diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/8021q/vlan_core.c | 46 | ||||
-rw-r--r-- | net/9p/client.c | 59 | ||||
-rw-r--r-- | net/9p/trans_rdma.c | 5 | ||||
-rw-r--r-- | net/core/dev.c | 3 | ||||
-rw-r--r-- | net/core/scm.c | 24 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
-rw-r--r-- | net/ipv4/xfrm4_state.c | 1 | ||||
-rw-r--r-- | net/ipv6/addrconf.c | 4 | ||||
-rw-r--r-- | net/ipv6/udp.c | 28 | ||||
-rw-r--r-- | net/ipv6/xfrm6_state.c | 1 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_helper.c | 3 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto.c | 5 | ||||
-rw-r--r-- | net/rfkill/rfkill.c | 2 | ||||
-rw-r--r-- | net/unix/af_unix.c | 31 | ||||
-rw-r--r-- | net/unix/garbage.c | 49 | ||||
-rw-r--r-- | net/xfrm/xfrm_policy.c | 4 | ||||
-rw-r--r-- | net/xfrm/xfrm_user.c | 2 |
17 files changed, 194 insertions, 76 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/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/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/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 71e259e866a..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) 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/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/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/unix/af_unix.c b/net/unix/af_unix.c index 4d3c6071b9a..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); 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 25872747762..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); } 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); } |