, 0); resched: @@ -169,9 +170,8 @@ expired: next = 2; goto resched; } - if (x->id.spi != 0) + if (!__xfrm_state_delete(x) && x->id.spi) km_state_expired(x, 1); - __xfrm_state_delete(x); out: spin_unlock(&x->lock); @@ -215,8 +215,10 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static void __xfrm_state_delete(struct xfrm_state *x) +static int __xfrm_state_delete(struct xfrm_state *x) { + int err = -ESRCH; + if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&xfrm_state_lock); @@ -245,14 +247,21 @@ static void __xfrm_state_delete(struct xfrm_state *x) * is what we are dropping here. */ atomic_dec(&x->refcnt); + err = 0; } + + return err; } -void xfrm_state_delete(struct xfrm_state *x) +int xfrm_state_delete(struct xfrm_state *x) { + int err; + spin_lock_bh(&x->lock); - __xfrm_state_delete(x); + err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); + + return err; } EXPORT_SYMBOL(xfrm_state_delete); @@ -557,16 +566,18 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { - km_state_expired(x, 1); - if (!mod_timer(&x->timer, jiffies + XFRM_ACQ_EXPIRES*HZ)) + x->km.state = XFRM_STATE_EXPIRED; + if (!mod_timer(&x->timer, jiffies)) xfrm_state_hold(x); return -EINVAL; } if (!x->km.dying && (x->curlft.bytes >= x->lft.soft_byte_limit || - x->curlft.packets >= x->lft.soft_packet_limit)) + x->curlft.packets >= x->lft.soft_packet_limit)) { + x->km.dying = 1; km_state_expired(x, 0); + } return 0; } EXPORT_SYMBOL(xfrm_state_check_expire); @@ -796,34 +807,56 @@ EXPORT_SYMBOL(xfrm_replay_advance); static struct list_head xfrm_km_list = LIST_HEAD_INIT(xfrm_km_list); static DEFINE_RWLOCK(xfrm_km_lock); -static void km_state_expired(struct xfrm_state *x, int hard) +void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { struct xfrm_mgr *km; - if (hard) - x->km.state = XFRM_STATE_EXPIRED; - else - x->km.dying = 1; + read_lock(&xfrm_km_lock); + list_for_each_entry(km, &xfrm_km_list, list) + if (km->notify_policy) + km->notify_policy(xp, dir, c); + read_unlock(&xfrm_km_lock); +} +void km_state_notify(struct xfrm_state *x, struct km_event *c) +{ + struct xfrm_mgr *km; read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) - km->notify(x, hard); + if (km->notify) + km->notify(x, c); read_unlock(&xfrm_km_lock); +} + +EXPORT_SYMBOL(km_policy_notify); +EXPORT_SYMBOL(km_state_notify); + +static void km_state_expired(struct xfrm_state *x, int hard) +{ + struct km_event c; + + c.data.hard = hard; + c.event = XFRM_MSG_EXPIRE; + km_state_notify(x, &c); if (hard) wake_up(&km_waitq); } +/* + * We send to all registered managers regardless of failure + * We are happy with one success +*/ static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { - int err = -EINVAL; + int err = -EINVAL, acqret; struct xfrm_mgr *km; read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) { - err = km->acquire(x, t, pol, XFRM_POLICY_OUT); - if (!err) - break; + acqret = km->acquire(x, t, pol, XFRM_POLICY_OUT); + if (!acqret) + err = acqret; } read_unlock(&xfrm_km_lock); return err; @@ -848,13 +881,11 @@ EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard) { - struct xfrm_mgr *km; + struct km_event c; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) - if (km->notify_policy) - km->notify_policy(pol, dir, hard); - read_unlock(&xfrm_km_lock); + c.data.hard = hard; + c.event = XFRM_MSG_POLEXPIRE; + km_policy_notify(pol, dir, &c); if (hard) wake_up(&km_waitq); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 97509011c27..5ce8558eac9 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -277,6 +277,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) struct xfrm_usersa_info *p = NLMSG_DATA(nlh); struct xfrm_state *x; int err; + struct km_event c; err = verify_newsa_info(p, (struct rtattr **) xfrma); if (err) @@ -286,6 +287,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) if (!x) return err; + xfrm_state_hold(x); if (nlh->nlmsg_type == XFRM_MSG_NEWSA) err = xfrm_state_add(x); else @@ -294,14 +296,24 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) if (err < 0) { x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); + goto out; } + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + c.event = nlh->nlmsg_type; + + km_state_notify(x, &c); +out: + xfrm_state_put(x); return err; } static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { struct xfrm_state *x; + int err; + struct km_event c; struct xfrm_usersa_id *p = NLMSG_DATA(nlh); x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); @@ -313,10 +325,19 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) return -EPERM; } - xfrm_state_delete(x); + err = xfrm_state_delete(x); + if (err < 0) { + xfrm_state_put(x); + return err; + } + + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + c.event = nlh->nlmsg_type; + km_state_notify(x, &c); xfrm_state_put(x); - return 0; + return err; } static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) @@ -681,6 +702,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr { struct xfrm_userpolicy_info *p = NLMSG_DATA(nlh); struct xfrm_policy *xp; + struct km_event c; int err; int excl; @@ -692,6 +714,10 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr if (!xp) return err; + /* shouldnt excl be based on nlh flags?? + * Aha! this is anti-netlink really i.e more pfkey derived + * in netlink excl is a flag and you wouldnt need + * a type XFRM_MSG_UPDPOLICY - JHS */ excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY; err = xfrm_policy_insert(p->dir, xp, excl); if (err) { @@ -699,6 +725,11 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr return err; } + c.event = nlh->nlmsg_type; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(xp, p->dir, &c); + xfrm_pol_put(xp); return 0; @@ -816,6 +847,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr struct xfrm_policy *xp; struct xfrm_userpolicy_id *p; int err; + struct km_event c; int delete; p = NLMSG_DATA(nlh); @@ -843,6 +875,12 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr NETLINK_CB(skb).pid, MSG_DONTWAIT); } + } else { + c.data.byid = p->index; + c.event = nlh->nlmsg_type; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(xp, p->dir, &c); } xfrm_pol_put(xp); @@ -852,15 +890,28 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { + struct km_event c; struct xfrm_usersa_flush *p = NLMSG_DATA(nlh); xfrm_state_flush(p->proto); + c.data.proto = p->proto; + c.event = nlh->nlmsg_type; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_state_notify(NULL, &c); + return 0; } static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { + struct km_event c; + xfrm_policy_flush(); + c.event = nlh->nlmsg_type; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(NULL, 0, &c); return 0; } @@ -1069,15 +1120,16 @@ nlmsg_failure: return -1; } -static int xfrm_send_state_notify(struct xfrm_state *x, int hard) +static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) { struct sk_buff *skb; + int len = NLMSG_LENGTH(sizeof(struct xfrm_user_expire)); - skb = alloc_skb(sizeof(struct xfrm_user_expire) + 16, GFP_ATOMIC); + skb = alloc_skb(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; - if (build_expire(skb, x, hard) < 0) + if (build_expire(skb, x, c->data.hard) < 0) BUG(); NETLINK_CB(skb).dst_groups = XFRMGRP_EXPIRE; @@ -1085,6 +1137,131 @@ static int xfrm_send_state_notify(struct xfrm_state *x, int hard) return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC); } +static int xfrm_notify_sa_flush(struct km_event *c) +{ + struct xfrm_usersa_flush *p; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = NLMSG_LENGTH(sizeof(struct xfrm_usersa_flush)); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, + XFRM_MSG_FLUSHSA, sizeof(*p)); + nlh->nlmsg_flags = 0; + + p = NLMSG_DATA(nlh); + p->proto = c->data.proto; + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC); + +nlmsg_failure: + kfree_skb(skb); + return -1; +} + +static int inline xfrm_sa_len(struct xfrm_state *x) +{ + int l = 0; + if (x->aalg) + l += RTA_SPACE(sizeof(*x->aalg) + (x->aalg->alg_key_len+7)/8); + if (x->ealg) + l += RTA_SPACE(sizeof(*x->ealg) + (x->ealg->alg_key_len+7)/8); + if (x->calg) + l += RTA_SPACE(sizeof(*x->calg)); + if (x->encap) + l += RTA_SPACE(sizeof(*x->encap)); + + return l; +} + +static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) +{ + struct xfrm_usersa_info *p; + struct xfrm_usersa_id *id; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = xfrm_sa_len(x); + int headlen; + + headlen = sizeof(*p); + if (c->event == XFRM_MSG_DELSA) { + len += RTA_SPACE(headlen); + headlen = sizeof(*id); + } + len += NLMSG_SPACE(headlen); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, headlen); + nlh->nlmsg_flags = 0; + + p = NLMSG_DATA(nlh); + if (c->event == XFRM_MSG_DELSA) { + id = NLMSG_DATA(nlh); + memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr)); + id->spi = x->id.spi; + id->family = x->props.family; + id->proto = x->id.proto; + + p = RTA_DATA(__RTA_PUT(skb, XFRMA_SA, sizeof(*p))); + } + + copy_to_user_state(x, p); + + if (x->aalg) + RTA_PUT(skb, XFRMA_ALG_AUTH, + sizeof(*(x->aalg))+(x->aalg->alg_key_len+7)/8, x->aalg); + if (x->ealg) + RTA_PUT(skb, XFRMA_ALG_CRYPT, + sizeof(*(x->ealg))+(x->ealg->alg_key_len+7)/8, x->ealg); + if (x->calg) + RTA_PUT(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + + if (x->encap) + RTA_PUT(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC); + +nlmsg_failure: +rtattr_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c) +{ + + switch (c->event) { + case XFRM_MSG_EXPIRE: + return xfrm_exp_state_notify(x, c); + case XFRM_MSG_DELSA: + case XFRM_MSG_UPDSA: + case XFRM_MSG_NEWSA: + return xfrm_notify_sa(x, c); + case XFRM_MSG_FLUSHSA: + return xfrm_notify_sa_flush(c); + default: + printk("xfrm_user: Unknown SA event %d\n", c->event); + break; + } + + return 0; + +} + static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp, int dir) @@ -1218,7 +1395,7 @@ nlmsg_failure: return -1; } -static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) +static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { struct sk_buff *skb; size_t len; @@ -1229,7 +1406,7 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) if (skb == NULL) return -ENOMEM; - if (build_polexpire(skb, xp, dir, hard) < 0) + if (build_polexpire(skb, xp, dir, c->data.hard) < 0) BUG(); NETLINK_CB(skb).dst_groups = XFRMGRP_EXPIRE; @@ -1237,6 +1414,103 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC); } +static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + struct xfrm_userpolicy_info *p; + struct xfrm_userpolicy_id *id; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = RTA_SPACE(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); + int headlen; + + headlen = sizeof(*p); + if (c->event == XFRM_MSG_DELPOLICY) { + len += RTA_SPACE(headlen); + headlen = sizeof(*id); + } + len += NLMSG_SPACE(headlen); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, headlen); + + p = NLMSG_DATA(nlh); + if (c->event == XFRM_MSG_DELPOLICY) { + id = NLMSG_DATA(nlh); + memset(id, 0, sizeof(*id)); + id->dir = dir; + if (c->data.byid) + id->index = xp->index; + else + memcpy(&id->sel, &xp->selector, sizeof(id->sel)); + + p = RTA_DATA(__RTA_PUT(skb, XFRMA_POLICY, sizeof(*p))); + } + + nlh->nlmsg_flags = 0; + + copy_to_user_policy(xp, p, dir); + if (copy_to_user_tmpl(xp, skb) < 0) + goto nlmsg_failure; + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC); + +nlmsg_failure: +rtattr_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_notify_policy_flush(struct km_event *c) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = NLMSG_LENGTH(0); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + + nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0); + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC); + +nlmsg_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + + switch (c->event) { + case XFRM_MSG_NEWPOLICY: + case XFRM_MSG_UPDPOLICY: + case XFRM_MSG_DELPOLICY: + return xfrm_notify_policy(xp, dir, c); + case XFRM_MSG_FLUSHPOLICY: + return xfrm_notify_policy_flush(c); + case XFRM_MSG_POLEXPIRE: + return xfrm_exp_policy_notify(xp, dir, c); + default: + printk("xfrm_user: Unknown Policy event %d\n", c->event); + } + + return 0; + +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index f0fb6d76f7c..92b057becb4 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -63,6 +63,8 @@ static struct nlmsg_perm nlmsg_route_perms[] = { RTM_GETPREFIX, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETMULTICAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETANYCAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_GETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_SETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; static struct nlmsg_perm nlmsg_firewall_perms[] = |