diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-11-10 09:16:27 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-11-10 09:16:27 +0100 |
commit | 4ecd33d930591d41fe356160593a9076467b961c (patch) | |
tree | b9051a334540bbce38db1b2b03cebb4cf1d51f73 /net | |
parent | 7d5a78cd98c3a5eb83bd6a061c5ea6ef1e9b8fcb (diff) | |
parent | f7160c7573615ec82c691e294cf80d920b5d588d (diff) |
Merge commit 'v2.6.28-rc4' into x86/apic
Diffstat (limited to 'net')
34 files changed, 371 insertions, 135 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 916061f681b..68ced4bf158 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -3,11 +3,20 @@ #include <linux/if_vlan.h> #include "vlan.h" +struct vlan_hwaccel_cb { + struct net_device *dev; +}; + +static inline struct vlan_hwaccel_cb *vlan_hwaccel_cb(struct sk_buff *skb) +{ + return (struct vlan_hwaccel_cb *)skb->cb; +} + /* VLAN rx hw acceleration helper. This acts like netif_{rx,receive_skb}(). */ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, u16 vlan_tci, int polling) { - struct net_device_stats *stats; + struct vlan_hwaccel_cb *cb = vlan_hwaccel_cb(skb); if (skb_bond_should_drop(skb)) { dev_kfree_skb_any(skb); @@ -15,23 +24,35 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, } skb->vlan_tci = vlan_tci; + cb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); + + return (polling ? netif_receive_skb(skb) : netif_rx(skb)); +} +EXPORT_SYMBOL(__vlan_hwaccel_rx); + +int vlan_hwaccel_do_receive(struct sk_buff *skb) +{ + struct vlan_hwaccel_cb *cb = vlan_hwaccel_cb(skb); + struct net_device *dev = cb->dev; + struct net_device_stats *stats; + netif_nit_deliver(skb); - skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); - if (skb->dev == NULL) { - dev_kfree_skb_any(skb); - /* Not NET_RX_DROP, this is not being dropped - * due to congestion. */ - return NET_RX_SUCCESS; + if (dev == NULL) { + kfree_skb(skb); + return -1; } - skb->dev->last_rx = jiffies; + + skb->dev = dev; + skb->priority = vlan_get_ingress_priority(dev, skb->vlan_tci); skb->vlan_tci = 0; - stats = &skb->dev->stats; + dev->last_rx = jiffies; + + stats = &dev->stats; stats->rx_packets++; stats->rx_bytes += skb->len; - skb->priority = vlan_get_ingress_priority(skb->dev, vlan_tci); switch (skb->pkt_type) { case PACKET_BROADCAST: break; @@ -43,13 +64,12 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ if (!compare_ether_addr(eth_hdr(skb)->h_dest, - skb->dev->dev_addr)) + dev->dev_addr)) skb->pkt_type = PACKET_HOST; break; }; - return (polling ? netif_receive_skb(skb) : netif_rx(skb)); + return 0; } -EXPORT_SYMBOL(__vlan_hwaccel_rx); struct net_device *vlan_dev_real_dev(const struct net_device *dev) { diff --git a/net/9p/client.c b/net/9p/client.c index 67717f69412..4b529454616 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -189,6 +189,9 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) printk(KERN_ERR "Couldn't grow tag array\n"); kfree(req->tc); kfree(req->rc); + kfree(req->wq); + req->tc = req->rc = NULL; + req->wq = NULL; return ERR_PTR(-ENOMEM); } req->tc->sdata = (char *) req->tc + sizeof(struct p9_fcall); @@ -311,12 +314,6 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r) r->status = REQ_STATUS_IDLE; if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool)) p9_idpool_put(tag, c->tagpool); - - /* if this was a flush request we have to free response fcall */ - if (r->rc->id == P9_RFLUSH) { - kfree(r->tc); - kfree(r->rc); - } } /** @@ -611,19 +608,21 @@ reterr: static struct p9_fid *p9_fid_create(struct p9_client *clnt) { - int err; + int ret; struct p9_fid *fid; + unsigned long flags; P9_DPRINTK(P9_DEBUG_FID, "clnt %p\n", clnt); fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL); if (!fid) return ERR_PTR(-ENOMEM); - fid->fid = p9_idpool_get(clnt->fidpool); + ret = p9_idpool_get(clnt->fidpool); if (fid->fid < 0) { - err = -ENOSPC; + ret = -ENOSPC; goto error; } + fid->fid = ret; memset(&fid->qid, 0, sizeof(struct p9_qid)); fid->mode = -1; @@ -632,27 +631,28 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) fid->clnt = clnt; fid->aux = NULL; - spin_lock(&clnt->lock); + spin_lock_irqsave(&clnt->lock, flags); list_add(&fid->flist, &clnt->fidlist); - spin_unlock(&clnt->lock); + spin_unlock_irqrestore(&clnt->lock, flags); return fid; error: kfree(fid); - return ERR_PTR(err); + return ERR_PTR(ret); } static void p9_fid_destroy(struct p9_fid *fid) { struct p9_client *clnt; + unsigned long flags; P9_DPRINTK(P9_DEBUG_FID, "fid %d\n", fid->fid); clnt = fid->clnt; p9_idpool_put(fid->fid, clnt->fidpool); - spin_lock(&clnt->lock); + spin_lock_irqsave(&clnt->lock, flags); list_del(&fid->flist); - spin_unlock(&clnt->lock); + spin_unlock_irqrestore(&clnt->lock, flags); kfree(fid); } @@ -818,7 +818,9 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, } P9_DPRINTK(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n", - qid.type, qid.path, qid.version); + qid.type, + (unsigned long long)qid.path, + qid.version); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); @@ -865,7 +867,9 @@ p9_client_auth(struct p9_client *clnt, char *uname, u32 n_uname, char *aname) } P9_DPRINTK(P9_DEBUG_9P, "<<< RAUTH qid %x.%llx.%x\n", - qid.type, qid.path, qid.version); + qid.type, + (unsigned long long)qid.path, + qid.version); memmove(&afid->qid, &qid, sizeof(struct p9_qid)); p9_free_req(clnt, req); @@ -930,7 +934,8 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, for (count = 0; count < nwqids; count++) P9_DPRINTK(P9_DEBUG_9P, "<<< [%d] %x.%llx.%x\n", - count, wqids[count].type, wqids[count].path, + count, wqids[count].type, + (unsigned long long)wqids[count].path, wqids[count].version); if (nwname) @@ -980,7 +985,9 @@ int p9_client_open(struct p9_fid *fid, int mode) } P9_DPRINTK(P9_DEBUG_9P, "<<< ROPEN qid %x.%llx.%x iounit %x\n", - qid.type, qid.path, qid.version, iounit); + qid.type, + (unsigned long long)qid.path, + qid.version, iounit); fid->mode = mode; fid->iounit = iounit; @@ -1023,7 +1030,9 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode, } P9_DPRINTK(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n", - qid.type, qid.path, qid.version, iounit); + qid.type, + (unsigned long long)qid.path, + qid.version, iounit); fid->mode = mode; fid->iounit = iounit; @@ -1230,9 +1239,9 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) "<<< name=%s uid=%s gid=%s muid=%s extension=(%s)\n" "<<< uid=%d gid=%d n_muid=%d\n", ret->size, ret->type, ret->dev, ret->qid.type, - ret->qid.path, ret->qid.version, ret->mode, - ret->atime, ret->mtime, ret->length, ret->name, - ret->uid, ret->gid, ret->muid, ret->extension, + (unsigned long long)ret->qid.path, ret->qid.version, ret->mode, + ret->atime, ret->mtime, (unsigned long long)ret->length, + ret->name, ret->uid, ret->gid, ret->muid, ret->extension, ret->n_uid, ret->n_gid, ret->n_muid); free_and_error: @@ -1255,9 +1264,9 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) " name=%s uid=%s gid=%s muid=%s extension=(%s)\n" " uid=%d gid=%d n_muid=%d\n", wst->size, wst->type, wst->dev, wst->qid.type, - wst->qid.path, wst->qid.version, wst->mode, - wst->atime, wst->mtime, wst->length, wst->name, - wst->uid, wst->gid, wst->muid, wst->extension, + (unsigned long long)wst->qid.path, wst->qid.version, wst->mode, + wst->atime, wst->mtime, (unsigned long long)wst->length, + wst->name, wst->uid, wst->gid, wst->muid, wst->extension, wst->n_uid, wst->n_gid, wst->n_muid); err = 0; clnt = fid->clnt; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 8d6cc4777aa..2f1fe5fc122 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -45,7 +45,6 @@ #include <net/9p/transport.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> -#include <rdma/ib_verbs.h> #define P9_PORT 5640 #define P9_RDMA_SQ_DEPTH 32 @@ -589,6 +588,9 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (IS_ERR(rdma->cm_id)) goto error; + /* Associate the client with the transport */ + client->trans = rdma; + /* Resolve the server's address */ rdma->addr.sin_family = AF_INET; rdma->addr.sin_addr.s_addr = in_aton(addr); @@ -669,7 +671,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (err || (rdma->state != P9_RDMA_CONNECTED)) goto error; - client->trans = rdma; client->status = Connected; return 0; diff --git a/net/core/dev.c b/net/core/dev.c index d9038e328cc..9174c77d311 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2218,6 +2218,9 @@ int netif_receive_skb(struct sk_buff *skb) int ret = NET_RX_DROP; __be16 type; + if (skb->vlan_tci && vlan_hwaccel_do_receive(skb)) + return NET_RX_SUCCESS; + /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) return NET_RX_DROP; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f1d07b5c1e1..1895a4ca9c4 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -325,6 +325,38 @@ void unregister_pernet_subsys(struct pernet_operations *module) } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); +int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) +{ + int rv; + + mutex_lock(&net_mutex); +again: + rv = ida_get_new_above(&net_generic_ids, 1, id); + if (rv < 0) { + if (rv == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + goto out; + } + rv = register_pernet_operations(first_device, ops); + if (rv < 0) + ida_remove(&net_generic_ids, *id); + mutex_unlock(&net_mutex); +out: + return rv; +} +EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); + +void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) +{ + mutex_lock(&net_mutex); + unregister_pernet_operations(ops); + ida_remove(&net_generic_ids, id); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys); + /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 99f656d35b4..a47f5bad110 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1973,28 +1973,27 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) /* make sure that we don't pick a non-existing transmit queue */ ntxq = pkt_dev->odev->real_num_tx_queues; - if (ntxq <= num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) { + if (ntxq > num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) { printk(KERN_WARNING "pktgen: WARNING: QUEUE_MAP_CPU " - "disabled because CPU count (%d) exceeds number ", - num_online_cpus()); - printk(KERN_WARNING "pktgen: WARNING: of tx queues " - "(%d) on %s \n", ntxq, pkt_dev->odev->name); + "disabled because CPU count (%d) exceeds number " + "of tx queues (%d) on %s\n", num_online_cpus(), ntxq, + pkt_dev->odev->name); pkt_dev->flags &= ~F_QUEUE_MAP_CPU; } if (ntxq <= pkt_dev->queue_map_min) { printk(KERN_WARNING "pktgen: WARNING: Requested " - "queue_map_min (%d) exceeds number of tx\n", - pkt_dev->queue_map_min); - printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " - "%s, resetting\n", ntxq, pkt_dev->odev->name); + "queue_map_min (zero-based) (%d) exceeds valid range " + "[0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_min, (ntxq ?: 1)- 1, ntxq, + pkt_dev->odev->name); pkt_dev->queue_map_min = ntxq - 1; } - if (ntxq <= pkt_dev->queue_map_max) { + if (pkt_dev->queue_map_max >= ntxq) { printk(KERN_WARNING "pktgen: WARNING: Requested " - "queue_map_max (%d) exceeds number of tx\n", - pkt_dev->queue_map_max); - printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " - "%s, resetting\n", ntxq, pkt_dev->odev->name); + "queue_map_max (zero-based) (%d) exceeds valid range " + "[0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_max, (ntxq ?: 1)- 1, ntxq, + pkt_dev->odev->name); pkt_dev->queue_map_max = ntxq - 1; } diff --git a/net/core/scm.c b/net/core/scm.c index 10f5c65f6a4..ab242cc1acc 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -75,6 +75,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (!fpl) return -ENOMEM; *fplp = fpl; + INIT_LIST_HEAD(&fpl->list); fpl->count = 0; } fpp = &fpl->fp[fpl->count]; @@ -106,9 +107,25 @@ void __scm_destroy(struct scm_cookie *scm) if (fpl) { scm->fp = NULL; - for (i=fpl->count-1; i>=0; i--) - fput(fpl->fp[i]); - kfree(fpl); + if (current->scm_work_list) { + list_add_tail(&fpl->list, current->scm_work_list); + } else { + LIST_HEAD(work_list); + + current->scm_work_list = &work_list; + + list_add(&fpl->list, &work_list); + while (!list_empty(&work_list)) { + fpl = list_first_entry(&work_list, struct scm_fp_list, list); + + list_del(&fpl->list); + for (i=fpl->count-1; i>=0; i--) + fput(fpl->fp[i]); + kfree(fpl); + } + + current->scm_work_list = NULL; + } } } @@ -284,6 +301,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) new_fpl = kmalloc(sizeof(*fpl), GFP_KERNEL); if (new_fpl) { + INIT_LIST_HEAD(&new_fpl->list); for (i=fpl->count-1; i>=0; i--) get_file(fpl->fp[i]); memcpy(new_fpl, fpl, sizeof(*fpl)); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4e22e3a3535..ebb6b94f8af 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -449,6 +449,18 @@ void kfree_skb(struct sk_buff *skb) __kfree_skb(skb); } +/** + * skb_recycle_check - check if skb can be reused for receive + * @skb: buffer + * @skb_size: minimum receive buffer size + * + * Checks that the skb passed in is not shared or cloned, and + * that it is linear and its head portion at least as large as + * skb_size so that it can be recycled as a receive buffer. + * If these conditions are met, this function does any necessary + * reference count dropping and cleans up the skbuff as if it + * just came from __alloc_skb(). + */ int skb_recycle_check(struct sk_buff *skb, int skb_size) { struct skb_shared_info *shinfo; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 490e035c6d9..2e78f6bd977 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -2063,9 +2063,10 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb, u32 opt_len; int len_delta; - buf_len = cipso_v4_genopt(buf, buf_len, doi_def, secattr); - if (buf_len < 0) - return buf_len; + ret_val = cipso_v4_genopt(buf, buf_len, doi_def, secattr); + if (ret_val < 0) + return ret_val; + buf_len = ret_val; opt_len = (buf_len + 3) & ~3; /* we overwrite any existing options to ensure that we have enough diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eccb7165a80..c5aca0bb116 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1374,8 +1374,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || - signal_pending(current) || - (flags & MSG_PEEK)) + signal_pending(current)) break; } else { if (sock_flag(sk, SOCK_DONE)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e4c5ac9fe89..ba85d883189 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2279,6 +2279,11 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } memset(&opts, 0, sizeof(opts)); +#ifdef CONFIG_SYN_COOKIES + if (unlikely(req->cookie_ts)) + TCP_SKB_CB(skb)->when = cookie_init_timestamp(req); + else +#endif TCP_SKB_CB(skb)->when = tcp_time_stamp; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5) + @@ -2304,11 +2309,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); -#ifdef CONFIG_SYN_COOKIES - if (unlikely(req->cookie_ts)) - TCP_SKB_CB(skb)->when = cookie_init_timestamp(req); - else -#endif tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2095abc3cab..cf02701ced4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -284,7 +284,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, } EXPORT_SYMBOL_GPL(udp4_lib_lookup); -static inline struct sock *udp_v4_mcast_next(struct sock *sk, +static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif) @@ -296,7 +296,8 @@ static inline struct sock *udp_v4_mcast_next(struct sock *sk, sk_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (s->sk_hash != hnum || + if (!net_eq(sock_net(s), net) || + s->sk_hash != hnum || (inet->daddr && inet->daddr != rmt_addr) || (inet->dport != rmt_port && inet->dport) || (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || @@ -1079,15 +1080,16 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, read_lock(&udp_hash_lock); sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]); dif = skb->dev->ifindex; - sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (sk) { struct sock *sknext = NULL; do { struct sk_buff *skb1 = skb; - sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr, - uh->source, saddr, dif); + sknext = udp_v4_mcast_next(net, sk_next(sk), uh->dest, + daddr, uh->source, saddr, + dif); if (sknext) skb1 = skb_clone(skb, GFP_ATOMIC); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 07735ed280d..55dc6beab9a 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -33,6 +33,7 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); x->sel.sport_mask = htons(0xffff); + x->sel.family = AF_INET; x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->sel.proto = fl->proto; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index eea9542728c..d9da5eb9dcb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2483,8 +2483,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); - if (idev) + if (idev) { idev->if_flags |= IF_READY; + run_pending = 1; + } } else { if (!addrconf_qdisc_ok(dev)) { /* device is still not ready. */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e51da8c092f..8b48512ebf6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -138,6 +138,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int peeked; int err; int is_udplite = IS_UDPLITE(sk); + int is_udp4; if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -158,6 +159,8 @@ try_again: else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; + is_udp4 = (skb->protocol == htons(ETH_P_IP)); + /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial @@ -180,9 +183,14 @@ try_again: if (err) goto out_free; - if (!peeked) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); + if (!peeked) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + } sock_recv_timestamp(msg, sk, skb); @@ -196,7 +204,7 @@ try_again: sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; - if (skb->protocol == htons(ETH_P_IP)) + if (is_udp4) ipv6_addr_set(&sin6->sin6_addr, 0, 0, htonl(0xffff), ip_hdr(skb)->saddr); else { @@ -207,7 +215,7 @@ try_again: } } - if (skb->protocol == htons(ETH_P_IP)) { + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { @@ -228,8 +236,14 @@ out: csum_copy_err: lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + if (!skb_kill_datagram(sk, skb, flags)) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + } release_sock(sk); if (flags & MSG_DONTWAIT) @@ -328,7 +342,7 @@ drop: return -1; } -static struct sock *udp_v6_mcast_next(struct sock *sk, +static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, __be16 loc_port, struct in6_addr *loc_addr, __be16 rmt_port, struct in6_addr *rmt_addr, int dif) @@ -340,7 +354,7 @@ static struct sock *udp_v6_mcast_next(struct sock *sk, sk_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (sock_net(s) != sock_net(sk)) + if (!net_eq(sock_net(s), net)) continue; if (s->sk_hash == num && s->sk_family == PF_INET6) { @@ -383,14 +397,14 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, read_lock(&udp_hash_lock); sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]); dif = inet6_iif(skb); - sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { kfree_skb(skb); goto out; } sk2 = sk; - while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, + while ((sk2 = udp_v6_mcast_next(net, sk_next(sk2), uh->dest, daddr, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 89884a4f23a..60c78cfc273 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -34,6 +34,7 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); x->sel.sport_mask = htons(0xffff); + x->sel.family = AF_INET6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->sel.proto = fl->proto; diff --git a/net/key/af_key.c b/net/key/af_key.c index e55e0441e4d..3440a4637f0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2075,7 +2075,6 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, in req_size += socklen * 2; } else { size -= 2*socklen; - socklen = 0; } rq = (void*)skb_put(skb, req_size); pol->sadb_x_policy_len += req_size/8; diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c index 0b024cd6b80..98f48070805 100644 --- a/net/mac80211/rc80211_minstrel_debugfs.c +++ b/net/mac80211/rc80211_minstrel_debugfs.c @@ -94,8 +94,8 @@ minstrel_stats_open(struct inode *inode, struct file *file) prob / 10, prob % 10, mr->last_success, mr->last_attempts, - mr->succ_hist, - mr->att_hist); + (unsigned long long)mr->succ_hist, + (unsigned long long)mr->att_hist); } p += sprintf(p, "\nTotal packet count:: ideal %d " "lookaround %d\n\n", @@ -106,7 +106,7 @@ minstrel_stats_open(struct inode *inode, struct file *file) return 0; } -static int +static ssize_t minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *o) { struct minstrel_stats_info *ms; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 9c06b9f86ad..c39b6a99413 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -21,6 +21,7 @@ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rculist.h> +#include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> @@ -167,10 +168,12 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) */ synchronize_rcu(); + rtnl_lock(); spin_lock_bh(&nf_conntrack_lock); for_each_net(net) __nf_conntrack_helper_unregister(me, net); spin_unlock_bh(&nf_conntrack_lock); + rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index a59a307e685..592d73344d4 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -22,6 +22,7 @@ #include <linux/notifier.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> @@ -221,8 +222,10 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) synchronize_rcu(); /* Remove all contrack entries for this protocol */ + rtnl_lock(); for_each_net(net) nf_ct_iterate_cleanup(net, kill_l3proto, proto); + rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); @@ -333,8 +336,10 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) synchronize_rcu(); /* Remove all contrack entries for this protocol */ + rtnl_lock(); for_each_net(net) nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); + rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index a2cdbcbf64c..4ab62ad85dd 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -335,7 +335,7 @@ static int __init nf_ct_proto_gre_init(void) rv = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_gre4); if (rv < 0) return rv; - rv = register_pernet_gen_device(&proto_gre_net_id, &proto_gre_net_ops); + rv = register_pernet_gen_subsys(&proto_gre_net_id, &proto_gre_net_ops); if (rv < 0) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); return rv; @@ -344,7 +344,7 @@ static int __init nf_ct_proto_gre_init(void) static void nf_ct_proto_gre_fini(void) { nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); - unregister_pernet_gen_device(proto_gre_net_id, &proto_gre_net_ops); + unregister_pernet_gen_subsys(proto_gre_net_id, &proto_gre_net_ops); } module_init(nf_ct_proto_gre_init); diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c index b0925a30335..249f6b92f15 100644 --- a/net/netlabel/netlabel_addrlist.c +++ b/net/netlabel/netlabel_addrlist.c @@ -315,6 +315,7 @@ struct netlbl_af6list *netlbl_af6list_remove(const struct in6_addr *addr, * Audit Helper Functions */ +#ifdef CONFIG_AUDIT /** * netlbl_af4list_audit_addr - Audit an IPv4 address * @audit_buf: audit buffer @@ -386,3 +387,4 @@ void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf, } } #endif /* IPv6 */ +#endif /* CONFIG_AUDIT */ diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index 0242bead405..07ae7fd82be 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -120,9 +120,19 @@ struct netlbl_af4list *netlbl_af4list_search(__be32 addr, struct netlbl_af4list *netlbl_af4list_search_exact(__be32 addr, __be32 mask, struct list_head *head); + +#ifdef CONFIG_AUDIT void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf, int src, const char *dev, __be32 addr, __be32 mask); +#else +static inline void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf, + int src, const char *dev, + __be32 addr, __be32 mask) +{ + return; +} +#endif #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -179,11 +189,23 @@ struct netlbl_af6list *netlbl_af6list_search(const struct in6_addr *addr, struct netlbl_af6list *netlbl_af6list_search_exact(const struct in6_addr *addr, const struct in6_addr *mask, struct list_head *head); + +#ifdef CONFIG_AUDIT void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf, int src, const char *dev, const struct in6_addr *addr, const struct in6_addr *mask); +#else +static inline void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf, + int src, + const char *dev, + const struct in6_addr *addr, + const struct in6_addr *mask) +{ + return; +} +#endif #endif /* IPV6 */ #endif diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index ee769ecaa13..0a0ef17b2a4 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -265,7 +265,7 @@ add_failure: static int netlbl_mgmt_listentry(struct sk_buff *skb, struct netlbl_dom_map *entry) { - int ret_val; + int ret_val = 0; struct nlattr *nla_a; struct nlattr *nla_b; struct netlbl_af4list *iter4; diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index b9d97effebe..defeb7a0d50 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -261,6 +261,8 @@ static inline int can_respond(struct sk_buff *skb) return 0; /* we are not the destination */ if (ph->pn_res == PN_PREFIX && !pskb_may_pull(skb, 5)) return 0; + if (ph->pn_res == PN_COMMGR) /* indications */ + return 0; ph = pn_hdr(skb); /* re-acquires the pointer */ pm = pn_msg(skb); @@ -309,7 +311,8 @@ static int send_reset_indications(struct sk_buff *rskb) return pn_raw_send(data, sizeof(data), rskb->dev, pn_object(oph->pn_sdev, 0x00), - pn_object(oph->pn_rdev, oph->pn_robj), 0x10); + pn_object(oph->pn_rdev, oph->pn_robj), + PN_COMMGR); } diff --git a/net/rfkill/rfkill-input.c b/net/rfkill/rfkill-input.c index 21124ec0a73..bfdade72e06 100644 --- a/net/rfkill/rfkill-input.c +++ b/net/rfkill/rfkill-input.c @@ -256,6 +256,11 @@ static struct input_handler rfkill_handler = { static int __init rfkill_handler_init(void) { + unsigned long last_run = jiffies - msecs_to_jiffies(500); + rfkill_wlan.last = last_run; + rfkill_bt.last = last_run; + rfkill_uwb.last = last_run; + rfkill_wimax.last = last_run; return input_register_handler(&rfkill_handler); } diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c index f949a482b00..25ba3bd57e6 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -603,7 +603,7 @@ static int rfkill_check_duplicity(const struct rfkill *rfkill) } /* 0: first switch of its kind */ - return test_bit(rfkill->type, seen); + return (test_bit(rfkill->type, seen)) ? 1 : 0; } static int rfkill_add_switch(struct rfkill *rfkill) diff --git a/net/socket.c b/net/socket.c index 2b7a4b5c9b7..57550c3bcab 100644 --- a/net/socket.c +++ b/net/socket.c @@ -990,7 +990,6 @@ static int sock_close(struct inode *inode, struct file *filp) printk(KERN_DEBUG "sock_close: NULL inode\n"); return 0; } - sock_fasync(-1, filp, 0); sock_release(SOCKET_I(inode)); return 0; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 436bf1b4b76..cb216b2df66 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -228,19 +228,21 @@ static int rpcauth_prune_expired(struct list_head *free, int nr_to_scan) { spinlock_t *cache_lock; - struct rpc_cred *cred; + struct rpc_cred *cred, *next; unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM; - while (!list_empty(&cred_unused)) { - cred = list_entry(cred_unused.next, struct rpc_cred, cr_lru); + list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { + + /* Enforce a 60 second garbage collection moratorium */ + if (time_in_range(cred->cr_expire, expired, jiffies) && + test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) + continue; + list_del_init(&cred->cr_lru); number_cred_unused--; if (atomic_read(&cred->cr_count) != 0) continue; - /* Enforce a 5 second garbage collection moratorium */ - if (time_in_range(cred->cr_expire, expired, jiffies) && - test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) - continue; + cache_lock = &cred->cr_auth->au_credcache->lock; spin_lock(cache_lock); if (atomic_read(&cred->cr_count) == 0) { @@ -453,7 +455,7 @@ need_lock: } if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0) rpcauth_unhash_cred(cred); - else if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) { + if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) { cred->cr_expire = jiffies; list_add_tail(&cred->cr_lru, &cred_unused); number_cred_unused++; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9a288d5eea6..0a50361e3d8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -249,6 +249,7 @@ struct sock_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); + void (*old_error_report)(struct sock *); }; /* @@ -698,8 +699,9 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: xs_nospace(task); break; - case -ECONNREFUSED: case -ECONNRESET: + xs_tcp_shutdown(xprt); + case -ECONNREFUSED: case -ENOTCONN: case -EPIPE: status = -ENOTCONN; @@ -742,6 +744,22 @@ out_release: xprt_release_xprt(xprt, task); } +static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk) +{ + transport->old_data_ready = sk->sk_data_ready; + transport->old_state_change = sk->sk_state_change; + transport->old_write_space = sk->sk_write_space; + transport->old_error_report = sk->sk_error_report; +} + +static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk) +{ + sk->sk_data_ready = transport->old_data_ready; + sk->sk_state_change = transport->old_state_change; + sk->sk_write_space = transport->old_write_space; + sk->sk_error_report = transport->old_error_report; +} + /** * xs_close - close a socket * @xprt: transport @@ -765,9 +783,8 @@ static void xs_close(struct rpc_xprt *xprt) transport->sock = NULL; sk->sk_user_data = NULL; - sk->sk_data_ready = transport->old_data_ready; - sk->sk_state_change = transport->old_state_change; - sk->sk_write_space = transport->old_write_space; + + xs_restore_old_callbacks(transport, sk); write_unlock_bh(&sk->sk_callback_lock); sk->sk_no_check = 0; @@ -1180,6 +1197,28 @@ static void xs_tcp_state_change(struct sock *sk) } /** + * xs_tcp_error_report - callback mainly for catching RST events + * @sk: socket + */ +static void xs_tcp_error_report(struct sock *sk) +{ + struct rpc_xprt *xprt; + + read_lock(&sk->sk_callback_lock); + if (sk->sk_err != ECONNRESET || sk->sk_state != TCP_ESTABLISHED) + goto out; + if (!(xprt = xprt_from_sock(sk))) + goto out; + dprintk("RPC: %s client %p...\n" + "RPC: error %d\n", + __func__, xprt, sk->sk_err); + + xprt_force_disconnect(xprt); +out: + read_unlock(&sk->sk_callback_lock); +} + +/** * xs_udp_write_space - callback invoked when socket buffer space * becomes available * @sk: socket whose state has changed @@ -1454,10 +1493,9 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_lock_bh(&sk->sk_callback_lock); + xs_save_old_callbacks(transport, sk); + sk->sk_user_data = xprt; - transport->old_data_ready = sk->sk_data_ready; - transport->old_state_change = sk->sk_state_change; - transport->old_write_space = sk->sk_write_space; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; sk->sk_no_check = UDP_CSUM_NORCV; @@ -1589,13 +1627,13 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_lock_bh(&sk->sk_callback_lock); + xs_save_old_callbacks(transport, sk); + sk->sk_user_data = xprt; - transport->old_data_ready = sk->sk_data_ready; - transport->old_state_change = sk->sk_state_change; - transport->old_write_space = sk->sk_write_space; sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; + sk->sk_error_report = xs_tcp_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dc504d308ec..eb90f77bb0e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1302,14 +1302,23 @@ static void unix_destruct_fds(struct sk_buff *skb) sock_wfree(skb); } -static void unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; + + /* + * Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + for (i=scm->fp->count-1; i>=0; i--) unix_inflight(scm->fp->fp[i]); - UNIXCB(skb).fp = scm->fp; skb->destructor = unix_destruct_fds; - scm->fp = NULL; + return 0; } /* @@ -1368,8 +1377,11 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); - if (siocb->scm->fp) - unix_attach_fds(siocb->scm, skb); + if (siocb->scm->fp) { + err = unix_attach_fds(siocb->scm, skb); + if (err) + goto out_free; + } unix_get_secdata(siocb->scm, skb); skb_reset_transport_header(skb); @@ -1538,8 +1550,13 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, size = min_t(int, size, skb_tailroom(skb)); memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); - if (siocb->scm->fp) - unix_attach_fds(siocb->scm, skb); + if (siocb->scm->fp) { + err = unix_attach_fds(siocb->scm, skb); + if (err) { + kfree_skb(skb); + goto out_err; + } + } if ((err = memcpy_fromiovec(skb_put(skb,size), msg->msg_iov, size)) != 0) { kfree_skb(skb); @@ -2213,7 +2230,7 @@ static int unix_net_init(struct net *net) #endif error = 0; out: - return 0; + return error; } static void unix_net_exit(struct net *net) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2a27b84f740..6d4a9a8de5e 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -186,8 +186,17 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), */ struct sock *sk = unix_get_socket(*fp++); if (sk) { - hit = true; - func(unix_sk(sk)); + struct unix_sock *u = unix_sk(sk); + + /* + * Ignore non-candidates, they could + * have been added to the queues after + * starting the garbage collection + */ + if (u->gc_candidate) { + hit = true; + func(u); + } } } if (hit && hitlist != NULL) { @@ -249,11 +258,11 @@ static void inc_inflight_move_tail(struct unix_sock *u) { atomic_long_inc(&u->inflight); /* - * If this is still a candidate, move it to the end of the - * list, so that it's checked even if it was already passed - * over + * If this still might be part of a cycle, move it to the end + * of the list, so that it's checked even if it was already + * passed over */ - if (u->gc_candidate) + if (u->gc_maybe_cycle) list_move_tail(&u->link, &gc_candidates); } @@ -267,6 +276,7 @@ void unix_gc(void) struct unix_sock *next; struct sk_buff_head hitlist; struct list_head cursor; + LIST_HEAD(not_cycle_list); spin_lock(&unix_gc_lock); @@ -282,10 +292,14 @@ void unix_gc(void) * * Holding unix_gc_lock will protect these candidates from * being detached, and hence from gaining an external - * reference. This also means, that since there are no - * possible receivers, the receive queues of these sockets are - * static during the GC, even though the dequeue is done - * before the detach without atomicity guarantees. + * reference. Since there are no possible receivers, all + * buffers currently on the candidates' queues stay there + * during the garbage collection. + * + * We also know that no new candidate can be added onto the + * receive queues. Other, non candidate sockets _can_ be + * added to queue, so we must make sure only to touch + * candidates. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { long total_refs; @@ -299,6 +313,7 @@ void unix_gc(void) if (total_refs == inflight_refs) { list_move_tail(&u->link, &gc_candidates); u->gc_candidate = 1; + u->gc_maybe_cycle = 1; } } @@ -325,14 +340,24 @@ void unix_gc(void) list_move(&cursor, &u->link); if (atomic_long_read(&u->inflight) > 0) { - list_move_tail(&u->link, &gc_inflight_list); - u->gc_candidate = 0; + list_move_tail(&u->link, ¬_cycle_list); + u->gc_maybe_cycle = 0; scan_children(&u->sk, inc_inflight_move_tail, NULL); } } list_del(&cursor); /* + * not_cycle_list contains those sockets which do not make up a + * cycle. Restore these to the inflight list. + */ + while (!list_empty(¬_cycle_list)) { + u = list_entry(not_cycle_list.next, struct unix_sock, link); + u->gc_candidate = 0; + list_move_tail(&u->link, &gc_inflight_list); + } + + /* * Now gc_candidates contains only garbage. Restore original * inflight counters for these as well, and remove the skbuffs * which are creating the cycle(s). diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 832b47c1de8..058f04f54b9 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -315,9 +315,9 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) return; } - spin_lock(&xfrm_policy_gc_lock); + spin_lock_bh(&xfrm_policy_gc_lock); hlist_add_head(&policy->bydst, &xfrm_policy_gc_list); - spin_unlock(&xfrm_policy_gc_lock); + spin_unlock_bh(&xfrm_policy_gc_lock); schedule_work(&xfrm_policy_gc_work); } @@ -1251,6 +1251,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, -EINVAL : -EAGAIN); xfrm_state_put(x); } + else if (error == -ESRCH) + error = -EAGAIN; if (!tmpl->optional) goto fail; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4a8a1abb59e..a278a6f3b99 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1816,7 +1816,7 @@ static int copy_to_user_kmaddress(struct xfrm_kmaddress *k, struct sk_buff *skb) uk.family = k->family; uk.reserved = k->reserved; memcpy(&uk.local, &k->local, sizeof(uk.local)); - memcpy(&uk.remote, &k->local, sizeof(uk.remote)); + memcpy(&uk.remote, &k->remote, sizeof(uk.remote)); return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk); } |