diff options
Diffstat (limited to 'net')
58 files changed, 456 insertions, 228 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c index 4d638944d933..34e42968b477 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -59,8 +59,10 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, proto = find_snap_client(skb->h.raw); if (proto) { /* Pass the frame on. */ + u8 *hdr = skb->data; skb->h.raw += 5; skb_pull(skb, 5); + skb_postpull_rcsum(skb, hdr, 5); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } else { skb->sk = NULL; diff --git a/net/Kconfig b/net/Kconfig index bc603d9aea56..5126f58d9c44 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -27,6 +27,13 @@ if NET menu "Networking options" +config NETDEBUG + bool "Network packet debugging" + help + You can say Y here if you want to get additional messages useful in + debugging bad packets, but can overwhelm logs under denial of service + attacks. + source "net/packet/Kconfig" source "net/unix/Kconfig" source "net/xfrm/Kconfig" diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ba442883e877..da687c8dc6ff 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -104,6 +104,7 @@ static void destroy_nbp(struct net_bridge_port *p) { struct net_device *dev = p->dev; + dev->br_port = NULL; p->br = NULL; p->dev = NULL; dev_put(dev); @@ -118,13 +119,24 @@ static void destroy_nbp_rcu(struct rcu_head *head) destroy_nbp(p); } -/* called with RTNL */ +/* Delete port(interface) from bridge is done in two steps. + * via RCU. First step, marks device as down. That deletes + * all the timers and stops new packets from flowing through. + * + * Final cleanup doesn't occur until after all CPU's finished + * processing packets. + * + * Protected from multiple admin operations by RTNL mutex + */ static void del_nbp(struct net_bridge_port *p) { struct net_bridge *br = p->br; struct net_device *dev = p->dev; - dev->br_port = NULL; + /* Race between RTNL notify and RCU callback */ + if (p->deleted) + return; + dev_set_promiscuity(dev, -1); cancel_delayed_work(&p->carrier_check); @@ -132,16 +144,13 @@ static void del_nbp(struct net_bridge_port *p) spin_lock_bh(&br->lock); br_stp_disable_port(p); + p->deleted = 1; spin_unlock_bh(&br->lock); br_fdb_delete_by_port(br, p); list_del_rcu(&p->list); - del_timer_sync(&p->message_age_timer); - del_timer_sync(&p->forward_delay_timer); - del_timer_sync(&p->hold_timer); - call_rcu(&p->rcu, destroy_nbp_rcu); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c5bd631ffcd5..e330b17b6d81 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -68,6 +68,7 @@ struct net_bridge_port /* STP */ u8 priority; u8 state; + u8 deleted; u16 port_no; unsigned char topology_change_ack; unsigned char config_pending; diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ce617b3dbbb8..802baf755ef4 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -46,7 +46,7 @@ #define PRINTR(format, args...) do { if (net_ratelimit()) \ printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0600); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) " "(defaults to 4096)"); @@ -98,12 +98,14 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR(KERN_ERR "ebt_ulog: can't alloc whole buffer " - "of size %ub!\n", nlbufsiz); - if (size < nlbufsiz) { + "of size %ub!\n", n); + if (n > size) { /* try to allocate only as much as we need for * current packet */ skb = alloc_skb(size, GFP_ATOMIC); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 00729b3604f8..cbd4020cc84d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -934,6 +934,13 @@ static int do_replace(void __user *user, unsigned int len) BUGPRINT("Entries_size never zero\n"); return -EINVAL; } + /* overflow check */ + if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) + return -ENOMEM; + countersize = COUNTER_OFFSET(tmp.nentries) * (highest_possible_processor_id()+1); newinfo = (struct ebt_table_info *) diff --git a/net/core/dev.c b/net/core/dev.c index fd070a098f20..2afb0de95329 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2543,13 +2543,14 @@ int dev_ioctl(unsigned int cmd, void __user *arg) case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: case SIOCBONDCHANGEACTIVE: case SIOCBRADDIF: case SIOCBRDELIF: if (!capable(CAP_NET_ADMIN)) return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: dev_load(ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(&ifr, cmd); @@ -3236,7 +3237,7 @@ static int __init net_dev_init(void) * Initialise the packet receive queues. */ - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct softnet_data *queue; queue = &per_cpu(softnet_data, i); diff --git a/net/core/filter.c b/net/core/filter.c index 9540946a48f3..93fbd01d2259 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -64,7 +64,7 @@ static inline void *load_pointer(struct sk_buff *skb, int k, } /** - * sk_run_filter - run a filter on a socket + * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on * @filter: filter to apply * @flen: length of filter @@ -78,8 +78,8 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int { struct sock_filter *fentry; /* We walk down these */ void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ + u32 A = 0; /* Accumulator */ + u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ u32 tmp; int k; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d0732e9c8560..6766f118f070 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -135,13 +135,15 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int fclone) { + kmem_cache_t *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + /* Get the HEAD */ - skb = kmem_cache_alloc(fclone ? skbuff_fclone_cache : skbuff_head_cache, - gfp_mask & ~__GFP_DMA); + skb = kmem_cache_alloc(cache, gfp_mask & ~__GFP_DMA); if (!skb) goto out; @@ -180,7 +182,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, out: return skb; nodata: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(cache, skb); skb = NULL; goto out; } diff --git a/net/core/utils.c b/net/core/utils.c index ac1d1fcf8673..fdc4f38bc46c 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -121,7 +121,7 @@ void __init net_random_init(void) { int i; - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, i+jiffies); } @@ -133,7 +133,7 @@ static int net_random_reseed(void) unsigned long seed[NR_CPUS]; get_random_bytes(seed, sizeof(seed)); - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, seed[i]); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 00f983226672..dc0487b5bace 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -119,7 +119,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - err = ip_route_newports(&rt, inet->sport, inet->dport, sk); + err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport, + sk); if (err != 0) goto failure; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index df074259f9c3..80c4d048869e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -468,6 +468,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, done: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); return err; } diff --git a/net/ieee80211/ieee80211_rx.c b/net/ieee80211/ieee80211_rx.c index 7a121802faa9..960aa78cdb97 100644 --- a/net/ieee80211/ieee80211_rx.c +++ b/net/ieee80211/ieee80211_rx.c @@ -350,6 +350,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, u8 src[ETH_ALEN]; struct ieee80211_crypt_data *crypt = NULL; int keyidx = 0; + int can_be_decrypted = 0; hdr = (struct ieee80211_hdr_4addr *)skb->data; stats = &ieee->stats; @@ -410,12 +411,23 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, return 1; } - if (is_multicast_ether_addr(hdr->addr1) - ? ieee->host_mc_decrypt : ieee->host_decrypt) { + can_be_decrypted = (is_multicast_ether_addr(hdr->addr1) || + is_broadcast_ether_addr(hdr->addr2)) ? + ieee->host_mc_decrypt : ieee->host_decrypt; + + if (can_be_decrypted) { int idx = 0; - if (skb->len >= hdrlen + 3) + if (skb->len >= hdrlen + 3) { + /* Top two-bits of byte 3 are the key index */ idx = skb->data[hdrlen + 3] >> 6; + } + + /* ieee->crypt[] is WEP_KEY (4) in length. Given that idx + * is only allowed 2-bits of storage, no value of idx can + * be provided via above code that would result in idx + * being out of range */ crypt = ieee->crypt[idx]; + #ifdef NOT_YET sta = NULL; @@ -553,7 +565,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, /* skb: hdr + (possibly fragmented, possibly encrypted) payload */ - if (ieee->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) && + if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted && (keyidx = ieee80211_rx_frame_decrypt(ieee, skb, crypt)) < 0) goto rx_dropped; @@ -617,7 +629,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, /* skb: hdr + (possible reassembled) full MSDU payload; possibly still * encrypted/authenticated */ - if (ieee->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) && + if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted && ieee80211_rx_frame_decrypt_msdu(ieee, skb, keyidx, crypt)) goto rx_dropped; @@ -1439,7 +1451,7 @@ void ieee80211_rx_mgt(struct ieee80211_device *ieee, break; case IEEE80211_STYPE_PROBE_REQ: - IEEE80211_DEBUG_MGMT("recieved auth (%d)\n", + IEEE80211_DEBUG_MGMT("received auth (%d)\n", WLAN_FC_GET_STYPE(le16_to_cpu (header->frame_ctl))); @@ -1473,7 +1485,7 @@ void ieee80211_rx_mgt(struct ieee80211_device *ieee, break; case IEEE80211_STYPE_AUTH: - IEEE80211_DEBUG_MGMT("recieved auth (%d)\n", + IEEE80211_DEBUG_MGMT("received auth (%d)\n", WLAN_FC_GET_STYPE(le16_to_cpu (header->frame_ctl))); diff --git a/net/ieee80211/ieee80211_wx.c b/net/ieee80211/ieee80211_wx.c index 23e1630f50b7..f87c6b89f845 100644 --- a/net/ieee80211/ieee80211_wx.c +++ b/net/ieee80211/ieee80211_wx.c @@ -232,15 +232,18 @@ static char *ipw2100_translate_scan(struct ieee80211_device *ieee, return start; } +#define SCAN_ITEM_SIZE 128 + int ieee80211_wx_get_scan(struct ieee80211_device *ieee, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct ieee80211_network *network; unsigned long flags; + int err = 0; char *ev = extra; - char *stop = ev + IW_SCAN_MAX_DATA; + char *stop = ev + wrqu->data.length; int i = 0; IEEE80211_DEBUG_WX("Getting scan\n"); @@ -249,6 +252,11 @@ int ieee80211_wx_get_scan(struct ieee80211_device *ieee, list_for_each_entry(network, &ieee->network_list, list) { i++; + if (stop - ev < SCAN_ITEM_SIZE) { + err = -E2BIG; + break; + } + if (ieee->scan_age == 0 || time_after(network->last_scanned + ieee->scan_age, jiffies)) ev = ipw2100_translate_scan(ieee, ev, stop, network); @@ -270,7 +278,7 @@ int ieee80211_wx_get_scan(struct ieee80211_device *ieee, IEEE80211_DEBUG_WX("exit: %d networks returned.\n", i); - return 0; + return err; } int ieee80211_wx_set_encode(struct ieee80211_device *ieee, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 105039eb7629..4d1c40972a4b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -385,7 +385,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) u32 daddr; if (ip_options_echo(&icmp_param->replyopts, skb)) - goto out; + return; if (icmp_xmit_lock()) return; @@ -416,7 +416,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ip_rt_put(rt); out_unlock: icmp_xmit_unlock(); -out:; } @@ -525,7 +524,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) iph->tos; if (ip_options_echo(&icmp_param.replyopts, skb_in)) - goto ende; + goto out_unlock; /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d8ce7133cd8f..0b4e95f93dad 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -970,7 +970,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMP_MTRACE_RESP: break; default: - NETDEBUG(KERN_DEBUG "New IGMP type=%d, why we do not know about it?\n", ih->type); + break; } drop: diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c index d34a9fa608e0..342d0b9098f5 100644 --- a/net/ipv4/multipath_wrandom.c +++ b/net/ipv4/multipath_wrandom.c @@ -228,7 +228,7 @@ static void wrandom_set_nhinfo(__u32 network, struct multipath_dest *d, *target_dest = NULL; /* store the weight information for a certain route */ - spin_lock(&state[state_idx].lock); + spin_lock_bh(&state[state_idx].lock); /* find state entry for gateway or add one if necessary */ list_for_each_entry_rcu(r, &state[state_idx].head, list) { @@ -276,7 +276,7 @@ static void wrandom_set_nhinfo(__u32 network, * we are finished */ - spin_unlock(&state[state_idx].lock); + spin_unlock_bh(&state[state_idx].lock); } static void __multipath_free(struct rcu_head *head) @@ -302,7 +302,7 @@ static void wrandom_flush(void) for (i = 0; i < MULTIPATH_STATE_SIZE; ++i) { struct multipath_route *r; - spin_lock(&state[i].lock); + spin_lock_bh(&state[i].lock); list_for_each_entry_rcu(r, &state[i].head, list) { struct multipath_dest *d; list_for_each_entry_rcu(d, &r->dests, list) { @@ -315,7 +315,7 @@ static void wrandom_flush(void) __multipath_free); } - spin_unlock(&state[i].lock); + spin_unlock_bh(&state[i].lock); } } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index afe3d8f8177d..dd1048be8a01 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -807,6 +807,13 @@ static int do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index c9ebbe0d2d9c..e0b5926c76f9 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -1216,7 +1216,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1567,6 +1567,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/ipv4/netfilter/ip_conntrack_tftp.c b/net/ipv4/netfilter/ip_conntrack_tftp.c index d3c5a371f993..4ba4463cec28 100644 --- a/net/ipv4/netfilter/ip_conntrack_tftp.c +++ b/net/ipv4/netfilter/ip_conntrack_tftp.c @@ -71,6 +71,7 @@ static int tftp_help(struct sk_buff **pskb, exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; exp->mask.src.ip = 0xffffffff; + exp->mask.src.u.udp.port = 0; exp->mask.dst.ip = 0xffffffff; exp->mask.dst.u.udp.port = 0xffff; exp->mask.dst.protonum = 0xff; diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index ad438fb185b8..92c54999a19d 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -209,8 +209,8 @@ ip_nat_in(unsigned int hooknum, && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - if (ct->tuplehash[dir].tuple.src.ip != - ct->tuplehash[!dir].tuple.dst.ip) { + if (ct->tuplehash[dir].tuple.dst.ip != + ct->tuplehash[!dir].tuple.src.ip) { dst_release((*pskb)->dst); (*pskb)->dst = NULL; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2371b2062c2d..16f47c675fef 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -921,6 +921,13 @@ do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 641dbc477650..180a9ea57b69 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -35,6 +35,10 @@ * each nlgroup you are using, so the total kernel memory usage increases * by that factor. * + * Actually you should use nlbufsiz a bit smaller than PAGE_SIZE, since + * nlbufsiz is used with alloc_skb, which adds another + * sizeof(struct skb_shared_info). Use NLMSG_GOODSIZE instead. + * * flushtimeout: * Specify, after how many hundredths of a second the queue should be * flushed even if it is not full yet. @@ -76,7 +80,7 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); #define PRINTR(format, args...) do { if (net_ratelimit()) printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0400); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size"); @@ -143,22 +147,26 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; /* alloc skb which should be big enough for a whole * multipart message. WARNING: has to be <= 131000 * due to slab allocator restrictions */ - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { - PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", - nlbufsiz); + PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", n); - /* try to allocate only as much as we need for - * current packet */ + if (n > size) { + /* try to allocate only as much as we need for + * current packet */ - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - PRINTR("ipt_ULOG: can't even allocate %ub\n", size); + skb = alloc_skb(size, GFP_ATOMIC); + if (!skb) + PRINTR("ipt_ULOG: can't even allocate %ub\n", + size); + } } return skb; diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c index 18ca8258a1c5..5a7a265280f9 100644 --- a/net/ipv4/netfilter/ipt_policy.c +++ b/net/ipv4/netfilter/ipt_policy.c @@ -26,10 +26,13 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e) { -#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((e->x.a4.s_addr == (e->y.a4.s_addr & (z))) \ + ^ e->invert.x)) +#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) - return MATCH(saddr, x->props.saddr.a4 & e->smask) && - MATCH(daddr, x->id.daddr.a4 & e->dmask) && + return MATCH_ADDR(saddr, smask, x->props.saddr.a4) && + MATCH_ADDR(daddr, dmask, x->id.daddr.a4) && MATCH(proto, x->id.proto) && MATCH(mode, x->props.mode) && MATCH(spi, x->id.spi) && @@ -89,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 39d49dc333a7..1b167c4bb3be 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -49,7 +49,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 3284cfb993e6..128de4d7c0b7 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -230,7 +230,6 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, if (tp->snd_cwnd < tp->snd_cwnd_clamp) tp->snd_cwnd++; tp->snd_cwnd_cnt = 0; - ca->ccount++; } } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6ea353907af5..233bdf259965 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -236,7 +236,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - err = ip_route_newports(&rt, inet->sport, inet->dport, sk); + err = ip_route_newports(&rt, IPPROTO_TCP, inet->sport, inet->dport, sk); if (err) goto failure; @@ -1845,7 +1845,6 @@ void __init tcp_v4_init(struct net_proto_family *ops) } EXPORT_SYMBOL(ipv4_specific); -EXPORT_SYMBOL(inet_bind_bucket_create); EXPORT_SYMBOL(tcp_hashinfo); EXPORT_SYMBOL(tcp_prot); EXPORT_SYMBOL(tcp_unhash); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d328d5986143..1db50487916b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3321,9 +3321,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: - dst_hold(&ifp->rt->u.dst); - if (ip6_ins_rt(ifp->rt, NULL, NULL, NULL)) - dst_release(&ifp->rt->u.dst); + ip6_ins_rt(ifp->rt, NULL, NULL, NULL); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); break; @@ -3334,8 +3332,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) dst_hold(&ifp->rt->u.dst); if (ip6_del_rt(ifp->rt, NULL, NULL, NULL)) dst_free(&ifp->rt->u.dst); - else - dst_release(&ifp->rt->u.dst); break; } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 064ffab82a9f..6c9711ac1c03 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -369,12 +369,6 @@ int inet6_destroy_sock(struct sock *sk) struct sk_buff *skb; struct ipv6_txoptions *opt; - /* - * Release destination entry - */ - - sk_dst_reset(sk); - /* Release rx options */ if ((skb = xchg(&np->pktoptions, NULL)) != NULL) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6c05c7978bef..4420948a1bfe 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1252,8 +1252,7 @@ int igmp6_event_query(struct sk_buff *skb) } } else { for (ma = idev->mc_list; ma; ma=ma->next) { - if (group_type != IPV6_ADDR_ANY && - !ipv6_addr_equal(group, &ma->mca_addr)) + if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; spin_lock_bh(&ma->mca_lock); if (ma->mca_flags & MAF_TIMER_RUNNING) { @@ -1268,11 +1267,10 @@ int igmp6_event_query(struct sk_buff *skb) ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || - mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) + mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); - if (group_type != IPV6_ADDR_ANY) - break; + break; } } read_unlock_bh(&idev->lock); @@ -1351,7 +1349,7 @@ static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) - return 0; + return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } @@ -1966,7 +1964,7 @@ static void sf_markstate(struct ifmcaddr6 *pmc) static int sf_setstate(struct ifmcaddr6 *pmc) { - struct ip6_sf_list *psf; + struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; @@ -1978,8 +1976,48 @@ static int sf_setstate(struct ifmcaddr6 *pmc) !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; - if (new_in != psf->sf_oldin) { - psf->sf_crcount = qrv; + if (new_in) { + if (!psf->sf_oldin) { + struct ip6_sf_list *prev = 0; + + for (dpsf=pmc->mca_tomb; dpsf; + dpsf=dpsf->sf_next) { + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + prev = dpsf; + } + if (dpsf) { + if (prev) + prev->sf_next = dpsf->sf_next; + else + pmc->mca_tomb = dpsf->sf_next; + kfree(dpsf); + } + psf->sf_crcount = qrv; + rv++; + } + } else if (psf->sf_oldin) { + psf->sf_crcount = 0; + /* + * add or update "delete" records if an active filter + * is now inactive + */ + for (dpsf=pmc->mca_tomb; dpsf; dpsf=dpsf->sf_next) + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + if (!dpsf) { + dpsf = (struct ip6_sf_list *) + kmalloc(sizeof(*dpsf), GFP_ATOMIC); + if (!dpsf) + continue; + *dpsf = *psf; + /* pmc->mca_lock held by callers */ + dpsf->sf_next = pmc->mca_tomb; + pmc->mca_tomb = dpsf; + } + dpsf->sf_crcount = qrv; rv++; } } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 847068fd3367..74ff56c322f4 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -978,6 +978,13 @@ do_replace(void __user *user, unsigned int len) if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv6/netfilter/ip6t_policy.c b/net/ipv6/netfilter/ip6t_policy.c index afe1cc4c18a5..3d39ec924041 100644 --- a/net/ipv6/netfilter/ip6t_policy.c +++ b/net/ipv6/netfilter/ip6t_policy.c @@ -26,8 +26,9 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ip6t_policy_elem *e) { -#define MATCH_ADDR(x,y,z) (!e->match.x || \ - ((ip6_masked_addrcmp((z), &e->x, &e->y)) == 0) ^ e->invert.x) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((!ip6_masked_addrcmp(&e->x.a6, &e->y.a6, z)) \ + ^ e->invert.x)) #define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) return MATCH_ADDR(saddr, smask, (struct in6_addr *)&x->props.saddr.a6) && @@ -91,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ip6t_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 50a13e75d70e..4238b1ed8860 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -38,7 +38,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu=0; cpu<NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 66d04004afda..ca9cf6853755 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -515,6 +515,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, done: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); return err; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 43f1ce74187d..ae86d237a456 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1620,6 +1620,7 @@ static int key_notify_sa_flush(struct km_event *c) 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_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->pid; hdr->sadb_msg_version = PF_KEY_V2; @@ -2385,6 +2386,7 @@ static int key_notify_policy_flush(struct km_event *c) if (!skb_out) return -ENOBUFS; hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); + hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->pid; hdr->sadb_msg_version = PF_KEY_V2; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 62bb509f05d4..0ce337a1d974 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -188,7 +188,7 @@ extern struct nf_conntrack_protocol nf_conntrack_generic_protocol; struct nf_conntrack_protocol * __nf_ct_proto_find(u_int16_t l3proto, u_int8_t protocol) { - if (unlikely(nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_generic_protocol; return nf_ct_protos[l3proto][protocol]; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index ab0c920f0d30..6f210f399762 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -657,8 +657,6 @@ static int __init init(void) /* FIXME should be configurable whether IPv4 and IPv6 FTP connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - memset(&ftp[i], 0, sizeof(struct nf_conntrack_helper)); - ftp[i][0].tuple.src.l3num = PF_INET; ftp[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 73ab16bc7d40..9ff3463037e1 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1232,7 +1232,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1589,6 +1589,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e10512e229b6..3b3c781b40c0 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -37,7 +37,7 @@ #include "../bridge/br_private.h" #endif -#define NFULNL_NLBUFSIZ_DEFAULT 4096 +#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ @@ -314,24 +314,28 @@ static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; + unsigned int n; UDEBUG("entered (%u, %u)\n", inst_size, pkt_size); /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ - skb = alloc_skb(inst_size, GFP_ATOMIC); + n = max(inst_size, pkt_size); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR("nfnetlink_log: can't alloc whole buffer (%u bytes)\n", inst_size); - /* try to allocate only as much as we need for current - * packet */ + if (n > pkt_size) { + /* try to allocate only as much as we need for current + * packet */ - skb = alloc_skb(pkt_size, GFP_ATOMIC); - if (!skb) - PRINTR("nfnetlink_log: can't even alloc %u bytes\n", - pkt_size); + skb = alloc_skb(pkt_size, GFP_ATOMIC); + if (!skb) + PRINTR("nfnetlink_log: can't even alloc %u " + "bytes\n", pkt_size); + } } return skb; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 18ed9c5d209c..cac38b2e147a 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -825,7 +825,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, } if (nfqa[NFQA_MARK-1]) - skb->nfmark = ntohl(*(u_int32_t *)NFA_DATA(nfqa[NFQA_MARK-1])); + entry->skb->nfmark = ntohl(*(u_int32_t *) + NFA_DATA(nfqa[NFQA_MARK-1])); issue_verdict(entry, verdict); instance_put(queue); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ee93abc71cb8..9db7dbdb16e6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -365,7 +365,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, */ err = -EMSGSIZE; - if(len>dev->mtu+dev->hard_header_len) + if (len > dev->mtu + dev->hard_header_len) goto out_unlock; err = -ENOBUFS; @@ -935,7 +935,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add * Check legality */ - if(addr_len!=sizeof(struct sockaddr)) + if (addr_len != sizeof(struct sockaddr)) return -EINVAL; strlcpy(name,uaddr->sa_data,sizeof(name)); @@ -1092,7 +1092,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * retries. */ - if(skb==NULL) + if (skb == NULL) goto out; /* @@ -1392,8 +1392,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (level != SOL_PACKET) return -ENOPROTOOPT; - if (get_user(len,optlen)) - return -EFAULT; + if (get_user(len, optlen)) + return -EFAULT; if (len < 0) return -EINVAL; @@ -1419,9 +1419,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, return -ENOPROTOOPT; } - if (put_user(len, optlen)) - return -EFAULT; - return 0; + if (put_user(len, optlen)) + return -EFAULT; + return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 4aa6fc60357c..cb78b50868ee 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -257,20 +257,26 @@ int sctp_rcv(struct sk_buff *skb) */ sctp_bh_lock_sock(sk); + /* It is possible that the association could have moved to a different + * socket if it is peeled off. If so, update the sk. + */ + if (sk != rcvr->sk) { + sctp_bh_lock_sock(rcvr->sk); + sctp_bh_unlock_sock(sk); + sk = rcvr->sk; + } + if (sock_owned_by_user(sk)) sk_add_backlog(sk, skb); else sctp_backlog_rcv(sk, skb); - /* Release the sock and any reference counts we took in the - * lookup calls. + /* Release the sock and the sock ref we took in the lookup calls. + * The asoc/ep ref will be released in sctp_backlog_rcv. */ sctp_bh_unlock_sock(sk); - if (asoc) - sctp_association_put(asoc); - else - sctp_endpoint_put(ep); sock_put(sk); + return ret; discard_it: @@ -296,12 +302,50 @@ discard_release: int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; - struct sctp_inq *inqueue = &chunk->rcvr->inqueue; - - sctp_inq_push(inqueue, chunk); + struct sctp_inq *inqueue = NULL; + struct sctp_ep_common *rcvr = NULL; + + rcvr = chunk->rcvr; + + BUG_TRAP(rcvr->sk == sk); + + if (rcvr->dead) { + sctp_chunk_free(chunk); + } else { + inqueue = &chunk->rcvr->inqueue; + sctp_inq_push(inqueue, chunk); + } + + /* Release the asoc/ep ref we took in the lookup calls in sctp_rcv. */ + if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) + sctp_association_put(sctp_assoc(rcvr)); + else + sctp_endpoint_put(sctp_ep(rcvr)); + return 0; } +void sctp_backlog_migrate(struct sctp_association *assoc, + struct sock *oldsk, struct sock *newsk) +{ + struct sk_buff *skb; + struct sctp_chunk *chunk; + + skb = oldsk->sk_backlog.head; + oldsk->sk_backlog.head = oldsk->sk_backlog.tail = NULL; + while (skb != NULL) { + struct sk_buff *next = skb->next; + + chunk = SCTP_INPUT_CB(skb)->chunk; + skb->next = NULL; + if (&assoc->base == chunk->rcvr) + sk_add_backlog(newsk, skb); + else + sk_add_backlog(oldsk, skb); + skb = next; + } +} + /* Handle icmp frag needed error. */ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) @@ -544,10 +588,16 @@ int sctp_rcv_ootb(struct sk_buff *skb) sctp_errhdr_t *err; ch = (sctp_chunkhdr_t *) skb->data; - ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length)); /* Scan through all the chunks in the packet. */ - while (ch_end > (__u8 *)ch && ch_end < skb->tail) { + do { + /* Break out if chunk length is less then minimal. */ + if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + break; + + ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb->tail) + break; /* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the * receiver MUST silently discard the OOTB packet and take no @@ -578,8 +628,7 @@ int sctp_rcv_ootb(struct sk_buff *skb) } ch = (sctp_chunkhdr_t *) ch_end; - ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length)); - } + } while (ch_end < skb->tail); return 0; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 2d33922c044b..297b8951463e 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -73,8 +73,10 @@ void sctp_inq_free(struct sctp_inq *queue) /* If there is a packet which is currently being worked on, * free it as well. */ - if (queue->in_progress) + if (queue->in_progress) { sctp_chunk_free(queue->in_progress); + queue->in_progress = NULL; + } if (queue->malloced) { /* Dump the master memory segment. */ diff --git a/net/sctp/output.c b/net/sctp/output.c index a40991ef72c9..437cba7260a4 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -608,7 +608,7 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * When a Fast Retransmit is being performed the sender SHOULD * ignore the value of cwnd and SHOULD NOT delay retransmission. */ - if (!chunk->fast_retransmit) + if (chunk->fast_retransmit <= 0) if (transport->flight_size >= transport->cwnd) { retval = SCTP_XMIT_RWND_FULL; goto finish; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index efb72faba20c..f148f9576dd2 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -406,7 +406,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * chunks that are not yet acked should be added to the * retransmit queue. */ - if ((fast_retransmit && chunk->fast_retransmit) || + if ((fast_retransmit && (chunk->fast_retransmit > 0)) || (!fast_retransmit && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * @@ -603,7 +603,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ - chunk->fast_retransmit = 0; + if (chunk->fast_retransmit > 0) + chunk->fast_retransmit = -1; *start_timer = 1; q->empty = 0; @@ -621,7 +622,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, list_for_each(lchunk1, lqueue) { chunk1 = list_entry(lchunk1, struct sctp_chunk, transmitted_list); - chunk1->fast_retransmit = 0; + if (chunk1->fast_retransmit > 0) + chunk1->fast_retransmit = -1; } } } @@ -1562,11 +1564,11 @@ static void sctp_mark_missing(struct sctp_outq *q, /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' - * value larger than or equal to 4, mark that chunk for + * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ - if (chunk->tsn_missing_report >= 4) { + if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = 1; do_fast_retransmit = 1; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 6e4dc28874d7..d47a52c303a8 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -176,7 +176,7 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos > sctp_ep_hashsize) + if (*pos >= sctp_ep_hashsize) return NULL; if (*pos < 0) @@ -185,8 +185,6 @@ static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) seq_printf(seq, " ENDPT SOCK STY SST HBKT LPORT UID INODE LADDRS\n"); - ++*pos; - return (void *)pos; } @@ -198,11 +196,9 @@ static void sctp_eps_seq_stop(struct seq_file *seq, void *v) static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (*pos > sctp_ep_hashsize) + if (++*pos >= sctp_ep_hashsize) return NULL; - ++*pos; - return pos; } @@ -214,19 +210,19 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; - int hash = *(int *)v; + int hash = *(loff_t *)v; - if (hash > sctp_ep_hashsize) + if (hash >= sctp_ep_hashsize) return -ENOMEM; - head = &sctp_ep_hashtable[hash-1]; + head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); for (epb = head->chain; epb; epb = epb->next) { ep = sctp_ep(epb); sk = epb->sk; seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, - sctp_sk(sk)->type, sk->sk_state, hash-1, + sctp_sk(sk)->type, sk->sk_state, hash, epb->bind_addr.port, sock_i_uid(sk), sock_i_ino(sk)); @@ -283,7 +279,7 @@ void sctp_eps_proc_exit(void) static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos > sctp_assoc_hashsize) + if (*pos >= sctp_assoc_hashsize) return NULL; if (*pos < 0) @@ -293,8 +289,6 @@ static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) seq_printf(seq, " ASSOC SOCK STY SST ST HBKT ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " "RPORT LADDRS <-> RADDRS\n"); - ++*pos; - return (void *)pos; } @@ -306,11 +300,9 @@ static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (*pos > sctp_assoc_hashsize) + if (++*pos >= sctp_assoc_hashsize) return NULL; - ++*pos; - return pos; } @@ -321,12 +313,12 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; - int hash = *(int *)v; + int hash = *(loff_t *)v; - if (hash > sctp_assoc_hashsize) + if (hash >= sctp_assoc_hashsize) return -ENOMEM; - head = &sctp_assoc_hashtable[hash-1]; + head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); for (epb = head->chain; epb; epb = epb->next) { @@ -335,7 +327,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%8p %8p %-3d %-3d %-2d %-4d %4d %8d %8d %7d %5lu %-5d %5d ", assoc, sk, sctp_sk(sk)->type, sk->sk_state, - assoc->state, hash-1, assoc->assoc_id, + assoc->state, hash, assoc->assoc_id, (sk->sk_rcvbuf - assoc->rwnd), assoc->sndbuf_used, sock_i_uid(sk), sock_i_ino(sk), diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 556c495c6922..5e0de3c0eead 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1275,7 +1275,12 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, unsigned int keylen; char *key; - headersize = sizeof(sctp_paramhdr_t) + SCTP_SECRET_SIZE; + /* Header size is static data prior to the actual cookie, including + * any padding. + */ + headersize = sizeof(sctp_paramhdr_t) + + (sizeof(struct sctp_signed_cookie) - + sizeof(struct sctp_cookie)); bodysize = sizeof(struct sctp_cookie) + ntohs(init_chunk->chunk_hdr->length) + addrs_len; @@ -1354,7 +1359,7 @@ struct sctp_association *sctp_unpack_cookie( struct sctp_signed_cookie *cookie; struct sctp_cookie *bear_cookie; int headersize, bodysize, fixed_size; - __u8 digest[SCTP_SIGNATURE_SIZE]; + __u8 *digest = ep->digest; struct scatterlist sg; unsigned int keylen, len; char *key; @@ -1362,7 +1367,12 @@ struct sctp_association *sctp_unpack_cookie( struct sk_buff *skb = chunk->skb; struct timeval tv; - headersize = sizeof(sctp_chunkhdr_t) + SCTP_SECRET_SIZE; + /* Header size is static data prior to the actual cookie, including + * any padding. + */ + headersize = sizeof(sctp_chunkhdr_t) + + (sizeof(struct sctp_signed_cookie) - + sizeof(struct sctp_cookie)); bodysize = ntohs(chunk->chunk_hdr->length) - headersize; fixed_size = headersize + sizeof(struct sctp_cookie); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b8b38aba92b3..8d1dc24bab4c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1300,7 +1300,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, "T1 INIT Timeout adjustment" " init_err_counter: %d" " cycle: %d" - " timeout: %d\n", + " timeout: %ld\n", asoc->init_err_counter, asoc->init_cycle, asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT]); @@ -1328,7 +1328,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, SCTP_DEBUG_PRINTK( "T1 COOKIE Timeout adjustment" " init_err_counter: %d" - " timeout: %d\n", + " timeout: %ld\n", asoc->init_err_counter, asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE]); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 477d7f80dba6..2b9a832b29a7 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -884,7 +884,7 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep, { struct sctp_transport *transport = (struct sctp_transport *) arg; - if (asoc->overall_error_count > asoc->max_retrans) { + if (asoc->overall_error_count >= asoc->max_retrans) { /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_U32(SCTP_ERROR_NO_ERROR)); @@ -2122,7 +2122,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(const struct sctp_endpoint *ep, struct sctp_bind_addr *bp; int attempts = asoc->init_err_counter + 1; - if (attempts >= asoc->max_init_attempts) { + if (attempts > asoc->max_init_attempts) { sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_U32(SCTP_ERROR_STALE_COOKIE)); return SCTP_DISPOSITION_DELETE_TCB; @@ -3090,6 +3090,8 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, break; ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb->tail) + break; if (SCTP_CID_SHUTDOWN_ACK == ch->type) ootb_shut_ack = 1; @@ -4638,7 +4640,7 @@ sctp_disposition_t sctp_sf_t1_init_timer_expire(const struct sctp_endpoint *ep, SCTP_DEBUG_PRINTK("Timer T1 expired (INIT).\n"); - if (attempts < asoc->max_init_attempts) { + if (attempts <= asoc->max_init_attempts) { bp = (struct sctp_bind_addr *) &asoc->base.bind_addr; repl = sctp_make_init(asoc, bp, GFP_ATOMIC, 0); if (!repl) @@ -4695,7 +4697,7 @@ sctp_disposition_t sctp_sf_t1_cookie_timer_expire(const struct sctp_endpoint *ep SCTP_DEBUG_PRINTK("Timer T1 expired (COOKIE-ECHO).\n"); - if (attempts < asoc->max_init_attempts) { + if (attempts <= asoc->max_init_attempts) { repl = sctp_make_cookie_echo(asoc, NULL); if (!repl) return SCTP_DISPOSITION_NOMEM; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c98ee375ba5e..0ea947eb6813 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2995,7 +2995,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->hbinterval = jiffies_to_msecs(sctp_hb_interval); sp->pathmaxrxt = sctp_max_retrans_path; sp->pathmtu = 0; // allow default discovery - sp->sackdelay = sctp_sack_timeout; + sp->sackdelay = jiffies_to_msecs(sctp_sack_timeout); sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; @@ -5426,7 +5426,7 @@ out: return err; do_error: - if (asoc->init_err_counter + 1 >= asoc->max_init_attempts) + if (asoc->init_err_counter + 1 > asoc->max_init_attempts) err = -ETIMEDOUT; else err = -ECONNREFUSED; @@ -5602,8 +5602,12 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, */ newsp->type = type; + spin_lock_bh(&oldsk->sk_lock.slock); + /* Migrate the backlog from oldsk to newsk. */ + sctp_backlog_migrate(assoc, oldsk, newsk); /* Migrate the association to the new socket. */ sctp_assoc_migrate(assoc, newsk); + spin_unlock_bh(&oldsk->sk_lock.slock); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index fcd7096c953d..dc6f3ff32358 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -159,12 +159,9 @@ static ctl_table sctp_table[] = { .ctl_name = NET_SCTP_PRESERVE_ENABLE, .procname = "cookie_preserve_enable", .data = &sctp_cookie_preserve_enable, - .maxlen = sizeof(long), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec }, { .ctl_name = NET_SCTP_RTO_ALPHA, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 68d73e2dd155..160f62ad1cc5 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -350,7 +350,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto_pending = 0; SCTP_DEBUG_PRINTK("%s: transport: %p, rtt: %d, srtt: %d " - "rttvar: %d, rto: %d\n", __FUNCTION__, + "rttvar: %d, rto: %ld\n", __FUNCTION__, tp, rtt, tp->srtt, tp->rttvar, tp->rto); } diff --git a/net/socket.c b/net/socket.c index b38a263853c3..a00851f981db 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2078,7 +2078,7 @@ void socket_seq_show(struct seq_file *seq) int cpu; int counter = 0; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) counter += per_cpu(sockets_in_use, cpu); /* It can be negative, by the way. 8) */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 9ac1b8c26c01..8d6f1a176b15 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -184,7 +184,7 @@ rpcauth_gc_credcache(struct rpc_auth *auth, struct hlist_head *free) */ struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, - int taskflags) + int flags) { struct rpc_cred_cache *cache = auth->au_credcache; HLIST_HEAD(free); @@ -193,7 +193,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, *cred = NULL; int nr = 0; - if (!(taskflags & RPC_TASK_ROOTCREDS)) + if (!(flags & RPCAUTH_LOOKUP_ROOTCREDS)) nr = acred->uid & RPC_CREDCACHE_MASK; retry: spin_lock(&rpc_credcache_lock); @@ -202,7 +202,7 @@ retry: hlist_for_each_safe(pos, next, &cache->hashtable[nr]) { struct rpc_cred *entry; entry = hlist_entry(pos, struct rpc_cred, cr_hash); - if (entry->cr_ops->crmatch(acred, entry, taskflags)) { + if (entry->cr_ops->crmatch(acred, entry, flags)) { hlist_del(&entry->cr_hash); cred = entry; break; @@ -224,7 +224,7 @@ retry: rpcauth_destroy_credlist(&free); if (!cred) { - new = auth->au_ops->crcreate(auth, acred, taskflags); + new = auth->au_ops->crcreate(auth, acred, flags); if (!IS_ERR(new)) { #ifdef RPC_DEBUG new->cr_magic = RPCAUTH_CRED_MAGIC; @@ -232,13 +232,21 @@ retry: goto retry; } else cred = new; + } else if ((cred->cr_flags & RPCAUTH_CRED_NEW) + && cred->cr_ops->cr_init != NULL + && !(flags & RPCAUTH_LOOKUP_NEW)) { + int res = cred->cr_ops->cr_init(auth, cred); + if (res < 0) { + put_rpccred(cred); + cred = ERR_PTR(res); + } } return (struct rpc_cred *) cred; } struct rpc_cred * -rpcauth_lookupcred(struct rpc_auth *auth, int taskflags) +rpcauth_lookupcred(struct rpc_auth *auth, int flags) { struct auth_cred acred = { .uid = current->fsuid, @@ -250,7 +258,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int taskflags) dprintk("RPC: looking up %s cred\n", auth->au_ops->au_name); get_group_info(acred.group_info); - ret = auth->au_ops->lookup_cred(auth, &acred, taskflags); + ret = auth->au_ops->lookup_cred(auth, &acred, flags); put_group_info(acred.group_info); return ret; } @@ -265,11 +273,14 @@ rpcauth_bindcred(struct rpc_task *task) .group_info = current->group_info, }; struct rpc_cred *ret; + int flags = 0; dprintk("RPC: %4d looking up %s cred\n", task->tk_pid, task->tk_auth->au_ops->au_name); get_group_info(acred.group_info); - ret = auth->au_ops->lookup_cred(auth, &acred, task->tk_flags); + if (task->tk_flags & RPC_TASK_ROOTCREDS) + flags |= RPCAUTH_LOOKUP_ROOTCREDS; + ret = auth->au_ops->lookup_cred(auth, &acred, flags); if (!IS_ERR(ret)) task->tk_msg.rpc_cred = ret; else diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8d782282ec19..bb46efd92e57 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -158,6 +158,7 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) old = gss_cred->gc_ctx; gss_cred->gc_ctx = ctx; cred->cr_flags |= RPCAUTH_CRED_UPTODATE; + cred->cr_flags &= ~RPCAUTH_CRED_NEW; write_unlock(&gss_ctx_lock); if (old) gss_put_ctx(old); @@ -580,7 +581,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } else { struct auth_cred acred = { .uid = uid }; spin_unlock(&gss_auth->lock); - cred = rpcauth_lookup_credcache(clnt->cl_auth, &acred, 0); + cred = rpcauth_lookup_credcache(clnt->cl_auth, &acred, RPCAUTH_LOOKUP_NEW); if (IS_ERR(cred)) { err = PTR_ERR(cred); goto err_put_ctx; @@ -758,13 +759,13 @@ gss_destroy_cred(struct rpc_cred *rc) * Lookup RPCSEC_GSS cred for the current process */ static struct rpc_cred * -gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) +gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { - return rpcauth_lookup_credcache(auth, acred, taskflags); + return rpcauth_lookup_credcache(auth, acred, flags); } static struct rpc_cred * -gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) +gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth); struct gss_cred *cred = NULL; @@ -785,13 +786,8 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) */ cred->gc_flags = 0; cred->gc_base.cr_ops = &gss_credops; + cred->gc_base.cr_flags = RPCAUTH_CRED_NEW; cred->gc_service = gss_auth->service; - do { - err = gss_create_upcall(gss_auth, cred); - } while (err == -EAGAIN); - if (err < 0) - goto out_err; - return &cred->gc_base; out_err: @@ -801,13 +797,34 @@ out_err: } static int -gss_match(struct auth_cred *acred, struct rpc_cred *rc, int taskflags) +gss_cred_init(struct rpc_auth *auth, struct rpc_cred *cred) +{ + struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth); + struct gss_cred *gss_cred = container_of(cred,struct gss_cred, gc_base); + int err; + + do { + err = gss_create_upcall(gss_auth, gss_cred); + } while (err == -EAGAIN); + return err; +} + +static int +gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags) { struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base); + /* + * If the searchflags have set RPCAUTH_LOOKUP_NEW, then + * we don't really care if the credential has expired or not, + * since the caller should be prepared to reinitialise it. + */ + if ((flags & RPCAUTH_LOOKUP_NEW) && (rc->cr_flags & RPCAUTH_CRED_NEW)) + goto out; /* Don't match with creds that have expired. */ if (gss_cred->gc_ctx && time_after(jiffies, gss_cred->gc_ctx->gc_expiry)) return 0; +out: return (rc->cr_uid == acred->uid); } @@ -1241,6 +1258,7 @@ static struct rpc_authops authgss_ops = { static struct rpc_credops gss_credops = { .cr_name = "AUTH_GSS", .crdestroy = gss_destroy_cred, + .cr_init = gss_cred_init, .crmatch = gss_match, .crmarshal = gss_marshal, .crrefresh = gss_refresh, diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 1b3ed4fd1987..df14b6bfbf10 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -75,7 +75,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) atomic_set(&cred->uc_count, 1); cred->uc_flags = RPCAUTH_CRED_UPTODATE; - if (flags & RPC_TASK_ROOTCREDS) { + if (flags & RPCAUTH_LOOKUP_ROOTCREDS) { cred->uc_uid = 0; cred->uc_gid = 0; cred->uc_gids[0] = NOGROUP; @@ -108,12 +108,12 @@ unx_destroy_cred(struct rpc_cred *cred) * request root creds (e.g. for NFS swapping). */ static int -unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int taskflags) +unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) { struct unx_cred *cred = (struct unx_cred *) rcred; int i; - if (!(taskflags & RPC_TASK_ROOTCREDS)) { + if (!(flags & RPCAUTH_LOOKUP_ROOTCREDS)) { int groups; if (cred->uc_uid != acred->uid diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9764c80ab0b2..a5c0c7b6e151 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -38,44 +38,42 @@ static kmem_cache_t *rpc_inode_cachep __read_mostly; #define RPC_UPCALL_TIMEOUT (30*HZ) -static void -__rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, int err) +static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, + void (*destroy_msg)(struct rpc_pipe_msg *), int err) { struct rpc_pipe_msg *msg; - void (*destroy_msg)(struct rpc_pipe_msg *); - destroy_msg = rpci->ops->destroy_msg; - while (!list_empty(head)) { + if (list_empty(head)) + return; + do { msg = list_entry(head->next, struct rpc_pipe_msg, list); - list_del_init(&msg->list); + list_del(&msg->list); msg->errno = err; destroy_msg(msg); - } -} - -static void -__rpc_purge_upcall(struct inode *inode, int err) -{ - struct rpc_inode *rpci = RPC_I(inode); - - __rpc_purge_list(rpci, &rpci->pipe, err); - rpci->pipelen = 0; + } while (!list_empty(head)); wake_up(&rpci->waitq); } static void rpc_timeout_upcall_queue(void *data) { + LIST_HEAD(free_list); struct rpc_inode *rpci = (struct rpc_inode *)data; struct inode *inode = &rpci->vfs_inode; + void (*destroy_msg)(struct rpc_pipe_msg *); - mutex_lock(&inode->i_mutex); - if (rpci->ops == NULL) - goto out; - if (rpci->nreaders == 0 && !list_empty(&rpci->pipe)) - __rpc_purge_upcall(inode, -ETIMEDOUT); -out: - mutex_unlock(&inode->i_mutex); + spin_lock(&inode->i_lock); + if (rpci->ops == NULL) { + spin_unlock(&inode->i_lock); + return; + } + destroy_msg = rpci->ops->destroy_msg; + if (rpci->nreaders == 0) { + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; + } + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, destroy_msg, -ETIMEDOUT); } int @@ -84,7 +82,7 @@ rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg) struct rpc_inode *rpci = RPC_I(inode); int res = -EPIPE; - mutex_lock(&inode->i_mutex); + spin_lock(&inode->i_lock); if (rpci->ops == NULL) goto out; if (rpci->nreaders) { @@ -100,7 +98,7 @@ rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg) res = 0; } out: - mutex_unlock(&inode->i_mutex); + spin_unlock(&inode->i_lock); wake_up(&rpci->waitq); return res; } @@ -115,21 +113,29 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); + struct rpc_pipe_ops *ops; mutex_lock(&inode->i_mutex); - if (rpci->ops != NULL) { + ops = rpci->ops; + if (ops != NULL) { + LIST_HEAD(free_list); + + spin_lock(&inode->i_lock); rpci->nreaders = 0; - __rpc_purge_list(rpci, &rpci->in_upcall, -EPIPE); - __rpc_purge_upcall(inode, -EPIPE); - rpci->nwriters = 0; - if (rpci->ops->release_pipe) - rpci->ops->release_pipe(inode); + list_splice_init(&rpci->in_upcall, &free_list); + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; rpci->ops = NULL; + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, ops->destroy_msg, -EPIPE); + rpci->nwriters = 0; + if (ops->release_pipe) + ops->release_pipe(inode); + cancel_delayed_work(&rpci->queue_timeout); + flush_scheduled_work(); } rpc_inode_setowner(inode, NULL); mutex_unlock(&inode->i_mutex); - cancel_delayed_work(&rpci->queue_timeout); - flush_scheduled_work(); } static struct inode * @@ -177,16 +183,26 @@ rpc_pipe_release(struct inode *inode, struct file *filp) goto out; msg = (struct rpc_pipe_msg *)filp->private_data; if (msg != NULL) { + spin_lock(&inode->i_lock); msg->errno = -EAGAIN; - list_del_init(&msg->list); + list_del(&msg->list); + spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } if (filp->f_mode & FMODE_WRITE) rpci->nwriters --; - if (filp->f_mode & FMODE_READ) + if (filp->f_mode & FMODE_READ) { rpci->nreaders --; - if (!rpci->nreaders) - __rpc_purge_upcall(inode, -EAGAIN); + if (rpci->nreaders == 0) { + LIST_HEAD(free_list); + spin_lock(&inode->i_lock); + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, + rpci->ops->destroy_msg, -EAGAIN); + } + } if (rpci->ops->release_pipe) rpci->ops->release_pipe(inode); out: @@ -209,6 +225,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) } msg = filp->private_data; if (msg == NULL) { + spin_lock(&inode->i_lock); if (!list_empty(&rpci->pipe)) { msg = list_entry(rpci->pipe.next, struct rpc_pipe_msg, @@ -218,6 +235,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) filp->private_data = msg; msg->copied = 0; } + spin_unlock(&inode->i_lock); if (msg == NULL) goto out_unlock; } @@ -225,7 +243,9 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) res = rpci->ops->upcall(filp, msg, buf, len); if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; - list_del_init(&msg->list); + spin_lock(&inode->i_lock); + list_del(&msg->list); + spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } out_unlock: @@ -610,7 +630,7 @@ rpc_lookup_negative(char *path, struct nameidata *nd) return ERR_PTR(error); dir = nd->dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(nd); + dentry = lookup_one_len(nd->last.name, nd->dentry, nd->last.len); if (IS_ERR(dentry)) goto out_err; if (dentry->d_inode) { @@ -672,7 +692,7 @@ rpc_rmdir(char *path) return error; dir = nd.dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(&nd); + dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto out_release; @@ -733,7 +753,7 @@ rpc_unlink(char *path) return error; dir = nd.dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(&nd); + dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto out_release; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 7415406aa1ae..802d4fe0f55c 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -908,10 +908,10 @@ void rpc_release_task(struct rpc_task *task) /** * rpc_run_task - Allocate a new RPC task, then run rpc_execute against it - * @clnt - pointer to RPC client - * @flags - RPC flags - * @ops - RPC call ops - * @data - user call data + * @clnt: pointer to RPC client + * @flags: RPC flags + * @ops: RPC call ops + * @data: user call data */ struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags, const struct rpc_call_ops *ops, @@ -930,6 +930,7 @@ EXPORT_SYMBOL(rpc_run_task); /** * rpc_find_parent - find the parent of a child task. * @child: child task + * @parent: parent task * * Checks that the parent task is still sleeping on the * queue 'childq'. If so returns a pointer to the parent. |