diff options
Diffstat (limited to 'net')
55 files changed, 590 insertions, 487 deletions
diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 798beac7f100..1e308f210928 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -178,27 +178,24 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, break; case 's':{ char **sptr = va_arg(ap, char **); - int16_t len; - int size; + uint16_t len; errcode = p9pdu_readf(pdu, proto_version, "w", &len); if (errcode) break; - size = max_t(int16_t, len, 0); - - *sptr = kmalloc(size + 1, GFP_KERNEL); + *sptr = kmalloc(len + 1, GFP_KERNEL); if (*sptr == NULL) { errcode = -EFAULT; break; } - if (pdu_read(pdu, *sptr, size)) { + if (pdu_read(pdu, *sptr, len)) { errcode = -EFAULT; kfree(*sptr); *sptr = NULL; } else - (*sptr)[size] = 0; + (*sptr)[len] = 0; } break; case 'Q':{ @@ -234,14 +231,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'D':{ - int32_t *count = va_arg(ap, int32_t *); + uint32_t *count = va_arg(ap, uint32_t *); void **data = va_arg(ap, void **); errcode = p9pdu_readf(pdu, proto_version, "d", count); if (!errcode) { *count = - min_t(int32_t, *count, + min_t(uint32_t, *count, pdu->size - pdu->offset); *data = &pdu->sdata[pdu->offset]; } @@ -404,9 +401,10 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, break; case 's':{ const char *sptr = va_arg(ap, const char *); - int16_t len = 0; + uint16_t len = 0; if (sptr) - len = min_t(int16_t, strlen(sptr), USHRT_MAX); + len = min_t(uint16_t, strlen(sptr), + USHRT_MAX); errcode = p9pdu_writef(pdu, proto_version, "w", len); @@ -438,7 +436,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, stbuf->n_gid, stbuf->n_muid); } break; case 'D':{ - int32_t count = va_arg(ap, int32_t); + uint32_t count = va_arg(ap, uint32_t); const void *data = va_arg(ap, const void *); errcode = p9pdu_writef(pdu, proto_version, "d", diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 1bf0cf503796..8184c031d028 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -740,12 +740,12 @@ static int setsockopt(struct socket *sock, if (cf_sk->sk.sk_protocol != CAIFPROTO_UTIL) return -ENOPROTOOPT; lock_sock(&(cf_sk->sk)); - cf_sk->conn_req.param.size = ol; if (ol > sizeof(cf_sk->conn_req.param.data) || copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) { release_sock(&cf_sk->sk); return -EINVAL; } + cf_sk->conn_req.param.size = ol; release_sock(&cf_sk->sk); return 0; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 84a422c98941..fa9dab372b68 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -76,6 +76,8 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) struct chnl_net *priv = container_of(layr, struct chnl_net, chnl); int pktlen; int err = 0; + const u8 *ip_version; + u8 buf; priv = container_of(layr, struct chnl_net, chnl); @@ -90,7 +92,21 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) * send the packet to the net stack. */ skb->dev = priv->netdev; - skb->protocol = htons(ETH_P_IP); + + /* check the version of IP */ + ip_version = skb_header_pointer(skb, 0, 1, &buf); + if (!ip_version) + return -EINVAL; + switch (*ip_version >> 4) { + case 4: + skb->protocol = htons(ETH_P_IP); + break; + case 6: + skb->protocol = htons(ETH_P_IPV6); + break; + default: + return -EINVAL; + } /* If we change the header in loop mode, the checksum is corrupted. */ if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) diff --git a/net/core/dev.c b/net/core/dev.c index a215269d2e35..a3ef808b5e36 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1732,33 +1732,6 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) -{ - return ((features & NETIF_F_NO_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) -{ - __be16 protocol = skb->protocol; - int features = dev->features; - - if (vlan_tx_tag_present(skb)) { - features &= dev->vlan_features; - } else if (protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - features &= dev->vlan_features; - } - - return can_checksum_protocol(features, protocol); -} - /** * skb_dev_set -- assign a new device to a buffer * @skb: buffer for the new device @@ -1971,16 +1944,14 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) /** * dev_gso_segment - Perform emulated hardware segmentation on skb. * @skb: buffer to segment + * @features: device features as applicable to this skb * * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb) +static int dev_gso_segment(struct sk_buff *skb, int features) { - struct net_device *dev = skb->dev; struct sk_buff *segs; - int features = dev->features & ~(illegal_highdma(dev, skb) ? - NETIF_F_SG : 0); segs = skb_gso_segment(skb, features); @@ -2017,22 +1988,52 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } -int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev) +static bool can_checksum_protocol(unsigned long features, __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} + +static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +{ + if (!can_checksum_protocol(protocol, features)) { + features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_SG; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; +} + +int netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; + int features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; - } else if (!skb->vlan_tci) - return dev->features; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, protocol, features); + } - if (protocol != htons(ETH_P_8021Q)) - return dev->features & dev->vlan_features; - else - return 0; + features &= skb->dev->vlan_features; + + if (protocol != htons(ETH_P_8021Q)) { + return harmonize_features(skb, protocol, features); + } else { + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM; + return harmonize_features(skb, protocol, features); + } } -EXPORT_SYMBOL(netif_get_vlan_features); +EXPORT_SYMBOL(netif_skb_features); /* * Returns true if either: @@ -2042,22 +2043,13 @@ EXPORT_SYMBOL(netif_get_vlan_features); * support DMA from it. */ static inline int skb_needs_linearize(struct sk_buff *skb, - struct net_device *dev) + int features) { - if (skb_is_nonlinear(skb)) { - int features = dev->features; - - if (vlan_tx_tag_present(skb)) - features &= dev->vlan_features; - - return (skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || + return skb_is_nonlinear(skb) && + ((skb_has_frag_list(skb) && + !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && - (!(features & NETIF_F_SG) || - illegal_highdma(dev, skb))); - } - - return 0; + !(features & NETIF_F_SG))); } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -2067,6 +2059,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { + int features; + /* * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache @@ -2079,8 +2073,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_orphan_try(skb); + features = netif_skb_features(skb); + if (vlan_tx_tag_present(skb) && - !(dev->features & NETIF_F_HW_VLAN_TX)) { + !(features & NETIF_F_HW_VLAN_TX)) { skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out; @@ -2088,13 +2084,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb->vlan_tci = 0; } - if (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) goto out_kfree_skb; if (skb->next) goto gso; } else { - if (skb_needs_linearize(skb, dev) && + if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; @@ -2105,7 +2101,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!dev_can_checksum(dev, skb) && + if (!(features & NETIF_F_ALL_CSUM) && skb_checksum_help(skb)) goto out_kfree_skb; } @@ -2301,7 +2297,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, */ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - __qdisc_update_bstats(q, skb->len); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_bstats_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -5621,18 +5620,20 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) } /** - * alloc_netdev_mq - allocate network device + * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @setup: callback to initialize device - * @queue_count: the number of subqueues to allocate + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subquue structs - * for each queue on the device at the end of the netdevice. + * for each queue on the device. */ -struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), unsigned int queue_count) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t alloc_size; @@ -5640,12 +5641,20 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, BUG_ON(strlen(name) >= sizeof(dev->name)); - if (queue_count < 1) { + if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device " "with zero queues.\n"); return NULL; } +#ifdef CONFIG_RPS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero RX queues.\n"); + return NULL; + } +#endif + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5676,14 +5685,14 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - dev->num_tx_queues = queue_count; - dev->real_num_tx_queues = queue_count; + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_pcpu; #ifdef CONFIG_RPS - dev->num_rx_queues = queue_count; - dev->real_num_rx_queues = queue_count; + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_pcpu; #endif @@ -5711,7 +5720,7 @@ free_p: kfree(p); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device diff --git a/net/core/filter.c b/net/core/filter.c index 2b27d4efdd48..afc58374ca96 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL(sk_filter); /** * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on - * @filter: filter to apply + * @fentry: filter to apply * * Decode and apply filter instructions to the skb->data. * Return length to keep, 0 for none. @skb is the data we are diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 750db57f3bb3..a5f7535aab5b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1820,7 +1820,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) return -EPERM; - if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { + if (kind == 2 && (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 45087052d894..5fdb07229017 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -426,7 +426,8 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); - dp->dccps_gsr = seq; + if (after48(seq, dp->dccps_gsr)) + dp->dccps_gsr = seq; /* Sequence validity window depends on remote Sequence Window (7.5.1) */ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); /* diff --git a/net/dccp/input.c b/net/dccp/input.c index 15af247ea007..8cde009e8b85 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -260,7 +260,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) */ if (time_before(now, (dp->dccps_rate_last + sysctl_dccp_sync_ratelimit))) - return 0; + return -1; DCCP_WARN("Step 6 failed for %s packet, " "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and " diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 563943822e58..42348824ee31 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -21,7 +21,8 @@ /* Boundary values */ static int zero = 0, u8_max = 0xFF; -static unsigned long seqw_min = 32; +static unsigned long seqw_min = DCCPF_SEQ_WMIN, + seqw_max = 0xFFFFFFFF; /* maximum on 32 bit */ static struct ctl_table dccp_default_table[] = { { @@ -31,6 +32,7 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &seqw_min, /* RFC 4340, 7.5.2 */ + .extra2 = &seqw_max, }, { .procname = "rx_ccid", diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index f00ef2f1d814..f9d7ac924f15 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -347,10 +347,11 @@ void ether_setup(struct net_device *dev) EXPORT_SYMBOL(ether_setup); /** - * alloc_etherdev_mq - Allocates and sets up an Ethernet device + * alloc_etherdev_mqs - Allocates and sets up an Ethernet device * @sizeof_priv: Size of additional driver-private structure to be allocated * for this Ethernet device - * @queue_count: The number of queues this device has. + * @txqs: The number of TX queues this device has. + * @txqs: The number of RX queues this device has. * * Fill in the fields of the device structure with Ethernet-generic * values. Basically does everything except registering the device. @@ -360,11 +361,12 @@ EXPORT_SYMBOL(ether_setup); * this private data area. */ -struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count) +struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, + unsigned int rxqs) { - return alloc_netdev_mq(sizeof_priv, "eth%d", ether_setup, queue_count); + return alloc_netdev_mqs(sizeof_priv, "eth%d", ether_setup, txqs, rxqs); } -EXPORT_SYMBOL(alloc_etherdev_mq); +EXPORT_SYMBOL(alloc_etherdev_mqs); static size_t _format_mac_addr(char *buf, int buflen, const unsigned char *addr, int len) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 880a5ec6dce0..86961bec70ab 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -314,14 +314,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->ip_summed = CHECKSUM_NONE; - ah = (struct ip_auth_hdr *)skb->data; - iph = ip_hdr(skb); - ihl = ip_hdrlen(skb); if ((err = skb_cow_data(skb, 0, &trailer)) < 0) goto out; nfrags = err; + ah = (struct ip_auth_hdr *)skb->data; + iph = ip_hdr(skb); + ihl = ip_hdrlen(skb); + work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); if (!work_iph) goto out; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a2fc7b961dbc..04c8b69fd426 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1143,6 +1143,23 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) return err; } +int arp_invalidate(struct net_device *dev, __be32 ip) +{ + struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); + int err = -ENXIO; + + if (neigh) { + if (neigh->nud_state & ~NUD_NOARP) + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE| + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); + } + + return err; +} +EXPORT_SYMBOL(arp_invalidate); + static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1163,7 +1180,6 @@ static int arp_req_delete(struct net *net, struct arpreq *r, { int err; __be32 ip; - struct neighbour *neigh; if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); @@ -1181,16 +1197,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, if (!dev) return -EINVAL; } - err = -ENXIO; - neigh = neigh_lookup(&arp_tbl, &ip, dev); - if (neigh) { - if (neigh->nud_state & ~NUD_NOARP) - err = neigh_update(neigh, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(neigh); - } - return err; + return arp_invalidate(dev, ip); } /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 25e318153f14..97e5fb765265 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -73,7 +73,7 @@ int inet_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) { + ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -122,7 +122,8 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && + !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { spin_unlock(&head->lock); snum = smallest_rover; goto have_snum; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 2ada17129fce..2746c1fa6417 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -858,7 +858,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) nlmsg_len(nlh) < hdrlen) return -EINVAL; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { if (nlmsg_attrlen(nlh, hdrlen)) { struct nlattr *attr; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3fac340a28d5..e855fffaed95 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -710,42 +710,25 @@ static void get_counters(const struct xt_table_info *t, struct arpt_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -759,7 +742,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) * about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1007,7 +990,7 @@ static int __do_replace(struct net *net, const char *name, struct arpt_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index a846d633b3b6..652efea013dc 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -884,42 +884,25 @@ get_counters(const struct xt_table_info *t, struct ipt_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU. - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -932,7 +915,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1203,7 +1186,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct ipt_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index ee82d4ef26ce..1aba54ae53c4 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -538,14 +538,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - ip6h = ipv6_hdr(skb); - - skb_push(skb, hdr_len); if ((err = skb_cow_data(skb, 0, &trailer)) < 0) goto out; nfrags = err; + ah = (struct ip_auth_hdr *)skb->data; + ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); if (!work_iph) goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e46305d1815a..d144e629d2b4 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -44,7 +44,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && + ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) && ipv6_rcv_saddr_equal(sk, sk2)) break; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 455582384ece..7d227c644f72 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -897,42 +897,25 @@ get_counters(const struct xt_table_info *t, struct ip6t_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -945,7 +928,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1216,7 +1199,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct ip6t_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 0cdba50c0d69..5cb8d3027b18 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -645,25 +645,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - rcu_read_lock(); + spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: - hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[cb->args[0]], + hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); - if (!atomic_inc_not_zero(&ct->ct_general.use)) - continue; /* Dump entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then dump everything. */ if (l3proto && nf_ct_l3num(ct) != l3proto) - goto releasect; + continue; if (cb->args[1]) { if (ct != last) - goto releasect; + continue; cb->args[1] = 0; } if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, @@ -681,8 +679,6 @@ restart: if (acct) memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX])); } -releasect: - nf_ct_put(ct); } if (cb->args[1]) { cb->args[1] = 0; @@ -690,7 +686,7 @@ releasect: } } out: - rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); if (last) nf_ct_put(last); @@ -928,7 +924,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, u16 zone; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, ctnetlink_done); @@ -1790,7 +1786,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, u16 zone; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { return netlink_dump_start(ctnl, skb, nlh, ctnetlink_exp_dump_table, ctnetlink_exp_done); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 80463507420e..c94237631077 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1325,7 +1325,8 @@ static int __init xt_init(void) for_each_possible_cpu(i) { struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); - spin_lock_init(&lock->lock); + + seqlock_init(&lock->lock); lock->readers = 0; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1781d99145e2..f83cb370292b 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -519,7 +519,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) security_netlink_recv(skb, CAP_NET_ADMIN)) return -EPERM; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { if (ops->dumpit == NULL) return -EOPNOTSUPP; diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index fd95beb72f5d..1072b2c19d31 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -37,7 +37,7 @@ /* Transport protocol registration */ static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static struct phonet_protocol *phonet_proto_get(int protocol) +static struct phonet_protocol *phonet_proto_get(unsigned int protocol) { struct phonet_protocol *pp; @@ -458,7 +458,7 @@ static struct packet_type phonet_packet_type __read_mostly = { static DEFINE_MUTEX(proto_tab_lock); -int __init_or_module phonet_proto_register(int protocol, +int __init_or_module phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp) { int err = 0; @@ -481,7 +481,7 @@ int __init_or_module phonet_proto_register(int protocol, } EXPORT_SYMBOL(phonet_proto_register); -void phonet_proto_unregister(int protocol, struct phonet_protocol *pp) +void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 67dc7ce9b63a..83ddfc07e45d 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -508,8 +508,7 @@ static int tcf_csum(struct sk_buff *skb, spin_lock(&p->tcf_lock); p->tcf_tm.lastuse = jiffies; - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); action = p->tcf_action; update_flags = p->update_flags; spin_unlock(&p->tcf_lock); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8daef9632255..c2a7c20e81c1 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -209,8 +209,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, spin_lock(&ipt->tcf_lock); ipt->tcf_tm.lastuse = jiffies; - ipt->tcf_bstats.bytes += qdisc_pkt_len(skb); - ipt->tcf_bstats.packets++; + bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev worry later - danger - this API seems to have changed diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0c311be92827..d765067e99db 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -165,8 +165,7 @@ static int tcf_mirred(struct sk_buff *skb, struct tc_action *a, spin_lock(&m->tcf_lock); m->tcf_tm.lastuse = jiffies; - m->tcf_bstats.bytes += qdisc_pkt_len(skb); - m->tcf_bstats.packets++; + bstats_update(&m->tcf_bstats, skb); dev = m->tcfm_dev; if (!dev) { diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 186eb837e600..178a4bd7b7cb 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -125,8 +125,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a, egress = p->flags & TCA_NAT_FLAG_EGRESS; action = p->tcf_action; - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); spin_unlock(&p->tcf_lock); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index a0593c9640db..445bef716f77 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -187,8 +187,7 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, bad: p->tcf_qstats.overlimits++; done: - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 7ebf7439b478..e2f08b1e2e58 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -298,8 +298,7 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, spin_lock(&police->tcf_lock); - police->tcf_bstats.bytes += qdisc_pkt_len(skb); - police->tcf_bstats.packets++; + bstats_update(&police->tcf_bstats, skb); if (police->tcfp_ewma_rate && police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 97e84f3ee775..7287cff7af3e 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -42,8 +42,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result spin_lock(&d->tcf_lock); d->tcf_tm.lastuse = jiffies; - d->tcf_bstats.bytes += qdisc_pkt_len(skb); - d->tcf_bstats.packets++; + bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 66cbf4eb8855..836f5fee9e58 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -46,8 +46,7 @@ static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a, spin_lock(&d->tcf_lock); d->tcf_tm.lastuse = jiffies; - d->tcf_bstats.bytes += qdisc_pkt_len(skb); - d->tcf_bstats.packets++; + bstats_update(&d->tcf_bstats, skb); if (d->flags & SKBEDIT_F_PRIORITY) skb->priority = d->priority; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 282540778aa8..943d733409d0 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -422,10 +422,8 @@ drop: __maybe_unused } return ret; } - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; - flow->bstats.bytes += qdisc_pkt_len(skb); - flow->bstats.packets++; + qdisc_bstats_update(sch, skb); + bstats_update(&flow->bstats, skb); /* * Okay, this may seem weird. We pretend we've dropped the packet if * it goes via ATM. The reason for this is that the outer qdisc diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index eb7631590865..c80d1c210c5d 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -390,8 +390,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, cl->q); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); cbq_mark_toplevel(q, cl); if (!cl->next_alive) cbq_activate_class(cl); @@ -650,8 +649,7 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) ret = qdisc_enqueue(skb, cl->q); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); if (!cl->next_alive) cbq_activate_class(cl); return 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index aa8b5313f8cf..de55e642eafc 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -351,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - unsigned int len; int err; cl = drr_classify(skb, sch, &err); @@ -362,7 +361,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } - len = qdisc_pkt_len(skb); err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -377,10 +375,8 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl->deficit = cl->quantum; } - cl->bstats.packets++; - cl->bstats.bytes += len; - sch->bstats.packets++; - sch->bstats.bytes += len; + bstats_update(&cl->bstats, skb); + qdisc_bstats_update(sch, skb); sch->q.qlen++; return err; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 1d295d62bb5c..60f4bdd4408e 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -260,8 +260,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 069c62b7bb36..2e45791d4f6c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1599,10 +1599,8 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (cl->qdisc->q.qlen == 1) set_active(cl, qdisc_pkt_len(skb)); - cl->bstats.packets++; - cl->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + bstats_update(&cl->bstats, skb); + qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 01b519d6c52d..984c1b0c6836 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -569,15 +569,12 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } return ret; } else { - cl->bstats.packets += - skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; - cl->bstats.bytes += qdisc_pkt_len(skb); + bstats_update(&cl->bstats, skb); htb_activate(q, cl); } sch->q.qlen++; - sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; - sch->bstats.bytes += qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } @@ -648,12 +645,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, htb_add_to_wait_tree(q, cl, diff); } - /* update byte stats except for leaves which are already updated */ - if (cl->level) { - cl->bstats.bytes += bytes; - cl->bstats.packets += skb_is_gso(skb)? - skb_shinfo(skb)->gso_segs:1; - } + /* update basic stats except for leaves which are already updated */ + if (cl->level) + bstats_update(&cl->bstats, skb); + cl = cl->parent; } } diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index f10e34a68445..bce1665239b8 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -63,8 +63,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch) result = tc_classify(skb, p->filter_list, &res); - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); switch (result) { case TC_ACT_SHOT: result = TC_ACT_SHOT; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 32690deab5d0..21f13da24763 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -83,8 +83,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e5593c083a78..1c4bce863479 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -240,8 +240,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (likely(ret == NET_XMIT_SUCCESS)) { sch->q.qlen++; - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); } else if (net_xmit_drop_count(ret)) { sch->qstats.drops++; } @@ -477,8 +476,7 @@ static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) __skb_queue_after(list, skb, nskb); sch->qstats.backlog += qdisc_pkt_len(nskb); - sch->bstats.bytes += qdisc_pkt_len(nskb); - sch->bstats.packets++; + qdisc_bstats_update(sch, nskb); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index b1c95bce33ce..966158d49dd1 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -84,8 +84,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a67ba3c5a0cc..a6009c5a2c97 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -94,8 +94,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) ret = qdisc_enqueue(skb, child); if (likely(ret == NET_XMIT_SUCCESS)) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index d54ac94066c2..239ec53a634d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -403,8 +403,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) slot->allot = q->scaled_quantum; } if (++sch->q.qlen <= q->limit) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 641a30d64635..77565e721811 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -134,8 +134,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) } sch->q.qlen++; - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 106479a7c94a..af9360d1f6eb 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -83,8 +83,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) if (q->q.qlen < dev->tx_queue_len) { __skb_queue_tail(&q->q, skb); - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index afe67849269f..67e31276682a 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -563,8 +563,17 @@ rpcauth_checkverf(struct rpc_task *task, __be32 *p) return cred->cr_ops->crvalidate(task, p); } +static void rpcauth_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, data); + encode(rqstp, &xdr, obj); +} + int -rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, +rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -574,11 +583,22 @@ rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, if (cred->cr_ops->crwrap_req) return cred->cr_ops->crwrap_req(task, encode, rqstp, data, obj); /* By default, we encode the arguments normally. */ - return encode(rqstp, data, obj); + rpcauth_wrap_req_encode(encode, rqstp, data, obj); + return 0; +} + +static int +rpcauth_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, data); + return decode(rqstp, &xdr, obj); } int -rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, +rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -589,7 +609,7 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, return cred->cr_ops->crunwrap_resp(task, decode, rqstp, data, obj); /* By default, we decode the arguments normally. */ - return decode(rqstp, data, obj); + return rpcauth_unwrap_req_decode(decode, rqstp, data, obj); } int diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 3835ce35e224..45dbf1521b9a 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1231,9 +1231,19 @@ out_bad: return NULL; } +static void gss_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, p); + encode(rqstp, &xdr, obj); +} + static inline int gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; struct xdr_buf integ_buf; @@ -1249,9 +1259,7 @@ gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); if (xdr_buf_subsegment(snd_buf, &integ_buf, offset, snd_buf->len - offset)) @@ -1325,7 +1333,8 @@ out: static inline int gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; u32 offset; @@ -1342,9 +1351,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); status = alloc_enc_pages(rqstp); if (status) @@ -1394,7 +1401,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static int gss_wrap_req(struct rpc_task *task, - kxdrproc_t encode, void *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1407,12 +1414,14 @@ gss_wrap_req(struct rpc_task *task, /* The spec seems a little ambiguous here, but I think that not * wrapping context destruction requests makes the most sense. */ - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; goto out; } switch (gss_cred->gc_service) { case RPC_GSS_SVC_NONE: - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; break; case RPC_GSS_SVC_INTEGRITY: status = gss_wrap_req_integ(cred, ctx, encode, @@ -1494,10 +1503,19 @@ gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, return 0; } +static int +gss_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + return decode(rqstp, &xdr, obj); +} static int gss_unwrap_resp(struct rpc_task *task, - kxdrproc_t decode, void *rqstp, __be32 *p, void *obj) + kxdrdproc_t decode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1528,7 +1546,7 @@ gss_unwrap_resp(struct rpc_task *task, cred->cr_auth->au_rslack = cred->cr_auth->au_verfsize + (p - savedp) + (savedlen - head->iov_len); out_decode: - status = decode(rqstp, p, obj); + status = gss_unwrap_req_decode(decode, rqstp, p, obj); out: gss_put_ctx(ctx); dprintk("RPC: %5u gss_unwrap_resp returning %d\n", task->tk_pid, diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 7dcfe0cc3500..1dd1a6890007 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -59,8 +59,8 @@ int bc_send(struct rpc_rqst *req) ret = task->tk_status; rpc_put_task(task); } - return ret; dprintk("RPC: bc_send ret= %d\n", ret); + return ret; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 92ce94f5146b..57d344cf2256 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1095,7 +1095,7 @@ static void rpc_xdr_encode(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t encode; + kxdreproc_t encode; __be32 *p; dprint_status(task); @@ -1535,7 +1535,7 @@ call_decode(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t decode = task->tk_msg.rpc_proc->p_decode; + kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; __be32 *p; dprintk("RPC: %5u call_decode (status %d)\n", @@ -1776,12 +1776,11 @@ out_overflow: goto out_garbage; } -static int rpcproc_encode_null(void *rqstp, __be32 *data, void *obj) +static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { - return 0; } -static int rpcproc_decode_null(void *rqstp, __be32 *data, void *obj) +static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { return 0; } @@ -1830,23 +1829,15 @@ static void rpc_show_task(const struct rpc_clnt *clnt, const struct rpc_task *task) { const char *rpc_waitq = "none"; - char *p, action[KSYM_SYMBOL_LEN]; if (RPC_IS_QUEUED(task)) rpc_waitq = rpc_qname(task->tk_waitqueue); - /* map tk_action pointer to a function name; then trim off - * the "+0x0 [sunrpc]" */ - sprint_symbol(action, (unsigned long)task->tk_action); - p = strchr(action, '+'); - if (p) - *p = '\0'; - - printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%s q:%s\n", + printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%ps q:%s\n", task->tk_pid, task->tk_flags, task->tk_status, clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops, clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task), - action, rpc_waitq); + task->tk_action, rpc_waitq); } void rpc_show_tasks(void) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 09f01f41e55a..72bc53683965 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -474,7 +474,7 @@ static int __rpc_create_common(struct inode *dir, struct dentry *dentry, { struct inode *inode; - BUG_ON(!d_unhashed(dentry)); + d_drop(dentry); inode = rpc_get_inode(dir->i_sb, mode); if (!inode) goto out_err; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index fa6d7ca2c851..c652e4cc9fe9 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -57,10 +57,6 @@ enum { RPCBPROC_GETSTAT, }; -#define RPCB_HIGHPROC_2 RPCBPROC_CALLIT -#define RPCB_HIGHPROC_3 RPCBPROC_TADDR2UADDR -#define RPCB_HIGHPROC_4 RPCBPROC_GETSTAT - /* * r_owner * @@ -693,46 +689,37 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); - if (unlikely(p == NULL)) - return -EIO; - - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); - *p++ = htonl(rpcb->r_prot); - *p = htonl(rpcb->r_port); - - return 0; + p = xdr_reserve_space(xdr, RPCB_mappingargs_sz << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p++ = cpu_to_be32(rpcb->r_vers); + *p++ = cpu_to_be32(rpcb->r_prot); + *p = cpu_to_be32(rpcb->r_port); } -static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; unsigned long port; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; rpcb->r_port = 0; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; - port = ntohl(*p); + port = be32_to_cpup(p); dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, port); if (unlikely(port > USHRT_MAX)) @@ -742,20 +729,18 @@ static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, unsigned int *boolp) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; *boolp = 0; - if (*p) + if (*p != xdr_zero) *boolp = 1; dprintk("RPC: %5u RPCB_%s call %s\n", @@ -764,73 +749,53 @@ static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, return 0; } -static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, - const u32 maxstrlen) +static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - u32 len; __be32 *p; + u32 len; - if (unlikely(string == NULL)) - return -EIO; len = strlen(string); - if (unlikely(len > maxstrlen)) - return -EIO; - - p = xdr_reserve_space(xdr, sizeof(__be32) + len); - if (unlikely(p == NULL)) - return -EIO; + BUG_ON(len > maxstrlen); + p = xdr_reserve_space(xdr, 4 + len); xdr_encode_opaque(p, string, len); - - return 0; } -static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_netid, rpcb->r_addr); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, - sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); - if (unlikely(p == NULL)) - return -EIO; - *p++ = htonl(rpcb->r_prog); - *p = htonl(rpcb->r_vers); - - if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) - return -EIO; + p = xdr_reserve_space(xdr, (RPCB_program_sz + RPCB_version_sz) << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p = cpu_to_be32(rpcb->r_vers); - return 0; + encode_rpcb_string(xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN); + encode_rpcb_string(xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN); + encode_rpcb_string(xdr, rpcb->r_owner, RPCB_MAXOWNERLEN); } -static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; u32 len; rpcb->r_port = 0; - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); - - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) goto out_fail; - len = ntohl(*p); + len = be32_to_cpup(p); /* * If the returned universal address is a null string, @@ -845,7 +810,7 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, if (unlikely(len > RPCBIND_MAXUADDRLEN)) goto out_fail; - p = xdr_inline_decode(&xdr, len); + p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, @@ -871,8 +836,8 @@ out_fail: static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -881,8 +846,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -891,8 +856,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -904,8 +869,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -914,8 +879,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -924,8 +889,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -937,8 +902,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -947,8 +912,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -957,8 +922,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -993,19 +958,19 @@ static struct rpcb_info rpcb_next_version6[] = { static struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, - .nrprocs = RPCB_HIGHPROC_2, + .nrprocs = ARRAY_SIZE(rpcb_procedures2), .procs = rpcb_procedures2 }; static struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, - .nrprocs = RPCB_HIGHPROC_3, + .nrprocs = ARRAY_SIZE(rpcb_procedures3), .procs = rpcb_procedures3 }; static struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, - .nrprocs = RPCB_HIGHPROC_4, + .nrprocs = ARRAY_SIZE(rpcb_procedures4), .procs = rpcb_procedures4 }; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6359c42c4941..0e659c665a8d 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -488,10 +488,6 @@ svc_destroy(struct svc_serv *serv) if (svc_serv_is_pooled(serv)) svc_pool_map_put(); -#if defined(CONFIG_NFS_V4_1) - svc_sock_destroy(serv->bc_xprt); -#endif /* CONFIG_NFS_V4_1 */ - svc_unregister(serv); kfree(serv->sv_pools); kfree(serv); @@ -1147,7 +1143,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); - svc_drop(rqstp); return 0; err_short_len: @@ -1218,7 +1213,6 @@ svc_process(struct svc_rqst *rqstp) struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_serv *serv = rqstp->rq_server; u32 dir; - int error; /* * Setup response xdr_buf. @@ -1246,11 +1240,13 @@ svc_process(struct svc_rqst *rqstp) return 0; } - error = svc_process_common(rqstp, argv, resv); - if (error <= 0) - return error; - - return svc_send(rqstp); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) + return svc_send(rqstp); + else { + svc_drop(rqstp); + return 0; + } } #if defined(CONFIG_NFS_V4_1) @@ -1264,10 +1260,9 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; - int error; /* Build the svc_rqst used by the common processing routine */ - rqstp->rq_xprt = serv->bc_xprt; + rqstp->rq_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; @@ -1292,12 +1287,15 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, svc_getu32(argv); /* XID */ svc_getnl(argv); /* CALLDIR */ - error = svc_process_common(rqstp, argv, resv); - if (error <= 0) - return error; - - memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); - return bc_send(req); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) { + memcpy(&req->rq_snd_buf, &rqstp->rq_res, + sizeof(req->rq_snd_buf)); + return bc_send(req); + } else { + /* Nothing to do to drop request */ + return 0; + } } EXPORT_SYMBOL(bc_svc_process); #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 07919e16be3e..d265aa700bb3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -66,6 +66,13 @@ static void svc_sock_free(struct svc_xprt *); static struct svc_xprt *svc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); +#endif /* CONFIG_NFS_V4_1 */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key svc_key[2]; static struct lock_class_key svc_slock_key[2]; @@ -1184,6 +1191,57 @@ static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); } +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); + +static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv, + struct net *net, + struct sockaddr *sa, int salen, + int flags) +{ + return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); +} + +static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt) +{ +} + +static struct svc_xprt_ops svc_tcp_bc_ops = { + .xpo_create = svc_bc_tcp_create, + .xpo_detach = svc_bc_tcp_sock_detach, + .xpo_free = svc_bc_sock_free, + .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, +}; + +static struct svc_xprt_class svc_tcp_bc_class = { + .xcl_name = "tcp-bc", + .xcl_owner = THIS_MODULE, + .xcl_ops = &svc_tcp_bc_ops, + .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, +}; + +static void svc_init_bc_xprt_sock(void) +{ + svc_reg_xprt_class(&svc_tcp_bc_class); +} + +static void svc_cleanup_bc_xprt_sock(void) +{ + svc_unreg_xprt_class(&svc_tcp_bc_class); +} +#else /* CONFIG_NFS_V4_1 */ +static void svc_init_bc_xprt_sock(void) +{ +} + +static void svc_cleanup_bc_xprt_sock(void) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + static struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, @@ -1207,12 +1265,14 @@ void svc_init_xprt_sock(void) { svc_reg_xprt_class(&svc_tcp_class); svc_reg_xprt_class(&svc_udp_class); + svc_init_bc_xprt_sock(); } void svc_cleanup_xprt_sock(void) { svc_unreg_xprt_class(&svc_tcp_class); svc_unreg_xprt_class(&svc_udp_class); + svc_cleanup_bc_xprt_sock(); } static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1509,41 +1569,45 @@ static void svc_sock_free(struct svc_xprt *xprt) kfree(svsk); } +#if defined(CONFIG_NFS_V4_1) /* - * Create a svc_xprt. - * - * For internal use only (e.g. nfsv4.1 backchannel). - * Callers should typically use the xpo_create() method. + * Create a back channel svc_xprt which shares the fore channel socket. */ -struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, + int protocol, + struct net *net, + struct sockaddr *sin, int len, + int flags) { struct svc_sock *svsk; - struct svc_xprt *xprt = NULL; + struct svc_xprt *xprt; + + if (protocol != IPPROTO_TCP) { + printk(KERN_WARNING "svc: only TCP sockets" + " supported on shared back channel\n"); + return ERR_PTR(-EINVAL); + } - dprintk("svc: %s\n", __func__); svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); if (!svsk) - goto out; + return ERR_PTR(-ENOMEM); xprt = &svsk->sk_xprt; - if (prot == IPPROTO_TCP) - svc_xprt_init(&svc_tcp_class, xprt, serv); - else if (prot == IPPROTO_UDP) - svc_xprt_init(&svc_udp_class, xprt, serv); - else - BUG(); -out: - dprintk("svc: %s return %p\n", __func__, xprt); + svc_xprt_init(&svc_tcp_bc_class, xprt, serv); + + serv->sv_bc_xprt = xprt; + return xprt; } -EXPORT_SYMBOL_GPL(svc_sock_create); /* - * Destroy a svc_sock. + * Free a back channel svc_sock. */ -void svc_sock_destroy(struct svc_xprt *xprt) +static void svc_bc_sock_free(struct svc_xprt *xprt) { - if (xprt) + if (xprt) { + kfree(xprt->xpt_bc_sid); kfree(container_of(xprt, struct svc_sock, sk_xprt)); + } } -EXPORT_SYMBOL_GPL(svc_sock_destroy); +#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index cd9e841e7492..679cd674b81d 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -552,6 +552,74 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b } EXPORT_SYMBOL_GPL(xdr_write_pages); +static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov, + __be32 *p, unsigned int len) +{ + if (len > iov->iov_len) + len = iov->iov_len; + if (p == NULL) + p = (__be32*)iov->iov_base; + xdr->p = p; + xdr->end = (__be32*)(iov->iov_base + len); + xdr->iov = iov; + xdr->page_ptr = NULL; +} + +static int xdr_set_page_base(struct xdr_stream *xdr, + unsigned int base, unsigned int len) +{ + unsigned int pgnr; + unsigned int maxlen; + unsigned int pgoff; + unsigned int pgend; + void *kaddr; + + maxlen = xdr->buf->page_len; + if (base >= maxlen) + return -EINVAL; + maxlen -= base; + if (len > maxlen) + len = maxlen; + + base += xdr->buf->page_base; + + pgnr = base >> PAGE_SHIFT; + xdr->page_ptr = &xdr->buf->pages[pgnr]; + kaddr = page_address(*xdr->page_ptr); + + pgoff = base & ~PAGE_MASK; + xdr->p = (__be32*)(kaddr + pgoff); + + pgend = pgoff + len; + if (pgend > PAGE_SIZE) + pgend = PAGE_SIZE; + xdr->end = (__be32*)(kaddr + pgend); + xdr->iov = NULL; + return 0; +} + +static void xdr_set_next_page(struct xdr_stream *xdr) +{ + unsigned int newbase; + + newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT; + newbase -= xdr->buf->page_base; + + if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); +} + +static bool xdr_set_next_buffer(struct xdr_stream *xdr) +{ + if (xdr->page_ptr != NULL) + xdr_set_next_page(xdr); + else if (xdr->iov == xdr->buf->head) { + if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + } + return xdr->p != xdr->end; +} + /** * xdr_init_decode - Initialize an xdr_stream for decoding data. * @xdr: pointer to xdr_stream struct @@ -560,41 +628,67 @@ EXPORT_SYMBOL_GPL(xdr_write_pages); */ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) { - struct kvec *iov = buf->head; - unsigned int len = iov->iov_len; - - if (len > buf->len) - len = buf->len; xdr->buf = buf; - xdr->iov = iov; - xdr->p = p; - xdr->end = (__be32 *)((char *)iov->iov_base + len); + xdr->scratch.iov_base = NULL; + xdr->scratch.iov_len = 0; + if (buf->head[0].iov_len != 0) + xdr_set_iov(xdr, buf->head, p, buf->len); + else if (buf->page_len != 0) + xdr_set_page_base(xdr, 0, buf->len); } EXPORT_SYMBOL_GPL(xdr_init_decode); -/** - * xdr_inline_peek - Allow read-ahead in the XDR data stream - * @xdr: pointer to xdr_stream struct - * @nbytes: number of bytes of data to decode - * - * Check if the input buffer is long enough to enable us to decode - * 'nbytes' more bytes of data starting at the current position. - * If so return the current pointer without updating the current - * pointer position. - */ -__be32 * xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes) +static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { __be32 *p = xdr->p; __be32 *q = p + XDR_QUADLEN(nbytes); if (unlikely(q > xdr->end || q < p)) return NULL; + xdr->p = q; return p; } -EXPORT_SYMBOL_GPL(xdr_inline_peek); /** - * xdr_inline_decode - Retrieve non-page XDR data to decode + * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data. + * @xdr: pointer to xdr_stream struct + * @buf: pointer to an empty buffer + * @buflen: size of 'buf' + * + * The scratch buffer is used when decoding from an array of pages. + * If an xdr_inline_decode() call spans across page boundaries, then + * we copy the data into the scratch buffer in order to allow linear + * access. + */ +void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen) +{ + xdr->scratch.iov_base = buf; + xdr->scratch.iov_len = buflen; +} +EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer); + +static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p; + void *cpdest = xdr->scratch.iov_base; + size_t cplen = (char *)xdr->end - (char *)xdr->p; + + if (nbytes > xdr->scratch.iov_len) + return NULL; + memcpy(cpdest, xdr->p, cplen); + cpdest += cplen; + nbytes -= cplen; + if (!xdr_set_next_buffer(xdr)) + return NULL; + p = __xdr_inline_decode(xdr, nbytes); + if (p == NULL) + return NULL; + memcpy(cpdest, p, nbytes); + return xdr->scratch.iov_base; +} + +/** + * xdr_inline_decode - Retrieve XDR data to decode * @xdr: pointer to xdr_stream struct * @nbytes: number of bytes of data to decode * @@ -605,13 +699,16 @@ EXPORT_SYMBOL_GPL(xdr_inline_peek); */ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { - __be32 *p = xdr->p; - __be32 *q = p + XDR_QUADLEN(nbytes); + __be32 *p; - if (unlikely(q > xdr->end || q < p)) + if (nbytes == 0) + return xdr->p; + if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr)) return NULL; - xdr->p = q; - return p; + p = __xdr_inline_decode(xdr, nbytes); + if (p != NULL) + return p; + return xdr_copy_to_scratch(xdr, nbytes); } EXPORT_SYMBOL_GPL(xdr_inline_decode); @@ -671,16 +768,12 @@ EXPORT_SYMBOL_GPL(xdr_read_pages); */ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) { - char * kaddr = page_address(xdr->buf->pages[0]); xdr_read_pages(xdr, len); /* * Position current pointer at beginning of tail, and * set remaining message length. */ - if (len > PAGE_CACHE_SIZE - xdr->buf->page_base) - len = PAGE_CACHE_SIZE - xdr->buf->page_base; - xdr->p = (__be32 *)(kaddr + xdr->buf->page_base); - xdr->end = (__be32 *)((char *)xdr->p + len); + xdr_set_page_base(xdr, 0, len); } EXPORT_SYMBOL_GPL(xdr_enter_page); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8eb889510916..d5e1e0b08890 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -26,6 +26,7 @@ #include <net/sock.h> #include <net/xfrm.h> #include <net/netlink.h> +#include <net/ah.h> #include <asm/uaccess.h> #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include <linux/in6.h> @@ -302,7 +303,8 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props, algo = xfrm_aalg_get_byname(ualg->alg_name, 1); if (!algo) return -ENOSYS; - if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) + if ((ualg->alg_trunc_len / 8) > MAX_AH_AUTH_LEN || + ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) return -EINVAL; *props = algo->desc.sadb_alg_id; @@ -2187,7 +2189,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) && - (nlh->nlmsg_flags & NLM_F_DUMP)) { + (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { if (link->dump == NULL) return -EINVAL; |